Problem Of Accuracy Research Articles

A novel intelligent risk prediction model for the effectiveness of CO2/N2–ECGD technology

AbstractTo solve the problems of high sampling requirements and low predictive accuracy resulting from the complexity, uniqueness, and randomness of predicting the risk of the CO2 and N2 injection to enhance coal seam gas drainage (CO2/N2–ECGD) technology. The principal component analysis (PCA) method to reduce the dimensionality of the factor data that contribute to the effect risk of the technology was adopted. And the particle swarm optimization (PSO) method was implemented to search for optimal hyperparameters in support vector machine (SVM) by particle search, as a solution to the traditional SVM hyperparameters optimization problem. A novel risk prediction model using machine learning algorithms for gas injection displacement technology was constructed. The prediction results were tested and compared with those of backpropagation (BP), Random Forest (RF), and Decision Tree (DT) models using data from 29 gas injection displacement field projects in China. The results demonstrated that the SVM model had greater accuracy in prediction than the other three models. Additionally, after PSO optimization and dimensionality reduction, the PCA–PSO–SVM model reached 100% prediction accuracy, while requiring less modeling and operation time. The study provided a reliable and reasonable model for predicting technical effects, along with a theoretical basis for risk management and prevention. First, the technology's influencing indicators were analyzed by examining its mechanisms. Second, we utilized the PCA method to reduce the dimensionality of the factor data that contribute to the risk of the technology's effects. Third, we implemented the PSO method to search for optimal hyperparameters in the SVM through particle search, as a solution to the traditional SVM hyperparameters optimization problem. Finally, the prediction results were tested and compared with those of BP, RF, and DT models using data from 29 gas injection displacement field projects in China. The SVM model was found to have greater accuracy in prediction than the other three models. After PSO optimization and dimensionality reduction, the PCA–PSO–SVM model achieved 100% prediction accuracy while requiring less modeling and operation time. The study presents a valid and reasonable model for predicting technical effects and a theoretical basis for risk management and prevention.

SPLINE OPTIMIZATION OF SOFT CONNECTIVES IN MACHINE LEARNING MODELS

In this study, the problem of limited accuracy of machine learning models using soft logical connectives is investigated. Such connectives have shown their effectiveness in models with fuzzy initial data. On the one hand, the fundamental disadvantage of soft connectives is their non-associativity. On the other hand, the disadvantages of the currently used soft connectives include the loss of monotonicity and the inability to control several factors simultaneously. All these problems have been solved by the authors. We have proposed an approximation of the signum function by a ?1-smooth spline. The first part of the spline is responsible for the curvature of the connective at the diagonal and is adjustable. The second part of the spline is the solution to the optimization problem. We minimized the difference between the connective and the associative connective, the latter in our study was the minimum function. In the resulting solution, the rate of deviation reduction is the highest among known connectives. We have achieved not only a small deviation from associativity, but also the presence of a large domain of exact associativity. This area is up to a third of the volume of all triples of arguments. A comparative analysis of the currently used soft connectives with the constructed model was carried out. It was shown that the spline approximation is able to reduce the influence of all negative factors and is more flexible in setting. Moreover, the constructed spline model allows numerous modifications depending on the factor that requires the most attention for different tasks.

Identification of Fish Hunger Degree with Deformable Attention Transformer

Feeding is a critical process in aquaculture, as it has a direct impact on the quantity and quality of fish. With advances in convolutional neural network (CNN) and vision transformer (ViT), intelligent feeding has been widely adopted in aquaculture, as the real-time monitoring of fish behavior can lead to better feeding decisions. However, existing models still have the problem of insufficient accuracy in the fish behavior-recognition task. In this study, the largemouth bass (Micropterus salmoides) was selected as the research subject, and three categories (weakly, moderately, and strongly hungry) were defined. We applied the deformable attention to the vision transformer (DeformAtt-ViT) to identify the fish hunger degree. The deformable attention module was extremely powerful in feature extraction because it improved the fixed geometric structure of the receptive fields with data-dependent sparse attention, thereby guiding the model to focus on more important regions. In the experiment, the proposed DeformAtt-ViT was compared with the state-of-the-art transformers. Among them, DeformAtt-ViT achieved optimal performance in terms of accuracy, F1-score, recall, and precision at 95.50%, 94.13%, 95.87%, and 92.45%, respectively. Moreover, a comparative evaluation between DeformAtt-ViT and CNNs was conducted, and DeformAtt-ViT still dominated the others. We further visualized the important pixels that contributed the most to the classification result, enabling the interpretability of the model. As a prerequisite for determining the feed time, the proposed DeformAtt-ViT could identify the aggregation level of the fish and then trigger the feeding machine to be turned on. Also, the feeding machine will stop working when the aggregation disappears. Conclusively, this study was of great significance, as it explored the field of intelligent feeding in aquaculture, enabling precise feeding at a proper time.

Impact of medical bloggers’ activities on the prevention of disease risk, public, population and individual health: the opinion of social media users

Due to the high information and communication importance and potential of the medical blogosphere in the formation of health literacy of the population, there is the increased need to study the opinions of Russian social media users on the impact of the content of medical blogs on personal and public health. Aim of the study was to find out the opinion of social media users on the extent to which the activities of bloggers specializing in public health and health care topics influence the prevention of major non-communicable and infectious diseases, public and personal health, within the changing boundaries of medical knowledge broadcasting (using sociological methods). Material and methods. The authors conducted a quantitative sociological survey of 178 respondents - users of social media: 55 (30.9 %) women and 123 (69.1 %) men about visiting blogs specializing in public health and healthcare. The collection of information was carried out by e-mailing a questionnaire developed by the authors, and analyzed the answers to questions from active blog users through a Google form in April – May 2023. Results. The study results of the impact of bloggers’ activities on personal and public health, including those related to the quality of medical information disseminated in social media, are described. Respondents believe that medical bloggers have a greater impact on public health than personal health. At the same time, according to the respondents, the spheres of influence in the field of public health do not coincide with the spheres of influence in the field of personal health. Thus, 74.7 % of respondents believe that medical bloggers have an impact on maintaining a healthy lifestyle of the population, prevention (61.8 % of all respondents think so) and treatment of infectious diseases (61.2 %). The requirements for the quality of information provided by bloggers are considered. Based on the analysis of Russian and foreign scientific literature, the authors developed a graphical diagram of the effect of dissemination through the blogosphere of information in the field of health care and disease prevention. Conclusions. The content published on medical blogs affects the health literacy of the population. That is why, medical blogs can be seen as a social determinant of health, because health blogs can be the key to the success of disease prevention and control efforts for public health maintaining. For organizing a communication intervention of medical personnel in social media to inform the population about methods for preventing the risk of developing major non-communicable and infectious diseases and increasing the level of health literacy of the population, medical blogs can and should be used to inform and educate patients as part of general or targeted multimodal educational practices or as a means of delivering electronic content. The risks of publishing inaccurate information in the blogosphere must be considered, whereby patients can easily become misinformed, which can have serious consequences for their health, and even increase their risk of mortality. To make the best use of the blogosphere, it is necessary to solve the problems of content accuracy and increase the level of professionalism of bloggers who write on medical topics. They need to be professionally trained to work for health, contributing to the prevention of the risk of developing major non-communicable and communicable diseases, improving the health of the population through education, and raising the level of health literacy. It makes sense to assess the success of the communicative intervention of doctors in social media and their management of the training of medical bloggers as a personnel determinant of public health, since it will depend on the personnel potential of the healthcare sector.

An Instance Segmentation Method for Insulator Defects Based on an Attention Mechanism and Feature Fusion Network

Among the existing insulator defect detection methods, the automatic detection of inspection robots based on the instance segmentation algorithm is relatively more efficient, but the problem of the limited accuracy of the segmentation algorithm is still a bottleneck for increasing inspection efficiency. Therefore, we propose a single-stage insulator instance defect segmentation method based on both an attention mechanism and improved feature fusion network. YOLACT is selected as the basic instance segmentation model. Firstly, to improve the segmentation speed, MobileNetV2 embedded with an scSE attention mechanism is introduced as the backbone network. Secondly, a new feature map that combines semantic and positional information is obtained by improving the FPN module and fusing the feature maps of each layer, during which, an attention mechanism is introduced to further improve the quality of the feature map. Thirdly, in view of the problems that affect the insulator segmentation, a Restrained-IoU (RIoU) bounding box loss function which covers the area deviation, center deviation, and shape deviation is designed for object detection. Finally, for the validity evaluation of the proposed method, experiments are performed on the insulator defect data set. It is shown in the results that the improved algorithm achieves a mask accuracy improvement of 5.82% and a detection speed of 37.4 FPS, which better complete the instance segmentation of insulator defect images.

An imbalance multi-faults data transfer learning diagnosis method based on finite element simulation optimization model of rolling bearing

In practical engineering applications, rotating machinery is often in a healthy state, with more healthy samples and fewer multi-faults samples, which leads to be misdiagnosed. A finite element simulation model (FEM) is proposed to expand imbalanced multi-faults sample data. However, there is a significant difference in vibration response between the FEM simulation data and the measured data collected on the rotating machinery. Therefore, a method based on vibration response eigenvalue model correction has been adopted, aiming to narrow the gap between the simulation data and the measured data. In order to solve the problem of low accuracy of sample imbalance fault diagnosis under different working conditions, a transfer learning (TL) fault diagnosis method based on finite element simulation optimization model of rolling bearings to supplement imbalanced multi-fault data is proposed. Firstly, the FEM of healthy bearings is established, and the optimal radial clearance of bearings is obtained by modifying the vibration response eigenvalue model. Then, corresponding simulated fault vibration responses were obtained by setting composite faults on the optimal model. Finally, supplementing the unbalanced fault data with simulation data to create a mixed balanced dataset as samples, the TL model is trained to accomplish intelligent fault diagnosis for multi-faults. The experimental results show that using mixed data as training samples to train neural network models can improve the accuracy of transfer learning fault diagnosis by over 10%. Expanding fault samples by modifying the bearing clearance of the FEM is an effective method to address sample imbalance.

Statement of requirements on the accuracy of rocket CFD analysis using exterior ballistics for example rocket models

In this paper, the problem of acceptable accuracy of a rocket’s aerodynamic characteristics obtained from CFD (computational fluid dynamics) analysis for defining its aerodynamic characteristics is considered from the point of view of exterior ballistics, particularly by the estimation of the rocket’s simulated flight range change caused by CFD errors. The results obtained in this paper allow stating the requirement on acceptable accuracy of defining the aerodynamic characteristics for developing new rockets through CFD analysis based on several examples, which can be propagated to other cases of rocket design and development. Using this study as a method, the CFD engineers who work on rocket design and development can estimate the accepted accuracy margin of their CFD analysis and research solutions to get reliable results for the expected flight characteristics of the rocket.

Intelligent vehicle trajectory tracking control based on physics-informed neural network dynamics model

In order to solve the accuracy problem of trajectory tracking control method based on data-driven model, an intelligent vehicle trajectory tracking control method based on physics-informed neural network (PINN) vehicle dynamics model is proposed. Aiming at the problem of poor interpretability of data-driven model, a vehicle dynamics model based on the PINN is established, and the physics-driven deep learning method is used instead of the data-driven deep learning method to obtain the dynamic characteristics of the intelligent vehicle, to benefit from both the physical-based method and the data-driven method. A sequential training method is also proposed to solve the coupling problem when training multiple PINNs simultaneously. The model takes the nonlinearity of the neural network model and physical interpretability into consideration compared to the standard neural network model. Then, based on the PINN vehicle dynamics model, a trajectory tracking controller based on the iterative linear quadratic regulator (ILQR) control algorithm is developed. The optimal control law is derived by optimizing the ILQR control algorithm to implement the intelligent vehicle’s precise and stable tracking for the desired trajectory. The Levenberg-Marquardt (LM) algorithm and line search technology are used and damping factor adjustment rules are set up to enhance the convergence performance of the ILQR control algorithm. In order to verify the effectiveness of the proposed method, the simulation is conducted under the condition of double lane change. The simulation results demonstrate that the proposed method can track the reference trajectory accurately under the limited conditions. Its control performance is much better than other algorithms.

Sensorless control of permanent magnet synchronous motor based on improved sliding mode observer

Aiming at the problems of chattering and low accuracy of rotor position observation in traditional sliding mode observer sensorless control of permanent magnet synchronous motor, an improved sliding mode observer sensorless control method is proposed. First, the sigmoid function is used to replace the traditional switching function, which can effectively improve the chattering problem of the sliding mode observer. Then, an adaptive back electromotive force observer is designed to avoid the use of low-pass filter and phase compensation and reduce the high-frequency harmonics in the back electromotive force estimation. Finally, the speed and rotor position information are obtained by improving the phase-locked loop, and the fundamental harmonics caused by the inverter nonlinearity are suppressed. The simulation and experimental results show that the improved sliding mode observer can effectively weaken the chattering problem of the system, and improve the position observation accuracy and the robustness of the system.

OPTIMASI SENSOR KOMPAS DENGAN METODE CIRCLE EQUATION PADA ROBOT SEPAK BOLA BERODA GERHANA DEWARUCI

The Indonesian Robot Contest (IRC) is an annual activity carried out by the National Achievement Center in the year of the change of government cabinet which was previously carried out by the Ministry of Research, Technology, and Higher Education. IRC has several competition categories, one of which is the Indonesian Wheeled Soccer Robot Contest. Most robots have accuracy problems in the navigation system during the game due to an error in the compass that is used to compare the gyroscope. As a result, many robots are inaccurate and even misdirected, both when attacking or defending. With these problems, one solution is to use the circle equation as a compass sensor filter, so that the robot can have an accurate navigation system, deviations from readings on the CMPS12 sensor can be reduced through the filtering process and have a large enough impact on the normalization process of CMPS12 sensor readings evenly. average error of 10° (degrees). With the addition of the circle equation method, the CMPS12 sensor reading data becomes more accurate with an average error of 1.08° (degrees). Compared with the kalman fillter method with CMPS12 sensor reading data which has an average error of 4 ° (degrees). In this research, the compass sensor is used to compare the gyroscope sensor by changing the gyroscope value using the reference reading of the CMPS12 value as a correction for gyroscope readings that are not in accordance with the set points and an average angle error of 0.6 ° (degrees) and 0.88 ° ( degrees) after the addition of the circle equation method. This method is better than the kalman fillter method with an average error of 3.1° (degrees) and 4.4° (degrees) but is better than that without the method with an average error of 3.6° (degrees) and 5 ,72° (degrees). The resulting error is smaller and can still be tolerated. CMPS12 as a gyroscope comparison can work well in this test because the wheeled KRSBI robot is designed so that the direction of the robot faces is appropriate, with a minimum error in each direction of motion.

Real-time pose estimation and motion tracking for motion performance using deep learning models

Abstract With the refinement and scientificization of sports training, the demand for sports performance analysis in the field of sports has gradually become prominent. In response to the problem of low accuracy and poor real-time performance in human pose estimation during sports, this article focused on volleyball sports and used a combination model of OpenPose and DeepSORT to perform real-time pose estimation and tracking on volleyball videos. First, the OpenPose algorithm was adopted to estimate the posture of the human body region, accurately estimating the coordinates of key points, and assisting the model in understanding the posture. Then, the DeepSORT model target tracking algorithm was utilized to track the detected human pose information in real-time, ensuring consistency of identification and continuity of position between different frames. Finally, using unmanned aerial vehicles as carriers, the YOLOv4 object detection model was used to perform real-time human pose detection on standardized images. The experimental results on the Volleyball Activity Dataset showed that the OpenPose model had a pose estimation accuracy of 98.23%, which was 6.17% higher than the PoseNet model. The overall processing speed reached 16.7 frames/s. It has good pose recognition accuracy and real-time performance and can adapt to various volleyball match scenes.

Enhancing Accuracy and Consistency in the Valuation of Plant and Equipment through Cubic Regression Models of Physical Deterioration

The valuation of plant and equipment often involves valuers deducting physical, functional and economic depreciation from replacement cost estimates. These calculations have faced accuracy and consistency problems in the aspect of determining how much physical deterioration should be deducted. This study attempted to develop cubic regression models to resolve these accuracy and consistency problems in the basic metal, iron and steel and fabricated metal product sectors in Ogun state, Nigeria (Sango Ota and Agbara). Questionnaire surveys were administered on senior operators of plant and equipment in these sectors to draw information on the degree of physical deterioration of plant and equipment over service life, using expenditure on repairs as a proxy for physical deterioration. The questionnaire sought information on the service lives of plant and equipment, the pattern of physical depreciation over the service lives, and the degree to which the pattern is influenced by various operational factors. Data were analysed using means, standard deviations, multiple linear regressions and cubic regressions, to produce what could be the first potentially accurate and consistent valuation model of physical deterioration in Africa. The service lives of various plant and equipment were found to range at various times between 8 to 60 years. Cubic regression analyses showed that the pattern of the movement of transitions of expenditure on repairs (proxy for physical deterioration) over useful life of plant and equipment were not linear but cubic, and generally followed S-shaped patterns. Multiple regression analyses showed that the S-shaped patterns were in turn influenced by operational factors (such as intensity of use and power outages). The study concluded that valuers’ interests in accuracy and consistency in plant and equipment valuation were not served by any of the accounting methods hitherto used by valuers; accuracy in physical deterioration modelling follows an S-shaped transition over time.

Application of One-Dimensional Hydrodynamic Coupling Model in Complex River Channels: Taking the Yongding River as an Example

River conditions are complex and affected by human activities. Various hydraulic structures change the longitudinal slope and cross-sectional shape of the riverbed, which has a significant impact on the simulation of water-head evolution. With continuous population growth, the hydrological characteristics of the Yongding River Basin have undergone significant changes. Too little or too much water discharge may be insufficient to meet downstream ecological needs or lead to the wastage of water resources, respectively. It is necessary to consider whether the total flow in each key section can achieve the expected value under different discharge flows. Therefore, a reliable computer model is needed to simulate the evolution of the water head and changes in the water level and flow under different flow rates to achieve efficient water resource allocation. A one-dimensional hydrodynamic coupling model based on the Saint-Venant equations was established for the Yongding River Basin. Different coupling methods were employed to calibrate the coupling model parameters, using centralised water replenishment data for the autumn of 2022, and the simulation results were verified using centralised water replenishment data for the spring of 2023. The maximum error of the water-head arrival time between different river sections was 4 h, and the maximum error of the water-head arrival time from the Guanting Reservoir to each key cross-section was 6 h. The maximum flow error was less than 5 m3/s, and the changing trend of the flow over time was consistent with the measured data. The model effectively solved the problem of low accuracy of the water level and flow calculation results when using the traditional one-dimensional hydrodynamic model to simulate the flow movement of complex river channels in the Yongding River. The output results of the model include the time when the water head arrives at the key section, the change process of the water level and flow of each section, the change process of the water storage of lakes and gravel pits, and the change process of the total flow and water surface area of the key section. This paper reports data that support the development of an ecological water compensation scheme for the Yongding River.

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.

The relationship between subjective difficulty in interoceptive processing and accuracy of heartbeat perception in autistic individuals

Most autistic people experience difficulties in sensory processing, including interoceptive processing. For example, they often report subjective difficulties in the interoceptive processing of interoceptive input, such as difficulty in interpreting bodily signals, including hunger, thirst, and fatigue. However, whether these subjective interoceptive difficulties are from underlying problems in interoceptive accuracy remains unclear. This study investigated the relationship between subjective interoceptive difficulty and behavioral interoceptive accuracy in autistic adults and a control group. Subjective interoceptive accuracy was measured using an interoceptive sensitivity questionnaire, and behavioral interoceptive accuracy was measured using a heartbeat counting task. The results showed no significant relationship between subjective interoceptive difficulty and behavioral interoceptive accuracy in the autistic or control groups. This suggests that subjective interoceptive difficulty and behavioral interoceptive accuracy reflect different aspects of interoceptive processing. One possible interpretation is that autistic adults can identify individual local sensory inputs, such as heartbeats, however, they have difficulty integrating multiple inputs and recognizing internal body states such as hunger and fatigue.

Evaluating extinct pseudosuchian body mass estimates using a femur volume-based model.

The clade Pseudosuchia appeared 250 million years ago. The exclusively semi-aquatic Crocodylia, which includes crocodiles, alligators, caimans, and gharials is the only surviving subgroup. Investigating Crocodylia biology is pivotal for inferring traits of extinct pseudosuchians. Alligator femur length is widely used for modeling pseudosuchian body mass, but the regression is influenced by sex and captivity status, leading to potential accuracy problems. An alternative model results from the correlation between alligator femur volume and body mass, which is unaffected by those covariates. Here, an alligator femur volume-based regression is applied to estimate the masses of non-crocodylian pseudosuchians, encompassing goniopholids, dyrosaurs, notosuchians, and thalattosuchians. For each, femur volume as the predictor yields lower body masses than does femur length. Morphological resemblances to existing crocodylians support the inference that extinct goniopholids and dyrosaurs were semi-aquatic. Therefore, body masses predicted from femur length and volume should be reasonable, although larger body masses obtained from femur length may reflect sensitivity to sex or environmental factors. Fully terrestrial notosuchians had proportionately longer femora for their body sizes compared to semi-aquatic crocodylians, suggesting that the higher body masses predicted from alligator femur length are overestimates. Fully aquatic thalattosuchians, skeletally adapted for buoyancy and with reduced reliance on the femur for locomotion, pose challenges for both femur length and volume-based models. The results of this study advocate for the use of femur volume to predict body mass, particularly for semi-aquatic and terrestrial pseudosuchians, and encourage further exploration of volumetric models as body size predictors for extinct vertebrates.

DDPG-Based Convex Programming Algorithm for the Midcourse Guidance Trajectory of Interceptor

To address the problem of low accuracy and efficiency in trajectory planning algorithms for interceptors facing multiple constraints during the midcourse guidance phase, an improved trajectory convex programming method based on the lateral distance domain is proposed. This algorithm can achieve fast trajectory planning, reduce the approximation error of the planned trajectory, and improve the accuracy of trajectory guidance. First, the concept of lateral distance domain is proposed, and the motion model of the midcourse guidance segment in the interceptor is converted from the time domain to the lateral distance domain. Second, the motion model and multiple constraints are convexly and discretely transformed, and the discrete trajectory convex model is established in the lateral distance domain. Third, the deep reinforcement learning algorithm is used to learn and train the initial solution of trajectory convex programming, and a high-quality initial solution trajectory is obtained. Finally, a dynamic adjustment method based on the distribution of approximate solution errors is designed to achieve efficient dynamic adjustment of grid points in iterative solving. The simulation experiments show that the improved trajectory convex programming algorithm proposed in this paper not only improves the accuracy and efficiency of the algorithm but also has good optimization performance.

Large Span Sizes and Irregular Shapes Target Detection Methods Using Variable Convolution-Improved YOLOv8.

In this work, an object detection method using variable convolution-improved YOLOv8 is proposed to solve the problem of low accuracy and low efficiency in detecting spanning and irregularly shaped samples. Aiming at the problems of the irregular shape of a target, the low resolution of labeling frames, dense distribution, and the ease of overlap, a deformable convolution module is added to the original backbone network. This allows the model to deal flexibly with the problem of the insufficient perceptual field of the target corresponding to the detection point, and the situations of leakage and misdetection can be effectively improved. In order to solve the issue that small target detection is susceptible to image background and noise interference, the Sim-AM (simple parameter-free attention mechanism) module is added to the backbone network of YOLOv8, which enhances the attention to the underlying features and, thus, improves the detection accuracy of the model. More importantly, the Sim-AM module does not need to add parameters to the original network, which reduces the computation of the model. To address the problem of complex model structures that can lead to slower detection, the spatial pyramid pooling of the backbone network is replaced with focal modulation networks, which greatly simplifies the computation process. The experimental validation was carried out on the scrap steel dataset containing a large number of targets of multiple shapes and sizes. The results showed that the improved YOLOv8 network model improves the AP (average precision) by 2.1%, the mAP (mean average precision value) by 0.8%, and reduces the FPS (frames per second) by 5.4, which meets the performance requirements of real-time industrial inspection.

Study on the method of transfer alignment based on the distributed inertial network of guided submunition

Aiming at the problem of poor transfer alignment accuracy between missiles with a high length-to-diameter ratio as a carrier missile and the internally carried guided submunition, this study proposes a transfer alignment method based on the distributed inertial network of the guided submunition. Initially, considering the influence of the deflection deformation of the carrier missile body and the dynamic nonlinear deformation of the lever arm on the transfer alignment accuracy, the corresponding error model is established and compensated for the sub-inertial guide velocity to improve the accuracy of the observed quantities. Additionally, in response to the high failure rate of low-cost inertial guidance systems equipped with guided submunition, we used an inertial network data fusion architecture based on the isolation of device failure monitoring, which effectively isolates the faulty data through the fusion of inertial measurements at the sensor level and optimal fusion of filtering to further improve the reliability of transmission alignment. The effectiveness of the method proposed in this paper is verified through a large number of simulation experiments. Compared with the traditional transfer alignment method between a single master inertial guide and a sub inertial guide, the method in the paper has obvious improvement in the transfer alignment accuracy. In addition, this method is not affected by the failure of inertial devices in the distributed inertial network, and can continuously maintain a high transfer alignment accuracy. For this kind of missile-borne distributed inertial network with a sub-node sets layer, it is found after comparison that: the transmission alignment error is basically the same for different slave nodes in the same sub-node sets; between different sub-node sets, the closer to the master inertial guide the transmission alignment error is smaller. This study provides a new solution idea and certain reference value for solving the problem of poor transfer alignment accuracy between missiles with a high length-to-diameter ratio as a carrier missile and the internally carried guided submunition.

Short-term Electricity Load Forecasting Based on Improved Seagull Algorithm Optimized Gated Recurrent Unit Neural Network

INTRODUCTION: The complexity of the power network, changes in weather conditions, diverse geographical locations, and holiday activities comprehensively affect the normal operation of power loads. Power load changes have characteristics such as non stationarity, randomness, seasonality, and high volatility. Therefore, how to construct accurate short-term power load forecasting models has become the key to the normal operation and maintenance of power.OBJECTIVES: Accurate short-term power load forecasting helps to arrange power consumption planning, optimize power usage and largely reduce power system losses and operating costs.METHODS: A hybrid decomposition-optimization-integration load forecasting method is proposed to address the problems of low accuracy of current short-term power load forecasting methods.RESULTS: The original power load time series is decomposed using the complete ensemble empirical modal decomposition method, while the correlation of power load influencing factors is analysed using Pearson correlation coefficients. The seagull optimisation algorithm is overcome to fall into local optimality by using the random adaptive non-linear adjustment strategy of manipulated variables and the differential variational Levy flight strategy, which improves the search efficiency of the algorithm. Then, the The gated cyclic unit hidden layer parameters are optimised by the improved seagull optimisation algorithm to construct a short-term electricity load forecasting model.The effectiveness of the proposed method is verified by simulation experimental analysis. The results show that the proposed method has improved the accuracy of the forecasting model.CONCLUSION: The CEEMD method is used to decompose the original load time series, which improves the accuracy of the measurement model. The GRU prediction model based on improved SOA optimization not only has better prediction accuracy than other prediction models, but also consumes the least amount of time compared to other prediction models.