论文部分内容阅读
为进一步提高电力系统在各种不同大小扰动下的静态稳定性和暂态稳定性,提出了一种模糊神经网络参数在线自校正稳定器的控制策略。该方案是在原有常规模糊稳定器的基础上,增加了一个模糊神经网络参数在线调整器。该调整器将定性的知识表达和定量的数值运算相结合,把模糊推理规则存储于神经元中,充分利用了神经网络联想记忆和大规模并行处理的功能,在线、快速、动态地调整常规模糊稳定器的量化因子和比例因子等参数。通过实验证明,与IEEE PSS2B和常规模糊稳定器相比,提出的控制策略能有效地增加电力系统的阻尼,加强系统承受各类不同大小扰动的能力,具有较强适应性和鲁棒性,较大地提高了电力系统的静态稳定性和暂态稳定性。该控制方法具有较为广阔的工业应用前景。
In order to further improve the static and transient stability of the power system under various disturbances, a control strategy based on fuzzy neural network parameters on-line self-tuning stabilizer is proposed. The program is based on the original conventional fuzzy stabilizer, an increase of a fuzzy neural network parameter online regulator. The regulator combines qualitative knowledge expression with quantitative numerical operation, and stores fuzzy inference rules in neurons. It makes full use of the function of neural network associative memory and large-scale parallel processing to adjust the conventional fuzzy online, fast and dynamically Stabilizer quantization and scaling factors and other parameters. Experiments show that compared with IEEE PSS2B and conventional fuzzy stabilizer, the proposed control strategy can effectively increase the damping of the power system, strengthen the ability of the system to withstand various types of disturbance of different sizes, and has strong adaptability and robustness. The earth improves the static and transient stability of the power system. The control method has a broader industrial application prospects.