Method and device for predicting barrel ablation wear amount based on combined model

Abstract

The embodiment of the present application provides a method and device for predicting the ablation wear amount of a gun barrel based on a combined model. By combining an adaptive neuron growth mechanism and a dynamic programming algorithm, a double-layer prediction architecture is constructed. The ablation wear amount is identified through a hierarchical neural network trained by temperature, pressure, and charge characteristic parameters, and an energy state constraint function is constructed based on sensor data. The system uses an escape search optimization operator to select the optimal wear evolution path, and establishes a multi-factor early warning threshold model by combining wear rate and acceleration indicators, realizing accurate prediction and evaluation and early warning of the ablation wear state. This method effectively solves the deficiencies of traditional technologies in model integration and state early warning, and provides a reliable basis for gun maintenance decision-making.

Description

Technical Field

[0001] The present application relates to the field of data processing, and in particular to a method and device for predicting barrel ablation wear based on a combined model. Background Art

[0002] Existing technologies for predicting barrel ablation wear have significant shortcomings. Traditional prediction methods often employ a single model structure, failing to effectively integrate the strengths of neural networks and dynamic programming. This results in limited prediction accuracy and generalization. Furthermore, existing methods lack appropriate constraints for addressing the temporal evolution of wear, making it difficult to ensure the physical interpretability of prediction results.

[0003] Furthermore, existing technologies face bottlenecks in energy state modeling and path optimization. Most methods ignore the cumulative effect of energy loss and fail to accurately characterize the evolution of ablation wear. Optimization algorithms also lack escape search mechanisms, making them prone to falling into local optimal solutions, impacting the reliability of prediction results.

[0004] Existing systems have technical shortcomings in status warning and assessment. The warning mechanism is overly simplistic, lacks comprehensive consideration of wear rate and acceleration, and struggles to achieve accurate multi-factor threshold warnings. Addressing these issues is crucial for improving artillery safety and ensuring more informed maintenance decisions. Summary of the Invention

[0005] In response to the problems in the existing technology, the present application provides a method and device for predicting barrel ablation wear based on a combined model, which can effectively solve the shortcomings of traditional technology in model integration and status warning, and provide a reliable basis for artillery maintenance decisions.

[0006] In order to solve at least one of the above problems, the present application provides the following technical solutions:

[0007] In a first aspect, the present application provides a method for predicting barrel ablation wear based on a combined model, comprising:

[0008] Collecting historical data on ablation wear of the gun barrel, extracting temperature characteristic parameters, pressure characteristic parameters, and charge characteristic parameters from the historical data, establishing a hierarchical neural network model using an adaptive neuron growth mechanism, training the hierarchical neural network model using the temperature characteristic parameters, pressure characteristic parameters, and charge characteristic parameters as input variables to obtain an ablation wear identifier, constructing a dynamic programming algorithm model for the change of ablation wear over time, and inputting the output of the ablation wear identifier into the dynamic programming algorithm model to establish a staged wear evolution model;

[0009] Collect the sensor data during the continuous firing of the gun barrel, input the sensor data into the ablation wear amount identifier to obtain the distribution parameters of the ablation wear amount, construct an energy state constraint function based on the distribution parameters, impose an evolution constraint on the dynamic programming algorithm model, substitute the dynamic programming algorithm model with the evolution constraint into the escape search operator for iterative optimization, generate a set of wear evolution paths that satisfy the energy constraint, calculate the cumulative energy loss of each path in the wear evolution path set, and select the path with the minimum cumulative energy loss as the optimal wear evolution path;

[0010] Extract the state vectors of the optimal wear evolution path at different firing times, establish an evolution state curve representing the barrel ablation wear according to the state vectors, extract the wear rate index and the wear acceleration index from the evolution state curve, input the wear rate index and the wear acceleration index into a preset multi-factor warning threshold model, determine the barrel ablation wear state based on the multi-factor warning threshold model, and trigger a warning mechanism when the ablation wear state exceeds the preset threshold, generating a state assessment report including the predicted value of the ablation wear amount and the warning level.

[0011] Furthermore, collect the historical data of the gun barrel ablation wear, extract the temperature characteristic parameters, pressure characteristic parameters and charge characteristic parameters from the historical data, establish a hierarchical neural network model using the adaptive neuron growth mechanism, and use the temperature characteristic parameters, the pressure characteristic parameters, and the charge characteristic parameters as input variables to train the hierarchical neural network model to obtain an ablation wear amount identifier, and construct a dynamic programming algorithm model for the ablation wear changing with time, including:

[0012] Collect the historical data of the gun barrel ablation wear, perform denoising processing on the historical data based on the wavelet transform method, calculate the numerical values of the temperature sensor, pressure sensor and charge sensor at different times, and convert the numerical values into temperature characteristic parameters, pressure characteristic parameters and charge characteristic parameters in combination with the sensor calibration curve, and perform normalization processing on the temperature characteristic parameters, the pressure characteristic parameters and the charge characteristic parameters to generate a feature vector;

[0013] Use the adaptive neuron growth mechanism to construct a hierarchical neural network model, input the feature vector into the hierarchical neural network model, train the hierarchical neural network model based on the backpropagation algorithm to obtain an ablation wear amount identifier, establish a state transition matrix for the ablation wear using the Markov process, construct a dynamic programming algorithm model including the state transition matrix, and substitute the output result of the ablation wear amount identifier into the dynamic programming algorithm model.

[0014] Further, inputting the output result of the ablation wear amount identifier into the dynamic programming algorithm model to establish a stage wear evolution model includes:

[0015] Dividing the output result of the ablation wear amount identifier into multiple time series intervals according to the number of shootings, performing piecewise linear fitting on the ablation wear data in each time series interval, calculating the wear change rate and wear acceleration in different intervals, and constructing a state transition probability matrix reflecting the ablation wear evolution characteristics based on the wear change rate and the wear acceleration;

[0016] Substituting the state transition probability matrix into the dynamic programming algorithm model to construct a stage wear evolution model including the temperature accumulation effect, pressure accumulation effect, and charge accumulation effect during the shooting process, applying physical boundary constraint conditions to the stage wear evolution model, and using the Bellman equation to perform iterative calculations on the state transition process of each stage.

[0017] Further, collecting the sensor data during continuous shooting of the gun barrel, inputting the sensor data into the ablation wear amount identifier to obtain the distribution parameters of the ablation wear amount, constructing an energy state constraint function based on the distribution parameters, applying an evolution constraint to the dynamic programming algorithm model, and substituting the dynamic programming algorithm model with the evolution constraint into the escape search operator for iterative optimization to generate a set of wear evolution paths satisfying the energy constraint, including:

[0018] Collecting the temperature sensor, pressure sensor, and charge sensor data during continuous shooting of the gun barrel, performing time domain sampling and feature extraction on the sensor data, inputting the extracted feature data into the ablation wear amount identifier, calculating the mean and variance distribution parameters of the ablation wear amount based on the Gaussian mixture model, and constructing an energy state constraint function including temperature energy dissipation, pressure energy loss, and charge energy conversion using the distribution parameters;

[0019] Substituting the energy state constraint function into the dynamic programming algorithm model to form a state transition equation with an evolution constraint, constructing a global optimization operator based on the escape search mechanism, inputting the state transition equation into the global optimization operator for iterative optimization, using the Monte Carlo sampling method to generate multiple groups of initial solutions, and performing escape search optimization on each group of initial solutions to obtain a set of wear evolution paths satisfying the energy constraint.

[0020] Further, calculating the cumulative energy loss of each path in the set of wear evolution paths, and selecting the path with the minimum cumulative energy loss as the optimal wear evolution path, including:

[0021] Calculate the temperature cumulative loss, pressure cumulative loss, and charge cumulative loss of each path in the set of wear evolution paths during continuous firing. Substitute the temperature cumulative loss, pressure cumulative loss, and charge cumulative loss into the energy weight fusion model, and calculate the comprehensive energy loss index of each path based on the energy weight fusion model. Normalize the comprehensive energy loss index.

[0022] Construct a path evaluation criterion based on the principle of minimum energy. Use the path evaluation criterion to sort the normalized comprehensive energy loss index, and select the path with the minimum comprehensive energy loss index from the set of wear evolution paths as the optimal wear evolution path. Calculate the state transition sequence of the optimal wear evolution path at different firing stages.

[0023] Further, extract the state vectors of the optimal wear evolution path at different firing moments. According to the state vectors, establish an evolution state curve representing the barrel ablation wear. Extract the wear rate index and wear acceleration index from the evolution state curve, including:

[0024] Extract the state vectors of each firing moment from the optimal wear evolution path. Based on the state vectors, construct a state space model including temperature state components, pressure state components, and charge state components. Use the cubic spline interpolation algorithm to continuously process the state space model, and map the interpolated state space trajectory to the time-wear amount coordinate system to obtain the evolution state curve.

[0025] Perform numerical differentiation operations on the evolution state curve, calculate the first derivative value of the curve at each sampling point to obtain the wear rate index, calculate the change rate of the first derivative value to obtain the wear acceleration index, and use the moving average filtering algorithm to smooth the wear rate index and the wear acceleration index.

[0026] Further, input the wear rate index and the wear acceleration index into a preset multi-factor warning threshold model. Based on the multi-factor warning threshold model, determine the barrel ablation wear state. When the ablation wear state exceeds the preset threshold, trigger the warning mechanism and generate a state evaluation report including the predicted value of the ablation wear amount and the warning level, including:

[0027] Normalize the wear rate index and the wear acceleration index and input them into a preset multi-factor warning threshold model. Based on the multi-factor warning threshold model, calculate the risk degree index of the current ablation wear state. Use the fuzzy comprehensive evaluation method to map the risk degree index to a preset ablation wear grading standard, and determine the ablation wear state by comparing the ablation wear grading standard with the preset threshold.

[0028] Construct an early warning trigger mechanism based on the remaining life of the gun barrel. When the ablation wear state exceeds a preset threshold, calculate the prediction interval and confidence level of the gun barrel ablation wear amount. Determine the early warning level according to the prediction interval and the confidence level, and generate a status evaluation report including the predicted value of the ablation wear amount and the early warning level.

[0029] In a second aspect, the present application provides a device for predicting the ablation wear amount of a gun barrel based on a combined model, including:

[0030] A wear evolution module, configured to collect historical data on the ablation wear of the gun barrel of the artillery, extract temperature characteristic parameters, pressure characteristic parameters, and charge characteristic parameters from the historical data, establish a hierarchical neural network model using an adaptive neuron growth mechanism, use the temperature characteristic parameters, the pressure characteristic parameters, and the charge characteristic parameters as input variables to train the hierarchical neural network model to obtain an ablation wear amount identifier, construct a dynamic programming algorithm model for the change of ablation wear over time, and input the output result of the ablation wear amount identifier into the dynamic programming algorithm model to establish a stage wear evolution model;

[0031] A path determination module, configured to collect sensor data during continuous firing of the gun barrel of the artillery, input the sensor data into the ablation wear amount identifier to obtain the distribution parameters of the ablation wear amount, construct an energy state constraint function based on the distribution parameters, impose an evolution constraint on the dynamic programming algorithm model, substitute the dynamic programming algorithm model with the evolution constraint into an escape search operator for iterative optimization, generate a set of wear evolution paths that satisfy the energy constraint, calculate the cumulative energy loss of each path in the set of wear evolution paths, and select the path with the minimum cumulative energy loss as the optimal wear evolution path;

[0032] A status evaluation module, configured to extract the state vectors of the optimal wear evolution path at different firing times, establish an evolution state curve representing the ablation wear of the gun barrel according to the state vectors, extract a wear rate index and a wear acceleration index from the evolution state curve, input the wear rate index and the wear acceleration index into a preset multi-factor early warning threshold model, determine the ablation wear state of the gun barrel based on the multi-factor early warning threshold model, trigger an early warning mechanism when the ablation wear state exceeds a preset threshold, and generate a status evaluation report including the predicted value of the ablation wear amount and the early warning level.

[0033] In a third aspect, the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the steps of the method for predicting the ablation wear amount of a gun barrel based on a combined model are implemented.

[0034] Fourthly, the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above-described method for predicting the barrel ablation wear amount based on a combined model are implemented.

[0035] Fifthly, the present application provides a computer program product, including a computer program / instructions, and when the computer program / instructions are executed by a processor, the steps of the above-described method for predicting the barrel ablation wear amount based on a combined model are implemented.

[0036] As can be seen from the above technical solutions, the present application provides a method and device for predicting the barrel ablation wear amount based on a combined model. By combining an adaptive neuron growth mechanism and a dynamic programming algorithm, a two-layer prediction architecture is constructed. The ablation wear amount is identified through a hierarchical neural network trained by temperature, pressure, and charge characteristic parameters, and an energy state constraint function is constructed based on sensor data. The system selects the optimal wear evolution path by using an escape search optimization operator, and establishes a multi-factor early warning threshold model by combining wear rate and acceleration indicators, realizing accurate prediction and evaluation and early warning of the ablation wear state. This method effectively solves the deficiencies of traditional technologies in model integration and state early warning, and provides a reliable basis for gun maintenance decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for describing the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0038] Figure 1 It is a schematic flow chart of the method for predicting the barrel ablation wear amount based on a combined model in an embodiment of the present application;

[0039] Figure 2 It is a schematic flow chart of the method for predicting the barrel ablation wear amount based on a combined model in an embodiment of the present application;

[0040] Figure 3 It is a schematic flow chart of the method for predicting the barrel ablation wear amount based on a combined model in an embodiment of the present application;

[0041] Figure 4 It is a schematic flow chart of the method for predicting the barrel ablation wear amount based on a combined model in an embodiment of the present application;

[0042] Figure 5 It is a schematic flow chart of the method for predicting the barrel ablation wear amount based on a combined model in an embodiment of the present application;

[0043] Figure 6 Sixth schematic flow diagram of the gun tube ablation wear prediction method based on a combined model in the embodiments of the present application;

[0044] Figure 7 Seventh schematic flow diagram of the gun tube ablation wear prediction method based on a combined model in the embodiments of the present application;

[0045] Figure 8 Structural diagram of the gun tube ablation wear prediction device based on a combined model in the embodiments of the present application;

[0046] Figure 9 Schematic structural diagram of the electronic device in the embodiments of the present application.

[0047] Reference numerals:

[0048] Electronic device 9600, central processing unit 9100, memory 9140, communication module 9110, input unit 9120, audio processor 9130, display 9160, power supply 9170, buffer memory 9141, application / function storage unit 9142, data storage unit 9143, driver program storage unit 9144, antenna 9111, speaker 9131, microphone 9132. Detailed implementation manners

[0049] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Apparently, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0050] In the technical solutions of the present application, the acquisition, storage, use, processing, etc. of data all comply with the relevant regulations of national laws and regulations.

[0051] Considering the problems existing in the prior art, the present application provides a gun tube ablation wear prediction method and device based on a combined model. By combining an adaptive neuron growth mechanism and a dynamic programming algorithm, a two-layer prediction architecture is constructed. An ablation wear amount identification is realized through a hierarchical neural network trained with temperature, pressure, and charge characteristic parameters, and an energy state constraint function is constructed based on sensor data. The system selects the optimal wear evolution path using an escape search optimization operator, and establishes a multi-factor early warning threshold model by combining wear rate and acceleration indicators, realizing accurate prediction and evaluation and early warning of the ablation wear state. This method effectively solves the deficiencies of traditional technologies in model integration and state early warning, providing a reliable basis for gun maintenance decision-making.

[0052] In order to effectively solve the deficiencies of traditional technologies in model integration and status warning and provide a reliable basis for gun maintenance decision-making, this application provides an embodiment of a method for predicting the erosion and wear amount of a gun barrel based on a combined model. See Figure 1 The method for predicting the erosion and wear amount of a gun barrel based on a combined model specifically includes the following content:

[0053] Step S101: Collect historical data on the erosion and wear of the gun barrel, extract temperature characteristic parameters, pressure characteristic parameters, and charge characteristic parameters from the historical data, establish a hierarchical neural network model using an adaptive neuron growth mechanism, use the temperature characteristic parameters, the pressure characteristic parameters, and the charge characteristic parameters as input variables to train the hierarchical neural network model to obtain an erosion and wear amount identifier, construct a dynamic programming algorithm model for the change of erosion and wear over time, and input the output result of the erosion and wear amount identifier into the dynamic programming algorithm model to establish a phased wear evolution model;

[0054] Optionally, in this embodiment, a high-precision sensor array is deployed at key positions of the gun barrel to collect historical data. The temperature sensor uses a high-temperature-resistant K-type thermocouple, and one measuring point is arranged every 50 mm along the axial direction of the gun barrel, with a total of 20 temperature measuring points to achieve continuous monitoring of the temperature field of the pipe wall. The sampling frequency of each temperature measuring point is 1 kHz to ensure the capture of transient temperature changes. The pressure sensor selects a piezoelectric sensor with a sensitivity of 5 pc / MPa, and 8 measuring points are arranged at different cross-sections of the gun chamber, with a sampling frequency of 100 kHz, for obtaining the characteristics of chamber pressure fluctuations. The charge parameters are obtained through a weighing system with an accuracy of 0.1 g to obtain the charge amount, and at the same time, temperature and humidity sensors are arranged to monitor the charge environment parameters.

[0055] This embodiment realizes a multi-level data preprocessing scheme. First, the original data is normalized to map different physical quantities to the interval [-1, 1] to eliminate the influence of dimensions. Then, the db4 wavelet basis function is used to decompose the signal into 5 layers, and the soft threshold method is selected to remove high-frequency noise. When reconstructing the signal, an adaptive threshold strategy is adopted, and the threshold size is related to the local characteristics of the signal to ensure the retention of important characteristic information. For the missing data points in the sampling, the cubic spline interpolation method is used for repair.

[0056] This embodiment innovatively designs a feature extraction framework. The temperature characteristics include parameters such as the highest temperature of the pipe wall, the radial temperature gradient, the axial temperature gradient, the heating rate, and the cooling rate, which comprehensively characterize the thermal stress distribution through these parameters. The pressure characteristics include parameters such as the maximum chamber pressure, the pressure rise rate, the pressure duration, and the pressure fluctuation frequency, which reflect the dynamic load characteristics during the projectile movement process. The charge characteristics include parameters such as the charge amount, the charge density, the filling coefficient, the ambient temperature, and the ambient humidity, which reflect the influence of the firing conditions.

[0057] This embodiment constructs a network model based on an improved neuron growth mechanism. The initial network adopts a 4-6-1 structure, where the input layer corresponds to three types of features: temperature, pressure, and charge. The ReLU activation function is used in the hidden layer. During the training process, by analyzing the distribution of samples in the feature space, high-error regions are identified. When the local error exceeds the preset threshold, neurons are dynamically added in this region. The initial weights of the newly added neurons are obtained by interpolating the weights of the surrounding neurons to ensure a smooth transition of the network structure.

[0058] This embodiment implements an innovative network training strategy. It is trained in the mini-batch manner with a batch size of 32, and the weights are updated by the Adam optimizer. The initial learning rate is set to 0.01 and is dynamically adjusted using the cosine annealing strategy. To prevent overfitting, an L2 regularization term is introduced with a regularization coefficient of 0.001. During the training process, when the validation set error does not decrease for five consecutive rounds, the early stopping mechanism is triggered.

[0059] This embodiment designs a comprehensive validation mechanism. The dataset is divided into a training set, a validation set, and a test set in a 7:2:1 ratio. The validation set contains data under different firing conditions, covering various combinations of temperature, pressure, and charge amount. The model performance is evaluated by calculating the mean squared error, mean absolute error, and R-squared coefficient. Based on the validation results, the network structure and training parameters are optimized.

[0060] This embodiment innovatively constructs a dynamic programming model. The ablation wear process is divided into multiple stages according to the number of firings, and the state of each stage is characterized by the current wear amount and wear rate. A state transition probability matrix is defined, and the element values are obtained based on historical data statistics. A cost function considering the thermal accumulation effect is constructed, and the optimal state sequence is solved iteratively through the Bellman equation.

[0061] This embodiment realizes the accurate modeling of the gun barrel ablation wear through the combination of an adaptive neural network and dynamic programming. This scheme fully considers the physical mechanisms during the firing process and establishes a mapping relationship between the characteristic parameters and the wear amount. Through the innovative network structure design and training strategy, the prediction accuracy and generalization ability of the model are ensured. The introduction of the dynamic programming model makes the prediction results have better temporal consistency. The overall scheme shows excellent prediction performance in practical applications and provides a reliable basis for gun maintenance decisions.

[0062] Step S102: Collect sensor data during continuous firing of the gun barrel, input the sensor data into the ablation wear amount identifier to obtain the distribution parameters of the ablation wear amount, construct an energy state constraint function based on the distribution parameters, impose an evolutionary constraint on the dynamic programming algorithm model, substitute the dynamic programming algorithm model with the evolutionary constraint into the escape search operator for iterative optimization, generate a set of wear evolution paths that satisfy the energy constraint, calculate the cumulative energy loss of each path in the set of wear evolution paths, and select the path with the minimum cumulative energy loss as the optimal wear evolution path;

[0063] Optionally, a real-time data acquisition system is designed in this embodiment. During the continuous firing of the gun, the temperature sensor adopts a distributed acquisition architecture, with an independent signal conditioning circuit configured for each measurement point, and the sampling frequency is dynamically adjusted. When the firing signal is detected, the sampling frequency is increased to 5 kHz to capture the transient temperature change characteristics; during the firing interval, it is reduced to 100 Hz to monitor the cooling process. The pressure sensor adopts a synchronous triggering method and starts collecting after the firing signal arrives, with the sampling frequency set to 200 kHz to record the complete pressure waveform. The charging parameters are recorded by a high-precision weighing system during each loading.

[0064] This embodiment implements a real-time data processing framework. The sliding window method is used to segment the sensor data, with a window length of 100 ms and an overlap rate of 50%. Fast Fourier transform is performed within each window to extract frequency domain features. Interference signals are removed through adaptive threshold filtering to ensure the stability of feature extraction. The processed feature data is transmitted to the ablation wear amount identifier through a cache queue.

[0065] This embodiment innovatively constructs a distribution parameter estimation model. The output result of the ablation wear amount identifier is input into the Gaussian mixture model, and the expectation maximization algorithm is used to estimate the model parameters. The mixture model contains three Gaussian components, corresponding to mild, moderate, and severe wear states respectively. By calculating the posterior probability, the probability distribution characteristics of the wear amount are obtained.

[0066] This embodiment designs an energy state constraint function. The constraint function considers three forms of energy: heat energy loss, mechanical energy loss, and chemical energy conversion. The heat energy loss is calculated through the temperature field distribution, considering heat conduction and convective heat transfer. The mechanical energy loss is evaluated based on the pressure fluctuation characteristics, including friction work and deformation work. The chemical energy conversion is estimated through the charging parameters, considering the influence of combustion efficiency.

[0067] This embodiment realizes the constraint optimization of the dynamic programming model. The energy constraint is transformed into a state transition cost, and an energy penalty term is added to the Bellman equation. When the state transition causes the energy loss to exceed the threshold, the corresponding transition probability is reduced. This mechanism ensures that the predicted wear evolution path conforms to the principle of energy conservation.

[0068] In this embodiment, an escape search algorithm is innovatively designed. The algorithm initializes multiple search paths, each path containing N state points, where N is the prediction step size. During the search process, candidate solutions are generated through local perturbations. The perturbation amplitude is related to the degree of satisfaction of the energy constraint. The more seriously the constraint is violated, the greater the perturbation. A tabu list mechanism is introduced to avoid repeated searches, and the tabu length is dynamically adjusted.

[0069] This embodiment implements a path optimization strategy. An elite solution set is maintained during the iteration process, and several paths with the minimum energy loss are saved. The elite solutions are updated after each iteration, and the paths with large energy losses are eliminated. The iteration termination conditions include the maximum number of iterations and the convergence criterion to ensure the convergence of the algorithm.

[0070] This embodiment designs a path evaluation system. For the generated set of wear evolution paths, the cumulative energy loss of each path is calculated. The energy loss includes the sum of the thermal energy, mechanical energy, and chemical energy losses at each time step. During the calculation, the temporal characteristics of the energy loss are considered, and a time weight factor is introduced.

[0071] This embodiment innovatively realizes the optimal path selection. Based on the Pareto optimization principle, two objectives of minimizing energy loss and path smoothness are comprehensively considered. By calculating the normalized value of the energy loss and the path curvature, a comprehensive evaluation index is constructed. The path with the optimal comprehensive evaluation is selected as the final prediction result.

[0072] By introducing the energy constraint and the escape search mechanism, this embodiment significantly improves the physical rationality of wear prediction. This scheme fully considers the energy conversion law during the firing process to ensure that the prediction results conform to the physical laws. Through the multi-objective optimization strategy, while ensuring the prediction accuracy, the interpretability of the prediction results is improved. The overall scheme exhibits excellent prediction performance in practical applications and provides reliable support for gun maintenance decision-making.

[0073] Step S103: Extract the state vectors of the optimal wear evolution path at different firing moments, establish an evolution state curve representing the barrel ablation wear according to the state vectors, extract the wear rate index and the wear acceleration index from the evolution state curve, input the wear rate index and the wear acceleration index into a preset multi-factor warning threshold model, determine the barrel ablation wear state based on the multi-factor warning threshold model, and trigger a warning mechanism when the ablation wear state exceeds the preset threshold, and generate a state evaluation report including the predicted value of the ablation wear amount and the warning level.

[0074] Optionally, in this embodiment, a state vector extraction module is implemented for the optimal wear evolution path. At each firing moment, a multi-dimensional state vector including temperature state variables, pressure state variables, and charge state variables is extracted. The temperature state variables include the tube wall temperature distribution, thermal stress distribution, and temperature gradient, which are obtained in real time through a thermocouple array. The pressure state variables include the maximum chamber pressure, pressure waveform characteristics, and pressure fluctuation frequency, which are collected by a pressure sensor network. The charge state variables include charge parameters and environmental parameters, which comprehensively characterize the firing conditions.

[0075] In this embodiment, an innovative state space modeling method is designed. A three-dimensional state space model is adopted, and the coordinate axes correspond to temperature, pressure, and charge characteristics respectively. The extracted state vectors are mapped into the state space to form a discrete sequence of state points. The cubic spline interpolation algorithm is used to connect the state points to ensure the continuity and smoothness of the state trajectory. A tension coefficient adaptive adjustment strategy is adopted during the interpolation process to avoid unreasonable oscillations in the trajectory.

[0076] In this embodiment, the construction of the evolution state curve is realized. The state space trajectory is projected onto the time-wear amount plane to generate a state curve representing the ablation wear evolution process. The ordinate of the curve represents the cumulative wear amount, and the abscissa represents the number of firings. The curve shape is optimized by piecewise polynomial fitting, and the fitting order is adaptively selected according to the data complexity to ensure that the curve can accurately reflect the wear trend without overfitting.

[0077] In this embodiment, an innovative feature extraction algorithm is designed. The evolution state curve is numerically differentiated, and the central difference scheme is used to calculate the first derivative to obtain the wear rate index. To improve the calculation accuracy, the differential step size is dynamically adjusted according to the local characteristics of the curve. The second derivative is further calculated to obtain the wear acceleration index, which reflects the change trend of the wear rate. The noise influence during the differentiation process is eliminated by moving average filtering.

[0078] In this embodiment, a multi-factor early warning model is implemented. The model inputs include the wear rate index, wear acceleration index, and state space features. A fuzzy logic inference mechanism is adopted, and a fuzzy rule base is designed to describe the relationship between each index and the wear state. The fuzzy rules are formulated by combining expert knowledge and data analysis to ensure the rationality and completeness of the rules.

[0079] In this embodiment, an adaptive threshold determination mechanism is designed. Based on the statistical analysis of historical data, a distribution model of wear indexes is established. The quantile method is used to determine the early warning threshold, and the threshold is dynamically updated according to the sample distribution. Multiple levels of early warning thresholds are set corresponding to different degrees of danger to achieve hierarchical early warning.

[0080] This embodiment innovatively implements an early warning trigger mechanism. When the monitoring index exceeds the corresponding threshold, the early warning program is started. The early warning level is comprehensively determined according to the degree of overrun and the duration. To avoid frequent alarms, a hysteresis judgment mechanism is introduced to ensure the stability of the early warning. At the same time, the prediction result is corrected online through the Kalman filter algorithm to improve the reliability of the early warning.

[0081] This embodiment designs a state evaluation report generation module. The report includes information such as the current wear amount, predicted wear amount, early warning level, and confidence interval. The predicted wear amount is obtained by extrapolating the state curve, and the confidence interval is determined based on the prediction error analysis. The early warning level is visually displayed in a color-coded manner for quick identification.

[0082] This embodiment realizes the accurate evaluation of the erosion wear state of the gun barrel through multi-dimensional state analysis and multi-factor early warning mechanism. This solution combines physical models with data-driven methods to establish a mapping relationship between wear evolution characteristics and early warning indicators. Through innovative feature extraction algorithms and early warning decision-making mechanisms, the accuracy and reliability of state evaluation are improved. The overall solution shows excellent early warning effects in practical applications, providing a scientific basis for gun maintenance and support.

[0083] As can be seen from the above description, the method for predicting the erosion wear amount of the gun barrel based on the combined model provided by the embodiment of the present application can construct a two-layer prediction architecture by combining the adaptive neuron growth mechanism and the dynamic programming algorithm. The erosion wear amount is identified through a hierarchical neural network trained by temperature, pressure, and charge characteristic parameters, and an energy state constraint function is constructed based on sensor data. The system uses an escape search optimization operator to select the optimal wear evolution path, and combines wear rate and acceleration indicators to establish a multi-factor early warning threshold model, realizing the accurate prediction and evaluation and early warning of the erosion wear state. This method effectively solves the deficiencies of traditional technologies in model integration and state early warning, providing a reliable basis for gun maintenance decision-making.

[0084] In an embodiment of the method for predicting the erosion wear amount of the gun barrel based on the combined model of the present application, refer to Figure 2 , it may also specifically include the following content:

[0085] Step S201: Collect the historical data of the erosion wear of the gun barrel, perform denoising processing on the historical data based on the wavelet transform method, calculate the values of the temperature sensor, pressure sensor, and charge sensor at different times, and convert the values into temperature characteristic parameters, pressure characteristic parameters, and charge characteristic parameters in combination with the sensor calibration curve, and perform normalization processing on the temperature characteristic parameters, the pressure characteristic parameters, and the charge characteristic parameters to generate a feature vector;

[0086] Step S202: Construct a hierarchical neural network model using an adaptive neuron growth mechanism, input the feature vector into the hierarchical neural network model, train the hierarchical neural network model based on the backpropagation algorithm to obtain an ablation wear amount identifier, establish an ablation wear state transition matrix using a Markov process, construct a dynamic programming algorithm model including the state transition matrix, and substitute the output result of the ablation wear amount identifier into the dynamic programming algorithm model.

[0087] Optionally, in this embodiment, a distributed data acquisition architecture is adopted to record the historical data of the gun barrel. A high-precision sensor array is arranged at key positions of the gun barrel, including 20 K-type thermocouple temperature measurement points evenly distributed along the axis, and each measurement point is equipped with a signal conditioning circuit and a 16-bit analog-to-digital converter. For pressure monitoring, 8 piezoelectric sensors with a sensitivity of 5 pc / MPa and a sampling frequency of 200 kHz are used. The charge parameters are obtained through a high-precision weighing system and environmental monitoring equipment to achieve comprehensive monitoring of the firing conditions.

[0088] This embodiment innovatively implements a signal denoising scheme based on wavelet transform. The db4 wavelet basis function is selected to decompose the original signal into 5 layers to obtain wavelet coefficients of different scales. By analyzing the statistical characteristics of the wavelet coefficients, an adaptive threshold method is used to distinguish signal and noise components. The threshold size is related to the local characteristics of the signal, and noise suppression is achieved while maintaining useful information. The signal reconstruction uses a soft threshold processing method to ensure the smoothness of the reconstructed signal.

[0089] This embodiment designs a high-precision sensor calibration system. The temperature sensor uses a blackbody furnace as a standard source and is calibrated at multiple points in the range of 25 - 1000 °C to establish the mapping relationship between the thermoelectric potential and the temperature. The pressure sensor is dynamically calibrated using a pressure standard generator, covering a range of 0 - 600 MPa. The calibration curve is fitted with a piecewise polynomial to ensure the conversion accuracy in different working intervals.

[0090] This embodiment implements a feature parameter extraction framework. The temperature features include parameters such as the maximum temperature, temperature gradient, heating rate, and cooling rate. The pressure features include parameters such as the maximum chamber pressure, pressure rise rate, pressure duration, and pressure fluctuation frequency. The charge features include the charge amount, charge density, filling coefficient, and environmental parameters. By normalizing the processing, each feature is mapped to a unified interval to eliminate the influence of the dimension.

[0091] This embodiment innovatively designs an adaptive neuron growth mechanism. The initial structure of the network adopts the minimum topology, the input layer corresponds to the dimension of the feature vector, and the output layer is the ablation wear amount. The number of hidden layer nodes is dynamically adjusted during the training process, and the position of the newly added nodes is determined based on the local error analysis. The node growth process considers the network complexity constraint to avoid the decline of the generalization ability caused by excessive growth.

[0092] This embodiment implements an improved backpropagation training algorithm. The batch stochastic gradient descent method is used to update the weights, and the batch size is dynamically adjusted. The learning rate adopts an adaptive adjustment strategy, maintaining a relatively large value at the initial stage to accelerate convergence and gradually decreasing in the later stage to ensure stability. The momentum term and weight decay term are introduced to optimize the training process.

[0093] This embodiment designs an innovative verification mechanism. The k-fold cross-validation is used to evaluate the model performance, and the validation set contains data under different working conditions. The verification metrics include prediction accuracy, generalization ability, and stability. Based on the verification results, the network structure and training parameters are dynamically adjusted to achieve model optimization.

[0094] This embodiment constructs a state transition model based on the Markov process. The ablation wear process is discretized into multiple states, and the transition probabilities between states are obtained through statistical analysis of historical data. Considering the influence of shooting conditions on the transition probabilities, a conditional transition matrix is established. The elements of the transition matrix are dynamically updated with the accumulation of samples to maintain the adaptability of the model.

[0095] This embodiment innovatively implements a dynamic programming algorithm model. The ablation wear prediction problem is transformed into an optimal path search problem, and the state space is jointly defined by the wear amount and working condition parameters. A cost function considering physical constraints is constructed, and the optimal state sequence is iteratively solved through the Bellman equation. A heuristic strategy is introduced in the optimization process to improve the solution efficiency.

[0096] This embodiment realizes the accurate modeling of the gun barrel ablation wear through the combination of an adaptive neural network and dynamic programming. This scheme fully considers the physical mechanisms during the firing process and establishes a mapping relationship between the characteristic parameters and the wear amount. Through the innovative network structure design and training strategy, the prediction accuracy and generalization ability of the model are ensured. The introduction of the dynamic programming model makes the prediction results have better temporal consistency. The overall scheme shows excellent prediction performance in practical applications and provides a reliable basis for gun maintenance decisions.

[0097] In an embodiment of the method for predicting the ablation wear amount of the gun barrel based on the combined model of the present application, refer to Figure 3 , it may further specifically include the following content:

[0098] Step S301: Divide the output results of the ablation wear amount identifier into multiple time series intervals according to the number of shootings, perform piecewise linear fitting on the ablation wear data in each time series interval, calculate the wear change rate and wear acceleration in different intervals, and construct a state transition probability matrix reflecting the evolution characteristics of ablation wear based on the wear change rate and the wear acceleration;

[0099] Step S302: Substitute the state transition probability matrix into the dynamic programming algorithm model to construct a phased wear evolution model that includes the temperature cumulative effect, pressure cumulative effect, and charge cumulative effect during the firing process. Apply physical boundary constraint conditions to the phased wear evolution model and use the Bellman equation to iteratively calculate the state transition process for each stage.

[0100] Optionally, in this embodiment, a time series partitioning module is implemented. Based on the output results of the ablation wear amount identifier, an adaptive partitioning strategy is used to partition the time series. Factors such as firing intensity, continuous firing time, and cooling interval are considered during the partitioning process to ensure that the data within each interval has similar physical characteristics. For the high-intensity continuous firing stage, a smaller time window is used; for the intermittent firing stage, the time window is appropriately increased to achieve accurate modeling of different firing modes.

[0101] In this embodiment, a piecewise linear fitting algorithm is innovatively designed. Within each time series interval, the dynamic programming method is used to determine the optimal segmentation points. The selection of the segmentation points is based on the error minimization criterion, and the constraint of the number of segments is also considered. Weighted least squares method is used to perform linear fitting on each segment of data, and the weights are related to the reliability of the data points. The wear change rate is obtained by analyzing the slope of the fitted line, and the wear acceleration is calculated by the change of the slopes of adjacent segments.

[0102] In this embodiment, the construction of the state transition probability matrix is realized. Based on the wear change rate and acceleration, the ablation wear state is discretized into multiple levels. By analyzing the transition relationship between states at adjacent times, the state transition frequency is statistically obtained. The Bayesian estimation method is used to calculate the transition probability, and prior knowledge is introduced to constrain the probability distribution to ensure the physical rationality of the transition matrix.

[0103] In this embodiment, an innovative cumulative effect model is designed. The temperature cumulative effect considers the thermal stress cycle and material fatigue, and the influence of temperature on material properties is determined through thermo-mechanical coupling analysis. The pressure cumulative effect reflects the cumulative material damage caused by chamber pressure shock and is modeled based on damage mechanics theory. The charge cumulative effect describes the coupling effect of chemical corrosion and mechanical wear and considers the influence of charge characteristics on the wear process.

[0104] In this embodiment, a phased wear evolution model is realized. The continuous wear process is decomposed into multiple evolution stages, and each stage corresponds to a specific combination of working conditions. The Markov chain is used to describe the state transition within the stage, and the transfer of cumulative effects is considered between stages. The model parameters are obtained through training with historical data to ensure the accuracy of the prediction results.

[0105] This embodiment innovatively designs physical boundary constraints. Based on materials science and mechanics principles, constraint conditions including strength limit, strain limit, and temperature limit are established. The constraint conditions are dynamically updated with the cumulative effect, reflecting the evolution of material properties during the usage process. The feasibility domain analysis is used to ensure that the prediction results satisfy physical laws.

[0106] This embodiment implements an improved Bellman equation solving algorithm. The forward dynamic programming method is used for state transition calculation, and the optimal value function is maintained at each stage. A heuristic search strategy is introduced to reduce the calculation space and improve the solving efficiency. The state transition sequence is optimized through error backpropagation to ensure the acquisition of the global optimal solution.

[0107] This embodiment designs an iterative optimization mechanism. During the process of solving the Bellman equation, the state transition cost is dynamically adjusted to make the prediction results consistent with the physical constraints. An adaptive step size strategy is used to control the iterative process to ensure the convergence of the algorithm. The prediction performance is evaluated through cross-validation to optimize the model parameters.

[0108] This embodiment significantly improves the reliability of wear prediction by introducing the cumulative effect and physical constraints. This solution combines statistical modeling with physical mechanisms to achieve an accurate description of the complex ablation wear process. The innovative state transition modeling and iterative optimization strategies ensure the physical rationality of the prediction results. The overall solution shows excellent prediction performance in practical applications, providing a scientific basis for gun maintenance decision-making.

[0109] This embodiment realizes the dynamic prediction of the ablation wear evolution process of the gun barrel through reasonable time series partitioning and state transition modeling. This solution fully considers the physical mechanisms during the shooting process and establishes the transition relationship between wear states. By introducing the cumulative effect and physical constraints, the reliability of the prediction results is improved. The overall solution provides important support for gun life assessment and maintenance decision-making.

[0110] In an embodiment of the method for predicting the ablation wear amount of the gun barrel based on the combined model in this application, refer to Figure 4 , it may specifically include the following content:

[0111] Step S401: Collect the data of temperature sensors, pressure sensors, and charge sensors during the continuous shooting of the gun barrel, perform time-domain sampling and feature extraction on the sensor data, input the extracted feature data into the ablation wear amount identifier, calculate the mean and variance distribution parameters of the ablation wear amount based on the Gaussian mixture model, and construct an energy state constraint function including temperature energy dissipation, pressure energy loss, and charge energy conversion by using the distribution parameters;

[0112] Step S402: Substitute the energy state constraint function into the dynamic programming algorithm model to form a state transition equation with evolution constraints, construct a global optimization operator based on the escape search mechanism, input the state transition equation into the global optimization operator for iterative optimization, generate multiple groups of initial solutions using the Monte Carlo sampling method, and perform escape search optimization on each group of initial solutions to obtain a set of wear evolution paths that satisfy the energy constraints.

[0113] Optionally, a high-precision data acquisition system is designed in this embodiment. The temperature sensor uses a K-type thermocouple array, and one measuring point is arranged every 50 mm along the axial direction of the gun barrel to achieve continuous monitoring of the temperature field. The pressure sensor uses a piezoelectric sensor, and 8 measuring points are arranged at key positions in the gun chamber, and the sampling frequency is 200 kHz. The charge parameters are obtained through a high-precision weighing system and environmental monitoring equipment to ensure the accuracy and integrity of the data.

[0114] [[ID=**6**]]An innovative time-domain sampling strategy is implemented in this embodiment. The adaptive sampling method is adopted to dynamically adjust the sampling frequency during the launch process. When the firing signal is detected, the sampling frequency of the pressure sensor is increased to the maximum value to capture the details of the pressure waveform; the sampling frequency of the temperature sensor is correspondingly increased to record the transient temperature change. The sampling frequency is reduced during the launch interval to achieve a balance between the data volume and the amount of information.

[0115] A multi-level feature extraction framework is designed in this embodiment. The temperature features include the maximum temperature, temperature gradient, heating rate, and cooling rate. The pressure features include the maximum chamber pressure, pressure rise rate, pressure duration, and pressure fluctuation frequency. The charge features include the charge amount, charge density, filling coefficient, and environmental parameters. The original signal is subjected to multi-scale analysis through wavelet transform to extract the feature information of each scale.

[0116] A Gaussian mixture model is innovatively constructed in this embodiment. The model contains three Gaussian components, corresponding to mild, moderate, and severe wear states respectively. The weights, means, and variances of each component are estimated through the expectation-maximization algorithm. The model parameters are dynamically updated with the accumulation of data to maintain an accurate description of the wear state. By calculating the posterior probability, the probability distribution characteristics of the wear amount are obtained.

[0117] The energy state constraint function is implemented in this embodiment. The temperature energy dissipation considers three mechanisms: heat conduction, convective heat transfer, and radiative heat transfer, and the energy loss is determined through thermodynamic analysis. The pressure energy loss includes frictional work and deformation work, and the energy conversion is calculated based on mechanical principles. The charge energy conversion considers the chemical reaction efficiency and the mechanical work conversion efficiency to achieve a quantitative description of the energy balance.

[0118] In this embodiment, an innovative state transition equation is designed. The energy constraint is transformed into a state transition cost, and an energy penalty term is added to the Bellman equation. When the state transition results in an energy loss exceeding the threshold, the corresponding transition probability is reduced. Through iterative optimization, it is ensured that the state transition sequence satisfies the principle of energy conservation.

[0119] In this embodiment, an escape search optimization algorithm is implemented. The algorithm maintains a set of candidate solutions, and each solution corresponds to a possible wear evolution path. New solutions are generated through local perturbations, and the perturbation amplitude is related to the degree of satisfaction of the energy constraint. A taboo list mechanism is introduced to avoid repeated searches, and the taboo length is dynamically adjusted. An elite retention strategy is adopted to save the optimal solution to ensure the convergence of the algorithm.

[0120] In this embodiment, a Monte Carlo sampling method is innovatively designed. Based on the statistical characteristics of historical data, a probability distribution model of the initial solution is constructed. Multiple groups of initial solutions are generated through importance sampling, and each group of solutions contains N state points. The physical constraints are considered during the sampling process to ensure the rationality of the initial solutions. Local optimization is performed on each group of initial solutions, and the path with the minimum energy loss is selected.

[0121] In this embodiment, an iterative optimization strategy is implemented. During the escape search process, the search parameters are dynamically adjusted, including the perturbation amplitude, taboo length, and termination condition. The optimization effect is evaluated through cross-validation to avoid falling into local optima. An energy evaluation is performed on the generated path set, and the feasible solutions that meet the constraints are screened.

[0122] In this embodiment, by introducing the energy constraint and escape search mechanism, the physical rationality of wear prediction is significantly improved. This scheme fully considers the energy conversion law during the launch process to ensure that the prediction results conform to the physical laws. Through the multi-objective optimization strategy, while ensuring the prediction accuracy, the interpretability of the prediction results is improved. The overall scheme exhibits excellent prediction performance in practical applications and provides reliable support for gun maintenance decisions.

[0123] In an embodiment of the method for predicting the barrel ablation wear amount based on a combined model in the present application, referring to Figure 5 , it may specifically include the following content:

[0124] Step S501: Calculate the temperature cumulative loss, pressure cumulative loss, and charge cumulative loss of each path in the wear evolution path set during continuous firing, substitute the temperature cumulative loss, pressure cumulative loss, and charge cumulative loss into the energy weight fusion model, calculate the comprehensive energy loss index of each path based on the energy weight fusion model, and perform normalization processing on the comprehensive energy loss index;

[0125] Step S502: Construct a path evaluation criterion based on the principle of minimum energy, and use the path evaluation criterion to sort the normalized comprehensive energy loss index. Select the path with the minimum comprehensive energy loss index from the set of wear evolution paths as the optimal wear evolution path, and calculate the state transition sequence of the optimal wear evolution path at different firing stages.

[0126] Optionally, this embodiment implements a multi-dimensional energy loss calculation module. The temperature cumulative loss is obtained through thermodynamic analysis, considering three mechanisms: heat conduction, convective heat transfer, and radiative heat transfer. During each firing cycle, the temperature field distribution of the tube wall is calculated, and the heat loss is evaluated based on Fourier's law of heat conduction. The convective heat transfer loss is calculated through the heat exchange between the tube wall and the projectile and the propellant gas. The radiative heat transfer loss is estimated based on the Stefan-Boltzmann law.

[0127] This embodiment innovatively designs a method for evaluating the pressure cumulative loss. By analyzing the action process of the pressure wave on the tube wall, the loss of the pressure work converted into mechanical energy is calculated. Consider the frictional work loss, including the sliding friction between the projectile and the tube wall and the viscous loss of the propellant gas. Evaluate the plastic deformation work, which reflects the energy loss of the tube wall material under high pressure. The pressure loss during the complete firing process is obtained through cumulative calculation.

[0128] This embodiment implements the analysis of the charge cumulative loss. Based on chemical reaction kinetics, the energy conversion efficiency during the charge combustion process is calculated. Consider the conversion loss of chemical energy into mechanical energy, including incomplete combustion loss and heat loss. Evaluate the influence of charge parameters on energy conversion, such as charge density, filling coefficient, etc. By establishing an energy balance equation, the quantitative description of the charge cumulative loss is realized.

[0129] This embodiment designs an innovative energy weight fusion model. The analytic hierarchy process is used to determine the weight coefficients of various energy losses, and the weight values reflect the influence degree of different energy forms on the wear process. The weight coefficients are determined by combining expert evaluation and data analysis. The model considers the coupling effect between energy losses and reflects the interaction through cross terms.

[0130] This embodiment implements a comprehensive energy loss evaluation system. The weighted energy losses are normalized to eliminate the influence of dimensions. By constructing dimensionless indexes, the comparability between different paths is realized. The normalization process uses the maximum-minimum method to maintain the relative relationship of the energy losses. The stability analysis of the normalization result is carried out to ensure the reliability of the evaluation.

[0131] In this embodiment, a path evaluation criterion is innovatively constructed. Based on the principle of minimum energy, the wear evolution process is equivalent to a state transition sequence with the minimum energy loss. The evaluation criterion includes an energy efficiency term and a path smoothness term, comprehensively considering the energy loss and the rationality of state transitions. By using the Pareto optimization method to handle multi-objective problems, a balanced evaluation result is obtained.

[0132] In this embodiment, a path ranking mechanism is designed. The fast non-dominated sorting algorithm is used to stratify the path set, and each layer contains paths with similar energy losses. The crowding degree calculation is introduced to maintain the diversity of solutions. The optimal path is selected through the elitist strategy to ensure the stability of the selection result. Sensitivity analysis is performed on the selected path to verify its robustness.

[0133] In this embodiment, the extraction of the state transition sequence is realized. The optimal wear evolution path is segmented, and each segment corresponds to a firing stage. The transition characteristics between adjacent states are analyzed, including the transition direction and transition rate. A state transition graph is established to intuitively display the wear evolution process. The rationality of the transition sequence is verified through Markov chain analysis.

[0134] In this embodiment, a verification mechanism is innovatively designed. The accuracy of path selection is evaluated through cross-validation, and the validation set contains data under different working conditions. The prediction error and confidence interval are calculated to quantify the reliability of the prediction result. Based on physical constraints, the rationality of state transitions is verified to ensure that the prediction result conforms to the actual situation.

[0135] In this embodiment, through energy loss analysis and path optimization, an accurate description of the erosion wear evolution process of the gun barrel is achieved. This scheme combines thermodynamics, mechanics, and chemical principles to establish a complete energy evaluation system. Through innovative path evaluation criteria and optimization strategies, the physical rationality of the prediction result is ensured. The overall scheme shows excellent prediction performance in practical applications, providing a scientific basis for gun maintenance decisions.

[0136] In an embodiment of the method for predicting the erosion wear amount of the gun barrel based on the combined model in the present application, referring to Figure 6 , it may further specifically include the following content:

[0137] Step S601: Extract the state vector at each firing moment from the optimal wear evolution path, construct a state space model including a temperature state component, a pressure state component, and a charge state component based on the state vector, use the cubic spline interpolation algorithm to continuously process the state space model, and map the interpolated state space trajectory to the time-wear amount coordinate system to obtain an evolution state curve;

[0138] Step S602: Perform numerical differentiation on the evolution state curve, calculate the first derivative value at each sampling point of the curve to obtain the wear rate index, calculate the change rate of the first derivative value to obtain the wear acceleration index, and use the moving average filtering algorithm to smooth the wear rate index and the wear acceleration index.

[0139] Optionally, in this embodiment, a state vector extraction module is implemented. Multidimensional state information is extracted from the optimal wear evolution path according to the firing time sequence. The temperature state component includes the tube wall temperature distribution, thermal stress distribution, and temperature gradient, which are obtained in real time through a thermocouple array. The pressure state component includes the maximum chamber pressure, pressure waveform characteristics, and pressure fluctuation frequency, which are collected by a pressure sensor network. The charge state component includes charge parameters and environmental parameters, which comprehensively characterize the firing conditions.

[0140] In this embodiment, a state space modeling method is innovatively designed. A three-dimensional state space model is adopted, and the coordinate axes correspond to temperature, pressure, and charge characteristics respectively. The extracted state vectors are mapped into the state space to form a discrete sequence of state points. The construction of the state space considers the coupling relationship between physical quantities to ensure that the model has physical significance. The dimension of the state space is reduced by principal component analysis, and key feature information is retained.

[0141] In this embodiment, a cubic spline interpolation algorithm is implemented. For the discrete sequence of state points, piecewise cubic polynomials are used for interpolation fitting. The interpolation function satisfies the continuity conditions of the first derivative and the second derivative at the nodes to ensure the smoothness of the state trajectory. The shape of the curve is adjusted by introducing a tension coefficient to avoid excessive oscillation. Endpoint derivative constraints are adopted to ensure the physical rationality at the boundaries.

[0142] In this embodiment, a trajectory mapping mechanism is designed. The three-dimensional state space trajectory is projected onto the time-wear amount plane to generate a state curve representing the ablation wear evolution process. The topological relationship between state points is maintained during the projection process to ensure that the evolution characteristics are not distorted. Different scale representations of the curve are achieved through coordinate transformation, which is convenient for analyzing wear characteristics at different time scales.

[0143] In this embodiment, a numerical differentiation algorithm is innovatively implemented. The central difference formula is used to calculate the first derivative of the state curve to obtain the wear rate index. The difference step size is dynamically adjusted according to the local characteristics of the curve, which suppresses the influence of noise while ensuring the calculation accuracy. The derivative calculation accuracy is improved by Richardson extrapolation to reduce the truncation error.

[0144] In this embodiment, a wear acceleration calculation method is designed. The wear rate index is numerically differentiated to obtain the wear acceleration index. The calculation process uses a second-order accurate difference scheme to ensure the accuracy of the acceleration estimation. An adaptive step control mechanism is introduced to avoid calculation instability at singular points. The rationality of the acceleration index is verified through physical constraints.

[0145] In this embodiment, a moving average filtering algorithm is implemented. A variable-length moving window is used to smooth the rate and acceleration indices. The window length is related to the local characteristics of the signal. A shorter window is used in the fast-changing region to retain details, and a longer window is used in the stationary region to suppress noise. The filtering weights follow a Gaussian distribution to ensure the continuity of the smoothing result.

[0146] In this embodiment, an index verification mechanism is innovatively designed. The rationality of the rate and acceleration indices is verified through physical model analysis. The corresponding relationship between the indices and the material damage mechanism is established to ensure that the indices have clear physical meanings. The stability and reliability of the indices are evaluated through cross-validation. Outliers are identified and processed to improve the robustness of the indices.

[0147] In this embodiment, through state space modeling and index extraction, an accurate characterization of the ablation wear process of the gun barrel is achieved. This solution fuses and analyzes multi-source sensing data to establish a complete description of the state evolution. Through innovative interpolation algorithms and differential calculation methods, the accuracy of feature extraction is ensured. The overall solution provides a reliable quantitative basis for wear state assessment and is of great value for guiding gun maintenance.

[0148] In this embodiment, excellent performance is demonstrated in practical applications. Through reasonable state space construction and trajectory processing, an accurate description of the complex wear process is achieved. Innovative numerical calculation methods and filtering strategies ensure the stability of index extraction. The overall solution provides a scientific basis for gun life assessment and maintenance decision-making and has important engineering application value.

[0149] In an embodiment of the method for predicting the ablation wear amount of the gun barrel based on the combined model in the present application, refer to Figure 7 , and it may specifically include the following content:

[0150] Step S701: After normalizing the wear rate index and the wear acceleration index, input them into a preset multi-factor early warning threshold model. Based on the multi-factor early warning threshold model, calculate the risk index of the current ablation wear state. Use the fuzzy comprehensive evaluation method to map the risk index to a preset ablation wear classification standard. Determine the ablation wear state by comparing the ablation wear classification standard with a preset threshold.

[0151] Step S702: Construct an early warning trigger mechanism based on the remaining life of the gun barrel. When the ablation and wear state exceeds a preset threshold, calculate the prediction interval and confidence level of the gun barrel ablation and wear amount, determine the early warning level according to the prediction interval and the confidence level, and generate a status evaluation report including the predicted value of the ablation and wear amount and the early warning level.

[0152] Optionally, in this embodiment, a normalization processing module is implemented. The maximum and minimum values of the wear rate index are normalized to eliminate the influence of dimension. The wear acceleration index adopts the Z-score normalization method to achieve data centralization and variance normalization. The normalization process considers the physical meaning of the index to ensure that the processing results have practical interpretability. The normalization effect is verified through mathematical statistics analysis to ensure the rationality of the data distribution characteristics.

[0153] In this embodiment, a multi-factor early warning threshold model is innovatively designed. The model includes three dimensions: temperature accumulation factor, pressure damage factor, and charge action factor. The weight coefficient of each factor is determined through physical analysis to reflect its influence degree on the wear state. The model structure adopts a hierarchical design to achieve the fusion analysis of multi-scale features. The model parameters are optimized through a combination of expert knowledge base and data-driven methods.

[0154] In this embodiment, a calculation method for the risk index is implemented. The comprehensive risk is calculated based on the weighted summation criterion, and the weight coefficient is dynamically adjusted according to the wear state. A non-linear mapping function is introduced to reflect the complex relationship between the index and the risk. The stability of the risk calculation is evaluated through Monte Carlo simulation to ensure the reliability of the results.

[0155] In this embodiment, an innovative fuzzy comprehensive evaluation mechanism is designed. A fuzzy set including slight wear, moderate wear, and severe wear is established, and the fuzzy characteristics of the state are described through the membership function. The evaluation matrix is constructed based on historical data and expert experience to reflect the contribution of each index to the wear level. The maximum membership degree principle is adopted to determine the final evaluation result.

[0156] In this embodiment, an ablation and wear grading standard is implemented. The standard includes multiple grade intervals, and each interval corresponds to specific wear characteristics. The interval division considers the material performance limit and the use safety requirements to ensure the practicality of the grading result. The interval boundary is determined through statistical analysis to achieve the accurate division of the wear state.

[0157] In this embodiment, an early warning trigger mechanism is innovatively designed. An early warning condition is established based on the remaining life of the gun barrel, and the early warning is triggered when the wear state exceeds the safety threshold. The early warning threshold is determined through reliability analysis, considering the material fatigue limit and the safety margin. An adaptive adjustment mechanism is introduced to dynamically update the threshold according to the use conditions.

[0158] This embodiment realizes a confidence interval estimation method. The Bootstrap resampling technique is used to construct a prediction interval to reflect the uncertainty of the prediction result. The probability distribution of the predicted value is obtained through kernel density estimation, and the interval range at different confidence levels is calculated. A bias correction mechanism is introduced to improve the accuracy of interval estimation.

[0159] This embodiment designs a warning level determination criterion. The prediction interval and confidence level are mapped into a multi-level warning system, and different levels correspond to different maintenance measures. The warning level considers factors such as wear rate, cumulative amount, and development trend to achieve a comprehensive state assessment. The warning rules are optimized through a decision tree algorithm to improve the accuracy of determination.

[0160] This embodiment innovatively constructs a state assessment report generation module. The report content includes key information such as the predicted value of the wear amount, prediction interval, confidence level, and warning level. The prediction result is displayed through data visualization technology to intuitively reflect the evolution trend of the wear state. The assessment report adopts a hierarchical structure for easy understanding and use by users at different levels.

[0161] This embodiment realizes an accurate assessment of the ablation wear state of the gun barrel through multi-factor analysis and fuzzy evaluation. This solution combines the physical model with data analysis to establish a complete warning decision-making framework. Through innovative warning mechanisms and evaluation methods, the reliability of state assessment is improved. The overall solution provides a scientific basis for gun maintenance management and has important engineering application value.

[0162] This embodiment shows excellent performance in engineering practice. Through a reasonable index system and evaluation mechanism, an accurate description of the complex wear process is achieved. The innovative warning strategy and report generation method provide strong support for maintenance decision-making. The overall solution significantly improves the scientificity and accuracy of gun maintenance and is of great significance for enhancing equipment reliability.

[0163] In order to effectively solve the deficiencies of traditional technologies in model integration and state warning and provide a reliable basis for gun maintenance decision-making, this application provides an embodiment of a prediction device for the ablation wear amount of the gun barrel based on a combined model, which is used to implement all or part of the content of the prediction method for the ablation wear amount of the gun barrel based on the combined model. See Figure 8 The prediction device for the ablation wear amount of the gun barrel based on the combined model specifically includes the following content:

[0164] The wear evolution module 10 is used to collect historical data on the ablation wear of the gun barrel, extract temperature characteristic parameters, pressure characteristic parameters, and charge characteristic parameters from the historical data, establish a hierarchical neural network model using an adaptive neuron growth mechanism, use the temperature characteristic parameters, the pressure characteristic parameters, and the charge characteristic parameters as input variables to train the hierarchical neural network model to obtain an ablation wear amount identifier, construct a dynamic programming algorithm model for the change of ablation wear over time, and input the output result of the ablation wear amount identifier into the dynamic programming algorithm model to establish a phased wear evolution model;

[0165] The path determination module 20 is used to collect sensor data during continuous firing of the gun barrel, input the sensor data into the ablation wear amount identifier to obtain distribution parameters of the ablation wear amount, construct an energy state constraint function based on the distribution parameters, impose an evolution constraint on the dynamic programming algorithm model, substitute the dynamic programming algorithm model with the evolution constraint into an escape search operator for iterative optimization, generate a set of wear evolution paths that satisfy the energy constraint, calculate the cumulative energy loss of each path in the wear evolution path set, and select the path with the minimum cumulative energy loss as the optimal wear evolution path;

[0166] The state evaluation module 30 is used to extract state vectors of the optimal wear evolution path at different firing times, establish an evolution state curve representing the ablation wear of the gun barrel according to the state vectors, extract a wear rate index and a wear acceleration index from the evolution state curve, input the wear rate index and the wear acceleration index into a preset multi-factor warning threshold model, determine the ablation wear state based on the multi-factor warning threshold model, trigger a warning mechanism when the ablation wear state exceeds a preset threshold, and generate a state evaluation report including a predicted value of the ablation wear amount and a warning level.

[0167] As can be seen from the above description, the device for predicting the ablation wear amount of the gun barrel based on a combined model provided by the embodiment of the present application can construct a two-layer prediction architecture by combining an adaptive neuron growth mechanism and a dynamic programming algorithm. The hierarchical neural network trained by temperature, pressure, and charge characteristic parameters realizes the identification of the ablation wear amount, and an energy state constraint function is constructed based on sensor data. The system uses an escape search optimization operator to select the optimal wear evolution path, and combines wear rate and acceleration indexes to establish a multi-factor warning threshold model, realizing the accurate prediction and evaluation warning of the ablation wear state. This method effectively solves the deficiencies of traditional technologies in model integration and state warning, and provides a reliable basis for gun maintenance decision-making.

[0168] At the hardware level, in order to effectively address the deficiencies of traditional technologies in model integration and status warning and provide a reliable basis for gun maintenance decision-making, this application provides an embodiment of an electronic device for implementing all or part of the method for predicting the erosion and wear amount of the gun barrel based on the combined model. The electronic device specifically includes the following:

[0169] A processor, a memory, a communications interface, and a bus; wherein, the processor, the memory, and the communications interface communicate with each other through the bus; the communications interface is used to implement information transmission between the device for predicting the erosion and wear amount of the gun barrel based on the combined model and related devices such as the core business system, the user terminal, and the relevant database. The logic controller can be a desktop computer, a tablet computer, a mobile terminal, etc., and this embodiment is not limited thereto. In this embodiment, the logic controller can be implemented with reference to the embodiments of the method for predicting the erosion and wear amount of the gun barrel based on the combined model and the embodiments of the device for predicting the erosion and wear amount of the gun barrel based on the combined model, and the content thereof is incorporated herein, and the repeated parts will not be elaborated.

[0170] It can be understood that the user terminal can include a smart phone, a tablet electronic device, a network set-top box, a portable computer, a desktop computer, a personal digital assistant (PDA), a vehicle-mounted device, a smart wearable device, etc. Among them, the smart wearable device can include smart glasses, a smart watch, a smart bracelet, etc.

[0171] In practical applications, part of the method for predicting the erosion and wear amount of the gun barrel based on the combined model can be executed on the electronic device side as described above, or all operations can be completed in the client device. Specifically, it can be selected according to the processing capacity of the client device and the limitations of the user usage scenario, etc. This application does not make any limitations in this regard. If all operations are completed in the client device, the client device may further include a processor.

[0172] The above-mentioned client device can have a communication module (i.e., a communication unit) and can communicate with a remote server to achieve data transmission with the server. The server can include a server on the task scheduling center side, and in other implementation scenarios, it can also include a server of the intermediate platform, such as a server of a third-party server platform that has a communication link with the task scheduling center server. The server can include a single computer device, or can include a server cluster composed of multiple servers, or a server structure of a distributed device.

[0173] Figure 9 It is a schematic block diagram of the system composition of the electronic device 9600 according to the embodiment of this application. AsFigure 9 As shown, the electronic device 9600 may include a central processing unit 9100 and a memory 9140; the memory 9140 is coupled to the central processing unit 9100. It should be noted that this Figure 9 is exemplary; other types of structures may also be used to supplement or replace this structure to implement telecommunication functions or other functions.

[0174] In one embodiment, the function of the prediction method for the barrel ablation wear amount based on the combined model may be integrated into the central processing unit 9100. Among them, the central processing unit 9100 may be configured to perform the following controls:

[0175] Step S101: Collect historical data on the ablation wear of the gun barrel, extract temperature characteristic parameters, pressure characteristic parameters, and charge characteristic parameters from the historical data, establish a hierarchical neural network model using the adaptive neuron growth mechanism, use the temperature characteristic parameters, the pressure characteristic parameters, and the charge characteristic parameters as input variables to train the hierarchical neural network model to obtain an ablation wear amount identifier, construct a dynamic programming algorithm model for the change of ablation wear over time, and input the output result of the ablation wear amount identifier into the dynamic programming algorithm model to establish a phased wear evolution model;

[0176] Step S102: Collect sensor data during continuous firing of the gun barrel, input the sensor data into the ablation wear amount identifier to obtain distribution parameters of the ablation wear amount, construct an energy state constraint function based on the distribution parameters, impose an evolution constraint on the dynamic programming algorithm model, substitute the dynamic programming algorithm model with the evolution constraint into the escape search operator for iterative optimization, generate a set of wear evolution paths that satisfy the energy constraint, calculate the cumulative energy loss of each path in the wear evolution path set, and select the path with the minimum cumulative energy loss as the optimal wear evolution path;

[0177] Step S103: Extract the state vectors of the optimal wear evolution path at different firing times, establish an evolution state curve representing the barrel ablation wear according to the state vectors, extract a wear rate index and a wear acceleration index from the evolution state curve, input the wear rate index and the wear acceleration index into a preset multi-factor warning threshold model, determine the barrel ablation wear state based on the multi-factor warning threshold model, trigger a warning mechanism when the ablation wear state exceeds the preset threshold, and generate a state evaluation report including a predicted value of the ablation wear amount and a warning level.

[0178] As can be seen from the above description, the electronic device provided by the embodiments of the present application constructs a two-layer prediction architecture by combining an adaptive neuron growth mechanism and a dynamic programming algorithm. The ablation wear amount is identified through a hierarchical neural network trained by temperature, pressure, and charge characteristic parameters, and an energy state constraint function is constructed based on sensor data. The system uses an escape search optimization operator to select the optimal wear evolution path, and establishes a multi-factor early warning threshold model by combining wear rate and acceleration indicators, realizing accurate prediction and evaluation and early warning of the ablation wear state. This method effectively solves the deficiencies of traditional technologies in model integration and state early warning, providing a reliable basis for gun maintenance decision-making.

[0179] In another embodiment, the prediction device for the barrel ablation wear amount based on the combined model can be separately configured from the central processor 9100. For example, the prediction device for the barrel ablation wear amount based on the combined model can be configured as a chip connected to the central processor 9100, and the functions of the method for predicting the barrel ablation wear amount based on the combined model are realized through the control of the central processor.

[0180] As Figure 9 shown, the electronic device 9600 may further include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It should be noted that the electronic device 9600 does not necessarily have to include Figure 9 all the components shown in Figure 9 ; in addition, the electronic device 9600 may further include

[0181] components not shown in Figure 9 ; reference may be made to the prior art.

[0182] Among them, the memory 9140 may be, for example, one or more of a buffer, a flash memory, a hard drive, a removable medium, a volatile memory, a non-volatile memory, or other suitable devices. The above information related to failures can be stored, and in addition, programs for executing relevant information can be stored. And the central processor 9100 can execute the program stored in the memory 9140 to implement information storage or processing, etc.

[0183] The input unit 9120 provides input to the central processor 9100. The input unit 9120 is, for example, a key or a touch input device. The power supply 9170 is used to provide power to the electronic device 9600. The display 9160 is used to display display objects such as images and texts. The display may be, for example, an LCD display, but is not limited thereto.

[0184] The memory 9140 can be a solid-state memory, for example, a read-only memory (ROM), a random access memory (RAM), a SIM card, etc. It can also be a memory that stores information even when power is off, can be selectively erased and has more data. Examples of such a memory are sometimes referred to as EPROMs, etc. The memory 9140 can also be some other type of device. The memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 can include an application / function storage unit 9142 that is used to store application programs and function programs or the processes for operating the electronic device 9600 by the central processing unit 9100.

[0185] The memory 9140 can also include a data storage unit 9143 that is used to store data, such as contacts, digital data, pictures, sounds, and / or any other data used by the electronic device. The driver storage unit 9144 of the memory 9140 can include various drivers of the electronic device for communication functions and / or for performing other functions of the electronic device (such as a messaging application, an address book application, etc.).

[0186] The communication module 9110 is a transmitter / receiver that transmits and receives signals via the antenna 9111. The communication module 9110 (transmitter / receiver) is coupled to the central processing unit 9100 to provide input signals and receive output signals, which can be the same as in the case of a conventional mobile communication terminal.

[0187] Based on different communication technologies, multiple communication modules 9110 can be provided in the same electronic device, such as a cellular network module, a Bluetooth module, and / or a wireless local area network module, etc. The communication module 9110 (transmitter / receiver) is also coupled to the speaker 9131 and the microphone 9132 via the audio processor 9130 to provide an audio output via the speaker 9131 and receive an audio input from the microphone 9132, thereby implementing normal telecommunication functions. The audio processor 9130 can include any suitable buffer, decoder, amplifier, etc. In addition, the audio processor 9130 is also coupled to the central processing unit 9100, so that recording can be performed on the local device via the microphone 9132, and the sound stored on the local device can be played via the speaker 9131.

[0188] An embodiment of the present application also provides a computer-readable storage medium that can implement all steps of the method for predicting the barrel ablation wear amount based on a combined model with the execution subject being a server or a client in the above embodiments. A computer program is stored on the computer-readable storage medium. When the computer program is executed by a processor, all steps of the method for predicting the barrel ablation wear amount based on a combined model with the execution subject being a server or a client in the above embodiments are implemented. For example, when the processor executes the computer program, the following steps are implemented:

[0189] Step S101: Collect historical data of the barrel ablation wear of the artillery, extract temperature characteristic parameters, pressure characteristic parameters, and charge characteristic parameters from the historical data, establish a hierarchical neural network model using an adaptive neuron growth mechanism, use the temperature characteristic parameters, the pressure characteristic parameters, and the charge characteristic parameters as input variables to train the hierarchical neural network model to obtain an ablation wear amount identifier, construct a dynamic programming algorithm model for the change of ablation wear over time, and input the output result of the ablation wear amount identifier into the dynamic programming algorithm model to establish a phased wear evolution model;

[0190] Step S102: Collect sensor data during continuous firing of the artillery barrel, input the sensor data into the ablation wear amount identifier to obtain distribution parameters of the ablation wear amount, construct an energy state constraint function based on the distribution parameters, impose an evolution constraint on the dynamic programming algorithm model, substitute the dynamic programming algorithm model with the evolution constraint into an escape search operator for iterative optimization, generate a set of wear evolution paths that satisfy the energy constraint, calculate the cumulative energy loss of each path in the wear evolution path set, and select the path with the minimum cumulative energy loss as the optimal wear evolution path;

[0191] Step S103: Extract the state vectors of the optimal wear evolution path at different firing times, establish an evolution state curve representing the barrel ablation wear according to the state vectors, extract a wear rate index and a wear acceleration index from the evolution state curve, input the wear rate index and the wear acceleration index into a preset multi-factor warning threshold model, determine the barrel ablation wear state based on the multi-factor warning threshold model, and trigger a warning mechanism when the ablation wear state exceeds a preset threshold, and generate a state evaluation report including a predicted value of the ablation wear amount and a warning level.

[0192] As can be seen from the above description, the computer-readable storage medium provided by the embodiments of the present application constructs a two-layer prediction architecture by combining an adaptive neuron growth mechanism and a dynamic programming algorithm. The ablation wear amount is identified through a hierarchical neural network trained by temperature, pressure, and charge characteristic parameters, and an energy state constraint function is constructed based on sensor data. The system uses an escape search optimization operator to select the optimal wear evolution path, and establishes a multi-factor early warning threshold model by combining wear rate and acceleration indicators, realizing accurate prediction and evaluation and early warning of the ablation wear state. This method effectively solves the deficiencies of traditional technologies in model integration and state early warning, providing a reliable basis for gun maintenance decision-making.

[0193] An embodiment of the present application also provides a computer program product that can implement all steps of the method for predicting the barrel ablation wear amount based on a combined model with the execution subject in the above embodiment being a server or a client. When the computer program / instructions are executed by a processor, the steps of the method for predicting the barrel ablation wear amount based on the combined model are implemented. For example, the computer program / instructions implement the following steps:

[0194] Step S101: Collect historical data on the ablation wear of the gun barrel, extract temperature characteristic parameters, pressure characteristic parameters, and charge characteristic parameters from the historical data, establish a hierarchical neural network model using the adaptive neuron growth mechanism, use the temperature characteristic parameters, the pressure characteristic parameters, and the charge characteristic parameters as input variables to train the hierarchical neural network model to obtain an ablation wear amount identifier, construct a dynamic programming algorithm model for the change of ablation wear over time, and input the output result of the ablation wear amount identifier into the dynamic programming algorithm model to establish a stage wear evolution model;

[0195] Step S102: Collect sensor data during continuous firing of the gun barrel, input the sensor data into the ablation wear amount identifier to obtain distribution parameters of the ablation wear amount, construct an energy state constraint function based on the distribution parameters, impose an evolution constraint on the dynamic programming algorithm model, substitute the dynamic programming algorithm model with the evolution constraint into the escape search operator for iterative optimization, generate a set of wear evolution paths that satisfy the energy constraint, calculate the cumulative energy loss of each path in the set of wear evolution paths, and select the path with the minimum cumulative energy loss as the optimal wear evolution path;

[0196] Step S103: Extract the state vectors of the optimal wear evolution path at different firing moments, establish an evolution state curve representing the barrel ablation wear according to the state vectors, extract the wear rate index and the wear acceleration index from the evolution state curve, input the wear rate index and the wear acceleration index into a preset multi-factor warning threshold model, determine the barrel ablation wear state based on the multi-factor warning threshold model, and trigger a warning mechanism when the ablation wear state exceeds the preset threshold, and generate a state evaluation report including the predicted value of the ablation wear amount and the warning level.

[0197] As can be seen from the above description, the computer program product provided by the embodiments of the present application constructs a two-layer prediction architecture by combining the adaptive neuron growth mechanism and the dynamic programming algorithm. The ablation wear amount is identified by a hierarchical neural network trained with temperature, pressure, and charge characteristic parameters, and an energy state constraint function is constructed based on sensor data. The system uses an escape search optimization operator to select the optimal wear evolution path, and establishes a multi-factor warning threshold model by combining the wear rate and acceleration indexes, realizing the accurate prediction and evaluation warning of the ablation wear state. This method effectively solves the deficiencies of traditional technologies in model integration and state warning, and provides a reliable basis for the maintenance decision-making of artillery.

[0198] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a device, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0199] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (devices), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, and the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0200] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to work in a particular manner, such that the instructions stored in the computer-readable memory produce a manufacture including an instruction device that implements the functions specified in one or more of the processes Figure 1 one or more of the processes and / or blocks Figure 1 specified in one or more of the blocks or blocks.

[0201] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, such that a series of operational steps are performed on the computer or other programmable apparatus to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions specified in one or more of the processes Figure 1 one or more of the processes and / or blocks Figure 1 specified in one or more of the blocks or blocks.

[0202] Specific embodiments are used in the present invention to illustrate the principles and implementation manners of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A prediction method for the ablation wear amount of a gun barrel based on a combined model, characterized in that The method includes: Collecting historical data on the ablation wear of the gun barrel, extracting temperature characteristic parameters, pressure characteristic parameters, and charge characteristic parameters from the historical data, where the charge characteristic parameters include charge amount, charge density, filling coefficient, ambient temperature, and ambient humidity, establishing a hierarchical neural network model using an adaptive neuron growth mechanism, using the temperature characteristic parameters, the pressure characteristic parameters, and the charge characteristic parameters as input variables to train the hierarchical neural network model to obtain an ablation wear amount identifier, constructing a dynamic programming algorithm model for the change of ablation wear over time, and inputting the output result of the ablation wear amount identifier into the dynamic programming algorithm model to establish a phased wear evolution model; Collecting sensor data during continuous firing of the gun barrel, inputting the sensor data into the ablation wear amount identifier to obtain distribution parameters of the ablation wear amount, constructing an energy state constraint function based on the distribution parameters, imposing an evolution constraint on the dynamic programming algorithm model, substituting the dynamic programming algorithm model with the evolution constraint into an escape search operator for iterative optimization, generating a set of wear evolution paths that satisfy the energy constraint, calculating the cumulative energy loss of each path in the wear evolution path set, and selecting the path with the minimum cumulative energy loss as the optimal wear evolution path; Extracting the state vectors of the optimal wear evolution path at different firing times, establishing an evolution state curve representing the ablation wear of the gun barrel according to the state vectors, extracting a wear rate index and a wear acceleration index from the evolution state curve, inputting the wear rate index and the wear acceleration index into a preset multi-factor warning threshold model, determining the ablation wear state of the gun barrel based on the multi-factor warning threshold model, and triggering a warning mechanism when the ablation wear state exceeds the preset threshold, generating a state evaluation report including a predicted value of the ablation wear amount and a warning level.

2. The method for predicting the amount of barrel ablation wear based on a combined model according to claim 1, wherein The collecting of historical data on the ablation wear of the gun barrel, extracting temperature characteristic parameters, pressure characteristic parameters, and charge characteristic parameters from the historical data, establishing a hierarchical neural network model using an adaptive neuron growth mechanism, using the temperature characteristic parameters, the pressure characteristic parameters, and the charge characteristic parameters as input variables to train the hierarchical neural network model to obtain an ablation wear amount identifier, and constructing a dynamic programming algorithm model for the change of ablation wear over time includes: Collecting historical data on the ablation wear of the gun barrel, performing denoising processing on the historical data based on the wavelet transform method, calculating the numerical values of the temperature sensor, pressure sensor, and charge sensor at different times, converting the numerical values into temperature characteristic parameters, pressure characteristic parameters, and charge characteristic parameters in combination with the sensor calibration curve, and performing normalization processing on the temperature characteristic parameters, the pressure characteristic parameters, and the charge characteristic parameters to generate a feature vector; Construct a hierarchical neural network model using an adaptive neuron growth mechanism. Input the feature vector into the hierarchical neural network model, train the hierarchical neural network model based on the backpropagation algorithm to obtain an ablation wear amount identifier, establish an ablation wear state transition matrix using a Markov process, construct a dynamic programming algorithm model containing the state transition matrix, and substitute the output result of the ablation wear amount identifier into the dynamic programming algorithm model.

3. The method for predicting the barrel ablation wear amount based on the combined model according to claim 1, wherein Inputting the output result of the ablation wear amount identifier into the dynamic programming algorithm model to establish a staged wear evolution model includes: Dividing the output result of the ablation wear amount identifier into multiple time series intervals according to the number of firing times, performing piecewise linear fitting on the ablation wear data in each time series interval, calculating the wear change rate and wear acceleration in different intervals, and constructing a state transition probability matrix reflecting the ablation wear evolution characteristics based on the wear change rate and the wear acceleration; Substitute the state transition probability matrix into the dynamic programming algorithm model, construct a staged wear evolution model including the temperature accumulation effect, pressure accumulation effect, and charge accumulation effect during the firing process, apply physical boundary constraint conditions to the staged wear evolution model, and use the Bellman equation to perform iterative calculations on the state transition process of each stage.

4. The method for predicting the barrel ablation wear amount based on the combined model according to claim 1, wherein Collecting sensor data during continuous firing of the gun barrel, inputting the sensor data into the ablation wear amount identifier to obtain the distribution parameters of the ablation wear amount, constructing an energy state constraint function based on the distribution parameters, applying an evolution constraint to the dynamic programming algorithm model, and substituting the dynamic programming algorithm model with the evolution constraint into the escape search operator for iterative optimization to generate a set of wear evolution paths that satisfy the energy constraint, including: Collecting temperature sensor, pressure sensor, and charge sensor data during continuous firing of the gun barrel, performing time-domain sampling and feature extraction on the sensor data, inputting the extracted feature data into the ablation wear amount identifier, calculating the mean and variance distribution parameters of the ablation wear amount based on the Gaussian mixture model, and constructing an energy state constraint function containing temperature energy dissipation, pressure energy loss, and charge energy conversion using the distribution parameters; Substitute the energy state constraint function into the dynamic programming algorithm model to form a state transition equation with an evolution constraint, construct a global optimization operator based on the escape search mechanism, input the state transition equation into the global optimization operator for iterative optimization, use the Monte Carlo sampling method to generate multiple groups of initial solutions, and perform escape search optimization on each group of initial solutions to obtain a set of wear evolution paths that satisfy the energy constraint.

5. The method for predicting the barrel ablation wear amount based on the combined model according to claim 1, wherein Calculating the cumulative energy loss of each path in the set of wear evolution paths, and selecting the path with the minimum cumulative energy loss as the optimal wear evolution path, including: Calculate the temperature cumulative loss, pressure cumulative loss, and charge cumulative loss of each path in the set of wear evolution paths during continuous firing. Substitute the temperature cumulative loss, pressure cumulative loss, and charge cumulative loss into the energy weight fusion model, and calculate the comprehensive energy loss index of each path based on the energy weight fusion model. Normalize the comprehensive energy loss index. Construct a path evaluation criterion based on the principle of minimum energy. Use the path evaluation criterion to sort the normalized comprehensive energy loss indexes, select the path with the minimum comprehensive energy loss index from the set of wear evolution paths as the optimal wear evolution path, and calculate the state transition sequence of the optimal wear evolution path at different firing stages.

6. The method for predicting the barrel ablation wear amount based on the combined model according to claim 1, wherein Extract the state vectors of the optimal wear evolution path at different firing moments. According to the state vectors, establish an evolution state curve representing the barrel ablation wear, and extract the wear rate index and wear acceleration index from the evolution state curve, including: Extract the state vectors of each firing moment from the optimal wear evolution path. Based on the state vectors, construct a state space model including temperature state components, pressure state components, and charge state components. Use the cubic spline interpolation algorithm to continuousize the state space model, and map the interpolated state space trajectory to the time-wear amount coordinate system to obtain the evolution state curve. Perform numerical differentiation operations on the evolution state curve, calculate the first derivative value at each sampling point of the curve to obtain the wear rate index, calculate the change rate of the first derivative value to obtain the wear acceleration index, and use the moving average filtering algorithm to smooth the wear rate index and the wear acceleration index.

7. The method for predicting the barrel ablation wear amount based on the combined model according to claim 1, wherein Input the wear rate index and the wear acceleration index into a preset multi-factor warning threshold model. Based on the multi-factor warning threshold model, determine the barrel ablation wear state. When the ablation wear state exceeds the preset threshold, trigger the warning mechanism and generate a state evaluation report including the predicted value of the ablation wear amount and the warning level, including: Normalize the wear rate index and the wear acceleration index and then input them into a preset multi-factor warning threshold model. Based on the multi-factor warning threshold model, calculate the risk degree index of the current ablation wear state. Use the fuzzy comprehensive evaluation method to map the risk degree index to the preset ablation wear grading standard, and determine the ablation wear state by comparing the ablation wear grading standard with the preset threshold. Construct a warning trigger mechanism based on the remaining life of the barrel. When the ablation wear state exceeds the preset threshold, calculate the prediction interval and confidence level of the barrel ablation wear amount, determine the warning level according to the prediction interval and the confidence level, and generate a state evaluation report including the predicted value of the ablation wear amount and the warning level.

8. A prediction device for the ablation wear amount of a gun barrel based on a combined model, characterized in that The device includes: A wear evolution module, which is used to collect historical data on the ablation wear of the gun barrel, extract temperature characteristic parameters, pressure characteristic parameters and charge characteristic parameters from the historical data, wherein the charge characteristic parameters include charge amount, charge density, filling coefficient, ambient temperature, and ambient humidity, establish a hierarchical neural network model by using an adaptive neuron growth mechanism, use the temperature characteristic parameters, the pressure characteristic parameters, and the charge characteristic parameters as input variables to train the hierarchical neural network model to obtain an ablation wear amount identifier, construct a dynamic programming algorithm model for the change of ablation wear over time, and input the output result of the ablation wear amount identifier into the dynamic programming algorithm model to establish a stage wear evolution model; A path determination module, which is used to collect sensor data during continuous firing of the gun barrel, input the sensor data into the ablation wear amount identifier to obtain distribution parameters of the ablation wear amount, construct an energy state constraint function based on the distribution parameters, impose an evolution constraint on the dynamic programming algorithm model, substitute the dynamic programming algorithm model with the evolution constraint into an escape search operator for iterative optimization, generate a set of wear evolution paths that meet the energy constraint, calculate the cumulative energy loss of each path in the wear evolution path set, and select the path with the minimum cumulative energy loss as the optimal wear evolution path; A state evaluation module, which is used to extract the state vectors of the optimal wear evolution path at different firing times, establish an evolution state curve representing the ablation wear of the gun barrel according to the state vectors, extract a wear rate index and a wear acceleration index from the evolution state curve, input the wear rate index and the wear acceleration index into a preset multi-factor early warning threshold model, determine the ablation wear state of the gun barrel based on the multi-factor early warning threshold model, trigger an early warning mechanism when the ablation wear state exceeds the preset threshold, and generate a state evaluation report including a predicted value of the ablation wear amount and an early warning level.

9. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the method for predicting the ablation wear amount of the gun barrel based on the combined model according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method for predicting the ablation wear amount of the gun barrel based on the combined model according to any one of claims 1 to 7.

Images