Ensembled mechanical fault recognition system based on deep learning algorithm

Abstract

Primary detection and removal of mechanical fault is vital for the recovery of mechanical and electrical equipment. The conventional mechanical fault recognition modules are not able obtain highly sensitive feature attributes for mechanical fault classification in the absence of prior knowledge. The fault diagnosis via data-driven methods have become a point of expansion with recent development in smart manufacturing and fault recognition techniques using the concept of deep learning. In this work, a combination of feature selection with Artificial Intelligence (AI) algorithm is presented for the mechanical fault recognition to deal with smart machine tools. This article proposes a CNN based fault recognition and classification framework that uses the combination of feature extraction, feature vector decomposition using Empirical Mode Decomposition (EMD) and deep neural network (DNN) for recognising the different fault states of the rotating machinery. The experimental outcomes obtained by the combination of EMD, feature selection module and Convolutional Neural Network (CNN) provides the detailed fault information by selecting the sensitive features from large number of faulty feature attributes. The proposed fault recognition and classification method performs better in terms of all the parameters yielding 99.01 % accuracy with respective cross-entropy loss of 0.325 and time complexity of 18 mins and 31 seconds. The comparative analysis is also done with other mainstream models and other state of the art methods, which reveals that the maximum improvement of 12.29 % is attained in terms of accuracy for the proposed fault recognition method. The presented method is robust in terms of reduction of network size, improvement of mechanical fault recognition, providing classification accuracy along with high fault diagnostic solution.

The use of power information technology in fault diagnosis of electrical equipment

“…With the gradual deepening of the application of information technology in power generation enterprises, large-scale electric equipment has achieved some results that can be practically applied in life management and prediction, equipment reliability technology, equipment condition monitoring, and fault diagnosis technology. Literature [17] combined with artificial intelligence algorithms to conceive a mechanical fault identification and analysis model, and in the fault identification test, compared with the traditional method, the identification accuracy has been improved to a certain extent. Literature [18] reveals the performance of electrical equipment fault identification and detection technology based on computer vision method through example analysis, realizes low-cost transmission line fault detection, and effectively reduces the operation risk of power plants.…”

Research on Image Recognition Methods Based on Deep Learning

“…Artificial intelligence is a strategic technology that leads the future, and the world's major developed countries take the development of artificial intelligence as a major strategy to enhance national competitiveness and maintain national security. Therefore, each big country is seizing the major strategic opportunities for the development of AI in their own countries, taking the development of AI as one of the indicators of a country's comprehensive national power and raising the development of AI in their own countries to the strategic issues of the country [4][5]. In addition, in the China New Generation Artificial Intelligence Science and Technology Industry Development Report 2021 released by Pujiang Innovation Forum, it is shown that 16 countries around the world have released national AI development strategies or plans one after another, and there are at least 18 other countries that are preparing to formulate AI development plans.…”

A Centrifugal Pump Fault Diagnosis Framework Based on Supervised Contrastive Learning

“…The mentioned ML methods result in a satisfactory classification, especially, SVM proved to provide a high accuracy in research conducted in [14]. In addition, a significant amount of research has been performed on artificial intelligence-based fault diagnosis in pumps [15]. However, the related algorithms classify data based on manually extracted features, which may not be the best for the classification of faults as it requires expertise in manual data analysis.…”