Real-time Sensor Fault Detection: A Predictive Maintenance Application

The Louisville and Jefferson County Metropolitan Sewer District (Louisville MSD) in Kentucky, USA, uses operations research, advanced analytics, and innovative engineering concepts to protect local community waterways by optimizing the collection, transport, and treatment of wastewater. To address the many challenges of reducing sewer overflows and protecting public health and the environment while also considering their financial limitations, Louisville MSD looked for innovations to optimize its wastewater system design and operation. In partnership with Tetra Tech, Louisville MSD pioneered the application of a predictive maintenance program to reduce maintenance costs related to sensors while guaranteeing accurate measurements for the operation of its collection system. The core of this predictive maintenance program is an innovative real-time sensor fault detection algorithm based on the statistical properties of redundant measurements.