Search results

The purpose of this paper is to discuss the application of computational intelligence techniques to the field of industrial robot control.

The core ideas behind using neural computation, evolutionary computation, and fuzzy logic techniques are presented, along with a selection of specific real‐world applications.

Their practical advantages and disadvantages relative to more traditional approaches are made clear.

The reader will appreciate the power of computational intelligence techniques for industrial robot control, and hopefully be encouraged to explore further the possibility of using them to achieve improved performance in their own applications.

The paper aims to advance methodologies to optimize fuzzy logic controller parameters via neural network and use the neuro‐fuzzy scheme to control two cooperating robots.

The paper presents a special neural network architecture that can be converted to fuzzy logic controller. Concepts of model predictive control (MPC) have been used to generate optimal signal to be used to train the neural network via backpropagation. Subsequently, a trained neural network is used to obtain fuzzy logic controller parameters.

The proposed neuro‐fuzzy scheme is able to precisely learn the control relation between input‐output training data generated by the learning algorithm. From the experiments performed on the industrial grade robots at Robotics and Manufacturing Automation (RAMA) Laboratory, it was found that the neuro‐fuzzy controller was able to learn fuzzy logic rules and parameters accurately.

The backpropagation method, used in this research, is extremely dependent on initial choice of parameters, and offers no mechanism to restrict the parameters within specified range during training. Use of alternative learning mechanisms, such as reinforcement learning, needs to be investigated.

The neuro‐fuzzy scheme presented can be used to develop controller for plants for which it is difficult to obtain analytical model or sufficient information about input‐output heuristic relation is not available.

The paper presents the neural network architecture and introduces a learning mechanism to train this architecture online.

Micro aerial vehicle is nonlinear plant; it is difficult to obtain stable control for MAV attitude due to uncertainties. The purpose of this paper is to propose one robust stable control strategy for MAV to accommodate system uncertainties, variations, and external disturbances.

First, by employing interval type-II fuzzy neural network (ITIIFNN) to approximate the nonlinearity function and uncertainty functions in the attitude angle dynamic model of micro aircraft vehicle (MAV). Then, the Lyapunov stability theorem is used to testify the asymptotic stability of the closed-loop system, the parameters of the ITIIFNN and gain of sliding mode control can be tuned on-line by adaptive laws based on Lyapunov synthesis approach, and the Lyapunov stability theorem has been used to testify the asymptotic stability of the closed-loop system.

The validity of the proposed control method has been verified through real-time experiments. The experimental results show that the performance of interval type-II fuzzy neural network based gain adaptive sliding mode controller (GASMC-ITIIFNN) is significantly improved compared with conventional adaptive sliding mode controller (CASMC), type-I fuzzy neural network based sliding mode controller (GASMC-TIFNN).

This approach has been used in one MAV, the controller works well, and which could guarantee the MAV control system with good performances under uncertainties, variations, and external disturbances.

The main original contributions of this paper are: the proposed control scheme makes full use of the nominal model of the MAV attitude control model; the overall closed-loop control system is globally stable demonstrated by Lyapunov stable theory; the tracking error can be asymptotically attenuated to a desired small level around zero by appropriate chosen parameters and learning rates; and the MAV attitude control system based on GASMC-ITIIFNN controller can achieve favourable tracking performance than GASMC-TIFNN and CASMC.

The purpose of this paper is to present an on-line modeling and controlling scheme based on the dynamic recurrent neural network for wastewater treatment system.

A control strategy based on rule adaptive recurrent neural network (RARFNN) is proposed in this paper to control the dissolved oxygen (D_O) concentration and nitrate nitrogen (S_No) concentration. The structure of the RARFNN is self-organized by a rule adaptive algorithm, and the rule adaptive algorithm considers the overall information processing ability of neural network. Furthermore, a stability analysis method is given to prove the convergence of the proposed RARFNN.

By application in the control problem of wastewater treatment process (WWTP), results show that the proposed control method achieves better performance compared to other methods.

The proposed on-line modeling and controlling method uses the RARFNN to model and control the dynamic WWTP. The RARFNN can adjust its structure and parameters according to the changes of biochemical reactions and pollutant concentrations. And, the rule adaptive mechanism considers the overall information processing ability judgment of the neural network, which can ensure that the neural network contains the information of the biochemical reactions.

The main purpose of this paper is to enhance the control performance of the robotic arm by the controller of fuzzy neural network (FNN).

The robot system has characters of high order, time delay, time variation and serious nonlinearity. The classical PID controller cannot achieve satisfactory performance in control of such a complex system. This paper combined the fuzzy control with neural networks and established the FNN controller and applied it in control of the robot.

The experimental results showed that the FNN controller had excellent performances in position control of the rehabilitation robotic arm such as fast response, small overshoot and small vibration.

This work is focused on the static FNN algorithm by updating the second and fifth layers of the membership functions. The performance can be improved further if the third layer (reasoning layer) can be updated online.

Based on a hierarchical structure of the FNN controller, this paper designed the FNN controller and applied it in control of the rehabilitation robot driven by pneumatic muscles.

Presents a switching type neuro‐fuzzy control synthesis. The control algorithm supposes as a component part a neurocontrol designed to optimize a performance index. Whenever the neurocontrol saturates or a certain performance parameter of the system decreases, the scheme of control switches to a feasible and reliable fuzzy logic control. Describes the procedure of return to the optimizing neurocontrol which is essential. This methodology of control synthesis ensures antisaturating, antichattering and robustness properties of the controlling system, as illustrated by numerical simulation in the case of a primary flight controls electrohydraulic servo actuator

The paper aims to overcome the shortcomings that proportional‐integral‐derivative (PID) control for unmanned robot applied to automotive test (URAT) needs a priori manual retuning, has large speed fluctuations and is hard to adjust control parameters. A novel control approach based on fuzzy neural network applied to URAT was proposed.

According to the target vehicle speed and driving command table, the multiple manipulator coordinated control model was established. After that, the displacement of throttle mechanical leg, clutch mechanical leg, brake mechanical leg and shift mechanical arm for URAT was used as input of fuzzy neural network (FNN) model, and vehicle speed was used as output of FNN model. The number of membership functions was three, and the type of that was generalized bell membership function (gbellmf). The hybrid learning algorithm which combined with back propagation algorithm and least square method was applied to train the model. The Sugeno model was selected as fuzzy reasoning model.

Experimental results demonstrated that compared with PID control method, the proposed approach can greatly improve the accuracy of vehicle speed tracking. The approach can accurately realize the vehicle speed tracking of given driving test cycle. Therefore, it can ensure the accuracy and effectiveness of automotive test results.

Future work will focus on improving the efficiency of this learning algorithm.

The paper provides effective methods for improving the accuracy of speed tracking and repeatability.

After establishing the multiple manipulator coordinated control model, this paper proposes a novel control approach based on FNN for URAT.

Nowadays, in order to improve current applications, industry incorporates to their solution approaches artificial intelligence techniques and methodologies like Fuzzy Logic, neural networks and/or genetic algorithms (GA). Artificial intelligence techniques complement classical methodologies and include concepts that simulate the way humans solve problems or how processes work in nature. In this work, the Fuzzy Logic system cancels the effects of load perturbances in an energy plant, by implementing a secondary controller which complements the main controller. The purpose of this paper is to use GA to tune this new secondary controller. The authors particularize the proposal for three specific applications: control the angular speed and position of a Direct Current (DC) motor and control the output voltage of a DC/DC buck converter.

The authors use GA for tuning a Proportional-Integral Fuzzy Controller (PI-Fuzzy). The proposal defines a new objective function in comparison with literature approaches. The main key in the new objective function is combining the best features of Integral Square Error (ISE) function and taking out the overshoot response.

In order to demonstrate the proposed methodology based on GA tuning a PI-Fuzzy, the authors apply the literature benchmark to the solution. The results are compared with the following techniques: Robust control, continuous PID control, discrete PID control, Optimal Control, Fuzzy Control and Artificial Neural Network based control. Comparisons are presented in terms of setting time and overshot.

Results demonstrate that ISE or integral of absolute value of error function do not provide the desired response. Achieved results demonstrate the usefulness of the proposal to eliminate the overshoot of the traditional behaviour without lost any of the main features of the literature methodologies.

With the help of basic physics, the application of computer algorithms in the form of recent advances such as machine learning and neural networking in textile Industry has been discussed in this review. Scientists have linked the underlying structural or chemical science of textile materials and discovered several strategies for completing some of the most time-consuming tasks with ease and precision. Since the 1980s, computer algorithms and machine learning have been used to aid the majority of the textile testing process. With the rise in demand for automation, deep learning, and neural networks, these two now handle the majority of testing and quality control operations in the form of image processing.

The state-of-the-art of artificial intelligence (AI) applications in the textile sector is reviewed in this paper. Based on several research problems and AI-based methods, the current literature is evaluated. The research issues are categorized into three categories based on the operation processes of the textile industry, including yarn manufacturing, fabric manufacture and coloration.

AI-assisted automation has improved not only machine efficiency but also overall industry operations. AI's fundamental concepts have been examined for real-world challenges. Several scientists conducted the majority of the case studies, and they confirmed that image analysis, backpropagation and neural networking may be specifically used as testing techniques in textile material testing. AI can be used to automate processes in various circumstances.

This research conducts a thorough analysis of artificial neural network applications in the textile sector.

In treating both sewage and storm runoff, wastewater treatment plants are important to maintaining a healthy environment. If the plant operations managers do not respond correctly to plant conditions, environmental damage resulting in the deterioration of human health may be the result. Unfortunately, there are no formal models to help these managers; they rely upon their own intuition to manage the plants. The purpose of this paper is to investigate the effectiveness of various models, originally used for manufacturing, to detect process conditions in wastewater treatment facilities. We compare and contrast the performance of five statistical models and three neural network architectures. The data used in the research is 527 daily measurements of 38 sensor readings of the process state variables of an urban wastewater treatment plant.