Modeling and Fault Detection of Brushless Direct Current Motor by Deep Learning Sensor Data Fusion

Abstract

Only with new sensor concepts in a network, which go far beyond what the current state-of-the-art can offer, can current and future requirements for flexibility, safety, and security be met. The combination of data from many sensors allows a richer representation of the observed phenomenon, e.g., system degradation, which can facilitate analysis and decision-making processes. This work addresses the topic of predictive maintenance by exploiting sensor data fusion and artificial intelligence-based analysis. With a dataset such as vibration and sound from sensors, we focus on studying paradigms that orchestrate the most optimal combination of sensors with deep learning sensor fusion algorithms to enable predictive maintenance. In our experimental setup, we used raw data obtained from two sensors, a microphone, and an accelerometer installed on a brushless direct current (BLDC) motor. The data from each sensor were processed individually and, in a second step, merged to create a solid base for analysis. To diagnose BLDC motor faults, this work proposes to use data-level sensor fusion with deep learning methods such as deep convolutional neural networks (DCNNs) for their ability to automatically extract relevant information from the input data, the long short-term memory method (LSTM), and convolutional long short-term memory (CNN-LSTM), a combination of the two previous methods. The results show that in our setup, sound signals outperform vibrations when used individually for training. However, without any feature selection/extraction step, the accuracy of the models improves with data fusion and reaches 98.8%, 93.5%, and 73.6% for the DCNN, CNN-LSTM, and LSTM methods, respectively, 98.8% being a performance that, according to our reading, has never been reached in the analysis of the faults of a BLDC motor without first going through the extraction of the characteristics and their fusion by traditional methods. These results show that it is possible to work with raw data from multiple sensors and achieve good results using deep learning methods without spending time and resources on selecting appropriate features to extract and methods to use for feature extraction and data fusion.

Predictive Maintenance of Electromechanical Systems Using Deep Learning Algorithms: Review

“…Equipment Fault Parameters Method [40] Motor Bearing Current signal CNN [41] CNC machine Condition Vibrations ANN [42] Motor Operations Current and voltage signal ANN/MLP [43] Pump Condition Multi variables AE [44] CNC machine Mechanical Vibrations signal SAE [45] Motor Operations Stator currents ANN [46] Motor Bearing Vibrations signal LSTM [47] Rotating machinery Bearing Vibrations signal AE+ MLP [48] Rotating machinery Bearing Vibrations signal LSTM [49] Cooling radiator Condition Thermal image CNN [50] Rotating machinery Degradation image Infrared image streams (CNN+LSTM) (LSTM+AE) [51] Compressor Condition Multi variables RNN-LSTM [52] Elevator system Movement Acceleration data AE [53] Motor Condition Current signal EWT-CNN [54] Autoclave sterilizer Pump NTC thermistors LSTM [55] Worm gearboxes Operations Multi variables CNN [56] Rotating machinery Rotor, bearing Vibration signals CNN [57] Railcar factories Wheel bearing Temperature variation ANN [58] Rotating machinery Bearing Accelerometers CNN [59] Motor Bearing Current signal ANN [60] Conveyors system Motor Multi variables CNN [61] Motor Bearing Accelerometer LSTM+RNN [62] Motor Rotor bar Torque control ANN [63] Motor Stator winding stator currents ANN [64] Motor Condition Vibrations signal ANN [65] Rotating machinery Bearing Rotation speed, load levels CNN [66] Motor Stator winding Multi variables MLP+LSTM+CNN [67] Motor Operations Current signal ANN [68] Motor+rotating equipment Bearing Vibrations signal CNN+DNN [69] Motor Bearing Microphone, accelerometer DCNN+CNN-LSTM+LSTM…”

Fault Diagnosis Methods for an Artillery Loading System Driving Motor in Complex Noisy Environments

“…Considerable literature on motor fault diagnosis has emerged around the topic of deep learning. Suawa et al [24] proposed a fusion method using data level sensors and deep learning, proposing Convolutional Long Short-Term Memory (CNN-LSTM), which is a combination of two deep learning methods in order to diagnos Brushless Direct Current motor faults. Husari et al [25] proposed a hybrid architecture namely a 1D convolutional neural network-long short-term memory (1DCNN-LSTM) and a 1DCNN-gated recurrent unit (GRU)-based approach, for early inter-turn fault diagnosis Li et al [26] proposed a wavelet kernel net, which used a wavelet basis instead of convo lutional kernels, and combined the advantages of deep learning and classical signal pro cessing methods.…”

Predictive maintenance of planetary gearboxes using FFT and machine learning technique

“…Maintenance staff can use machine learning algorithms that have been trained on this data to accurately diagnose issues and anticipate probable failures. The advantages of predictive maintenance, such as decreased delay, improved maintenance scheduling, and enhanced equipment performance, make it a worthwhile investment for sectors that rely on planetary gearboxes despite hurdles in data collecting and model building (Suawa et al 2022).…”