Search

Research on control of multi-variable system with strong coupling has been a significant issue in industry. To accurately eliminate the coupling between system variables and improve the control effect, decoupling control techniques are investigated. In this paper, a decoupling control scheme based on fractional-order proportion integration differentiation neural network and sparrow search algorithm (SSA-FPIDNN) is proposed, where sparrow search algorithm is employed to derive the optimal initial weights, preventing the weights from falling into the local optimum, while the fractional-order algorithm is used to correct its connection weights to improve control accuracy. Compared with traditional PIDNN, the proposed SSA-FPIDNN has better decoupling control performance, and the tracking time can be reduced significantly. Numerical simulation and engineering examples verified its effectiveness.

Background: Hydraulic quadruped robot is a representative of the redundant transmission. This is a great challenge for multi-joints coordinated movement of the robot, because of the movement coupling with several freedom degrees among kinematic chains. Therefore, there is an urgent need to realize the decoupling among the joints of the hydraulic quadruped robot. Objective: The purpose of this study is to provide an overview of controller design from many studies and patents, and propose a novel controller to realize the decoupling control among joints of a hydraulic quadruped robot. Methods: For the coupling problems between the thigh and calf of a hydraulic quadruped robot, based on the Lagrangian method, dynamics model of the robot’s leg is established. The influence of driven system is considered. The model of the hydraulic servo driven system is built, so as to obtain the coupling relationship between thigh and calf of hydraulic quadruped robot. Based on the multivariable decoupling theory, a PID neural network decoupling controller is designed. Results: The researches on experiments are executed. The PID neural network decoupling control method is compared with the control that does not use any decoupling method. The decoupling effect of the proposed algorithm is verified on the thigh and the calf of the hydraulic quadruped robot. Conclusion: The designed PID neural network decoupling control method reduces the crosscoupling between thigh and calf of the hydraulic quadruped robot, and has obvious effect to improve the dynamic characteristics of single joint of robot's leg.

Control load system is an important equipment of flight simulator. The basic requirement of the controller is that it can control the model force needed for output and good dynamic characteristics. In this paper, the mathematical model of the control load system is studied. In order to solve the problem of poor universality and difficult parameter tuning of the existing control load system, a control algorithm of flight simulator general control load system based on the combination of PID control algorithm and BP neural network is proposed. The algorithm is called PIDNN algorithm. This paper introduces the arithmetic principle and weight updating method of PIDNN, and designs the controller and chooses the parameters according to the PID neural network. The system model is built with MATLAB/SIMULINK and the simulation experiment is carried out. The simulation results show that the controller based on the PIDNN algorithm has excellent performance. Through the control algorithm, the feedback feel of the output is more accurate and more versatile, which frees the developer from the trouble of poor consistency of parameter setting and control quality. It provides a solution for the design of general control load system controller of small aircraft simulator.

This paper proposes a new intelligent control strategy to meet the tracking requirement of the power itself considering the coupling impacts of the plasma cutting technology. The dynamic intense coupling impacts of the technologies can’t be simulated, and a novel style of PID neural network (PID-NN) is applied to obtain closed-loop controller’s reference cutting current via its nonlinear mapping effect. The PID algorithm parameters are self-adjusted through fuzzy logic, whose inputs are both the reference current error and its variation rate. Simulation and testing experiments have verified the greater improvements of this project in steady precision, response speed and robustness, and the controller’s advantage in dealing with discrete events and multivariate decoupling problems.

A decentralized PID neural network (PIDNN) control scheme was proposed to a quadrotor helicopter subjected to wind disturbance. First, the dynamic model that considered the effect of wind disturbance was established via Newton-Euler formalism. For quadrotor helicopter flying at low altitude in actual situation, it was more susceptible to be influenced by the turbulent wind field. Therefore, the turbulent wind field was generated according to Dryden model and taken into consideration as the disturbance source of quadrotor helicopter. Then, a nested loop control approach was proposed for the stabilization and navigation problems of the quadrotor subjected to wind disturbance. A decentralized PIDNN controller was designed for the inner loop to stabilize the attitude angle. A conventional PID controller was used for the outer loop in order to generate the reference path to inner loop. Moreover, the connective weights of the PIDNN were trained on-line by error back-propagation method. Furthermore, the initial connective weights were identified according to the principle of PID control theory and the appropriate learning rate was selected by discrete Lyapunov theory in order to ensure the stability. Finally, the simulation results demonstrate that the controller can effectively resist external wind disturbances, and presents good stability, maneuverability and robustness.

Digital hydraulic component (DHC) has the advantages including strong controllability, high precision and good energy efficiency, it plays an important role in an intelligent mobile machinery, which integrates the functions of interaction, perception, analysis, decision and control. Interactive layer: realizing intelligent data acquisition, transmission and processing, remote supervision, fault warning, life feature identification, VR interaction which brings immersion experience and so on; Sensing layer: using the techniques of SLAM and nonlinear optimization to make intelligent mobile machinery navigate autonomously in the uncertain environment. A high precision environmental map is used to ensure a fine navigation in any uncertain environment. Analysis layer: hierarchical planning strategy, task decomposition, path planning, trajectory planning and trajectory optimization are performed in turn. Combined with AI technology, self-learning and experience summary of operation process and results are given, and applied to guide the next construction operation to realize the pre-compensation of operational bias and improve the accuracy and efficiency of the operation. Decision level: 2 level control structure and PID neural network control strategy are applied to avoid the impact of uncertain factors in the control layer, and realize the intelligent planning and precise control of mobile machinery. Control level: A brief introduction about the development of DHC is given and the work of ZJU in DHC is presented.

The PID neural network controller can make both neural networks and PID control into an organic whole, which has the merit of any PID controller for its simple construction and definite physical meaning of parameters, and also has the self-study and adaptive functions of neural network. The approach to realize neural network control in virtual instrument is researched. Combining virtual instrument technology and PID neural network together organically and adopting LabVIEW to design the module of PID neural network, which will improve performance of the control system and development efficiency.

This paper introduced a “PID-NN” based on Particle Swarm Optimization control that was applied to a boost converter operating in large-signal domains. Simulation results have shown that the proposed “PID-NN controller” could enhance the (boost converter) startup response with the use of fewer on-off switch operations compared to the Conventional “PID controllers”. This result has been of high importance in practice for reducing the number of on-off switches can effectively decrease the transient disturbances and losses due to switching. Simulations also prove that the proposed “PID-NN controller” is capable of efficiently, improving rejecting potential disturbances that could happen in the input voltage. Moreover, it has been noticed that the output voltage is more efficiently controlled when applying “PID-NN controller”. The results of the simulation show the efficiency of the suggested algorithm compared with other well-known learning methods.

The unmanned powered paraglider (UPP) is a nonlinear time-varying dynamic system with high coupling degree. In view of how to make the UPP flying along arbitrary predetermined trajectory, the conventional control method is difficult to obtain the control trajectory with a better fitting degree of the presupposition trajectory. To solve this problem, the six degree of freedom (SDOF)dynamic model of the UPP is built and the control characteristics of the UPP is studied. In view of the control characteristics of the UPP, the controller suitable for the UPP is designed and compiled with the PID neural network method (PIDNN), and the simulation system for the flight process is built, which is used to simulate the flight path control. And the results show that the controller realizes the effective flight path control of the UPP.

The temperature of agricultural film unit affects the plastic film directly. Since unit heating process has the characters of time delay, nonlinear, time-varying and strong coupling. It is difficult to create a mathematical model structure of plastic melting process. Thus, temperature control is very difficult. This paper presents decoupling control strategy and corresponding control algorithm based on PID (proportional-Integral-differential) neural network. Proportional, integral, differential neurons form a three-layer neural network. This design gives full play to respective advantages of PID control and neural network, and takes advantage of BP neural network to establish the dynamic model of system.

The Phase shifted Full-bridge Zero-voltage Zero-current-switching Pulse-Width Modulation (PS-FB-ZVZCS-PWM) converter is discussed in this paper and the PID neural network is used to be the dual loop controller of the system. The results of the simulation prove that the PID neural network double close loop system has achieved the nice control characteristics which are no overshoot, no static error, fast response, short transition time, good tracking performance.

A decentralized proportional-integral-derivative neural network (PIDNN) control scheme is proposed to regulate and stabilize a fully suspended five degree-of-freedom (DOF) active magnetic bearing (AMB) system which is composed of two radial AMBs (RAMBs) and one thrust AMB (TAMB). First, the structure and operating principles of the five-DOF AMB system are introduced. Then, the adopted differential driving mode (DDM) for the drive system of the AMB is analyzed. Moreover, due to the exact dynamic model of the five-DOF AMB system is vague, a decentralized PIDNN controller is proposed to control the five-axes of the rotor simultaneously in order to confront the uncertainties including inherent nonlinearities and external disturbances effectively. Furthermore, the connective weights of the PIDNN are trained on-line and the convergence analysis of the regulating error is provided using a discrete-type Lyapunov function. Based on the decentralized concepts, the computational burden is reduced and the controller design is simplified. Finally, the experimental results show that the proposed control scheme provides good control performances and robustness for controlling the fully suspended five-DOF AMB system in different operating conditions.

According to the time delay in industrial control objects, the PID neural network control method and Smith predictor compensation principle are combined to form the PIDNN-Smith control algorithm. Namely, in Smith predictor compensation control system, the PIDNN as the controller, using the PIDNN neural network on-line self-learning function to tune weight value, make the implicit layers of proportion, integral and differential neurons to achieve the best combination, thus overcome disadvantages of the conventional PID algorithm that does not adapt to the control of large delay system and conventional Smith algorithm depended too much on model precision of the defect. Simulation results show strong robustness and good control quality of this algorithm.

In this paper, traditional PID neural network (PIDNN) control theory was introduced and the characteristics and disadvantages of the algorithm was been analysis. An improvement PIDNN method based on multi-innovation theory was proposed. Then the steward tracking control system was simulated, some planning trace was given out and the math model of the control system was established. The result showed that the improvement algorithm is effect.

Aiming at the shortages of traditional PID controller, and problems of hardly setting the controller parameters, and the setting time is long, this paragraph gives a design of ACA-BP arithmetic based controller of PID Neural Network. First, uses the Ant Colony algorithm to thickly select the PID neuron network weight parameter. Then adjust parameters online by PID Neural Network and BP algorithm. Finally, we can obtain optimal parameters. The simulation result shows, compared with traditional PID controller, this controller has greatly improved its control performances. This would have some theoretical and practical significance.

A mathematical model of engine throttle as the controlled object is established and then the neural network algorithms and PID control are combined. With the self -learning function of the neural network, self -tunings of PID parameters are realized. The method overcomes disadvantages of PID as parameters which are difficult to determine and embodies better intelligence and robustness of the neural network, the simulation is researched by Matlab and the results show that the PID neural network controller is more accurate and adaptive than conventional PID.

Theoretical models of hydraulic pump-motor and electro-hydraulic servo control systems of hydraulic pumps were established and the system transfer function was derived In view of bad dynamic property, small damp, long transient time, low precision, nonlinearity and etc existing in the speed control system of Hydraulic Pump-Motor, a controller based on PID Neural Network was designed. The simulation results showed that the PID Neural Network controller has better dynamic property, load disturbance adaptability , robustness and cranking ability than traditional PID controller.

This paper introduces the general temperature data processing procedure which stems from the thermocouple.On the base of summing up exsiting methods,the problem is detailed studied on how to select the special points of thermocouple.And a system is designed to collecting multichannel temperature data.By means of analysing the data,the mathematical model of thermocouple is founded. Proved by experiments, this method increases the temperature measurement precision and fits to actual request,which is wide rang with high pricise.

In view of the serious misalignment, the mathematical model's uncertainty, the characteristic of the system operating point changing fiercely of the heating furnace temperature control system, this paper designed a new type of intelligent control system - PID neural network system (PIDNN) which melt the PID control rule in the neural network. This system has the quick reasoning speed and the strong anti-interference ability.

Because it is difficult for the traditional PID algorithm for nonlinear time-variant control objects to obtain satisfactory control results, this paper studies a neuron PID controller. The neuron PID controller makes use of neuron self-learning ability, complies with certain optimum indicators, and automatically adjusts the parameters of the PID controller and makes them adapt to changes in the controlled object and the input reference signals. The PID controller is used to control a nonlinear time-variant membrane structure inflation system. Results show that the neural network PID controller can adapt to the changes in system structure parameters and fast track the changes in the input signal with high control precision.

In order to overcome the system nonlinear instability and uncertainty inherent in magnetic bearing systems, two PID neural network controllers (BP-based and GA-based) are designed and trained to emulate the operation of a complete system. Through the theoretical deduction and simulation results, the principles for the parameters choice of two neural network controllers are given. The feasibility of using the neural network to control nonlinear magnetic bearing systems with un-known dynamics is demonstrated. The robust performance and reinforcement learning capability in controlling magnetic bearing systems are compared between two PID neural network controllers.

In this paper, a novel adaptive tuning method of PID neural network (PIDNN) controller for nonlinear process is proposed. The presented method utilizes an improved gradient descent method to adjust PIDNN parameters where the margin stability will be employed to get high tracking performance and robustness with regard to external load disturbance and parameter variation. Simulation results show the effectiveness of the proposed algorithm compared with other well-known learning methods.