Installations of advanced metering infrastructure (AMS) continue to grow among power utilities as the benefits of smart meter communications with grid operators become increasingly evident. However, determining the quality of a smart meter installation is often difficult without physical site presence and local electrical testing. Misconnections could result in lost utility revenue, while earth faults could create shock hazards, and TN-grid mis-connections could potentially result in fatalities.
A European power utility faced a regulatory mandate to install AMS across its customer base. In the process of installing these smart meters, it realized it lacked processes for discovering the quality of meter installations. Arundo worked with this utility to deploy machine learning models through Arundo Composer and Arundo Fabric to monitor the quality of its installations based on pre- and post-AMS consumption, GIS, and electrical data. In addition, using Composer, the company was able to easily deploy 3rd party consumption analysis predictions built with TensorFlow.
The Arundo software identified that 1% of initial wave of new smart meters were not installed correctly—a number that was substantially higher than expected. This included a number of single and double-earth faults. In addition, Arundo identified several severe TN-grid misconnections. These represented a significant shock hazard that could have resulted in potential fatalities. Arundo’s software identified fault locations at specific properties based on appliance usage patterns, which could potentially improve the management and efficiency of field engineer interventions. Across the total base of new AMS installation, these findings represented up to $8.5 million in potential lost value from installation errors, in addition to the significant safety hazards that the software discovered.
Determine connection quality for newly installed smart meters
Cloud-based machine learning models to determine potential misconnections and shock hazards
Discovered up to $8.5 million in potential annual lost value from meter installation errors, plus identification of unexpected shock hazards
Learn how we helped a large EPC company improve accuracy and processing time of extracting information from P&IDs using a machine learning application leveraging deep learning and computer vision techniques.Read Full Article
Learn how we are helping a shipowner and operator reduce fuel consumption, reduce OPEX, improve port turn-around time and empower the crew to make better decisions.Read Full Article
Learn how we helped an offshore crane manufacturer be a trusted service provider implementing a proactive approach to maintenance routines and equipment monitoring using data science and analytics.Read Full Article
Learn how we safely reduced a ships' on-vessel water quantity by 15%, leading to significantly decreased fuel usage and increased cargo space.Read Full Article
Determining the quality of smart meter installations are often difficult without physical site presence and local electrical testing. Learn how we solved it for a European power utility.Read Full Article
An international oil and gas company had trouble with their asset performance and equipment failure rates. Learn how our solution reduced non-productive drilling time.Read Full Article
A large national oil company had reactive repairs and supply chain decisions resulting in high rig non-productive time. Learn how we used forecasting product to predict and optimize repair routes.Read Full Article
A leading oil and gas company wanted to reduce hazardous leakage risk on their heat exchangers. Learn how we used condition-based monitoring to detect subtle precursors to failure.Read Full Article
A large oil company sought to reduce yearly equipment maintenance cost by 10%. Learn how we solved it using a condition-based monitoring solution for gas compressors.Read Full Article