Adaptive Neural Network Algorithm Research Articles

Adaptive third-order integral sliding mode control for the mobile petroleum crane-form pipelines system with input bounded

The mobile petroleum crane-form pipelines (MPCFP) system is one of the most important mechanical equipment in the petrochemical industry, consisting of rigid pipelines and rotating elbows, mainly used for loading and unloading petrochemical fluids. This paper proposes a novel neural network adaptive third-order integral sliding mode tracking control strategy with bounded inputs to achieve automatic alignment between the MPCFP system and the inlet of the tank truck. The proposed strategy replaces normal system inputs with the time derivative of the control torque. Although there are discontinuous terms in the derivative of the control torque, the integrated control torque is continuous. This unique feature ensures finite-time convergence of system state errors and eliminates sliding mode chattering. To address the issues of bounded input and modeling error, a state compensation method is introduced, and a neural network adaptive algorithm is utilized to estimate the modeling error. The stability proof process employs the Lyapunov function method, demonstrating that the system state error can converge to zero. Numerous simulation experiments validate the effectiveness of this control strategy.

Rapid and precise calibration of soil microparameters for high-fidelity discrete element models in vehicle mobility simulation

In the realm of numerical simulations concerning vehicle mobility, the establishment of a high-fidelity soil discrete element model often necessitates substantial parameter adjustments to align with the mechanical responses of actual soil. In pursuit of a rapid and precise calibration of the microparameters of the soil model, this paper describes an approach rooted in machine learning surrogate models. This method calibrates the corresponding discrete element microparameters based on the macroscopic Mohr–Coulomb parameters derived from actual soil direct shear tests. The distinct contribution lies in the creation of a dataset that bridges the soil microparameters and macroparameters through simulated direct shear tests, which serves as training data for machine learning algorithms. Additionally, an adaptive particle swarm optimization neural network algorithm is proposed to represent the nonlinear relationships among parameters within the dataset, thus achieving intelligent calibration. To verify the reliability of the proposed soil calibration model in the context of vehicle mobility simulations, a co-simulation is conducted using a vehicle multibody dynamics simulation model and the calibrated soil model, with validation conducted across multiple criteria.

An optimized model based on adaptive convolutional neural network and grey wolf algorithm for breast cancer diagnosis.

Medical image classification (IC) is a method for categorizing images according to the appropriate pathological stage. It is a crucial stage in computer-aided diagnosis (CAD) systems, which were created to help radiologists with reading and analyzing medical images as well as with the early detection of tumors and other disorders. The use of convolutional neural network (CNN) models in the medical industry has recently increased, and they achieve great results at IC, particularly in terms of high performance and robustness. The proposed method uses pre-trained models such as Dense Convolutional Network (DenseNet)-121 and Visual Geometry Group (VGG)-16 as feature extractor networks, bidirectional long short-term memory (BiLSTM) layers for temporal feature extraction, and the Support Vector Machine (SVM) and Random Forest (RF) algorithms to perform classification. For improved performance, the selected pre-trained CNN hyperparameters have been optimized using a modified grey wolf optimization method. The experimental analysis for the presented model on the Mammographic Image Analysis Society (MIAS) dataset shows that the VGG16 model is powerful for BC classification with overall accuracy, sensitivity, specificity, precision, and area under the ROC curve (AUC) of 99.86%, 99.9%, 99.7%, 97.1%, and 1.0, respectively, on the MIAS dataset and 99.4%, 99.03%, 99.2%, 97.4%, and 1.0, respectively, on the INbreast dataset.

Selective capture of PM2.5 by urban trees: The role of leaf wax composition and physiological traits in air quality enhancement

Human health risks from particles with a diameter of less than 2.5 µm (PM2.5) highlight the role of urban trees as bio-filters in air pollution control. However, whether the size and composition of particles captured by various tree species differ or not remain unclear. This study investigates how leaf attributes affect the capture of PM2.5, which can penetrate deep into the lungs and pose significant health risks. Using a self-developed particulate matter (PM) resuspension chamber and single-particle aerosol mass spectrometer, we measured the size distribution and mass spectra of particles captured by ten tree species. Notably, Cinnamomum camphora (L.) J.Presl and Osmanthus fragrans Lour. are more effective at capturing particles under 1 µm, which are most harmful because they can reach the alveoli, whereas Ginkgo biloba L. and Platanus × acerifolia (Aiton) Willd. tend to capture larger particles, up to 1.6 µm, which are prone to being trapped in the upper respiratory tract. Leaf physiological traits such as stomatal conductance and water potential significantly enhance the capture of larger particles. The Adaptive Resonance Theory neural network (ART-2a) algorithm classified a large number of single particles to determine their composition. Results indicate distinct inter-species variations in chemical composition of particles captured by leaves. Moreover, we identified how specific leaf wax compositions—beyond the known sticky nature of hydrophobic waxes—contribute to particle adhesion, particularly highlighting the roles of fatty acids and alkanes in adhering particles rich in organic carbon and heavy metals, respectively. This research advances our understanding by linking leaf physiological and wax characteristics to the selective capture of PM2.5, providing actionable insights for urban forestry management. The detailed exploration of particle size and composition, tied to specific tree species, enriches the current literature by quantifying how and why different species contribute variably to air quality improvement. This adds a crucial layer of specificity to the general knowledge that trees serve as bio-filters, offering a refined strategy for planting urban trees based on their particulate capture profiles.

Neural-based fixed-time composite learning control for multiagent systems with intermittent faults

In this paper, a distributed fixed-time composite learning control problem is addressed for nonlinear multiagent systems (MASs) subject to intermittent actuator faults. First, a distributed estimator is constructed for followers that are unable to communicate directly with the leader. Then, instead of using the traditional adaptive neural network (NN) algorithm, a predictor-based composite learning technique is proposed, which incorporates the prediction error into the NN update law to enhance the estimation accuracy of the unknown nonlinearity. Furthermore, an adaptive fault-tolerant control compensation mechanism is developed for intermittent faults that may occur indefinitely and frequently. To guarantee that all signals of the closed-loop system are bounded in fixed time, a nonsingular fixed-time fault-tolerant controller in the form of quadratic function is established. Finally, simulation results confirm the effectiveness of the presented algorithm.

Neural network adaptive PID-like coupling control for double pendulum cranes with time-varying input constraints

Industrial cranes commonly experience the double pendulum swing effect as a result of a number of reasons, including the magnitude of the cargo and the non-negligible hook mass. Nevertheless, the majority of control strategies for double-pendulum cranes, whether open-loop or closed-loop, are created using linearized dynamics and necessitate accurate knowledge of the model parameters, rendering them susceptible to parametric uncertainties and unmodeled disturbances. To solve these problems, a new neural network adaptive PID-like coupling control method for the nonlinear double pendulum cranes is proposed in this paper. By making full use of the designed composite signal and its integral action, oscillation suppression and precise positioning are realized. In addition, the problem of conventional PID parameter adjustment is solved successfully by determining the PID gains through a neural network adaptive algorithm, automatically. Moreover, it has been shown that the systematic error converges into a compact set around zero for a variety of time-varying actuator failures and saturation situations that can easily occur in practical engineering. Finally, the effectiveness of the proposed control method is verified through hardware experiments, and the comparison results prove the superior performance of the designed controller.

Retracted: Football Match Scoring Method Based on Adaptive Neural Network Algorithm

Retracted: Football Match Scoring Method Based on Adaptive Neural Network Algorithm

Vehicle Platoon Tracking Control Based on Adaptive Neural Network Algorithm

Vehicle Platoon Tracking Control Based on Adaptive Neural Network Algorithm

A Novel Adaptive Neural Network-Based Thermoelectric Parameter Prediction Method for Enhancing Solid Oxide Fuel Cell System Efficiency

Efficiency prediction plays a crucial role in the ongoing development of electrochemical energy technology. Our industries heavily depend on a reliable energy supply for power and electricity, and solid oxide fuel cell (SOFC) systems stand out as renewable devices with immense potential. SOFCs, as one of the various types of fuel cells, are renowned for their capability of combined heat and power generation. They can achieve an efficiency of up to 90% in operation. Furthermore, due to the fact that water is the byproduct of their electricity generation process, they are extremely environmentally friendly, contributing significantly to humanity’s sustainable development. With the advancement of renewable energy technologies and the increasing emphasis on sustainable development requirements, predicting and optimizing the efficiency of SOFC systems is gaining importance. This study leverages data collected from an SOFC system and applies an improved neural network structure, specifically the dendritic network (DN) architecture, to forecast thermoelectric efficiency. The key advantage of this method lies in the adaptive neural network algorithm based on the dendritic network structure without manually setting hidden nodes. Moreover, the predicted model of thermoelectric efficiency is validated using 682 and 1099 h of operational data from the SOFC system, and the results are compared against a conventional machine learning method. After comparison, it is found that when the novel method with adaptive characteristics proposed was used for SOFC system efficiency prediction, the MAE and RMSE values were both lower than 0.014; the result is significantly better than from other traditional methods. Additionally, this study demonstrated its effectiveness in predicting the thermoelectric efficiency of SOFC systems through secondary experiments. This study offers guidance on enhancing SOFC systems thermoelectric efficiency. Therefore, this study provides a foundation for the future industrialization of fuel cell systems.

Numerical solution of ruin probability of continuous time model based on optimal adaptive particle swarm optimization-triangular neural network algorithm

Numerical solution of ruin probability of continuous time model based on optimal adaptive particle swarm optimization-triangular neural network algorithm

Adaptive memetic differential evolution-back propagation-fuzzy neural network algorithm for robot control

This study established an adaptive memetic differential evolution-back propagation-fuzzy neural network (AMDE-BP-FNN) control method to achieve high-efficiency and precise control of robots with complex dynamic characteristics while reducing control costs. The adaptive differential evolution (ADE) method was applied to search the optimal parameters in the global scope and delimited the pseudo-global search scope. The memetic differential evolution (MDE) method was used to search for optimal parameters in the pseudo-global scope, and the probability factor was set to decide whether to use the back propagation (BP) algorithm for online optimization. Finally, simulations, experiments, and real-world applications were conducted. The results indicated the high efficiency, high precision, and viability of the proposed AMDE-BP-FNN method.

Application of Adaptive Back Propagation Neural Network Algorithm in Vehicle Scheduling of Logistics Enterprises

Application of Adaptive Back Propagation Neural Network Algorithm in Vehicle Scheduling of Logistics Enterprises

Application of adaptive back propagation neural network algorithm in vehicle scheduling of logistics enterprises

Application of adaptive back propagation neural network algorithm in vehicle scheduling of logistics enterprises

Retracted: Application of Adaptive Neural Network Algorithm Model in English Text Analysis.

[This retracts the article DOI: 10.1155/2022/4866531.].

Building Energy Models at Different Time Scales Based on Multi-Output Machine Learning

Machine learning techniques are widely applied in the field of building energy analysis to provide accurate energy models. The majority of previous studies, however, apply single-output machine learning algorithms to predict building energy use. Single-output models are unable to concurrently predict different time scales or various types of energy use. Therefore, this paper investigates the performance of multi-output energy models at three time scales (daily, monthly, and annual) using the Bayesian adaptive spline surface (BASS) and deep neural network (DNN) algorithms. The results indicate that the multi-output models based on the BASS approach combined with the principal component analysis can simultaneously predict accurate energy use at three time scales. The energy predictions also have the same or similar correlation structure as the energy data from the engineering-based EnergyPlus models. Moreover, the results from the multi-time scale BASS models have consistent accumulative features, which means energy use at a larger time scale equals the summation of energy use at a smaller time scale. The multi-output models at various time scales for building energy prediction developed in this research can be used in uncertainty analysis, sensitivity analysis, and calibration of building energy models.

Identifying peanut maturity based on Hyper Spectral Invariant Scaled Feature Selection using Adaptive Dense Net Recurrent Neural Network

With the rapid development of agricultural resources in south India, the peanut is important for cultivation in delta regions. The findings of suitable peanut seeds are analyzed through digital image processing with the support of deep learning analysis. Identifying seed maturity is a challenging task because seed level finding in features contains various scaled our dimensions, and increasing on successive feature observation leads to maturity findings inaccuracy in precision rate. We propose a Hyper Spectral Invariant Scaled Feature Selection (HSISFS) using an Adaptive Dense Net Recurrent Neural Network (ADNRNN) to resolve this problem. This initiates with preprocessing and scaling peanut entities' regions to normalize the image pixel by reducing the noiseless image. The entries of the peanut image features are observed by covering the exact boundary regions to apply the Space Retention Log Edge Detector (SRLogED) to make sliding segmentation. The sliding segments are normalized to find the matured objects through color quantization by observing pods entities. This is enhanced with Entity scalar histogram equalization (ESHE) by projecting the entities of peanut buds regions to find the scaled weights of features. Then the equivalent distance of matured and non-matured seeds are extracted through the hyperspectral Invariant scaled feature selection method and classified using the Adaptive Dense Net Recurrent Neural Network Algorithm. This proposed system produces high classification results by finding the exact scaled feature dimension to predict the maturity of seed and higher performance to increase the precision rate compared to the other systems.

Decentralized position–force zero-sum approximate optimal control for reconfigurable robots with unmodeled dynamic

In this paper, the position–force–based approximate optimal control method is developed for reconfigurable robots using zero-sum game strategy. By utilizing the Newton–Euler iteration technique, the robotic system’s dynamic model is formulated and the state space equation is derived. According to adaptive dynamic programming (ADP) and neural network algorithm, the trajectory tracking control problem is transformed into a zero-sum game-based optimal control issue. The optimal control policy and worst disturbance policy are obtained by Hamilton–Jacobi–Issacs (HJI) function, respectively. Unlike the conventional learning–based robotic control method, the proposed zero-sum game-based method no need extra sub-controller that can reduce the computational burden. The reconfigurable robot system’s tracking error is uniformly ultimately bounded by the Lyapunov theorem. Finally, simulation experiments demonstrate the advantages of the proposed method.

Brain Tumor Detection using Decision-Based Fusion Empowered with Fuzzy Logic

Brain tumor is regarded as one of the fatal and dangerous diseases on the planet. It is present in the form of uncontrolled and irregular cells in the brain of an infected individual. Around 60% of glioblastomas turn into large tumors if it is not diagnosed earlier. Some valuable literature is available on tumor diagnosis, but there is room for improvement in overall performance. Machine Learning (ML)-based techniques have been widely used in the medical domain for early diagnostic diseases. The use of ML techniques in conjunction with improved image-guided technology may help in improving the performance of the brain tumor detection process. In this work, an ML-based brain tumor detection technique is presented. Adaptive Back Propagation Neural Network (ABPNN) and Support Vector Machine (SVM) algorithms are used along with fuzzy logic. The fuzzy logic is used to fuse the result of ABPNN and SVM. The proposed technique is developed using the BRATS dataset. Experimental results reveal that the ABPNN model achieved 98.67% accuracy in the training phase and 96.72% accuracy in the testing phase. On the other hand, the SVM model has attained 98.48% and 97.70% accuracy during the training and testing phases. After applying fuzzy logic for decision-based fusion, the overall accuracy of the proposed technique reaches 98.79% and 97.81% for the training and the testing phases, respectively. The comparative analysis with existing techniques shows the supremacy of the proposed technique.

A Novel Adaptive Back Propagation Neural Network-Unscented Kalman Filtering Algorithm for Accurate Lithium-Ion Battery State of Charge Estimation

Accurate State of Charge (SOC) estimation for lithium-ion batteries has great significance with respect to the correct decision-making and safety control. In this research, an improved second-order-polarization equivalent circuit (SO-PEC) modelling method is proposed. In the process of estimating the SOC, a joint estimation algorithm, the Adaptive Back Propagation Neural Network and Unscented Kalman Filtering algorithm (ABP-UKF), is proposed. It combines the advantages of the robust learning rate in the Back Propagation (BP) neural network and the linearization error reduction in the Unscented Kalman Filtering (UKF) algorithm. In the BP neural network part, the self-adjustment of the learning factor accompanies the whole estimation process, and the improvement of the self-adjustment algorithm corrects the shortcomings of the UKF algorithm. In the verification part, the model is validated using a segmented double-exponential fit. Using the Ampere-hour integration method as the reference value, the estimation results of the UKF algorithm and the Back Propagation Neural Network and Unscented Kalman Filtering (BP-UKF) algorithm are compared, and the estimation accuracy of the proposed method is improved by 1.29% under the Hybrid Pulse Power Characterization (HPPC) working conditions, 1.28% under the Beijing Bus Dynamic Stress Test (BBDST) working conditions, and 2.24% under the Dynamic Stress Test (DST) working conditions. The proposed ABP-UKF algorithm has good results in estimating the SOC of lithium-ion batteries and will play an important role in the high-precision energy management process.

Adaptive neural network-based sliding mode control for a hydraulic rotary drive joint

Hydraulic system has specific nonlinear and unknown modeling characteristics, realizing precise tracking control is a very challenging task. In this study, a sliding mode controller based on an adaptive higher-order neural network is proposed for realizing precise position-tracking control of a hydraulic rotary drive joint. First, the structural design and working principle of the target joint are introduced, and the mathematical model of the corresponding valve-controlled hydraulic position servo system is developed. Then, the adaptive neural network algorithm and sliding mode control are effectively combined. Based on the measurement information obtained from the control process, the feedback error is used to adaptively approximate the control parameters and realize online adjustment of the controller output. Finally, the parameter identification and position tracking of the system are validated, and the results indicate that the proposed strategy exhibits a 20% improvement in position-tracking control compared to the conventional sliding mode control methods.