When developing a solution for fault diagnosis, cost is a key factor that must be considered to ensure a practical and feasible final product. In an effort to reduce costs, the authors conducted a feasibility study using a low-cost MEMS accelerometer in conjunction with an Arduino Uno. To verify the performance of this setup, a study was carried out using a MEMS sensor and the Arduino Uno as the data acquisition system in fault diagnosis applications. The maximum sampling rate of the sensor and Arduino Uno was used to set the data acquisition parameters, However optimal sample length studies were lacking. Therefore, this study aimed to determine the effect of sample length on fault classification by varying it from 50 to 5000 to identify the optimal value for this particular application.
After finalizing the parameters, the vibration signal was acquired using the MEMS sensor and Arduino Uno. The resulting classification accuracy using decision tree was 90.2%, a satisfactory result that can be further improved for industrial applications. To enhance the accuracy of decision tree classifiers, the authors proposed a novel approach using probabilistic voting method.
To demonstrate the feasibility of utilizing MEMS sensors for the fault diagnosis of suspension systems in automobiles, a case study was conducted using a vibration signal as a typical diagnostic scenario. The study also determined the optimal sample length required for this application. Additionally, a novel method, the Probabilistic Voting Method, was proposed to enhance performance. Revolutionizing the monitoring system, the utilization of an Arduino Uno and MEMS sensor (ADXL335) drastically cut down costs, while achieving a remarkable classification accuracy of 90.2%. The implementation of the Probabilistic Voting Method further elevated the accuracy to an astounding 98.5%, setting a new benchmark in the field.