Reverse-engineering an electromechanical Central Air Data Computer

Determining the airspeed and altitude of a fighter plane is harder than you'd expect. At slower speeds, pressure measurements can give the altitude, air speed, and other "air data". But as planes approach the speed of sound, complicated equations are needed to accurately compute these values. The Bendix Central Air Data Computer (CADC) solved this problem for military planes such as the F-101 and the F-111 fighters, and the B-58 bomber.1 This electromechanical marvel was crammed full of 1955 technology: gears, cams, synchros, and magnetic amplifiers. In this blog post I look inside the CADC, describe the calculations it performed, and explain how it performed these calculations mechanically.

The Bendix MG-1A Central Air Data Computer with the case removed, showing the complex mechanisms inside. Click this image (or any other) for a larger version.

This analog computer performs calculations using rotating shafts and gears, where the angle of rotation indicates a numeric value. Differential gears perform addition and subtraction, while cams implement functions. The CADC is electromechanical, with magnetic amplifiers providing feedback signals and three-phase synchros providing electrical outputs. It is said to contain 46 synchros, 511 gears, 820 ball bearings, and a total of 2,781 major parts. The photo below shows a closeup of the gears.

A closeup of the complex gears inside the CADC,

What it does

For over a century, aircraft have determined airspeed from air pressure. A port in the side of the plane provides the static air pressure,2 which is the air pressure outside the aircraft. A pitot tube points forward and receives the "total" air pressure, a higher pressure due to the speed of the airplane forcing air into the tube. (In the photo below, you can see the long pitot tube sticking out from the nose of a F-101.) The airspeed can be determined from the ratio of these two pressures, while the altitude can be determined from the static pressure.

The F-101 "Voodoo", USAF photo.

But as you approach the speed of sound, the fluid dynamics of air change and the calculations become very complicated. With the development of supersonic fighter planes in the 1950s, simple mechanical instruments were no longer sufficient. Instead, an analog computer to calculate the "air data" (airspeed, altitude, and so forth) from the pressure measurements. One option would be for each subsystem (instruments, weapons control, engine control, etc) to compute the air data separately. However, it was more efficient to have one central system perform the computation and provide the data electrically to all the subsystems that need it. This system was called a Central Air Data Computer or CADC.

The Bendix CADC has two pneumatic inputs through tubes: the static pressure3 and the total pressure. It also receives the total temperature from a platinum temperature probe. From these, it computes many outputs: true air speed, Mach number, log static pressure, differential pressure, air density, air density × the speed of sound, total temperature, and log true free air temperature.

The CADC implemented a surprisingly complex set of functions derived from fluid dynamics equations describing the behavior of air at various speeds and conditions. First, the Mach number is computed from the ratio of total pressure to static pressure. Different equations are required for subsonic and supersonic flight. Although this equation looks difficult to solve mathematically, fundamentally M is a function of one variable ($P_t / P_s$), and this function is encoded in the shape of a cam. (You are not expected to understand the equations below. They are just to illustrate the complexity of what the CADC does.)

\[M<1:\] \[~~~\frac{P_t}{P_s} = ( 1+.2M^2)^{3.5}\]

\[M > 1:\]

\[~~~\frac{P_t}{P_s} = \frac{166.9215M^7}{( 7M^2-1)^{2.5}}\]

Next, the temperature is determined from the Mach number and the temperature indicated by a temperature probe.

\[T = \frac{T_{ti}}{1 + .2 M^2} \]

The indicated airspeed and other outputs are computed in turn, but I won't go through all the equations. Although these equations may seem ad hoc, they can be derived from fluid dynamics principles. These equations were standardized in the 1950s by various government organizations including the National Bureau of Standards and NACA (the precursor of NASA). While the equations are complicated, they can be computed with mechanical means.

How it is implemented

The Air Data Computer is an analog computer that determines various functions of the static pressure, total pressure and temperature. An analog computer was selected for this application because the inputs are analog and the outputs are analog, so it seemed simplest to keep the computations analog and avoid conversions. The computer performs its computations mechanically, using the rotation angle of shafts to indicate values. For the most part, values are represented logarithmically, which allows multiplication and division to be implemented by adding and subtracting rotations. A differential gear mechanism provides the underlying implementation of addition and subtraction. Specially-shaped cams provide the logarithmic and exponential conversions as necessary. Other cams implement various arbitrary functions.

The diagram below, from patent 2,969,210, shows some of the operations. At the left, transducers convert the pressure and temperature inputs from physical quantities into shaft rotations, applying a log function in the process. Subtracting the two pressures with a differential gear mechanism (X-in-circle symbol) produces the log of the pressure ratios. Cam "CCD 12" generates the Mach number from this log pressure ratio, still expressed as a shaft rotation. A synchro transmitter converts the shaft rotation into a three-phase electrical output from the CADC. The remainder of the diagram uses more cams and differentials to produce the other outputs. Next, I'll discuss how these steps are implemented.

A diagram showing how values are computed by the CADC. Source: Patent 2969910.

The pressure transducer

The CADC receives the static and total pressure through tubes connected to the front of the CADC. (At the lower right, one of these tubes is visible.) Inside the CADC, two pressure transducers convert the pressures into rotational signals. The pressure transducers are the black domed cylinders at the top of the CADC.

The pressure transducers are the two black domes at the top. The circuit boards next to each pressure transducer are the amplifiers. The yellowish transformer-like devices with three windings are the magnetic amplifiers.

Each pressure transducer contains a pair of bellows that expand and contract as the applied pressure changes. They are connected to opposite sides of a shaft so they cause small rotations of the shaft.

Inside the pressure transducer. The two disc-shaped bellows are connected to opposite sides of a shaft so the shaft rotates as the bellows expand or contract.

The pressure transducer has a tricky job: it must measure tiny pressure changes, but it must also provide a rotational signal that has enough torque to rotate all the gears in the CADC. To accomplish this, the pressure transducer uses a servo loop. The bellows produce a small shaft motion that is detected by an inductive pickup. This signal is amplified and drives a motor with enough power to move all the gears. The motor is also geared to counteract the movement of the bellows. This creates a feedback loop so the motor's rotation tracks the air pressure, but provides much more force. A cam is used so the output corresponds to the log of the input pressure.

This diagram shows the structure of the transducer. From "Air Data Computer Mechanization."

Each transducer signal is amplified by three circuit boards centered around a magnetic amplifier, a transformer-like amplifier circuit that was popular before high-power transistors came along. The photo below shows how the amplifier boards are packed next to the transducers. The boards are complex, filled with resistors, capacitors, germanium transistors, diodes, relays, and other components.

This end-on view of the CADC shows the pressure transducers, the black cylinders. Next to each pressure transducer is a complex amplifier consisting of multiple boards with transistors and other components. The magnetic amplifiers are the yellowish transformer-like components.

Temperature

The external temperature is an important input to the CADC since it affects the air density. A platinum temperature probe provides a resistance4 that varies with temperature. The resistance is converted to rotation by an electromechanical transducer mechanism. Like the pressure transducer, the temperature transducer uses a servo mechanism with an amplifier and feedback loop. For the temperature transducer, though, the feedback signal is generated by a resistance bridge using a potentiometer driven by the motor. By balancing the potentiometer's resistance with the platinum probe's resistance, a shaft rotation is produced that corresponds to the temperature. The cam is configured to produce the log of the temperature as output.

This diagram shows the structure of the temperature transducer. From "Air Data Computer Mechanization."

The temperature transducer section of the CADC is shown below. The feedback potentiometer is the red cylinder at the lower right. Above it is a metal-plate adjustment cam, which will be discussed below. The CADC is designed in a somewhat modular way, with the temperature section implemented as a removable wedge-shaped unit, the lower two-thirds of the photo. The temperature transducer, like the pressure transducer, has three boards of electronics to implement the feedback amplifier and drive the motor.

The temperature transducer section of the CADC.

The differential

The differential gear assembly is a key component of the CADC's calculations, as it performs addition or subtraction of rotations: the rotation of the output shaft is the sum or difference of the input shafts, depending on the direction of rotation.5 When rotations are expressed logarithmically, addition and subtraction correspond to multiplication and division. This differential is constructed as a spur-gear differential. It has inputs at the top and bottom, while the body of the differential rotates to produce the sum. The two visible gears in the body mesh with the internal input gears, which are not visible. The output is driven by the body through a concentric shaft.

A closeup of a differential mechanism.

The cams

The CADC uses cams to implement various functions. Most importantly, cams perform logarithms and exponentials. Cams also implement more complex functions of one variable such as ${M}/{\sqrt{1 + .2 M^2}}$. The photo below shows a cam (I think exponential) with the follower arm in front. As the cam rotates, the follower moves in and out according to the cam's radius, providing the function value.

A cam inside the CADC implements a function.

The cams are combined with a differential in a clever way to make the cam shape more practical, as shown below.6 The input (23) drives the cam (30) and the differential (37-41). The follower (32) tracks the cam and provides a second input (35) to the differential. The sum from the differential produces the output (26).

This diagram, from Patent 2969910, shows how the cam and follower are connected to a differential.

The warped plate cam

Some functions are implemented by warped metal plates acting as cams. This type of cam can be adjusted by turning the 20 setscrews to change the shape of the plate. A follower rides on the surface of the cam and provides an input to a differential underneath the plate. The differential adds the cam position to the input rotation, producing a modified rotation, as with the solid cam. The pressure transducer, for instance, uses a cam to generate the desired output function from the bellows deflection. By using a cam, the bellows can be designed for good performance without worrying about its deflection function.

A closeup of a warped-plate cam.

The synchro outputs

Most of the outputs from the CADC are synchro signals.7 A synchro is an interesting device that can transmit a rotational position electrically over three wires. In appearance, a synchro is similar to an electric motor, but its internal construction is different, as shown below. In use, two synchros have their stator windings connected together, while the rotor windings are driven with AC. Rotating the shaft of one synchro causes the other to rotate to the same position. I have a video showing synchros in action here.

Cross-section diagram of a synchro showing the rotor and stators.

Internally, a synchro has a moving rotor winding and three fixed stator windings. When AC is applied to the rotor, voltages are developed on the stator windings depending on the position of the rotor. These voltages produce a torque that rotates the synchros to the same position. In other words, the rotor receives power (26 V, 400 Hz in this case), while the three stator wires transmit the position. The diagram below shows how a synchro is represented schematically, with rotor and stator coils.

The schematic symbol for a synchro.

Before digital systems, synchros were very popular for transmitting signals electrically through an aircraft. For instance, a synchro could transmit an altitude reading to a cockpit display or a targeting system. For the CADC, most of the outputs are synchro signals, which convert the rotational values of the CADC to electrical signals. The three stator windings from the synchro inside the CADC are wired to an external synchro that receives the rotation. For improved resolution, many of these outputs use two synchros: a coarse synchro and a fine synchro. The two synchros are typically geared in an 11:1 ratio, so the fine synchro rotates 11 times as fast as the coarse synchro. Over the output range, the coarse synchro may turn 180°, providing the approximate output, while the fine synchro spins multiple times to provide more accuracy.

The front of the CADC has multiple output synchros with anti-backlash springs.

The air data system

The CADC is one of several units in the system, as shown in the block diagram below.8 The outputs of the CADC go to another box called the Air Data Converter, which is the interface between the CADC and the aircraft systems that require the air data values: fire control, engine control, navigation system, cockpit display instruments, and so forth. The motivation for this separation is that different aircraft types have different requirements for signals: the CADC remains the same and only the converter needed to be customized. Some aircraft required "up to 43 outputs including potentiometers, synchros, digitizers, and switches."

This block diagram shows how the Air Data Computer integrates with sensors and other systems. The unlabeled box on the right is the converter. From MIL-C-25653C(USAF).

The CADC was also connected to a cylindrical unit called the "Static pressure and angle of attack compensator." This unit compensates for errors in static pressure measurements due to the shape of the aircraft by producing the "position error correction". Since the compensation factor depended on the specific aircraft type, the compensation was computed outside the Central Air Data Computer, again keeping the CADC generic. This correction factor depends on the Mach number and angle of attack, and was implemented as a three-dimensional cam. The cam's shape (and thus the correction function) was determined empirically, rather than from fundamental equations.

The CADC was wired to other components through five electrical connectors as shown in the photo below.9 At the bottom are the pneumatic connections for static pressure and total pressure. At the upper right is a small elapsed time meter.

The front of the CADC has many mil-spec round connectors.

Conclusions

The Bendix MG-1A Central Air Data Computer is an amazingly complex piece of electromechanical hardware. It's hard to believe that this system of tiny gears was able to perform reliable computations in the hostile environment of a jet plane, subjected to jolts, accelerations, and vibrations. But it was the best way to solve the problem at the time,10 showing the ingenuity of the engineers who developed it.

The CADC inside its case. From the outside, its mechanical marvels are hidden.

I plan to continue reverse-engineering the Bendix CADC and hope to get it operational,11 so follow me on Twitter @kenshirriff or RSS for updates. I've also started experimenting with Mastodon recently as @oldbytes.space@kenshirriff. Until then, you can check out CuriousMarc's video below to see more of the CADC. Thanks to Joe for providing the CADC. Thanks to Nancy Chen for obtaining a hard-to-find document for me.

Notes and references

1. I haven't found a definitive list of which planes used this CADC. Based on various sources, I believe it was used in the F-86, F-101, F-104, F-105, F-106, and F-111, and the B-58 bomber. ↩

2. The static air pressure can also be provided by holes in the side of the pitot tube. I couldn't find information indicating exactly how these planes received static pressure. ↩

3. The CADC also has an input for the "position error correction". This provides a correction factor because the measured static pressure may not exactly match the real static pressure. The problem is that the static pressure is measured from a port on the aircraft. Distortions in the airflow may cause errors in this measurement. A separate box, the "compensator", determines the correction factor based on the angle of attack. ↩

4. The platinum temperature probe is type MA-1, defined by specification MIL-P-25726. It apparently has a resistance of 50 Ω at 0 °C. ↩

5. Strictly speaking, the output of the differential is the sum of the inputs divided by two. I'm ignoring the factor of 2 because the gear ratios can easily cancel it out. ↩

6. Cams are extensively used in the CADC to implement functions of one variable, including exponentiation and logarithms. The straightforward way to use a cam is to read the value of the function off the cam directly, with the radius of the cam at each angle representing the value. This approach encounters a problem when the cam wraps around, since the cam's profile will suddenly jump from one value to another. This poses a problem for the cam follower, which may get stuck on this part of the cam unless there is a smooth transition zone. Another problem is that the cam may have a large range between the minimum and maximum outputs. (Consider an exponential output, for instance.) Scaling the cam to a reasonable size will lose accuracy in the small values. The cam will also have a steep slope for the large values, making it harder to track the profile.

   The solution is to record the difference between the input and the output in the cam. A differential then adds the input value to the cam value to produce the desired value. The clever part is that by scaling the input so it matches the output at the start and end of the range, the difference function drops to zero at both ends. Thus, the cam profile matches when the angle wraps around, avoiding the sudden transition. Moreover, the difference between the input and the output is much smaller than the raw output, so the cam values can be more accurate. (This only works because the output functions are increasing functions; this approach wouldn't work for a sine function, for instance.)

   

   This diagram, from Patent 2969910, shows how a cam implements a complex function.

   The diagram above shows how this works in practice. The input is \(log~ dP/P_s\) and the output is \(log~M / \sqrt{1+.2KM^2}\). (This is a function of Mach number used for the temperature computation; K is 1.) The small humped curve at the bottom is the cam correction. Although the input and output functions cover a wide range, the difference that is encoded in the cam is much smaller and drops to zero at both ends. ↩

7. The US Navy made heavy use of synchros for transmitting signals throughout ships. The synchro diagrams are from two US Navy publications: US Navy Synchros (1944) and Principles of Synchros, Servos, and Gyros (2012). These are good documents if you want to learn more about synchros. The diagram below shows how synchros could be used on a ship.

   

   A Navy diagram illustrating synchros controlling a gun on a battleship.

    ↩

8. To summarize the symbols, the outputs are: log T_FAT: true free air temperature (the ambient temperature without friction and compression); log P_s: static pressure; M: Mach number; Q_c: differential pressure; ρ: air density; ρa: air density times the speed of sound; V_t: true airspeed. T_t: total temperature (higher due to compression of the air). Inputs are: T_T: total temperature (higher due to compression of the air). P_ti: indicated total pressure (higher due to velocity); P_si: indicated static pressure; log P_si/P_s: the position error correction from the compensator. The compensator uses input α_i: angle of attack; and produces α_T: true angle of attack; a_T: speed of sound. ↩

9. The electrical connectors on the CADC have the following functions: J614: outputs to the converter, J601: outputs to the converter, J603: AC power (115 V, 400 Hz), J602: to/from the compensator, and J604: input from the temperature probe. ↩

10. An interesting manual way to calculate air data was with a circular slide rule, designed for navigation and air data calculation. It gave answers for various combinations of pressure, temperature, Mach number, true airspeed, and so forth. See the MB-2A Air Navigation Computer instructions for details. Also see patent 2528518. I'll also point out that from the late 1800s through the 1940s and on, the term "computer" was used for any sort of device that computed a value, from an adding machine to a slide rule (or even a person). The meaning is very different from the modern usage of "computer". ↩

11. It was very difficult to find information about the CADC. The official military specification is MIL-C-25653C(USAF). After searching everywhere, I was finally able to get a copy from the Technical Reports & Standards unit of the Library of Congress. The other useful document was in an obscure conference proceedings from 1958: "Air Data Computer Mechanization" (Hazen), Symposium on the USAF Flight Control Data Integration Program, Wright Air Dev Center US Air Force, Feb 3-4, 1958, pp 171-194. ↩

Reverse-engineering an airspeed/Mach indicator from 1977

How does a vintage airspeed indicator work? CuriousMarc picked one up for a project, but it didn't have any documentation, so I reverse-engineered it. This indicator was used in the cockpit panel for business jets such as the Gulfstream G-III, Cessna Citation, and Bombardier Challenger CL600. It was probably manufactured in 1977 based on the dates on its transistors.

You might expect that the indicators on an aircraft control panel are simple dials. But behind this dial is a large, 2.8-pound box with a complex system of motors, gears, and feedback potentiometers, controlled by two boards of electronics. But for all this complexity, the indicator doesn't have any smarts: the pointers just indicate voltages fed into it from an air data computer. This is a quick blog post to summarize what I found.

Front view of the indicator.

The dial has two rotating pointers: the white pointer indicates airspeed in knots while the striped pointer indicates the maximum airspeed (which varies depending on altitude). The "digital" indicator at the top shows Mach number from 0.10 to 0.99, implemented with rotating digit wheels. When the unit is operating, the OFF indicator flag switches to black. The flag switches to a bright V_MO warning if the pilot exceeds the maximum airspeed.1 On the rim of the dial, two small markers called "bugs" can be manually moved to indicate critical speeds such as takeoff speed.

In use, the indicator is connected to a Sperry air data computer and receives voltage signals to control the dial positions.3 The air data computer measures the static and dynamic air pressure from pitot tubes and determines the airspeed, Mach number, altitude, and other parameters. (These calculations become nontrival near Mach 1 as air compresses and the fluid dynamics change.) Since we didn't have the air data computer or its specifications, I needed to figure out the connections from the computer to the display.

With the unit's cover removed, you can see the internal mechanisms and circuitry. Each of the three indicators is controlled by a small DC motor with a potentiometer providing feedback. To the right, two circuit boards provide the electronics to drive the indicators.4 At the upper right, the black blob is a 26-volt 400-Hertz transformer to power the unit. Some power supply components are in front of it. Below the transformer is an orangish flexible printed-circuit board, which seems advanced for the timeframe. This flexible ribbon connects the transformer, the external connector, and the printed-circuit board sockets, providing the backplane for the system.

A side view of the unit shows the gears to control the indicators.

The diagram below shows the principle behind the servo mechanism that controls each indicator. The goal is to rotate the indicator to a position corresponding to the input voltage. A feedback loop is used to achieve this. The potentiometer provides a voltage proportional to its rotation. The input voltage and the feedback voltage are inputs to an op amp, which generates an error signal based on the difference between the inputs. The error signal rotates the DC motor in the appropriate direction until the potentiometer voltage matches the input voltage. Because the indicator and the potentiometer are geared together, the indicator will be in the correct position. As the input voltage changes, the system will continuously track the changes and keep the indicator updated.

A diagram illustrating the servo feedback loop.

Because the DC motor spins much faster than the dial moves, reduction gears slow the rotation. The photo below shows the gear train in the unit. A potentiometer is at the upper-right with three wires attached.

A closeup of the gear train. A potentiometer is on the right.

The Mach number has additional gearing to rotate the numbered wheels. When the low-digit wheel cycles around, it advances the high-digit wheel, similar to an odometer.

The mechanism to rotate the digit wheels for the Mach number.

Fault checking

One interesting feature of the indicator unit is that it implements fault checking to alert the pilot if something goes wrong. The front panel has a three-position flag. By default it's in the OFF position. Powering the coil in one direction rotates the flag to the blank side. Powering the coil in the other direction rotates the flag to the "V_MO" position which indicates that the pilot has exceeded the maximum operating speed.

I figured that powering up the unit would move the flag out of the OFF position, but it's more complicated than that. First, the unit checks that the air data computer is providing a suitable reference voltage. Second, the unit verifies that the motor voltages for the two needles are within limits; this ensures that the servo loop is operating successfully. Third, the unit checks that signals are received on status pins K and L. The unit only moves out of the OFF state if all these conditions are satisfied.5 Thus, if the unit receives bad signals or is malfunctioning, the pilot will be alerted by the OFF indicator, rather than trusting the faulty display.

The circuitry

The unit is powered by 26 volts, 400 Hz, a standard voltage for aviation. A small transformer provides multiple outputs for the various internal voltages. The unit has four power supplies: three on the first board and one on the back wall of the unit. One power supply is for the status indicator, one is for the op amps, one powers the 41.7V motors, and the fourth provides other power.

One subtlety is how the feedback potentiometers are powered. The servo loop compares the potentiometer voltage with the input voltage. But this only works if the potentiometer and the input voltage are using the same reference. One solution would be for the indicator unit and the air data computer to contain matching precision voltage regulators. Instead, the system uses a simpler, more reliable approach: the air data computer provides a reference voltage that the indicator unit uses to power the potentiometers.6 With this approach, the air data computer's voltage reference can fluctuate and the indicator will still reach the right position. (In other words, a 5V input with a 10V reference and a 6V input with a 12V reference are both 50%.)

The diagram below shows the board with the servo circuitry. The board uses dual op-amp integrated circuits, packaged in 10-pin metal cans that protected against interference.7 The ICs and some of the other components have obscure military part numbers; I don't know if this unit was built for military use or if military-grade parts were used for reliability.

The servo board is full of transistors, resistors, capacitors, diodes, and op-amp integrated circuits.

The circuitry in the lower-left corner handles the reference voltage from the air data computer. The board buffers this voltage with an op amp to power the three feedback potentiometers. The op amp also ensures that the reference voltage is at least 10 volts. If not, the indicator unit shows the "OFF" flag to alert the pilot.

The schematic below shows one of the servo circuits; the three circuits are roughly the same. The heart of the circuit is the error op amp in the center. It compares the voltage from the potentiometer with the input voltage and generates an error output that moves the motor appropriately. A positive error output will turn on the upper transistor, driving the motor with a positive voltage. Conversely, a negative error output will turn on the lower transistor, driving the motor with a negative voltage. The motor drive circuit has clamp diodes to limit the transistor base voltages.

Schematic of one of the servo circuits.

The op amp also receives a feedback signal from the motor output. I don't entirely understand this signal, which goes through a filter circuit with resistors, diodes, and a capacitor. I think it dampens the motor signal so the motor doesn't overshoot the desired position. I think it also keeps the transistor drive signal biased relative to the emitter voltage (i.e. the motor output).

On the input side, the potentiometer voltage goes through an op amp follower buffer, which simply outputs its input voltage. This may seem pointless, but the op amp provides a high-impedance input so the potentiometer's voltage doesn't get distorted.

The external input voltage goes through a resistor/capacitor circuit to scale it and filter out noise. Curiously, the circuit board was modified by cutting a trace and adding a resistor and capacitor to change the input circuit for one of the inputs. In the photo below, you can see the added resistor and capacitor; the cut trace is just to the right of the capacitor. I don't know if this modification changed the scale factor or if it filtered out noise. A label on the box says that Honeywell performed a modification on November 8, 1991, which presumably was this circuit.

A closeup of the circuit board showing the modification.

The second board implements three power supplies as well as the circuitry for the OFF/V_MO flag. The power supplies are simple and unregulated, just diode bridges to convert AC to DC, along with filter capacitors. Most of the circuitry on the board controls the status flag. Two dual op amps check the motor voltages against upper and lower limits to ensure that the motors are tracking the inputs. These outputs, along with other logic status signals, are combined with diode-transistor logic to determine the flag status. Driver transistors provide +18 or -18 volts to the flag's coil to drive it to the desired position.

This board has power supply circuitry and the control circuitry for the indicator flag.

Conclusions

After reverse-engineering the pinout, I connected the airspeed indicator to a stack of power supplies and succeeded in getting the indicators to operate (video). This unit is much more complex than I expected for a simple display, with servoed motors controlled by two boards of electronics. Air safety regulations probably account for much of the complexity, ensuring that the display provides the pilot with accurate information. For all that complexity, the unit is essentially a voltmeter, indicating three voltages on its display. This airspeed indicator is a bit different from most of the hardware I examine, but hopefully you found this look at its internal circuitry interesting.

With the case removed, the internal circuitry is visible.

You can follow me on Twitter @kenshirriff or rss. I've also started experimenting with mastodon recently as @oldbytes.space@kenshirriff.

Notes and references

1. Since the unit has airspeed and maximum airspeed indicators, you might expect it to display the maximum airspeed warning flag based on the two speed inputs. Instead, the flag is controlled by input pin "L". In other words, the air data computer, not the indicator unit, determines when the maximum airspeed is exceeded. ↩

2. This unit is a "Mach Airspeed Indicator", 4018366, apparently also called the SI-225,2

   

   Product label with part number 4018366-901.

   Note that the label says Sperry. In 1986, Sperry attempted to buy Honeywell but instead Burroughs made a hostile takeover bid. The merger of Sperry and Burroughs formed Unisys. A couple of months after the merger, the Sperry Aerospace Group was sold to Honeywell for $1.025 billion. Thus, the indicator became a Honeywell product. This corporate history explains why the unit has a Honeywell product support sticker.

   

   Labels on top of the unit indicate that it worked with the Sperry 4013242 and 4013244 air data computers. These became the Honeywell AZ-242 and AZ-244.

    ↩

3. The connector is a 32-pin MIL Spec round connector. Most of the 32 pins are unused. The connector has complex keying with 5 slots. I assume the keying is specific to this indicator, so the wrong indicator doesn't get connected.

   

   A closeup of the 32-pin connector, probably a MIL Spec 18-32.

   For reference, here is the pinout of the unit. Since this is based on reverse engineering, I don't guarantee it 100%. Don't use this for flight!

   Pin	Use
   A	5V illumination
   B	Chassis ground
   C	AC ground
   E	26V 400 Hz
   F	26V 400 Hz
   K	Enable
   L	Speed ok
   M	Signal ground
   N	Ref. voltage
   P	Vmax control voltage
   R	Airspeed control voltage
   S	Mach control voltage
   V	Chassis ground

   Pins D, G, H, J, T, U, W, X, Y, Z, a, b, c, d, e, f, g, h, and j are unused. ↩

4. The chassis has an empty slot for a third circuit board. My guess is that this chassis was used for multiple types of indicators and others required a third board. ↩

5. If the L pin goes low, the indicator will move to the V_MO position. ↩

6. My hypothesis is that the correct reference voltage is 11.7 volts. This yields a scale factor of 1 volt equals 50 knots. It also matches up the display's change in scale at 250 knots with the measured scale change. ↩

7. The meter uses three different integrated circuits in 10-pin metal cans with mysterious military markings: "FHL 24988", "JM38510/10102BIC 27014", and "SL14040". These appear to all be equivalent to uA747 dual op amps. (Note that JM38510 is not a part number; it is a general military specification for integrated circuits. The number after it is the relevant part number.) ↩

The unusual bootstrap drivers inside the 8086 microprocessor chip

The 8086 microprocessor is one of the most important chips ever created; it started the x86 architecture that still dominates desktop and server computing today. I've been reverse-engineering its circuitry by studying its silicon die. One of the most unusual circuits I found is a "bootstrap driver", a way to boost internal signals to improve performance.1

The bootstrap driver circuit from the 8086 processor.

This circuit consists of just three NMOS transistors, amplifying an input signal to produce an output signal, but it doesn't resemble typical NMOS logic circuits and puzzled me for a long time. Eventually, I stumbled across an explanation:2 the "bootstrap driver" uses the transistor's capacitance to boost its voltage. It produces control pulses with higher current and higher voltage than otherwise possible, increasing performance. In this blog post, I'll attempt to explain how the tricky bootstrap driver circuit works.

A die photo of the 8086 processor. The metal layer on top of the silicon is visible. Around the edge of the chip, bond wires provide connections to the chip's external pins. Click this image (or any other) for a larger version.

NMOS transistors

The 8086 is built from MOS transistors (MOSFETs), specifically NMOS transistors. Understanding the bootstrap driver requires some understanding of these transistors. If you're familiar with MOSFETs as components, they have source and drain pins and current flows from the drain to the source, controlled by the gate pin. Most of the time I treat an NMOS transistor as a digital switch between the drain and the source: a 1 input turns the transistor on, closing the switch, while a 0 turns the transistor off. However, for the bootstrap driver, we must consider the MOSFET in a bit more detail.

A MOSFET switches current from the drain to the source, under control of the gate.

The important aspect of the gate is the difference between the gate voltage and the (typically lower) source voltage; this is denoted as V_gs. Without going into semiconductor physics, a slightly more accurate model is that the transistor turns on when the voltage between the gate and the source exceeds the fixed threshold voltage, V_th. This creates a conducting channel between the transistor's source and drain. Thus, if V_gs > V_th, the transistor turns on and current flows. Otherwise, the transistor turns off and no current flows.

The voltage between the gate and the source (V_gs) controls the transistor.

The threshold voltage has an important consequence for a chip such as the 8086. The 8086, like most chips of that era, used a 5-volt power supply. The threshold voltage depends on manufacturing characteristics, but I'll use 1 volt as a typical value.3 The result is that if you put 5 volts on the drain and on the gate, the transistor can pull the source up to about 4 volts, but then V_gs falls to the threshold voltage and the transistor stops conducting. Thus, the transistor can't pull the source all the way up to the 5-volt supply, but falls short by a volt on the output. In some circumstances this is a problem, and this is the problem that the bootstrap driver fixes.

Due to the threshold voltage, the transistor doesn't pull the source all the way to the drain's voltage, but "loses" a volt.

If you get a transistor as a physical component, the source and drain are not interchangeable. However, in an integrated circuit, there is no difference between the source and the drain, and this will be important.4 The diagram below shows how a MOSFET is constructed on the silicon die. The source and drain consist of regions of silicon doped with impurities to change their property. Between them is a channel of undoped silicon, which normally does not conduct. Above the channel is the gate, made of a special type of silicon called polysilicon. The voltage on the gate controls the conductivity of the channel. A very thin insulating layer separates the gate from the channel. As a side effect, the insulating layer creates some capacitance between the gate and the underlying silicon.

Diagram of an NMOS transistor in an integrated circuit.

Basic NMOS circuits

Before getting to the bootstrap driver, I'll explain how a basic inverter is implemented in an NMOS chip like the 8086. The inverter is built from two transistors: a normal transistor on the bottom, and a special load transistor on top that acts like a pull-up resistor, providing a small constant current.5 With a 1 input, the lower transistor turns on, pulling the output to ground to produce a 0 output. With a 0 input, the lower transistor turns off and the current from the upper transistor drives the output high to produce a 1 output. Thus, the circuit implements an inverter: producing a 1 when the input is 0 and vice versa.

A standard NMOS inverter is built from two transistors. The upper transistor is a "depletion load" transistor.

The disadvantage of this inverter circuit is that when it produces a 0 output, current continuously flows through the load transistor and the lower transistor to ground. This wastes power, leading to high power consumption for NMOS circuitry. (To solve this, CMOS circuitry took over in the 1980s and is used in modern microprocessors.) This also limits the current that the inverter can provide.

If a gate needs to provide a relatively large current, for instance to drive a long bus inside the chip, a more complex circuit is used, the "superbuffer". The superbuffer uses one transistor to pull the output high and a second transistor to pull the output low.6 Because only one transistor is on at a time, a high-current output can be produced without wasting power. There are two disadvantages of the superbuffer, though. First, the superbuffer requires an inverter to control the high-side transistor, so it uses considerably more space on the die. Second, the superbuffer can't pull the high output all the way up; it loses a volt due to the threshold voltage as described earlier.

Combining two output transistors with an inverter produces a higher-current output, known as a superbuffer.

The bootstrap driver

In some circumstances, you want both a high-current output, and the full output voltage. One example is connecting a register to an internal bus. Since the 8086 is a 16-bit chip, it uses 16 transistors for the bus connection. Driving 16 transistors in parallel requires a fairly high current. But the bus transistors are "pass" transistors, which lose a volt due to the threshold voltage, so you want to start with the full voltage, not already down one volt. To provide both high current and the full voltage, bootstrap drivers are used to control the buses, as well as similar tasks such as ALU control.

The concept behind the bootstrap driver is to drive the gate voltage significantly higher than 5 volts, so even after losing the threshold voltage, the transistor can produce the full 5-volt output.7 The higher voltage is generated by a charge pump, as illustrated below. Suppose you charge a capacitor with 5 volts. Now, disconnect the bottom of the capacitor from ground, and connect it to +5 volts. The capacitor is still charged with 5 volts, so now the high side is at +10 volts with respect to ground. Thus, a capacitor can be used to create a higher voltage by "pumping" the charge to a higher level.

On the left, the "flying capacitor' is charged to 5 volts. By switching the lower terminal to +5 volts, the capacitor now outputs +10 volts

The idea of the bootstrap driver is to attach a capacitor to the gate and charge it to 5 volts. Then, the low side of the capacitor is raised to 5 volts, boosting the gate side of the capacitor to 10 volts. With this high voltage on the gate, the threshold voltage is easily exceeded and the transistor can pass the full 5 volts from the drain to the source, producing a 5-volt output.

With a large voltage on the gate, the threshold voltage is exceeded and the transistor remains on until the source reaches 5 volts.

In the 8086 bootstrap driver,8 an explicit capacitor is not used.9 Instead, the transistor's inherent capacitance is sufficient. Due to the thin insulating oxide layer between the gate and the underlying silicon, the gate acts as the plate of a capacitor relative to the source and drain. This "parasitic" capacitance is usually a bad thing, but the bootstrap driver takes advantage of it.

The diagrams below show how the bootstrap driver works. Unlike an inverter, the bootstrap driver is controlled by the chip's clock, generating an output only when the clock is high. In the first diagram, we assume that the input is a 1 and the clock is low (0). Two things happen. First, the inverted clock turns on the bottom transistor, pulling the output to ground. Second, the 5V input passes through the first transistor; the left side of the transistor acts as the drain and the right side as the source. Due to the threshold voltage, a volt is "lost" so about 4 volts reaches the gate of the second transistor. Since the source and drain of the second transistor are at 0 volts, the gate capacitors are charged with 4 volts. (Recall that these are not explicit capacitors, but are parasitic capacitors.)

The first step in the operation of the bootstrap driver. The gate capacitance is charged by the input.

In the next step, the clock switches state and things become more interesting. The second transistor is on due to the voltage on the gate, so current flows from the clock to the output. In a "normal" circuit, the output would rise to 4 volts, losing a volt due to the threshold voltage of the second transistor. However, as the output voltage rises, it boosts the voltage on the gate capacitors and thus raises the gate voltage. The increased gate voltage allows the output voltage to rise above 4 volts, pushing the gate voltage even higher, until the output reaches 5 volts.10 Thus, the bootstrap driver produces a high-current output with the full 5 volts.

The second step in the operation of the bootstrap driver. As the output rises, it boosts the gate voltage even higher.

An important factor is that the first transistor now has a higher voltage on the right than on the left, so the source and drain switch roles. Since the transistor has 5 volts on the gate and on the (now) source, V_gs is 0 and current can't flow. Thus the first transistor blocks current flow from the gate, keeping the gate at its higher voltage. This is the critical role of the first transistor in the bootstrap driver, acting as a diode to block current flow out of the gate.

The diagram below shows what happens when the clock switches state again, assuming a low input. Now the first transistor's source voltage drops, making V_gs large and turning the transistor on. This allows the second transistor's gate voltage to flow out. Note that the first transistor is no longer acting as a diode, since current can flow in the "reverse" direction. The other important action in this clock phase is that the bottom transistor turns on, pulling the output low. These actions discharge the gate capacitance, preparing it for the next bootstrap cycle.

When the clock switches off, the driver is discharged, preparing it for the next cycle.

The 8086 die

Now that I've explained the theory, how do bootstrap drivers appear on the silicon die of the 8086? The diagram below shows six drivers that control the ALU operation.11 There's a lot happening in this diagram, but I'll try to explain what's going on. For this photo, I removed the metal layer with acid to reveal the silicon underneath; the yellow lines show where the metal wiring was. The large pinkish regions are doped silicon, while the gray speckled lines are polysilicon on top. The greenish and reddish regions are undoped silicon, which doesn't conduct and can be ignored. A transistor is formed where a polysilicon line crosses silicon, with the source and drain on opposite sides. Note that some transistors share the source or drain region with a neighboring transistor, saving space. The circles are vias, connections between the metal and a lower layer.

Six bootstrap drivers as they appear on the chip.

The drivers start with six inputs at the right. Each input goes through a "diode" transistor with the gate tied to +5V. I've labeled two of these transistors and the other four are scattered around the image. Next, each signal goes to the gate of one of the drive transistors. These six large transistors pass the clock to the output when turned on. Note that the clock signal flows through large silicon regions, rather than "wires". Finally, each output has a pull-down transistor on the left, connecting it to ground (another large silicon region) under control of the inverted clock. The drive transistors are much larger than the other transistors, so they can provide much more current. Their size also provides the gate capacitance necessary for the operation of the bootstrap driver.

Although the six drivers in this diagram are electrically identical, each one has a different layout instead of repeating the same layout six times. This demonstrates how the layout has been optimized, moving transistors around to use space most efficiently.

In total, the 8086 has 81 bootstrap drivers, mostly controlling the register file and the ALU (arithmetic-logic unit). The die photo below shows the location of the drivers, indicated with red dots. Most of them are in the center-left of the chip, between the registers and ALU on the left and the control circuitry in the center.

The 8086 die with main functional blocks labeled. The bootstrap drivers are indicated with red dots.

Conclusions

For the most part, the 8086 uses standard NMOS logic circuits. However, a few of its circuits are unusual, and the bootstrap driver is one of them. This driver is a tricky circuit, depending on some subtle characteristics of MOS transistors, so I hope my explanation made sense. This driver illustrates how Intel used complex, special-case circuitry when necessary to get as much performance from the chip as possible.

If you're interested in the 8086, I wrote about the 8086 die, its die shrink process and the 8086 registers earlier. I plan to write more about the 8086 so follow me on Twitter @kenshirriff or RSS for updates.

Notes and references

1. Intel used a "bootstrap load" circuit in the 4004 and 8008 processors. The bootstrap load has many similarities to the bootstrap driver, using capacitance to boost the output voltage. But it is a different circuit, used in a different role. The bootstrap load was designed for PMOS circuits to boost the voltage from a pull-up transistor, using explicit capacitors, built with a process invented by Federico Faggin. I wrote about the bootstrap load here. ↩

2. The only explanation of a bootstrap driver that I could find is in section 2.3.1 of DRAM Circuit Design: A Tutorial. The 8086 transistors with the gate wired to +5V puzzled me for the longest time. It seemed to me that this transistor would always be on, and thus had no function. However, the high voltage of the bootstrap driver gives it a function. I was randomly reading the DRAM book and suddenly recognized that one of the circuits in that book was similar to the mysterious 8086 circuit. ↩

3. The threshold voltage was considerably higher for older PMOS transistors. To get around this, old chips used considerably higher supply voltages, so "losing" the threshold voltage wasn't as much of a problem. For instance, the Intel 4004 used a 15-volt supply. ↩

4. The reason that MOSFETs are symmetrical in an integrated circuit and asymmetrical as physical components is that MOSFETs really have four terminals: source, gate, drain, and the substrate (the underlying silicon on which the transistor is constructed). In component MOSFETs, the substrate is internally connected to the source, so the transistor has three pins. However, the source-substrate connection creates a diode, making the component MOSFET asymmetrical. Four-terminal MOSFETs such as the 3N155 exist but are rare. The MOnSter 6502 made use of 4-terminal MOSFET modules to implement the 6502's pass transistors. ↩

5. The load transistor is a special type of transistor, a depletion transistor that is doped differently. The doping produces a negative threshold voltage, so the transistor remains on and provides a relatively constant current. See Wikipedia for more on depletion loads. ↩

6. The superbuffer has some similarity with a CMOS gate. Both use separate transistors to pull the signal high or low, with only one transistor on at a time. The difference is that CMOS uses a complementary transistor, i.e. PMOS, to pull the signal high. PMOS performs better in this role than NMOS. Moreover, a PMOS transistor is turned on by a 0 on the gate. This behavior eliminates the need for the inverter in a superbuffer. ↩

7. The 8086 processor also uses completely different charge pumps to create a negative voltage for a substrate bias. I discuss that use of charge pumps here. ↩

8. Why is it called a bootstrap driver? The term originates with footwear: boots often had boot straps on the top, physical straps to help pull the boots on. In the 1800s, the saying "No man can lift himself by his own boot straps" was used as a metaphor for the impossibility of improvement solely through one's own effort. (Pulling on the straps on your boots superficially seems like it should lift you off the ground, but is of course physically impossible.) By the mid-1940s, "bootstrap" was used in electronics to describe a circuit that started itself up through positive feedback, metaphorically pulling itself up by its bootstraps. The bootstrap driver continues this tradition, pulling itself up to a higher voltage. ↩

9. Some circuits in the 8086 use physical capacitors on the die, constructed from a metal layer over silicon. The substrate bias generators use relatively large capacitors. There are also some small capacitors that appear to be used for timing reasons. ↩

10. The exact voltage on the gate will depend on the relative capacitances of different parts of the circuit, but I'm ignoring these factors. The voltages that I show in the diagram are illustrations of the principle, not accurate values. ↩

11. Some of the 8086's bootstrap drivers pre-discharge when the clock is low and produce an output when the clock is high, while other drivers operate on the opposite clock phases. The ALU drivers in the die photo operate on the opposite phases, but I've labeled the diagram to match the previous discussion. ↩