The power generation sector has been challenged by trends in digitalization, growth of intermittent renewables, equipment performance improvements, new generation, and storage technologies. Digitalization is a broad concept that can be used as a tool to achieve multiple goals in this new scenario where performance and availability are critical.
Operators are responsible not just for maximizing performance, but also for safety, asset management, and other technical and strategical aspects. Considering these multiple goals and the multiple ways to operate a power plant, advisory systems are tools that help to optimize the decision-making process. An advisory system displays suggested best conditions, and then the operator can decide whether or not to proceed. This approach enables long-term reliability testing and certification process of operating rules that can be automated to optimize the efficiency of the plant.
Based on its extensive experience, applying different methodologies of engineering modeling and software development to provide plant optimization solutions, Radix has developed X!Power - a digital platform to enable an intelligent and efficient way to operate power plants. Combining real-time data with first principal equation models, the platform has already brought significant savings on the operation costs of power plants.
X!Power - The Energy Management System for Power Plant is designed to operate the plant at maximum efficiency and also to provide a clearer picture of the status of the process.
To support the operation, the first step is to centralize the information from multiple data sources using PI System, including plant equipment, power meters, field flow meters, and fuel price information. These data allow the calculation of the main KPIs related to the operating costs and energy efficiency of the plant and are performed by PI AF. Since the power plant can be operated in multiple ways, displaying the data is not enough. To address that problem, a decision tree methodology is used, with a rules engine based on the results of offline thermodynamic simulations, to achieve the most efficient operating conditions to the plant. The overall methodology combines an engineering assessment, based on the simulations, with the development of an operational intelligence system. The optimization model combines: (1) an approach that could indicate the best operational configuration considering multiple scenarios and (2) a real-time model considering all main equipment linked. The solution is an online decision tree that stores hundreds of scenarios simulated offline under distinct configurations and notifies the operators by using Event Frames, reducing the engineering team’s response time. During real-time operation, the application analyzes the online variables and indicates the best configuration to operate.
The system consolidates several data sources that feed the optimization and efficiency models, forecasts, and key performance indicators that are displayed and accessed in the PI Vision dashboards. PI Vision provides, among other advantages, a better event data visualization (including a comparison of events), availability on mobile platforms, better user interface, and usability.