Mine safety warning method, device, system and equipment based on multi-source heterogeneous data and medium
By clustering and risk assessment of multi-source heterogeneous data, combined with K-means and BP early warning models, timely monitoring and alarm of mine safety hazards were achieved, solving the problems of small monitoring range and alarm delay in existing technologies, and improving construction safety.
Patent Information
- Application Number
- CN202511276875.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-09-08
- Publication Date
- 2025-11-21
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Existing technologies are insufficient for effectively monitoring potential safety hazards during mining and construction processes, resulting in a small monitoring range, easy omissions, delayed alarms, and low timeliness.
A mine safety alarm method based on multi-source heterogeneous data is adopted. By acquiring multi-source heterogeneous data collected by heterogeneous equipment in different areas of the mine, clustering is performed using the K-means algorithm, and the risk level of the safety hazard type is determined by combining the preset BP early warning model and alarm is triggered.
It has increased the monitoring range, reduced blind spots and omissions, enabled the early detection of safety risks, shortened alarm delays, and improved construction safety.
Smart Images
Figure CN120997995A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of safety alarms, and in particular to a mine safety alarm method, device, system, equipment and medium based on multi-source heterogeneous data. Background Technology
[0002] With the continuous promotion and application of new coal mine production technologies and the continuous improvement of management levels, the comprehensive monitoring level of mine production and safety is also improving. Therefore, in addition to considering accelerating the speed and efficiency of certain stages of the production process, it is also necessary to conduct on-site safety monitoring and alarms to achieve real-time and accurate supervision of high-risk production lines and key areas, thereby ensuring the safety of workers.
[0003] To monitor high-risk areas in real time and ensure the safety of on-site personnel, one common method is to install monitoring equipment (such as cameras) at different construction sites or high-risk areas to collect monitoring images of construction workers and transmit them to a central control platform. The central control platform uses image recognition models (such as tiny-YOLOv3 or yolov7) to identify the construction behavior of construction workers and the characteristics of objects in the construction area. Based on the construction behavior and object characteristics, a safety risk estimate is calculated. When the safety risk estimate is high, a safety alarm is triggered to improve the evacuation of construction workers.
[0004] However, the commonly used methods have the following technical problems: During mining and construction, safety hazards are easily overlooked due to non-standard engineering operations or negligence. These hazards often lead to safety accidents at some point afterward (such as ground collapse, gas leaks, or explosions). Furthermore, various safety accidents often occur instantaneously, and existing technical solutions are difficult to monitor for potential safety hazards, resulting in a small monitoring range and a high risk of omissions. Summary of the Invention
[0005] In view of the aforementioned problems, this application is made to provide a mine safety alarm method, apparatus, system, equipment, and medium based on multi-source heterogeneous data that overcomes or at least partially solves the aforementioned problems, including: A mine safety alarm method based on multi-source heterogeneous data, the method comprising: Acquire multi-source heterogeneous data from the mine, wherein the multi-source heterogeneous data is heterogeneous data collected by heterogeneous devices set up in different areas of the mine; Multiple abnormal data are extracted from the multi-source heterogeneous data, and several safety hazard types are matched from a preset hazard list based on the change amplitude of the multiple abnormal data. The preset hazard list is a list of hazard types updated before construction on the same day. The K-means algorithm is called to cluster the multi-source heterogeneous data to obtain multiple heterogeneous categories, and the target category corresponding to each type of security hazard is determined from the multiple heterogeneous categories, wherein each heterogeneous category contains several heterogeneous data; The preset BP early warning model is invoked to determine the risk level value corresponding to each type of safety hazard based on the data contained in the target category, and a safety alarm is triggered based on the risk level value.
[0006] A mine safety alarm device based on multi-source heterogeneous data, the device comprising: The acquisition module is used to acquire multi-source heterogeneous data from the mine, wherein the multi-source heterogeneous data is heterogeneous data collected by heterogeneous devices set up in different areas of the mine; The type determination module is used to extract multiple abnormal data from the multi-source heterogeneous data, and match several safety hazard types from a preset hazard list based on the change amplitude of the multiple abnormal data, wherein the preset hazard list is a list of hazard types updated before construction on the same day; The category determination module is used to call the K-means algorithm to perform clustering processing on the multi-source heterogeneous data to obtain multiple heterogeneous categories, and to determine the target category corresponding to each type of security hazard from the multiple heterogeneous categories, wherein each heterogeneous category contains several heterogeneous data; The alarm module is used to call the preset BP early warning model to determine the risk level value corresponding to each type of safety hazard based on the data contained in the target category, and to trigger safety alarm processing based on the risk level value.
[0007] A mine safety alarm system based on multi-source heterogeneous data is disclosed. The system includes a central control platform and multiple heterogeneous devices, wherein the central control platform is communicatively connected to the multiple heterogeneous devices. The central control platform is applicable to the mine safety alarm method based on multi-source heterogeneous data as described above.
[0008] An apparatus includes a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program, when executed by the processor, implements the steps described above for mine safety alarms based on multi-source heterogeneous data.
[0009] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps described above for mine safety alarms based on multi-source heterogeneous data.
[0010] This application has the following advantages: In the embodiments of this application, the application can acquire multi-source heterogeneous data from the mine; extract multiple abnormal data from the multi-source heterogeneous data, and match several safety hazard types from a preset hazard list based on the change amplitude of the multiple abnormal data; call the K-means algorithm to perform clustering processing on the multi-source heterogeneous data to obtain multiple heterogeneous categories, and determine the target category corresponding to each safety hazard type from the multiple heterogeneous categories, wherein each heterogeneous category contains several heterogeneous data; call a preset BP early warning model to determine the risk level value corresponding to each safety hazard type based on the data contained in the target category, and trigger safety alarm processing based on the risk level value. This application can acquire different data, match real-time data with the hazard types determined before construction each day, determine the potential hazard risks for the day, and then perform risk assessments for different hazards. When any one of the risks is high, an alarm is triggered; by combining multiple data to assess multiple hazards simultaneously, the monitoring range can be increased, monitoring blind spots and omissions can be reduced, and safety risks can be detected earlier, alarm delays can be shortened, thereby improving the safety of construction. Attached Figure Description
[0011] To more clearly illustrate the technical solution of this application, the drawings used in the description of this application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0012] Figure 1 This is a flowchart illustrating the steps of a mine safety alarm method based on multi-source heterogeneous data, provided in one embodiment of this application. Figure 2 This is a structural block diagram of a mine safety alarm device based on multi-source heterogeneous data provided in one embodiment of this application; Figure 3 This is a structural block diagram of a mine safety alarm system based on multi-source heterogeneous data provided in one embodiment of this application; Figure 4 This is a schematic diagram of the structure of a computer device provided in one embodiment of this application. Detailed Implementation
[0013] To make the objectives, features, and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.
[0014] With the continuous promotion and application of new coal mine production technologies and the continuous improvement of management levels, the comprehensive monitoring level of mine production and safety is also improving. Therefore, in addition to considering accelerating the speed and efficiency of certain stages of the production process, it is also necessary to conduct on-site safety monitoring and alarms to achieve real-time and accurate supervision of high-risk production lines and key areas, thereby ensuring the safety of workers.
[0015] To monitor high-risk areas in real time and ensure the safety of on-site personnel, one common method is to install monitoring equipment (such as cameras) at different construction sites or high-risk areas to collect monitoring images of construction workers and transmit them to a central control platform. The central control platform uses image recognition models (such as tiny-YOLOv3 or yolov7) to identify the construction behavior of construction workers and the characteristics of objects in the construction area. Based on the construction behavior and object characteristics, a safety risk estimate is calculated. When the safety risk estimate is high, a safety alarm is triggered to improve the evacuation of construction workers.
[0016] However, currently used methods have the following technical problems: During mining and construction, safety hazards are easily overlooked due to non-standard engineering operations or negligence. These hazards often lead to accidents at some point afterward (such as ground collapse, gas leaks, or explosions). Furthermore, various safety accidents often occur instantaneously, and existing technical solutions are insufficient to monitor potential safety hazards. Not only is the monitoring range small and prone to omissions, but alarms are also often triggered only after identifying the characteristics of high-risk accidents, resulting in delays and low timeliness.
[0017] To solve the above technical problems, refer to Figure 1 The diagram shows a flowchart of the steps of a mine safety alarm method based on multi-source heterogeneous data provided in an embodiment of this application. In one embodiment, the mine safety alarm method based on multi-source heterogeneous data is applicable to a central control platform, which can be located in the management backend or the monitoring room of the mine construction site. The central control platform can communicate with multiple different heterogeneous devices. Heterogeneous devices refer to network devices of different types, manufacturers, and protocols used in the heterogeneous network of the central control platform. These may include different sensors and detectors.
[0018] Different heterogeneous devices can be installed in various locations at mining construction sites, such as mine shaft supports, on-site equipment, and workers' helmets. Data from these different devices can be acquired in real time through a central control platform, allowing for the collection of heterogeneous data from multiple sources. By simultaneously monitoring and detecting different heterogeneous data, potentially overlooked items or areas can be identified, thus broadening the scope of monitoring and reducing omissions. Furthermore, combining multiple data points improves the accuracy of detection.
[0019] As an example, the mine safety alarm method based on multi-source heterogeneous data may include: S11. Obtain multi-source heterogeneous data of the mine, wherein the multi-source heterogeneous data is heterogeneous data collected by heterogeneous devices set up in different areas of the mine.
[0020] In one embodiment, each heterogeneous device can transmit its detection and monitoring data to the central control platform in real time, and the central control platform can obtain multi-source heterogeneous data of the mine.
[0021] For example, heterogeneous devices can be cameras. The cameras are mounted on supports in the mine shaft and can transmit monitoring images to the central control platform, which can then obtain the first type of multi-source heterogeneous data.
[0022] For example, a heterogeneous device could be a gas sensor that can convert the volume fraction of a certain gas in the mine into a corresponding electrical signal and transmit the corresponding electrical signal to the central control platform, which can then obtain a second type of multi-source heterogeneous data.
[0023] For example, a heterogeneous device could be a temperature sensor that can transmit temperature data from inside the mine to the central control platform, which can then obtain a third type of multi-source heterogeneous data.
[0024] For example, a heterogeneous device could be a pressure sensor that can transmit pressure data from inside the mine to the central control platform, which can then obtain a fourth type of multi-source heterogeneous data.
[0025] For example, heterogeneous equipment could be a hydraulic support test bench, which can transmit the detection data of each support in the mine to the central control platform, allowing the central control platform to obtain a fifth type of multi-source heterogeneous data.
[0026] Different devices can collect different data, which the central control platform can then monitor and process to determine if there are any safety risks. If there are branch lines, early warnings or alarms can be issued to ensure the safety of construction personnel.
[0027] S12. Extract multiple abnormal data from the multi-source heterogeneous data, and match several safety hazard types from a preset hazard list based on the abnormal values of the multiple abnormal data, wherein the preset hazard list is a list of hazard types updated before construction on the same day.
[0028] Under normal circumstances, the values or data detected by various heterogeneous devices will fall within a certain range or remain at a fixed value. If the data fluctuates or deviates, the mine under construction may exhibit abnormalities. For example, if the pressure sensor detects a higher pressure value, the mine may have abnormal air pressure. Similarly, if the hydraulic support test bench detects higher values, the mine may be at risk of collapse. Furthermore, if the gas sensor detects a deviated gas value, the mine may be at risk of gas leakage.
[0029] Therefore, one or more anomalous data can be extracted from multi-source heterogeneous data, specifically anomalous values or anomalous images.
[0030] Next, several safety hazard types can be matched from a preset hazard list based on the abnormal values of one or more abnormal data.
[0031] As explained above, there are multiple heterogeneous devices. Correspondingly, multi-source heterogeneous data can include heterogeneous data from multiple different sources, and each type of heterogeneous data can correspond to one device. One security vulnerability may correspond to one type of heterogeneous data, or it may correspond to multiple types of heterogeneous data. One or more security vulnerability types can be obtained by matching the abnormal values of one or more abnormal data, and each security vulnerability type corresponds to one security vulnerability.
[0032] For example, in the case of a gas leak safety hazard, the gas sensor detects inaccurate gas values, and the pressure sensor detects inaccurate pressure values. Similarly, in the case of a fire safety hazard, the temperature sensor detects inaccurate temperature values, and the monitoring footage shows a heat source. And in the case of a collapse safety hazard, the hydraulic support test bench detects abnormal values.
[0033] In one embodiment, multiple types of safety hazards can be pre-determined, and a preset hazard list can be constructed using these hazard types. Then, the corresponding safety hazard type is matched from the preset hazard list. Since there are various types of safety hazards that may exist in a mine, recording each type in the list would require many matching items, increasing processing time and consequently delaying alarms. Therefore, the preset hazard list is a list of hazard types updated before construction begins each day. Specifically, before construction begins each day, multiple types of safety hazards that may exist that day can be statistically analyzed and input into the central control platform. The central control platform can then construct and update the preset hazard list for the day based on these multiple safety hazard types.
[0034] There may be three safety hazards in the mine shaft or mine site under construction. The first and second hazards may occur on the same day, and the third hazard may have been eliminated after yesterday's alarm. The first and second safety hazards can be used to build and update the preset hazard list for the day.
[0035] In an optional embodiment, the step of matching several safety hazard types from a preset hazard list based on the abnormal values of the multiple abnormal data may include the following sub-steps: S121. Based on the abnormal value of each of the abnormal data, select several target data from the multiple abnormal data, wherein the target data is data whose abnormal value is greater than the corresponding change threshold.
[0036] S122. Extract the data label of each target data and extract several type labels corresponding to each hazard type in the preset hazard list.
[0037] S123. Select the tags that are the same as the type tags from the data tags and count the number of tags to obtain the number of identical tags.
[0038] S124. Determine the type of potential hazard as having a number of identical labels greater than a preset number.
[0039] In one operational method, the value of each heterogeneous data point can be compared with its corresponding normal value or range value. If the value of the heterogeneous data point is different from its corresponding normal value or is not within its corresponding range value, the heterogeneous data point is determined to be abnormal data. Then, the value of each abnormal data point can be obtained, and the difference between that value and the endpoints of its corresponding normal value or range value can be calculated to obtain the abnormal value.
[0040] Next, it can be determined whether the abnormal value is greater than the preset value. If the abnormal value is greater than the preset change threshold, it means that the heterogeneous data deviation is large and there may be an anomaly. The heterogeneous data with the abnormal value greater than the preset value can be identified as the target data. Conversely, if the abnormal value is less than the preset value, it means that the heterogeneous data deviation is small and may only be caused by construction or different factors that cause the data collected by the heterogeneous equipment to deviate. The heterogeneous data with the abnormal value less than the preset value can be eliminated.
[0041] Then, data tags can be extracted for each target data point. These tags can be tags for heterogeneous devices, and several type tags corresponding to each hazard type can be obtained from a pre-set hazard list. Each hazard type can correspond to one or more type tags. For example, referring to the example above, the gas leak safety hazard type requires two types of data, which can correspond to two type tags. Referring again to the example above, the collapse safety hazard type requires data from a hydraulic support test bench, which can correspond to one category tag.
[0042] Next, you can filter data tags that match the type tag from several data tags, and then count the number of data tags to get the number of identical tags. If the number of identical tags is determined to be equal to the preset number, then the hazard type is identified as the safety hazard type.
[0043] For example, there are 3 type labels for hazard type A, and the preset quantity is 3; there are 2 type labels for hazard type B, and the preset quantity is 2; there are 2 type labels for hazard type C, and the preset quantity is 2; there are 4 type labels for hazard type D, and the preset quantity is 4.
[0044] Ten data tags were obtained. Among the ten data tags, three type tags corresponded to safety hazard type A. The number of identical tags was 3, which is equal to the preset number of 3. Therefore, it can be determined that hazard type A is a safety hazard type.
[0045] Among the 10 data labels, there is 1 type label corresponding to safety hazard type B. The number of identical labels is 1, which is not equal to the preset number of 2. Therefore, it can be determined that hazard type B is not a safety hazard type.
[0046] Among the 10 data labels, there are 2 type labels that correspond to the C safety hazard type. The number of identical labels is 2, which is equal to the preset number of 2. Therefore, the C hazard type can be identified as a safety hazard type.
[0047] Among the 10 data labels, there are 3 type labels corresponding to safety hazard type D. The number of identical labels is 3, which is not equal to the preset number of 4. Therefore, it can be determined that hazard type D is not a safety hazard type.
[0048] S13. The K-means algorithm is called to perform clustering processing on the multi-source heterogeneous data to obtain multiple heterogeneous categories, and the target category corresponding to each type of security hazard is determined from the multiple heterogeneous categories, wherein each heterogeneous category contains several heterogeneous data.
[0049] Since multi-source heterogeneous data can be diverse, with each type of heterogeneous data potentially containing one or more data points, and the resulting safety hazard types can also be varied, the K-means algorithm can be used to cluster the multi-source heterogeneous data, resulting in multiple heterogeneous categories. Each category contains several heterogeneous data points. Then, the categories corresponding to each safety hazard type are selected from these categories, yielding one or more target categories for each safety hazard type. This allows for the selection of heterogeneous data for each safety hazard type from multiple datasets, facilitating subsequent analysis.
[0050] For example, in the above case, we determine safety hazard type A and safety hazard type C. Let's assume that safety hazard type A is a gas leak safety hazard type and safety hazard type C is a mine collapse safety hazard type.
[0051] If there are 3 type labels corresponding to safety hazard type A, then heterogeneous data of three different categories is required; similarly, if there are 2 type labels corresponding to safety hazard type C, then heterogeneous data of two different categories is required.
[0052] After clustering is completed, three target categories corresponding to safety hazard type A can be determined from multiple heterogeneous categories, and two target categories corresponding to safety hazard type C can be determined from multiple heterogeneous categories.
[0053] In one embodiment, determining the target category corresponding to each of the multiple heterogeneous categories may include the following sub-steps: S131. Using several type labels corresponding to each of the aforementioned safety hazard types, calculate the matching degree between the safety hazard type and each of the heterogeneous categories.
[0054] S132. Select target matching degrees that meet the matching threshold from multiple matching degrees, and take the heterogeneous category of the target matching degree as the target category.
[0055] In one embodiment, since each type of security hazard can correspond to one or more type labels, several type labels corresponding to each type of security hazard can be used to calculate the matching degree between the security hazard type and each heterogeneous category; Then, select the target matching degree that meets the matching threshold from multiple matching degrees, and take the heterogeneous category of the target matching degree as the target category.
[0056] For example, the matching degree between the text of the type label and the category text after each heterogeneous category classification can be calculated.
[0057] As explained above, each heterogeneous data corresponds to a heterogeneous device, each heterogeneous device corresponds to a data label, and after clustering, each heterogeneous category corresponds to a heterogeneous device. Any heterogeneous data can be obtained from the heterogeneous category, then the data label of the heterogeneous data can be obtained, and then the corresponding category can be matched according to the data label to obtain the target category.
[0058] It should be noted that since heterogeneous data is generally non-linear, the K-means algorithm used can be the kernel K-means algorithm. Specifically, this algorithm maps the data to a high-dimensional space using a kernel function, and then performs clustering in that high-dimensional space. In one embodiment, the kernel function (Radial Basis Function, RBF), also known as the Gaussian kernel function, is a kernel function with strong non-linear expressive power.
[0059] S14. Call the preset BP early warning model to determine the risk level value corresponding to each type of safety hazard based on the data contained in the target category, and trigger a safety alarm processing based on the risk level value.
[0060] In one embodiment, after obtaining the target category corresponding to each type of safety hazard, the data contained in the target category corresponding to each type of safety hazard can be input into a preset BP early warning model. The preset BP early warning model can perform risk prediction based on the data contained in the target category to obtain the risk level value corresponding to each type of safety hazard.
[0061] The preset BP early warning model can be a user-trained model, which can be a BP neural network. Specifically, it is trained and predicted through two stages: forward propagation and backward propagation. In the forward propagation stage, the input signal travels from the input layer through the hidden layers to the output layer; in the backward propagation stage, the weights and thresholds of each layer are adjusted based on the output error.
[0062] During training, historical risk event data of safety hazard types can be obtained as training samples. The data needs to be normalized and preprocessed before feature selection, and the extracted features are used for training.
[0063] In one embodiment, the risk level value output by the preset BP early warning model can be the occurrence probability value corresponding to each type of safety hazard. Then, based on the occurrence probability value and the type of safety hazard, the corresponding level value is calculated, and the safety alarm processing is triggered based on the corresponding level value.
[0064] In one embodiment, the type of safety hazard can be an internal collapse of the mine shaft. The deeper the mine shaft, the longer the evacuation time required; conversely, the shallower the mine shaft, the shorter the evacuation time required. Therefore, to allow sufficient time for the evacuation of construction workers, the risk level value can be determined based on the depth of the mine shaft.
[0065] As an example, the step of calling the preset BP early warning model to determine the risk level value corresponding to each type of safety hazard based on the data contained in the target category may include the following sub-steps: S21. If the safety hazard type is an internal collapse type, the data contained in the target category is input into the preset BP early warning model for evaluation and calculation to obtain the first hazard probability value.
[0066] S22. Determine the location of the heterogeneous equipment corresponding to the target category, and use the equipment location to calculate the mining distance value.
[0067] S23. Convert the mining distance value into a collapse weight value, and determine the risk level value using the first hidden danger probability value and the collapse weight value.
[0068] Specifically, if the safety hazard type is internal collapse, the data of the target category corresponding to the internal collapse type is input into a preset BP early warning model for evaluation and calculation to obtain a first hazard probability value. This first hazard probability value can be the probability value of a collapse predicted by the model. Next, the equipment location of the heterogeneous equipment corresponding to the target category can be obtained. This equipment location can be the equipment's location coordinates. Then, the coordinates of the starting point of the mine can be obtained, and the distance between the location coordinates and the starting point coordinates can be calculated to obtain the mining distance value. Finally, the mining distance value is converted into a collapse weight value, and the risk level value is calculated using the first hazard probability value and the collapse weight value.
[0069] As analyzed above, the deeper the mine, the longer the evacuation time; conversely, the shallower the mine, the shorter the evacuation time. Therefore, the greater the mining distance value, the greater the collapse weight value.
[0070] Alternatively, the conversion between mining distance values and collapse weight values can be expressed as follows: S = AY; Where S is the mining distance value, Y is the collapse weight value, and A is a positive integer greater than 1.
[0071] After converting the collapse weight value, the product of the first hidden danger probability value and the collapse weight value can be calculated to obtain the collapse product value. Then, the interval in which the collapse product value is located can be determined, and the risk level value can be determined based on the interval.
[0072] For example, consider multiple intervals, each 10 units apart. 0-10 is the first interval, 10-20 is the second, and so on, from 20 to N. 0-10 is level 1, 10-20 is level 2, and so on. The higher the risk level value, the greater the risk and the more serious the safety hazard. If the collapse product value is 15, and the interval is 10-20, the corresponding risk level value is 2.
[0073] In one embodiment, the safety hazard type can be a gas leak in the mine. The more gas leaked, the more serious the hazard; conversely, the less gas leaked, the less serious the hazard. Therefore, a risk level value can be determined based on the gas concentration.
[0074] As an example, the step of calling the preset BP early warning model to determine the risk level value corresponding to each type of safety hazard based on the data contained in the target category may include the following sub-steps: S31. If the safety hazard type is a gas leak, the data contained in the target category is input into the preset BP early warning model for evaluation and calculation to obtain the second hazard probability value.
[0075] S32. Count the number of data for the target category corresponding to the gas leakage type to obtain the data quantity value.
[0076] S33. Convert the data quantity value into a leakage weight value, and use the second hidden danger probability value and the leakage weight value to determine the risk level value.
[0077] If the safety hazard type is gas leak, the data from the target category corresponding to the gas leak type can be input into a preset BP early warning model for evaluation and calculation to obtain a second hazard probability value. This second hazard probability value can be the probability value of a gas leak predicted by the model. Next, the number of data points for the target category corresponding to the gas leak type can be counted to obtain a data quantity value. For example, in the above example, there are two target categories corresponding to the gas leak type; the first target category has 60 data points, and the second target category has 40 data points, for a total of 100 data points, resulting in a data quantity value of 100.
[0078] The data quantity value can be converted into a leakage weight value, and then the risk level value can be calculated using the second hidden danger probability value and the leakage weight value.
[0079] Optionally, the conversion between the data quantity value and the leakage weight value can be represented by the following formula: L=BC; Where C is the data quantity value, L is the leakage weight value, and B is a positive number greater than 0 and less than 1.
[0080] After converting the leakage weight value, the product of the second hidden danger probability value and the leakage weight value can be calculated to obtain the leakage product value. Then, the interval in which the leakage product value is located can be determined, and the risk level value can be determined based on the interval.
[0081] Referring to the example above, multiple intervals can also be set, with intervals of 20. 0-20 is the first interval, 20-40 is the second interval, and so on, from 40 to N. 0-20 is level 1, 20-40 is level 2, and so on. The higher the risk level value, the greater the risk and the more serious the safety hazard. If the leakage product value is 46, and the interval is 40-60, the corresponding risk level value is 3.
[0082] To handle security alarms differently based on risk levels, the step of triggering a security alarm based on the risk level value, as an example, may include the following sub-steps: S41. Determine the risk level value, find the corresponding alarm information, and perform alarm processing based on the alarm information.
[0083] Different risk level values correspond to different alarm messages. You can find the corresponding alarm message based on the risk level value and then play the alarm message for alarm processing.
[0084] For example, if the risk level is 1, the alarm information could be a warning broadcast, which would remind construction workers to pay attention. The risk level is 2. The alarm information can be a real-time audit alarm broadcast, a work suspension warning, or a prompt for back-end personnel to take emergency measures. The risk level is 3. Notify the construction personnel to activate the emergency response, such as cutting off the power to the equipment and arranging evacuation.
[0085] In one embodiment, since there may be multiple types of safety hazards, one or more of them may pose a risk, or none of them may pose a safety risk.
[0086] Therefore, after determining the risk level value for each type of safety hazard, the corresponding alarm information is searched based on the risk level value for each type of safety hazard before the alarm is triggered.
[0087] Referring to the above example, assuming there are two types of safety hazards, a gas leak alarm can be played once, followed by a collapse alarm, so that construction workers know the actual situation of each hazard and can ensure the safety of each worker.
[0088] In this embodiment, the present application provides a mine safety alarm method based on multi-source heterogeneous data. Its advantages are as follows: the present application can acquire multi-source heterogeneous data from the mine; extract multiple abnormal data from the multi-source heterogeneous data, and match several safety hazard types from a preset hazard list based on the change amplitude of the multiple abnormal data; call the K-means algorithm to perform clustering processing on the multi-source heterogeneous data to obtain multiple heterogeneous categories, and determine the target category corresponding to each safety hazard type from the multiple heterogeneous categories, wherein each heterogeneous category contains several heterogeneous data; call a preset BP early warning model to determine the risk level value corresponding to each safety hazard type based on the data contained in the target category, and trigger safety alarm processing based on the risk level value. This application can acquire different data, match real-time data with the types of hazards identified before each day's construction, determine the potential hazards and risks for the day, and then conduct risk assessments for different hazards. When any hazard is high, an alarm is triggered. By combining multiple data to assess multiple hazards simultaneously, the monitoring range can be increased, blind spots and omissions can be reduced, and safety risks can be detected earlier, alarm delays can be shortened, and construction safety can be improved.
[0089] This application also provides a mine safety alarm device based on multi-source heterogeneous data. See [link to relevant documentation]. Figure 2 The diagram shows a structural schematic of a mine safety alarm device based on multi-source heterogeneous data according to an embodiment of this application.
[0090] As an example, the mine safety alarm device based on multi-source heterogeneous data may include: The acquisition module 201 is used to acquire multi-source heterogeneous data of the mine, wherein the multi-source heterogeneous data is heterogeneous data collected by heterogeneous devices set in different areas of the mine; The type determination module 202 is used to extract multiple abnormal data from the multi-source heterogeneous data, and match several safety hazard types from a preset hazard list according to the change amplitude of the multiple abnormal data, wherein the preset hazard list is a list of hazard types updated before construction on the same day; The category determination module 203 is used to call the K-means algorithm to perform clustering processing on the multi-source heterogeneous data to obtain multiple heterogeneous categories, and to determine the target category corresponding to each type of security hazard from the multiple heterogeneous categories, wherein each heterogeneous category contains several heterogeneous data; The alarm module 204 is used to call the preset BP early warning model to determine the risk level value corresponding to each type of safety hazard based on the data contained in the target category, and to trigger safety alarm processing based on the risk level value.
[0091] Optionally, the step of matching several safety hazard types from a preset hazard list based on the change amplitude of multiple abnormal data includes: Based on the abnormal value of each of the abnormal data, several target data are selected from the multiple abnormal data, wherein the target data is the data whose abnormal value is greater than the corresponding change threshold; Extract the data tags for each target data item, and extract several type tags corresponding to each hazard type in the preset hazard list; Filter out tags that are the same type of tags from a number of data tags and count the number of tags to obtain the number of identical tags; The type of potential hazard is defined as one in which the number of identical labels exceeds a preset number.
[0092] Optionally, determining the target category corresponding to each type of security hazard from the plurality of heterogeneous categories includes: Using several type labels corresponding to each of the aforementioned safety hazard types, the matching degree between the safety hazard type and each of the heterogeneous categories is calculated; Target matching degrees that meet the matching threshold are selected from multiple matching degrees, and the heterogeneous categories of the target matching degrees are used as the target categories.
[0093] Optionally, the step of calling the preset BP early warning model to determine the risk level value corresponding to each type of safety hazard based on the data contained in the target category includes: If the safety hazard type is internal collapse, the data contained in the target category is input into the preset BP early warning model for evaluation and calculation to obtain the first hazard probability value; Determine the location of the heterogeneous equipment corresponding to the target category, and calculate the mining distance value using the equipment location; The mining distance value is converted into a collapse weight value, and the risk level value is determined by using the first hazard probability value and the collapse weight value.
[0094] Optionally, the step of calling the preset BP early warning model to determine the risk level value corresponding to each type of safety hazard based on the data contained in the target category includes: If the safety hazard type is a gas leak, the data contained in the target category is input into a preset BP early warning model for evaluation and calculation to obtain a second hazard probability value; The number of data points corresponding to the target category for the gas leak type is counted to obtain the data quantity value; The data quantity value is converted into a leakage weight value, and the risk level value is determined by using the second hidden danger probability value and the leakage weight value.
[0095] Optionally, the step of triggering a security alarm based on the risk level value includes: Determine the risk level value, find the corresponding alarm information, and perform alarm processing based on the alarm information.
[0096] This application also provides a mine safety alarm system based on multi-source heterogeneous data. See [link to relevant documentation]. Figure 3 The diagram shows a structural schematic of a mine safety alarm system based on multi-source heterogeneous data according to an embodiment of this application.
[0097] As an example, the mine safety alarm system based on multi-source heterogeneous data may include: A central control platform and multiple heterogeneous devices, wherein the central control platform is communicatively connected to each of the multiple heterogeneous devices; The central control platform is applicable to the mine safety alarm method based on multi-source heterogeneous data as described in the above embodiments.
[0098] Reference Figure 4 The present application illustrates a computer device for a mine safety alarm method based on multi-source heterogeneous data, which may specifically include the following: The computer device 12 described above is in the form of a general-purpose computing device. The components of the computer device 12 may include, but are not limited to: one or more processors or processing units 16, system memory 28, and bus 18 connecting different system components (including system memory 28 and processing unit 16).
[0099] Bus 18 refers to one or more of several types of bus 18 architectures, including memory bus 18 or memory controller, peripheral bus 18, graphics acceleration port, processor, or local bus 18 using any of the various bus 18 architectures. For example, these architectures include, but are not limited to, Industry Standard Architecture (ISA) bus 18, Micro Channel Architecture (MAC) bus 18, Enhanced ISA bus 18, Audio / Video Electronics Standards Association (VESA) local bus 18, and Peripheral Component Interconnect (PCI) bus 18.
[0100] Computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by computer device 12, including volatile and non-volatile media, removable and non-removable media.
[0101] System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. Computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be used to read and write non-removable, non-volatile magnetic media (commonly referred to as a "hard disk drive"). Figure 3 As not shown, a disk drive for reading and writing to a removable non-volatile disk (such as a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk (such as a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 via one or more data media interfaces. The memory may include at least one program product having a set (e.g., at least one) of program modules 42 configured to perform the functions of the embodiments of this application.
[0102] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory. Such program modules 42 include—but are not limited to—an operating system, one or more application programs, other program modules 42, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 42 typically perform the functions and / or methods described in the embodiments of this application.
[0103] Computer device 12 can also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, camera, etc.), and with one or more devices that enable a user to interact with the computer device 12, and / or with any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed through input / output (I / O) interface 22. Furthermore, computer device 12 can also communicate with one or more networks (e.g., local area network (LAN)), wide area network (WAN), and / or public networks (e.g., the Internet) via network adapter 20. As shown, network adapter 20 communicates with other modules of computer device 12 via bus 18. It should be understood that, although... Figure 4 Not shown, it can be combined with computer device 12 to use other hardware and / or software modules, including but not limited to: microcode, device drivers, redundant processing unit 16, external disk drive array, RAID system, tape drive and data backup storage system 34, etc.
[0104] The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, such as implementing the mine safety alarm method based on multi-source heterogeneous data provided in the embodiments of this application.
[0105] That is, when the processing unit 16 executes the above program, it achieves the following: Acquire multi-source heterogeneous data from the mine, wherein the multi-source heterogeneous data is heterogeneous data collected by heterogeneous devices set up in different areas of the mine; Multiple abnormal data are extracted from the multi-source heterogeneous data, and several safety hazard types are matched from a preset hazard list based on the change amplitude of the multiple abnormal data. The preset hazard list is a list of hazard types updated before construction on the same day. The K-means algorithm is called to cluster the multi-source heterogeneous data to obtain multiple heterogeneous categories, and the target category corresponding to each type of security hazard is determined from the multiple heterogeneous categories, wherein each heterogeneous category contains several heterogeneous data; The preset BP early warning model is invoked to determine the risk level value corresponding to each type of safety hazard based on the data contained in the target category, and a safety alarm is triggered based on the risk level value.
[0106] In this application embodiment, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the mine safety alarm method based on multi-source heterogeneous data as provided in all embodiments of this application.
[0107] That is, to implement the following when the program is executed by the processor: Acquire multi-source heterogeneous data from the mine, wherein the multi-source heterogeneous data is heterogeneous data collected by heterogeneous devices set up in different areas of the mine; Multiple abnormal data are extracted from the multi-source heterogeneous data, and several safety hazard types are matched from a preset hazard list based on the change amplitude of the multiple abnormal data. The preset hazard list is a list of hazard types updated before construction on the same day. The K-means algorithm is called to cluster the multi-source heterogeneous data to obtain multiple heterogeneous categories, and the target category corresponding to each type of security hazard is determined from the multiple heterogeneous categories, wherein each heterogeneous category contains several heterogeneous data; The preset BP early warning model is invoked to determine the risk level value corresponding to each type of safety hazard based on the data contained in the target category, and a safety alarm is triggered based on the risk level value.
[0108] Any combination of one or more computer-readable media may be used. A computer-readable medium may be a computer-to-signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium that contains or stores a program that may be used by or in connection with an instruction execution system, apparatus, or device.
[0109] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including—but not limited to—electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of transmitting, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.
[0110] Computer program code for performing the operations of this application can be written in one or more programming languages or a combination thereof. These programming languages include object-oriented programming languages—such as Java, Smalltalk, and C++—and conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider). The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably.
[0111] Although preferred embodiments of the present application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present application.
[0112] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.
[0113] The above provides a detailed description of a mine safety alarm method, device, system, equipment, and medium based on multi-source heterogeneous data provided in this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and its core ideas. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.
Claims
1. A mine safety alarm method based on multi-source heterogeneous data, characterized in that, The method includes: Acquire multi-source heterogeneous data from the mine, wherein the multi-source heterogeneous data is heterogeneous data collected by heterogeneous devices set up in different areas of the mine; Multiple abnormal data are extracted from the multi-source heterogeneous data, and several safety hazard types are matched from a preset hazard list based on the change amplitude of the multiple abnormal data. The preset hazard list is a list of hazard types updated before construction on the same day. The K-means algorithm is called to cluster the multi-source heterogeneous data to obtain multiple heterogeneous categories, and the target category corresponding to each type of security hazard is determined from the multiple heterogeneous categories, wherein each heterogeneous category contains several heterogeneous data; The preset BP early warning model is invoked to determine the risk level value corresponding to each type of safety hazard based on the data contained in the target category, and a safety alarm is triggered based on the risk level value.
2. The mine safety alarm method based on multi-source heterogeneous data according to claim 1, characterized in that, The step involves matching several safety hazard types from a preset hazard list based on the magnitude of changes in multiple abnormal data points, including: Based on the abnormal value of each of the abnormal data, several target data are selected from the multiple abnormal data, wherein the target data is the data whose abnormal value is greater than the corresponding change threshold; Extract the data tags for each target data item, and extract several type tags corresponding to each hazard type in the preset hazard list; Filter out tags that are the same type of tags from a number of data tags and count the number of tags to obtain the number of identical tags; The type of potential hazard is defined as one in which the number of identical labels exceeds a preset number.
3. The mine safety alarm method based on multi-source heterogeneous data according to claim 2, characterized in that, The step of determining the target category corresponding to each type of security hazard from multiple heterogeneous categories includes: Using several type labels corresponding to each of the aforementioned safety hazard types, the matching degree between the safety hazard type and each of the heterogeneous categories is calculated; Target matching degrees that meet the matching threshold are selected from multiple matching degrees, and the heterogeneous categories of the target matching degrees are used as the target categories.
4. The mine safety alarm method based on multi-source heterogeneous data according to claim 1, characterized in that, The step of calling the preset BP early warning model to determine the risk level value corresponding to each type of safety hazard based on the data contained in the target category includes: If the safety hazard type is internal collapse, the data contained in the target category is input into the preset BP early warning model for evaluation and calculation to obtain the first hazard probability value; Determine the location of the heterogeneous equipment corresponding to the target category, and calculate the mining distance value using the equipment location; The mining distance value is converted into a collapse weight value, and the risk level value is determined by using the first hazard probability value and the collapse weight value.
5. The mine safety alarm method based on multi-source heterogeneous data according to claim 1, characterized in that, The step of calling the preset BP early warning model to determine the risk level value corresponding to each type of safety hazard based on the data contained in the target category includes: If the safety hazard type is a gas leak, the data contained in the target category is input into a preset BP early warning model for evaluation and calculation to obtain a second hazard probability value; The number of data points corresponding to the target category for the gas leak type is counted to obtain the data quantity value; The data quantity value is converted into a leakage weight value, and the risk level value is determined by using the second hidden danger probability value and the leakage weight value.
6. The mine safety alarm method based on multi-source heterogeneous data according to any one of claims 1-5, characterized in that, The process of triggering a security alarm based on the risk level value includes: Determine the risk level value, find the corresponding alarm information, and perform alarm processing based on the alarm information.
7. A mine safety alarm device based on multi-source heterogeneous data, characterized in that, The device includes: The acquisition module is used to acquire multi-source heterogeneous data from the mine, wherein the multi-source heterogeneous data is heterogeneous data collected by heterogeneous devices set up in different areas of the mine; The type determination module is used to extract multiple abnormal data from the multi-source heterogeneous data, and match several safety hazard types from a preset hazard list based on the change amplitude of the multiple abnormal data, wherein the preset hazard list is a list of hazard types updated before construction on the same day; The category determination module is used to call the K-means algorithm to perform clustering processing on the multi-source heterogeneous data to obtain multiple heterogeneous categories, and to determine the target category corresponding to each type of security hazard from the multiple heterogeneous categories, wherein each heterogeneous category contains several heterogeneous data; The alarm module is used to call the preset BP early warning model to determine the risk level value corresponding to each type of safety hazard based on the data contained in the target category, and to trigger safety alarm processing based on the risk level value.
8. A mine safety alarm system based on multi-source heterogeneous data, characterized in that, The system includes: a central control platform and multiple heterogeneous devices, wherein the central control platform is communicatively connected to the multiple heterogeneous devices respectively; The central control platform is applicable to the mine safety alarm method based on multi-source heterogeneous data as described in any one of claims 1-6.
9. An electronic device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, when the processor executes the computer program, it implements the mine safety alarm method based on multi-source heterogeneous data as described in any one of claims 1-6.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer-executable program, which is used to cause a computer to execute the mine safety alarm method based on multi-source heterogeneous data as described in any one of claims 1-6.