Equalis Predictive Motor Maintenance Solution (PMM)
Electric motors are used in a wide variety of industrial and transportation applications. Reliability of their operation in most of these applications is of very high importance and failures can incur significant costs and downtime or even lead to disastrous consequences. Traditionally, the problem of ensuring motor reliability is dealt with using fixed interval maintenance, whereby personal at a certain time interval check the machines and their state of operation. This practice however has serious drawbacks: it can incur high costs, require a large amount of maintenance person's direct time, and additional downtime regardless of the health state of a motor.
An attractive alternative is condition-based maintenance, whereby instrumentation is located on the motor that allows diagnosis of potential problems before they actually occur. The main idea of this technology is continuous monitoring of the motor health and scheduling motor maintenance or replacement depending on its current and projected condition. This approach allows one to have always up-to-date information about the state of the critically important equipment, plan maintenance, reduce maintenance costs, minimize undesirable downtime, and prevent unexpected and possibly disastrous equipment failures. However, the absence of this type of equipment that is, accurate, robust, and low cost has not allowed this option to exist. However, current state-of-the-art controllers, along with Equalis software solutions, make a package available today that is easy-to-deploy, easy-to-operate, and scalable for automated remote monitoring of motor health. This type of solution is particularly beneficial to the transportation industry where the Equalis solution can include a cellular up-link to a server.
In this series of blog posts we will describe the process of development of a solution to the mentioned problem of condition-based maintenance for the railroads sector called Equalis Predictive Motor Maintenance Solution by Equalis (www.equalis.com), a division of the Institute for Human Factors Engineering, an engineering and scientific software and solutions provider.
The aim of the solution is providing a railroad with the up-to-date information about the health state of critical electric motors on railroad vehicles and recommendations on the plans of motor maintenance.
Although motor health can be monitored using different technologies, the most attractive approach is vibration measurement which can be done using low cost sensors that can be deployed with minimum time and effort and do not require any special integration into the existing systems of a vehicle. A practical condition-based maintenance system based on this approach has to involve:
motor vibrations measurement
collection of the measurements obtained from different motors of interest
analysis of the collected measurements, detection and prognosis of motor faults, and generation of motor maintenance plans
delivery of results of the analysis
All these items are taken into account and implemented in the Equalis Predictive Motor Maintenance Solution, using the combination of the following technologies:
motor vibration measurement using compact, self-contained, intelligent vibration sensors
transmission of the vibration data over a cellular network from the sensors to a specialized cloud computing service on the Internet for storage and further analysis
state-of-the-art data-driven, configurable algorithms for vibration signal analysis and motor fault detection and prognosis based on joint time and frequency measurements along with machine learning techniques
web interface for convenient access to the up-to-date automatically generated reports on the health state of the motors and the recommended maintenance plans
software interfaces for integration with enterprise information and management systems
A high-level overview of Equalis Predictive Motor Maintenance Solution is illustrated below.
The details of implementation of each part of the system, the discussion of the design decisions, and the reports of deployment and testing of the system’s components will be described in the next blog posts.
