Guolian Hou

Operation and maintenance (O&M) costs account for a substantial share of offshore wind expenditures. However, maintenance optimization models for offshore wind turbines (OWTs) typically rely on idealized states, neglecting stochastic environmental shocks and spatiotemporal dependencies. To bridge this gap, a dynamic optimization framework for intelligent maintenance of OWTs with competing failure modes is proposed. The objective of optimal scheduling is to maximize wind energy profit and reduce maintenance costs. This problem is formulated as a mixed-integer programming model that explicitly characterizes uncertainties in operational revenue and turbine lifespan. Additionally, the objective function integrates time discounting and penalty factors to quantify expected profits and maintenance expenditures accurately. Then, a novel daily rolling optimization algorithm is designed to dynamically update O&M decisions. In the framework, the spatiotemporal dependencies among OWTs are captured to refine assessment of power losses. And a reliability function considering degradation-induced and shock-induced competing failures is derived. Case studies on two real-world offshore wind farms demonstrate the superior performance and robustness of the proposed method.

To smooth out the power fluctuations caused by the large-scale integration of new energy into the power grid, it is necessary to enhance the rapid load variation capacity of the combined heat and power (CHP) unit. Based on this, an advanced strategy combining deep deterministic policy gradient (DDPG) and error-based active disturbance rejection control (EADRC) is proposed to achieve flexible operation of the CHP unit integrated with absorption heat pump (AHP). First, a new coordinated control system (CCS) is designed to achieve heat-power decoupling by flexibly adjusting the heating valve and the heat pump regulating valve. The decoupled system can balance stable heating and power peak shaving, significantly improving the variable load rate of the unit. Second, a hierarchical control framework is proposed to achieve the optimal control of the CHP unit integrated with AHP. The EADRC estimates and compensates for the total system disturbance through an extended state observer to obtain the initial control law. The DDPG forms a compensation control law via online weight learning, enhancing the robustness of EADRC against uncertainty and disturbances. Finally, the hierarchical DDPG–EADRC strategy is applied to the 350 MW CHP unit integrated with AHP, and the effectiveness of the proposed scheme is evaluated in set value tracking, disturbance rejection, and model mismatch tests. The experimental results show that in the set value tracking test scenario, the settling time of the proposed strategy is reduced by 862 s compared to the traditional CCS, and the maximum overshoot is reduced by 3.74 MW.

Deep and rapid peak shaving requirements of thermal power unit are becoming more significant in the low-carbon power system consisting of high-proportion renewable energy sources. In order to meet these requirements, this article proposes an improved Mamba-2-based intelligent modeling method to obtain the precise deep peak shaving process model of thermal power-molten salt heat storage coupled system. Based on the state space duality, the Mamba-2 shows great prediction accuracy and speed in dealing with the multiple long-time sequences. To efficiently model the wide-range and rapidly changing deep peak shaving sequences, the context learning capacity, computational efficiency and convergence speed of Mamba-2 must be improved. First, the sparse attention mechanism that can selectively process some of the tokens is established to promote the modeling precision of Mamba-2. Moreover, the novel least-squares interpolation (Lion) optimizer is successfully utilized to accelerate the training process in Mamba-2 for the first time. Then, both the inputs and outputs sequences inside Mamba-2 are normalized to facilitate the modeling accuracy improvement of thermal power-molten salt heat storage coupled system. The improved Mamba-2 with stable state space model, prominent modeling precision and speed effectively provides guarantee for the deep peak shaving of unit. Finally, the superior model accuracy of the proposed intelligent modeling method is verified based on the on-site deep peak shaving sequences of 660 MW thermal power unit and 40 MW molten salt heat storage system.

With the wide application of renewable energy sources in power system, the advantages of flexible combined heat and power (CHP) unit on the stable generation are becoming prominent. In order to fully explore the operational flexibility of CHP unit to provide flexible load services, a practical hierarchical model predictive control (HMPC) approach is proposed in this article. First, to facilitate the CHP unit response to variable load demand, the advanced HMPC algorithm integrating the multiobjective model predictive control (MPC)-based guidance layer and reinforcement learning (RL) agent-based optimization layer is designed. Then, the initial control law reaching the Pareto optimization between the carbon emission and generation cost is attained in the guidance layer. As the control law is employed to accelerate the training of underlying RL agent, the economic and flexible load services can be provided by the unit. Moreover, with the continuous learning feature of RL agent, the control law is adjusted in real time to match the load demand uncertainties and model perturbations. Finally, the economic and flexible load services are successfully offered in wide load range by 350 MW CHP unit combined with the proposed HMPC algorithm. Especially, both the energy-saving and carbon trading indices of CHP unit have been improved at low-rated load, which confirms the effectiveness of the proposed HMPC approach.

PID control is the longest history and the most vital basic control mode that has been widely applied in the production process. The oscillatory dynamics of the process have various features, and parameter tuning is complicated. To reduce the complexity of the parameter tuning process and improve the performance of the system, in this research, we propose a new tuning method for the PID/PIDD2 controllers for second-order oscillatory systems with time delays under the constraint of certain robustness. In comparison to existing PID for second-order oscillatory systems with time delays, simulation findings demonstrate that the tuning method of the proposed PID/PIDD2 controllers trades off robustness and disturbance rejection performance.

The pitch control system has a profound impact on the development of wind energy, and yet a delay or non-minimum phase can weaken its performance. Thus, there is a strong incentive to enhance pitch control technology in order to counteract the negative effects of unidentified delays and non-minimum phase characteristics. To reduce the complexity of the parameter-tuning process and improve the performance of the system, in this paper, we propose a novel control method for wind turbine pitch angle with time delays. Specifically, the proposed control method is state-space PIDD2, which is based on internal model control (IMC) and the open-loop system step response. Then, considering the tracking, disturbance rejection and measurement noise, the proposed controller is verified through simulations. The simulation results demonstrate that the state-space PIDD2 (SS-PIDD2) can provide a trade-off between robustness, time domain performance and measurement noise attenuation and effectively improve pitch control performance in contrast to series PID and PI control methods.

In order to reduce the high built-in test (BIT) false alarms of analog circuits caused by intermittent faults, a BIT-based intermittent fault diagnosis method for analog circuits by improved deep forest (DF) classifier is proposed. First, the local mean decomposition and multiscale entropy (LMD-MSE) are employed for multiscale time–frequency analysis since it can handle the data nonlinearity and eliminate redundant information. Second, the particle swarm optimization (PSO) algorithm is adopted in optimizing the multiscale factors to form the feature sets. Then, the feature sets are used to train the DF classifier and the intermittent faults of the analog circuits are diagnosed by the classifier. Meanwhile, in order to improve the diagnostic accuracy of the DF classifier for intermittent faults, the classifiers of each level of DF are replaced by extreme random forests and rotation forests. The optimized characteristic of DF improves the diagnosis accuracy and can locate the intermittent faults to the circuit branch with intermittent faults. The method is evaluated with the four-opamp biquad high-pass filter circuit. Compared with other common methods, it is shown by the given extensive comparative experiment test results that the proposed approach has achieved better diagnostic results, exhibiting greater advantages in intermittent fault diagnosis with small sample data.