科教文汇
科教文彙
과교문회
EDUCATION SCIENCE & CULTURE MAGAZINE
2012年
9期
97-99
,共3页
主汽温%PID%BP神经网络%MATLAB仿真
主汽溫%PID%BP神經網絡%MATLAB倣真
주기온%PID%BP신경망락%MATLAB방진
main stream temperature%PID%BP neural network%MATLAB simulation
电厂主汽温被控对象是一个大惯性、大迟延、非线性且对象变化的系统,基于BP神经网络的PID控制,利用神经网络的自学习、非线性和不依赖模型等特性实现PID参数的在线自整定,充分利用PID和神经网络的优点。用一个多层前向神经网络,采用反向传播算法,依据控制要求实时输出Kp、Ki、Kd,依次作为PID控制器的实时参数,代替传统PID参数靠经验的人工整定和工程整定,以达到对大迟延主汽温系统的良好控制。对这样一个系统在MATLAB平台上进行仿真研究,仿真结果表明基于BP神经网络的自整定PID控制具有良好的自适应能力和自学习能力,对大迟延和变对象的系统可取得良好的控制效果。
電廠主汽溫被控對象是一箇大慣性、大遲延、非線性且對象變化的繫統,基于BP神經網絡的PID控製,利用神經網絡的自學習、非線性和不依賴模型等特性實現PID參數的在線自整定,充分利用PID和神經網絡的優點。用一箇多層前嚮神經網絡,採用反嚮傳播算法,依據控製要求實時輸齣Kp、Ki、Kd,依次作為PID控製器的實時參數,代替傳統PID參數靠經驗的人工整定和工程整定,以達到對大遲延主汽溫繫統的良好控製。對這樣一箇繫統在MATLAB平檯上進行倣真研究,倣真結果錶明基于BP神經網絡的自整定PID控製具有良好的自適應能力和自學習能力,對大遲延和變對象的繫統可取得良好的控製效果。
전엄주기온피공대상시일개대관성、대지연、비선성차대상변화적계통,기우BP신경망락적PID공제,이용신경망락적자학습、비선성화불의뢰모형등특성실현PID삼수적재선자정정,충분이용PID화신경망락적우점。용일개다층전향신경망락,채용반향전파산법,의거공제요구실시수출Kp、Ki、Kd,의차작위PID공제기적실시삼수,대체전통PID삼수고경험적인공정정화공정정정,이체도대대지연주기온계통적량호공제。대저양일개계통재MATLAB평태상진행방진연구,방진결과표명기우BP신경망락적자정정PID공제구유량호적자괄응능력화자학습능력,대대지연화변대상적계통가취득량호적공제효과。
The system of power plant main steam temperature is a large inertia,big time-delayed and nonlinear dynamic system. PID control based BP neural network.Using such characteristics of neural network self-learning, nonlinear and don't rely on too- del realize PID parameters auto-tuning.It can make full use of the advantages of PID and neural network.Here,we use a muh- ilayer feed forward neural network using back propagation alg- orithm. This net can real-time output Kp, Ki, Kd as the PID controller parameters, instead of the traditional PID parameters determined by experience,so it can obtain good control perfor- mance.For such a system,we can simulate in MATLAB simula- tion platform.The simulation results show that the PID control based BP neural network has good adaptive ability and self- learning ability.For the system of large delay and free-model can obtain good control effect.
