IEEE TRANSACTIONS ON ENERGY CONVERSION, VOL. 23, NO. 2, JUNE 2008 651 Clustering-Based Performance Optimization of the Boiler–Turbine System Andrew Kusiak, Member, IEEE, and Zhe Song Abstract—In this paper, two optimization models for improve- ment of the boiler–turbine system performance are formulated. The models are constructed using a data-mining approach. His- torical process data is clustered and the discovered patterns are selected for performance improvement of the boiler–turbine sys- tem. The first model optimizes a widely used performance index, the unit heat rate. The second model minimizes the total fuel con- sumption while meeting the electricity demand. The strengths and weaknesses of the two models are discussed. An industrial case study illustrates the concepts presented in the paper. Index Terms—Boiler–turbine system, clustering, data mining, performance optimization. I. INTRODUCTION I MPROVING performance of a boiler–turbine unit is of in- terest to the energy industry due to increasing fuel costs. The system performance depends on the accuracy of models and the selected performance metrics. Performance optimization of a boiler–turbine system is usu- ally considered in two phases. The first is the design and imple- mentation of a control system before the power plant becomes operational. The second is the use of the performance test code [e.g., American Society of Mechanical Engineers (ASME) per- formance test code] to periodically evaluate the system perfor- mance to update the operating parameters (set points) of the controllers. Kuprianov [13] discussed different objective func- tions to improve boiler thermal efficiency and reduce emissions based on certain test codes (or “a test code”). Farhad et al. [10] demonstrated the use of the ASME performance test code in reducing fuel and energy consumption. Numerous modeling approaches of boiler–turbine systems have focused on using the first principle, e.g., thermodynam- ics. Researchers applied energy and material balance, material flow, and chemistry to derive models in the form of differential equations. Typical benchmark nonlinear models of boilers and turbines can be found in [2], [3], [8], and [22]. Ben-Abdennour and Lee [5] reported test results of a fuzzy fault accommo- dation controller. Moon and Lee [20] presented a fuzzy con- troller that can update the fuzzy rules adaptively by a simple set-point error-checking process. Espinosa et al. [9] applied fuzzy logic to identify the boiler–turbine system and imple- mented it to reduce overshooting and settling time. Yu and Manuscript received July 20, 2006; revised October 29, 2007. This work was supported in part by the Iowa Energy Center under Grant IEC 04-06. Paper no. TEC-00362-2006. The authors are with the Intelligent Systems Laboratory, Department of Me- chanical and Industrial Engineering, The University of Iowa, Iowa City, IA 52242-1527 USA (e-mail: andrew-kusiak@uiowa.edu; zhe-song@uiowa.edu). Digital Object Identifier 10.1109/TEC.2007.914183 Xu [31] discussed the feasibility and efficacy of applying a feedback linearization technique to a nonlinear boiler–turbine model for control of steam pressure and electricity output. Tan et al. [28] attempted to determine control settings where dis- tances between the nonlinear system and its corresponding lin- earization model were minimal; thus, the linear controller’s per- formance was guaranteed. Other applications of boiler–turbine control can be found in [17], [18], and [23]. The results published in the literature are not based on benchmark nonlinear boiler–turbine models. Fuzzy logic and autotuning techniques were used by [17]. A model predictive control approach [24] was illustrated in the papers by [18] and [23]. Such a technique generally uses an accurate model to predict the system behavior based on the changing inputs, and calls for the continuous solving of a quadratic programming optimization problem. Although the literature reports progress in controlling boiler– turbine systems, the existing approaches usually are expensive to implement due to uncertainty involved in operating such sys- tems. System errors accumulate due to the assumptions made in modeling. Also, control systems are usually designed to ensure system stability and fast response. System performance met- rics, e.g., fuel consumption, are usually not well integrated in the control system. The performance test code is widely used to monitor performance; however, it involves a number of con- stants that are difficult to obtain, which may cause unreliable test results. The research reported in this paper focuses on metacontrol of a single boiler–turbine unit to reduce fuel consumption while satisfying megawatt load constraints. The economic and emis- sion aspects are not considered in this paper. They can be inte- grated into the load dispatch optimization models [1]. However, the approach presented in this paper is general, and it allows for solving models with a variety of objectives and constraints. It is obvious that controllers do not fully capture the boiler–turbine system dynamics due to process changes, e.g., boiler aging. Opportunities exist to adjust (bias) controllable parameters to improve performance. A data-driven approach is proposed to generate control settings to improve the performance of the boiler–turbine system. II. OPTIMIZATION MODELS AND PERFORMANCE METRICS A. Performance Criteria Before the optimization models are presented, three perfor- mance metrics are discussed. A performance criterion directly impacts the optimization result. A widely used metric for boiler– turbine unit (steam turbine) performance is the unit heat rate 0885-8969/$25.00 © 2008 IEEE