A method and system for early warning, flame retardancy and explosion suppression in production workshops

Abstract

This invention provides a method and system for early warning, flame retardancy, and explosion suppression in production workshops, relating to the field of safety production technology. The method includes: collecting equipment parameters, material properties, and environmental parameters of the production workshop; preprocessing these parameters using Kalman filtering technology; constructing a geometric model of the workshop equipment based on this technology; dynamically calibrating the geometric model to obtain a dynamic geometric model of the workshop equipment; constructing a multidimensional physical field coupling model based on multidimensional model technology; simulating the risk evolution of the dynamic geometric model of the workshop equipment based on the multidimensional physical field coupling model and the preprocessed material properties and environmental parameters to obtain corresponding workshop risk factors, and then executing corresponding solutions; constructing an early warning model of the production workshop based on a neural convolutional network and the workshop risk factors, thereby generating a production workshop early warning score; and generating a graded response early warning based on the production workshop early warning score. This significantly improves the accuracy of early warnings.

Description

Technical Field

[0001] This invention relates to the field of safety production technology, specifically to a method and system for early warning, flame retardancy, and explosion suppression in production workshops. Background Technology

[0002] With the deepening development of industry and intelligent manufacturing, the automation and complexity of production workshops are constantly increasing, and safety risks such as fires and explosions are exhibiting characteristics of multi-parameter coupling and dynamic evolution. Traditional early warning systems rely on single-point sensor threshold alarms, which has shortcomings:

[0003] Data isolation and risk omission: lack of analysis of multi-sensor data; static model and poor adaptability: workshop equipment displacement and material characteristic changes are not dynamically calibrated, and fixed thresholds are difficult to cope with complex working conditions; single physical field analysis and insufficient linkage: lack of coupled simulation of flow field, thermal field and electromagnetic field, unable to simulate risk evolution path, and the linkage strategy of fire protection and process system is crude, with a high risk of accident expansion.

[0004] Against this backdrop, there is an urgent need for a new generation of early warning technology that integrates dynamic modeling, multi-physics coupling, and intelligent algorithms. Therefore, this paper presents an early warning, flame retardant, and explosion suppression method and system for production workshops. Summary of the Invention

[0005] In order to solve the above-mentioned technical problems, the purpose of this invention is to provide a method and system for early warning, flame retardant and explosion suppression in production workshops.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] A method for early warning, flame retardancy, and explosion suppression in a production workshop, the method comprising:

[0008] Collect equipment parameters, material properties, and environmental parameters from the production workshop, and preprocess these parameters using Kalman filtering technology.

[0009] based on The technology is used to construct a workshop equipment geometric model based on the preprocessed equipment parameters, and the workshop equipment geometric model is dynamically calibrated to obtain a dynamic workshop equipment geometric model.

[0010] Based on multidimensional modeling technology, a multidimensional physical field coupling model is constructed. According to the multidimensional physical field coupling model and the pre-processed material properties and environmental parameters, the dynamic workshop equipment geometric model is simulated to evolve risk, obtain the corresponding workshop risk factors, and then execute the corresponding solutions.

[0011] Based on neural convolutional networks and according to workshop risk factors, a production workshop early warning model is constructed, and then a production workshop early warning score is generated. Based on the production workshop early warning score, a graded response early warning is generated.

[0012] According to a preferred embodiment of the present invention, the process of collecting equipment parameters, material properties, and environmental parameters in a production workshop includes:

[0013] A preset data acquisition device is provided; the data acquisition device includes: an equipment parameter acquisition unit, a material property acquisition unit, and an environmental parameter acquisition unit; and a corresponding acquisition cycle is set, the acquisition cycle including several acquisition moments;

[0014] The equipment parameter acquisition unit is used to collect equipment parameters in the production workshop; the material attribute acquisition unit is used to collect material attributes in the production workshop; and the environmental parameter acquisition unit is used to collect environmental parameters in the production workshop.

[0015] According to a preferred embodiment of the present invention, the process of preprocessing equipment parameters, material properties, and environmental parameters includes:

[0016] Set the preprocessing state equation:

[0017] ;in, For the time of data collection The state vector; This is the state transition matrix; The input vector; The input matrix; Let be the process noise vector, and , Let be the covariance matrix of the process noise;

[0018] Set the preprocessing measurement equation:

[0019] ;in, For measurement vectors; For measurement matrix; Measure the noise vector, and , The covariance matrix of the measurement noise;

[0020] Based on Kalman filtering, the steps for predicting data are as follows:

[0021] ;in, This is the predicted state value; The prediction error covariance matrix;

[0022] The steps to update the data are as follows:

[0023] ;in, Kalman gain; This is the preprocessed data; To estimate the error covariance matrix;

[0024] Based on the prediction and update steps, the corresponding preprocessing equipment parameters, material properties, and environmental parameters are obtained.

[0025] According to one preferred embodiment of the present invention, the process of constructing a geometric model of workshop equipment includes:

[0026] Obtain the pre-processed equipment parameters, and based on the pre-processed equipment parameters, obtain a distribution map of the equipment in the production workshop;

[0027] The floor plan, elevation, and section drawings of the production workshop are imported into BIM modeling software to construct the geometric model of the workshop.

[0028] The distribution map of the equipment in the production workshop is imported into the workshop geometric model, and the workshop equipment geometric model is constructed based on the actual dimensions of the production workshop and the corresponding equipment.

[0029] According to a preferred embodiment of the present invention, the process of dynamically calibrating the geometric model of workshop equipment to obtain a dynamic geometric model of workshop equipment includes:

[0030] At the time of collection Obtain the device's location coordinates ; Compared with the previous data collection time Position coordinates Perform calculations to obtain the device offset distance. ;

[0031] Preset device offset distance threshold ;

[0032] If the device offset distance If so, dynamic calibration will not be performed;

[0033] If the device offset distance Then, the corresponding devices will be dynamically updated;

[0034] Device offset distance The position coordinates of the equipment at that time are mapped into the geometric model of the workshop equipment to generate a dynamic geometric model of the workshop equipment.

[0035] According to a preferred embodiment of the present invention, the process of constructing a multidimensional physical field coupling model based on multidimensional modeling technology includes:

[0036] The multidimensional modeling technology includes computational fluid dynamics algorithms, Fourier equations, and Maxwell equations; the multidimensional physical field coupling model includes: a dust diffusion model, a heat conduction model, and an electric spark generation model.

[0037] The process of constructing a dust diffusion model based on computational fluid dynamics algorithms includes:

[0038] An unstructured mesh is used to divide the production workshop into grids, and the mesh density is set according to the actual situation of the production workshop. Based on the actual dust concentration requirements of the production workshop, the Eulerian-Lagrange model, Eulerian-Eulerian model, or turbulence model is selected as the basic model. Dust diffusion boundary conditions are set, including: inlet boundary conditions, outlet boundary conditions, and wall boundary conditions.

[0039] A dust diffusion model is constructed based on the unstructured mesh, mesh density, basic model, inlet boundary conditions, outlet boundary conditions, and wall boundary conditions.

[0040] The process of constructing a heat conduction model based on the Fourier equation includes:

[0041] Select unstructured mesh as the mesh type to divide the production workshop and equipment into meshes, and set the mesh density according to the actual situation of the production workshop and equipment;

[0042] Set heat conduction boundary conditions, including: first type boundary conditions, second type boundary conditions and third type boundary conditions;

[0043] A heat conduction model is constructed based on the unstructured mesh, mesh density, first type boundary conditions, second type boundary conditions, and third type boundary conditions;

[0044] The process of constructing an electric spark generation model based on Maxwell's equations includes:

[0045] Select unstructured mesh as the mesh type to divide the production workshop and equipment into meshes, and set the mesh density according to the actual situation of the production workshop and equipment;

[0046] Set the boundary conditions for electric spark generation, including: electric field boundary conditions and magnetic field boundary conditions;

[0047] An electric spark generation model is constructed based on the unstructured mesh, mesh density, electric field boundary conditions, and magnetic field boundary conditions.

[0048] According to a preferred embodiment of the present invention, the process of simulating the risk evolution of a dynamic workshop equipment geometric model to obtain corresponding workshop risk factors, and then executing the corresponding solution includes:

[0049] The pre-treated material properties and environmental parameters are used as the initial state conditions of the physical field, and the dust diffusion model, heat conduction model, and electric spark generation model are used as the boundary conditions.

[0050] The initial state conditions and boundary conditions are imported into the dynamic workshop equipment geometric model, and risk index thresholds are set, including: high concentration dust risk index threshold, equipment thermal anomaly risk index threshold and electric spark risk index threshold.

[0051] Based on different boundary conditions, corresponding risk indicators are output, including: high-concentration dust risk indicators, equipment thermal anomaly risk indicators, and electrical spark risk indicators.

[0052] If the high-concentration dust risk index is less than or equal to the high-concentration dust risk index threshold, the probability of dust explosion in the production workshop is lower. If the high-concentration dust risk index is greater than the high-concentration dust risk index threshold, the probability of dust explosion in the production workshop is higher. The simulation outputs the corresponding workshop risk factor and reminds relevant personnel to take corresponding solutions. The records are also uploaded to the background for storage via wireless transmission technology.

[0053] If the equipment thermal anomaly risk index is less than or equal to the equipment thermal anomaly risk index threshold, the probability of the equipment in the production workshop generating thermal anomaly risk is lower. If the equipment thermal anomaly risk index is greater than the equipment thermal anomaly risk index threshold, the probability of the equipment in the production workshop generating thermal anomaly risk is higher. The simulation outputs the corresponding workshop risk factor and reminds relevant personnel to take corresponding solutions. The records are also uploaded to the backend for storage via wireless transmission technology.

[0054] If the electrical spark risk index is less than or equal to the electrical spark risk index threshold, the probability of electrical sparks occurring in the production workshop's wiring is lower. If the electrical spark risk index is greater than the electrical spark risk index threshold, the probability of electrical sparks occurring in the production workshop's wiring is higher. The simulation outputs the corresponding workshop risk factor and reminds relevant personnel to take corresponding solutions. The records are also uploaded to the backend for storage via wireless transmission technology.

[0055] According to a preferred embodiment of the present invention, a production workshop early warning model is constructed, and a production workshop early warning score is generated. The process of generating a graded response early warning based on the production workshop early warning score includes:

[0056] Obtain several groups of historical workshop risk factors; group and label these groups of historical workshop risk factors, denoted as [group name missing]. For natural numbers; The historical workshop risk factors were used as sample data, and Less than The natural numbers are used to obtain the mean of the sample data, which is denoted as the sample set; the remaining groups of historical workshop risk factors are used as the test set; and a training sample set is formed based on the sample set and the test set.

[0057] A standard risk warning model is constructed based on convolutional neural networks;

[0058] The training sample set is then input into the standard risk warning model to train it. The trained standard risk warning model is then recorded as the production workshop warning model.

[0059] Based on the aforementioned production workshop early warning model, a production workshop early warning score is generated under the current environmental factors. The production workshop early warning score for:

[0060] ;in, For the convolutional network neuron in the output feature map of the convolutional layer, the first... The weights corresponding to each convolutional kernel; The workshop risk factors at the corresponding data collection time; It is the first The bias value corresponding to each convolution kernel;

[0061] Preset production workshop early warning threshold range ;

[0062] If the production workshop early warning score If the production workshop is in a safe operating state, then there is no risk, and the corresponding data is recorded in real time; if the production workshop receives an early warning score... If the production workshop is at risk of an accident, it is classified as a medium-level warning, triggering local alarms and remote notifications, and reminding relevant maintenance personnel to perform corresponding maintenance on the equipment; if the production workshop warning score is low... If an accident risk is detected in the production workshop, it will be identified as a high-level alarm, triggering a full alarm, issuing a siren warning, saving on-site video, promptly cutting off power to the equipment, and reminding maintenance personnel to take appropriate emergency measures.

[0063] This invention further provides an early warning flame retardant and explosion suppression system for a production workshop, implementing the aforementioned method for early warning flame retardant and explosion suppression in a production workshop, comprising:

[0064] The data acquisition module is used to collect equipment parameters, material properties, and environmental parameters in the production workshop;

[0065] The data preprocessing module, based on Kalman filtering technology, preprocesses equipment parameters, material properties, and environmental parameters.

[0066] Workshop geometry model building module, based on The technology is used to construct a workshop equipment geometric model based on the preprocessed equipment parameters, and the workshop equipment geometric model is dynamically calibrated to obtain a dynamic workshop equipment geometric model.

[0067] The simulation analysis engine module, based on multidimensional model technology, constructs a multidimensional physical field coupling model. Based on the multidimensional physical field coupling model and the preprocessed material properties and environmental parameters, it simulates the risk evolution of the dynamic workshop equipment geometric model, obtains the corresponding workshop risk factors, and executes the corresponding solutions.

[0068] The intelligent early warning module is based on a neural convolutional network and constructs a production workshop early warning model according to workshop risk factors, thereby generating a production workshop early warning score, and generating a graded response early warning based on the production workshop early warning score.

[0069] The present invention further provides a computer-readable storage medium storing a computer program that can be executed by a processor to implement the above-described method for early warning, flame retardancy, and explosion suppression in a production workshop.

[0070] Compared with the prior art, the beneficial effects of the present invention are:

[0071] 1. Kalman filtering technology is used to preprocess equipment parameters, material properties, and environmental parameters, effectively filtering noise and repairing abnormal data to ensure the reliability of input data. Combined with dynamically calibrated workshop equipment geometric models and multi-dimensional physical field coupling models, complex physical processes such as dust diffusion, heat conduction, and electrical spark generation can be simulated in real time, accurately capturing hidden risks caused by multi-parameter coupling.

[0072] 2. The early warning model, built upon convolutional neural networks, can automatically learn feature correlations in historical risk data, generate dynamic early warning scores, and support tiered responses. Through a closed loop of "data acquisition - simulation analysis - strategy execution - effect feedback," it self-optimizes early warning thresholds and control strategies based on actual working conditions, significantly reducing false alarm rates and substantially improving the safety level of the production workshop. Attached Figure Description

[0073] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0074] Figure 1 This is a schematic diagram illustrating the steps of a pre-warning, flame-retardant, and explosion-suppressing method for production workshops.

[0075] Figure 2 This is a flow chart of a method and system for early warning, flame retardant and explosion suppression in a production workshop.

[0076] Figure 3 This is a schematic diagram of a module for an early warning, flame retardant, and explosion suppression system in a production workshop. Detailed Implementation

[0077] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be described in detail below. Obviously, the described embodiments are merely some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other implementation methods obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0078] like Figure 1 As shown, a method for early warning, flame retardancy, and explosion suppression in a production workshop includes the following steps:

[0079] Collect equipment parameters, material properties, and environmental parameters from the production workshop, and preprocess these parameters using Kalman filtering technology.

[0080] based on The technology is used to construct a workshop equipment geometric model based on the preprocessed equipment parameters, and the workshop equipment geometric model is dynamically calibrated to obtain a dynamic workshop equipment geometric model.

[0081] Based on multidimensional modeling technology, a multidimensional physical field coupling model is constructed. According to the multidimensional physical field coupling model and the pre-processed material properties and environmental parameters, the dynamic workshop equipment geometric model is simulated to evolve risk, obtain the corresponding workshop risk factors, and then execute the corresponding solutions.

[0082] Based on neural convolutional networks and according to workshop risk factors, a production workshop early warning model is constructed, and then a production workshop early warning score is generated. Based on the production workshop early warning score, a graded response early warning is generated.

[0083] It should be further explained that, in the specific implementation process, the process of collecting equipment parameters, material properties, and environmental parameters in the production workshop includes:

[0084] A preset data acquisition device is provided; the data acquisition device includes: an equipment parameter acquisition unit, a material property acquisition unit, and an environmental parameter acquisition unit; and a corresponding acquisition cycle is set, the acquisition cycle including several acquisition moments;

[0085] The equipment parameter acquisition unit is used to collect equipment parameters in the production workshop; the material attribute acquisition unit is used to collect material attributes in the production workshop; the environmental parameter acquisition unit is used to collect environmental parameters in the production workshop.

[0086] It should be further explained that the equipment parameters include the equipment's operating parameters, such as temperature, pressure, speed, current, and voltage, as well as the equipment's location information, such as the equipment's coordinates within the production workshop; the material properties include the physical properties of the materials within the production workshop, such as density, specific heat capacity, and thermal conductivity, as well as the chemical properties of the materials, such as chemical composition and reactivity; and the environmental parameters include the temperature, humidity, air pressure, light intensity, and noise level within the production workshop.

[0087] For example, in a production workshop, position sensors are installed on each piece of equipment that needs to be monitored. These sensors include GPS positioning modules (suitable for workshops with larger spaces and where extremely high accuracy is not required), beacon and receiver combinations based on Bluetooth positioning technology (suitable for indoor positioning with relatively high accuracy), and UWB (ultra-wideband) positioning systems (high positioning accuracy, down to the centimeter level, suitable for positioning equipment in workshops with high accuracy requirements). These sensors collect the position coordinates of the equipment in real time.

[0088] It should be further explained that, in the specific implementation process, the preprocessing of equipment parameters, material properties, and environmental parameters based on Kalman filtering technology includes:

[0089] Set the preprocessing state equation:

[0090] ;in, For the time of data collection The state vector; This is the state transition matrix; The input vector; The input matrix; Let be the process noise vector, and , Let be the covariance matrix of the process noise.

[0091] Set the preprocessing measurement equation:

[0092] ;in, For measurement vectors; For measurement matrix; Measure the noise vector, and , This is the covariance matrix of the measurement noise.

[0093] Based on Kalman filtering, the steps for predicting data are as follows:

[0094] ;in, This is the predicted state value; This is the prediction error covariance matrix.

[0095] The steps to update the data are as follows:

[0096] ;in, Kalman gain; This is the preprocessed data; To estimate the error covariance matrix;

[0097] Based on the prediction and update steps, the corresponding preprocessed equipment parameters, material properties, and environmental parameters are obtained, thereby reducing the impact of noise on subsequent analysis.

[0098] For example, putting the device at a certain time The temperature is recorded as If the temperature of the device changes slowly in adjacent time intervals, then the state transition matrix... Measurement matrix Input vector ; Process noise refers to the change in equipment temperature between adjacent time points due to some unpredictable factors (such as small thermal fluctuations inside the equipment). ,in, This indicates that the variance of the process noise is set based on experience or a preliminary understanding of the equipment.

[0099] Therefore, the pretreatment state equation for the corresponding temperature of the equipment is: ;

[0100] Pretreatment measurement equation for the corresponding temperature of the equipment: ;in, For the time of data collection The measured temperature The noise in temperature measurement reflects the measurement error of the corresponding sensor; Based on the sensor's accuracy specifications, set , which represents the variance of the measurement noise.

[0101] Based on the normal operating temperature range of the equipment, the estimated temperature of the equipment at the initial moment is assumed to be... The initial estimation error covariance matrix is ​​set according to the degree of confidence in the initial estimate. It should be further explained that the covariance matrix The magnitude of the value represents the uncertainty of the initial estimate; the larger the value, the higher the uncertainty.

[0102] Let the temperature at time 1 correspond to the temperature collected by the sensor. ;

[0103] The steps for predicting temperature based on Kalman filtering are as follows:

[0104] ;

[0105] The steps to update the temperature are as follows:

[0106] ;

[0107] Let the temperature at the second moment correspond to the temperature collected by the sensor. ;

[0108] The steps for predicting temperature based on Kalman filtering are as follows:

[0109] ;

[0110] The steps to update the temperature are as follows:

[0111] .

[0112] It needs to be further explained that, in the specific implementation process, based on The specific process of constructing a geometric model of the workshop equipment based on the preprocessed equipment parameters includes:

[0113] Obtain the pre-processed equipment parameters, and based on the pre-processed equipment parameters, obtain a distribution map of the equipment in the production workshop;

[0114] The floor plan, elevation, and section drawings of the production workshop are imported into BIM modeling software to construct the geometric model of the workshop.

[0115] The distribution map of the equipment in the production workshop is imported into the workshop geometric model, and the workshop equipment geometric model is constructed based on the actual dimensions of the production workshop and the corresponding equipment.

[0116] It should be further explained that, in the specific implementation process, the dynamic calibration of the workshop equipment geometric model to obtain the dynamic workshop equipment geometric model includes the following steps:

[0117] At the time of collection Obtain the device's location coordinates ; Compared with the previous data collection time Position coordinates Perform calculations to obtain the device offset distance. ;

[0118] Preset device offset distance threshold ;

[0119] If the device offset distance If so, dynamic calibration will not be performed;

[0120] If the device offset distance This allows for dynamic updates to the corresponding equipment, reducing accidents caused by equipment misalignment.

[0121] Device offset distance The position coordinates of the equipment at that time are mapped into the geometric model of the workshop equipment to generate a dynamic geometric model of the workshop equipment.

[0122] It should be further explained that, in the specific implementation process, the construction of a multidimensional physical field coupling model based on multidimensional model technology includes:

[0123] It should be further noted that the multidimensional modeling technology includes computational fluid dynamics algorithms, Fourier equations, and Maxwell equations; the multidimensional physical field coupling model includes: a dust diffusion model, a heat conduction model, and an electric spark generation model;

[0124] The specific process of constructing a dust diffusion model based on computational fluid dynamics algorithms includes:

[0125] Unstructured grids are used to divide the production workshop into grids, and the grid density is set according to the actual situation of the production workshop.

[0126] For example, in areas near dust sources and around ventilation openings, the mesh density is increased to improve computational accuracy; in areas with relatively gentle changes, the mesh density is appropriately reduced to decrease computational load.

[0127] Based on the actual dust concentration requirements of the production workshop, a turbulence model is selected as the basic model. It should be further noted that the basic model is not limited to the turbulence model, and the Euler-Lagrange model and the Euler-Euler model can be selected according to the actual situation.

[0128] It should be further noted that the Euler-Lagrange model is suitable for situations with low dust concentration, the Euler-Euler model is suitable for situations with high dust concentration and strong interaction between particles, and the turbulence model is used for scenarios with high accuracy requirements.

[0129] Set dust diffusion boundary conditions, including: inlet boundary conditions, outlet boundary conditions, and wall boundary conditions;

[0130] The inlet boundary conditions are used to further limit the parameters at inlets such as ventilation openings and dust sources, including:

[0131] 1. Inlet flow velocity boundary conditions, fluid velocity ;in, This refers to the rated air volume of the fan. This represents the cross-sectional area of ​​the ventilation duct; for adjustable ventilation systems, consider speed variations under different operating conditions.

[0132] 2. Temperature boundary conditions: When ventilation air passes through heating or cooling equipment, the outlet temperature is determined based on the equipment's operating parameters; if the ventilation air comes from the external environment, the temperature can be obtained based on local meteorological data or real-time monitoring.

[0133] 3. Dust concentration boundary conditions: Based on the production process and equipment operating parameters, estimate the generation rate and spatial distribution of dust sources to determine the dust concentration; for intermittent dust generation processes, it is necessary to consider the changes in dust concentration at different time periods.

[0134] The export boundary conditions include:

[0135] 1. Pressure boundary conditions: For outlets open to the atmosphere, the pressure is usually set to the local atmospheric pressure; if the outlet is connected to other equipment or piping systems, the outlet pressure needs to be matched with the pressure of the connected system.

[0136] 2. Outlet velocity boundary condition: When pressure is used as the outlet boundary condition, the velocity is obtained by solving the flow field. When setting the outlet boundary condition, it is generally not necessary to directly specify the velocity. It is necessary to ensure the rationality of the pressure value so that the calculated velocity matches the actual situation.

[0137] The wall boundary conditions include:

[0138] 1. No-slip boundary condition, meaning that for solid surfaces such as workshop walls and equipment surfaces, the fluid velocity at the wall surface is zero;

[0139] 2. Adsorption boundary conditions: Different wall materials (such as metal, plastic, concrete, etc.) have different adsorption capacities for dust. The adsorption coefficient of the wall material should be obtained according to the actual situation.

[0140] 3. Deposition boundary conditions: A deposition model is used to calculate the deposition rate of dust on the wall surface. Based on parameters such as dust particle size distribution, flow velocity, and wall characteristics, the deposition rate of dust particles of different sizes is calculated, thereby obtaining the change of dust deposition on the wall surface over time.

[0141] 4. Resuspension boundary conditions: When the dust deposited on the wall is disturbed by the airflow or other external forces, it may be resuspended and re-enter the airflow. The resuspension of dust is determined based on the shear force of the airflow and the adhesion force between the dust and the wall, and the amount of resuspended dust is calculated.

[0142] A dust diffusion model is constructed based on the unstructured mesh, mesh density, basic model, and dust diffusion boundary conditions.

[0143] The specific process of constructing a heat conduction model based on the Fourier equation includes:

[0144] Select unstructured mesh as the mesh type to divide the production workshop and equipment into meshes, and set the mesh density according to the actual situation of the production workshop and equipment;

[0145] It should be further noted that for areas with drastic temperature changes, such as near heat sources or heat dissipation surfaces, the mesh density should be increased; for areas with gradual temperature changes, the mesh density should be appropriately reduced.

[0146] Set heat conduction boundary conditions, including:

[0147] 1. First type of boundary condition: Given the temperature value on the boundary. For example, if the temperature of the part of the equipment surface in contact with the coolant is known to be constant, then that part of the boundary can be set as a first-type boundary condition.

[0148] 2. Second type of boundary condition: given heat flux density on the boundary ,in It refers to the normal direction of the boundary. For example, when a device exchanges heat with its surroundings, if the heat dissipation power of the device's surface is known, this part of the boundary can be set as a second-type boundary condition.

[0149] 3. Third type of boundary condition: Given the convective heat transfer coefficient on the boundary. and the temperature of the surrounding fluid The boundary conditions are: For example, when considering heat conduction in pipes within a production workshop, the third type of boundary condition can be used to account for convective heat transfer between the pipes and the surrounding air.

[0150] A heat conduction model is constructed based on the unstructured mesh, mesh density, and heat conduction boundary conditions.

[0151] The specific process of constructing an electric spark generation model based on Maxwell's equations includes:

[0152] Select unstructured mesh as the mesh type to divide the production workshop and equipment into meshes, and set the mesh density according to the actual situation of the production workshop and equipment;

[0153] It should be further noted that, due to the drastic changes in the electromagnetic field during the generation of the electric spark, it is necessary to refine the mesh in key areas such as near the electrodes and in the plasma region to accurately capture these changes. Appropriate mesh types should be selected, such as tetrahedral meshes or hexahedral meshes.

[0154] Set boundary conditions for electric spark generation, including:

[0155] 1. Electric field boundary conditions: The electric potential at the surface of the conductor is constant. The normal electric field strength on the insulating surface is zero, that is... ;

[0156] 2. Magnetic field boundary conditions: continuity of magnetic flux at the boundary The magnetic field at infinity is zero. .

[0157] Based on the finite-difference time-domain method, the time-domain form of Maxwell's equations is as follows:

[0158] ; ; ;in, It is the electric field strength. It is the magnetic field strength. It is an electric displacement vector. It is the magnetic flux density. It is the current density. It is charge density;

[0159] Obtaining electric and magnetic fields The update formula for direction is:

[0160] ;in, Indicates the index of a spatial grid node; It represents the dielectric constant of the medium at that location in space; , They represent Spatial step size in the direction; Indicates the index of the time step; Indicates the time step; , They represent the first The time step and the first At each time step, the spatial location ( The electric field intensity component at that location; , , Indicates a specific time step and spatial location ( The magnetic field strength component at that location.

[0161] Similarly, the electric and magnetic fields can be obtained in The update formula in the direction and the acquisition of electric and magnetic fields in The formula for updating in direction.

[0162] An electric spark generation model is constructed based on the unstructured mesh, mesh density, electric spark generation boundary conditions, and update formula.

[0163] It should be further explained that, in the specific implementation process, the process of simulating the risk evolution of the dynamic workshop equipment geometric model based on the multidimensional physical field coupling model, pre-processed material properties, and environmental parameters to obtain the corresponding workshop risk factors, and then executing the corresponding solution, includes:

[0164] Obtain dust diffusion models, heat conduction models, electric spark generation models, as well as pre-treated material properties and environmental parameters;

[0165] The pre-processed material properties and environmental parameters are used as the initial state conditions of the physical field, and the dust diffusion model, heat conduction model, and electric spark generation model are used as boundary conditions.

[0166] The initial state conditions and boundary conditions are imported into the dynamic workshop equipment geometric model, and risk index thresholds are set, including: high concentration dust risk index threshold, equipment thermal anomaly risk index threshold and electric spark risk index threshold.

[0167] Based on different boundary conditions, corresponding risk indicators are output, including: high-concentration dust risk indicators, equipment thermal anomaly risk indicators, and electrical spark risk indicators.

[0168] If the high-concentration dust risk index is less than or equal to the high-concentration dust risk index threshold, the probability of a dust explosion in the production workshop is lower. If the high-concentration dust risk index is greater than the high-concentration dust risk index threshold, the probability of a dust explosion in the production workshop is higher. The simulation outputs the corresponding workshop risk factor and reminds relevant personnel to take corresponding solutions, such as turning on the exhaust fan for ventilation. The records are also uploaded to the backend for storage via wireless transmission technology.

[0169] If the equipment thermal anomaly risk index is less than or equal to the equipment thermal anomaly risk index threshold, the probability of the equipment in the production workshop generating thermal anomalies is lower. If the equipment thermal anomaly risk index is greater than the equipment thermal anomaly risk index threshold, the probability of the equipment in the production workshop generating thermal anomalies is higher. The simulation outputs the corresponding workshop risk factor and reminds relevant personnel to take corresponding solutions, such as checking whether the equipment is overloaded. The records are also uploaded to the backend for storage via wireless transmission technology.

[0170] If the electrical spark risk index is less than or equal to the electrical spark risk index threshold, the probability of electrical sparks occurring in the production workshop's wiring is lower. If the electrical spark risk index is greater than the electrical spark risk index threshold, the probability of electrical sparks occurring in the production workshop's wiring is higher. The simulation outputs the corresponding workshop risk factor and reminds relevant personnel to take corresponding solutions, such as checking whether the equipment's wiring is damaged. The records are then uploaded to the backend for storage via wireless transmission technology.

[0171] It should be further explained that, in the specific implementation process, a production workshop early warning model is constructed based on neural convolutional networks and according to workshop risk factors, thereby generating a production workshop early warning score. The specific process of generating a graded response early warning based on the production workshop early warning score includes:

[0172] Obtain several sets of historical workshop risk factors;

[0173] Several groups of historical workshop risk factors are grouped and labeled, denoted as follows: It is a natural number;

[0174] Will The historical workshop risk factors were used as sample data, and Less than The natural numbers are used to obtain the mean of the sample data, which is denoted as the sample set; the remaining groups of historical workshop risk factors are used as the test set.

[0175] A training sample set is formed based on the aforementioned sample set and test set;

[0176] A standard risk warning model is constructed based on convolutional neural networks;

[0177] The training sample set is then input into the standard risk warning model to train it. The trained standard risk warning model is then recorded as the production workshop warning model.

[0178] It should be further explained that, in the specific implementation process, the process of generating a graded response early warning based on the production workshop early warning score includes:

[0179] Based on the aforementioned production workshop early warning model, a production workshop early warning score is generated under the current environmental factors. The production workshop early warning score for:

[0180] ;in, For the convolutional network neuron in the output feature map of the convolutional layer, the first... The weights corresponding to each convolutional kernel; The workshop risk factors at the corresponding data collection time; It is the first The bias value corresponding to each convolution kernel.

[0181] Preset production workshop early warning threshold range ;

[0182] If the production workshop early warning score If the production workshop is deemed safe to operate, then there is no risk; the corresponding data is recorded in real time.

[0183] If the production workshop early warning score If an accident risk is detected in the production workshop, it is identified as a medium-level warning, triggering local alarms and remote notifications, and reminding relevant maintenance personnel to perform corresponding maintenance on the equipment;

[0184] If the production workshop early warning score If an accident risk is detected in the production workshop, it will be identified as a high-level alarm, triggering a full alarm, issuing a siren warning, saving on-site video, promptly cutting off power to the equipment, and reminding maintenance personnel to take appropriate emergency measures.

[0185] like Figure 3 As shown, a fire-retardant and explosion-suppressing early warning system for a production workshop includes: a data acquisition module, a data preprocessing module, a workshop geometric model construction module, a simulation analysis engine module, and an intelligent early warning module.

[0186] The data acquisition module is used to collect equipment parameters, material properties, and environmental parameters in the production workshop;

[0187] The data preprocessing module, based on Kalman filtering technology, preprocesses equipment parameters, material properties, and environmental parameters.

[0188] Workshop geometry model building module, based on The technology is used to construct a workshop equipment geometric model based on the preprocessed equipment parameters, and the workshop equipment geometric model is dynamically calibrated to obtain a dynamic workshop equipment geometric model.

[0189] The simulation analysis engine module, based on multidimensional model technology, constructs a multidimensional physical field coupling model. Based on the multidimensional physical field coupling model and the preprocessed material properties and environmental parameters, it simulates the risk evolution of the dynamic workshop equipment geometric model, obtains the corresponding workshop risk factors, and executes the corresponding solutions.

[0190] The intelligent early warning module is based on a neural convolutional network and constructs a production workshop early warning model according to workshop risk factors, thereby generating a production workshop early warning score, and generating a graded response early warning based on the production workshop early warning score.

[0191] The above embodiments are only used to illustrate the technical methods of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of the present invention without departing from the spirit and scope of the technical methods of the present invention.

Claims

1. A method for early warning, flame retardancy, and explosion suppression in a production workshop, characterized in that, The method includes: Collect equipment parameters, material properties, and environmental parameters from the production workshop, and preprocess these parameters using Kalman filtering technology. based on The technology is used to construct a workshop equipment geometric model based on the preprocessed equipment parameters, and the workshop equipment geometric model is dynamically calibrated to obtain a dynamic workshop equipment geometric model. The process of constructing a dust diffusion model based on computational fluid dynamics algorithms includes: using an unstructured mesh to divide the production workshop into meshes and setting the mesh density according to the actual conditions of the production workshop; selecting a turbulence model as the basic model based on the actual dust concentration requirements of the production workshop; setting dust diffusion boundary conditions; and constructing a dust diffusion model based on the unstructured mesh, mesh density, basic model, and dust diffusion boundary conditions. The process of constructing a heat conduction model based on the Fourier equation includes: selecting an unstructured mesh as the mesh type to divide the production workshop and equipment into meshes, and setting the mesh density according to the actual situation of the production workshop and equipment; setting heat conduction boundary conditions; and constructing a heat conduction model based on the unstructured mesh, mesh density, and heat conduction boundary conditions. Based on Maxwell's equations, the process of constructing an electrical discharge model includes: selecting an unstructured mesh as the mesh type to divide the production workshop and equipment into meshes, and setting the mesh density according to the actual situation of the production workshop and equipment; setting electrical discharge generation boundary conditions; and constructing an electrical discharge model based on the unstructured mesh, mesh density, and electrical discharge generation boundary conditions. Based on the dust diffusion model, heat conduction model and electric spark generation model, the dynamic workshop equipment geometric model is simulated to evolve the risk, obtain the corresponding workshop risk factors, and then execute the corresponding solutions. Based on neural convolutional networks and according to workshop risk factors, a production workshop early warning model is constructed, and then a production workshop early warning score is generated. Based on the production workshop early warning score, a graded response early warning is generated.

2. The method for early warning, flame retardancy, and explosion suppression in a production workshop according to claim 1, characterized in that, The process of collecting equipment parameters, material properties, and environmental parameters in the production workshop includes: A preset data acquisition device is provided; the data acquisition device includes: an equipment parameter acquisition unit, a material property acquisition unit, and an environmental parameter acquisition unit; and a corresponding acquisition cycle is set, the acquisition cycle including several acquisition moments; The equipment parameter acquisition unit is used to collect equipment parameters in the production workshop; the material attribute acquisition unit is used to collect material attributes in the production workshop; and the environmental parameter acquisition unit is used to collect environmental parameters in the production workshop.

3. The method for early warning, flame retardancy, and explosion suppression in a production workshop according to claim 2, characterized in that, The process of preprocessing equipment parameters, material properties, and environmental parameters includes: Set the preprocessing state equation: ;in, For the time of data collection The state vector; This is the state transition matrix; The input vector; The input matrix; Let be the process noise vector, and , Let be the covariance matrix of the process noise; Set the preprocessing measurement equation: ;in, For measurement vectors; For measurement matrix; Measure the noise vector, and , The covariance matrix of the measurement noise; Based on Kalman filtering, the steps for predicting data are as follows: ;in, This is the predicted state value; The prediction error covariance matrix; The steps to update the data are as follows: ;in, Kalman gain; This is the preprocessed data; To estimate the error covariance matrix; Based on the prediction and update steps, the corresponding preprocessing equipment parameters, material properties, and environmental parameters are obtained.

4. The method for early warning, flame retardancy, and explosion suppression in a production workshop according to claim 3, characterized in that, The process of constructing the geometric model of workshop equipment includes: Obtain the pre-processed equipment parameters, and based on the pre-processed equipment parameters, obtain a distribution map of the equipment in the production workshop; The floor plan, elevation, and section drawings of the production workshop are imported into BIM modeling software to construct the geometric model of the workshop. The distribution map of the equipment in the production workshop is imported into the workshop geometric model, and the workshop equipment geometric model is constructed based on the actual dimensions of the production workshop and the corresponding equipment.

5. A method for early warning, flame retardancy, and explosion suppression in a production workshop according to claim 4, characterized in that, The process of dynamically calibrating the geometric model of workshop equipment to obtain a dynamic geometric model of workshop equipment includes: At the time of collection Obtain the device's location coordinates ; Compared with the previous data collection time Position coordinates Perform calculations to obtain the device offset distance. ; Preset device offset distance threshold ; If the device offset distance If so, dynamic calibration will not be performed; If the device offset distance Then, the corresponding devices will be dynamically updated; Device offset distance The position coordinates of the equipment at that time are mapped into the geometric model of the workshop equipment to generate a dynamic geometric model of the workshop equipment.

6. The method for early warning, flame retardancy, and explosion suppression in a production workshop according to claim 5, characterized in that, The process of constructing a multidimensional physical field coupling model based on multidimensional modeling technology includes: The multidimensional modeling technology includes computational fluid dynamics algorithms, Fourier equations, and Maxwell equations; the multidimensional physical field coupling model includes: a dust diffusion model, a heat conduction model, and an electric spark generation model. The process of constructing a dust diffusion model based on computational fluid dynamics algorithms includes: An unstructured mesh was used to divide the production workshop into grids, and the mesh density was set according to the actual situation of the production workshop. Based on the dust concentration requirements of the actual production workshop, a turbulence model was selected as the basic model. Dust diffusion boundary conditions were set, including: inlet boundary conditions, outlet boundary conditions, and wall boundary conditions. A dust diffusion model is constructed based on the unstructured mesh, mesh density, basic model, inlet boundary conditions, outlet boundary conditions, and wall boundary conditions. The process of constructing a heat conduction model based on the Fourier equation includes: Select unstructured mesh as the mesh type to divide the production workshop and equipment into meshes, and set the mesh density according to the actual situation of the production workshop and equipment; Set heat conduction boundary conditions, including: first type boundary conditions, second type boundary conditions and third type boundary conditions; A heat conduction model is constructed based on the unstructured mesh, mesh density, first type boundary conditions, second type boundary conditions, and third type boundary conditions; The process of constructing an electric spark generation model based on Maxwell's equations includes: Select unstructured mesh as the mesh type to divide the production workshop and equipment into meshes, and set the mesh density according to the actual situation of the production workshop and equipment; Set the boundary conditions for electric spark generation, including: electric field boundary conditions and magnetic field boundary conditions; An electric spark generation model is constructed based on the unstructured mesh, mesh density, electric field boundary conditions, and magnetic field boundary conditions.

7. A method for early warning, flame retardancy, and explosion suppression in a production workshop according to claim 6, characterized in that, The process of simulating the risk evolution of a dynamic workshop equipment geometric model, obtaining corresponding workshop risk factors, and then implementing corresponding solutions includes: The pre-treated material properties and environmental parameters are used as the initial state conditions of the physical field, and the dust diffusion model, heat conduction model, and electric spark generation model are used as the boundary conditions. The initial state conditions and boundary conditions are imported into the dynamic workshop equipment geometric model, and risk index thresholds are set, including: high concentration dust risk index threshold, equipment thermal anomaly risk index threshold and electric spark risk index threshold. Based on different boundary conditions, corresponding risk indicators are output, including: high-concentration dust risk indicators, equipment thermal anomaly risk indicators, and electrical spark risk indicators. If the high-concentration dust risk index is less than or equal to the high-concentration dust risk index threshold, the probability of dust explosion in the production workshop is lower. If the high-concentration dust risk index is greater than the high-concentration dust risk index threshold, the probability of dust explosion in the production workshop is higher. The simulation outputs the corresponding workshop risk factor and reminds relevant personnel to take corresponding solutions. The records are also uploaded to the background for storage via wireless transmission technology. If the equipment thermal anomaly risk index is less than or equal to the equipment thermal anomaly risk index threshold, the probability of the equipment in the production workshop generating thermal anomaly risk is lower. If the equipment thermal anomaly risk index is greater than the equipment thermal anomaly risk index threshold, the probability of the equipment in the production workshop generating thermal anomaly risk is higher. The simulation outputs the corresponding workshop risk factor and reminds relevant personnel to take corresponding solutions. The records are also uploaded to the backend for storage via wireless transmission technology. If the electrical spark risk index is less than or equal to the electrical spark risk index threshold, the probability of electrical sparks occurring in the production workshop's wiring is lower. If the electrical spark risk index is greater than the electrical spark risk index threshold, the probability of electrical sparks occurring in the production workshop's wiring is higher. The simulation outputs the corresponding workshop risk factor and reminds relevant personnel to take corresponding solutions. The records are also uploaded to the backend for storage via wireless transmission technology.

8. A method for early warning, flame retardancy, and explosion suppression in a production workshop according to claim 7, characterized in that, The process of constructing a production workshop early warning model, generating a production workshop early warning score, and generating a tiered response early warning based on the production workshop early warning score includes: Obtain several groups of historical workshop risk factors; group and label these groups of historical workshop risk factors, denoted as [group name missing]. For natural numbers; The historical workshop risk factors were used as sample data, and Less than The natural numbers are used to obtain the mean of the sample data, which is denoted as the sample set; the remaining groups of historical workshop risk factors are used as the test set; and a training sample set is formed based on the sample set and the test set. A standard risk warning model is constructed based on convolutional neural networks; The training sample set is then input into the standard risk warning model to train it. The trained standard risk warning model is then recorded as the production workshop warning model. Based on the aforementioned production workshop early warning model, a production workshop early warning score is generated under the current environmental factors. The production workshop early warning score for: ;in, For the convolutional network neuron in the output feature map of the convolutional layer, the first... The weights corresponding to each convolutional kernel; The workshop risk factors at the corresponding data collection time; It is the first The bias value corresponding to each convolution kernel; Preset production workshop early warning threshold range If the production workshop early warning score If the production workshop is in a safe operating state, then there is no risk, and the corresponding data is recorded in real time; if the production workshop receives an early warning score... If the production workshop is at risk of an accident, it is classified as a medium-level warning, triggering local alarms and remote notifications, and reminding relevant maintenance personnel to perform corresponding maintenance on the equipment; if the production workshop warning score is low... If an accident risk is detected in the production workshop, it will be identified as a high-level alarm, triggering a full alarm, issuing a siren warning, saving on-site video, promptly cutting off power to the equipment, and reminding maintenance personnel to take appropriate emergency measures.

9. A pre-warning flame-retardant and explosion-suppressing system for a production workshop, implementing the pre-warning flame-retardant and explosion-suppressing method for a production workshop as described in any one of claims 1 to 8, comprising: The data acquisition module is used to collect equipment parameters, material properties, and environmental parameters in the production workshop; The data preprocessing module, based on Kalman filtering technology, preprocesses equipment parameters, material properties, and environmental parameters. Workshop geometry model building module, based on The technology is used to construct a workshop equipment geometric model based on the preprocessed equipment parameters, and the workshop equipment geometric model is dynamically calibrated to obtain a dynamic workshop equipment geometric model. The simulation analysis engine module, based on multidimensional model technology, constructs a multidimensional physical field coupling model. Based on the multidimensional physical field coupling model and the preprocessed material properties and environmental parameters, it simulates the risk evolution of the dynamic workshop equipment geometric model, obtains the corresponding workshop risk factors, and executes the corresponding solutions. The intelligent early warning module is based on a neural convolutional network and constructs a production workshop early warning model according to workshop risk factors, thereby generating a production workshop early warning score, and generating a graded response early warning based on the production workshop early warning score.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that can be executed by a processor to implement a pre-warning, flame-retardant, and explosion-suppressing method for a production workshop as described in any one of claims 1-8.

Images