EECOMOBILITY has developed fault detection, diagnosis and prognostic software technology, designed for automotive, fleet and off-highway markets. ECCOMOBILITY’s software is a self-learning technology that has been proven and tested in real market conditions, providing high-speed analysis, with easy implementation and customization.

EECOMOBILITY’s software is being developed for the new automotive markets of (ACES) autonomous, connected, electric and shared vehicles. Testing is being conducted in various sectors, including heavy duty autonomous vehicles, electric vehicle battery development, electric motor and inverter development and testing.

This start-up company is supported by a skilled, experienced and dedicated team of professionals led by Dr. Saeid Habibi of McMaster University.  Dr. Habibi is the Director of the Centre for Mechatronics and Hybrid Technology (CMHT) at McMaster.  The Centre has considerable research funding and state of the art automotive testing facilities.  The Centre is involved in collaborative projects with OEM’s and Tier One Automotive industry partners, enabling further development and application of the software for ACES vehicles.

EECOMOBILITY’s Technology provides extremely fast detection/diagnostic/prognosis for cyclical processes, utilizing both time and position based high frequency measured signals. The signals are processed to generate fault signatures (which are multi-faceted representations of the information contained within the measured signals). Artificial intelligence is used to classify and diagnose the fault conditions at their inception and predict their progression into failure modes. Results of 100% detection and 97% fault diagnoses are providing exceptional solutions for clients.

The software has been incorporated into real-world performance, endurance and production testing within multiple automotive manufacturing environments. Automotive industry leaders have provided platforms for validation, testing and implementation of the software technology with exceptional results. The software has proven capable of utilizing multiple sensors individually or together ranging from Accelerometers, Microphones, Voltage and Current Sensors, Torque and Speed sensors, to conventional Knock sensors.