Automation and control systems are widely used in smart buildings and facilities. The capabilities of the control hardware and software grow more sophisticated as trends such as artificial intelligence (A.I.) and machine learning continue to proliferate in the world at large. This is especially true since electrical loads may change significantly in the near future, as many vehicle fleets transition to electric and will require charging infrastructure to be part of the electrical power landscape of buildings and facilities.

The Reality Check Motor Toolbox is one software solution pioneered by Renseas Electronics Corp., San Jose, Calif., a supplier of advanced semiconductor solutions. This toolbox can provide granular data and details regarding motors and their optimal management in a building or industrial landscape.

The company describes the solution as “an advanced machine learning software toolbox, [that] uses electrical information from the motor control process to enable the development of predictive maintenance, anomaly detection and smart control feedback—all without the need for additional sensors.”

Part of the utility of the new software is to enable predictive maintenance to apply for motor maintenance and health. This is ideal, as predictive maintenance navigates through uncertainty as the operational and environmental demands placed on motors and motor equipment varies greatly.

Plugging into the equipment, the software can compute failure analysis, check operational parameters and ferret out red flags that may warrant maintenance. It could tell maintenance managers about bearing misalignment, overheating, insulation breakdown and other maintenance problems—based on history and performance. Ultimately, it can drive decisions for where and what maintenance action is necessary. It may also send a signal that it may be time to replace a motor entirely.

Unique to the software is that it uses the equipment’s design data and performance data by plugging into the equipment microprocessors and mobile processing units. The extracted data feeds A.I. algorithms, allowing it to output data and information without being too disruptive to the control configuration.

Other types of software can help users test motors and predict maintenance needs. For example, Magtrol, a manufacturer of motor test equipment based in Buffalo, N.Y., has a different motor testing equipment for users’ distinctive needs. The M-TEST 7 program is for PCs and is designed for data acquisition and helps to determine motor characteristics. Up to 63 parameters are calculated, and users can see results in graphical or tabular formats. It performs ramp, curve, manual, pass/fail, coast, temperature, locked rotor temperature and running heating temperature tests. Users can duplicate tests and run them automatically.