Bearing-Fault Diagnosis with Signal-to-RGB Image Mapping and Multichannel Multiscale Convolutional Neural Network

Abstract

Deep learning bearing-fault diagnosis has shown strong vitality in recent years. In industrial practice, the running state of bearings is monitored by collecting data from multiple sensors, for instance, the drive end, the fan end, and the base. Given the complexity of the operating conditions and the limited number of bearing-fault samples, obtaining complementary fault features using the traditional fault-diagnosis method, which uses statistical characteristic in time or frequency, is difficult and relies heavily on prior knowledge. In addition, intelligent bearing-fault diagnosis based on a convolutional neural network (CNN) has several deficiencies, such as single-scale fixed convolutional kernels, excessive dependence on experts’ experience, and a limited capacity for learning a small training dataset. Considering these drawbacks, a novel intelligent bearing-fault-diagnosis method based on signal-to-RGB image mapping (STRIM) and multichannel multiscale CNN (MCMS-CNN) is proposed. First, the signals from three different sensors are converted into RGB images by the STRIM method to achieve feature fusion. To extract RGB image features effectively, the proposed MCMS-CNN is established, which can automatically learn complementary and abundant features at different scales. By increasing the width and decreasing the depth of the network, the overfitting caused by the complex network for a small dataset is eliminated, and the fault classification capability is guaranteed simultaneously. The performance of the method is verified through the Case Western Reserve University’s (CWRU) bearing dataset. Compared with different DL approaches, the proposed approach can effectively realize fault diagnosis and substantially outperform other methods.

Multiscale permutation entropy gray image coding method and its application in bearing fault diagnosis

“…Given that CNN has excelled in image classification tasks [26]. Encoding sensor-collected signals in a unique way to portray them in image form has become a current research hotspot [27,28].…”

Machine Fault Diagnosis through Vibration Analysis: Time Series Conversion to Grayscale and RGB Images for Recognition via Convolutional Neural Networks

“…Common sensors are divided by the type of measurement: (a) mechanical quantities like vibration (a popular choice due to its sensitivity to faults) [1][2][3][4][5], displacement [6], torque [7,8], and angular velocity/position [9,10]; (b) electrical quantities like current [11,12] and voltage [13,14], can reveal issues related to power delivery and motor health; and (c) other signals like temperature (inner/outer) [15,16], sound [17][18][19], and even chemical analysis [20,21] can be valuable for specific fault types. Beyond traditional sensors, recent research explores image-based diagnostics using cameras [22][23][24][25] and signals converted into virtual images [12,[26][27][28][29][30]. This versatility in sensor selection allows for a comprehensive approach to machine health monitoring and fault detection.…”

“…This approach aimed to recognize one of five classes of tool wear (initial wear, slight wear, stable wear, serious wear, and failure). Ming Xu et al [30] proposed a method for diagnosing bearing failure by converting the raw signals from three 1-axis accelerometers (located at the drive end, fan end, and base) into the R, G, and B channels of an RGB image. Converting high-dimensional sensor data to RGB images with only three channels can lead to information loss.…”

Fusion of Audio and Vibration Signals for Bearing Fault Diagnosis Based on a Quadratic Convolution Neural Network

“…To summarize, great advances have been achieved in fault diagnosis, but there are still several limitations. For instance, information provided by single modality is limited, and commonly utilized deep-learning networks need a huge amount of parameters to achieve complex mapping functions [26,27]. In the evolving landscape of bearing fault diagnosis, quadratic convolutional neural network (QCNN) has emerged as a transformative tool.…”