Restoring a liveatc.net pi station

I hosted the T67 radio feed to Liveatc.net.   We'd had a storm with lightning and power hits which was the demise of the SD memory card in the old Raspberry pi (I think from 2014).   A new image got the unit back on line, but it was having memory issues.   

A new pi 4 was ordered, a new RTLSDR V4 dongle, and 978 and 1090 dongles for adsbexchange.  It was a challenge to get all services running correctly since I'm a noob with this hardware and software.  After futzing for a few days, decided to split the radio traffic from ADS-B and ordered another pi 4.

One of the struggles with adsbexchange dongles is that process may grab the wrong USB dongle.  The common work around is to write or change the serial number in the dongle and specify that serial number in the config file.  A problem is that despite doing this, one of the apps was still using the index and not the serial number.  The index number stays with the port and not the dongle, so it's important to not swap ports.  Also the blue USB 3.0 port supplies more power and was recommended for the 1090 dongle.

So one project had turned into two.  Or three.  I want to try to do some things with speech to text later.

With Dave Pascoe's help from Liveatc, we got the T67 feed working and added Copeland 4T2.  The new dongle works good with good audio quality.  I moved the antenna several times and will ultimately move it to the peak of the hangar and add lightning protection.

The adsbexchange system initially went fairly well except for the issue with serializing the dongles and getting the config files to use the serial number (or the index).  Piaware was added to feed to Flightaware.  Puzzling, was that the stats at times indicated UAT (978 Mhz) traffic on the local info page, but Flightaware only showed a couple of aircraft on one day.  Peering at the local graphs, the one that shows signal strength looked pretty noisy.   Going into the adsbexchange GUI, found the 978 gain was set to max.  I backed it down, swapped antennas etc. and the graph looked better.  However, Flightaware continued showing zero aircraft.  Pinging Grok and Google's AI, found there was a process that was not running that pulled the UAT data to forward to Flightaware.   After getting it running and tweaking gain, aircraft were showing up in the stats.  The 978 and 1090 are on temporary antennas.  The 1090 is picking up aircraft more than 250 miles away.  The 978 varies.  Occasionally it picks up 60 miles away and others, loses aircraft just west of here.  Having the two antennas to close together or near our outside weather station degrades reception.

Flightaware's stats for my reciever:https://www.flightaware.com/adsb/stats/site/262213#stats-262213

Link for Liveatc.net & T67 feed (pi 4 with RTLSDR V4 BLOG dongle) https://www.liveatc.net/hlisten.php?mount=t67&icao=t67

https://www.liveatc.net/

Squat detection

I asked Grok about integrating wheels on ground and possible CG determination using bend or strain gauges.

 Using a strain gauge or bend sensor on the fiberglass main gear bow of your Cozy MK IV is a promising approach for a squat switch or weight detection system. Both options have merits, but the choice depends on your requirements for simplicity, accuracy, durability, and ease of implementation. Let’s break down the options and consider their suitability for your application, including the potential for gross weight and center of gravity (CG) determination.

### Strain Gauge **How it works**: A strain gauge measures the deformation (strain) of the gear bow by detecting changes in electrical resistance as the material flexes under load. For a squat switch, you’d detect the presence of strain (indicating weight on wheels), and for weight/CG estimation, you’d quantify the strain magnitude. **Pros**: - **High Sensitivity**: Strain gauges can detect small deformations, making them suitable for both binary squat switch detection and quantitative weight measurement. - **Quantitative Output**: With proper calibration, strain gauges can provide data for estimating gross weight and CG by placing sensors on the main gear bow and nose gear strut. - **Compact and Lightweight**: Strain gauges are small, lightweight, and can be bonded directly to the fiberglass gear, minimizing aerodynamic impact. - **Established Technology**: Widely used in aviation for load monitoring, with well-documented installation and calibration methods. **Cons**: - **Temperature Sensitivity**: Fiberglass has a relatively high coefficient of thermal expansion compared to metals, and strain gauges are sensitive to temperature changes. Without compensation (e.g., a Wheatstone bridge with a dummy gauge or temperature sensor), readings may drift, especially in varying environmental conditions. - **Complex Installation**: Requires careful surface preparation, precise bonding, and protection from moisture and vibration. Fiberglass’s composite nature can complicate strain transfer and bonding reliability. - **Signal Conditioning**: Needs amplification and conditioning circuits to convert resistance changes into usable signals, adding complexity. - **Calibration**: For weight/CG estimation, calibration is critical and may need periodic rechecking due to fiberglass creep or aging. ### Bend Sensor (Flex Sensor) **How it works**: A bend sensor (e.g., a resistive flex sensor) changes resistance based on the degree of bending. It could be mounted on the gear bow to detect flexing when the aircraft’s weight is on the gear. **Pros**: - **Simpler Installation**: Bend sensors are typically easier to mount, often requiring only adhesive or mechanical attachment, and are less sensitive to surface preparation than strain gauges. - **Less Temperature Sensitivity**: While not immune, flex sensors are generally less affected by temperature-induced errors in the context of binary detection (squat switch). - **Lower Cost and Complexity**: For a simple squat switch, a bend sensor requires minimal signal conditioning, making it a plug-and-play option for detecting gear deflection. - **Rugged**: Some flex sensors are designed for harsh environments, potentially offering good durability on a landing gear. **Cons**: - **Lower Precision**: Bend sensors are less accurate for quantitative measurements like weight or CG. Their output is typically nonlinear and less repeatable than strain gauges. - **Limited Range**: Flex sensors have a finite bending range, and excessive deflection (e.g., during hard landings) could damage them or yield unreliable readings. - **Durability Concerns**: Fiberglass gear undergoes cyclic loading, and some flex sensors may degrade over time under repeated bending or UV exposure. - **Not Ideal for CG/Weight**: Due to lower accuracy and repeatability, bend sensors are less suitable for precise weight or CG calculations. ### Alternative Solutions 1. **Microswitch or Limit Switch**: - **Description**: A mechanical microswitch mounted to detect gear deflection or contact with the ground. - **Pros**: Extremely simple, reliable, and binary (on/off) for squat switch use. No temperature compensation needed. - **Cons**: Not suitable for weight/CG measurement. May require mechanical modification to the gear or airframe, and moving parts can wear or jam. - **Use Case**: Best for a basic squat switch if weight/CG isn’t a priority. 2. **Optical or Laser-Based Deflection Sensor**: - **Description**: A non-contact sensor (e.g., laser displacement sensor) measures gear bow deflection by detecting changes in position or distance. - **Pros**: High precision, no direct contact with the gear, and potentially easier temperature compensation. Suitable for both squat detection and weight/CG estimation. - **Cons**: Expensive, complex to integrate, and sensitive to environmental factors like dirt or vibration. May require significant modification to mount. - **Use Case**: Viable for a high-end system but likely overkill for a Cozy MK IV unless precision is paramount. 3. **Load Cells**: - **Description**: Install load cells at the gear attachment points or axles to directly measure weight. - **Pros**: Highly accurate for weight and CG calculations, with established use in aircraft weighing systems. Temperature compensation is standard in many load cells. - **Cons**: Requires significant structural modification to integrate into the gear system, adding weight and complexity. Not ideal for a simple squat switch. - **Use Case**: Best for precise weight/CG measurement but impractical for retrofit on a fiberglass gear bow. ### Analysis for Your Application - **Squat Switch**: For a simple weight-on-wheels detection, a **bend sensor** is likely the most elegant and cost-effective solution. Its simplicity and sufficient sensitivity to detect gear deflection make it ideal for a binary output. A microswitch could also work but may require more mechanical integration. - **Weight and CG Estimation**: If you want to extend the system to measure gross weight and CG, **strain gauges** are the better choice due to their higher precision and ability to provide quantitative data. By placing gauges on the main gear bow and nose gear strut, you can correlate strain to load and calculate CG based on the distribution of weight. However, this requires: - Temperature compensation (e.g., using a Wheatstone bridge with a dummy gauge on an unloaded fiberglass sample). - Calibration with known weights to establish a strain-to-weight relationship. - Signal conditioning (amplifier and analog-to-digital converter) for accurate readings. - Software to process data and compute CG based on gear geometry. - **Fiberglass Considerations**: Fiberglass gear bows are anisotropic and may exhibit creep or fatigue over time, which could affect long-term calibration. Strain gauges must be bonded carefully to ensure consistent strain transfer, and protective coatings (e.g., epoxy or silicone) are needed to shield them from moisture and abrasion. Bend sensors are less sensitive to these issues but may not withstand repeated high-deflection cycles. ### Recommendation - **For Squat Switch Only**: Use a **bend sensor** mounted on the main gear bow. It’s simple, lightweight, and sufficient for detecting deflection without the complexity of strain gauges. Ensure the sensor is rated for the expected deflection range and environmental conditions (e.g., FlexiForce or Spectra Symbol flex sensors). - **For Squat Switch + Weight/CG**: Use **strain gauges** on the main gear bow and nose gear strut. This setup offers the precision needed for weight and CG estimation. Implement a Wheatstone bridge with temperature compensation (e.g., a dummy gauge on unloaded fiberglass) and a microcontroller-based data acquisition system (e.g., Arduino or similar with a strain gauge amplifier). Calibration will be critical, and you’ll need to account for fiberglass’s thermal expansion (coefficient ~10-20 µm/m/°C) and potential creep. - **Hybrid Approach**: If budget and complexity allow, consider a bend sensor for the squat switch (simplicity) and strain gauges for weight/CG (accuracy). This separates the systems, reducing the squat switch’s reliance on complex electronics while enabling precise weight measurements. ### Practical Considerations - **Installation**: For strain gauges, follow aerospace-grade bonding procedures (e.g., using Vishay or Omega gauges with M-Bond adhesive). For bend sensors, ensure secure mounting without constraining gear flex. - **Electronics**: A simple squat switch needs minimal processing (e.g., a comparator circuit). Weight/CG measurement requires a data acquisition system with at least 12-bit resolution and temperature compensation. - **FAA Compliance**: Since the Cozy MK IV is experimental, you have flexibility, but ensure any modifications meet airworthiness standards (e.g., FAR Part 23 for guidance). Consult with an A&P mechanic or DER if integrating into a certified aircraft or if safety-critical systems (e.g., gear warning) rely on the sensor. - **Testing**: Bench-test the system with simulated loads and temperature cycles. For weight/CG, calibrate with known weights on the aircraft and verify CG calculations against manual measurements. ### Conclusion For a squat switch alone, a **bend sensor** is the simplest and most elegant solution due to its ease of use and adequate sensitivity. For combined squat switch and weight/CG measurement, **strain gauges** are superior despite their complexity, offering the precision needed for quantitative data. If budget and expertise allow, strain gauges with proper temperature compensation and calibration are the best path for a dual-purpose system. Avoid load cells or optical sensors unless you’re prepared for significant modifications. Let me know if you need help with specific sensor models, circuit design, or calibration procedures!

Establising a performance baseline

After looking at EFIS data uploaded to SavvyAviation's web site, trying to see if there were speed and cooling improvements, found it was difficult to glean from different flights since the altitude, power setting, CG varied quite a bit.   

I asked Grok how to establish a baseline and got this: 

To establish a performance baseline for speed improvements on an experimental aircraft, follow a systematic, repeatable, and data-driven approach. The goal is to create a reliable reference point for the aircraft’s current speed performance under controlled conditions, which you can use to measure the impact of modifications. Here’s how to do it effectively:

1. Define Key Performance Metrics:
   • Focus on speed-related metrics such as maximum level speed, cruise speed, climb rate, and acceleration time to a specific speed (e.g., time to reach 200 knots).
   • Include related parameters like fuel consumption, engine RPM, and airspeed (indicated, true, and ground speed) to provide context.
   • Specify units (e.g., knots, mph, or km/h) and ensure consistency across measurements.
2. Standardize Test Conditions:
   • Environment: Conduct tests in consistent weather conditions (e.g., calm winds, standard temperature, and pressure). Use a day with minimal turbulence and stable atmospheric conditions (e.g., clear skies, no significant thermal activity).
   • Altitude: Test at a fixed altitude (e.g., 5,000 ft above sea level) to minimize variations in air density. Record density altitude for each test.
   • Weight and Balance: Ensure the aircraft is at a consistent weight, including fuel, payload, and pilot. Use a standard configuration (e.g., 50% fuel, solo pilot) and document the center of gravity.
   • Configuration: Test with a fixed aircraft configuration (e.g., flaps up, gear retracted if applicable, and a specific propeller setting for variable-pitch props).
3. Use Precise Measurement Tools:
   • Airspeed: Use calibrated onboard instruments (e.g., pitot-static system) and cross-check with GPS-derived ground speed, adjusted for wind.
   • Data Logging: Employ a flight data recorder or avionics system (e.g., Garmin G1000, Dynon SkyView) to log airspeed, altitude, engine parameters, and GPS data at regular intervals (e.g., 1 Hz).
   • External Validation: If possible, use ground-based radar or a chase plane with calibrated instruments to verify speeds.
   • Time Trials: For specific tests (e.g., acceleration), use a stopwatch or automated timing system synced with GPS.
4. Conduct Controlled Flight Tests:
   • Test Plan: Develop a detailed flight test plan with specific procedures for each test. For example:
     • Max Speed Test: Fly level at full power for a set distance (e.g., 10 nautical miles) in two opposing directions to average out wind effects.
     • Cruise Speed Test: Fly at a fixed power setting (e.g., 75% power) and record stabilized speed over a set time or distance.
     • Climb Rate Test: Measure time to climb between two altitudes (e.g., 3,000 to 5,000 ft) at a constant airspeed or power setting.
   • Repetition: Perform each test at least three times to ensure repeatability and calculate average values. Discard outliers only if there’s a clear error (e.g., instrument malfunction).
   • Flight Path: Use GPS to maintain a consistent flight path (e.g., straight and level or a specific climb angle). Fly in areas with minimal air traffic to avoid deviations.
5. Document and Normalize Data:
   • Record all relevant data, including airspeed, ground speed, altitude, temperature, pressure, wind speed/direction, and aircraft configuration.
   • Normalize data to standard conditions (e.g., sea-level equivalent speed) using formulas like true airspeed (TAS) calculations:
     \text{TAS} = \text{IAS} \times \sqrt{\frac{\rho_0}{\rho}}
     where

     \text{IAS}

     is indicated airspeed,

     \rho_0

     is sea-level air density, and

     \rho

     is actual air density at test altitude.
   • Account for wind by averaging speeds from reciprocal headings or using GPS ground speed with wind vector corrections.
6. Establish the Baseline:
   • Compile the averaged, normalized results into a performance baseline. For example:
     • Max speed: 180 knots TAS at 5,000 ft, 100% power, 50% fuel.
     • Cruise speed: 160 knots TAS at 75% power, 8,000 ft.
     • Climb rate: 1,200 ft/min from 3,000 to 5,000 ft.
   • Document the baseline in a detailed report, including test conditions, equipment used, and any deviations from the plan.
7. Validate and Refine:
   • Cross-check results with theoretical performance models (e.g., drag polar, engine power curves) or manufacturer data (if available).
   • Conduct a second set of tests on a different day to confirm consistency.
   • If results vary significantly, investigate sources of error (e.g., instrument calibration, pilot technique, or unaccounted wind).
8. Use the Baseline for Comparisons:
   • After modifications (e.g., aerodynamic fairings, engine upgrades), repeat the same test procedures under identical conditions.
   • Compare new results to the baseline to quantify improvements (e.g., “Max speed increased by 5 knots after installing wingtip fairings”).
   • Use statistical methods (e.g., t-tests) to confirm that changes are significant and not due to random variation.

Additional Tips:

• Safety First: Ensure all tests comply with FAA (or relevant authority) regulations for experimental aircraft. Use a qualified test pilot and conduct a thorough pre-flight inspection.
• Calibration: Verify instrument accuracy before testing. For example, perform a pitot-static system check or calibrate GPS units.
• Incremental Changes: When testing modifications, change one variable at a time (e.g., propeller pitch) to isolate its effect on speed.
• Real-Time Monitoring: If possible, use telemetry to monitor performance live and abort tests if parameters (e.g., engine temps) exceed safe limits.

By following this approach, you’ll create a robust, repeatable baseline that allows you to accurately measure speed improvements and make data-driven decisions for your experimental aircraft. If you have specific details about the aircraft (e.g., type, engine, or mods planned), I can tailor the advice further.