VARYC Model Based Hardware Fault Detection
Why Model Based Fault Detection
Traditional fault detection systems only consider real-time data, and based on these data they conclude whether a measurement is off and sends a fault signal accordingly. VARYC's model based fault detection system utilizes a complete mathematical model of your hardware that can predict how temperature, fan speed, voltages etc. must react according to previous and current measurements. These predictions are compared to actual measurements and a fault evaluation is made before an actual fault occurs.
Predictive Fault Detection
The below figures show a graph of the model prediction output and actual measurements. At some point the actual measurements deviate from the model output. The left figure shows how temperature increases more than it should according to the model, which has predicted the temperature output based on load activity, fan speed, and other parameters. Examining the top right figure it is clear that the actual and predicted duty cycles are the same. This means the fault does not lie in the control signal. However, from the bottom right figure, it is seen that the fan RPM is lower than what the model evaluates it to be. This indicates that the fan is not running as it should. The reason might be increase resistance due to external conditions or the fan simply does not get the power it requires. This also explains the increase in CPU temperature. See the results page for more examples.
Dynamic Fault Prevention
Because the fault detection system can predict how the system should behave, it can make corrections as it notices deviations. Traditional fault detection systems do not notice these small deviations, naturally because they have not evolved to become faults yet, but we do consider these abnormalities and, integrated with our control systems, we can even make changes to prevent faults from happening.
Get it Tailored to Your System
VARYC's Model Based Fault Detection System is designed after physical principles and dynamics. It is not limited to a specific platform and can therefore be adapted to any product with hardware and hardware sensors, giving you a more fault robust system, saving you time and providing you a more reliable system.
