Utilities can save money and improve their networks' overall dependability and performance by incorporating advanced analytics into their asset management plans.
FREMONT, CA: Asset management can account for a significant portion of the operating and capital expenditures of a transmission and distribution (T&D) company, with optimized operations and investments being the key to generating savings. Companies, with the help of modern technologies, can capture these efficiencies. Utilities can leverage advanced analytics in their asset management strategies in savings while enhancing their networks' overall reliability and performance. It utilizes an optimization engine to prioritize asset replacement and PM tasks by the asset's risk.
The risk of each asset develops the optimization engine by multiplying its health score by its criticality. The replacement of assets was then prioritized based on their risk scores and replacement costs. A high-risk transformer with a lower replacement cost precedes a similar transformer with a higher replacement cost. A comprehensive failure-mode analysis was incorporated into the optimization engine to estimate the amount of risk each PM activity eliminated to optimize PM. The optimization engine considered the cost of performing each activity and prioritized those significantly reducing risk.
Stay ahead of the industry with exclusive feature stories on the top companies, expert insights and the latest news delivered straight to your inbox. Subscribe today.
They implemented an asset management program driven by advanced analytics, particularly about getting started, data integrity, talent and capabilities, change management, and implementation and governance. At the outset, the team encountered internal resistance, including concerns that they needed more or appropriate data to address regulatory considerations. Implementing a proof of concept, identifying assets with sufficient data to get started, and developing a solution superior to the present state was the first crucial step in overcoming this resistance.
The success of the proof-of-concept gives the confidence to proceed with the solution's deployment across multiple assets and operating entities. Developing data architecture and implementing processes to capture and conduct quality control checks on the appropriate categories of data were crucial to resolving this issue in the future. Asset managers were required to modify their management processes while implementing advanced analytics. The key to resolving this issue was to involve asset managers early on and include them in the solution development process.
AI and ML are still in their infancy, expanding rapidly. Data scientists and engineers, who are essential for developing solutions, need more supply. Implementing and governing the incorporation of advanced analytics into the processes for selecting assets for replacement and revising maintenance processes and policies based on model recommendation poses a challenge. The ability of the models to meet its requirements as a result of early engagement of subject matter experts (SMEs) and testing of new processes via pilot programs is essential.