Problem Of Poor Accuracy Research Articles

Parameter identification of photovoltaic current loop parameters based on parameter separation

Abstract Accurate control parameters are the basis for analyzing the fault characteristics of PV, but due to technical confidentiality reasons, equipment manufacturers do not provide accurate parameters, so they need to be identified. This paper aims to solve the problem of poor accuracy of the integration coefficient identification of a current loop with low sensitivity by proposing a parameter identification method for a photovoltaic current loop based on parameter separation. By analyzing the current response of the fault and fault recovery stages, the scale coefficient kp and the integration coefficient ki are separated and identified separately. Finally, a simulation system was built on the PSCAD/EMTDC platform, and the validity of the method was verified by using the simulation data.

Research on Fault Diagnosis Method of CNC Machine Tools Based on Integrated MPA Optimised Random Forests

INTRODUCTION: Intelligent diagnosis of CNC machine tool faults can not only early detection and troubleshooting to improve the reliability of machine tool operation and work efficiency, but also in advance of the station short maintenance to extend the life of the machine tool to ensure that the production line of normal production.OBJECTIVES: For the current research on CNC machine tool fault diagnosis, there are problems such as poorly considered feature selection and insufficiently precise methods.METHODS: This paper proposes a CNC machine tool fault diagnosis method based on improving random forest by intelligent optimisation algorithm with integrated learning as the framework. Firstly, the CNC machine tool fault diagnosis process is analysed to extract the CNC machine tool fault features and construct the time domain, frequency domain and time-frequency domain feature system; then, the random forest is improved by the marine predator optimization algorithm with integrated learning as the framework to construct the CNC machine tool fault diagnosis model; finally, the validity and superiority of the proposed method is verified by simulation experiment analysis.RESULTS: The results show that the proposed method meets the real-time requirements while improving the diagnosis accuracy.CONCLUSION: Solve the problem of poor accuracy of fault diagnosis of CNC machine tools and unsound feature system.

Automatic Defect Detection of Jet Engine Turbine and Compressor Blade Surface Coatings Using a Deep Learning-Based Algorithm

The application of additive manufacturing (AM) in the aerospace industry has led to the production of very complex parts like jet engine components, including turbine and compressor blades, that are difficult to manufacture using any other conventional manufacturing process but can be manufactured using the AM process. However, defects like nicks, surface irregularities, and edge imperfections can arise during the production process, potentivally affecting the operational integrity and safety of jet engines. Aiming at the problems of poor accuracy and below-standard efficiency in existing methodologies, this study introduces a deep learning approach using the You Only Look Once version 8 (YOLOv8) algorithm to detect surface, nick, and edge defects on jet engine turbine and compressor blades. The proposed method achieves high accuracy and speed, making it a practical solution for detecting surface defects in AM turbine and compressor blade specimens, particularly in the context of quality control and surface treatment processes in AM. The experimental findings confirmed that, in comparison to earlier automatic defect recognition procedures, the YOLOv8 model effectively detected nicks, edge defects, and surface defects in the turbine and compressor blade dataset, attaining an elevated level of accuracy in defect detection, reaching up to 99.5% in just 280 s.

Optimising Deep Neural Networks for Tumour Diagnosis Algorithms Based on Improved MRFO Algorithm

INTRODUCTION: Cancer has become one of the most prevalent diseases with the highest mortality rate in the world, and timely detection and early acceptance of medical therapeutic interventions are effective means of controlling the progression of cancer patients and improving their post-intervention outcomes.OBJECTIVES: To make the defects of incomplete features, low accuracy and low real-time performance of current tumour diagnosis methods.METHODS: This paper proposes a tumour diagnosis method based on the improved MRFO algorithm to improve the optimization process of DBN network parameters. Firstly, the diagnostic features are extracted by analysing the tumour diagnosis identification problem; then, the manta ray foraging optimization algorithm is improved by combining the good point set initialization strategy, the adaptive control parameter strategy and the distribution estimation strategy, and the tumour diagnostic model based on the improved manta ray foraging optimization algorithm to optimize the parameters of the depth confidence network is constructed; finally, the high accuracy and real-time performance of the proposed method are verified by the analysis of simulation experiments.RESULTS: The results show that the proposed method improves the accuracy of the diagnostic model.CONLUSION: Addresses the problem of poor accuracy and real-time availability of tumour diagnostic methods.

Hardware-in-the-loop simulation test platform for UAV flight control system

The flight control system is the integrated command center and core component of the UAV system. Aiming at the problems of poor accuracy and low efficiency in the field measurement of flight control system parameters, combined with the configuration of the flight attitude sensor-vertical gyroscope, hardware-in-the-loop simulation technology, and integrated automatic test methods are adopted. The hardware-in-the-loop simulation test platform for the UAV flight control system composed of a low-cost, high-precision miniaturized UAV attitude calibration platform and a control piston deflection angle test device is designed. The main controller replaces the ground master control station of the UAV and directly sends remote control commands to the aircraft. By changing the attitude of the aircraft, and measuring the voltage of the control signal, the feedback signal, and the rudder angle, the comprehensive performance test of the parameters of the flight control system is realized. The performance test of the platform shows that the platform can meet the test requirements of angular position, system voltage, and control piston deflection angle.

Surface and Underwater Acoustic Source Recognition Using Array Feature Extraction Based on Machine Learning

Sound source recognition is an important application of passive sonar. How to distinguish between surface and underwater sound sources is always a difficult problem. In order to solve the problem of S/U sound source identification, this paper proposes a machine learning method based on array feature extraction, which has certain innovative value. Firstly, according to the experimental environment of SACLANT 1993, simulation data is generated based on KRAKEN. Secondly, the simulation data and experimental data are used to extract the array features. Thirdly, the accuracy, recall rate, F1 and accuracy of GBDT classifier in three different frequency bands are evaluated. The results show that the training model established by using the array feature extraction method can effectively solve the problem of poor accuracy of some channels in the single channel classification, and obtain good experimental accuracy. Finally, the experimental accuracy of the three bandwidths is 0.9920, 0.9857 and 0.9713, respectively.

Co-occurrence word model for news media hotspot mining-text mining method design.

Currently, with the rapid growth of online media, more people are obtaining information from it. However, traditional hotspot mining algorithms cannot achieve precise and fast control of hot topics. Aiming at the problem of poor accuracy and timeliness in current news media hotspot mining methods, this paper proposes a hotspot mining method based on the co-occurrence word model. First, a new co-occurrence word model based on word weight is proposed. Then, for key phrase extraction, a hotspot mining algorithm based on the co-occurrence word model and improved smooth inverse frequency rank (SIFRANK) is designed. Finally, the Spark computing framework is introduced to improve the computing efficiency. The experimental outcomes expresses that the new word discovery algorithm discovered 16871 and 17921 new words in the Weibo Short News and Weibo Short Text datasets respectively. The heat weight values of the keywords obtained by the improved SIFRANK reaches 0.9356, 0.9991, and 0.6117. In the Covid19 Tweets dataset, the accuracy is 0.6223, the recall is 0.7015, and the F1 value is 0.6605. In the President-elects Tweets dataset, the accuracy is 0.6418, the recall is 0.7162, and the F1 value is 0.6767. After applying the Spark computing framework, the running speed has significantly improved. The text mining news media hotspot mining method based on the co-occurrence word model proposed in this study has improved the accuracy and efficiency of mining hot topics, and has great practical significance.

Avatar-Based Picture Exchange Communication System Enhancing Joint Attention Training for Children With Autism.

Children with Autism Spectrum Disorder (ASD) often struggle with social communication and feel anxious in interactive situations. The Picture Exchange Communication System (PECS) is commonly used to enhance basic communication skills in children with ASD, but it falls short in reducing social anxiety during therapist interactions and in keeping children engaged. This paper proposes the use of virtual character technology alongside PECS training to address these issues. By integrating a virtual avatar, children's communication skills and ability to express needs can be gradually improved. This approach also reduces anxiety and enhances the interactivity and attractiveness of the training. After conducting a T-test, it was found that PECS assisted by a virtual avatar significantly improves children's focus on activities and enhances their behavioral responsiveness. To address the problem of poor accuracy of gaze estimation in unconstrained environments, this study further developed a visual feature-based gaze estimation algorithm, the three-channel gaze network (TCG-Net). It utilizes binocular images to refine the gaze direction and infer the primary focus from facial images. Our focus was on enhancing gaze tracking accuracy in natural environments, crucial for evaluating and improving Joint Attention (JA) in children during interactive processes.TCG-Net achieved an angular error of 4.0 on the MPIIGaze dataset, 5.0 on the EyeDiap dataset, and 6.8 on the RT-Gene dataset, confirming the effectiveness of our approach in improving gaze accuracy and the quality of social interactions.

Enhanced lightweight deep network for efficient livestock detection in grazing areas

There are problems in the special pastoral environment, including large changes in target size and serious interference from light and environmental factors. To solve the above problems, an enhanced YOLOv4-tiny target detection network is proposed in this study. This network first solves the problem of livestock size fluctuation in pastoral areas, uses a pyramid network with multiscale feature fusion, and considers shallow local detail features and deep semantic information. Subsequently, a novel compound multichannel attention mechanism is proposed to increase the accuracy of the target detection network for the pastoral environment. The problem of poor accuracy of target detection network is solved. The algorithm is ported to Jetson AGX embedded platform for validation to examine the real-time performance of the algorithm. As revealed by the experimental results, enhanced YOLOv4-tiny achieves 89.77% detection accuracy and 30 frames/second detection speed, which increases the average detection accuracy by 11.67% compared with the conventional YOLOv4-tiny while maintaining almost the same detection rate.

Rapid Detection of Total Viable Count in Intact Beef Dishes Based on NIR Hyperspectral Hybrid Model

The total viable count (TVC) of bacteria is an important index to evaluate the freshness and safety of dishes. To improve the accuracy and robustness of spectroscopic detection of total viable bacteria count in a complex system, a new method based on a near-infrared (NIR) hyperspectral hybrid model and Support Vector Machine (SVM) algorithms was developed to directly determine the total viable count in intact beef dish samples in this study. Diffuse reflectance data of intact and crushed samples were tested by NIR hyperspectral and processed using Multiplicative Scattering Correction (MSC) and Competitive Adaptive Reweighted Sampling (CARS). Kennard–Stone (KS) and Samples Set Partitioning Based on Joint X-Y Distance (SPXY) algorithms were used to select the optimal number of standard samples transferred by the model combined with root mean square error. The crushed samples were transferred into the complete samples prediction model through the Direct Standardization (DS) algorithm. The spectral hybrid model of crushed samples and full samples was established. The results showed that the Determination Coefficient of Calibration (RP2) value of the total samples prediction set increased from 0.5088 to 0.8068, and the value of the Root Mean Square Error of Prediction (RMSEP) decreased from 0.2454 to 0.1691 log10 CFU/g. After establishing the hybrid model, the RMSEP value decreased by 9.23% more than before, and the values of Relative Percent Deviation (RPD) and Reaction Error Relation (RER) increased by 12.12% and 10.09, respectively. The results of this study showed that TVC instewed beef samples can be non-destructively determined based on the DS model transfer method combined with the hybrid model strategy. This study provided a reference for solving the problem of poor accuracy and reliability of prediction models in heterogeneous samples.

Examination and Repair of Technology of Equipment Status Based on SNN in Intelligent Substation

Aiming at the problems of poor accuracy and low reliability in equipment evaluation and decision results of examination and repair (E&R) for the traditional power system (P-S) state, an E&R technology of intelligent substation (INSU) equipment state based on SNN is proposed. Firstly, based on the operational status of devices and systems in the intelligent substation (INSU), the E&R risks of devices and systems in INSU are evaluated through analysis of device availability. Then, by analyzing traditional CNN and improved SNN networks, a P-S state E&R model for power equipment detection based on SNN is proposed. Finally, a simulation experiment was conducted to compare and analyze the proposed SNN-based INSU device state E&R model with other methods. The results show that the proposed method has a lower system risk in the E&R process and is superior to other comparison methods.

3D Simulation and Leakage Detection Technique for Deep Foundation Pits Based on Electric Field

To solve the problems of poor accuracy, poor anti-interference ability and unclear distribution of leakage electric field response characteristics of the traditional ground DC method for leakage detection of underground diaphragm walls in foundation pits, this paper proposes a deep foundation pit leakage detection technology based on the electric field. Secondly, it constructed the multi-field coupling equations and boundary conditions of the leakage electric field coupled with the leakage flow field and ion diffusion field, and then realized the three-dimensional forward evolution of the leakage electric field of the pit using the nonstructural mesh dissection method and the finite-element-infinite-element discretization method. Finally, physical model experiments and numerical simulations are used to confirm the reliability and accuracy of the foundation pit leakage detection technology and system. The results shows that monitoring the continuous change of the electric field for a period of time, the electric field detection technology for foundation pit leakage can effectively identify the location of hidden leakage and overcome the site’s strong industrial interference, resulting in a new technical solution for foundation pit leakage detection.

Optimizing prior distribution parameters for probabilistic prediction of remaining useful life using deep learning

In this study, a deep learning-based probabilistic remaining useful life (RUL) prediction model is proposed to improve the strong prior limitations of traditional probabilistic RUL prediction methods through a flexible prior distribution and strategy for sequential optimization of hyperparameters with regularization factor. It enables output richer probabilistic lifetime density distributions and confidence intervals with various parameters and overcome the problem of poor accuracy of short RUL predictions to some extent. Eventually, the model is effectively validated on a benchmark dataset, and the experimental results show that the probabilistic lifetime prediction model with optimized prior distribution parameters significantly improves prediction performance and demonstrates good learning performance and robustness of test results compared with traditional point estimation methods and parameter-free models. This study informs maintenance decisions and reliability assessments in engineering systems and guides the research and application of probabilistic-based prediction methods in deep learning framework.

Research on unmanned vehicle obstacle avoidance technology based on LIDAR and depth camera fusion

Abstract To address the problems of poor accuracy of traditional EKF algorithm in estimating the position of unmanned vehicles and the deficiencies in accuracy and map completeness of the traditional map building method with single-line LiDAR, this paper proposes a method to create fused raster maps realized with multi-source data. Firstly, the combined data of the inertial measurement unit and wheel encoder are corrected by adding the positional information output from the visual odometer using the error-state SLAM algorithm, and the local raster constructed by LiDAR and depth camera is fused frame by frame using the idea of Bayesian estimation to finally generate the fused global map. Then, a four-wheeled mobile unmanned vehicle with a LiDAR sensor and depth camera is selected as the experimental object, and dynamic environment avoidance simulation experiments are conducted to draw conclusions. The simulation experiment results show that when γ = 5.99, the algorithm generates a new local target point p g 2 (17.49, 13.49) and the corresponding getaway path and finally guides the unmanned vehicle to the specified target point, verifying that the method in this paper can achieve the avoidance capability of the unmanned vehicle in the process of getting away from the newly emerged obstacles. This study uses the scanned data of LiDAR for the estimation of the real-time position of the unmanned vehicle to realize obstacle avoidance and path planning of the unmanned vehicle.

An RNN With Small Sequence Trained by Multi-Level Optimization for SOC Estimation in Li-Ion Battery Applications

To ensure safe operation, the high-precision estimation of the state of charge (SOC) in the battery management system (BMS) is relied on. The classical recurrent neural network (RNN) has a gradient and poor accuracy problem, and the RNN with additional gates is complex and hard to apply in engineering. To address these issues, the RNN with small sequence trained by multi-level optimization is proposed in this paper to improve the accuracy and the gradient problem of the SOC estimation. First, the small sequence is introduced to improve the gradient problem and running speed of RNN and the SOC post filter is used to increase the continuity of SOC estimation. Then, the particle swarm optimization (PSO) is used to pre-train the RNN to obtain the optimal weight and threshold value, and the hybrid optimizer of Adam and stochastic gradient descent (SGD) is utilized to improve the accuracy of SOC estimation. The experimental data of the charging and discharging test, and the performances of the proposed method, the nonlinear autoregressive with exogeneous inputs neural network (NARX), RNN, long short-term memory (LSTM), and gated recurrent unit (GRU) for estimating the SOC of lithium batteries are compared. The results show that the estimation error of the RNN is within 3.66% and that of NARX is within 6%, and the proposed method, LSTM, and GRU reduce the error to 0.47%, 1.04%, and 0.48%, respectively. Moreover, the calculation time of the proposed method is 1/3 and 1/9 of that of LSTM and GRU. Besides, the proposed method is robust to different vehicle cycles, measurement noises, temperature variations, and battery aging.

A Multiscale Local–Global Feature Fusion Method for SAR Image Classification with Bayesian Hyperparameter Optimization Algorithm

In recent years, the advancement of deep learning technology has led to excellent performance in synthetic aperture radar (SAR) automatic target recognition (ATR) technology. However, due to the interference of speckle noise, the task of classifying SAR images remains challenging. To address this issue, a multi-scale local–global feature fusion network (MFN) integrating a convolution neural network (CNN) and a transformer network was proposed in this study. The proposed network comprises three branches: a CovNeXt-SimAM branch, a Swin Transformer branch, and a multi-scale feature fusion branch. The CovNeXt-SimAM branch extracts local texture detail features of the SAR images at different scales. By incorporating the SimAM attention mechanism to the CNN block, the feature extraction capability of the model was enhanced from the perspective of spatial and channel attention. Additionally, the Swin Transformer branch was employed to extract SAR image global semantic information at different scales. Finally, the multi-scale feature fusion branch was used to fuse local features and global semantic information. Moreover, to overcome the problem of poor accuracy and inefficiency of the model due to empirically determined model hyperparameters, the Bayesian hyperparameter optimization algorithm was used to determine the optimal model hyperparameters. The model proposed in this study achieved average recognition accuracies of 99.26% and 94.27% for SAR vehicle targets under standard operating conditions (SOCs) and extended operating conditions (EOCs), respectively, on the MSTAR dataset. Compared with the baseline model, the recognition accuracy has been improved by 12.74% and 25.26%, respectively. The results demonstrated that Bayes-MFN reduces the inter-class distance of the SAR images, resulting in more compact classification features and less interference from speckle noise. Compared with other mainstream models, the Bayes-MFN model exhibited the best classification performance.

Performance Analysis of Integrated Navigation of New Energy vehicle based on GPS+BDS-3 PPP/INS/ODO in complex Transmission Line Environment

In a complex environment, the single navigation and positioning method has problems of poor accuracy, reliability, and integrity. This paper proposes a PPP/INS/ODO integrated navigation scheme of GPS+BDS-3. Using the GPS+BDS-3 dual system, the non-ionization combined PPP model is derived, the PPP/INS/ODO combined model is further given, and the processing strategy of time asynchrony and lever arm error is analyzed. Combining the odometer speed measurement information and non-integrity constraint information, it improves the positioning performance of integrated navigation to a certain extent. In the state of GPS+BDS-3 non-ionization combination, PPP and PPP/INS/ODO integrated navigation are analyzed respectively using the simulated dynamic, and new energy measured data. Through the experiment, it can be concluded that the positioning accuracy of the combination of GPS and Beidou 3 is higher than that of a single system to some extent. The PPP/INS/ODO integrated system can provide technical support for new energy vehicle navigation in complex environments with RMS better than 1m.

Sine-SSA-BP Ship Trajectory Prediction Based on Chaotic Mapping Improved Sparrow Search Algorithm.

In this paper, we propose a Sine chaos mapping-based improved sparrow search algorithm (SSA) to optimize the BP neural network for trajectory prediction of inland river vessels because of the problems of poor accuracy and easy trapping in local optimum in BP neural networks. First, a standard BP model is constructed based on the AIS data of ships in the Yangtze River section. A Sine-BP model is built using Sine chaos mapping to assign neural network weights and thresholds. Finally, a Sine-SSA-BP model is built using the sparrow search algorithm (SSA) to solve the optimal solutions of the neural network weights and thresholds. The Sine-SSA-BP model effectively improves the initialized population of uniform distribution, and reduces the problem that population intelligence algorithms tend to be premature. The test results show that the Sine-SSA-BP neural network has higher prediction accuracy and better stability than conventional LSTM and SVM, especially in the prediction of corners, which is in good agreement with the real ship navigation trajectory.

Temperature Prediction for Subway Station Based on LSTM-SVR Algorithm with Multi Period Characteristics

By analyzing the timing characteristics of historical temperature data of the subway sensors, aiming at the problem of poor accuracy of a single temperature prediction model, combined with the long-term trend, multi period and irregular change characteristics of the temperature data, this paper proposes a combined prediction model based on the Long Short-Term Memory network (LSTM) and Support Vector Regression (SVR) theory, the prediction mean error of LSTM-SVR is lower than single model, which can predict the temperature of subway station with high accuracy, so as to provide a basis for controlling air-conditioning and ventilation equipment, also saving energy and reducing consumption.

Improved YOLOX Foreign Object Detection Algorithm for Transmission Lines

It is quite simple for foreign objects to attach themselves to transmission line corridors because of the wide variety of laying and the complex, changing environment. If these foreign objects are not found and removed in a timely manner, they can have a significant impact on the transmission lines’ ability to operate safely. Due to the problem of poor accuracy of foreign object identification in transmission line image inspection, we provide an improved YOLOX technique for detection of foreign objects in transmission lines. The method improves the YOLOX target detection network by first using Atrous Spatial Pyramid Pooling to increase sensitivity to foreign objects of different scales, then by embedding Convolutional Block Attention Module to increase model recognition accuracy, and finally by using GIoU loss to further optimize. The testing findings show that the enhanced YOLOX network has a mAP improvement of around 4.24% over the baseline YOLOX network. The target detection SSD, Faster R-CNN, YOLOv5, and YOLOV7 networks have improved less than this. The effectiveness and superiority of the algorithm are proven.