Position Prediction Model Research Articles

Research on Submersible Position Prediction Based on Kalman Filter Algorithm

The global situation of the world's submersible technology is experiencing a boom, with countries competing to develop advanced submersible equipment to explore the deep sea, undersea resources, and uncharted territories. With the wide range of applications of submersibles in various fields, the risks of communication loss and mechanical failures faced during their missions require the establishment of accurate predictive models of submersible positions to ensure safe and efficient rescue. In this study, a model containing equations of motion is developed from the motion characteristics of a submersible on the seafloor. Uncertainties such as sea currents, topography, and seawater density are considered, and a random walk model is used to simulate these effects to ensure that the model is closer to reality. Subsequently, combined with the Kalman filter algorithm, a time-dependent position prediction model is constructed in this study. The model can predict the position of the submersible in real-time, and after error analysis, it shows that the average variance and root mean square error are at a low level, which proves that its prediction is accurate and reliable, and provides strong technical support for the safe rescue of the submersible.

Submersible Position Prediction Model Based on HMM and Six Degrees of Freedom Motion

Submersible Position Prediction Model Based on HMM and Six Degrees of Freedom Motion

Research and Application of Submersible Position Prediction Model Based on Kalman Filtering

Research and Application of Submersible Position Prediction Model Based on Kalman Filtering

Research on deep-sea submarine position prediction and search and rescue strategy based on multi-intelligence optimization and machine learning

In this paper, the position prediction and search and rescue strategy of deep-sea submarine are effectively studied by using multi-intelligence optimization and machine learning. First, the possible position of the submarine is predicted by building an accurate position prediction model, combining historical data and real-time ocean dynamic data. Secondly, NSGA-II, a multi-objective optimization algorithm, optimizes the combination of search and rescue equipment carried by search and rescue vessels, determines the best initial deployment point, designs an efficient search mode, and uses Bayesian probability algorithm to evaluate the rescue probability. Through these studies, this paper provides strong technical support for the safe operation and fault rescue of deep-sea submarines.

Intelligent real-time prediction for shield machine position on the basis of BWO-LSTM-GRU

Due to the complexity and variability of shield machine working environment, it is very important to accurately control and regulate the position trajectory of shield machine. For that reason, an intelligent real-time prediction model of shield machine position based on BWO-LSTM-GRU (Beluga whale optimization-Long Short-term Memory-Gated recurrent unit) is proposed in this paper. Firstly, the real-time data of shield machine are processed based on Pearson correlation analysis, and the tunneling parameters presenting medium-strong correlation with the position parameters are filtered to obtain, which were used to be input variables for prediction models. Secondly, LSTM-GRU position prediction model was established separately for shield machine position parameters, and four hyperparameters of the model were optimized separately using BWO. Finally, BWO-LSTM-GRU position prediction models are used to realize the intelligent real-time prediction of the motion trajectories at four positions for shield machine. The simulation results indicate that the prediction deviation in the position prediction model is within 3 mm, and it can accurately complete the task of real-time prediction, providing real-time data support for shield machine drivers.

Submarine Position Prediction and Rescue Equipment Optimization Model Based on Dung Beetle Optimizer and Bayes' Theorem

Submarine Position Prediction and Rescue Equipment Optimization Model Based on Dung Beetle Optimizer and Bayes' Theorem

Precision positioning control of wind tunnel centrosome

AbstractThe centrosome plays a crucial role in regulating the flow field of a continuous wind tunnel, and its positioning precision directly impacts the control accuracy of the Mach number. A high‐precision positioning control algorithm for the wind tunnel centrosome is proposed based on a model predictive control framework. Since that the centrosome is a typical non‐linear system with a Hammerstein structure comprising an input backlash and a linear dynamic block in series, a parameterized least‐squares identification method is constructed based on an adaptive forgetting factor strategy and a centrosome position prediction model with input backlash is established. To counteract the weakening effect of the backlash non‐linear block on the control signal, a compensator is constructed to compensate for the non‐linear input block. Considering that the input undetectable disturbance signal in the actuator may lead to unpredictable responses, an intermediate state observer is designed and the stable convergence of the observer algorithm is also proved. Finally, the closed‐loop stability of the proposed control algorithm is analyzed by constructing a Lyapunov function. Experimental testing verifies the superiority and applicability of the proposed algorithm.

Thermal runaway fault prediction in air-cooled lithium-ion battery modules using machine learning through temperature sensors placement optimization

The rise of severe accidents caused due to thermal runaway (TR) and its propagation in lithium-ion battery (LiB) modules is one of the most challenging factors that decelerate the rapid expansion of the electric vehicle (EV) industry. Timely detection of the TR undergoing cells in the module is crucial as the heat generated during TR is adequate to trigger the TR of the surrounding cells. In this study, an accurate machine learning (ML) based faulty cell position prediction model is developed for the air-cooled cylindrical LiB modules with the cells in aligned, staggered, and cross arrangements. The CFD model used for data generation is validated with the in-house experiments on an aligned surrogate 32-cell module for multiple failure positions. Further, to predict the TR cell position in the battery module, the random forest classification (RFC) model is developed based on the temperature distribution data obtained from the optimized temperature sensors derived for the two types of initial temperature sensor distributions (single and multiple-planes) using a heat map approach. The model developed is tested for varying design and operating conditions, and the prediction results, along with the error metrics and the prediction timings, are compared. It is revealed that except for the cross-cell arrangement in the single-plane temperature sensors distribution scenario, the RFC model produces higher accuracy when tested on the optimized temperature sensor layouts for the multiple-plane sensor distribution. The results of this study can allow early failure detection in battery modules, resulting in increased safety and cost savings.

Dynamic Equilibrium Position Prediction Model for the Confluence Area of Nakdong River

Dynamic Equilibrium Position Prediction Model for the Confluence Area of Nakdong River

Sensorless position detection of reluctance spherical motors based on inductive characteristics

The rotor attitude detection of spherical motors usually requires the installation of position sensors on the rotor shaft or stator to achieve, which occupy a large space and cause negative effects for the practical installation and application of spherical motors. In this paper, a sensorless position detection method for reluctance spherical motors based on the structure and operating characteristics of reluctance spherical motors is proposed. By detecting the stator coil inductance data at different rotor attitude angles, the position prediction model is constructed using the extreme learning machine algorithm. Through comparison and validation, it is demonstrated that the rotor attitude angle obtained by the method is highly accurate, providing a feasible idea for the control and application of reluctance spherical motors.

Long Short-Term Memory Auto-Encoder-Based Position Prediction Model for Fixed-Wing UAV During Communication Failure

Unmanned aerial vehicles (UAV's) safe flight is one of the most important tasks of ground control stations (GCS). However, sometimes due to communication failure between ground data terminal (GDT) and UAV, GCS is not able to ensure a safe flight, which could be hazardous. In such conditions, the accurate UAV position finding prediction becomes essential to serve as sustenance for UAVs. Hence, this article proposes a UAV's position finding prediction model using a deep neural network application for successfully pointing the GDT toward UAV in real time. The proposed work consists of three components, namely <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">data preprocessing</i> , <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">long short-term memory autoencoder</i> (LSTM-AE)- <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">based deep learning model</i> , and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">mathematical formulation</i> to calculate the ground radar look angle. First, we use different preprocessing techniques on a historical raw dataset for better visualization and generate patterns. To achieve this, Tensor flow along with Keras packages have been used. Next, an LSTM autoencoder deep learning model is applied to the same dataset in order to predict an accurate 4-D position of the UAV. Finally, the output from the LSTM autoencoder model is used in a mathematical model to calculate the GDT look-angles called Azimuth and Elevation. Both the parameters have been used to point the GDT toward the predicted point on the Airspace. We evaluate our proposed model against famous evaluation matrices, namely mean absolute error, mean square error, and root-mean-square error to validate the experimental results.

A static load position identification method for optical fiber-composite structures based on particle swarm optimization- back Propagation neural network algorithm

Aiming at researching on health monitoring of composite materials, a static load position identification method for optical-fiber composite structures based on the Particle Swarm Optimization-Back Propagation (PSO-BP) neural network algorithm is proposed. Based on the 2 × 2 optical fibers-composite structures, the PSO-BP algorithm is used to establish a nonlinear mapping between the fiber output intensity and the position. At first, a three-layer BP neural network is established. The number of the hidden layer is 30. And then the PSO algorithm is used to optimize the initial weights and thresholds of the BP neural network. Finally, a BP neural network is built using optimized initial weights and thresholds. A total of 515 sets of data samples are collected by the experimental system, of which 500 sets are used for training and 15 sets are used for the final model prediction. Simulation results show that the Mean Square Error (MSE) of the static load position prediction based on the PSO-BP algorithm is 0.0485. Compared with the position prediction model established by the BP neural network, Radial Basis Function (RBF) neural network and Support Vector Regression Machine (SVRM), the PSO-BP neural network model has a higher accuracy. The proposed method has an important application value for the research of health self-diagnosis of composite structures.

An optimal goal point determination algorithm for automatic navigation of agricultural machinery: Improving the tracking accuracy of the Pure Pursuit algorithm

• A goal point determination method is proposed for the problem of selecting the optimal path point by Pure Pursuit. • An evaluation function is established to select the optimal goal point based on tractor position prediction model. • The performance of the proposed path tracking algorithm is studied by field test. The development of precision agriculture requires the implementation of automatic navigation technology for agricultural machinery. Path tracking control as one of the key steps in automatic navigation technology has great research value. Pure Pursuit algorithm as a popular control algorithm for automatic navigation technology for agricultural machinery, the look-ahead distance is the key to the tracking effect, while the calculation of look-ahead distance has the problem that many influencing factors are difficult to be accurately described by mathematical expressions, which leads to the difficulty to select a suitable goal point tracking path. In order to solve the above problems, this paper proposes a path tracking algorithm for agricultural machinery based on the optimal goal point. The algorithm simulates the look-ahead behavior of the driver and searches for optimal goal point in the look-ahead area according to the evaluation function. The objective of the study is to minimize the lateral error and heading error to achieve the adaptive optimization of the goal point. Finally, the feasibility of the algorithm proposed in this paper was verified in simulations and bumpy field tests under various different conditions, with tracking errors reduced by more than 20% compared to the pure pursuit algorithm. The tracking accuracy is significantly improved.

Localization of low velocity impacts on CFRP laminates based on FBG sensors and BP neural networks

Carbon fiber reinforced plastic (CFRP) structures are vulnerable to low-speed impacts, which will lead to almost invisible impact damage. Therefore, the timely localization of impact is of great significance to damage detection and maintenance of the structure. In this article, a low velocity impact supervisory and testing system based on fiber Bragg grating (FBG) sensors was built up for CFRP laminates to obtain the low velocity impact strain sensitivity model. Meanwhile, genetic algorithm was applied to optimize the configuration of the FBG sensing network. The eigenvectors of the impact signals were extracted by applying fast Fourier transform (FFT) transform and principal component analysis (PCA) technology used as the input of the back propagation (BP) neural network model, while the corresponding impact coordinates were used as the output, to train the model. After training, the impact position prediction model based on BP neural network was obtained, thereby achieving the impact localization for CFRP laminates successfully with an average localization error of 2.1 cm.

Ensemble learning model for Wifi indoor positioning systems

&lt;p&gt;WiFi indoor positioning researches have received much attention from researchers recently. In this research, we focus on studying the performance of indoor positioning systems that utilize our new proposed ensemble machine learning model. Our new ensemble learning model uses several models for normal data training and position prediction, then it uses the verification data together with its' prediction errors from trained models as the input data to train an intermediate classification model to classify which set of Wifi received signal strength indicator (RSSI) is the best match for each position prediction model. The experimental result shows that our proposed ensemble model outperforms other compared models.&lt;/p&gt;

Location method of Sagnac distributed optical fiber sensing system based on CNNs ensemble learning

Aiming at the location problem of high-pressure pipeline leakage, this paper proposes a method for predicting the disturbed position of a Sagnac distributed optical fiber sensing system based on ensemble learning of convolutional neural networks (CNNs). A Stacking ensemble method is used to combine two different CNN models to improve the stability and location accuracy of the disturbance position prediction model. By training the prediction model using the spectrum features of interference signals generated by the disturbances at partial sensing positions, accurate prediction of an arbitrary disturbance position can be realized. The disturbance position prediction was carried out numerically on a sensing fiber with an effective length of 8.5 km. Simulation results show that a mean absolute error of no more than 14.6 m and a location resolution of 10 m are achieved. The method is insensitive to noise, low in system complexity, simple in data processing and accurate in location results.

Microstructure-Forming Mechanism of Optical Sheet Based on Polymer State Transition in Injection-Rolling Process.

Polymeric optical sheets are significant components in large-scale display devices and are difficult to fabricate due to small size and high accuracy of large-area microstructures. As a newly developed molding technique, injection-rolling is capable of continuously and efficiently achieving large-area microstructures on the polymer surface with short time and high replication. However, the microstructure-forming mechanism during the injection-rolling process has not been fully understood. In this paper, a three-dimensional steady-state heat-flow coupling simulation model of the injection-rolling zone was established to obtain the distributions of the polymer state transition interfaces. According to the state transition interfaces, the entire microstructure-forming process was numerically simulated by dividing into filling and embossing stages to systematically analyze the effects of the polymer state transition interface on filling rate. After this, the relationship between process parameters such as injection temperature, rolling speed, and roll temperature and polymer state transition interface was investigated to develop a position prediction model of the state transition interface. In addition, the optical sheet injection-rolling experiments were also carried out to reveal that the filling rate of the microstructures on the optical sheet can be affected by varying the positions of the state transition interfaces. Therefore, the microstructure-forming mechanism could be revealed as theoretical guidance for the subsequent injection-rolling production with high quality and high efficiency.

A Markov Chain Position Prediction Model Based on Multidimensional Correction

User location prediction in location-based social networks can predict the density of people flow well in terms of intelligent transportation, which can make corresponding adjustments in time to make traffic smooth, reduce fuel consumption, reduce greenhouse gas emissions, and help build a green cycle low-carbon transportation green system. This paper proposes a Markov chain position prediction model based on multidimensional correction (MDC-MCM). Firstly, extract corresponding information from the user’s historical check-in position sequence as a position-position conversion map. Secondly, the influence of check-in period, space distance, and other factors on the position prediction is linearly weighted and merged with the position prediction of the n-order Markov chain to construct MDC-MCM. Finally, we conduct a comprehensive performance evaluation of MDC-MCM using the dataset collected from Brightkite. Experimental results show that compared with other advanced location prediction technologies, MDC-MCM achieves better location prediction results.

Design of HL-2A plasma position predictive model based on deep learning

In tokamak discharge experiments, the plasma position prediction model’s research is to understand the law of plasma motion and verify the correctness of the plasma position controller design. Although Maxwell equations can completely describe plasma movement, obtaining an accurate physical model for predicting plasma behavior is still challenging. This paper describes a deep neural network model that can accurately predict the HL-2A plasma position. That is a hybrid neural network model based on a long short-term memory network. We introduce the topology, training parameter setting, and prediction result analysis of this model in detail. The test results show that a trained deep neural network model has high prediction accuracy for plasma vertical and horizontal displacements.

Improved particle swarm optimization LSSVM spatial location trajectory data prediction model in health care monitoring system

With the real-time recording of the health care system, real-time monitoring of user trajectory data can effectively protect the health and health of the body. In order to accurately establish the spatial position trajectory data prediction model, a space trajectory data prediction model based on variable space chaotic particle swarm optimization (CPSO)-optimized least squares support vector machine (LSSVM) is proposed. Firstly, aiming at the problem that particle swarm optimization (PSO) is easy to fall into local optimum, the global optimization performance of PSO algorithm is improved by using variable space chaos search strategy and particle out-of-bounds mirror processing strategy. Numerical simulation experiments verify the superiority of improved particle swarm optimization algorithm. Based on the CPSO algorithm, the hyper parameters of the CPSO-optimized least squares support vector machine (CPSO-LSSVM) are proposed to improve the prediction accuracy of the model. Finally, using GeoLife and T-Drive dataset as the research object, the CPSO-LSSVM spatial position prediction model is established by using the trajectory data of the dataset. The simulation experiment verifies that the CPSO-LSSVM positional space prediction model has higher prediction accuracy and more strong generalization ability to accurately and effectively predict spatial location.