Adaptive Neural Network Algorithm Research Articles

Technical analysis of adaptive neuron fuzzy intelligent system in tennis serve

Serving is the most important hitting technique in tennis, and a good service receiving can instantly reverse the active and passive relationship between serve and receive on the tennis court, and control the rhythm of the court. The purpose of this study is to use an adaptive neuron fuzzy intelligent system to analyze some techniques of tennis serve. In this study, eight male players from the school tennis team were selected as the experimental subjects, whose sports level was above the national tennis level II. Ten weeks before the simulation test, the training time and frequency of 8 subjects were the same. In other words, 5 times a week, 2.5 hours±0.5 hours. The work engineering of adaptive fuzzy system firstly, in the off-line modeling stage, the adaptive fuzzy system uses the rule self splitting technology to generate the initial fuzzy rules, and uses the improved adaptive neural network algorithm to optimize the calculation; then according to the error between the system input and the predicted output, the independent variable is adjusted and replaced; at the same time, the adaptive fuzzy system is further used for calculation In the process of tennis serving, the nonlinear control variables are obtained online and applied to the fuzzy system for control. Next, in the experiment, the system was used to record the body’s movement and service scores during service. The experimental results show that during the service process, the maximum trunk torsion amplitude can reach 48.26 ° and the minimum is only 5.41 ° and the service score accounts for 81.41% and 80.47% of the total scores of the two sections respectively. This shows that the fuzzy system in this study can effectively analyze the service posture and score of athletes. It is concluded that the accurate calculation and analysis of tennis serve by adaptive neuron intelligent fuzzy system in this study is conducive to improve the tennis serviceability and competition performance of players. This research has made a certain contribution to the intellectualization of sports.

Compensation of Geometric Parameter Errors for Terrestrial Laser Scanner by Integrating Intensity Correction

The accuracy of geometric parameters (mainly referred to the incidence angle and measuring distance) in a terrestrial laser scanner (TLS) is not only influenced by the TLS intrinsic systematic instrumental error but also the extrinsic received intensity data. However, the current error compensation methods for geometric parameters mainly focus on the calibration of TLS intrinsic systematic instrumental error and rarely consider the extrinsic intensity data correction. For this reason, this article presents a new method integrating the TLS intrinsic systematic instrumental error calibration and extrinsic intensity data correction to compensate the TLS geometric parameter error. The error compensation procedure is implemented as follows. First, the error compensation mathematical model integrated with TLS intrinsic systematic instrumental error calibration parameters and extrinsic intensity data correction coefficient is established. Second, the hybrid harmonic analysis (HA) and the adaptive wavelet neural network (AWNN) algorithm are proposed to calculate the TLS incidence angle error compensation values. Subsequently, the cubic spline interpolation (CSI) is applied to compute the measuring distance error compensate values. Finally, the TLS (model FARO Focus S150) and the hemispherical angle calibration instrument were used to evaluate the proposed compensation method. The experimental results demonstrate that the geometric parameters are significantly influenced by the intensity data received from TLS, and the proposed method can effectively improve the overall accuracy of the TLS incidence angle and measuring distance.

Size‐Resolved Mixing States and Sources of Amine‐Containing Particles in the East China Sea

AbstractSingle‐particle aerosol mass spectrometry was employed during a cruise campaign from 3 to 27 June 2017 to investigate the mixing states and sources of amine‐containing particles in the East China Sea. A total of 271,160 particles were successfully identified, and 19,861 of these particles contained amines. Monomethylamine (MMA), trimethylamine (TMA), and diethylamine (DEA) were the most abundant amines. They accounted for 50%, 16%, and 29%, respectively, of the amine‐containing particles. The size distributions (mean ± geometric standard deviation) of the MMA‐, TMA‐, and DEA‐containing particles peaked at 0.58 ± 0.12, 0.56 ± 0.10, and 0.40 ± 0.10 μm, respectively. Using an adaptive resonance theory neural network algorithm, four major clusters of amine‐containing particles were categorized: carbon‐rich particles, K‐rich particles, Na‐rich particles, and metal‐rich particles. The MMA‐containing particles contained abundant elemental carbon‐, K‐, Mn‐, and Fe‐rich particles, which exhibit higher concentrations in land air masses, indicating that the MMA mainly originated from terrestrial anthropogenic sources. The TMA‐containing particles contained abundant organic and elemental carbon‐, EC‐, K‐, and V‐rich particles. High concentrations of TMA‐containing particles were measured near ports, indicating the significant contribution of the ports. The DEA‐containing particles contained abundant organic and elemental carbon‐, K‐, Mn‐, Cu‐, and Na‐rich particles, and high concentrations of DEA‐containing particles were observed in remote marine areas, suggesting that both terrestrial anthropogenic and marine sources are important contributors to DEA‐containing particles.

Innovative Scaled Hardware Simulator for Designing and Testing an EV’s Battery Storage System Incorporated with an Adaptive ANN Model

In this study, a scaled-down system, which can be used as a benchmark test for the battery storage designing of electric vehicles (EVs) is proposed. This model was based on the hardware simulator of the battery storage system (BSS) used from a single cell up to 4 cells in a series pack system, which simulates a practical battery pack. The developed simulator can charge and discharge any rechargeable battery, such as Li-Ion, Ni–MH or Pb battery. The scaling ratio of the simulator was evaluated by the ratio of the current or power of the battery pack specimen related to the specification. Also, this study proposes an innovative state of charge (SoC) estimation of the battery pack for EVs based on genuine results obtained through practical tests. This estimation was carried out by an adaptive artificial neural network (ANN) algorithm, using simple inputs. As well, this model can deduct the state of health (SoH) of the battery pack based on the power output level and waveform characteristics. The results of the ANN showed high generalization, a low error of SoC estimation at the level of 1.1%, with a calculation time less than 16.5 s. Regarding the hardware simulator, the similarity of the results and waveform accuracy of the scaled-down battery systems compared with the real battery pack was very acceptable with a maximum deviation of 2.1% in the worst scenario. The cells cycled with different depths of discharge (DoD) or C-rates, at different temperatures with different initial SoCs using any arbitrary current waveforms. Our conclusions will help battery manufacturers to test and evaluate the performance of the BSS in different applications, such as EVs, PV generation, and wind farm, with significant cost reduction. Also, the ANN algorithm can be used and embedded in EVs or in any other industrial application, as proposed in this paper. This study contributed to the real-time diagnosis of the BSS without interrupting the normal operation based on its features.

The Load Forecasting Method Based on Adaptive Neural Network and TLBO Algorithm

Load forecasting is of great significance for the arrangement and optimization of the distribution network scheduling. This paper proposes a load forecasting method based on an improved TLBO optimized adaptive neural network. Firstly, the ‘teaching’ phase in the basic TLBO algorithm is improved, and the average value of all search individuals is changed while adopting adaptive teaching factors, so that the performance of TLBO in the entire search space can be adaptively improved. Then, the ‘learning’ phase of the TLBO is improved. The Gaussian mutation operator is introduced in the learning phase to maintain the diversity of the population and avoid the TLBO algorithm’s premature convergence and local optimization. Finally, using the improved TLBO algorithm to optimize the adaptive neural network forecast model. In the end, the actual load data of Tianjin Power Grid was used to verify the accuracy of the simulation results.

Teeth infection and fatigue prediction using optimized neural networks and big data analytic tool

Despite the rapid improvement in dental health over the last few decades, a significant portion of our population continue seek dental care every year. Estimates show that 13% of adults seek dental care for dental infection or fatigue within four years. The Social and individual burden of this disease can be reduced by its early detection. However, the symptoms of teeth infection in the early stages are not clear, hence, it would be relatively difficult to predict teeth infections based solely on human skills and experience. Big Data (BD) technologies have a great potential in transforming dental care, as they have revolutionized other industries. In addition to reducing cost, they could save millions of lives and improve patient outcomes. This paper proposes a novel integrated prediction model that extracts hidden knowledge from radiographic datasets containing a large volume of dental X-ray images and utilizes this knowledge to predict dental infections. Initially, preprocessing techniques using morphological skeleton and mean approach is applied to eliminate noise and enhance the images. Next, Multi Scale Segmented Region (MSR) approach, Watershed Approach (WA), Sobel edge Detection (SD), Histogram based Segmentation (HS), Trainable Segmentation (TS), Dual Clustering (DC), and Fuzzy C-Means clustering (FCM) are examined for image segmentation and feature extraction. Among these methods, MSR was selected for feature extraction since it outperformed other methods in terms of accuracy, specificity, precision, recall and F1-score. Then, a set of neural network classifiers are trained to identify patterns in the extracted optimized features and predict dental infections. For this purpose, we have examined Bacterial Optimized Recurrent Neural Networks (BORNN), Deep Learning Neural Networks (DANN), Genetic Optimized Neural Networks (GONN) and Adaptive Neural Networks Algorithm (ADNN). BORNN have shown maximum accuracy and Roc value (98.1% and 0.92 respectively), and minimum error values (MSE = 0.189, MAE = 0.143). The output of the proposed integrated prediction model is fed into a dental robot who proceeds with the treatment process with high accuracy and minimum delay. The proposed prediction model was implemented using a big data analytics tool called Apache SAMOA and experimental results showed its correctness and effectiveness.

Adaptive Neural Fuzzy Petri Net Algorithm for Motor Fault Diagnosis

This study aimed to improve the application of fuzzy Petri net to fault diagnosis of motor systems. An adaptive Neural Fuzzy Petri Network Algorithm based on the traditional Petri net theory, fuzzy theory, and neural network algorithm is proposed and applied to the diagnosis of motor faults. The transition confidence is replaced by a Gaussian function to solve the uncertainty of fault propagation. Combined with the BP neural network, fault diagnosis parameters are adaptively trained. Finally, the Neural Fuzzy Petri Net Algorithm is applied to the fault diagnosis of a three-phase asynchronous motor, considering its fault operation mechanism and fault characteristics. The results show that the algorithm can diagnose the fault of the three-phase asynchronous motor with satisfactory accuracy and adaptability.

Adaptive Learning-Rate Backpropagation Neural Network Algorithm Based on the Minimization of Mean-Square Deviation for Impulsive Noises

This paper presents a novel adaptive learning-rate backpropagation neural network (ALR-BPNN) algorithm based on the minimization of mean-square deviation (MSD) to implement a fast convergence rate and robustness to impulsive noises. The learning rates of the weights in each hidden layer are derived to minimize the upper bound of the MSD obtained by the analysis, which guarantees a fast convergence rate in a stable range. Moreover, by adopting the variance of the kind of the measurement noises in each layer through the variance of the error signals, the proposed scheme provides robustness to the impulsive noises. The performance of the proposed algorithm is evaluated on various sequential signals and industrial data including the impulsive noise and compared with conventional ALR-BPNN algorithms. Simulation results indicate that the proposed algorithm outperforms the existing algorithms.

Precise Motion Control of Wafer Stages via Adaptive Neural Network and Fractional-Order Super-Twisting Algorithm

To obtain precise motion control of wafer stages, an adaptive neural network and fractional-order super-twisting control strategy is proposed. Based on sliding mode control (SMC), the proposed controller aims to address two challenges in SMC: 1) reducing the chattering phenomenon, and 2) attenuating the influence of model uncertainties and disturbances. For the first challenge, a fractional-order terminal sliding mode surface and a super-twisting algorithm are integrated into the SMC design. To attenuate uncertainties and disturbances, an add-on control structure based on the radial basis function (RBF) neural network is introduced. Stability analysis of the closed-loop control system is provided. Finally, experiments on a wafer stage testbed system are conducted, which proves that the proposed controller can robustly improve the tracking performance in the presence of uncertainties and disturbances compared to conventional and previous controllers.

Adaptive Neural Backstepping Control Design for A Class of Nonsmooth Nonlinear Systems

This paper investigates the problems of backstepping control for a class of nonsmooth nonlinear systems. With the help of set-valued functions (or maps) and set-valued derivatives, a new Lyapunov criterion is developed for nonsmooth systems. The concept of semi-globally uniformly ultimately bounded (SGUUB) stability that is widely used for smooth nonlinear systems in lower triangular form is, for the first time, applied to the nonsmooth case, and such a concept provides a theory foundation for the subsequent backstepping control design. Then, two types of continuous controllers are designed based on the backstepping technique and adaptive neural network (NN) algorithm. In the light of Cellina approximate selection theorem and smooth approximation theorem for Lipschitz functions, the system under investigation is first transformed into an equivalent model. Then, the first type of controller can be efficiently designed by using the traditional backstepping technique. On the other hand, when the unknown uncertainty is taken into account in the equivalent systems, another type of controller is designed based on adaptive NN control strategy. It is proved that in both cases, all the closed-loop signals are SGUUB by using our proposed controllers. Finally, a numerical example with two types of controllers is supplied to show the availability of the provided control schemes.

Adaptive Backstepping Control Design for Uncertain Non-smooth Strictfeedback Nonlinear Systems with Time-varying Delays

This paper is concerned with the problem of adaptive neural tracking control for uncertain non-smooth nonlinear time-delay systems with a class of lower triangular form. Based on Filippov’s theory, the bounded stability and asymptotic stability are extended to the ones for the considered systems, which provides the theory foundation for the subsequent adaptive control design. In the light of Cellina approximate selection theorem and smooth approximation theorem for Lipschitz functions, the system under investigation is first transformed into an equivalent system model, based on which, two types of controllers are designed by using adaptive neural network (NN) algorithm. The first designed controller can guarantee the system output to track a target signal with bounded error. In order to achieve asymptotic tracking performance, the other type of controller with proportional-integral(PI) compensator is then proposed. It is also noted that by exploring a novel Lyapunov-Krasovskii functional and designing proper controllers, the singularity problem frequently encountered in adaptive backstepping control methods developed for time-delay nonlinear systems with lower triangular form is avoided in our design approach. Finally, a numerical example is given to show the effectiveness of our proposed control schemes.

Adaptive Steering Feedback Torque Design and Control for Driver–Vehicle System Considering Driver Handling Properties

Steering feedback torque system, as the joint between the driver and the vehicle, should be well designed to aid driver handling by considering the driver handling properties and the control accuracy and performance of the system. In this paper first, the compensation mechanism of the driver arm for the change of the steering feedback torque is researched. It is found that drivers try to maintain the dynamic properties of the overall driver-vehicle systems as constant as possible by adjusting their arm mechanical characteristics. Moreover, the desired dynamic properties of the overall driver-vehicle system, which include the information of the driver desired handling properties, can be defined as a system transfer function. Second, a novel adaptive steering feedback torque controller is proposed on the basis of the findings. In this controller, the consideration and realization of the desired driver-vehicle dynamic properties are decoupled in the outer and inner control loops. In the outer control loop, a desired steering feedback torque model is identified with consideration of the desired driver-vehicle dynamic properties. In the inner control loop, the identified desired steering feedback torque model is realized using an adaptive neural network algorithm with robust control. In this way, the controller can be easily used by different drivers and applied to different vehicles. The stability of the system with the controller is analyzed. In the end, simulation and experiments are carried out to prove the validity of the proposed controller.

Adaptive Speed Controller for a Permanent Magnet Synchronous Motor

This paper presents a controller performance that is develop employing an adaptive B-spline neural network algorithm for adjusting the rotor speed of the permanent magnet synchronous motor. It includes a comparative analysis with three control strategies: conventional proportional integral, sliding mode and fuzzy logic. Also, gives a systematic way to determine the optimal control gains and improve the tracking error performance. A methodology for the adaptive controller and its training procedure are explained. The efficacy of the proposed method is analyzed using time simulations where the motor is subjected to disturbances and reference changes. The proposed control technique exhibits the best performance because it can adapt to every condition, demanding low computational effort for an on-line operation and considering the system nonlinearities.

Cognitive diagnosis of cultural and rural tourism convergence

Neural networks are widely used in the field of cognitive diagnosis. Cognitive diagnosis can diagnose the subjects’ knowledge of cognitive attributes according to their responses, so as to obtain the specific cognitive status of the subjects and provide remedial measures. The studies on the convergence of cultural industry and tourism industry are emerging, but the theoretical system needs to be improved. The research on the convergence mechanism between cultural industry and tourism industry can complement each other on the basis of independent theoretical system, which establishes relationship between the two theoretical systems. Based on the adaptive neural network algorithm and from the perspective of blockchain, this study takes cultural industry and rural tourism industry as examples to diagnose the industry convergence of rural cultural industry and rural tourism industry development, which will further consolidate the theoretical basis for the convergence and development of tourism industry and cultural industry, as well as contribute to promoting development of industry convergence.

Stability control of in-wheel motor electric vehicles under extreme conditions

To investigate the stability of in-wheel motor electric vehicles (IWMEVs) under extreme conditions, a novel control strategy including active rear steering (ARS) mode and direct yaw moment control (DYC) mode is proposed in this paper, utilizing the adaptive dynamic neural network (ADNN) algorithm to make the most of the two control modes. Firstly, a three-degree of freedom nonlinear vehicle model as well as some subsystems is established. Then, a two-layer stability control strategy is put forward, where the upper-layer calculates the desired rear steering angle as well as the differential torque of the rear wheels and the lower-layer executes commands and returns relevant signals. Besides, a stability controller based on ADNN algorithm is designed in the upper-layer so as to take advantage of the two modes under extreme conditions. Next, the impacts of initial values of the connection weights on the ability of ADNN algorithm to train and learn are revealed. Consequently, the optimal initial values can be ascertained before the following simulations. Finally, the closed loop simulations of ARS and DYC are carried out under some extreme conditions such as high velocity and low adhesion coefficient roads, and the results indicate that compared with DYC’s difficulty in playing its role, ARS mode can significantly improve the stability of IWMEVs even under extreme conditions.

Research on Multivariable Adaptive Control of HVAC System

HVAC system need be quickly diagnosed the location and location of the fault and find the cause of the failure, and reduce the failure to improve the comfort of users, improve the energy efficiency of buildings. Firstly, features of HVAC system failures were introduced in this paper. Failure correlation and transitivity and hierarchy of faults and parameter alignment were analyzed. On this basis, step size selection of depth neural network model was constructed by statistical-based machine learning. Adaptive depth neural network algorithm was built by weight updating formula. Finally, by an application case, multivariable adaptive control of HVAC System can strengthen the fault prediction and monitoring, can reduce the occurrence of fault, and prolong the life of equipment.

Adaptive control schemes applied to a control moment gyroscope of 2 degrees of freedom

Control of underactuated mechanical systems has been an important trend in mechatronics and nonlinear systems. Typical examples are the Furuta pendulum and inertia wheel pendulum. On the other hand, gyroscopes are important in aerial and space systems. In this paper, a two-degree of freedom underactuated control moment gyroscope (CMG) is studied. This system is highly coupled of one joint to the another and is difficult to control, which make it an important benchmark system. The problem addressed in this paper is to achieve robust motion control of the underactuated CMG. Firstly, a trajectory tracking controller is developed by using the feedback linearization technique. Secondly, two new adaptive algorithms are introduced, which correspond to an adaptive neural network algorithm and an adaptive model regressor scheme. A real–time experimental comparison is carried out among a linear PD control law, a cascade PID-PID controller and the introduced schemes. The real-time experimental study validates the introduced theory, where the performance of the controllers is evaluated with and without a periodic disturbance at the input.

Femtosecond pulse compression using a neural-network algorithm.

A key requirement for femtosecond spectroscopy measurements is to compress the laser pulse to its transform-limited duration. In particular, for few-cycle laser pulses, the compression process is time-consuming using conventional algorithms that converge statistically. Here we show that machine learning can accelerate the process of pulse compression: we have developed an adaptive neural-network algorithm to control a deformable-mirror-based pulse shaper that converges 100× faster than a standard evolutionary algorithm.

Adaptive neural network control of hexapod for aerospace application

This research is a part of the work implemented by BSTU “Voenmeh” under the financial support of the Ministry of Education and Science of the Russian Federation for design and development of a precision mechanism with the parallel kinematics called “Hexapod”. Based on the Stewart platform Hexapod as a positioning system with the parallel kinematics has many advantages in comparison with the serial kinematics mechanism. In engineering applications, very precise motion of parallel manipulators to track the desired trajectory has received a great deal of attention. The inverse kinematics problem of the hexapod is described, on the basis of which the desired trajectories are formed. The simulation model of hexapod dynamics implemented in the Matlab Simulink environment is shown. In this paper provides adaptive neural networks algorithm of the hexapods control with on-line tuning synaptic weights of network. Our results show an advantage of applying of the investigated algorithm in the problem of tracking control of the space applications hexapod.

Rheumatic Heart Disease Classification Using Adaptive Filters

An efficient and innovative method has been proposed in this paper to detect heart murmurs as a method to identify rheumatic fever with the use of adaptive filters, transform techniques and Neural Network Algorithms by considering various parameters such as number of peaks, Signal to Noise Ratio (SNR) and Power Spectral Density. Under optimum conditions the classification returned exact outputs even when the neural network was trained under false positive data thus showing its effectiveness.