An improved Adam Algorithm for BP neural network feedforward compensation control

Similar to many complex systems, the operation process of electric balanced forklifts has characteristics such as time-varying model parameters and nonlinearity. Establishing an accurate mathematical model becomes challenging, making it difficult to apply model-based control methods in engineering practice. Aiming at the longitudinal control system of electric forklifts containing external disturbances, this paper proposes an improved full-format dynamic linearization model-free adaptive PID control (iFFDL-MFA-PID) method. Firstly, the full-format dynamic linearization (FFDL) method is employed to transform the operating system of the electric balanced forklift into a virtual equivalent linear data model. Secondly, the nonlinear residual term and pseudo-gradient (PG) of the data model are estimated using the difference estimation algorithm and the optimal criterion function, respectively. Furthermore, in order to enhance the robustness of the system, the idea of intelligent PID (iPID) is introduced and the principle of equivalent feedback is utilized to derive the iFFDL-MFA-PID control scheme. The design process of this scheme only requires the use of the input and output data of the system, without relying on the mathematical model of the system. Finally, the iFFDL-MFA-PID method proposed in this paper is simulated and tested with the EFG-BC/320 counterbalanced forklift equipped in the Special Equipment Testing Center and compared with the model-free adaptive control method (FFDL-MFAC) and the PID control method. Simulation results show that the speed-tracking error of the electric forklift truck under the action of the iFFDL-MFA-PID algorithm is maintained within ±0.132 m/s throughout the process, achieving higher tracking accuracy and better robustness compared to the MFAC and PID methods.

The hover, transition, and fixed-wing modes are the three flight configurations available for the tilt tri-rotor unmanned aerial vehicle (UAV). . PID and SMC controllers were commonly used to build flight controllers to help realize stable flight for this UAV. The PID control method has the ability to adjust the error as low as possible, increase the response speed, reduce the overshoot, and limit the oscillation. The outstanding advantage of the sliding controller is its stability and stability even when the system has noise or when the object's parameters change over time. This paper will build flight control including attitude control, and position control for the Tilt tri-rotor model in hover mode based on PID control and SMC to evaluate their performance. First, the kinematic equations of Tilt tri-rotor UAV are built based on coordinate systems and Newton's laws. Secondly, two control diagrams and built two flight controllers based on PID and SMC control methods are investigated. Finally, the simulation results of these two methods are shown and discussed. The results show that the SMC controllers give better stability and better orbital tracking in both cases of noise and no noise.

Due to improper selection of gradient update direction or learning rate, SGD optimization algorithms for deep learning suffer from oscillation and slow convergence. Although Adam algorithm can adaptively adjust the update direction and learning rate at the same time, it still has the overshoot phenomenon, and hence suffers from wasting computing resources and slow convergence. In this work, the PID controller from the feedback control area is borrowed to re‐express the adaptive optimization algorithm (the Adam optimization algorithm is derived into the integral I component form) of deep learning. In order to alleviate the overshoot phenomenon and hence speed up the convergence of Adam, a complete adaptive PID optimizer (adaptive‐PID) is proposed by incorporating the proportional P and derivative D component. Extensive experiments on standard data sets verify that the proposed adaptive‐PID algorithm significantly outperforms Adam algorithm in terms of convergence rate and accuracy.

The electro-hydraulic proportional position servo system is a kind of highly non-linear and time-varying system as well as parameter uncertainties. It is often difficult to achieve satisfactory control results with the traditional control methods. Considering that the adaptive neural network PID control method has the characteristics of online learning and adjustment PID control parameters adaptively, this paper puts forward to adopt BP-PID control method for the position servo control of electro-hydraulic proportional system. An online adaptive BP-PID controller is designed. The simulation model of the system is established based on Simulink platform. The step response and Sinusoidal tracking characteristics are researched for electro-hydraulic proportional position servo system by using traditional PID and BP-PID control algorithms through simulations and experiments. The results show that BP-PID has a strong ability of online learning and self-tuning PID parameters. Compared with the traditional PID control method, the BP-PID control has strong self-adaptability and robustness, and can significantly improve the step response speed and tracking control precision.

VAV (VAV) air-conditioning systems always have the characteristics of nonlinear, strong coupling, large time delay, thus the conventional PID control method can't meet the requirement of control performance. In order to adapt to the changes of the load in air-conditioning systems, and make an accurate rapid response, this paper proposes a fuzzy adaptive PID control method. The temperature control by terminal air valves in VAV air-conditioning systems was selected as a control object, through collecting the deviation between setting value and room temperature, the parameters of the PID controller were selected to realize the accurate control of the temperature. In order to evaluate the effectiveness of the proposed control method, it was compared with conventional PID control method by simulation experiment, the results show that the proposed Fuzzy adaptive PID control method has more shorter setting time, less overshoot and more steady state performance than the latter.

In a controller design process, it is interesting to find the inverse model, in which the desired input signal of the system is determined by using a desired output of the system. In many cases, the inverse model problem is very difficult, and sometimes impossible to determine and implement. There are some methods to make an inverse dynamic model, such as computed torque control, which had been studied in the previous Chapters. The capability of the NNs to learn the inverse model of the plant has been investigated for many years; the NN can be used to learn an approximate inverse system. In this approach, the desired output of the dynamic system should be known, and the NN can be trained by the desired output of the dynamic system to obtain the inverse dynamic model. In early studies of adaptive learning control using an NN model, Barto et al. [1], Jordan [2], Miller et al. [3] and Psaltis et al. [4] addressed the problem of how to obtain the error signal for training the NN controller. Generally, the cost function, consisting of the squared norm of the output reference errors, can not correctly train the NN controller as an inverse dynamic model. Therefore, Jordan [2] proposed a forward-inverse-modeling, and Albus [5], Atkeson and Reinkensmeyer [6], Psaltis et al. [4], and Kuperstein and Rubinstein [7] used a direct-inverse-modeling to obtain the command-error for forming the inverse dynamic model as a feedforward controller. Moreover, Watanabe et al. [8] proposed a linear NN using feedforward NNs with two layers and a linear unit function in the output-layer. Kawato [9] proposed a learning method to obtain a feedforward controller, which uses the output of a feedback controller as the error for training an NN model. The conventional feedback controller is configured in parallel to the NN controller, in the same manner as reported by Gomi and Kawato [10], and Miyamoto et al. [11], but with a different SF and learning algorithm. In another work, Wada and Kawato [12] used a feedforward NN as an inverse dynamic model.

Motion control is an important part of the robot system in the MiroSot soccer robot system. At present, PID control method and fuzzy logic control method are commonly used. Due to the lag of image acquisition and the imprecision of image recognition, the motion of the robot is nonlinear and uncertain, and the traditional PID controller can not achieve excellent control effect. This paper proposes a motion control method of soccer robot based on fuzzy-PID control, in which the fuzzy control is adopted to ensure the control speed, while the PID control to ensure the control accuracy. The simulation and experiment prove that the improved motion control method has excellent reliability and effectiveness.

In this paper, a control method was designed based on particle swarm optimization (PSO)–fuzzy PID (PSO-Fuzzy PID). In order to address the issues of significant nonlinearity and extensive hysteresis in the vapor temperature of litchi hot vapor preservation treatment equipment, as well as the inadequacy of traditional control schemes, a PSO-Fuzzy PID controller was developed through the integration of particle swarm optimization and fuzzy logic algorithms. This controller incorporates a scale factor and quantization factor, building upon the foundation of the Fuzzy PID controller. Additionally, a transfer function model was established for both the heating and disturbance links, utilizing a combination of test data modeling methods and relevant theory. Thirdly, a system simulation model was built to compare and verify PID, Fuzzy PID, and PSO-Fuzzy PID control methods, which were carried out on the MATLAB/Simulink simulation platform. Finally, the litchi load test was conducted to further verify the control performance of the PSO-Fuzzy PID method, where the litchi variety was “Jinggang Hongnuo”. The simulation results showed that the overshoot of the optimized control system was reduced by 93.5% and 42.9% compared with the traditional PID control and Fuzzy PID, and the regulation time was shortened by 46% and 31%, which indicates a better control effect. The test results showed that PSO-Fuzzy PID showed better system stability and accuracy than the fuzzy PID control method in different processing temperature and processing time for litchi’s hot vapor treatment. The maximum temperature difference decreased by 0.56 °C on average and the interference adjustment time was reduced by 7.5 s on average. PSO-Fuzzy PID has a good control effect on the temperature of litchi hot vapor treatment, which can provide a reference for model building and temperature control of other similar fruit and vegetable heat treatment equipment.

A novel control scheme based on an improved RBF neural network and PID control method is proposed. When used the RBF network in the PID controller, if RBF network provides the parameter to revise PID while it does not have training finished, the controller will oscillated or even to diverge. As the structure is more complex, and the adjustment speed is slower, the improvements are made to the standard RBF neural network trained algorithm. Uses the matrix operation substitute the iterative algorithm, may avoid the above question effectively. Finally, choosing a certain type of PID controller, the improved RBF neural network algorithm is used to design the control law for control command tracking, the simulation results show that the improved RBF neural network algorithm can avoid oscillated and diverge.

In satellite attitude control algorithms, PID control is often used in engineering practice due to its simple, effective, stable and reliable characteristics. However, PID parameter tuning requires manual adjustment based on experience or a large number of experiments, which has a low efficiency. BP neural network is an intelligent algorithm based on the gradient descent method in the optimization theory, which can approximate any nonlinear function. This paper first establishes the satellite dynamic model under the ideal rigid body, then combines BP neural network with PID and applies it to satellite attitude control, where BP neural network's error back propagation characteristic is used to autonomously adjust the PID parameters, which improves the efficiency. The simulation shows that the step length has a great impact on the results of the control system, so it is necessary to select an appropriate step length for a specific task.

The performance of active suspension systems is directly related to the mechanical design and control of the system. The stable operation of the controller improves driving comfort and handling. The quarter car model is frequently used in the analysis of suspension systems due to its simple structure. In this study, Matlab Simulink software was used in the modeling, control and simulation of the quarter car active suspension model. System performance was investigated for four different road profiles with PID and fuzzy logic control methods. Two of the road profiles used are in the form of impact signals consisting of pits and bumps. The other two road profiles are random road disturbances with high frequency. The effects of active and passive suspension systems on driving comfort are compared by taking into account the control methods used. As a result of the study, it has been determined that the fuzzy logic controller gives better results in pulse signals consisting of bumps and pits, and the PID controller gives better results in high-frequency random road disturbances. In addition, with the use of fuzzy logic control method in the active suspension system, a significant decrease in the actuator force has occurred. This result is very interesting in terms of minimizing energy, reducing actuator sizes and reducing costs.

Aiming at the problem that drilling parameters are difficult to adjust in time for the driller due to the complex geological environment in underground coal mines, a drilling parameter control method based on online identification of drillability and multi-objective optimization of drilling parameters is proposed. A drillability grade identification model is established, with rotational speed and torque as input parameters, which can accurately identify the current drilling state. A multi-objective optimization model of the optimal drilling parameters is established with the mechanical specific energy and drilling speed prediction model as the objective functions, and the NSGA-II algorithm and TOPSIS algorithm are used for solutions and decision-making. A fuzzy PID controller is established. For the control of rotational speed parameters and drilling pressure parameters, the advantages and disadvantages of the fuzzy PID control method and the traditional PID control method are compared through simulation and experiments. A control method based on the drillability identification model and the multi-objective optimization model is established. According to the different drillability grades, the drilling parameters are adjusted in time to ensure the normal drilling state. By constantly approaching the optimal parameters through the drilling parameters, the drilling efficiency is improved. Through experimental verification, this control method effectively prevents the occurrence of drilling speed reduction and intermittent sticking and can adjust the drilling parameters to continuously optimize.

The aim of this paper is to propose a neural network based reference modified PID control which has a simple duration design method for transient characteristics improvement of digitally controlled dc-dc converters. In renewable energy network systems, various types of dc-dc converters are widely used for power conversion and such converters require a superior control method for a stable operation. Especially, transient characteristics should be improved since they heavily affect the stability of the system. For such purposes, designing of conventional control methods becomes a difficult task since the optimization of control parameters needs complicated analysis and it is affected from variations of circuit components of converters. Therefore, simple and easy design of control is widely required for a stable operation of power converters. The neural network can provide a suitable control methodology for such situation since it treats the plant as a black box and it can realize a non-linear control based on training of the input-output relation without complicated modelling and analysis. On the other hand, the neural network based method has a disadvantage caused from the fact that the neural network is trained with data obtained in advance and an overcompensation phenomenon occurs in the transient response. In this paper, the neural network control is adopted to control the dc-dc converter in coordination with a conventional PID control. The neural network predicts the output voltage of the converter and the reference value in the PID control is modified with the predictions to reduce the error of the output voltage. To avoid overcompensation, a simple duration design for the neural network control is also provided to improve the transient response effectively. From prototype testing in simulation and experiment, it is revealed that the proposed method contributes to obtain a superior transient performance compared with the conventional PID control.

This paper puts forward a novel design method of controller based on BP neural network, which is applied to the permanent magnet synchronous motor (PMSM) double closed loop speed regulation system of speed regulator, by using the neural network controller instead of traditional PID controller. It applies the nonlinear adaptive ability of neural network for optimizing the control parameters of PID controller for PMSM. The simulation model was established in Matlab/Simulink. The simulation results indicate that the neutral network PID controller, compared with the traditional PID, has strong robustness and adaptive ability to the model and environments, indicating the good dynamic and static characteristics and control effects.

An ALQR (Adaptive Linear Quadratic Regulation) method for the variable speed wind turbines system is proposed in this paper. The controller is designed for the wind turbine operating in the low wind speed (Region 2), in which the pitch of the blades is fixed at the optimal angle. Since the wind turbine is a nonlinear system, the Kalman filter and the adaptive method are implemented in the controller to make the LQR compatible with the nonlinear system. The proposed control scheme is compared in the simulation with several commonly used control methods, i.e. look-up table, PID control and gain-scheduling method. The step changed wind speed profile and the turbulent wind speed profile are adopted for the tests. The results of the simulations show that the proposed ALQR method is much better than the conventional methods.