A coal mining environment perception system based on multi-sensor fusion

Abstract

The present invention relates to the field of environmental monitoring technology, and in particular to a coal mining environment perception system based on multi-sensor fusion, comprising a coal mining environment analysis module, an environment detection module, a regional analysis module, an environment perception module and a coal mining environment early warning module; the coal mining environment analysis module determines the coal mining environment to be perceived, and determines the functional type of each perception area; the environment detection module detects the detection information of each perception area; the regional analysis module determines the type of safety hazard in each area; the environment perception module determines the environment perception strategy according to the type of safety hazard in each perception area; the coal mining environment early warning module is used to issue early warning information; the present invention divides the coal mining area into multiple functional areas, and deploys corresponding sensors according to the characteristics and safety requirements of each area, so as to ensure the relevance and accuracy of monitoring data, and improve the pertinence of data collection and the accuracy of coal mining environment perception.

Description

Technical Field

[0001] The present invention relates to the technical field of environmental monitoring, and in particular to a coal mining environment perception system based on multi-sensor fusion. Background Art

[0002] With the continuous development of the coal industry, the safety and efficiency of coal mining operations have received more and more attention. Traditional coal mining environment monitoring methods often rely on a single type of sensor, which is inadequate in the changing mine environment. In addition, due to the functional differences between different areas in the mine, the use of a unified monitoring standard cannot accurately reflect the actual safety status of each area. Therefore, it is necessary to develop a more advanced monitoring system to achieve comprehensive perception and early warning of the coal mining environment.

[0003] Chinese Patent Publication No.: CN118466217A, discloses a coal mine energy intelligent control method and system based on deep learning and environmental perception, including: collecting data from the target mining area and preprocessing the data; using an exponent to describe the nonlinear process of gas accumulation, and quantifying it through integration, incorporating the cumulative effect of gas concentration into the environmental perception model, processing the data of the target mining area through an information filtering function, using logarithmic transformation to improve the modeling ability of nonlinear relationships, and enhancing the recognition of key environmental parameters through Gaussian weight adjustment to establish an environmental perception model; focusing on monitoring gas concentration and mining area water level, combining environmental perception models with key monitoring for dynamic safety control; analyzing equipment energy consumption patterns, and combining environmental perception models to achieve intelligent control and scheduling of energy; it can be seen that the coal mine energy intelligent control method and system based on deep learning and environmental perception have the following problems: it does not take into account that in actual situations, different safety standards in different areas of the mining area are different, and direct analysis leads to easy misjudgment. Summary of the invention

[0004] To this end, the present invention provides a coal mining environment perception system based on multi-sensor fusion, which is used to overcome the problem that the prior art does not take into account the different safety standards in different areas of the mining area in actual situations, and directly performs analysis, which leads to easy misjudgment.

[0005] To achieve the above objectives, the present invention provides a coal mining environment perception system based on multi-sensor fusion, comprising:

[0006] A coal mining environment analysis module, which is used to determine the complete coal mining environment to be sensed and determine the functional type of each sensing area;

[0007] An environment detection module, which is connected to the coal mining environment analysis module and is used to detect detection information of each of the sensing areas, wherein the detection information includes coal mining environment information and coal mining equipment information;

[0008] A regional analysis module, which is connected to the coal mining environment analysis module and the environmental detection module respectively, and is used to determine the type of safety hazard in each area according to the detection information;

[0009] An environmental perception module, which is respectively connected to the environmental detection module, the coal mining environment analysis module and the regional analysis module, is used to determine an environmental perception strategy according to the type of safety hazard in each perception area, including:

[0010] Acquire the coal mining equipment information, and determine whether there is an abnormality in the equipment within the sensing area according to the coal mining equipment information;

[0011] Or, under environmental safety conditions, obtain sensor detection data of other sensing areas with the same functional type and sensor detection data of the same type in the current sensing area to calculate the calibration coefficient, and calibrate the sensor according to the calibration coefficient;

[0012] The coal mining environment early warning module is respectively connected to the coal mining environment analysis module and the environment perception module, and is used to determine whether to issue an early warning according to the perception results of the environment perception module, and to send early warning information to the corresponding perception area.

[0013] Furthermore, the environment detection module includes:

[0014] A coal mining environment detection unit, comprising a first sensor group, for detecting the coal mining environment information in each sensing area;

[0015] A coal mining equipment detection unit, comprising a second sensor group, for detecting the coal mining equipment information in each sensing area;

[0016] The coal mining environment information includes harmful gas concentration, air flow velocity and dust concentration, and the coal mining equipment information includes equipment temperature and equipment vibration information.

[0017] Furthermore, in a single sensing area, the number of sensors collecting various types of detection information in the first sensor group and the second sensor group is not unique.

[0018] Furthermore, the area analysis module determines the potential safety hazard type of each area according to the detection information and the functional type of each perception area, including:

[0019] The area analysis module determines the safety standard corresponding to each of the perception areas according to the functional type of each of the perception areas;

[0020] Determine the type of potential safety hazard in each area according to the safety standard corresponding to each sensing area and the detection information of each sensing area;

[0021] If all detection information of a single perception area meets the corresponding safety standards, the safety hazard type of the current perception area is a hidden safety hazard type;

[0022] If the detection information of a single perception area does not meet the corresponding safety standards, the safety hazard type of the current perception area is an explicit safety hazard type.

[0023] Furthermore, the environmental perception module determines an environmental perception strategy according to the potential safety hazard type of each perception area, including:

[0024] If the current sensing area is of the hidden safety hazard type, its environmental sensing strategy is to obtain the coal mining equipment information and determine whether there is any abnormality in the equipment in the sensing area based on the coal mining equipment information;

[0025] If the current perception area is of an explicit safety hazard type, its environmental perception strategy is to obtain the sensor detection data of other perception areas of the same functional type and the sensor detection data of the same type in the current perception area under environmental safety conditions to calculate the calibration coefficient, and calibrate the sensor according to the calibration coefficient.

[0026] Furthermore, the environmental perception module determines whether there is an abnormality in the equipment in the perception area according to the coal mining equipment information, including:

[0027] The environment sensing module determines whether there is a temperature abnormality in the device in the area according to the device temperature;

[0028] The environment perception module determines the vibration stability of the device according to the device vibration information, and determines whether the device has an operating abnormality according to the device stability.

[0029] Furthermore, the environmental safety condition is that the number of sensors of the same type in the first sensor group of a single sensing area whose detection results exceed the corresponding standard does not exceed a safe number.

[0030] Further, the environment perception module obtains a first calibration factor by comparing the detection data of the sensors in the perception area of ​​the same functional type with the detection data of the sensors whose detection data exceeds the corresponding standard;

[0031] The environment perception module obtains a second calibration factor by comparing the detection data of the same type of sensor in the current perception area with the detection data of the sensor whose detection data exceeds the corresponding standard;

[0032] The environment sensing module determines the calibration coefficient according to an average value of the first calibration factor and the second calibration factor.

[0033] Furthermore, the coal mining environment early warning module determines whether to issue an early warning according to the perception result of the environment perception module.

[0034] If the environmental perception module determines that there is an abnormality in the equipment within the perception area or the perception area does not meet the environmental safety conditions, it determines to issue an early warning.

[0035] Furthermore, the coal mining environment early warning module sends early warning information to the corresponding sensing area, including:

[0036] The coal mining environment early warning module determines the type of perception area for which early warning information is to be issued, and issues early warning information in combination with the perception results for issuing early warnings.

[0037] Compared with the prior art, the beneficial effect of the present invention lies in that, by deploying multiple sensors in different functional areas, the present invention collects key data including coal mining environment perception in real time. The regional analysis module determines the type of safety hazard according to the safety standards and detection information of each area, and the environmental perception module adopts corresponding strategies according to the type of hazard, including equipment status monitoring and sensor calibration; the early warning module determines whether it is necessary to issue an early warning based on the perception results to ensure timely response to potential risks; the present invention realizes the refined management of the coal mine operating environment through a classified and regional monitoring method. The system divides the coal mining area into multiple functional areas and deploys corresponding sensors according to the characteristics and safety requirements of each area, thereby ensuring the relevance and accuracy of the monitoring data, improving the pertinence of data collection and the accuracy of coal mining environment perception, and enabling the system to adjust the monitoring plan according to the specific environment of each area. In addition, by setting different safety thresholds and response mechanisms, the system can more accurately identify and warn of potential risks and take preventive measures in time, thereby significantly improving the safety and environmental adaptability of coal mine operations.

[0038] Furthermore, in the present invention, the number of sensors of each type in a single sensing area is not unique, so that the monitoring scheme can be customized according to the actual environment and safety requirements. By deploying multiple sensors of the same type, the system not only improves the redundancy and accuracy of the data, but also enhances the real-time and fault-tolerance capabilities, ensuring the integrity and reliability of the monitoring data. In addition, this design also improves the adaptability and ease of maintenance of the system, allowing the sensor configuration to be adjusted according to the specific conditions of the mine, which improves the safety of mine operations. By increasing the monitoring points of key safety parameters, it can prevent and respond to potential dangerous situations in a timely manner, thereby providing a safer working environment.

[0039] Furthermore, in the present invention, the environmental perception module evaluates the equipment status by monitoring the temperature and vibration data of the equipment, and can identify abnormal temperature increases by comparing the real-time monitored equipment temperature with the average value of the historical normal operating temperature. At the same time, by analyzing the vibration audio loudness of the equipment in a continuous period of time under the same working state, calculating its average deviation, and comparing it with the standard of normal vibration stability, the vibration stability can be quantified. If the vibration stability exceeds the normal range, the system will determine that the equipment has an abnormal operation, thereby providing a basis for taking preventive measures, avoiding potential equipment failures and safety risks, and ensuring the continuity and safety of coal mining operations.

[0040] Furthermore, in the present invention, by comparing sensor data from different regions, the environmental perception module can enhance the accuracy and robustness of the calibration coefficients and reduce the impact of single sensor errors. This method uses multi-source data for cross-validation, which helps to identify and correct system deviations, thereby improving the reliability of the overall measurement. In addition, comprehensive data utilization and standardized calibration simplify the calibration process, reduce complexity, and ensure consistency. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a structural schematic diagram of a coal mining environment perception system based on multi-sensor fusion according to an embodiment of the present invention;

[0042] Figure 2 A logic diagram for determining the type of potential safety hazard in each area according to an embodiment of the present invention;

[0043] Figure 3 A logic diagram for determining whether there is an abnormality in a device within a sensing area according to an embodiment of the present invention;

[0044] Figure 4 A logic diagram for determining whether to issue an early warning according to an embodiment of the present invention. DETAILED DESCRIPTION

[0045] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0046] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0047] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0048] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0049] See also Figure 1 As shown, it is a structural schematic diagram of a coal mining environment perception system based on multi-sensor fusion according to an embodiment of the present invention; the present invention provides a coal mining environment perception system based on multi-sensor fusion, comprising:

[0050] A coal mining environment analysis module, which is used to determine the complete coal mining environment to be sensed and determine the functional type of each sensing area;

[0051] An environment detection module, which is connected to the coal mining environment analysis module and is used to detect detection information of each of the sensing areas, wherein the detection information includes coal mining environment information and coal mining equipment information;

[0052] A regional analysis module, which is connected to the coal mining environment analysis module and the environmental detection module respectively, and is used to determine the type of safety hazard in each area according to the detection information;

[0053] An environmental perception module, which is respectively connected to the environmental detection module, the coal mining environment analysis module and the regional analysis module, is used to determine an environmental perception strategy according to the type of safety hazard in each perception area, including:

[0054] Acquire the coal mining equipment information, and determine whether there is an abnormality in the equipment within the sensing area according to the coal mining equipment information;

[0055] Or, under environmental safety conditions, obtain sensor detection data of other sensing areas with the same functional type and sensor detection data of the same type in the current sensing area to calculate the calibration coefficient, and calibrate the sensor according to the calibration coefficient;

[0056] The coal mining environment early warning module is respectively connected to the coal mining environment analysis module and the environment perception module, and is used to determine whether to issue an early warning according to the perception results of the environment perception module, and to send early warning information to the corresponding perception area.

[0057] During implementation, the entire coal mining area is divided into several sensing areas according to the different functions of each area. The functional types of the sensing areas include operation areas, transportation and maintenance areas, safety areas, and ventilation areas.

[0058] The operating area is the area where coal mining is actually carried out, where equipment and workers are operating;

[0059] Haulage and Maintenance Area: An area used for hauling coal and other materials and for repairing and maintaining mine equipment, including conveyor belts, railroads, or coal mine tracks.

[0060] The safety zone is equipped with emergency shelters and safety equipment to ensure that workers have a safe place to evacuate in case of emergencies, as well as areas for miners to rest and live, including dormitories, canteens and other facilities.

[0061] Ventilation areas are areas specially designed to ventilate the mine to ensure air circulation and exhaust of harmful gases.

[0062] The present invention deploys multiple sensors in different functional areas to collect key data including coal mining environment perception in real time. The regional analysis module determines the type of safety hazard according to the safety standards and detection information of each area, and the environmental perception module adopts corresponding strategies according to the type of hazard, including equipment status monitoring and sensor calibration; the early warning module determines whether it is necessary to issue an early warning based on the perception results to ensure timely response to potential risks; the present invention realizes refined management of the coal mine operating environment through a classified and regional monitoring method. The system divides the coal mining area into multiple functional areas and deploys corresponding sensors according to the characteristics and safety requirements of each area, thereby ensuring the relevance and accuracy of the monitoring data, improving the pertinence of data collection and the accuracy of coal mining environment perception, and enabling the system to adjust the monitoring plan according to the specific environment of each area. In addition, by setting different safety thresholds and response mechanisms, the system can more accurately identify and warn of potential risks and take preventive measures in time, thereby significantly improving the safety and environmental adaptability of coal mine operations.

[0063] Specifically, the environment detection module includes:

[0064] A coal mining environment detection unit, comprising a first sensor group, for detecting the coal mining environment information in each sensing area;

[0065] A coal mining equipment detection unit, comprising a second sensor group, for detecting the coal mining equipment information in each sensing area;

[0066] The coal mining environment information includes harmful gas concentration, air flow velocity and dust concentration, and the coal mining equipment information includes equipment temperature and equipment vibration information.

[0067] In implementation, the first sensor group in the coal mining environment detection unit includes a dust concentration sensor: used to detect the dust concentration in the mine in real time to prevent the occurrence of dust explosions; a gas sensor: used to monitor the concentration of harmful gases in the mine, such as methane and carbon dioxide, to ensure the safety of workers, and a differential pressure flow meter: to determine the gas flow rate by measuring the pressure difference generated when the gas flows in the ventilation duct;

[0068] The second sensor group includes temperature and humidity sensors: used to monitor the temperature and humidity of the coal mining environment to ensure that the equipment operates under suitable environmental conditions to avoid equipment failure or reduced work efficiency due to inappropriate temperature or humidity, and vibration sensors: used to monitor the mechanical vibration of the coal mining machine and provide early warning of possible mechanical failures, such as gear wear or bearing failure.

[0069] Specifically, the number of sensors that collect various types of detection information in the first sensor group and the second sensor group within a single sensing area is not unique.

[0070] It is understandable that the number of sensors of each type in a single sensing area is not unique, so that the monitoring plan can be customized according to the actual environment and safety requirements. By deploying multiple sensors of the same type, the system not only improves the redundancy and accuracy of the data, but also enhances the real-time and fault-tolerance capabilities, ensuring the integrity and reliability of the monitoring data. In addition, this design also improves the adaptability and ease of maintenance of the system, allowing the sensor configuration to be adjusted according to the specific conditions of the mine. It improves the safety of mine operations and can prevent and respond to potential dangerous situations in a timely manner by increasing the monitoring points of key safety parameters, thereby providing a safer working environment.

[0071] See also Figure 2 As shown, it is a logic diagram for determining the safety hazard type of each area in an embodiment of the present invention. The area analysis module determines the safety hazard type of each area according to the detection information and the function type of each perception area, including:

[0072] The area analysis module determines the safety standard corresponding to each of the perception areas according to the functional type of each of the perception areas;

[0073] Determine the type of potential safety hazard in each area according to the safety standard corresponding to each sensing area and the detection information of each sensing area;

[0074] If all detection information of a single perception area meets the corresponding safety standards, the safety hazard type of the current perception area is a hidden safety hazard type;

[0075] If the detection information of a single perception area does not meet the corresponding safety standards, the safety hazard type of the current perception area is an explicit safety hazard type.

[0076] In implementation, the safety standards of each area are determined based on the functional type of the sensing area combined with the average value of each detection information without safety hazards in the historical detection data of each functional type;

[0077] In this implementation, the concentration standards for harmful gases are:

[0078] The working area generally requires that the concentration of harmful gases should be lower than the occupational exposure limit (such as CO, SO2, NO2 and methane, etc.), usually between a few ppm and tens of ppm, preferably 50ppm;

[0079] The standard in the transportation maintenance area usually needs to be lower than the standard in the operation area, preferably 10ppm;

[0080] The safety zone is usually required to be below the detection limit, for example, less than 1ppm;

[0081] The ventilation area should be well ventilated and the gas concentration should be maintained at a safe level, usually lower than the standard of the working area, preferably 5ppm.

[0082] The air velocity standards are:

[0083] The working area usually requires the air flow velocity to be between 0.5 and 2 m / s to ensure the dilution of harmful gases;

[0084] The transport maintenance area may have higher requirements for air flow velocity, usually between 1 and 3 m / s;

[0085] It is usually recommended that the safe area have a stable airflow, preferably 0.2-0.5m / s, to maintain air circulation to ensure air quality;

[0086] The air flow velocity in the ventilation area should be sufficient to achieve effective ventilation, usually between 2 and 4 m / s.

[0087] The dust concentration standards are:

[0088] The working area should not usually exceed the industry standard, preferably, the TWA (time weighted average) is 1mg / m³~10mg / m³;

[0089] The requirements for transportation maintenance areas are usually lower, preferably 0.5mg / m³ to 5mg / m³;

[0090] The safety zone should be controlled at a very low level as much as possible, usually below the detection limit, preferably less than 0.1 mg / m³;

[0091] The ventilation area should be kept below the standard of the working area to ensure that dust does not accumulate, preferably less than 1mg / m³.

[0092] All detection information of a single perception area meets the corresponding safety standards if the harmful gas concentration, airflow velocity and dust concentration are all lower than the corresponding standards. The detection information of a single perception area does not meet the corresponding safety standards if any one or more of the harmful gas concentration, airflow velocity and dust concentration in the perception area is greater than or equal to the corresponding standard value.

[0093] Specifically, the environment perception module determines the environment perception strategy according to the potential safety hazard type of each perception area, including:

[0094] If the current sensing area is of the hidden safety hazard type, its environmental sensing strategy is to obtain the coal mining equipment information and determine whether there is any abnormality in the equipment in the sensing area based on the coal mining equipment information;

[0095] If the current perception area is of an explicit safety hazard type, its environmental perception strategy is to obtain the sensor detection data of other perception areas of the same functional type and the sensor detection data of the same type in the current perception area under environmental safety conditions to calculate the calibration coefficient, and calibrate the sensor according to the calibration coefficient.

[0096] See also Figure 3 As shown, it is a logic diagram of judging whether there is an abnormality in the equipment in the sensing area according to an embodiment of the present invention. The environmental perception module judges whether there is an abnormality in the equipment in the sensing area according to the coal mining equipment information, including:

[0097] The environment sensing module determines whether there is a temperature abnormality in the device in the area according to the device temperature;

[0098] The environment perception module determines the vibration stability of the device according to the device vibration information, and determines whether the device has an operating abnormality according to the device stability.

[0099] In implementation, the vibration stability is obtained by comparing the average deviation of the vibration audio loudness of the detected device in several consecutive time periods under the same working state with the average value of all audio loudness.

[0100] If the device temperature exceeds the average device temperature under normal working conditions in the historical working records of the same working device, it is determined that the device has a temperature abnormality;

[0101] If the vibration stability of the equipment is greater than the standard vibration stability, it is judged that the equipment has an abnormal operation. The standard vibration stability is selected in the interval [0.2, 0.3].

[0102] The equipment is also equipped with current and voltage sensors and load sensors. The current and voltage sensors are used to monitor the electrical operating status of the equipment to ensure that problems can be discovered in time when the current and voltage change abnormally to avoid malfunctions. The load sensors are used to monitor the load conditions of the equipment to prevent overload operation.

[0103] In practice, the alarm information of the equipment includes:

[0104] The alarm information of the coal mining machine includes: left cutting temperature is too high, right cutting temperature is too high, left cutting overload, right cutting overload, left cutting reverse traction, right cutting reverse traction, left cutting serious overload shutdown, right cutting serious overload shutdown, left traction overload shutdown, right traction overload shutdown, transformer temperature abnormal shutdown, left cutting leakage, right cutting leakage, traction leakage, oil pressure abnormal signal, low pressure system oil pressure abnormal, left brake chamber oil pressure abnormal, right brake chamber oil pressure abnormal, high pressure system oil pressure abnormal;

[0105] The alarm information of the hydraulic support controller includes: main power supply voltage failure, mainboard power supply voltage failure, guardrail pressure sensor failure, column pressure sensor failure, infrared receiving sensor failure;

[0106] Scraper conveyor alarm information includes: overload alarm, low voltage alarm, transmission failure alarm, over-temperature alarm, abnormal operation alarm;

[0107] The alarm information of the transfer conveyor includes: overload alarm, equipment failure alarm, sensor abnormality alarm, and operation abnormality alarm;

[0108] The alarm information of crushing conveyor includes: overload, blockage, failure, abnormal temperature and abnormal vibration.

[0109] These temperature and vibration anomalies can be collected by sensors, and the temperature changes caused by overload and voltage anomalies can also be characterized by temperature sensors.

[0110] For the supports installed near the equipment, multiple sensors are also installed on the supports, including height sensors, inclination sensors, pressure sensors and position sensors; the height sensor measures the height changes of the supports in real time to ensure that the supports adjust their height in time according to the formation conditions to prevent the roof from collapsing; the inclination sensor monitors the inclination angle of the supports to prevent tilting or collapse due to uneven terrain or uneven force on the supports; the pressure sensor detects the pressure borne by the supports to ensure that the supports operate within a safe range and avoid instability of the supports due to excessive pressure; the position sensor monitors the position changes of the supports to prevent the supports from deviating from the designed position to ensure that they maintain correct positioning during the coal mining process.

[0111] During implementation, the stability of the support can be accurately judged by jointly analyzing the support inclination sensor data and the support pressure sensor data. During the mining process, the top plate of the working face is subjected to pressure, and the pressure of the top plate will be transmitted to the ground. At this time, according to the pressure change characteristics, it can be obtained: if the inclination angle of the base does not change, the inclination angle of the top beam changes, and the pressure sensor becomes larger, then the working pressure of the support increases; if the inclination angle of the base changes, the inclination angle of the top beam changes, the pressure does not change, and the support is pressed into the base; if the inclination angle changes, the pressure becomes smaller, and the pressure is transferred to the adjacent support or the rear collapse area.

[0112] By performing wavelet transform analysis on the inclination data, small inclination changes of the support can be identified:

[0113]

[0114] In the formula, is the wavelet transform coefficient, α is the scale parameter, b is the pressure parameter, is a wavelet function. Through wavelet transform, the system can analyze the slight changes in the tilt angle of the bracket and detect the risk of the bracket tipping in advance. The scale parameter is obtained through the tilt sensor, and the pressure parameter is obtained through the pressure sensor.

[0115] It can be understood that based on the center of gravity offset of the central position of the bracket model and the sudden change value of the pressure sensor, the large pressure caused by the sudden change in the center of gravity will cause the bracket to tip over. The allowable threshold for the bracket tilt change is determined based on historical data, which is 0.8 times the mean value of the bracket tilt change corresponding to the risk of tipping over.

[0116] In addition, an abnormal increase in equipment temperature may be caused by overload, poor heat dissipation or internal failure. If these situations are not discovered and handled in time, they may cause equipment damage or safety accidents. Vibration data reflects the mechanical dynamics of the equipment. An abnormal increase in vibration usually indicates wear, looseness or imbalance of mechanical parts, which may cause equipment performance degradation or failure.

[0117] In the present invention, the environmental perception module evaluates the equipment status by monitoring the temperature and vibration data of the equipment. By comparing the real-time monitored equipment temperature with the average value of the historical normal working temperature, the abnormal temperature rise can be identified. At the same time, by analyzing the vibration audio loudness of the equipment in a continuous time period under the same working state, calculating its average deviation, and comparing it with the standard of normal vibration stability, the stability of the vibration can be quantified. If the vibration stability exceeds the normal range, the system will determine that the equipment has an abnormal operation, thereby providing a basis for taking preventive measures, avoiding potential equipment failures and safety risks, and ensuring the continuity and safety of coal mining operations.

[0118] If the function type of the sensing area is a safe area, it is directly determined that there is no abnormality and no detection is performed.

[0119] Specifically, the environmental safety condition is that the number of sensors of the same type in the first sensor group of a single perception area whose detection results exceed the corresponding standard does not exceed a safe number.

[0120] In practice, the safe number is 2.

[0121] When the environmental safety conditions are not met, the prediction model is used to determine the predicted value of the next detection moment. The process of establishing the prediction model includes: collecting the sensor data of the equipment in real time through technologies such as the Internet of Things; processing the collected data to remove noise, fill in missing values, and standardize input features; using historical data to train machine learning models (such as linear regression, decision trees, deep learning, etc.) and fit various parameters; at runtime, the current sensor data is input into the model to output the health status or failure risk of the equipment. The prediction model is calculated using the following formula:

[0122]

[0123] formula, is the predicted value at the next moment, is the regression coefficient, is the input feature at the current moment, is an error term, which represents unpredictable factors or unknown noise in the model. This is a prior art and will not be described in detail.

[0124] When the predicted value reaches the set threshold, the system automatically sends out an early warning signal to notify equipment maintenance or overhaul.

[0125] Establishing a prediction model, predicting the detection value at the next moment according to the prediction model, and the system issuing a warning message are existing technologies and are not specifically limited here.

[0126] It is understandable that, when only one or two sensors have abnormal detection results for the same type of data in an area, it can be determined that the detection results of the sensors are inaccurate and calibration is required.

[0127] By deploying multiple sensors of the same type in key areas, the system achieves data redundancy. Even if one or two sensors fail or provide abnormal data, other sensors that are working properly can still provide accurate monitoring results, allowing a certain number of sensor abnormalities to enhance the system's fault tolerance. At the same time, by comparing the data of multiple sensors, the reliability of the data can be improved. The data of sensors that are working properly can verify each other and provide more accurate environmental conditions.

[0128] Specifically, the environment perception module obtains a first calibration factor by comparing detection data of sensors in the perception area of ​​the same functional type with detection data of sensors whose detection data exceeds a corresponding standard;

[0129] The environment perception module obtains a second calibration factor by comparing the detection data of the same type of sensor in the current perception area with the detection data of the sensor whose detection data exceeds the corresponding standard;

[0130] The environment sensing module determines the calibration coefficient according to an average value of the first calibration factor and the second calibration factor.

[0131] In implementation, when determining the first calibration factor, sensors in the sensing area of ​​the same functional type and sensors whose detection data exceeds the corresponding standard are sensors of the same type, that is, the detected data and units are the same; similarly, when determining the second calibration factor, the sensor type is also the same.

[0132] In the present invention, by comparing sensor data from different areas, the environmental perception module can enhance the accuracy and robustness of the calibration coefficient and reduce the impact of single sensor errors. This method uses multi-source data for cross-validation, which helps to identify and correct system deviations, thereby improving the reliability of the overall measurement. In addition, comprehensive data utilization and standardized calibration simplify the calibration process, reduce complexity, and ensure consistency.

[0133] See also Figure 4 As shown, it is a logic diagram for determining whether to issue an early warning according to an embodiment of the present invention. The coal mining environment early warning module determines whether to issue an early warning according to the perception result of the environment perception module.

[0134] If the environmental perception module determines that there is an abnormality in the equipment within the perception area or the perception area does not meet the environmental safety conditions, it determines to issue an early warning.

[0135] In implementation, the environment sensing module determines that there is an abnormality in the equipment in the sensing area as at least one of a temperature abnormality and an operating abnormality in the equipment in the current area.

[0136] Specifically, the coal mining environment early warning module sends early warning information to the corresponding sensing area, including:

[0137] The coal mining environment early warning module determines the type of perception area for which early warning information is to be issued, and issues early warning information in combination with the perception results for issuing early warnings.

[0138] In this implementation, the state of the device is determined by the DS fusion algorithm, and the process of generating the final state trust by the DS fusion algorithm includes: obtaining initial trust data, including the alarm and sensor readings of the device; conflict calculation function; determining the DS synthesis function; obtaining the multi-sensor and alarm data fusion function; integrating the sensor and alarm data as a whole, and integrating the sensor and alarm trust to obtain the final prediction result;

[0139] Each sensor and alarm signal is used to determine the trustworthiness of the three states of "normal", "warning" and "fault" based on its value. For example:

[0140] Trust of the temperature sensor: If the temperature is within the normal range, the “normal” trust is high; if it exceeds the threshold, the “fault” trust increases.

[0141] Trust of the current sensor: If the current value is within the normal range, the “normal” trust is high; if it is overloaded or abnormal, the “fault” trust is high.

[0142] The DS fusion formula is as follows:

[0143]

[0144] in, The fusion state The degree of trust, and is the trust of sensors A and B for different states, is the conflict degree, which is used to measure the inconsistency of trust between sensors, that is, the conflict between different sensor data.

[0145] Conflict The calculation formula is as follows:

[0146]

[0147] The fusion formula for each data obtained by using the DS fusion algorithm is a prior art and will not be described in detail here.

[0148] If the normal output result is greater than 0.6, the device status is normal. If the warning output result is greater than 0.4, the warning is triggered. If the output result of the fault status is greater than 0.6;

[0149] For example, for coal mining machine fault prediction, coal mining machine sensors include left traction current, right traction current, left cutting current, right cutting current, left cutting temperature, right cutting temperature, oil pump motor current, left and right traction motor temperature, oil pump temperature / hydraulic oil tank temperature, hydraulic oil tank level, gas concentration / dust concentration, head scraper load (current A), tail scraper load (current A), conveyor load (current A), and coal mining machine inertial navigation, including roll angle, pitch angle, azimuth angle, accelerometer X, accelerometer Y, accelerometer Z, gyroscope X, gyroscope Y, gyroscope Z, spatial position X, spatial position Y, spatial position and inertial navigation time;

[0150] The above parameters are named x1-xn, and each has a custom coefficient according to the situation. The sum of all coefficients is not equal to 100%. An error coefficient is adjusted to 100%, and then the fault level line is determined. For example, when the prediction result is greater than 60, it is determined that there is a high probability of a fault, and a level 1 alarm is output; when the prediction result is greater than 75 points, a level 2 alarm is output, and when the prediction result is greater than 90 points, a level 3 alarm is output.

[0151] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0152] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A coal mining environment perception system based on multi-sensor fusion, characterized in that: include: A coal mining environment analysis module is used to determine the complete coal mining environment to be sensed and determine the functional type of each sensing area; wherein the complete coal mining area is divided into several sensing areas according to the different functions of each area, and the functional types of the sensing areas include the operating area, the transportation and maintenance area, the safety area, and the ventilation area; An environment detection module, which is connected to the coal mining environment analysis module and is used to detect detection information of each of the sensing areas, wherein the detection information includes coal mining environment information and coal mining equipment information; A regional analysis module, which is connected to the coal mining environment analysis module and the environmental detection module respectively, and is used to determine the type of safety hazard in each area according to the detection information; Wherein, the regional analysis module determines the safety standard corresponding to each of the perception areas according to the functional type of each of the perception areas; Determine the type of potential safety hazard in each area according to the safety standard corresponding to each sensing area and the detection information of each sensing area; If all detection information of a single perception area meets the corresponding safety standards, the safety hazard type of the current perception area is a hidden safety hazard type; If the detection information of a single perception area does not meet the corresponding safety standard, the safety hazard type of the current perception area is an explicit safety hazard type; An environmental perception module, which is respectively connected to the environmental detection module, the coal mining environment analysis module and the regional analysis module, is used to determine an environmental perception strategy according to the type of safety hazard in each perception area, including: If the current sensing area is of the hidden safety hazard type, its environmental sensing strategy is to obtain the coal mining equipment information and determine whether there is any abnormality in the equipment in the sensing area based on the coal mining equipment information; If the current perception area is of the type of explicit safety hazard, its environmental perception strategy is to obtain the sensor detection data of other perception areas of the same functional type and the detection data of the same type of sensors in the current perception area under environmental safety conditions to calculate the calibration coefficient, and calibrate the sensor according to the calibration coefficient; The coal mining environment early warning module is respectively connected to the coal mining environment analysis module and the environment perception module, and is used to determine whether to issue an early warning according to the perception results of the environment perception module, and to send early warning information to the corresponding perception area.

2. The coal mining environment perception system based on multi-sensor fusion according to claim 1 is characterized in that: The environment detection module comprises: A coal mining environment detection unit, comprising a first sensor group, for detecting the coal mining environment information in each sensing area; A coal mining equipment detection unit, comprising a second sensor group, for detecting the coal mining equipment information in each sensing area; The coal mining environment information includes harmful gas concentration, air flow velocity and dust concentration, and the coal mining equipment information includes equipment temperature and equipment vibration information.

3. The coal mining environment perception system based on multi-sensor fusion according to claim 2 is characterized in that: In a single sensing area, the number of sensors that collect various types of detection information in the first sensor group and the second sensor group is not unique.

4. The coal mining environment perception system based on multi-sensor fusion according to claim 3 is characterized in that: The environmental perception module determines whether there is an abnormality in the equipment in the perception area according to the coal mining equipment information, including: The environment sensing module determines whether there is a temperature abnormality in the device in the area according to the device temperature; The environment perception module determines the vibration stability of the device according to the device vibration information, and determines whether the device has an operating abnormality according to the device stability.

5. The coal mining environment perception system based on multi-sensor fusion according to claim 4 is characterized in that: The environmental safety condition is that the number of sensors of the same type in the first sensor group of a single sensing area whose detection results exceed the corresponding standard does not exceed a safe number.

6. The coal mining environment perception system based on multi-sensor fusion according to claim 5 is characterized in that: The environment perception module obtains a first calibration factor by comparing the detection data of the sensor in the perception area of ​​the same functional type with the detection data of the sensor whose detection data exceeds the corresponding standard; The environment perception module obtains a second calibration factor by comparing the detection data of the same type of sensor in the current perception area with the detection data of the sensor whose detection data exceeds the corresponding standard; The environment sensing module determines the calibration coefficient according to an average value of the first calibration factor and the second calibration factor.

7. The coal mining environment perception system based on multi-sensor fusion according to claim 6 is characterized in that: The coal mining environment early warning module determines whether to issue an early warning based on the perception result of the environment perception module. If the environmental perception module determines that there is an abnormality in the equipment within the perception area or the perception area does not meet the environmental safety conditions, it determines to issue an early warning.

8. The coal mining environment perception system based on multi-sensor fusion according to claim 7 is characterized in that: The coal mining environment early warning module sends early warning information to the corresponding sensing area, including: The coal mining environment early warning module determines the type of perception area for which early warning information is to be issued, and issues early warning information in combination with the perception results for issuing early warnings.

Images