Output Control Research Articles

Security-Guaranteed PID Control for Discrete-Time Systems Subject to Periodic Dos Attacks

This paper is concerned with the observer-based H∞ proportional-integral-derivative (PID) control issue for discrete-time systems using event-triggered mechanism subject to periodic random denial of service (DoS) jamming attacks and infinitely distributed delays. In order to characterize the occurrence of periodic random DoS jamming attacks in the network channel between controller and actuator, the Kronecker delta function is used to represent the periodic switching between the sleeping period and attack period, and a Bernoulli-distributed random variable is utilized to reflect the probabilistic occurrence of DoS attacks. Infinitely distributed delay is involved to reflect actual state lag. The relative event-triggering mechanism is employed to reduce unnecessary information transmission and save communication energy in the network channel between sensor and observer. An observer-based PID controller is constructed for the regulation of the system to achieve an appropriate working effect. The aim of this paper is to design a security-guaranteed PID controller for delayed systems such that both the exponential mean-square stability and the H∞ performance are satisfied. Using the Lyapunov stability theory, stochastic analysis method and matrix inequality technique, a sufficient condition is put forward that ensures the existence of the required observer and PID controller. Gain parameters of the observer and the PID controller are computed by solving a certain matrix inequality. A simulation is carried out to verify the effectiveness of the developed observer-based H∞ PID control method. The obtained H∞ noise rejection level is below 0.85, the average event-based release interval is 13, the absolute values of the maximum estimation error of two elements in the system state are 1.434 and 0.371 using the observer, and two elements of the system state converge to 0.238 and −0.054 at the 41th time step with two elements of the control output being 0.031 and 0.087.

Boundary Fuzzy Output Tracking Control of Nonlinear Parabolic Infinite-Dimensional Dynamic Systems: Application to Cooling Process in Hot Strip Mills

This paper utilizes a combination of integral control, fuzzy control, and observer-based output feedback control to deal with the issue of nonlinear output tracking control (OTC) design for nonlinear infinite-dimensional dynamic systems. The system dynamics model is represented by a semi-linear parabolic partial differential equation (PDE) with boundary control and non-collocated boundary measurement. Initially, a Takagi-Sugeno (T-S) fuzzy parabolic PDE model is constructed to surmount the OTC design difficulty from the infinite-dimensional nonlinear system dynamics. Subsequently, a fuzzy-observer-based OTC law is proposed via the T-S fuzzy PDE model and the integral control approach. Here, the integral control ensures asymptotic output regulation, and the observer-based output feedback control is employed to conquer the stabilizing control design difficulty caused by the non-collocation between control actuation and measurement. It is shown via the Lyapunov technique with variants of vector-valued Poincaré-Wirtinger's inequality that the suggested fuzzy OTC law drives the measurement output to asymptotically track the desired reference signal and ensures the boundedness of the resulting closed-loop system, provided that a sufficient condition given in the form of linear matrix inequalities is fulfilled. Moreover, the proposed fuzzy-model-based OTC design is also revised for the exponential stabilization case. Finally, extensive simulation results for a numerical example and a cooling process in hot strip mills are provided to examine the effectiveness and merit of the proposed fuzzy OTC scheme.

Optimization control of the double‐capacity water tank‐level system using the deep deterministic policy gradient algorithm

AbstractProcess control systems are subject to external factors such as changes in working conditions and perturbation interference, which can significantly affect the system's stability and overall performance. The application and promotion of intelligent control algorithms with self‐learning, self‐optimization, and self‐adaption characteristics have thus become a challenging yet meaningful research topic. In this article, we propose a novel approach that incorporates the deep deterministic policy gradient (DDPG) algorithm into the control of double‐capacity water tanklevel system. Specifically, we introduce a fully connected layer on the observer side of the critic network to enhance its expression capability and processing efficiency, allowing for the extraction of important features for water‐level control. Additionally, we optimize the node parameters of the neural network and use the RELU activation function to ensure the network's ability to continuously observe and learn from the external water tank environment while avoiding the issue of vanishing gradients. We enhance the system's feedback regulation ability by adding the PID controller output to the observer input based on the liquid level deviation and height. This integration with the DDPG control method effectively leverages the benefits of both, resulting in improved robustness and adaptability of the system. Experimental results show that our proposed model outperforms traditional control methods in terms of convergence, tracking, anti‐disturbance and robustness performances, highlighting its effectiveness in improving the stability and precision of double‐capacity water tank systems.

Performance Evaluation Of Permanent Magnet Synchronous Generator (PMSG) On Tidal Power Generation Optimization

In a tidal current energy generation system, optimization of power generation can be done through turbine design, system design, and control of mechanical transmission from the turbine to the generator, as well as from the aspect of electronic generator output control. This research aims to analyze the performance of the PMSG generator from a prototype of the tidal current energy power plant. Turbine rotation is simulated using an ac motor equipped with an ac drive that supports separate speed and torque control. The hydraulic transmission system consists of a pump and a hydraulic motor that transfers the rotation of the turbine to the generator, where the power output is observed with variations in turbine speed and torque. The results indicate that the transmission system has worked well in transmitting the turbine’s mechanical power and increasing the rotational speed. The decrease in speed with increasing load and low average efficiency (less than 20%) occurs, mainly due to the characteristics of the generator being tested. The generator has a large rated torque requirement of 32 Nm, which is much higher than the main drive capacity of the turbine simulator. The design of a tidal energy conversion system, in which the tidal current speed fluctuates, requires careful selection of the generator, not only from the aspect of power capacity and rated rotational speed, but also from the initial torque value and required rated torque.

Fully Distributed Pull-Based Event-Triggered Bipartite Fixed-Time Output Control of Heterogeneous Systems With an Active Leader.

This article deals with the fully distributed pull-based event-triggered bipartite fixed-time output consensus problem of heterogeneous linear multiagent systems (HLMASs) with an active leader, whose information can be merely accessed by a small fraction of followers. First, a class of fully distributed fixed-time observers is proposed for each follower to estimate the leader's system matrices, position, and control input under the signed communication topology, respectively. Then, based on the estimations of leader's system matrices, two adaptive algorithms are given to solve the regulator equations. Furthermore, the fully distributed fixed-time observer-based controllers associated with state feedback and output feedback are, respectively, proposed by employing the pull-based event-triggered mechanism (ETM) where each agent merely updates controller at its own triggering instants. Correspondingly, some sufficient criteria and the rigorous proofs are provided to ensure the implementation of bipartite output consensus in fixed time by using the Lyapunov stability theory and fixed-time stability theory. Moreover, the strictly positive lower bounds of intervals between two adjacent event-triggered times are derived, which means the Zeno behavior is ruled out. Finally, numerical simulations are performed to demonstrate the theoretical analysis.

RELIABILITY OF THE CONTROL OF ELECTRONIC DEVICES BY LOW-FREQUENCY NOISE

The article examines the stages of input and output control of electronic equipment products according to the level of their own low-frequency noise, namely, the measurement of an informative parameter and its comparison with predetermined limits. It was established that for each type of control there is a need to have a methodology for assessing the compliance of control results with valid characteristics and its effectiveness. One of the main parameters of the effectiveness of all stages of control is the probability, which requires separate studies and the definition of a universal mechanism for its assessment. Therefore, the task was set to obtain a complete method of probability assessment for the input and output control of electronic equipment products by the level of their own noise. To determine the probabilistic characteristics of the control, the main informative parameters were investigated: the measuring noise voltage, which is random in nature, and the random error. It is established that the measured value has a confidence interval that takes into account measurement errors and determination of control limits. Control limits were obtained, on the basis of which analytical expressions were obtained for the distribution of the informative parameter within the specified limits for reliable and unreliable electronic products. Taking into account the limit of separation of products into suitable and unsuitable, control limits were proposed, which contain the coefficient of possible error cut-off. A generalized analytical expression for evaluating the probability of control is obtained, which takes into account the minimization of the effect of systematic and random factors influencing the result to increase the efficiency of input and output control on the level of low-frequency noise.

Vehicle-Mounted Solar Occultation Flux Fourier Transform Infrared Spectrometer and Its Remote Sensing Application.

For the demand of rapid monitoring of pollution gas disorganized emissions in industrial parks, this paper studies the solar fast tracker system of vehicle-mounted SOF-FTIR (Solar Occultation Flux Fourier Transform Infrared Spectroscopy) system, where the spectrometer directly measures the broadband absorption spectrum of solar radiation light. A fast portable solar tracking system based on PSD (position sensitive detector) is designed, the mathematical model of solar spot position on the PSD surface source is established, and the optimal optical design parameters are simulated using the model. The dead-zone integral separation PID (Proportion Integration Differentiation) control algorithm is used to track the trajectory of the solar, and the light spot position model is used to nonlinearly compensate the output of PID control so that the PID controller has the same control precision and response speed in different error areas. Experimental analysis of the solar tracking performance of the vehicle-mounted SOF-FTIR under static and dynamic conditions, as well as the spectral effects on the measurements under static vehicle, constant speed, and turning driving conditions. The remote sensing application experiment of vehicle-mounted SOF-FTIR pollution gas emission flux was carried out in a tire factory in Hefei City, Anhui Province. A vehicle-mounted SOF-FTIR system realized the qualitative and quantitative analysis of the pollution gas at the boundary of the tire plant and calculated the flux of each component pollution gas. The emission flux of pollution gas was highly consistent with the actual pollution distribution of the tire plant. The results show that the positioning accuracy of PSD in the vehicle tracking experiment can also meet SOF-FTIR requirements for solar tracking. The remote sensing system will be useful in the field of atmospheric environment monitoring, and the mobile monitoring of regional pollutant gases based on solar infrared spectroscopy has application value.

Optimal control method of induction motor torque ripple based on harmonic component

AbstractThe torque ripple of an induction motor has strong harmonic interference, which causes stator current distortion. Stability control is always a difficult problem in this field. An optimal control method for the torque ripple of induction motors based on harmonic components is proposed. To address the instability and significant energy loss caused by torque ripple in induction motors, an optimization control method for torque ripple in induction motors based on harmonic components is studied and designed. On the basis of the induction motor model, according to the characteristics and generation principle of torque ripple, combined with controllable and uncontrollable parts of harmonic torque, the stator current harmonics are used to suppress torque harmonics and minimize torque ripple. For the purpose of to cancel the harmonic component of the output voltage, achieve digital output voltage filtering, reduce the harmonic component of the stator current, and achieve optimal control of the torque ripple of the induction motor, the resonant digital filter is simultaneously deployed at the controller's output. The test results showed that the maximum torque ripple value was 2 Nm and the minimum torque ripple value was 0.1 Nm, which can restrain the distortion of stator current to the greatest extent and reduce the harmonic content of torque. In summary, the optimization control method proposed in the study can effectively suppress harmonic interference, which has important practical implications for future harmonic research.

Automatic control of the boiler heat power based on changing hydrocarbon fuelʼs calorific value

This paper is devoted to the development and research of an advanced approach to automatic control of the heat output of the boiler when compensating the load disturbances by regulating the composition of the combusted hydrocarbon fuel mixture. The proposed approach gives the opportunity to design the boiler’s automatic control system (ACS) with the possibility of creating the conditions for the formation and determination of the current calorific value of the gases mixture, which corresponds to the current heat load of the boiler, as well as determining the flue gas flow and temperature in the boiler. The implementation of the developed approach of the boiler’s load control allows for providing a constant nominal flue gas flow at any level of heat output. The fuel composition control process consists of mixing certified and non-certified hydrocarbon gases, which ensures maximum efficiency and compliance with environmental emission standards. The effectiveness study of the proposed approach is carried out in the development of the heat output ACS for the GM-50 boiler and conducting a computational experiment of operating at a power different from the nominal one. The obtained results fully confirm the high efficiency of the developed approach, as well as the expediency of its application for boilers of various types and capacities when operating at a power different from the nominal one.

Cooperative Guidance Law for the Mother-Cabin of the Anti-UAV Cluster Mother-Son Missile

This article investigates a novel operational pattern for intercepting UAV clusters over the range of middle and far distances using mother-son missiles. To address the guidance issue of the mother-cabin in the operational pattern, a special cooperative guidance law, which takes into account acceleration constraint and satisfies the constraints of impact time, speed, and zero line of sight angle (LOS), is proposed. Based on consistency theory and sliding mode control theory, the proposed cooperative guidance law is specifically designed for the mother-cabin of the mother-son missile. This approach offers several advantages, including a simple structure and smooth controller output, and smooth flight trajectory. Finally, numerical simulations are presented to demonstrate the effectiveness and applicability of the cooperative guidance law.

A Prediction Method of Ship Motion Based on LSTM Neural Network with Variable Step-Variable Sampling Frequency Characteristics

In active heave compensation, in order to realize the smooth control of the heave compensation platform, it is necessary to use the ship motion measurement system to accurately obtain the ship displacement signal, invert the ship displacement signal, and then control the expansion and contraction of the electric cylinder so that the compensation platform remains horizontal. The ship displacement measurement system generally adopts the second integral of the acceleration sensor to obtain the ship displacement signal. During the acquisition process of the ship displacement signal, the quadratic integration process of the acceleration, and the communication process of the output control command, there is a processing lag which makes the error accumulate, resulting in a delay in the measurement of the ship motion. In order to collect the ship motion more accurately and control the heave compensation platform more precisely, this paper proposes a ship motion prediction method based on a variable step-variable sampling frequency characteristic LSTM (Long Short-Term Memory) neural network. First, we use the autocorrelation function algorithm to calculate the inherent delay of the lag in the process of signal acquisition by the measurement system. Secondly, the LSTM neural network is used to predict the inherent delay step of the lagging ship displacement signal. During the prediction process, it is found that the difference in the sampling frequency of the displacement signal will lead to a change in the step of the inherent delay—experiment in the laboratory to verify. By controlling the motion platform to simulate the motion of the ship and using the ship motion measurement system and the laser sensor system to measure the displacement signal of the motion platform synchronously, it is verified that the ship motion measurement system does have an inherent delay. Thirdly, on a sailing ship, ship displacement signals are collected by setting multiple sets of ship motion measurement systems. Finally, multiple sets of sampling frequency and multiple steps are set, and the ship motion is predicted based on the variable step-variable sampling frequency LSTM neural network. It is verified that the prediction accuracy is related to the sampling frequency of the signal collector and the prediction step of the LSTM neural network, which improves the prediction accuracy of the model and the timeliness of ship motion acquisition.

КОМБІНОВАНЕ КЕРУВАННЯ БЕЗРЕДУКТОРНИМ ДУГОСТАТОРНИМ ЕЛЕКТРОПРИВОДОМ АНТЕНИ СУДНОВОЇ РАДІОЛОКАЦІЙНОЇ СТАНЦІЇ З НЕЧІТКИМ РЕГУЛЯТОРОМ ШВИДКОСТІ

The synthesis of a fuzzy proportional-integral-differential speed regulator of the arc stator electric drive of the rotation of the radar station antenna with combined control was carried out. The structural diagram of the fuzzy regulator was developed, the input and output linguistic variables are defined, the rule base was compiled, the dependence surfaces of the output control variable on the input coordinates are obtained. A simulation model of an electric drive in the Matlab system with a synthesized fuzzy logic regulator based on a two-phase model of an asynchronous arc-stator motor was built. Modeling of the nominal and the most difficult mode of operation of the electric drive was carried out, graphs of transient processes were obtained, which confirm its operability even under conditions of extreme loads. Refreces 9, figures 7, table 1.

Modular fuzzy control for nonlinear multipoint based core model of TMI PWR under variable fuel cycle conditions

This paper provides design of modular fuzzy controller based on reactor power for multipoint kinetic model of TMI PWR, under transients and variable operational fuel cycle conditions. The validated four-point kinetic model is developed considering six groups of delayed neutron precursors, reactivity feedbacks and diffusion among selected nodes. Fuel burn-up effects and power variations are modeled using the variable thermal coefficients. The ability of adaptive multi-module fuzzy controller for reactor power is evaluated and compared at start and end of burn-up cycle. The power dependant nonlinearity of reactor core and time dependant variations of reactivity characteristics are handled with modular approach of TS fuzzy control. The performance monitoring and control improvements are achieved by online parametric identification of process model. The four modules are distributed on the power base line using the triangular mapping. Design of fuzzy controller is based on the optimized gain requirement at different power levels, error and error change. Control output is mapped as biased linear function of selected input variables using TS type fuzzy logic inference. Safety analysis is performed with Lyapunov function criteria for multipoint model. Transient analysis is performed for power tracking and accident handling ability of proposed control design and compared with the PID controller. The power variation among the adjacent nodes is reduced up to 5% under load following transients with the proposed model. Modular fuzzy approach found proficient in handling the changing operational conditions and variable dynamics of the system.

Prototype Monitoring and Controlling of Wastewater Treatment Plant (WWTP) on IoT-Free Output Channels

The largest water pollution occurs due to the disposal of waste from the industrial sector, while some of it comes from the household sector. In the labor-intensive industrial sector and the household sector, domestic liquid waste is generated. The high level of liquid waste pollution can be overcome by using a wastewater treatment plant (WWTP). Wastewater parameters according to research that has been done, namely pH, Turbidity, and Ammonia are very important parameters and the main priority for the quality of wastewater discharged into the environment. In this study, a prototype monitoring and controlling WWTP on the output channel was designed by measuring wastewater parameters and an Internet of Things (IoT) based pump output control system. This prototype is programmed with 2 mode options, namely auto mode where the controlling system works based on program commands with target limits, namely pH 6 – 9, Turbidity < 300 NTU, and Ammonia < 20 PPM, if the wastewater measurement value is on target, the system activates the outgoing pump. for direct disposal to the environment. Meanwhile, if it does not meet the target, the system activates the treatment pump to return the wastewater back to the WWTP. Then the manual mode, which is the controlling system, works by operating the operator directly to activate the outgoing or treatment pump on a smartphone using the Blynk application. In Auto and Manual mode, wastewater parameters can be monitored on a smartphone using the Blynk application. All sensors used have been calibrated with 2 calibrator solutions. The calibration results show an error value of 0.115 for the pH sensor, an error value of 0.075 for the Turbidity sensor, and an error value of 0.115 for the Ammonia sensor.

Semi-active fuzzy cooperative control of vehicle suspension with a magnetorheological damper

This study attempts to improve the vibration isolation performance of a vehicle suspension system with a magnetorheological damper (MRD) under complex driving conditions. Structure parameter uncertainty, disturbance of the driving process, and response time delay of MRD are all addressed. Firstly, experiments of MRD were carried out in a damping force testing machine to identify the parameters of the MRD adjustable Sigmoid model by the Levenberg-Marquardt optimization algorithm. Then, the parameter identification is verified by comparing experimental and simulation data. Secondly, the state space equations of the suspension system are derived by Newton’s second law. The transfer function from the bounded disturbance input to the control output is obtained based on H∞ control theory. To make the Infinite norm of the system transfer function less than a certain value, three control strategies are proposed: variable structure control (VSC), disturbance rejection control (DRC), and delay tolerance control (DTC). Thirdly, considering these issues together to weaken the effect of disturbances on vehicle driving conditions, a fuzzy cooperative control (FCC) strategy is proposed based on the linear matrix inequality (LMI) theory. Simulation results demonstrate that FCC semi-active vehicle suspension systems conduct effective vibration isolation performance while responding to multiple external disturbances.

Predefined Time Synchronization of Multi-Agent Systems: A Passivity Based Analysis.

This paper deals with the predefined-time synchronization for a class of nonlinear multi-agent systems. The notion of passivity is exploited to design the controller for predefined-time synchronization of a nonlinear multi-agent system, where the time of synchronization can be preassigned. Developed control can be used to synchronize large-scale, higher-order multi-agent systems as passivity is an important property in designing control for complex control systems, where the control inputs and outputs are considered in determining the stability of the system in contrast to other approaches, such as state-based Control We introduced the notion of predefined-time passivity and as an application of the exposed stability analysis, static and adaptive predefined-time control algorithms are designed to study the average consensus problem for nonlinear leaderless multiagent systems in predefined-time. We provide a detailed mathematical analysis of the proposed protocol, including convergence proof and stability analysis. We discussed the tracking problem for a single agent, and designed state feedback and adaptive state feedback control scheme to make tracking error predefined-time passive and then showed that in the absence of external input, tracking error reduces to zero in predefined-time. Furthermore, we extended this concept for a nonlinear multi-agent system and designed state feedback and adaptive state feedback control scheme which ensure synchronization of all the agents in predefined-time. To further strengthen the idea, we applied our control scheme to a nonlinear multi-agent system by taking the example of Chua's circuit. Finally, we compared the result of our developed predefined-time synchronization framework with finite-time synchronization scheme available in literature for the Kuramoto model.

DISCRETE-TIME MODEL-BASED SLIDING MODE CONTROLLERS FOR TOWER CRANE SYSTEMS

This paper applies three classical and very popular discrete-time model-based sliding mode controllers, namely the Furuta controller, the Gao controller, and the quasi-relay controller due to Milosavljević, to the position control of tower crane systems. Three single input-single output (SISO) control systems are considered, for cart position control, arm angular position control and payload position control, and separate SISO controllers are designed in each control system. Experimental results are included to support the comparison of the three plus three plus three sliding mode controllers.

IPDT Model-Based Ziegler-Nichols Tuning Generalized to Controllers with Higher-Order Derivatives.

The paper extends the earlier work entitled "Making the PI and PID Controller Tuning Inspired by Ziegler and Nichols Precise and Reliable", to higher-order controllers and a broader range of experiments. The original series PI and PID controllers, based on automatic reset calculated by filtered controller outputs, are now augmented by higher-order output derivatives. This increases the number of degrees of freedom that can be used to modify the resulting dynamics, accelerates transient responses, and increases robustness to unmodeled dynamics and uncertainties. The fourth order noise attenuation filter used in the original work allows for the addition of an acceleration feedback signal, thus resulting in a series PIDA controller or even a jerk feedback that leads to a PIDAJ series controller. Such a design can further use the original process and filter approximation of the step responses through the integral-plus-dead-time (IPDT) model, while allowing experimentation with disturbance and setpoint step responses of the series PI, PID, PIDA and PIDAJ controllers, and thus, evaluating the role of output derivatives and noise attenuation from a broader perspective. All controllers considered are tuned using the Multiple Real Dominant Pole (MRDP) method, which is complemented by a factorization of the controller transfer functions to achieve the smallest possible time constant for automatic reset. The smallest time constant is chosen to improve the constrained transient response of the considered controller types. The obtained excellent performance and robustness allow the proposed controllers to be applied to a wider range of systems with dominant first-order dynamics. The proposed design is illustrated on a real-time speed control of a stable direct-current (DC) motor, which is approximated (together with a noise attenuation filter) by an IPDT model. The transient responses obtained are nearly time-optimal, with control signal limitations active for most setpoint step responses. Four controllers with different degrees of derivative with generalized automatic reset were used for comparison. It was found that controllers with higher-order derivatives may significantly improve the disturbance performance and virtually eliminate overshoots in the setpoint step responses in constrained velocity control.

Distributed processing for value-based choice by prelimbic circuits targeting anterior-posterior dorsal striatal subregions in male mice

Fronto-striatal circuits have been implicated in cognitive control of behavioral output for social and appetitive rewards. The functional diversity of prefrontal cortical populations is strongly dependent on their synaptic targets, with control of motor output mediated by connectivity to dorsal striatum. Despite evidence for functional diversity along the anterior-posterior striatal axis, it is unclear how distinct fronto-striatal sub-circuits support value-based choice. Here we found segregated prefrontal populations defined by anterior/posterior dorsomedial striatal target. During a feedback-based 2-alternative choice task, single-photon imaging revealed circuit-specific representations of task-relevant information with prelimbic neurons targeting anterior DMS (PL::A-DMS) robustly modulated during choices and negative outcomes, while prelimbic neurons targeting posterior DMS (PL::P-DMS) encoded internal representations of value and positive outcomes contingent on prior choice. Consistent with this distributed coding, optogenetic inhibition of PL::A-DMS circuits strongly impacted choice monitoring and responses to negative outcomes while inhibition of PL::P-DMS impaired task engagement and strategies following positive outcomes. Together our data uncover PL populations engaged in distributed processing for value-based choice.

An anti-rolling control method of rudder fin system based on ADRC decoupling and DDPG parameter adjustment

To achieve high-precision attitude control of ships, the output delay, state coupling, and controller parameter maladjustment of the rudder fin joint anti-rolling system are studied. A predictive anti-rolling method based on active disturbance rejection control (ADRC) and deep deterministic policy gradient (DDPG) is proposed. The external forces on the ship are analyzed, and a three-degree-of-freedom mathematical model considering rolling, yawing, and pitching is established. The model is decoupled using the idea of ADRC total disturbance for the state coupling problem, then the pitch ADRC controller and the roll-yaw predictive observer are designed respectively. In pitch ADRC, the nonlinear extended state observer (NLESO) is used to observe the total disturbance between models. And the total disturbance observations are feedforward compensated to the error control law. As a result, the rapidity of reference output tracking and robustness of total disturbance are realized. The roll-yaw predictive observer solves the output delay by feeding the predicted output back to the controller instead of the actual output. To ensure the accuracy of the prediction output, the DDPG algorithm is introduced to modify the parameters of the prediction observer in real-time. Finally, state constraints are added to solve the rudder angle and fin angle control laws. This method can perform control, parameter adjustment, and solution online and continuously. The wave disturbance test based on the experimental ship shows that the anti-rolling effect of the method is improved by 10% compared with the previous study. Under the condition of a small overshoot, the new expected value can be tracked quickly.