Electromechanical Maintenance Research Articles

Application of Deep Learning Techniques in the Development of Predictive Maintenance and Fault Detection in Electric Motors

During the last two decades, there has been remarkable growth in the processing capacity of computers and the evolution of digital cameras. As a result, the thermographic technique and thermal analysis became more applied in electromechanical maintenance due to the low measuring device cost. Simultaneously, new methods based on Deep Learning focused on image and video processing have emerged. In this sense, this contribution aims to verify the applicability of using the deep learning technique of convolutional neural networks to classify patterns of thermographic images of a bench grinder. The methodology used was the collection of thermographic pictures of a bench grinder after starting, without, and after applying loads to the discs. This procedure induced a temperature increase in the grinding machine housing since some types of faults in electric motors can be diagnosed due to over-temperature by thermographic inspection. Furthermore, a Python computational code was developed using a convolutional neural network to classify different grinder operation profiles based on thermal images. In conclusion, the technique proved promising for diagnosing motor failures by thermography and can be implemented in automatic predictive maintenance routines.

An Industrial Maintenance Decision Support System based on Fuzzy Inference to Optimize Scope Definition

General industrial maintenance projects (also called Shutdown Projects) in the process industry are key to the operational viability of a plant. Such projects are broad in scope, very costly, highly risky, quality strict, and involve a large number of human resources; moreover, the cost of maintenance works is added to the losses for non-producing, thus rendering these projects of paramount importance in the life of the industry. A most common, fundamental challenge faced is the optimization of the project scope, to include the equipment that can only be maintained predictively, preventively or correctively, during the shutdown period while excluding equipment that exhibits decreased failure risk. The present work deals with the development of a Decision Support System (DSS) that employs Fuzzy Logic (FL) to help define the scope of electro-mechanical maintenance works in large industrial settings. The system encompasses and combines crisp technical and functional parameters with experts’ judgment to generate a “verdict” on whether or not to include the equipment in the project scope. Results based on extensive industrial dataset show that the developed system provides more robust results and tackles many of the deficiencies of other approaches.

The Change and Prospect of “Automobile Electromechanical Maintenance Skills Competition” under the Chinese Model

This paper analyzes the origin, status, changes and characteristics of the automotive electromechanical maintenance skills competition in China, and presents the developing trend in the future.

Motion as an Instructional Feature in Maintenance Training

This paper draws upon both an extensive review of the literature, and a series of experiments manipulating motion-based (videotaped) versus static (35-mm slide) presentations of instructional material across a variety of instructional conditions. Performance measures in the experiments included both hands-on tasks and conceptual knowledge tests. Results indicated that electromechanical maintenance performance did not differ significantly between statically and dynamically trained groups across a variety of types and complexities of electromechanical maintenance tasks and instructional strategy conditions.

Effects of Instructional Delivery System and Training Parameter Manipulations on Electromechanical Maintenance Performance

A research program is presented in which computer assisted instructional (CAI) based delivery systems were compared with other training media to determine the extent to which instruction delivered via these methods affects performance on electromechanical maintenance tasks. Summaries of two preliminary studies are presented and a third study is discussed in greater detail. In the latter study opportunity for hands-on practice, access to job aids, and instructional delivery system parameters were manipulated. Performance was measured immediately following training and again after a one-week interval. Both handson practice of the maintenance activity and access to job aids during training were found to significantly improve maintenance performance. However, no differences in performance of procedural maintenance tasks were found among students who were trained using CAI-based as opposed to other lower technology-based instructional delivery systems.

Simulator Fidelity in Electro-Mechanical Maintenance Training

A program of research aimed at investigating the degree of functional and physical fidelity needed in maintenance training simulators is described. A unique aspect of this work is the use of a generic reference system to serve as both an actual equipment trainer and system for simulation. This system as well as five training simulators differing in their functional and physical resemblance to the reference system are described. Program plans, objectives, and preliminary observations are discussed.