Coal mine hidden danger checking system

Abstract

The invention discloses a coal mine hidden danger checking system in the technical field of coal mines. The coal mine hidden danger checking system comprises the following modules: a data acquisition module, which is used for collecting data related to coal mine hidden dangers from various channels such as a coal mine site, a sensor and historical records; the coal mine hidden danger model module is used for constructing and continuously optimizing a coal mine hidden danger prediction model; the hidden danger detection and feedback module is used for guiding detection personnel to carry out on-site hidden danger investigation according to the predicted hidden danger number; the data analysis and evaluation module is used for deeply analyzing the collected data; the model training and optimizing module is used for automatically adjusting parameters and algorithms of the coal mine hidden danger model module according to the result of the data analysis and evaluation module; and the report and decision support module is used for integrating output results of all the modules and generating a hidden danger checking report. The method is scientific and reasonable, the coal mine hidden danger prediction model is continuously optimized through continuous feedback, and the number of unidentified hidden dangers of the system and the number of hidden dangers missed by detection personnel are reduced.

Description

Technical Field

[0001] The invention belongs to the technical field of coal mines, and in particular is a coal mine hidden danger detection system. Background Art

[0002] With the rapid development of information and intelligent technology, the coal mining industry has also begun to gradually introduce these advanced technologies to improve production efficiency and safety management. The coal mine hidden danger inspection system is based on these technologies. Through data collection, processing and analysis, it can realize the comprehensive inspection and management of safety hazards in the coal mine production process.

[0003] The Internet of Things technology enables various devices in the mine to be interconnected and transmit data in real time. The coal mine hidden danger inspection system uses the Internet of Things technology to collect the operating status data of various equipment in the mine in real time, providing data support for hidden danger inspection. Big data technology enables the system to process massive amounts of data and mine valuable information. The application of artificial intelligence technology, such as machine learning and deep learning, enables the system to automatically identify and analyze potential risks in the data, and improve the accuracy and efficiency of hidden danger inspection. Coal mine hidden danger inspection requires professional skills and knowledge. However, the current coal mining industry still has deficiencies in talent cultivation and training, which makes it difficult for some personnel to skillfully eliminate all coal mine hidden dangers, which in turn leads to secondary hidden dangers caused by the inability to eliminate the main hidden dangers.

[0004] In summary, the high missed detection rate in coal mine hidden danger inspection has become a problem that technical personnel in this field need to solve urgently. Therefore, it is necessary to propose a coal mine hidden danger inspection system. Summary of the invention

[0005] In order to solve the above problems, the purpose of the present invention is to provide a coal mine hidden danger detection system, which continuously optimizes the coal mine hidden danger prediction model through continuous feedback, thereby reducing the number of unidentified hidden dangers in the system and the number of hidden dangers missed by inspection personnel.

[0006] In order to achieve the above purpose, the technical solution of the present invention is as follows: a coal mine hidden danger detection system, comprising the following modules:

[0007] Data collection module: used to collect data related to coal mine hazards from multiple channels such as coal mine sites, sensors that collect coal mine hazard factors, and historical records. The data includes geological conditions, equipment status, personnel operation records, and environmental monitoring data.

[0008] Coal mine hidden danger model module: used to use machine learning and statistical methods to build and continuously optimize the coal mine hidden danger prediction model based on historical data and expert knowledge. The coal mine hidden danger prediction model takes into account multiple factors, including geological complexity, equipment aging, and personnel training level, and predicts and generates the number and types of hidden dangers in a single coal mine.

[0009] Hidden danger detection and feedback module: It is used to guide the inspection personnel to conduct on-site hidden danger inspections according to the predicted number and type of hidden dangers, and record the actual number of hidden dangers detected as the number of detected hidden dangers. At the same time, it collects the number of hidden dangers that actually occurred, and divides the actual hidden dangers into the number of predicted but not inspected, inspected but not resolved, unpredicted, and resolved but causing secondary hidden dangers. It calculates the predicted compliance value, the number of unpredicted hidden dangers and the value missed by the inspection personnel.

[0010] Data analysis and evaluation module: used to learn the collected data, generate a first relationship function of the predicted compliance value and the predicted number of hidden dangers, a second relationship function of the number of unpredicted hidden dangers and the predicted number of hidden dangers, a third relationship function of the mapping relationship between the missed detection value of the inspection personnel and the number and type of hidden dangers in a single coal mine, and a fourth relationship function of the number of predicted but unchecked and solved but secondary hidden dangers and the predicted but unchecked hidden dangers;

[0011] Model training and optimization module: used to adjust the parameters and algorithms of the coal mine hidden danger model module according to the first relationship function and the second relationship function generated by the data analysis and evaluation module, so as to improve the prediction accuracy and reduce the number of unidentified hidden dangers; the model training and optimization module is also used to generate the personnel management risk coefficient value corresponding to each coal mine based on the third relationship function and the fourth relationship function. The personnel management risk coefficient value is used to feedback the impact value of different coal mine personnel management on the probability of hidden dangers under the same coal mine hidden danger model module prediction result; the model training and optimization module is also used to generate targeted training directions to improve the skill level of supplementary detection personnel and reduce missed detection;

[0012] Report and decision support module: used to integrate the output results of each module and generate a hidden danger investigation report. The hidden danger investigation report includes hidden danger distribution, prediction accuracy and improvement suggestions to provide decision support for management.

[0013] Furthermore, the data acquisition module is provided with a multi-source data fusion unit, which is used to integrate data from different channels to form a coal mine safety monitoring network.

[0014] Furthermore, the data acquisition module also includes a data preprocessing unit, which is used to clean, denoise, process missing values, detect and process outliers, remove redundant values, and standardize and normalize data from different channels.

[0015] Furthermore, the coal mine hidden danger model module uses convolutional neural network and recurrent neural network training, combined with big data analysis technology, to mine multi-source data and summarize the patterns between geological complexity, equipment aging, personnel training level and the number of hidden dangers.

[0016] Furthermore, the hidden danger detection and feedback module is equipped with an intelligent scheduling unit, which is used to automatically assign detection tasks to the detection personnel closest to the hidden danger point according to the predicted urgency and location information of the hidden danger.

[0017] Furthermore, the data analysis and evaluation module also includes a visualization unit, which is used to display the analysis results in the form of charts and heat maps.

[0018] Furthermore, the model training and optimization module supports online learning and adaptive adjustment, and can continuously receive new data and automatically update model parameters to adapt to dynamic changes in coal mine environment and conditions.

[0019] Furthermore, the reporting and decision support module also includes a safety warning unit, which is used to automatically trigger the warning mechanism when the number of predicted hidden dangers exceeds a preset threshold, and send warning information via SMS, email and system notification.

[0020] Furthermore, the hidden danger detection and feedback module is also used for remote monitoring, which can view the coal mine site conditions, hidden danger inspection progress and prediction results in real time.

[0021] Furthermore, the coal mine hidden danger model module provides customized services and configures prediction sensitive parameters according to the needs and characteristics of different coal mines.

[0022] The following principles and beneficial effects are achieved by adopting the above scheme:

[0023] 1. The present invention deeply analyzes the collected data, including the comparison of the predicted and actual number of hidden dangers, the calculation of unidentified hidden dangers and missed detection values, and the logical and mathematical correlation analysis between these values. The visualization unit displays the analysis results in the form of intuitive charts and heat maps, which is convenient for management to understand and make decisions. Through data analysis and evaluation, model training and optimization, as well as intelligent scheduling and feedback mechanisms, the number of hidden dangers not identified by the system and the number of hidden dangers missed by inspectors can be reduced.

[0024] 2. The present invention collects comprehensive and rich data through diversified data sources such as coal mine sites, sensors, and historical records, including multi-dimensional information such as geology, equipment, personnel operations, and environmental monitoring. The data preprocessing unit cleans, denoises, processes missing values, detects and processes outliers, and standardizes and normalizes the data to ensure the accuracy and consistency of the data, providing a high-quality data foundation for subsequent analysis.

[0025] 3. The present invention uses machine learning and statistical methods, combined with historical data and expert knowledge, to construct a coal mine hidden danger prediction model. The model comprehensively considers multiple key factors such as geological complexity, equipment aging, and personnel training level. Through deep learning algorithms and big data analysis technology, it conducts in-depth mining of multi-source data to improve the accuracy and reliability of hidden danger prediction. The model training and optimization module automatically adjusts the model parameters and algorithms based on the results of data analysis and evaluation to achieve continuous optimization of the model and reduce the number of unidentified hidden dangers.

[0026] 4. According to the predicted number of hidden dangers, the intelligent scheduling unit of the present invention automatically assigns the detection task to the most suitable detection personnel to ensure that the hidden dangers are promptly checked. At the same time, the number of hidden dangers actually detected is recorded and compared with the number of hidden dangers actually occurring, and the predicted compliance value, the number of hidden dangers not identified by the system and the number of missed detections by the detection personnel are calculated to provide feedback for model optimization.

[0027] 5. The present invention can integrate the output results of each module to generate a detailed hidden danger investigation report, including hidden danger distribution, prediction accuracy and improvement suggestions, to provide scientific decision-making support for management. When the number of predicted hidden dangers exceeds the preset threshold, the safety warning unit automatically triggers the warning mechanism to ensure timely response to potential risks.

[0028] 6. The hidden danger detection and feedback module in the present invention has a remote monitoring function, and the management can view the coal mine site conditions, hidden danger investigation progress and prediction results in real time to improve management efficiency. At the same time, the coal mine hidden danger model module provides customized services to meet the specific needs and characteristics of different coal mines and improve the flexibility and adaptability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 is a flow chart of an embodiment of the present invention. DETAILED DESCRIPTION

[0030] The following is further described in detail through specific implementation methods:

[0031] The embodiment is basically as shown in the attached Figure 1 As shown: A coal mine hidden danger detection system, including the following modules:

[0032] Data acquisition module: used to collect data related to coal mine hazards from multiple channels, including coal mine sites, sensors responsible for coal mine hazard factors, and historical records. The data includes geological conditions, equipment status, personnel operation records, and environmental monitoring data; it also includes a multi-source data fusion unit, which is used to integrate data from different channels to form a coal mine safety monitoring network. The data acquisition module also includes a data preprocessing unit, which is used to clean, denoise, process missing values, detect and process outliers, remove redundant values, and standardize and normalize data from different channels.

[0033] Coal mine hidden danger model module: The coal mine hidden danger model module uses convolutional neural network and recurrent neural network training, combined with big data analysis technology, to mine multi-source data. Based on historical data and expert knowledge, it builds and continuously optimizes the coal mine hidden danger prediction model. The coal mine hidden danger prediction model considers multiple factors, including geological complexity, equipment aging, and personnel training level, and predicts and generates the number and type of hidden dangers in a single coal mine; at the same time, it provides customized services and configures prediction sensitivity parameters according to the needs and characteristics of different coal mines.

[0034] Hidden danger detection and feedback module: used to guide detection personnel to conduct on-site hidden danger inspection according to the predicted number and type of hidden dangers, and record the number of hidden dangers actually detected as the number of hidden dangers detected. At the same time, the number of hidden dangers that actually occurred is collected, and the hidden dangers that actually occurred are divided into the number of predicted but not inspected, inspected but not resolved, unpredicted, and resolved but causing secondary hidden dangers. The predicted compliance value, the number of unpredicted hidden dangers, and the value of missed inspection by detection personnel are calculated; it also has an intelligent scheduling unit, which is used to automatically assign detection tasks to the detection personnel closest to the hidden danger point according to the urgency and location information of the predicted hidden dangers. It is also used for remote monitoring, which can view the on-site situation of the coal mine, the progress of hidden danger inspection, and the predicted results in real time.

[0035] Data analysis and evaluation module: used to learn the collected data, generate a first relationship function between the predicted compliance value and the predicted number of hidden dangers, a second relationship function between the number of unpredicted hidden dangers and the predicted number of hidden dangers, a third relationship function between the missed detection value of the inspection personnel and the number and type of hidden dangers in a single coal mine, and a fourth relationship function between the number of predicted but unchecked hidden dangers and resolved but secondary hidden dangers and the number of predicted but unchecked hidden dangers; also includes a visualization unit, which is used to display the analysis results in the form of charts.

[0036] Model training and optimization module: used to adjust the parameters and algorithms of the coal mine hidden danger model module according to the first relationship function and the second relationship function generated by the data analysis and evaluation module, so as to improve the prediction accuracy and reduce the number of unidentified hidden dangers; the model training and optimization module is also used to generate the personnel management hazard coefficient value corresponding to each coal mine based on the third relationship function and the fourth relationship function. The personnel management hazard coefficient value is used to feedback the impact value of different coal mine personnel management on the probability of hidden dangers under the same coal mine hidden danger model module prediction result; the model training and optimization module is also used to generate targeted training directions to improve the skill level of supplementary detection personnel and reduce missed detections; it also supports online learning and adaptive adjustment, and is also used to continuously receive new data and automatically update model parameters to adapt to the dynamic changes in coal mine environment and conditions.

[0037] Report and decision support module: used to integrate the output results of each module and generate a hidden danger investigation report, which includes hidden danger distribution, prediction accuracy and improvement suggestions to provide decision support for management. It also includes a safety warning unit, which is used to automatically trigger the warning mechanism when the number of predicted hidden dangers exceeds the preset threshold, and send warning information through SMS, email and system notification.

[0038] Specific implementation steps:

[0039] Assume that a coal mine is located in a mountainous area with complex geological conditions and has increasingly prominent equipment aging problems in recent years. In order to improve the safety management level of the coal mine, the coal mine has introduced the above-mentioned coal mine hidden danger inspection system.

[0040] The data acquisition module first collects real-time monitoring data from various sensors at the coal mine site, such as gas concentration sensors, temperature sensors, vibration sensors, etc. At the same time, it obtains equipment maintenance records, personnel operation logs, geological exploration reports and other data from the coal mine's database and historical records.

[0041] The data preprocessing unit automatically cleans the collected data, removes noise and redundant values, fills in missing values, handles outliers, and performs data standardization and normalization to ensure data quality. The multi-source data fusion unit integrates data from sensors, databases, and historical records to form a comprehensive coal mine safety monitoring network. For example, geological data is combined with equipment status data to analyze the possibility of equipment failure under specific geological conditions.

[0042] The coal mine hidden danger model module is based on deep learning algorithms and big data analysis technology, combined with historical data and expert knowledge, to build a coal mine hidden danger prediction model. The model considers multiple factors such as geological complexity, equipment aging, and personnel training level to predict the number of hidden dangers in coal mines.

[0043] Since the coal mine pays special attention to gas explosions and roof accidents, the model module is configured with additional prediction factors based on these needs, such as gas concentration change rate, roof pressure monitoring data, etc.

[0044] The hidden danger detection and feedback module predicts that the gas concentration in a certain area may exceed the standard. The hidden danger detection and feedback module generates a hidden danger investigation task and notifies the detection personnel to go to the area for investigation. The intelligent scheduling unit automatically assigns the investigation task to the detection personnel closest to the hidden danger point according to the urgency and location information of the hidden danger, thereby improving the investigation efficiency. The management can understand the progress of the hidden danger investigation by viewing the video surveillance screen of the coal mine site in real time, and check the comparison between the hidden danger distribution map predicted by the system and the actual detection results.

[0045] The data analysis and evaluation module compares the number of predicted hidden dangers with the number of hidden dangers actually detected, and finds that the prediction accuracy is high, but there are still a small number of unidentified hidden dangers. Through the visualization unit, the management can intuitively see the heat map of hidden danger distribution, the prediction accuracy curve, etc., and quickly understand the safety status of the coal mine.

[0046] Based on the results of data analysis and evaluation, the model training and optimization module automatically adjusts the model parameters to improve prediction accuracy and reduce the number of unidentified hidden dangers. At the same time, it continuously receives new data and conducts online learning to automatically update the model parameters to adapt to the dynamic changes in the coal mine environment and conditions. It also generates targeted training plans and recommends that detection personnel strengthen monitoring and inspections in specific areas to improve their skills and reduce missed detections.

[0047] The reporting and decision support module integrates the output results of each module to generate a detailed hidden danger investigation report, including hidden danger distribution, prediction accuracy, improvement suggestions, etc. When the number of hidden dangers in a certain area is predicted to exceed the preset threshold, the safety warning unit automatically triggers the warning mechanism and sends warning information to management, safety supervisors and inspection personnel through SMS, email and system notification to ensure timely measures to deal with potential hidden dangers.

[0048] The above is only an embodiment of the present invention. The common sense such as the known specific structure and characteristics in the scheme is not described in detail here. The ordinary technicians in the relevant field know all the common technical knowledge in the technical field of the invention before the application date or priority date, can obtain all the existing technologies in the field, and have the ability to apply the conventional experimental means before that date. The ordinary technicians in the relevant field can improve and implement this scheme in combination with their own abilities under the enlightenment given by this application. Some typical known structures or known methods should not become obstacles for ordinary technicians in the relevant field to implement this application. It should be pointed out that for those skilled in the art, without departing from the structure of the present invention, several deformations and improvements can be made, which should also be regarded as the protection scope of the present invention, which will not affect the effect of the implementation of the present invention and the practicality of the patent. The protection scope required by this application shall be based on the content of its claims, and the specific implementation methods and other records in the specification can be used to interpret the content of the claims.

Claims

1. A coal mine hidden danger detection system, characterized by: Includes the following modules: Data collection module: used to collect data related to coal mine hazards from multiple channels, including sensors and historical records of coal mine hidden danger factors at coal mine sites, including geological conditions, equipment status, personnel operation records and environmental monitoring data; Coal mine hidden danger model module: It is used to build and continuously optimize the coal mine hidden danger prediction model based on historical data and expert knowledge by using machine learning and statistical methods. The coal mine hidden danger prediction model considers multiple factors, including geological complexity, equipment aging, and personnel training level, and predicts and generates the number and type of hidden dangers in a single coal mine; Hidden danger detection and feedback module: used to guide the inspection personnel to conduct on-site hidden danger inspection according to the predicted number and type of hidden dangers, and record the number of hidden dangers actually detected as the number of hidden dangers detected. At the same time, the number of hidden dangers that actually occurred is collected, and the hidden dangers that actually occurred are divided into the number of predicted but not inspected, inspected but not resolved, unpredicted, and resolved but causing secondary hidden dangers. The predicted compliance value, the number of unpredicted hidden dangers, and the value of missed inspections by inspection personnel are calculated; Data analysis and evaluation module: used to learn the collected data, generate a first relationship function of the predicted compliance value and the predicted number of hidden dangers, a second relationship function of the number of unpredicted hidden dangers and the predicted number of hidden dangers, a third relationship function of the mapping relationship between the missed detection value of the inspection personnel and the number and type of hidden dangers in a single coal mine, and a fourth relationship function of the number of predicted but unchecked and solved but secondary hidden dangers and the predicted but unchecked hidden dangers; Model training and optimization module: used to adjust the parameters and algorithms of the coal mine hidden danger model module according to the first relationship function and the second relationship function generated by the data analysis and evaluation module, so as to improve the prediction accuracy and reduce the number of unidentified hidden dangers; The model training and optimization module is also used to generate the personnel management risk coefficient value corresponding to each coal mine based on the third relationship function and the fourth relationship function. The personnel management risk coefficient value is used to feedback the impact value of different coal mine personnel management on the probability of hidden dangers under the same coal mine hidden danger model module prediction result; The model training and optimization module is also used to generate targeted training directions to improve the skill level of complementary inspection personnel and reduce missed detections; Report and decision support module: used to integrate the output results of each module and generate a hidden danger investigation report. The hidden danger investigation report includes hidden danger distribution, prediction accuracy and improvement suggestions to provide decision support for management.

2. The coal mine hidden danger detection system according to claim 1, characterized in that: The data acquisition module is equipped with a multi-source data fusion unit, which is used to integrate data from different channels to form a coal mine safety monitoring network.

3. The coal mine hidden danger detection system according to claim 2 is characterized in that: The data acquisition module also includes a data preprocessing unit, which is used to clean, denoise, process missing values, detect and process outliers, remove redundant values, and standardize and normalize data from different channels.

4. The coal mine hidden danger detection system according to claim 3 is characterized in that: The coal mine hidden danger model module uses convolutional neural network and recurrent neural network training, combined with big data analysis technology, to mine multi-source data and summarize the laws between geological complexity, equipment aging, personnel training level and the number of hidden dangers.

5. The coal mine hidden danger detection system according to claim 4 is characterized in that: The hidden danger detection and feedback module is equipped with an intelligent scheduling unit, which is used to automatically assign detection tasks to the detection personnel closest to the hidden danger point based on the predicted urgency and location information of the hidden danger.

6. The coal mine hidden danger detection system according to claim 5, characterized in that: The data analysis and evaluation module also includes a visualization unit, which is used to display the analysis results in the form of charts.

7. The coal mine hidden danger detection system according to claim 6, characterized in that: The model training and optimization module supports online learning and adaptive adjustment. It is also used to continuously receive new data and automatically update model parameters to adapt to dynamic changes in coal mine environment and conditions.

8. The coal mine hidden danger detection system according to claim 7, characterized in that: The reporting and decision support module also includes a safety warning unit, which is used to automatically trigger the warning mechanism when the number of predicted hidden dangers exceeds the preset threshold, and send warning information via SMS, email and system notification.

9. The coal mine hidden danger detection system according to claim 8, characterized in that: The hidden danger detection and feedback module is also used for remote monitoring, which displays the on-site conditions of the coal mine, the progress of hidden danger inspection and the predicted results in real time.

10. The coal mine hidden danger detection system according to claim 9, characterized in that: The coal mine hidden danger model module provides customized services and configures prediction sensitive parameters according to the needs and characteristics of different coal mines.

Images