Explosive and powder safety information management system

Abstract

The invention discloses an explosive and powder safety information management system, and belongs to the technical field of explosive and powder management. The system comprises an information acquisition module, an explosive and powder state monitoring module, an explosive and powder safety evaluation module, a data processing module, an early warning and control module and an emergency plan storage module, the information acquisition module acquires safety information of explosives and powders; the explosive and powder state monitoring module predicts a potential explosion risk; the explosive and powder safety evaluation module monitors and analyzes stress distribution conditions of explosives and powders in storage and transportation processes; the data processing module is used for comprehensively analyzing potential explosion risks and stress distribution conditions of explosives and powders; the early warning and control module sends out an early warning signal; and the emergency plan storage module stores and calls a corresponding emergency plan. According to the invention, the monitoring precision and response speed of the system are improved, and the safety and reliability of explosive and powder management are ensured.

Description

Technical Field

[0001] The invention belongs to the technical field of explosive management, and in particular relates to an explosive safety information management system. Background Art

[0002] As a highly dangerous substance, explosives are widely used in military, mining, construction and other fields. How to ensure the safety of explosives during their production, storage, transportation and use has always been the focus of the industry. Due to the special properties of explosives, the slightest carelessness may lead to serious safety accidents, causing casualties and property losses. Therefore, comprehensive and accurate safety monitoring and risk assessment of explosives are crucial to ensure production and use safety.

[0003] Traditional safety management methods for explosives and explosives mainly rely on manual monitoring and conventional detection methods. These methods have problems such as low monitoring accuracy, slow response speed, and weak risk prediction ability. In addition, existing monitoring systems can often only collect limited environmental parameters, and lack monitoring of the internal state of explosives and explosives, making it difficult to achieve real-time detection and prediction of tiny cracks and structural changes. Therefore, how to improve the monitoring accuracy, response speed and risk prediction ability of explosives and explosives safety management has become an urgent problem to be solved. Summary of the invention

[0004] The purpose of the present invention is to solve the problems of low monitoring accuracy, slow response speed, weak risk prediction ability, etc. in traditional explosives safety management methods, and to provide an explosives safety information management system for this purpose.

[0005] The objective of the present invention is achieved through the following technical solutions:

[0006] The explosives safety information management system of the present invention comprises an information collection module, an explosives status monitoring module, an explosives safety assessment module, a data processing module, an early warning and control module and an emergency plan storage module;

[0007] The information collection module is used to collect safety information of explosives during production, storage, transportation and use; the safety information includes environmental parameters and explosives information, the environmental parameters include temperature, humidity, pressure, vibration and light, and the explosives information includes the type, quantity, production date and storage location of the explosives;

[0008] The explosive state monitoring module is used to detect cracks and structural changes inside the explosive in real time and predict potential explosion risks;

[0009] The explosive state monitoring module includes: a high-frequency sound wave detection submodule, a signal processing submodule and a signal analysis submodule;

[0010] The high-frequency sound wave detection submodule is used to transmit and receive high-frequency sound wave signals;

[0011] Signal processing submodule: used to filter and amplify the received sound wave signal and extract the characteristic signal;

[0012] Signal analysis submodule: Based on the extracted feature signals, a recurrent neural network (RNN) model is used to identify and predict internal changes and potential risks of explosives;

[0013] The explosive safety assessment module is used to monitor and analyze the stress distribution of explosives during storage and transportation, and to assess their structural integrity and safety status in combination with a finite element analysis model;

[0014] The data processing module is used to comprehensively analyze the potential explosion risk and stress distribution of explosives and generate a safety assessment report;

[0015] The warning and control module is used to send out warning signals when there is a safety risk, and manually trigger corresponding emergency measures according to the warning signals;

[0016] The emergency plan storage module is used to store and call corresponding emergency plans according to the safety assessment results of different types of explosives.

[0017] Optionally, the information collection module includes:

[0018] Temperature monitoring submodule: monitors the temperature around the explosive in real time through the temperature sensor;

[0019] Humidity monitoring submodule: monitors the humidity around explosives in real time through humidity sensors;

[0020] Pressure monitoring submodule: real-time monitoring of the pressure in the explosive storage environment through pressure sensors;

[0021] Vibration monitoring submodule: real-time monitoring of the vibration of explosives during production, storage and transportation through vibration sensors;

[0022] Light monitoring submodule: monitors the light intensity around the explosives in real time through light sensors;

[0023] Data collection submodule: records the type, quantity, production date and storage location of explosives.

[0024] Optionally, the detection method adopted by the high-frequency sound wave detection submodule is: emitting high-frequency sound wave signals into the interior of the explosive through a high-frequency sound wave transmitting device; receiving high-frequency sound wave signals reflected and scattered back from the interior of the explosive through a high-frequency sound wave receiving device; processing the received reflected and scattered sound wave signals, and detecting and identifying tiny cracks and structural changes inside the explosive by analyzing the time delay, frequency change and waveform change of the sound wave signals.

[0025] Optionally, the processing method adopted by the signal processing submodule is:

[0026] 1) Filtering: A bandpass filter is used to filter the received sound wave signal. The expression of the filtering process is:

[0027]

[0028]

[0029] in, represents the Fourier transform, represents the inverse Fourier transform, x(t) is the received sound wave signal, H(f) is the frequency domain transfer function of the bandpass filter, y(t) is the filtered signal, f0 is the center frequency, and Δf is the bandwidth;

[0030] 2) Amplification: The filtered sound wave signal is amplified using an automatic gain control (AGC) circuit. The expression for the amplification process is:

[0031] y(t)′=G(t)·y(t);

[0032]

[0033] Where y(t)′ is the amplified signal, G(t) is the gain control function, G0 is the initial gain, T is the time window length, and y(t) is the filtered signal;

[0034] 3) Feature extraction: The expression of feature extraction is:

[0035] Feature extraction: Fourier transform (FFT) and wavelet transform are used to extract the frequency domain and time-frequency domain features of the amplified acoustic wave signal, and the features reflecting the micro cracks and structural changes inside the explosive are identified. The expression for feature extraction is:

[0036]

[0037] Among them, X(f) is the frequency domain signal, x(t) is the amplified time domain signal, f is the frequency, j is the imaginary unit, W(a, b) is the wavelet coefficient, ψ is the mother wavelet function, and a and b are the scale and translation parameters respectively.

[0038] Optionally, the method for the RNN model to identify and predict internal changes and potential risks of explosives is:

[0039] 1) Signal preprocessing: perform mean normalization and bandpass filtering on the input signal;

[0040] 2) Phase space reconstruction: The one-dimensional signal is reconstructed into a high-dimensional phase space using the delay embedding method. The dynamic characteristics of the signal are extracted through phase space reconstruction. The expression of phase space reconstruction is:

[0041] X(t)=[x(t), x(t+τ), x(t+2τ),..., x(t+(m-1)τ)];

[0042] Where X(t) is a point in phase space, τ is the time delay, and m is the embedding dimension;

[0043] 3) Multi-scale RNN construction: Construct a multi-layer RNN, each layer processes signals of different time scales. The expression for multi-scale RNN construction is:

[0044]

[0045] in, are the hidden states of the 1st, 2nd, and 3rd layers respectively. and are the weight matrices of the first, second, and third layers, respectively, and b 1 、b 2 、b 3 are the biases of the first, second and third layers respectively, and σ is the activation function;

[0046] 4) Multi-head attention mechanism: A multi-head attention mechanism is introduced based on the output of multi-scale RNN. The expression of the multi-head attention mechanism is:

[0047]

[0048] Among them, v i and is the parameter of the ith attention head, is the attention weight of the ith attention head at time step t, is the weighted output of multi-head attention;

[0049] 5) Signal analysis and prediction: The signal is analyzed and small cracks and structural changes are predicted through the fully connected layer and activation function. The expression of signal analysis and prediction is:

[0050]

[0051] Among them, W ois the weight matrix of the output layer, b o is the bias of the output layer;

[0052]

[0053] Where σ is the activation function, is the prediction result.

[0054] Optionally, the method for monitoring and analyzing the safety of explosives and propellants adopted by the explosives and propellants safety assessment module includes:

[0055] 1) Stress sensor data acquisition: During the storage and transportation of explosives, stress data is collected in real time through stress sensors. The expression for stress data acquisition is:

[0056] σ(t,x,y,z)=σ sensor (t, x, y, z);

[0057] Where σ(t, x, y, z) represents the stress data at time t and position (x, y, z), σ sensor (t, x, y, z) is the stress value measured by the sensor;

[0058] 2) Stress data preprocessing: Filter and denoise the collected stress data. The expression for stress data preprocessing is:

[0059] σ filtered (t,x,y,z)=σ(t,x,y,z)*h filter (t);

[0060] Among them, σ filtered (t, x, y, z) is the filtered stress data, h filter (t) is the impulse response of the filter, * indicates the convolution operation;

[0061] 3) Stress distribution analysis: Using the pre-processed stress data, the stress distribution of explosives during storage and transportation is analyzed. The expression of stress distribution analysis is:

[0062] σ distribution (x, y, z) = f(σ filtered (t, x, y, z));

[0063] Among them, σ distribution (x, y, z) is the stress distribution at the spatial position (x, y, z), and f represents the spatial distribution function of the stress data;

[0064] 4) Finite element analysis: Based on the physical and mechanical properties of explosives, a finite element analysis model is established to simulate the behavior of explosives under different stress conditions;

[0065] 5) Structural integrity and safety status assessment: Combined with the results of finite element analysis, the structural integrity and safety status of explosives are assessed to identify potential safety hazards. The evaluation expression is:

[0066]

[0067] Among them, σ yield is the yield strength of explosive materials, max(σ distribution (x, y, z)) is the maximum stress value in the stress distribution, and Safety Index is an evaluation index of structural integrity and safety status.

[0068] Optionally, the analysis method adopted by the finite element analysis model includes:

[0069] 1) Discretization: Adaptive meshing technology is used to dynamically adjust the unit size according to the stress concentration area. The discretization expression is:

[0070]

[0071] where u(x, y, z) is the displacement at position (x, y, z), N i is the shape function of the ith node, u i is the displacement of the ith node;

[0072] 2) Unit stiffness matrix: Introducing the nonlinear characteristics of the material and the influence of temperature, considering the mechanical response of explosives in different environments, the expression of the unit stiffness matrix is ​​obtained as follows:

[0073]

[0074] Among them, K e is the element stiffness matrix, B is the strain-displacement matrix, D(T) is the material elasticity matrix considering the temperature effect, V e is the unit volume;

[0075] 3) Global stiffness matrix: Using sparse matrix technology, the stiffness matrices of all units are assembled into a global stiffness matrix to describe the mechanical behavior of the entire structure. The expression of the global stiffness matrix is:

[0076]

[0077] Where K is the global stiffness matrix and m is the number of elements;

[0078] 4) Real-time equation solving: Solve the global equilibrium equation in real time to obtain the displacement of the node, the expression is:

[0079] Ku=f(t);

[0080] Where u is the node displacement vector, f(t) is the node external force vector at time t;

[0081] 5) Stress and strain calculation: Introduce the dynamic stress concentration factor, consider the influence of microcracks on stress distribution, and calculate the stress and strain in each unit according to the node displacement. The expression is:

[0082] ε(t)=Bu(t);

[0083] σ(t)=D(T)ε(t)+K c ε(t);

[0084] Where ε(t) is the strain vector at time t, σ(t) is the stress vector at time t, and K c is the dynamic stress concentration factor matrix.

[0085] Optionally, the data processing method adopted by the data processing module includes:

[0086] 1) Preliminary data processing: Preliminary processing of the collected safety information and stress data, including cleaning, normalization and denoising;

[0087] 2) Feature extraction: Extract key features from the initially processed safety information and stress data, including stress peak, stress distribution, and temperature change. The expression for feature extraction is:

[0088] Stress max = max(σ(t, x, y, z));

[0089]

[0090] Where, σ(t, x, y, z) is the stress data at time t and position (x, y, z), Stress max and Stress mean are the peak stress and mean stress, respectively, and N is the number of data points;

[0091] 3) Risk assessment: The extracted key features are evaluated using logistic regression algorithm to predict the potential explosion risk of explosives. The risk assessment expression is:

[0092]

[0093] Among them, Risk is the probability of explosion risk, β0, β1, …, β n are the parameters of the logistic regression model, Temp is the temperature feature;

[0094] 4) Stress distribution analysis: Combined with the output of the finite element analysis model, analyze the stress distribution, identify stress concentration areas and potential risk points. The expression for stress distribution analysis is:

[0095] σ distribution (x, y, z) = Ku(t);

[0096] Among them, σ distribution (x, y, z) is the stress distribution at the spatial position (x, y, z), K is the global stiffness matrix, and u(t) is the nodal displacement vector at time t;

[0097] 5) Generate safety assessment report: Generate a safety assessment report based on the results of risk assessment and stress distribution analysis, including stress distribution diagram, risk prediction results and safety recommendations.

[0098] Optionally, the early warning and control module includes: a risk assessment result monitoring submodule, an early warning signal generating submodule and an emergency measure triggering submodule;

[0099] The risk assessment result monitoring submodule: monitors the risk assessment results generated by the data processing module in real time to determine whether there is a security risk, which is expressed as:

[0100] Risk threshold =α;

[0101] if Risk>Risk threshold then trigger warning;

[0102] Among them, Risk is the output explosion risk probability, Risk threshold is the preset risk threshold, α is the threshold constant;

[0103] Warning signal generation submodule: when the explosion risk probability is detected to exceed the preset risk threshold, a warning signal is generated and issued;

[0104] Emergency measures triggering submodule: Based on the early warning signal, manually trigger the corresponding emergency measures, including personnel evacuation, isolation of explosives and fire, and cooling.

[0105] Optionally, the emergency plan storage module includes: an emergency plan classification storage submodule, a safety assessment result mapping submodule and an emergency plan calling submodule;

[0106] Emergency plan classification storage submodule: According to the characteristics and potential risks of different types of explosives, the emergency plans are classified and stored in the database, and classification labels are established. The corresponding emergency plans are designed for each type of explosives, including explosives plans (fire isolation, explosion isolation, evacuation of rescue personnel, cooling measures), flammable and explosive gas plans (fire extinguishing, gas leakage treatment, ventilation measures, explosion isolation) and hazardous chemicals plans (leakage treatment, neutralization treatment, chemical protection, hazardous waste disposal);

[0107] Safety assessment result mapping submodule: Identify the type of explosives through safety assessment results and find the corresponding emergency plan;

[0108] Emergency plan calling submodule: extracts the emergency plan matching the current explosive type from the database and generates emergency response measures.

[0109] Beneficial effects of the present invention:

[0110] The present invention comprehensively collects environmental parameters and explosive information during the production, storage, transportation and use of explosives through an information collection module, and combines high-frequency acoustic wave detection technology to monitor tiny cracks and structural changes inside the explosives in real time, and accurately predicts potential explosion risks through signal processing and a recursive neural network model. The system greatly improves the accuracy and sensitivity of explosive status monitoring, achieves a comprehensive understanding of the explosive status, and thus significantly improves the monitoring accuracy and response speed of the system, ensuring the safety and reliability of explosive management.

[0111] The present invention monitors and analyzes the stress distribution of explosives during storage and transportation by combining stress sensor data with a finite element analysis model, and evaluates the structural integrity and safety status thereof. The data processing module generates a detailed safety assessment report by comprehensively analyzing safety information and stress data, and provides accurate risk assessment and reliable safety guidance. The early warning and control module monitors the risk assessment results in real time, and when a safety risk is detected, a warning signal is issued in time, and corresponding emergency measures are manually triggered according to the warning signal, so as to ensure the safety and reliability of the management of explosives.

[0112] The present invention classifies, stores and calls corresponding emergency plans according to the characteristics and potential risks of different types of explosives. Through the mapping of safety assessment results, the system can quickly identify the types of explosives and extract matching emergency plans, and generate specific emergency response measures including fire isolation, explosion isolation, personnel evacuation, cooling measures, gas leakage treatment, chemical neutralization, hazardous waste disposal, etc. This module ensures that when safety risks occur in explosives, corresponding emergency response measures can be quickly and accurately executed, thereby improving the emergency response capability and reliability of the system and effectively preventing and responding to potential safety risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0113] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0114] Figure 1 This is a module schematic diagram of the explosive safety information management system of the present invention;

[0115] Figure 2 It is a schematic diagram of the explosive state monitoring module in the explosive safety information management system of the present invention. DETAILED DESCRIPTION

[0116] The present invention is described in detail below with reference to the accompanying drawings and embodiments.

[0117] Example

[0118] like Figure 1 As shown, the explosive safety information management system of the present invention includes an information collection module, an explosive state monitoring module, an explosive safety assessment module, a data processing module, an early warning and control module, and an emergency plan storage module;

[0119] The information collection module is used to collect safety information of explosives during production, storage, transportation and use; the safety information includes environmental parameters and explosives information, the environmental parameters include temperature, humidity, pressure, vibration and light, and the explosives information includes the type, quantity, production date and storage location of the explosives;

[0120] The explosive state monitoring module is used to detect cracks and structural changes inside the explosive in real time and predict potential explosion risks;

[0121] like Figure 2 As shown, the explosive state monitoring module includes: a high-frequency sound wave detection submodule, a signal processing submodule and a signal analysis submodule;

[0122] The high-frequency sound wave detection submodule is used to transmit and receive high-frequency sound wave signals;

[0123] Signal processing submodule: used to filter and amplify the received sound wave signal and extract the characteristic signal;

[0124] Signal analysis submodule: Based on the extracted feature signals, a recurrent neural network (RNN) model is used to identify and predict internal changes and potential risks of explosives;

[0125] The explosive safety assessment module is used to monitor and analyze the stress distribution of explosives during storage and transportation, and to assess their structural integrity and safety status in combination with a finite element analysis model;

[0126] The data processing module is used to comprehensively analyze the potential explosion risk and stress distribution of explosives and generate a safety assessment report;

[0127] The warning and control module is used to send out warning signals when there is a safety risk, and manually trigger corresponding emergency measures according to the warning signals;

[0128] The emergency plan storage module is used to store and call corresponding emergency plans according to the safety assessment results of different types of explosives.

[0129] Optionally, the information collection module includes:

[0130] Temperature monitoring submodule: monitors the temperature around the explosive in real time through the temperature sensor;

[0131] Humidity monitoring submodule: monitors the humidity around explosives in real time through humidity sensors;

[0132] Pressure monitoring submodule: real-time monitoring of the pressure in the explosive storage environment through pressure sensors;

[0133] Vibration monitoring submodule: real-time monitoring of the vibration of explosives during production, storage and transportation through vibration sensors;

[0134] Light monitoring submodule: monitors the light intensity around the explosives in real time through light sensors;

[0135] Data collection submodule: records the type, quantity, production date and storage location of explosives.

[0136] Optionally, the detection method adopted by the high-frequency sound wave detection submodule is: emitting high-frequency sound wave signals into the interior of the explosive through a high-frequency sound wave transmitting device; receiving high-frequency sound wave signals reflected and scattered back from the interior of the explosive through a high-frequency sound wave receiving device; processing the received reflected and scattered sound wave signals, and detecting and identifying tiny cracks and structural changes inside the explosive by analyzing the time delay, frequency change and waveform change of the sound wave signals.

[0137] Optionally, the processing method adopted by the signal processing submodule is:

[0138] 1) Filtering: A bandpass filter is used to filter the received sound wave signal. The expression of the filtering process is:

[0139]

[0140] in, represents the Fourier transform, represents the inverse Fourier transform, x(t) is the received sound wave signal, H(f) is the frequency domain transfer function of the bandpass filter, y(t) is the filtered signal, f0 is the center frequency, and Δf is the bandwidth;

[0141] 2) Amplification: The filtered sound wave signal is amplified using an automatic gain control (AGC) circuit. The expression for the amplification process is:

[0142] y(t)′=G(t)·y(t);

[0143]

[0144] Where y(t)′ is the amplified signal, G(t) is the gain control function, G0 is the initial gain, T is the time window length, and y(t) is the filtered signal;

[0145] 3) Feature extraction: The expression of feature extraction is:

[0146] Feature extraction: Fourier transform (FFT) and wavelet transform are used to extract the frequency domain and time-frequency domain features of the amplified acoustic wave signal, and the features reflecting the micro cracks and structural changes inside the explosive are identified. The expression for feature extraction is:

[0147]

[0148] Among them, X(f) is the frequency domain signal, x(t) is the amplified time domain signal, f is the frequency, j is the imaginary unit, W(a, b) is the wavelet coefficient, ψ is the mother wavelet function, and a and b are the scale and translation parameters respectively.

[0149] Optionally, the method for the RNN model to identify and predict internal changes and potential risks of explosives is:

[0150] 1) Signal preprocessing: perform mean normalization and bandpass filtering on the input signal;

[0151] 2) Phase space reconstruction: The one-dimensional signal is reconstructed into a high-dimensional phase space using the delay embedding method. The dynamic characteristics of the signal are extracted through phase space reconstruction. The expression of phase space reconstruction is:

[0152] X(t)=[x(t), x(t+τ), x(t+2τ),..., x(t+(m-1)τ)];

[0153] Where X(t) is a point in phase space, τ is the time delay, and m is the embedding dimension;

[0154] 3) Multi-scale RNN construction: Construct a multi-layer RNN, each layer processes signals of different time scales. The expression for multi-scale RNN construction is:

[0155]

[0156]

[0157] in, are the hidden states of the 1st, 2nd, and 3rd layers respectively. and are the weight matrices of the first, second, and third layers, respectively, and b 1 、b 2 、b 3 are the biases of the first, second and third layers respectively, and σ is the activation function;

[0158] 4) Multi-head attention mechanism: A multi-head attention mechanism is introduced based on the output of multi-scale RNN. The expression of the multi-head attention mechanism is:

[0159]

[0160] Among them, v i and is the parameter of the ith attention head, is the attention weight of the ith attention head at time step t, is the weighted output of multi-head attention;

[0161] 5) Signal analysis and prediction: The signal is analyzed and small cracks and structural changes are predicted through the fully connected layer and activation function. The expression of signal analysis and prediction is:

[0162]

[0163] Among them, W o is the weight matrix of the output layer, b o is the bias of the output layer;

[0164]

[0165] Where σ is the activation function, is the prediction result.

[0166] Optionally, the method for monitoring and analyzing the safety of explosives and propellants adopted by the explosives and propellants safety assessment module includes:

[0167] 1) Stress sensor data acquisition: During the storage and transportation of explosives, stress data is collected in real time through stress sensors. The expression for stress data acquisition is:

[0168] σ(t,x,y,z)=σ sensor (t, x, y, z);

[0169] Where σ(t, x, y, z) represents the stress data at time t and position (x, y, z), σ sensor (t, x, y, z) is the stress value measured by the sensor;

[0170] 2) Stress data preprocessing: Filter and denoise the collected stress data. The expression for stress data preprocessing is:

[0171] σ filtered (t,x,y,z)=σ(t,x,y,z)*h filter (t);

[0172] Among them, σ filtered (t, x, y, z) is the filtered stress data, h filter (t) is the impulse response of the filter, * indicates the convolution operation;

[0173] 3) Stress distribution analysis: Using the pre-processed stress data, the stress distribution of explosives during storage and transportation is analyzed. The expression of stress distribution analysis is:

[0174] σ distribution (x, y, z) = f(σ filtered (t, x, y, z));

[0175] Among them, σ distribution (x, y, z) is the stress distribution at the spatial position (x, y, z), and f represents the spatial distribution function of the stress data;

[0176] 4) Finite element analysis: Based on the physical and mechanical properties of explosives, a finite element analysis model is established to simulate the behavior of explosives under different stress conditions;

[0177] 5) Structural integrity and safety status assessment: Combined with the results of finite element analysis, the structural integrity and safety status of explosives are assessed to identify potential safety hazards. The evaluation expression is:

[0178]

[0179] Among them, σ yield is the yield strength of explosive materials, max(σ distribution (x, y, z)) is the maximum stress value in the stress distribution, and Safety Index is an evaluation index of structural integrity and safety status.

[0180] Optionally, the analysis method adopted by the finite element analysis model includes:

[0181] 1) Discretization: Adaptive meshing technology is used to dynamically adjust the unit size according to the stress concentration area. The discretization expression is:

[0182]

[0183] where u(x, y, z) is the displacement at position (x, y, z), N i is the shape function of the ith node, u i is the displacement of the ith node;

[0184] 2) Unit stiffness matrix: Introducing the nonlinear characteristics of the material and the influence of temperature, considering the mechanical response of explosives in different environments, the expression of the unit stiffness matrix is ​​obtained as follows:

[0185]

[0186] Among them, K e is the element stiffness matrix, B is the strain-displacement matrix, D(T) is the material elasticity matrix considering the temperature effect, V e is the unit volume;

[0187] 3) Global stiffness matrix: Using sparse matrix technology, the stiffness matrices of all units are assembled into a global stiffness matrix to describe the mechanical behavior of the entire structure. The expression of the global stiffness matrix is:

[0188]

[0189] Where K is the global stiffness matrix and m is the number of elements;

[0190] 4) Real-time equation solving: Solve the global equilibrium equation in real time to obtain the displacement of the node, the expression is:

[0191] Ku=f(t);

[0192] Where u is the node displacement vector, f(t) is the node external force vector at time t;

[0193] 5) Stress and strain calculation: Introduce the dynamic stress concentration factor, consider the influence of microcracks on stress distribution, and calculate the stress and strain in each unit according to the node displacement. The expression is:

[0194] ε(t)=Bu(t);

[0195] σ(t)=D(T)ε(t)+K c ε(t);

[0196] Where ε(t) is the strain vector at time t, σ(t) is the stress vector at time t, and K cis the dynamic stress concentration factor matrix.

[0197] Optionally, the data processing method adopted by the data processing module includes:

[0198] 1) Preliminary data processing: Preliminary processing of the collected safety information and stress data, including cleaning, normalization and denoising;

[0199] 2) Feature extraction: Extract key features from the initially processed safety information and stress data, including stress peak, stress distribution, and temperature change. The expression for feature extraction is:

[0200] Stress max = max(σ(t, x, y, z));

[0201]

[0202] Where, σ(t, x, y, z) is the stress data at time t and position (x, y, z), Stress max and Stress mean are the peak stress and mean stress, respectively, and N is the number of data points;

[0203] 3) Risk assessment: The extracted key features are evaluated using logistic regression algorithm to predict the potential explosion risk of explosives. The risk assessment expression is:

[0204]

[0205] Among them, Risk is the probability of explosion risk, β0, β1, …, β n are the parameters of the logistic regression model, Temp is the temperature feature;

[0206] 4) Stress distribution analysis: Combined with the output of the finite element analysis model, analyze the stress distribution, identify stress concentration areas and potential risk points. The expression for stress distribution analysis is:

[0207] σ distribution (x, y, z) = Ku(t);

[0208] Among them, σ distribution (x, y, z) is the stress distribution at the spatial position (x, y, z), K is the global stiffness matrix, and u(t) is the nodal displacement vector at time t;

[0209] 5) Generate safety assessment report: Generate a safety assessment report based on the results of risk assessment and stress distribution analysis, including stress distribution diagram, risk prediction results and safety recommendations.

[0210] Optionally, the early warning and control module includes: a risk assessment result monitoring submodule, an early warning signal generating submodule and an emergency measure triggering submodule;

[0211] The risk assessment result monitoring submodule: monitors the risk assessment results generated by the data processing module in real time to determine whether there is a security risk, which is expressed as:

[0212] Risk threshold =α;

[0213] if Risk>Risk threshold then trigger warning;

[0214] Among them, Risk is the output explosion risk probability, Risk threshold is the preset risk threshold, α is the threshold constant;

[0215] Warning signal generation submodule: when the explosion risk probability is detected to exceed the preset risk threshold, a warning signal is generated and issued;

[0216] Emergency measures triggering submodule: Based on the early warning signal, manually trigger the corresponding emergency measures, including personnel evacuation, isolation of explosives and fire, and cooling.

[0217] Optionally, the emergency plan storage module includes: an emergency plan classification storage submodule, a safety assessment result mapping submodule and an emergency plan calling submodule;

[0218] Emergency plan classification storage submodule: According to the characteristics and potential risks of different types of explosives, the emergency plans are classified and stored in the database, and classification labels are established. The corresponding emergency plans are designed for each type of explosives, including explosives plans (fire isolation, explosion isolation, evacuation of rescue personnel, cooling measures), flammable and explosive gas plans (fire extinguishing, gas leakage treatment, ventilation measures, explosion isolation) and hazardous chemicals plans (leakage treatment, neutralization treatment, chemical protection, hazardous waste disposal);

[0219] Safety assessment result mapping submodule: Identify the type of explosives through safety assessment results and find the corresponding emergency plan;

[0220] Emergency plan calling submodule: extracts the emergency plan matching the current explosive type from the database and generates emergency response measures.

Claims

1. The explosives safety information management system is characterized by: It includes information collection module, explosive and fire state monitoring module, explosive and fire safety assessment module, data processing module, early warning and control module and emergency plan storage module; The information collection module is used to collect safety information of explosives during production, storage, transportation and use; The explosive state monitoring module is used to detect cracks and structural changes inside the explosive in real time and predict potential explosion risks; The explosive safety assessment module is used to monitor and analyze the stress distribution of explosives during storage and transportation, and to assess their structural integrity and safety status in combination with a finite element analysis model; The data processing module is used to comprehensively analyze the potential explosion risk and stress distribution of explosives and generate a safety assessment report; The warning and control module is used to send out warning signals when there is a safety risk, and manually trigger corresponding emergency measures according to the warning signals; The emergency plan storage module is used to store and call corresponding emergency plans according to the safety assessment results of different types of explosives.

2. The explosives safety information management system according to claim 1, characterized in that: The explosive state monitoring module includes: a high-frequency sound wave detection submodule, a signal processing submodule and a signal analysis submodule; The high-frequency sound wave detection submodule is used to transmit and receive high-frequency sound wave signals; Signal processing submodule: used to filter and amplify the received sound wave signal and extract the characteristic signal; Signal analysis submodule: Based on the extracted feature signals, a recursive neural network model is used to identify and predict internal changes and potential risks of explosives.

3. The explosives safety information management system according to claim 2, characterized in that: The detection method adopted by the high-frequency sound wave detection submodule is: A high-frequency sound wave transmitting device transmits a high-frequency sound wave signal into the interior of the explosive; a high-frequency sound wave receiving device receives the high-frequency sound wave signal reflected and scattered from the interior of the explosive; the received reflected and scattered sound wave signal is processed, and the minute cracks and structural changes inside the explosive are detected and identified by analyzing the time delay, frequency change and waveform change of the sound wave signal.

4. The explosives safety information management system according to claim 2, characterized in that: The processing method adopted by the signal processing submodule is: 1) Filtering: A bandpass filter is used to filter the received sound wave signal. The expression of the filtering process is: in, represents the Fourier transform, represents the inverse Fourier transform, x(t) is the received sound wave signal, H(f) is the frequency domain transfer function of the bandpass filter, y(t) is the filtered signal, f0 is the center frequency, and Δf is the bandwidth; 2) Amplification: The filtered sound wave signal is amplified using an automatic gain control circuit. The expression for the amplification process is: y(t)′=G(t)·y(t); Where y(t)′ is the amplified signal, G(t) is the gain control function, G0 is the initial gain, T is the time window length, and y(t) is the filtered signal; 3) Feature extraction: The expression of feature extraction is: Feature extraction: Fourier transform and wavelet transform are used to extract the frequency domain and time-frequency domain features of the amplified sound wave signal, and the features reflecting the micro cracks and structural changes inside the explosive are identified. The expression for feature extraction is: Among them, X(f) is the frequency domain signal, x(t) is the amplified time domain signal, f is the frequency, j is the imaginary unit, W(a, b) is the wavelet coefficient, ψ is the mother wavelet function, and a and b are the scale and translation parameters respectively.

5. The explosives safety information management system according to claim 2, characterized in that: The method for the recursive neural network model to identify and predict internal changes and potential risks of explosives is: 1) Signal preprocessing: perform mean normalization and bandpass filtering on the input signal; 2) Phase space reconstruction: The one-dimensional signal is reconstructed into a high-dimensional phase space using the delay embedding method. The dynamic characteristics of the signal are extracted through phase space reconstruction. The expression of phase space reconstruction is: X(t)=[x(t), x(t+τ), x(t+2τ),..., x(t+(m-1)τ)]; Where X(t) is a point in phase space, τ is the time delay, and m is the embedding dimension; 3) Construction of multi-scale recursive neural network: Construct a multi-layer recursive neural network, each layer processes signals of different time scales. The expression for constructing a multi-scale recursive neural network is: in, are the hidden states of the 1st, 2nd, and 3rd layers respectively. and are the weight matrices of the first, second, and third layers, respectively, and b 1 , b 2 , b 3 are the biases of the first, second and third layers respectively, and σ is the activation function; 4) Multi-head attention mechanism: A multi-head attention mechanism is introduced based on the output of the multi-scale recurrent neural network. The expression of the multi-head attention mechanism is: Among them, v i and is the parameter of the i-th attention head, is the attention weight of the ith attention head at time step t, is the weighted output of multi-head attention; 5) Signal analysis and prediction: The signal is analyzed and small cracks and structural changes are predicted through the fully connected layer and activation function. The expression of signal analysis and prediction is: Among them, W o is the weight matrix of the output layer, b o is the bias of the output layer; Where σ is the activation function, is the prediction result.

6. The explosives safety information management system according to claim 2, characterized in that: The method for monitoring and analyzing the safety of explosives and propellants used in the explosives and propellants safety assessment module includes: 1) Stress sensor data acquisition: During the storage and transportation of explosives, stress data is collected in real time through stress sensors. The expression for stress data acquisition is: σ(t,x,y,z)=σ sensor (t,x,y,z); Where σ(t, x, y, z) represents the stress data at time t and position (x, y, z), σ sensor (t, x, y, z) is the stress value measured by the sensor; 2) Stress data preprocessing: Filter and denoise the collected stress data. The expression for stress data preprocessing is: σ filtered (t,x,y,z)=σ(t,x,y,z)*hfilter(t): Among them, σ filtered (t, x, y, z) is the filtered stress data, h filter (t) is the impulse response of the filter, * indicates the convolution operation; 3) Stress distribution analysis: Using the pre-processed stress data, the stress distribution of explosives during storage and transportation is analyzed. The expression of stress distribution analysis is: σ distribution (x,y,z)=f(σ filtered (t,x,y,z)); Among them, σ distribution (x, y, z) is the stress distribution at the spatial position (x, y, z), and f represents the spatial distribution function of the stress data; 4) Finite element analysis: Based on the physical and mechanical properties of explosives, a finite element analysis model is established to simulate the behavior of explosives under different stress conditions; 5) Structural integrity and safety status assessment: Combined with the results of finite element analysis, the structural integrity and safety status of explosives are assessed to identify potential safety hazards. The evaluation expression is: Among them, σ yield is the yield strength of explosive materials, max(σ distribution (x, y, z)) is the maximum stress value in the stress distribution, and Safety Index is an evaluation index of structural integrity and safety status.

7. The explosives safety information management system according to claim 6, characterized in that: The analysis method adopted by the finite element analysis model includes: 1) Discretization: Adaptive meshing technology is used to dynamically adjust the unit size according to the stress concentration area. The discretization expression is: where u(x, y, z) is the displacement at position (x, y, z), N i is the shape function of the ith node, u i is the displacement of the ith node; 2) Unit stiffness matrix: Introducing the nonlinear characteristics of the material and the influence of temperature, considering the mechanical response of explosives in different environments, the expression of the unit stiffness matrix is ​​obtained as follows: Among them, K e is the element stiffness matrix, B is the strain-displacement matrix, D(T) is the material elasticity matrix considering the temperature effect, V e is the unit volume; 3) Global stiffness matrix: Using sparse matrix technology, the stiffness matrices of all units are assembled into a global stiffness matrix to describe the mechanical behavior of the entire structure. The expression of the global stiffness matrix is: Where K is the global stiffness matrix and m is the number of elements; 4) Real-time equation solving: Solve the global equilibrium equation in real time to obtain the displacement of the node, the expression is: Ku=f(t); Where u is the node displacement vector, f(t) is the node external force vector at time t; 5) Stress and strain calculation: Introduce the dynamic stress concentration factor, consider the influence of microcracks on stress distribution, and calculate the stress and strain in each unit according to the node displacement. The expression is: ε(t)=Bu(t); σ(t)=D(T) ε (t)+K c ε(t); Where ε(t) is the strain vector at time t, σ(t) is the stress vector at time t, and K c is the dynamic stress concentration factor matrix.

8. The explosives safety information management system according to claim 1, characterized in that: The data processing method adopted by the data processing module includes: 1) Preliminary data processing: Preliminary processing of the collected safety information and stress data, including cleaning, normalization and denoising; 2) Feature extraction: Extract key features from the initially processed safety information and stress data, including stress peak, stress distribution, and temperature change. The expression for feature extraction is: Stress max =max(σ(t,x,y,z)); Where, σ(t, x, y, z) is the stress data at time t and position (x, y, z), Stress max and Stress mean are the peak stress and mean stress, respectively, and N is the number of data points; 3) Risk assessment: The extracted key features are evaluated using logistic regression algorithm to predict the potential explosion risk of explosives. The risk assessment expression is: Among them, Risk is the probability of explosion risk, β0, β1, …, β n are the parameters of the logistic regression model, Temp is the temperature feature; 4) Stress distribution analysis: Combined with the output of the finite element analysis model, analyze the stress distribution, identify stress concentration areas and potential risk points. The expression for stress distribution analysis is: σ distribution (x,y,z)=Ku(t); Among them, σ distribution (x, y, z) is the stress distribution at the spatial position (x, y, z), K is the global stiffness matrix, and u(t) is the nodal displacement vector at time t; 5) Generate safety assessment report: Generate a safety assessment report based on the results of risk assessment and stress distribution analysis, including stress distribution diagram, risk prediction results and safety recommendations.

9. The explosives safety information management system according to claim 1, characterized in that: The early warning and control module includes: a risk assessment result monitoring submodule, an early warning signal generation submodule and an emergency measure triggering submodule; The risk assessment result monitoring submodule: monitors the risk assessment results generated by the data processing module in real time to determine whether there is a security risk, which is expressed as: Risk threshold =α; if Risk>Risk threshold then trigger warning; Among them, Risk is the output explosion risk probability, Risk threshold is the preset risk threshold, α is the threshold constant; Warning signal generation submodule: when the explosion risk probability is detected to exceed the preset risk threshold, a warning signal is generated and issued; Emergency measures triggering submodule: Based on the early warning signal, manually trigger the corresponding emergency measures, including personnel evacuation, isolation of explosives and fire, and cooling.

10. The explosives safety information management system according to claim 1, characterized in that: The emergency plan storage module includes: an emergency plan classification storage submodule, a safety assessment result mapping submodule and an emergency plan calling submodule; Emergency plan classification storage submodule: According to the characteristics and potential risks of different types of explosives, the emergency plans are classified and stored in the database, and classification labels are established to design corresponding emergency plans for each type of explosives; Safety assessment result mapping submodule: Identify the type of explosives through safety assessment results and find the corresponding emergency plan; Emergency plan calling submodule: extracts the emergency plan matching the current explosive type from the database and generates emergency response measures.

Images