A mine safety risk investigation method and system based on intelligent Internet of Things devices

Abstract

The present invention relates to a mine safety risk investigation method and system based on intelligent Internet of Things devices. The method comprises the following steps: first, obtaining the working event data of the intelligent Internet of Things device, identifying and extracting the key features related to the safety symptoms; then, establishing a mapping model between the working events and the safety symptoms, performing statistical analysis on the real-time monitoring data, and identifying potential safety risk points; comparing the risk points with the mine safety management regulations, generating a safety risk assessment report, and issuing early warning information according to the assessment report. The system comprises a data acquisition module, a mapping model module, a data analysis module, a comparison and assessment module, and an early warning module, and can realize automated mine safety monitoring and risk investigation. The present invention significantly improves the real-time and accuracy of mine safety management through intelligent data analysis and early warning mechanisms, can effectively prevent and reduce the occurrence of mine safety accidents, and provides strong support for mine safety management.

Description

Technical Field

[0001] The present invention belongs to the technical field of mine safety detection, and specifically relates to a mine safety risk investigation method and system based on intelligent Internet of Things devices. Background Art

[0002] With the rapid development of Internet of Things technology, smart devices are being used more and more widely in all walks of life. As one of the high-risk industries, the mining industry is facing security challenges from many aspects, such as equipment failure, environmental degradation, and human operational errors. Traditional mine safety management usually relies on manual inspections and regular maintenance, which is not only time-consuming and labor-intensive, but also has the risk of missed inspections and delayed responses. Especially in some mining scenarios with complex environments and a wide variety of equipment, traditional safety management methods are difficult to fully cover and respond to emergencies in a timely manner.

[0003] In recent years, with the development of sensor technology, wireless communication technology and data analysis technology, intelligent IoT devices have gradually been introduced into mine safety management systems. These devices can monitor various operating parameters of mines in real time, such as equipment temperature, vibration, current, etc., and transmit data to the background for analysis. However, many current mine safety management systems still lack the ability to deeply analyze and intelligently process data, especially when faced with massive multi-dimensional data. It is difficult for the system to effectively identify potential safety risk points and generate timely and accurate warning information.

[0004] In addition, existing mine safety risk screening methods are usually based on the analysis of a single or a few parameters, and cannot fully consider the complex relationship between various factors, resulting in limitations in risk identification. Especially when there are interrelated or synergistic effects between multiple devices, traditional methods often cannot accurately determine the potential risks caused by these complex relationships. In addition, traditional systems usually lack real-time and automation functions, making it difficult to respond to the operating status of mining equipment in the first time, and cannot meet the high requirements of modern mine safety management.

[0005] Therefore, there is an urgent need for a mine safety risk investigation method based on intelligent IoT devices that can integrate data from multiple sensors, use advanced algorithm models for in-depth analysis, monitor in real time and accurately identify potential safety risks, and provide timely warnings and emergency response measures to improve the overall safety management level of mines. Summary of the invention

[0006] In view of the problems existing in the above-mentioned prior art, the present invention provides:

[0007] A mine safety risk investigation method based on intelligent Internet of Things devices includes the following steps:

[0008] S1. Obtain working event data of smart IoT devices, identify and extract key features related to safety signs;

[0009] S2. Establish the corresponding relationship between work events and safety symptoms, and form a mapping model between work events and safety symptoms;

[0010] S3. Based on the mapping model, statistical analysis is performed on the real-time monitoring data of the current smart IoT devices to identify potential security risk points;

[0011] S4. Compare the potential safety risk points with the mine safety management regulations to generate a safety risk assessment report for the current mine;

[0012] S5. Based on the safety risk assessment report, issue early warning information on mine safety risks.

[0013] Furthermore, in step S2, a mapping model between work events and safety symptoms is established using a support vector machine algorithm, specifically including:

[0014] S21. The set of working events of the smart IoT device in the historical records is:

[0015] ;

[0016] in, Indicates the first work events, with a maximum of work events;

[0017] The set of safety symptoms in the history record is:

[0018] ;

[0019] in, Indicates the first Safety signs, at most safety signs;

[0020] S22. Represent each work event in the historical data set as a high-dimensional feature matrix:

[0021] ;

[0022] in, Respectively represent The first to the second work events High-dimensional features;

[0023] S23, construct a prediction function model, the prediction function model satisfies:

[0024] ;

[0025] ;

[0026] ;

[0027] Among them, the high-dimensional feature matrix As input, is the work event response matrix, as the output quantity; is the work event matrix; and are the weight matrix and bias vector respectively, and are the parameters to be solved;

[0028] is a regular function, which means that the working event matrix Compare any element of with 0, keep the non-negative elements and set the negative elements to zero;

[0029] is the work event characteristic function, which is used to characterize the characteristic complexity of the work event and satisfies:

[0030] ;

[0031] in, Indicates Work event No. High-dimensional features;

[0032] S24, solving the prediction function model; specifically including:

[0033] S241. Construct an angle function that satisfies:

[0034] ;

[0035] in, represents the safety sign vector, satisfying: ; Represents a work event response vector that satisfies: ; is the output value of the angle function, which numerically represents the vector angle, and the weight matrix and the bias vector As input value, the output value represents the safety symptom vector and work incident response vector The angle between

[0036] S242, Minimize the angle function: Solve the angle function ,satisfy:

[0037] ;

[0038] in, is the minimization algorithm, which means to find Get the minimum value And assign it to , and Represent the weight matrix and the bias vector The best value of

[0039] S243. Construct a prediction function model to satisfy:

[0040] ;

[0041] in, represents the work event as input quantity, Indicates a predicted safety symptom.

[0042] Furthermore, in step S1, identifying and extracting key feature data related to safety signs specifically includes: performing multi-dimensional feature analysis on historical operating data of smart IoT devices, including at least device temperature, vibration frequency, and current intensity, based on operating parameters of different dimensions, comprehensively considering the changing trends of various parameters and their interrelationships, using time series sorting, monitoring the changes in the operating status of smart IoT devices over time, capturing potential trends that may cause safety signs, and identifying key features that may cause safety signs.

[0043] Furthermore, the key features are extracted and standardized, specifically including: normalizing the data of different devices and different operating environments to eliminate data deviations caused by differences in device performance or changes in the external environment; unifying the feature data formats of each device through standardization, so that data from different devices can be compared and analyzed in the same mapping model; filtering and filling out outliers to verify the data integrity and validity of the input model.

[0044] Furthermore, in step S3, identifying potential security risk points specifically includes:

[0045] S31. Perform pattern matching and comparison analysis on real-time monitoring data and historical event data: perform similarity comparison on real-time monitoring data and historical event data to determine whether the current work event has similar characteristics to known safety symptoms;

[0046] S32. For abnormal behaviors that exceed the predetermined threshold range, the potential threat level of the abnormal behavior to mine safety is determined through a priority sorting algorithm, and the most risky abnormal behaviors are marked as high-priority safety risk points, which are highlighted in the generated safety risk assessment report.

[0047] Furthermore, step S4 also includes performing multi-dimensional automated analysis on the generated security risk assessment report; the analysis content at least includes:

[0048] According to the safety risk levels of different areas in the mine, risk points are divided into regions;

[0049] Based on the frequency and severity of historical accidents, specific early warning information is generated for different types of safety risks.

[0050] Furthermore, in step S5, the warning information is automatically sent to the mine safety management system and preset safety managers in the form of real-time notification, and is accompanied by a detailed risk analysis report and recommended measures.

[0051] Furthermore, the recommended measures include: dynamically adjusting the operating parameters of smart IoT devices, including at least: reducing the operating power of high-risk equipment, increasing the inspection frequency of equipment, and adjusting the working hours of equipment.

[0052] The present invention also provides a mine safety risk investigation system based on intelligent Internet of Things devices, which is used to execute the mine safety risk investigation method based on intelligent Internet of Things devices. The system includes the following modules:

[0053] Data acquisition module, used to obtain work event data from multiple smart IoT devices and extract key feature data related to mine safety;

[0054] A mapping model module, which establishes a corresponding relationship between work events and safety symptoms based on the key feature data obtained by the data acquisition module, and generates a mapping model between work events and safety symptoms;

[0055] Data analysis module, which is used to analyze monitoring data from smart IoT devices in real time and identify potential security risk points based on mapping models;

[0056] The comparison and assessment module compares the identified safety risk points with the mine safety management regulations and generates a mine safety risk assessment report;

[0057] The early warning module issues early warning information on mine safety risks based on the assessment report.

[0058] Furthermore, the system also includes an automated management module, which is connected to the early warning module and is used to receive early warning information and automatically generate a corresponding safety emergency response plan; the safety emergency response plan includes adjusting the working parameters of the smart Internet of Things device, increasing the inspection frequency, and initiating an emergency plan.

[0059] Beneficial effects:

[0060] The mine safety risk investigation method based on intelligent Internet of Things devices provided by the present invention has the following significant technical effects:

[0061] 1. Efficient and accurate risk identification: Through multi-dimensional data collection and feature extraction, the present invention can comprehensively monitor the operating status of various types of equipment in the mine, and establish a mapping model between work events and safety symptoms through advanced machine learning algorithms (such as support vector machines and deep learning), thereby achieving efficient identification of potential safety risks. Compared with traditional manual inspections and single parameter monitoring methods, the present invention can significantly improve the accuracy and response speed of risk identification, and reduce the possibility of missed detection and false alarms.

[0062] 2. Real-time warning and dynamic adjustment: By establishing an online monitoring and real-time analysis system, the present invention can issue early warning information in a timely manner when equipment abnormalities occur or risk factors increase. The system can dynamically adjust early warning parameters and emergency measures based on the comparison of real-time monitoring data and historical data to ensure that effective risk response measures are taken as soon as possible. This real-time early warning mechanism enables mine managers to respond quickly and prevent accidents.

[0063] 3. Intelligent risk assessment and decision support: Through comprehensive analysis of multi-dimensional data of mining equipment, the present invention can generate detailed safety risk assessment reports and provide three-dimensional visualization combined with geographic information system (GIS) to help managers intuitively understand the overall safety situation of the mine. The system can not only identify current risk points, but also predict possible safety issues in the future and provide specific response measures, thereby providing intelligent decision support for mine safety management.

[0064] 4. Improve the efficiency of mine safety management: The present invention combines intelligent IoT devices with advanced data analysis algorithms to achieve automation and intelligence in mine safety management. Through real-time monitoring and analysis of the operating data of various types of equipment, the present invention can timely discover and resolve potential safety hazards, reduce the workload of manual inspections, and improve management efficiency. At the same time, the system's automatic warning and reporting functions can reduce the burden on management personnel, making mine safety management more efficient and scientific.

[0065] 5. Prevent major safety accidents: Through timely risk identification and early warning, the present invention can effectively prevent major safety accidents caused by equipment failure or environmental abnormalities. During the implementation process, through comprehensive analysis of parameters such as temperature, vibration, and current, the system successfully warned and prevented major accidents that may cause production stagnation or casualties, thereby significantly improving the safety of mines and ensuring the life safety of operators. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 It is a schematic diagram of the steps of the troubleshooting method of the present invention. DETAILED DESCRIPTION

[0067] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. 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.

[0068] Embodiment 1

[0069] The embodiment of the present invention relates to a mine safety risk investigation system and method based on intelligent Internet of Things devices. The specific implementation methods are as follows:

[0070] 1. System Architecture

[0071] The mine safety risk investigation system of this embodiment is mainly composed of the following modules:

[0072] Data collection module: Intelligent IoT devices deployed at key locations in the mine monitor the working environment and equipment operating status in real time. This module collects operating parameters such as temperature, vibration frequency, and current intensity through sensors to form a work event data set.

[0073] Mapping model module: By analyzing historical work event data and mine safety accident data, a support vector machine (SVM) algorithm model is constructed. Based on a high-dimensional feature matrix, the model maps the relationship between work events and safety symptoms into an event response matrix, which is used to predict and identify potential safety risk points.

[0074] Data analysis module: obtains the operating data of smart IoT devices in real time, and compares these data with the prediction function in the mapping model to identify possible security risk points.

[0075] Comparison and evaluation module: The identified safety risk points are compared with the mine safety management regulations in detail to generate a safety risk assessment report. The assessment report includes not only the current risk level, but also the possibility of risk occurrence and potential hazards.

[0076] Early warning module: According to the evaluation report generated by the comparison and evaluation module, early warning information is sent to the mine safety management system and relevant personnel in real time. The early warning information contains a detailed risk description and corresponding recommended measures.

[0077] Automated management module: The system automatically generates emergency response plans, including dynamic adjustment of equipment parameters, increased inspection frequency, etc., to ensure the timeliness and effectiveness of mine safety management.

[0078] 2. Implementation process

[0079] Taking the actual application of a mine as an example, the specific implementation process of the system is described:

[0080] S1. Data collection and preprocessing

[0081] Smart IoT devices are installed in key areas of the mine, and relevant work event data is collected through sensors. Each work event data set consists of multi-dimensional parameters such as temperature, vibration frequency, and current intensity. The data acquisition module monitors the changing trend of equipment status through time series analysis, identifies key features that may cause safety issues, and transmits these feature data to the mapping model module.

[0082] S2. Mapping model construction

[0083] The mapping model module uses historical data to build a support vector machine algorithm model. The model represents work events as a high-dimensional feature matrix and calculates the work event response matrix through a prediction function model. Finally, the system establishes a mapping model based on the relationship between historical work events and known safety symptoms to identify new safety risk points in real time.

[0084] S3, Real-time Data Analysis

[0085] After receiving the real-time work event data, the data analysis module inputs it into the mapping model for analysis. By comparing the output values ​​of the prediction function model, potential safety risk points are identified and the data of these risk points are recorded in real time.

[0086] S4. Risk assessment and early warning

[0087] The comparison and assessment module compares and analyzes the identified safety risk points with the mine safety management regulations and generates a detailed safety risk assessment report. The report includes the location of the risk point, the risk level and its possible impact. The early warning module sends early warning information to mine safety managers based on the results of the report generation.

[0088] S5. Emergency Response

[0089] After the early warning information is issued, the automation management module executes the corresponding emergency response according to the recommended measures in the risk assessment report. Specific measures include dynamically adjusting the operating parameters of the equipment, such as reducing the working power of high-risk equipment, increasing the inspection frequency of equipment, adjusting the working hours of equipment, etc. These measures can effectively reduce potential risks and ensure the safe operation of the mine.

[0090] 3. Experimental Verification

[0091] The application scenario of the system was simulated in an experimental environment. The accuracy of the mapping model constructed by the support vector machine algorithm was verified by analyzing the historical data of a mine. The experimental results show that the system can efficiently identify potential safety risk points and issue early warning information in a timely manner. The generated emergency response plan shows high reliability and effectiveness in actual operation.

[0092] 4. Application Effect

[0093] The system has successfully prevented many potential mine safety accidents in actual applications. By dynamically adjusting the operating parameters of the equipment, it has reduced the frequency of equipment failures and improved the safety and efficiency of mine operations. The promotion and application of this system is expected to significantly improve the safety management level of mines.

[0094] Embodiment 2

[0095] Application example of mine safety risk investigation method based on smart IoT devices: In a large open-pit mine, in order to improve the safety of mine operations, the mine management department decided to introduce a mine safety risk investigation method based on smart IoT devices to monitor and analyze mine equipment and environmental data in real time, so as to promptly discover and respond to potential safety hazards. The mine has deployed multiple smart IoT devices covering key production areas, which can continuously monitor the operating status and environmental conditions of the equipment. The specific implementation process is as follows: Figure 1 As shown:

[0096] Step S1: Obtain work event data and extract key features

[0097] The mine management system first uses the IoT data collection module to obtain work event data from the smart devices deployed in the mine within a week. These data include but are not limited to: temperature, pressure, vibration frequency, current intensity, ambient humidity, air quality index and other multi-dimensional operating parameters of the mine equipment.

[0098] To ensure the accuracy and real-time nature of the data, the system performs multiple checks and time synchronization on all collected data to ensure that data from different devices and sensors can be analyzed on the same timeline. After data preprocessing, the system uses machine learning algorithms to extract features from the data, analyze the changing trends of each parameter, and identify key features related to historical security events. For example:

[0099] Temperature feature extraction: The temperature data of a key device (for example, T1, T2, …, Tn) shows a continuous upward trend within a week, and the temperature increase rate exceeds the abnormal threshold of 2°C / hour in a short period of time, which indicates that the device may have heat dissipation problems or other potential failures.

[0100] Vibration frequency feature extraction: Vibration frequency data (e.g., F1, F2, …, Fn) shows that the vibration frequency of a device has suddenly increased in the past 24 hours, exceeding the abnormal threshold of 10Hz / minute, which may indicate wear or looseness of internal components of the device.

[0101] Current feature extraction: By analyzing the fluctuations in current intensity, the system found that the current of a certain device fluctuated significantly within a specific time period, which is similar to the current fluctuation characteristics before the device failed in historical data.

[0102] Step S2: Establish a mapping model between work events and safety symptoms

[0103] Using the key feature data extracted in step S1, the system uses the support vector machine (SVM) algorithm and deep learning method to establish a mapping model between work events and safety symptoms. Specifically, the system first converts the collected historical data and current data into high-dimensional feature vectors and uses these feature vectors to build a training set. Each work event set X={x1, x2, …, xn} and the safety symptom set Y={y1, y2, …, ym} are mapped through a high-dimensional feature matrix.

[0104] Assume that the high-dimensional feature matrix of work event x_i is x_i=[xi^1, xi^2, …, xi^k], where xi^1 and xi^2 represent feature values ​​of different dimensions. In the mapping model, the system learns the weight matrix W and the bias B, and the prediction function model satisfies:

[0105] ;

[0106] ;

[0107] ;

[0108] Among them, the high-dimensional feature matrix As input, is the work event response matrix, as the output quantity; is the work event matrix; and are the weight matrix and bias vector respectively, and are the parameters to be solved;

[0109] is a regular function, which means that the working event matrix Compare any element of with 0, keep the non-negative elements and set the negative elements to zero;

[0110] is the work event characteristic function, which is used to characterize the characteristic complexity of the work event and satisfies:

[0111] ;

[0112] in, Indicates Work event No. High-dimensional features;

[0113] The system can determine the correlation between the current work event and the specific safety symptom yj, thereby predicting possible safety problems.

[0114] Step S3: Identify potential security risk points

[0115] Based on the mapping model established in step S2, the system performs statistical analysis on the real-time monitoring data currently acquired, and performs pattern matching and comparison with historical safety event data. For example, by comparing the temperature, vibration frequency, current fluctuation and other multi-dimensional data of a certain device with the characteristic patterns before historical safety accidents, the system finds that the changing trends of these data are highly similar to the characteristics before a major accident. Therefore, the system identifies the area where the device is located as a potential safety risk point.

[0116] In addition, the system also combines the Geographic Information System (GIS) to conduct spatial analysis of safety risks in different areas of the mine. Through the three-dimensional visualization model, the system can intuitively display the operating status of equipment inside the mine and potential risk areas. This provides mine managers with more comprehensive and accurate risk identification information.

[0117] Step S4: Generate a security risk assessment report

[0118] Based on the safety risk points identified in step S3, the system automatically generates a detailed safety risk assessment report. The report not only includes the current safety risk level of each area of ​​the mine, but also conducts an in-depth analysis of potential risk factors. Specifically:

[0119] The report pointed out that in the southern operating area of ​​the mine, there was a high safety risk due to the high temperature and abnormal vibration of a key equipment. The report described the equipment's operating history and current status in detail, and explained in detail the temperature increase and abnormal vibration of the equipment.

[0120] Based on the predictions of the mapping model, the system suggests several countermeasures, including: immediately shutting down the equipment to check the cooling system, detecting whether the internal parts of the equipment are loose or worn, and recommending replacement of parts that may have problems.

[0121] The report also includes predictions and recommendations for the mine’s overall safety posture, such as increasing the frequency of equipment inspections in the southern operating area, adding additional temperature and vibration monitoring sensors, and installing emergency shutdown devices on key equipment so that timely response measures can be taken when abnormalities occur.

[0122] Step S5: Issue warning information

[0123] According to the safety risk assessment report, the system automatically sends warning information to the safety management module of the mine management system and the preset safety management personnel. The warning information includes:

[0124] The specific location of potential safety risk points and detailed information on related equipment;

[0125] Analysis of the current operating parameters of the equipment and their differences from normal values;

[0126] The possible accident types predicted by the system and their probability of occurrence;

[0127] Recommended emergency actions and inspection procedures.

[0128] In addition, the system also pushes warning information to the mine's central control room, displaying a 3D visualization of potential risk points on a large screen. Mine managers can monitor the status changes of each risk point in real time in the control room and arrange on-site inspections and emergency response based on the warning information.

[0129] Implementation effect:

[0130] Through the method of the present invention, the mine management can effectively identify potential safety risks and take countermeasures before problems occur. In this embodiment, the mine management system successfully identified a high-risk equipment in the southern operating area, and immediately conducted an equipment inspection after the warning information was issued, and found that there were indeed problems of poor heat dissipation and loose components inside the equipment. Due to the timely maintenance and replacement measures, major safety accidents that may cause production stagnation or casualties were avoided.

[0131] Parameter example:

[0132] During the implementation process, in order to ensure the accuracy and timeliness of risk identification, the system sets the following parameters:

[0133] Abnormal temperature rise rate threshold: 2℃ / hour.

[0134] Abnormal vibration frequency threshold: 10Hz / minute.

[0135] Current fluctuation detection window period: 24 hours.

[0136] Kernel function of the support vector machine model: RBF (radial basis function).

[0137] Similarity threshold for pattern matching: 85%.

[0138] Spatial resolution of GIS: 1 meter.

[0139] These parameters are obtained through statistical analysis and comparative experiments of historical data and have been verified through multiple field applications. They can effectively improve the accuracy of risk identification and issue early warning information in a timely manner.

[0140] Obviously, the above embodiments are merely examples for clear explanation, and are not intended to limit the implementation methods. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. The obvious changes or modifications derived from them are still within the protection scope of the invention.

Claims

1. A mine safety risk investigation method based on intelligent Internet of Things devices, characterized in that: The method comprises the following steps: S1. Obtain working event data of smart IoT devices, identify and extract key features related to safety signs; S2. Establish the corresponding relationship between work events and safety symptoms to form a mapping model between work events and safety symptoms. The mapping model between work events and safety symptoms is established using a support vector machine algorithm, specifically including: S21. The set of working events of the smart IoT device in the historical records is: ; in, Indicates the first work events, with a maximum of work events; The set of safety symptoms in the history record is: ； in, Indicates the first Safety signs, at most safety signs; S22. Represent each work event in the historical data set as a high-dimensional feature matrix: ； in, Respectively represent The first to the second work events High-dimensional features; S23, construct a prediction function model, the prediction function model satisfies: ； ； ； Among them, the high-dimensional feature matrix As input, is the work event response matrix, as the output quantity; is the work event matrix; and are the weight matrix and bias vector respectively, and are the parameters to be solved; is a regular function, which means that the working event matrix Compare any element of with 0, keep the non-negative elements and set the negative elements to zero; is the work event characteristic function, which is used to characterize the characteristic complexity of the work event and satisfies: ； in, Indicates Work event No. High-dimensional features; S24, solving the prediction function model; specifically including: S241. Construct an angle function that satisfies: ； in, represents the safety sign vector, satisfying: ; Represents a work event response vector that satisfies: ; is the output value of the angle function, which numerically represents the vector angle, and the weight matrix and the bias vector As input value, the output value represents the safety symptom vector and work incident response vector The angle between S242, Minimize the angle function: Solve the angle function ,satisfy: ； in, is the minimization algorithm, which means to find Get the minimum value And assign it to , and Represent the weight matrix and the bias vector The best value of S243. Construct a prediction function model to satisfy: ； in, represents the work event as input quantity, Indicates a predicted safety symptom; S3. Based on the mapping model, statistical analysis is performed on the real-time monitoring data of the current smart IoT devices to identify potential security risk points; S4. Compare the potential safety risk points with the mine safety management regulations to generate a safety risk assessment report for the current mine; S5. Based on the safety risk assessment report, issue early warning information on mine safety risks.

2. According to claim 1, a mine safety risk investigation method based on intelligent Internet of Things devices is characterized in that: In step S1, identifying and extracting key feature data related to safety signs specifically includes: performing multi-dimensional feature analysis on the historical operation data of the smart IoT device, including at least device temperature, vibration frequency, and current intensity, based on operating parameters of different dimensions, comprehensively considering the change trends of various parameters and their interrelationships, using time series sorting, monitoring the changes in the operating status of the smart IoT device over time, capturing potential trends that may cause safety signs, and identifying key features that may cause safety signs.

3. According to claim 2, a mine safety risk investigation method based on intelligent Internet of Things devices is characterized in that: After the key features are extracted, standardization processing is performed, specifically including: normalizing the data of different devices and under different operating environments to eliminate data deviations caused by differences in device performance or changes in the external environment; unifying the feature data formats of each device through standardization processing, so that data from different devices can be compared and analyzed in the same mapping model; filtering and filling out outliers to verify the data integrity and validity of the input model.

4. According to claim 3, a mine safety risk investigation method based on intelligent Internet of Things devices is characterized in that: In step S3, identifying potential security risk points specifically includes: S31. Perform pattern matching and comparison analysis on real-time monitoring data and historical event data: perform similarity comparison on real-time monitoring data and historical event data to determine whether the current work event has similar characteristics to known safety symptoms; S32. For abnormal behaviors that exceed the predetermined threshold range, the potential threat level of the abnormal behavior to mine safety is determined through a priority sorting algorithm, and the most risky abnormal behaviors are marked as high-priority safety risk points, which are highlighted in the generated safety risk assessment report.

5. According to claim 3, a mine safety risk investigation method based on intelligent Internet of Things devices is characterized in that: Step S4 also includes performing multi-dimensional automated analysis on the generated security risk assessment report; The analysis shall at least include: According to the safety risk levels of different areas in the mine, risk points are divided into regions; Based on the frequency and severity of historical accidents, specific early warning information is generated for different types of safety risks.

6. A mine safety risk investigation method based on intelligent Internet of Things devices according to claim 3, characterized in that: In step S5, the warning information is automatically sent to the mine safety management system and the preset safety management personnel in the form of real-time notification, and is accompanied by a detailed risk analysis report and recommended measures.

7. A mine safety risk investigation method based on intelligent Internet of Things devices according to claim 6, characterized in that: The recommended measures include: dynamically adjusting the operating parameters of smart IoT devices, including at least: reducing the operating power of high-risk equipment, increasing the inspection frequency of equipment, and adjusting the working hours of equipment.

8. A mine safety risk investigation system based on intelligent Internet of Things devices, used to execute a mine safety risk investigation method based on intelligent Internet of Things devices as described in any one of claims 1 to 7, characterized in that: The system includes the following modules: Data acquisition module, used to obtain work event data from multiple smart IoT devices and extract key feature data related to mine safety; A mapping model module, which establishes a corresponding relationship between work events and safety symptoms based on the key feature data obtained by the data acquisition module, and generates a mapping model between work events and safety symptoms; Data analysis module, which is used to analyze monitoring data from smart IoT devices in real time and identify potential security risk points based on mapping models; The comparison and assessment module compares the identified safety risk points with the mine safety management regulations and generates a mine safety risk assessment report; The early warning module issues early warning information on mine safety risks based on the assessment report.

9. A mine safety risk investigation system based on intelligent Internet of Things devices according to claim 8, characterized in that: The system also includes an automated management module, which is connected to the early warning module and is used to receive early warning information and automatically generate a corresponding safety emergency response plan; the safety emergency response plan includes adjusting the working parameters of the smart Internet of Things devices, increasing the inspection frequency, and initiating an emergency plan.

Images