Auxiliary decision-making system applied to mine fire discharging and extinguishing field
By designing an auxiliary decision-making system for mines, the hysteresis that relies on manual monitoring and analysis in the prior art is solved, the accuracy and efficiency of fire prediction are improved, and timely prevention and response of mine fires are achieved.
Patent Information
- Application Number
- CN202411641364.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-18
- Publication Date
- 2025-02-14
AI Technical Summary
The hysteresis of relying on manual monitoring and analysis in the prior art makes it difficult to effectively monitor and prevent mine fires, and traditional data analysis methods lack scientificity and accuracy when processing massive and multi-dimensional monitoring data.
An auxiliary decision-making system is designed, including a data acquisition unit, a back-end auxiliary decision-making unit and a front-end interactive unit. The data acquisition unit obtains the environmental and positioning parameters of each monitoring area of the mine, and the back-end auxiliary decision-making unit uses the fire warning model to predict and make decision suggestions, and visualizes and displays and real-time warnings through the front-end interactive unit.
It improves the accuracy and efficiency of fire prediction, reduces the hysteresis of manual inspections, provides timely decision-making support, and enhances the prevention and response capabilities of mine fires.
Smart Images
Figure CN119435120A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of mine fire prevention and extinguishing, and in particular to an auxiliary decision-making system applied to the field of mine fire prevention and extinguishing. Background Art
[0002] In the current field of mine fire extinguishing, fire monitoring and prevention mainly rely on manual inspections and traditional data analysis methods. This method has significant defects, especially in the context of complex and changeable mine environments, massive monitoring data and high real-time requirements, its limitations are becoming more and more prominent.
[0003] First, the manual inspection method has obvious hysteresis. Due to the vast area and complex terrain of the mine, it is difficult for inspectors to conduct a comprehensive inspection of all monitoring areas in a short period of time, which leads to the discovery and treatment of fire hazards often lagging behind the actual situation, posing a serious threat to mine safety.
[0004] Secondly, traditional data analysis methods are unable to cope with the massive, multi-dimensional mine monitoring data. These methods are often based on empirical judgments, lack scientificity and accuracy, and are difficult to accurately predict and evaluate fire risks. At the same time, due to the low efficiency of data processing, it is difficult to provide effective decision support in a timely manner, making the prevention and response of mine fires face many difficulties.
[0005] Therefore, there is an urgent need for a more efficient decision support system. Summary of the invention
[0006] The purpose of the present invention is to provide an auxiliary decision-making system applied to the field of mine fire extinguishing, which can solve the hysteresis of relying on manual monitoring and analysis in the prior art and improve the accuracy and efficiency of fire prediction.
[0007] To achieve the above object, the present invention provides the following solutions:
[0008] An auxiliary decision-making system applied to the field of mine fire extinguishing, comprising:
[0009] A data acquisition unit, used to obtain relevant parameters of each monitoring area in the target mine; the relevant parameters include environmental parameters and positioning parameters; the environmental parameters include gas component concentrations of carbon monoxide, oxygen, carbon dioxide, and methane, as well as temperature and humidity;
[0010] A back-end auxiliary decision unit is used to make predictions based on the relevant parameters and the fire warning model, make decision recommendations for the predicted level results, and visualize the level results by color differentiation; the fire warning model includes a prediction network and a classifier connected in sequence; the prediction network includes an EMD decomposition layer, a BiLSTM prediction layer, and a DLSTM correction layer connected in sequence;
[0011] The front-end interactive unit is used to simulate the monitoring environment of the target mine, associate the level result color corresponding to each monitoring area with the simulation model and display it, and when the level result is lower than the safety limit, send the corresponding decision suggestion to the staff's mobile device for warning.
[0012] Optionally, the data acquisition unit includes a sensor assembly and a positioning element installed in the target mine; the sensor assembly includes but is not limited to a temperature sensor, a smoke sensor and a gas concentration sensor.
[0013] Optionally, the backend auxiliary decision-making unit specifically includes:
[0014] Model training module, used to tune the parameters of the pre-trained network and build a fire warning model;
[0015] A data preprocessing module, used to perform dynamic sampling processing on the relevant parameters using a numerical resampling algorithm to obtain valid data;
[0016] The auxiliary decision-making module is used to input the valid data into the prediction network, perform probability prediction through the softmax function, and input the predicted fire probability into the classifier for grade classification, determine the grade result of the current fire, and output the preset decision suggestions corresponding to the grade result, and visualize the grade result through color differentiation.
[0017] Optionally, the model training module specifically includes:
[0018] A historical data collection submodule is used to obtain training data; the training data includes historical collection data and corresponding prediction labels; the prediction labels include fire levels and decision suggestions;
[0019] The model building submodule is used to build a pre-trained network for the target model;
[0020] The model training submodule is used to input the training data into the pre-trained network, perform training with the goal of minimizing the loss between the prediction result of the pre-trained network and the prediction label, and determine the trained network as the fire warning model.
[0021] Optionally, the historical data collection submodule includes a historical database and an expert knowledge base; the historical database is used to store the collected data of historical related parameters; the expert knowledge base is used to regularly collect, store, and update industry standards and specifications related to mine fire prevention and extinguishing work, the causes of mine spontaneous combustion fire accidents, expert experience and knowledge, fire prevention and extinguishing measures and expected implementation effects, and use natural language processing technology to structure unstructured data to construct a structured expert knowledge base.
[0022] Optionally, the data preprocessing module specifically includes:
[0023] The resampling submodule is used to perform continuity detection on the relevant parameters within a set time length: when the relevant parameters have missing points, they are supplemented by quadratic Lagrange interpolation to obtain resampled data;
[0024] The filtering submodule is used to construct an FIR digital filter using a window function method, and use the FIR digital filter to filter the resampled data to obtain valid data.
[0025] Optionally, the front-end interaction unit also includes: an NB-IoT communication module; the NB-IoT communication module is used to connect the staff's mobile device to the back-end auxiliary decision-making unit in the intranet through the NB-IoT base station.
[0026] Optionally, the NB-IoT communication module includes a NB-IoT base station enhancement device for enhancing signal coverage.
[0027] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:
[0028] The present invention discloses an auxiliary decision-making system applied to the field of mine fire extinguishing, and the system includes a data acquisition unit, a back-end auxiliary decision-making unit and a front-end interactive unit. The data acquisition unit is used to obtain relevant parameters of each monitoring area in the target mine; the back-end auxiliary decision-making unit is used to make predictions based on the relevant parameters and the fire warning model, and make decision suggestions for the predicted level results, and visualize the level results by color differentiation; the front-end interactive unit is used to simulate the monitoring environment of the target mine, associate the level result colors corresponding to each monitoring area with the simulation model, and when the level result is lower than the safety limit, send the corresponding decision suggestions to the mobile device of the staff for warning. The present invention can solve the hysteresis of the prior art that relies on manual monitoring and analysis, and improve the accuracy and efficiency of fire prediction. BRIEF DESCRIPTION OF THE DRAWINGS
[0029] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.
[0030] Figure 1 It is a schematic diagram of the structure of the auxiliary decision-making system of the present invention. DETAILED DESCRIPTION
[0031] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0032] The purpose of the present invention is to provide an auxiliary decision-making system applied to the field of mine fire extinguishing, which can solve the hysteresis of relying on manual monitoring and analysis in the prior art and improve the accuracy and efficiency of fire prediction.
[0033] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.
[0034] like Figure 1 As shown, the present invention provides an auxiliary decision system applied to the field of mine fire extinguishing, including: a data acquisition unit, a back-end auxiliary decision unit and a front-end interaction unit.
[0035] The data acquisition unit is used to obtain relevant parameters of each monitoring area in the target mine; the relevant parameters include environmental parameters and positioning parameters; the environmental parameters include gas component concentrations of carbon monoxide, oxygen, carbon dioxide, and methane, as well as temperature and humidity.
[0036] The back-end auxiliary decision unit is used to make predictions based on the relevant parameters and the fire warning model, make decision recommendations for the predicted level results, and visualize the level results through color differentiation; the fire warning model includes a prediction network and a classifier connected in sequence; the prediction network includes an EMD decomposition layer, a BiLSTM prediction layer and a DLSTM correction layer connected in sequence.
[0037] The front-end interactive unit is used to simulate the monitoring environment of the target mine, associate the level result color corresponding to each monitoring area with the simulation model and display it, and when the level result is lower than the safety limit, send the corresponding decision suggestion to the staff's mobile device for warning.
[0038] As a specific implementation, the data acquisition unit includes a sensor assembly and a positioning element installed in the target mine; the sensor assembly includes but is not limited to a temperature sensor, a smoke sensor and a gas concentration sensor.
[0039] As a specific implementation, the back-end auxiliary decision-making unit specifically includes:
[0040] The model training module is used to tune the parameters of the pre-trained network and build a fire warning model.
[0041] The data preprocessing module is used to perform dynamic sampling processing on the relevant parameters using a numerical resampling algorithm to obtain valid data.
[0042] The auxiliary decision-making module is used to input the valid data into the prediction network, perform probability prediction through the softmax function, and input the predicted fire probability into the classifier for grade classification, determine the grade result of the current fire, and output the preset decision suggestions corresponding to the grade result, and visualize the grade result through color differentiation.
[0043] As a specific implementation of the model training module, it includes: a historical data collection submodule, a model construction submodule and a model training submodule. The historical data collection submodule is used to obtain training data; the training data includes historical collection data and corresponding prediction labels; the prediction labels include fire levels and decision recommendations. The model construction submodule is used to build a pre-trained network of the target model. The model training submodule is used to input the training data into the pre-trained network, train with the goal of minimizing the loss between the prediction result of the pre-trained network and the prediction label, and determine the trained network as the fire warning model.
[0044] Among them, the historical data collection submodule includes a historical database and an expert knowledge base; the historical database is used to store the collection data of historical related parameters; the expert knowledge base is used to regularly collect, store and update industry standards and specifications related to mine fire prevention and fire fighting, the causes of mine spontaneous combustion fire accidents, expert experience and knowledge, fire prevention and fire fighting measures and expected implementation effects, and use natural language processing technology to structure unstructured data to construct a structured expert knowledge base.
[0045] As a specific implementation of the data preprocessing module, it includes: a resampling submodule and a filtering submodule. The resampling submodule is used to perform continuity detection on the relevant parameters within a set time length: when the relevant parameters have missing points, they are supplemented by quadratic Lagrange interpolation to obtain resampled data. The filtering submodule is used to construct an FIR digital filter using a window function method, and use the FIR digital filter to filter the resampled data to obtain valid data.
[0046] As a specific implementation, the front-end interaction unit further includes: an NB-IoT communication module; the NB-IoT communication module is used to connect the staff's mobile device to the back-end auxiliary decision-making unit in the intranet through the NB-IoT base station. The NB-IoT communication module includes an NB-IoT base station enhancement device for enhancing the signal coverage range.
[0047] Based on the above technical solution, the following embodiments are provided to illustrate the application process of each part.
[0048] 1. Application process of data acquisition unit
[0049] Sensor components and positioning element deployment: Sensor components (such as temperature sensors, smoke sensors, gas concentration sensors, etc.) and positioning elements are installed in each monitoring area of the target mine. These devices are responsible for collecting environmental parameters (such as gas component concentrations of carbon monoxide, oxygen, carbon dioxide, and methane, as well as temperature and humidity) and positioning information in the mine in real time.
[0050] Data collection and transmission: The data collected by the sensor components and positioning elements are transmitted to the data collection unit through the communication network in the mine (such as wired or wireless). The data collection unit receives and organizes the data to provide a basis for subsequent processing and analysis.
[0051] 2. Application process of back-end decision-making support unit
[0052] Data preprocessing:
[0053] Resampling processing: The resampling submodule in the data preprocessing module performs continuity detection on the received related parameters. If there are missing data points, the quadratic Lagrange interpolation method is used to supplement them to obtain complete resampled data.
[0054] Filtering: The filtering submodule uses the window function method to construct a FIR digital filter to filter the resampled data to remove noise and interference and obtain valid data.
[0055] Model training and fire warning:
[0056] Model training: The model training module obtains historical data and its corresponding prediction labels (fire level and decision suggestions) from the historical database, and uses these data to tune the parameters of the pre-trained network to build a fire warning model. The model construction submodule is responsible for building the pre-trained network of the target model, while the model training submodule is responsible for inputting the training data into the pre-trained network for training.
[0057] Fire warning: The auxiliary decision module inputs valid data into the prediction network in the fire warning model. The prediction network includes the EMD decomposition layer, the BiLSTM prediction layer, and the DLSTM correction layer, which processes the input data and outputs the fire probability. Then, the fire probability is input into the classifier for classification to determine the level result of the current fire. At the same time, the preset decision suggestions corresponding to the level result are output, and the level result is visualized by color differentiation.
[0058] Decision suggestions and visual display: The back-end auxiliary decision unit outputs corresponding decision suggestions based on the predicted fire level results. At the same time, the level results are visualized by color differentiation (such as red for high risk level, yellow for medium risk level, and green for low risk level) so that the staff can intuitively understand the fire risk situation in the mine.
[0059] 3. Application process of front-end interaction unit
[0060] Monitoring environment simulation: The front-end interactive unit uses 3D modeling technology to simulate the monitoring environment of the target mine. Through the simulation model, the staff can intuitively understand the layout, equipment, monitoring area and other information in the mine.
[0061] Level result association display: The front-end interactive unit associates the level result color corresponding to each monitoring area with the simulation model for display. When the fire level result of a monitoring area is lower than the safety limit, the color of the area in the simulation model will change (such as turning red or yellow) to attract the attention of the staff.
[0062] Decision suggestion sending and warning: When the front-end interactive unit detects that the fire level result of a certain monitoring area is lower than the safety limit, the corresponding decision suggestion will be automatically sent to the staff's mobile device. The mobile device is connected to the back-end auxiliary decision unit through the NB-IoT communication module to receive and display the decision suggestion information. At the same time, the mobile device can also send warning signals such as sound or vibration to remind the staff to take timely measures to respond.
[0063] NB-IoT communication module application: The NB-IoT communication module is responsible for realizing the communication between the front-end interaction unit and the back-end auxiliary decision-making unit. Through the NB-IoT base station enhancement device, the signal coverage can be enhanced to ensure the stability and reliability of communication. In the mine intranet, the mobile devices of the staff can transmit and interact with the back-end auxiliary decision-making unit through the NB-IoT communication module.
[0064] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.
[0065] This article uses specific examples to illustrate the principles and implementation methods of the present invention. The above examples are only used to help understand the core idea of the present invention. At the same time, for those skilled in the art, according to the idea of the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.
Claims
1. An auxiliary decision-making system applied to the field of mine fire extinguishing, characterized in that: include: A data acquisition unit, used to obtain relevant parameters of each monitoring area in the target mine; the relevant parameters include environmental parameters and positioning parameters; the environmental parameters include gas component concentrations of carbon monoxide, oxygen, carbon dioxide, and methane, as well as temperature and humidity; A back-end auxiliary decision unit is used to make predictions based on the relevant parameters and the fire warning model, make decision recommendations for the predicted level results, and visualize the level results by color differentiation; the fire warning model includes a prediction network and a classifier connected in sequence; the prediction network includes an EMD decomposition layer, a BiLSTM prediction layer, and a DLSTM correction layer connected in sequence; The front-end interactive unit is used to simulate the monitoring environment of the target mine, associate the level result color corresponding to each monitoring area with the simulation model and display it, and when the level result is lower than the safety limit, send the corresponding decision suggestion to the staff's mobile device for warning.
2. The auxiliary decision-making system applied to the field of mine fire extinguishing according to claim 1 is characterized in that: The data acquisition unit includes a sensor assembly and a positioning element installed in the target mine; the sensor assembly includes but is not limited to a temperature sensor, a smoke sensor and a gas concentration sensor.
3. The auxiliary decision-making system applied to the field of mine fire extinguishing according to claim 1 is characterized in that: The back-end auxiliary decision-making unit specifically includes: Model training module, used to tune parameters of pre-trained networks and build fire warning models; A data preprocessing module, used to perform dynamic sampling processing on the relevant parameters using a numerical resampling algorithm to obtain valid data; The auxiliary decision-making module is used to input the valid data into the prediction network, perform probability prediction through the softmax function, and input the predicted fire probability into the classifier for grade classification, determine the grade result of the current fire, and output the preset decision suggestions corresponding to the grade result, and visualize the grade result through color differentiation.
4. The auxiliary decision-making system for use in the field of mine fire extinguishing according to claim 3 is characterized in that: The model training module specifically includes: A historical data collection submodule is used to obtain training data; the training data includes historical collection data and corresponding prediction labels; the prediction labels include fire levels and decision suggestions; The model building submodule is used to build a pre-trained network for the target model; The model training submodule is used to input the training data into the pre-trained network, perform training with the goal of minimizing the loss between the prediction result of the pre-trained network and the prediction label, and determine the trained network as the fire warning model.
5. The auxiliary decision-making system for use in the field of mine fire extinguishing according to claim 4 is characterized in that: The historical data collection submodule includes a historical database and an expert knowledge base; the historical database is used to store the collected data of historical related parameters; the expert knowledge base is used to regularly collect, store and update industry standards and specifications related to mine fire prevention and extinguishing work, the causes of mine spontaneous combustion fire accidents, expert experience and knowledge, fire prevention and extinguishing measures and expected implementation effects, and uses natural language processing technology to structure unstructured data to construct a structured expert knowledge base.
6. The auxiliary decision-making system applied to the field of mine fire extinguishing according to claim 3 is characterized in that: The data preprocessing module specifically includes: The resampling submodule is used to perform continuity detection on the relevant parameters within a set time length: when the relevant parameters have missing points, they are supplemented by quadratic Lagrange interpolation to obtain resampled data; The filtering submodule is used to construct an FIR digital filter using a window function method, and use the FIR digital filter to filter the resampled data to obtain valid data.
7. The auxiliary decision-making system applied to the field of mine fire extinguishing according to claim 1 is characterized in that: The front-end interaction unit also includes: an NB-IoT communication module; the NB-IoT communication module is used to enable the staff's mobile device to connect to the back-end auxiliary decision-making unit in the intranet through the NB-IoT base station.
8. The auxiliary decision-making system for use in the field of mine fire extinguishing according to claim 7, characterized in that: The NB-IoT communication module includes an NB-IoT base station enhancement device for enhancing signal coverage.