No abstract

PurposeThe purpose of this paper is to provide a shorter time cost, high-accuracy fault diagnosis method for water pumps. Water pumps are widely used in industrial equipment and their fault diagnosis is gaining increasing attention. Considering the time-consuming empirical mode decomposition (EMD) method and the more efficient classification provided by the convolutional neural network (CNN) method, a novel classification method based on incomplete empirical mode decomposition (IEMD) and dual-input dual-channel convolutional neural network (DDCNN) composite data is proposed and applied to the fault diagnosis of water pumps.Design/methodology/approachThis paper proposes a data preprocessing method using IEMD combined with mel-frequency cepstrum coefficient (MFCC) and a neural network model of DDCNN. First, the sound signal is decomposed by IEMD to get numerous intrinsic mode functions (IMFs) and a residual (RES). Several IMFs and one RES are then extracted by MFCC features. Ultimately, the obtained features are split into two channels (IMFs one channel; RES one channel) and input into DDCNN.FindingsThe Sound Dataset for Malfunctioning Industrial Machine Investigation and Inspection (MIMII dataset) is used to verify the practicability of the method. Experimental results show that decomposition into an IMF is optimal when taking into account the real-time and accuracy of the diagnosis. Compared with EMD, 51.52% of data preprocessing time, 67.25% of network training time and 63.7% of test time are saved and also improve accuracy.Research limitations/implicationsThis method can achieve higher accuracy in fault diagnosis with a shorter time cost. Therefore, the fault diagnosis of equipment based on the sound signal in the factory has certain feasibility and research importance.Originality/valueThis method provides a feasible method for mechanical fault diagnosis based on sound signals in industrial applications.

Machine fault detection has great practical significance. Compared with the detection method that requires external sensors, the detection of machine fault by sound signal does not need to destroy its structure. The current popular audio-based fault detection often needs a lot of learning data and complex learning process, and needs the support of known fault database. The fault detection method based on audio proposed in this paper only needs to ensure that the machine works normally in the first second. Through the correlation coefficient calculation, energy analysis, EMD and other methods to carry out time-frequency analysis of the subsequent collected sound signals, we can detect whether the machine has fault.

Failure diagnosis is of great significance for the timely detection of the safety hazard of the equipment and the guarantee of the normal operation of the production. In fault diagnosis, the way based on the processing of sound signal has the advantages of strong fault sensitivity, easy acquisition, and noncontact measurement, and the way of using neural network provides a more efficient and generally applicable method for fault diagnosis efficiency. For the poor diagnostic accuracy of traditional methods, which requires manual extraction of features and poor general applicability of the model, in this paper, we propose a mechanical failure diagnosis method based on acoustic signals and CNNs. The sound signals were first sampled and features extracted by MFCC, then the data were split into training and test sets in a 6:4 ratio and input to the convolutional neural network. After adjusting the parameters for the comparison experiment, the final experimental model was able to achieve 97.05% test accuracy over 20 training test iterations.