Abnormal data monitoring method and system of coal mine informatization system

Abstract

The invention relates to the technical field of data processing, in particular to an abnormal data monitoring method and system of a coal mine informatization system. The method comprises the following steps: acquiring content data and image brightness data of various gases in a coal mine; respectively carrying out data processing on the various gas content data and the image brightness data to obtain monitoring gas information and monitoring image information; determining the maximum slope of the difference value between the monitored gas information and the preset gas value, and the brightness change rate in the monitored image information and the preset image information; determining a proportionality coefficient based on the difference value maximum slope and the brightness change rate; and comparing the proportionality coefficient with a preset monitoring coefficient to obtain abnormal data in the coal mine. The invention aims to solve the problem that abnormal data is difficult to accurately monitor due to the fact that dust is raised in air and gas circulation in a mine is blocked in the mine operation process.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to an abnormal data monitoring method and system of a coal mine informatization system. BACKGROUND

[0002] Coal mine informatization is a technology system that builds an automated and intelligent coal mine operation by collecting, transmitting, processing and integrating mine geographic, production, safety and equipment data. It aims to optimize production processes and improve safety management efficiency. The coal mine informatization system is mainly used to monitor various environments and equipment states in the coal mine, such as timely alarm or power-off control when the concentration of gas exceeds the monitoring limit, which plays a great role in preventing and reducing coal mine safety accidents.

[0003] At present, the existing coal mine informatization system based on abnormal data in the coal mine can realize power-off alarm function. However, in the mining process, the mine may be humid, dust appears in the air during mine operation, gas circulation in the mine is blocked, and the gas collection sensor is easily blocked by dust or soil and other foreign matters, which increases the difficulty of judging abnormal data. When the gas data in the coal mine is abnormal, the gas often develops rapidly, and the main component of the gas is methane, which leads to the failure of the sensor to monitor the abnormality of the methane concentration in the air in time, and the abnormal data cannot be monitored accurately and timely.

[0004] Therefore, it is necessary to design an abnormal data monitoring method and system of a coal mine informatization system to solve the problems in the prior art. SUMMARY

[0005] In view of this, the present application provides an abnormal data monitoring method and system of a coal mine informatization system, aiming to solve the problem that it is difficult to accurately monitor abnormal data due to dust in the air during mine operation and blocked gas circulation in the mine.

[0006] In one aspect, the present application provides an abnormal data monitoring method of a coal mine informatization system, comprising:

[0007] Obtaining multiple gas content data and image brightness data in the coal mine;

[0008] Respectively processing the multiple gas content data and image brightness data to obtain monitoring gas information and monitoring image information;

[0009] Confirming the maximum slope of the difference between the monitoring gas information and the preset gas value, and the brightness change rate in the monitoring image information and the preset image information;

[0010] Confirming the proportion coefficient based on the maximum slope of the difference and the brightness change rate;

[0011] Compare the proportion coefficient with the preset monitoring coefficient to obtain abnormal data in the coal mine.

[0012] Further, the step of obtaining the multiple gas content data and the image brightness data in the coal mine includes:

[0013] Confirming a time alignment error of collecting the multiple gas content data and the image brightness data;

[0014] After time calibration of the time alignment error, the multiple gas content data and the image brightness data in the coal mine are obtained.

[0015] Further, the step of respectively processing the multiple gas content data and the image brightness data to obtain monitoring gas information and monitoring image information includes:

[0016] Processing the multiple gas content data to remove pulse interference to obtain processed multiple gas content data;

[0017] Detecting outliers from the processed multiple gas content data to confirm monitoring gas information;

[0018] Segmenting the image brightness data to obtain multiple brightness segmentation data;

[0019] Processing each of the brightness segmentation data to obtain mean value to confirm monitoring image information.

[0020] Further, the step of confirming the maximum slope of the difference between the monitoring gas information and the preset gas value, and the brightness change rate of the monitoring image information and the preset image information includes:

[0021] Comparing each gas in the monitoring gas information with its corresponding preset gas value to confirm a gas difference curve;

[0022] Confirming the slope of each gas in the gas difference curve to obtain the maximum slope of the difference;

[0023] Confirming the brightness ratio of each segmented region in the monitoring image information to the corresponding segmented region in the preset image information to obtain each brightness ratio;

[0024] Processing each brightness ratio to obtain a brightness change rate.

[0025] Further, based on the maximum slope of the difference and the brightness change rate, the step of confirming the proportion coefficient includes:

[0026] Assigning the maximum slope of the difference and the brightness change rate to a ratio weight to obtain a difference parameter and a brightness parameter;

[0027] Confirm the ratio between the difference value parameter and the brightness parameter, and confirm the proportion coefficient.

[0028] Further, in the step of comparing the proportion coefficient with the preset monitoring coefficient to obtain the abnormal data in the coal mine, the construction step of the preset monitoring coefficient comprises:

[0029] From the historical monitoring records of the coal mine, collect the historical data of the content of various gases and the historical data of the brightness of images under normal working conditions and abnormal working conditions;

[0030] Process the historical data of the content of various gases and the historical data of the brightness of images respectively to obtain historical information of monitoring gases and historical information of monitoring images;

[0031] Based on the historical information of monitoring gases and the historical information of monitoring images, confirm the historical maximum slope of the difference value and the historical change rate of brightness under normal working conditions and the historical maximum slope of the difference value and the historical change rate of brightness under abnormal working conditions;

[0032] Based on the historical maximum slope of the difference value and the historical change rate of brightness under normal working conditions and the historical maximum slope of the difference value and the historical change rate of brightness under abnormal working conditions, construct the preset monitoring coefficient.

[0033] Further, the step of constructing the preset monitoring coefficient based on the historical maximum slope of the difference value and the historical change rate of brightness under normal working conditions and the historical maximum slope of the difference value and the historical change rate of brightness under abnormal working conditions comprises:

[0034] Using a neural network model, train the historical proportion coefficient between the historical maximum slope of the difference value and the historical change rate of brightness under normal working conditions and the historical proportion coefficient between the historical maximum slope of the difference value and the historical change rate of brightness under abnormal working conditions to construct the preset monitoring coefficient.

[0035] Further, the step of comparing the proportion coefficient with the preset monitoring coefficient to obtain the abnormal data in the coal mine comprises:

[0036] Compare the proportion coefficient with the preset monitoring coefficient in size, if the proportion coefficient is greater than the preset monitoring coefficient, the abnormal data in the coal mine is obtained.

[0037] Further, if the proportion coefficient is greater than the preset monitoring coefficient, the step of obtaining the abnormal data in the coal mine further comprises:

[0038] If the proportion coefficient is between the preset monitoring coefficient and 1 times the preset monitoring coefficient, a third-level warning information is generated;

[0039] If the proportion coefficient is between 1 times the preset monitoring coefficient and 1.5 times the preset monitoring coefficient, a second-level warning information is generated;

[0040] If the proportional coefficient is greater than 1.5 times the preset monitoring coefficient, a first-level warning information is generated.

[0041] Compared with the prior art, the present application has the beneficial effects that: by acquiring the multiple gas content data and image brightness data in the coal mine, basic data is provided for subsequent monitoring of abnormal data; the multiple gas content data and image brightness data are respectively processed to obtain monitoring gas information and monitoring image information, so as to improve the overall quality of the acquired data, confirm the maximum slope of the difference between the monitoring gas information and the preset gas value, so as to confirm the abnormal gas in the coal mine, and the brightness change rate in the monitoring image information and the preset image information. Further, by combining the maximum slope of the difference and the brightness change rate, the maximum slope of the difference quantifies the monitoring gas information, which can avoid the influence of the collected values on the judgment of abnormal data, and by judging whether the gas and vision appear simultaneously in the coal mine, the single data measurement error and false alarm can also be avoided, and more accurate and intelligent monitoring of abnormal data in the coal mine is realized.

[0042] In another aspect, the present application also provides an abnormal data monitoring system of a coal mine informatization system, comprising:

[0043] An acquisition module is configured to acquire multiple gas content data and image brightness data in a coal mine.

[0044] A data processing module is configured to process the multiple gas content data and image brightness data respectively to obtain monitoring gas information and monitoring image information.

[0045] A first confirmation module is configured to confirm the maximum slope of the difference between the monitoring gas information and the preset gas value, and the brightness change rate in the monitoring image information and the preset image information.

[0046] A second confirmation module is configured to confirm the proportional coefficient based on the maximum slope of the difference and the brightness change rate.

[0047] A comparison module is configured to compare the proportional coefficient with a preset monitoring coefficient to obtain abnormal data in the coal mine.

[0048] It can be understood that the abnormal data monitoring method and system of the coal mine informatization system have the same beneficial effects, which will not be described here. BRIEF DESCRIPTION OF DRAWINGS

[0049] Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments with reference made to the accompanying drawings. The drawings are for purposes of illustration only and are not intended to limit the present application thereto, as the present application can have additional forms that fall within the scope of the same. Like reference numerals indicate like elements throughout the following figures. In the drawings:

[0050] Figure 1 The flow chart of the abnormal data monitoring method of the coal mine informatization system provided by the embodiment of the present application.

[0051] Figure 2 The flow chart of the S100 step of the abnormal data monitoring method of the coal mine informatization system provided by the embodiment of the present application.

[0052] Figure 3 The flow chart of the S200 step of the abnormal data monitoring method of the coal mine informatization system provided by the embodiment of the present application.

[0053] Figure 4 The flow chart of the S300 step of the abnormal data monitoring method of the coal mine informatization system provided by the embodiment of the present application.

[0054] Figure 5 The flow chart of the S400 step of the abnormal data monitoring method of the coal mine informatization system provided by the embodiment of the present application.

[0055] Figure 6 The flow chart of the construction of the preset monitoring coefficient of the abnormal data monitoring method of the coal mine informatization system provided by the embodiment of the present application.

[0056] Figure 7 The flow chart of the generation of the early warning information of the abnormal data monitoring method of the coal mine informatization system provided by the embodiment of the present application.

[0057] Figure 8 The functional block diagram of the abnormal data monitoring system of the coal mine informatization system provided by the embodiment of the present application. DETAILED DESCRIPTION

[0058] Exemplary embodiments of the present disclosure will be described below in greater detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it is to be understood that the present disclosure can be embodied in various forms without being limited by the embodiments set forth herein. Rather, these embodiments are provided so that the present disclosure will be thorough and complete, and will fully convey the scope of the present disclosure to those skilled in the art. Note that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict. The present application will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

[0059] Reference Figure 1As shown, the present application provides an abnormal data monitoring method of a coal mine informatization system, comprising the following steps:

[0060] S100: Obtain multiple gas content data and image brightness data in the coal mine. Among them, the multiple gas content data includes the concentration measurement value of multiple gases (such as methane CH4, carbon monoxide CO, carbon dioxide CO2, etc.) existing in the coal mine; these data are important indicators for evaluating the safety condition of the mine, and can reflect the risk of disasters such as gas explosion and fire. Electrochemical sensor array is used to collect multiple gas content data, and median filter is used to remove pulse interference. The image brightness data is the brightness information of the internal image of the mine obtained by the image acquisition device such as camera (such as using explosion-proof industrial camera). The brightness data can reflect the lighting conditions, dust concentration and possible abnormal situations such as fire in the mine. By simultaneously collecting the related data of gas and image, multiple data support is provided for subsequent abnormal analysis, and the accuracy of abnormal detection is improved.

[0061] S200: Data processing is performed on the multiple gas content data and image brightness data respectively to obtain monitoring gas information and monitoring image information. Specifically, by performing data processing on the multiple gas content data and image brightness data respectively, the noise and interference in the original data are eliminated, the data quality is improved, and a reliable foundation is provided for subsequent feature extraction and abnormal analysis. Thus, the actual situation of the gas in the mine can be more accurately reflected through the monitoring gas information. The monitoring image information can more clearly reflect the lighting conditions, dust concentration and possible abnormal situations in the mine.

[0062] S300: Confirm the maximum slope of the difference between the monitoring gas information and the preset gas value, and the brightness change rate in the monitoring image information and the preset image information. Among them, the maximum slope of the difference is the maximum value of the change rate of the difference between each gas in the monitoring gas information and its corresponding preset gas value; reflects the speed and trend of gas concentration change, and is used to evaluate the disaster risk such as gas explosion. The brightness change rate is the change rate of the brightness value in the monitoring image information and the preset image information; reflects the change of environmental factors such as lighting conditions and dust concentration in the mine. By obtaining the abnormal situation in the mine, it can be used to assist in judging whether the sensor for collecting multiple gas content data has monitoring error.

[0063] S400: Confirm the proportion coefficient based on the maximum slope of the difference and the brightness change rate. Specifically, the proportion coefficient is an index that comprehensively reflects the trend of gas concentration change and the brightness change rate of the image; is used to quantify the abnormal risk of the mine environment.

[0064] S500: compare the proportion coefficient with a preset monitoring coefficient to obtain abnormal data in the coal mine. The preset monitoring coefficient is a proportion coefficient threshold set according to historical data; it is used to compare with the proportion coefficient actually calculated, so that the presence of abnormal data in the coal mine can be more accurately determined. In order to trigger corresponding early warning or disposal measures in the future. Provide decision support for coal mine safety management personnel, assist in taking timely measures to deal with abnormal conditions in the coal mine, and ensure the safety production of the coal mine.

[0065] The present application provides basic data for subsequent monitoring of abnormal data by obtaining various gas content data and image brightness data in the coal mine; the various gas content data and image brightness data are respectively processed to obtain monitoring gas information and monitoring image information, so as to improve the overall quality of the obtained data, confirm the maximum slope of the difference between the monitoring gas information and the preset gas value, so as to confirm the abnormal gas in the coal mine, and confirm the brightness change rate of the monitoring image information and the preset image information. The proportion coefficient is compared with the preset monitoring coefficient to obtain the abnormal data in the coal mine. Then, by combining the maximum slope of the difference with the brightness change rate, the maximum slope of the difference is quantized to the monitoring gas information, which can avoid the influence of the collected values on the judgment of abnormal data. By judging whether the gas and vision appear simultaneously in the coal mine, the single data measurement error and false alarm can also be avoided, and the precision and intelligence of the coal mine monitoring abnormal data are realized.

[0066] In some embodiments of the present application, please refer to Figure 2 As shown in the figure, S100: the step of obtaining various gas content data and image brightness data in the coal mine includes:

[0067] S110: confirm the time alignment error of collecting various gas content data and image brightness data. In the data collection process, due to the working principle of gas sensor and image acquisition equipment, data transmission delay and other factors, the various gas content data and image brightness data cannot be completely synchronized in time. By confirming the time alignment error, more accurate data can be provided for subsequent data fusion and abnormal analysis.

[0068] S120: after time calibration of the time alignment error, obtain various gas content data and image brightness data in the coal mine. Specifically, for the time alignment error, existing algorithms or hardware synchronization mechanisms are used to calibrate the gas content data and image brightness data in time to ensure the synchronization of the two in time. Specifically, time calibration can more accurately obtain various gas content data and image brightness data in the coal mine, reduce the error during collection, and improve the accuracy of subsequent monitoring of abnormalities.

[0069] In some embodiments of the present application, please refer to Figure 3 As shown in FIG. 2, the step S200 of processing the plurality of gas content data and the image brightness data respectively to obtain the monitoring gas information and the monitoring image information includes:

[0070] S211: removing pulse interference from the plurality of gas content data to obtain processed plurality of gas content data. Specifically, the interference can be caused by electromagnetic pulse, mechanical vibration or sensor transient failure in the mine, and the burst noise or abnormal peak in the gas concentration data is eliminated by using existing filtering algorithm. Thus, after removing the pulse interference, the gas concentration data is smoother, reflecting the real environmental changes, avoiding misjudgment (such as false gas overrun) caused by noise, and improving the data quality. At the same time, it provides a clean data basis for anomaly detection and trend analysis, reduces the error accumulation of subsequent processing steps, and ensures the accuracy of subsequent analysis.

[0071] S212: detecting abnormal values from the processed plurality of gas content data to confirm the monitoring gas information. Wherein, the abnormal values in the plurality of gas content data can be caused by sensor failure, data transmission error or extreme environmental events, and the abnormal value detection is to identify the points that deviate significantly from the overall data distribution by using existing statistical methods. Thus, the error data is eliminated, the real environmental anomalies (such as gas leakage) are distinguished from the data noise, the effective abnormal data is retained, and a reliable basis is provided for subsequent early warning.

[0072] S221: performing region segmentation processing on the image brightness data to obtain a plurality of brightness segmentation data. Wherein, the region segmentation processing is to divide the image into a plurality of regions according to the image content or the preset rules. The region segmentation processing is performed by using existing segmentation method, which can also be used for local analysis of high-risk areas (such as gas accumulation area and equipment intensive area) in the mine, improving the monitoring efficiency. At the same time, under the interference of dust or water mist, the robustness of brightness analysis is improved by focusing on the clear area through region segmentation; it can also be used to judge the environment of the sensor for collecting the plurality of gas content data, to determine whether the sensor is affected by the mine environment, and to assist in confirming the feasibility of the collected plurality of gas content data.

[0073] S222: performing mean value processing on each of the brightness segmentation data to confirm the monitoring image information. The average brightness value of each segmentation region is calculated to quantify the illumination intensity or the smoke coverage degree of the region. The image brightness information is reduced from pixel level to region level, reducing data redundancy; at the same time, the mean value processing can suppress the influence of local noise (such as dust particle reflection) on the overall brightness judgment, enhancing the anti-noise ability.

[0074] In some embodiments of the present application, please refer to Figure 4As shown, the step S300 of confirming the maximum slope of the difference between the monitored gas information and the preset gas value, and the luminance change rate in the monitored image information and the preset image information comprises:

[0075] S310: difference comparison is performed between each gas in the monitored gas information and its corresponding preset gas value to confirm a gas difference curve. In the difference comparison, the real-time monitored gas concentration value (such as methane CH4 or carbon monoxide CO) is subtracted from its preset safety threshold (preset gas value) item by item to obtain a gas concentration deviation value. The gas difference curve is a dynamic curve plotted with time as the horizontal axis and the gas concentration deviation value as the vertical axis, which directly reflects the degree and change trend of the gas concentration deviating from the safety range. The continuous change of the gas concentration deviation is displayed in the form of a curve, which facilitates the observation of the dynamic characteristics of the gas accumulation, leakage and other processes.

[0076] S320: the slope of each gas in the gas difference curve is confirmed to obtain the maximum slope of the difference. By obtaining the maximum slope of the difference, the maximum value among all the slopes of the gas difference curves in the monitoring period is obtained, which represents the most severe degree of change of the gas concentration, and indicates that the faster the gas concentration rises or falls, the higher the disaster risk increases.

[0077] S330: the luminance ratio of each segmented area in the monitored image information to the corresponding segmented area in the preset image information is confirmed to obtain each luminance ratio. The luminance ratio is obtained by dividing the real-time luminance average of a segmented area in the monitored image by the luminance average of the corresponding area in the preset image information (under normal working conditions). The luminance change of each area is quantified by the ratio to locate the dust accumulation, equipment heating or smoke diffusion area.

[0078] S340: the mean value of each luminance ratio is processed to obtain the luminance change rate. The abnormal degree of the luminance of the whole mine or the key area is reflected by the result after the mean value processing, which is used for fusion analysis with the gas data. Thus, the influence of single area noise (such as local reflection) on the overall judgment can be weakened, and the stability of the change rate is improved.

[0079] Specifically, by combining the maximum slope of the difference of the gas concentration change with the luminance change rate of the image luminance change, the maximum slope of the difference quantifies the monitored gas information, which can avoid the influence of the collected numerical value on the judgment of abnormal data, and also provides complementary information for subsequent multi-modal fusion decision, which significantly improves the accuracy and timeliness of abnormal monitoring.

[0080] In some embodiments of the present application, please refer to Figure 5 As shown, the step S400 of confirming the proportion coefficient based on the maximum slope of the difference and the luminance change rate comprises:

[0081] S410: Assign the difference value maximum slope and the brightness change rate with a ratio weight respectively to obtain a difference value parameter and a brightness parameter. The ratio weight refers to the relative importance coefficient assigned to different features such as gas concentration change rate and image brightness change rate in multi-source data fusion. The weight is determined by historical data training or expert experience, reflecting the contribution of each feature to the abnormal risk. For example, the ratio weight of the difference value maximum slope is 0.7, and the ratio weight of the brightness change rate is 0.3, which can more accurately monitor abnormal data and identify abnormal risks. The difference value parameter refers to the product of the difference value maximum slope (gas concentration change rate) and its weight, representing the weighted gas abnormal risk value. The brightness parameter refers to the product of the brightness change rate (image brightness change rate) and its weight, representing the weighted visual abnormal risk value. Through weight allocation, the weight of sudden gas concentration rise may be higher than that of high-risk features such as brightness change, making the proportion coefficient more focused on key risk sources.

[0082] S420: Confirm the ratio between the difference value parameter and the brightness parameter to confirm the proportion coefficient. Specifically, the proportion coefficient is the ratio of the difference value parameter to the brightness parameter, which comprehensively reflects the relative intensity of gas concentration change and visual abnormal change. The larger the proportion coefficient, the more dominant the gas abnormal risk; the smaller the proportion coefficient, the more significant the visual abnormality. In this embodiment, the proportion coefficient quantifies the monitored data, avoiding abnormal data judgment affected by the collection process and improving the accuracy of monitoring.

[0083] In some embodiments of the present application, referring to Figure 6 The construction steps of the preset monitoring coefficient in the step of comparing the proportion coefficient with the preset monitoring coefficient to obtain the abnormal data in the coal mine are as follows:

[0084] S510: Collect a plurality of gas content historical data and image brightness historical data under normal and abnormal working conditions from the historical monitoring records of the coal mine. Specifically, the historical monitoring records are the gas concentration (such as CH4, CO and CO2) and image brightness data continuously collected in the past period (such as 6 months to 1 year) of the coal mine, covering different working conditions such as normal production, equipment maintenance and disaster simulation. The normal working condition is a safe production state with good mine ventilation, no gas accumulation or fire risk. The abnormal working condition is a simulated or real gas leakage, carbon monoxide overrun, belt friction fire and other dangerous scenarios. The plurality of gas content historical data and image brightness historical data provide data-based training for the preset monitoring coefficient, ensuring that the model has the ability to distinguish between normal and abnormal.

[0085] S520: data processing is performed on the historical data of the plurality of gas contents and the historical data of the image brightness respectively to obtain historical information of the monitored gas and historical information of the monitored image. The historical data of the plurality of gas contents and the historical data of the image brightness are respectively subjected to denoising and outlier rejection data processing. The noise such as sensor drift or dust interference in the historical data is eliminated, the data quality is improved, and a reliable basis is provided for subsequent feature extraction.

[0086] S530: based on the historical information of the monitored gas and the historical information of the monitored image, the difference historical maximum slope and the brightness historical change rate under normal working conditions and the difference historical maximum slope and the brightness historical change rate under abnormal working conditions are confirmed. The difference historical maximum slope is the maximum rate of change of the gas concentration deviation with time under normal or abnormal working conditions in the historical data, which reflects the degree of change of the gas. The brightness historical change rate is the average rate of change of the image brightness ratio with time under normal or abnormal working conditions in the historical data, which quantifies the evolution speed of the visual anomaly. Data support is provided for the construction of the preset monitoring coefficient.

[0087] S540: based on the difference historical maximum slope and the brightness historical change rate under normal working conditions and the difference historical maximum slope and the brightness historical change rate under abnormal working conditions, a preset monitoring coefficient is constructed. The preset monitoring coefficient is a threshold value determined by a machine learning model (such as a support vector machine or a random forest), which is used to compare with the real-time calculated proportion coefficient to determine whether the coal mine is in an abnormal state.

[0088] Specifically, the preset coefficient is constructed based on the historical data to avoid the subjectivity of manually setting the threshold value and improve the scientificity of the decision. Through comparative analysis of normal and abnormal working conditions, it is ensured that the preset coefficient can distinguish between gas leakage, fire or equipment failure and other types of risks, adapt to complex coal mine scenes, and improve the accuracy of data judgment.

[0089] In some embodiments of the present application, the step of constructing the preset monitoring coefficient based on the difference historical maximum slope and the brightness historical change rate under normal working conditions and the difference historical maximum slope and the brightness historical change rate under abnormal working conditions comprises:

[0090] The historical proportion coefficient between the difference historical maximum slope and the brightness historical change rate under normal working conditions and the historical proportion coefficient between the difference historical maximum slope and the brightness historical change rate under abnormal working conditions are trained by using a neural network model to construct the preset monitoring coefficient. The preset monitoring coefficient constructed by the neural network model such as the long short-term memory network model is more accurate and has higher construction efficiency, so that the historical data in the coal mine is quantified, the preset monitoring coefficient can be more objectively obtained, and the accuracy of the abnormal detection is improved.

[0091] In some embodiments of the present application, the step of comparing the proportionality coefficient with the preset monitoring coefficient to obtain abnormal data in the coal mine comprises:

[0092] The proportionality coefficient is compared with the preset monitoring coefficient in size, and if the proportionality coefficient is greater than the preset monitoring coefficient, the abnormal data in the coal mine is obtained. By comparing the proportionality coefficient with the preset monitoring coefficient in size, if the proportionality coefficient is greater than the preset monitoring coefficient, it can be judged that an abnormality occurs in the coal mine, which provides a basis for subsequent early warning.

[0093] In some embodiments of the present application, please refer to Figure 7 As shown in the figure, if the proportionality coefficient is greater than the preset monitoring coefficient, the step of obtaining abnormal data in the coal mine further comprises:

[0094] S610: If the proportionality coefficient is between the preset monitoring coefficient and 1 times the preset monitoring coefficient, a third-level early warning information is generated. The third-level early warning information indicates that the environmental risk is slightly higher than the normal range, and needs to be monitored but does not need to be evacuated urgently. The early warning provides an early intervention window for safety personnel. Avoid triggering high-level early warning due to slight fluctuations, reduce unnecessary emergency response such as shutdown or evacuation, and reduce operating costs.

[0095] S620: If the proportionality coefficient is between 1 times the preset monitoring coefficient and 1.5 times the preset monitoring coefficient, a second-level early warning information is generated. The second-level early warning information indicates that the environmental risk is significantly increased, and needs to start local emergency measures, such as strengthening ventilation or checking sensors, cleaning dust and other hidden trouble investigation. Thus, the probability of accident escalation is reduced.

[0096] S630: If the proportionality coefficient is greater than 1.5 times the preset monitoring coefficient, a first-level early warning information is generated. The first-level early warning information indicates that the environmental risk is extremely high, and needs to immediately start a global emergency plan, such as evacuating personnel and cutting off power. Through multi-channel alarm, such as sound and light alarm, short message push and broadcast system, the information transmission is ensured, and the response delay caused by single channel failure is avoided.

[0097] In this embodiment, through the three-level early warning mechanism, the size relationship between the proportionality coefficient and the preset monitoring coefficient is judged, the early warning mechanism is set step by step, the false alarm caused by sensor noise or temporary fluctuation is reduced, and the emergency resources are accurately configured according to the severity of the mine risk.

[0098] Based on the abnormal data monitoring method of the coal mine information system described in any of the above embodiments, referring to Figure 8 The present application also provides an abnormal data monitoring system of a coal mine information system, which comprises an acquisition module 710, a data processing module 720, a first confirmation module 730, a second confirmation module 740 and a comparison module 750.

[0099] The acquisition module 710 is configured to acquire the gas content data and the image brightness data in the coal mine;

[0100] The data processing module 720 is configured to process the gas content data and the image brightness data respectively to obtain the monitoring gas information and the monitoring image information;

[0101] The first confirmation module 730 is configured to confirm the maximum slope of the difference between the monitoring gas information and the preset gas value, and the brightness change rate in the monitoring image information and the preset image information;

[0102] The second confirmation module 740 is configured to confirm the proportion coefficient based on the maximum slope of the difference and the brightness change rate;

[0103] The comparison module 750 is configured to compare the proportion coefficient with the preset monitoring coefficient to obtain the abnormal data in the coal mine.

[0104] In the embodiment, the acquisition module 710 is configured to acquire the gas content data and the image brightness data in the coal mine, thereby providing the basic data for subsequent monitoring of the abnormal data; the data processing module 720 is configured to process the gas content data and the image brightness data respectively to obtain the monitoring gas information and the monitoring image information, thereby improving the overall quality of the acquired data; the first confirmation module 730 is configured to confirm the maximum slope of the difference between the monitoring gas information and the preset gas value, and the brightness change rate in the monitoring image information and the preset image information, thereby judging whether the visual abnormality occurs in the coal mine and avoiding false positives of a single data; the second confirmation module 740 is configured to confirm the proportion coefficient based on the maximum slope of the difference and the brightness change rate; and the comparison module 750 is configured to compare the proportion coefficient with the preset monitoring coefficient to obtain the abnormal data in the coal mine. The monitoring gas information is quantified by the maximum slope of the difference, which can avoid the influence of the collected values on the judgment of the abnormal data, thereby realizing the precision and intelligence of the abnormal monitoring of the coal mine.

[0105] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system or a computer program product. Therefore, the present application can be in the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can be in the form of a computer program product implemented on one or more computer usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer usable program code.

[0106] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart or flowsheet block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 means for functionally implementing the steps listed in the flowchart

[0107] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart or flowsheet block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 means for functionally implementing the steps listed in the flowchart

[0108] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart or flowsheet block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 means for functionally implementing the steps listed in the flowchart

[0109] Finally, it should be noted that the above-mentioned embodiments are merely intended to illustrate the technical solutions of the present application, rather than limit the technical solutions of the present application. Although the present application has been described in detail with reference to the above-mentioned embodiments, those skilled in the art should understand that the specific embodiments of the present application can be modified or replaced equivalently without departing from the spirit and scope of the present application, and any modification or equivalent replacement without departing from the spirit and scope of the present application should be covered in the protection scope of the claims of the present application.

Claims

1. A method for monitoring abnormal data in a coal mine information system, characterized in that: include: Obtain various gas content data and image brightness data in coal mines; Processing the gas content data and the image brightness data to obtain monitoring gas information and monitoring image information; Confirm the maximum slope of the difference between the monitored gas information and the preset gas value, and the brightness change rate between the monitored image information and the preset image information; Determining a proportionality coefficient based on the maximum slope of the difference and the brightness change rate; The proportional coefficient is compared with a preset monitoring coefficient to obtain abnormal data in the coal mine.

2. The abnormal data monitoring method of the coal mine information system according to claim 1, characterized in that: The step of obtaining the data of various gas contents and image brightness in the coal mine includes: Confirm the time alignment error of collecting multiple gas content data and image brightness data; After time calibration is performed on the time alignment error, multiple gas content data and image brightness data in the coal mine are obtained.

3. The abnormal data monitoring method of the coal mine information system according to claim 1, characterized in that: The steps of respectively processing the plurality of gas content data and the image brightness data to obtain monitoring gas information and monitoring image information include: performing pulse interference removal processing on the multiple gas content data to obtain processed multiple gas content data; Performing abnormal value detection on the processed gas content data to confirm the monitored gas information; Performing region segmentation processing on the image brightness data to obtain a plurality of brightness segmentation data; Perform mean processing on each of the brightness segmentation data to confirm the monitoring image information.

4. The abnormal data monitoring method of the coal mine information system according to claim 3, characterized in that: The step of confirming the maximum slope of the difference between the monitored gas information and the preset gas value, and the brightness change rate between the monitored image information and the preset image information includes: Comparing the difference between each gas in the monitored gas information and its corresponding preset gas value to determine a gas difference curve; Confirm the slope of each gas in the gas difference curve and obtain the maximum slope of the difference; Confirming the brightness ratio of each segmented area in the monitoring image information to the corresponding segmented area in the preset image information to obtain each brightness ratio; Each brightness ratio is averaged to obtain the brightness change rate.

5. The abnormal data monitoring method of the coal mine information system according to claim 1, characterized in that: The step of determining the proportional coefficient based on the maximum slope of the difference and the brightness change rate includes: Assigning ratio weights to the maximum slope of the difference and the brightness change rate respectively to obtain a difference parameter and a brightness parameter; Confirm the ratio between the difference parameter and the brightness parameter and confirm the proportional coefficient.

6. The abnormal data monitoring method of the coal mine information system according to claim 1, characterized in that: In the step of comparing the proportional coefficient with a preset monitoring coefficient to obtain abnormal data in the coal mine, the step of constructing the preset monitoring coefficient includes: Collect historical data on various gas contents and image brightness under normal and abnormal working conditions from historical monitoring records of coal mines; Data processing is performed on the historical data of various gas contents and the historical data of image brightness to obtain the historical information of monitored gases and the historical information of monitored images; Based on the historical information of the monitored gas and the historical information of the monitored image, determining the historical maximum slope of the difference and the historical rate of change of brightness under normal operating conditions and the historical maximum slope of the difference and the historical rate of change of brightness under abnormal operating conditions; Based on the historical maximum slope of the difference and the historical rate of change of brightness under normal working conditions and the historical maximum slope of the difference and the historical rate of change of brightness under abnormal working conditions, a preset monitoring coefficient is constructed.

7. The abnormal data monitoring method of the coal mine information system according to claim 6, characterized in that: The step of constructing a preset monitoring coefficient based on the historical maximum slope of the difference and the historical rate of change of brightness under normal working conditions and the historical maximum slope of the difference and the historical rate of change of brightness under abnormal working conditions includes: Using the neural network model, the historical proportional coefficient between the historical maximum slope of the difference and the historical rate of change of brightness under normal working conditions and the historical proportional coefficient between the historical maximum slope of the difference and the historical rate of change of brightness under abnormal working conditions are trained to construct the preset monitoring coefficient.

8. The abnormal data monitoring method of the coal mine information system according to claim 1, characterized in that: The steps of comparing the proportional coefficient with a preset monitoring coefficient to obtain abnormal data in the coal mine include: The proportional coefficient is compared with the preset monitoring coefficient. If the proportional coefficient is greater than the preset monitoring coefficient, abnormal data in the coal mine is obtained.

9. The abnormal data monitoring method of the coal mine information system according to claim 8, characterized in that: If the proportional coefficient is greater than the preset monitoring coefficient, the step of obtaining abnormal data in the coal mine further includes: If the proportional coefficient is between the preset monitoring coefficient and 1 times the preset monitoring coefficient, a level 3 warning message is generated; If the proportional coefficient is between 1 times the preset monitoring coefficient and 1.5 times the preset monitoring coefficient, a second-level warning information is generated; If the proportional coefficient is greater than 1.5 times the preset monitoring coefficient, a first-level warning message is generated.

10. An abnormal data monitoring system for a coal mine information system, characterized in that: include: An acquisition module is used to obtain various gas content data and image brightness data in a coal mine; a data processing module, configured to process the gas content data and the image brightness data respectively to obtain monitoring gas information and monitoring image information; A first confirmation module is used to confirm the maximum slope of the difference between the monitored gas information and the preset gas value, and the brightness change rate between the monitored image information and the preset image information; A second confirmation module is used to confirm a proportional coefficient based on the maximum slope of the difference and the brightness change rate; The comparison module is used to compare the proportional coefficient with the preset monitoring coefficient to obtain abnormal data in the coal mine.

Images