Coal mine pipeline intelligent monitoring system based on Internet of Things

Abstract

The invention discloses a coal mine pipeline intelligent monitoring system based on the Internet of Things, relates to the technical field of intelligent monitoring, and solves the technical problems that a fault point is difficult to accurately position, the risk of the fault point is not predicted, and prevention cannot be carried out in advance. Abnormal conditions are found in time, risk prediction is carried out, safety accidents caused by pipeline faults can be effectively prevented, shutdown and production halt time caused by the pipeline faults can be shortened through accurate monitoring and fault positioning, risk values are calculated through comprehensive analysis on maintenance frequency, abnormal data change values, fault values and the like, and the maintenance efficiency is improved. According to the method, a more reasonable pipeline maintenance plan can be made, maintenance resources can be arranged in a targeted mode according to the risk level, a high-risk area or equipment is maintained preferentially, the service life of the pipeline is prolonged, and the maintenance cost is reduced.

Description

Technical Field

[0001] The present invention relates to the field of intelligent monitoring technology, and in particular to a coal mine pipeline intelligent monitoring system based on the Internet of Things. Background Art

[0002] The pipeline system in coal mine production undertakes key tasks such as ventilation, drainage, gas extraction, etc. The normal operation of the pipeline is crucial to the safe production and efficient mining of coal mines.

[0003] According to the publication number CN118112100A, an intelligent pipeline monitoring system based on the Internet of Things is disclosed, including a server, a non-destructive testing module, a pipeline defect assessment module, a pipeline displacement decision module and an intelligent early warning module; the present invention performs segmented defect detection and analysis on the pipeline to generate a defect assessment qualified signal or a defect assessment unqualified signal, thereby achieving an accurate assessment of the pipeline defect performance status, and when generating the defect assessment qualified signal, the displacement risk status of the pipeline is analyzed by the pipeline displacement decision module to achieve an accurate assessment of the pipeline displacement risk status, which can effectively reduce the safety hazards of the pipeline, and during the operation of the pipeline, the real-time operation impact detection and analysis module is used to analyze to determine the abnormal operation status of the pipeline, so that the operation risk degree of the pipeline can be reasonably assessed in real time and early warning feedback can be given in time, effectively ensuring the safe and stable operation of the pipeline.

[0004] However, some existing intelligent monitoring systems have difficulty in accurately locating fault points when in use, which will affect subsequent analysis. Secondly, there is no good corresponding risk prediction for the fault point, so prevention cannot be carried out in advance. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention provides an intelligent monitoring system for coal mine pipelines based on the Internet of Things, which solves the problems of difficulty in accurately locating fault points, lack of risk prediction for fault points, and inability to take precautions in advance.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: an intelligent monitoring system for coal mine pipelines based on the Internet of Things, comprising:

[0007] The pipeline data comparison and analysis module is used to identify the state of the coal mine pipeline according to the sensor data transmitted by the pipeline data information acquisition module, generate pipeline identification results, and transmit the pipeline identification results to the abnormal data identification and analysis module;

[0008] The abnormal data identification and analysis module is used to process the abnormal analysis signals in the pipeline identification results, generate secondary analysis signals and fault point information by identifying the features of the abnormal data and matching them with historical data, calculate the specific fault point location based on the acoustic wave sensor data, generate fault point information, and transmit the fault point information to the fault point risk analysis module;

[0009] The fault point risk analysis module is used to perform risk prediction analysis on the fault point based on the fault point information. The risk value of the fault point is obtained by calculating the fault value, abnormal data change value and maintenance frequency of the fault point. At the same time, risk prediction is performed based on the risk value, and risk analysis information is generated. The risk analysis information is then transmitted to the pipeline monitoring information output module.

[0010] As a further solution of the present invention: it also includes a pipeline data information acquisition module and a pipeline monitoring information output module;

[0011] The pipeline data information acquisition module is used to acquire sensor data of the coal mine pipeline and transmit the acquired sensor data to the pipeline data comparison and analysis module, wherein the sensor data includes pressure data, temperature data and flow data;

[0012] The pipeline monitoring information output module is used to display the acquired risk analysis information to the corresponding operators.

[0013] As a further solution of the present invention: the specific method for the pipeline data comparison and analysis module to identify the coal mine pipeline status is:

[0014] Acquire sensor data and standard thresholds of different sensor data at the same time, then compare the sensor data with the standard thresholds, if the sensor data is greater than the standard threshold, generate an abnormal analysis signal, otherwise, if the sensor data is less than the threshold, generate a normal monitoring signal;

[0015] The normal monitoring signal is transmitted to the pipeline monitoring information output module, and the abnormal analysis signal is transmitted to the abnormal data identification and analysis module.

[0016] As a further solution of the present invention: the specific manner in which the abnormal data identification and analysis module processes the abnormal analysis signal is:

[0017] The sensor data corresponding to the abnormal analysis signal is obtained and marked as abnormal data. Then, the abnormal features of the abnormal data are identified and extracted. Meanwhile, the historical data is subjected to feature extraction and sorting. The specific extraction and sorting method is as follows: the corresponding abnormal situations in the historical data are classified and sorted to obtain the corresponding feature matching interval;

[0018] The abnormal feature is matched with the feature matching interval. If the abnormal feature exists in the feature matching interval, the fault point information is generated according to the abnormal situation corresponding to the feature matching interval. Otherwise, if the abnormal feature does not exist in the feature matching interval, a secondary analysis signal is generated and analyzed and processed.

[0019] As a further solution of the present invention: the specific method in which the abnormal data identification and analysis module analyzes and processes the secondary analysis signal is as follows:

[0020] Acquire the abnormal data corresponding to the secondary analysis signal, determine the corresponding abnormal sensor according to the abnormal data, and determine the fault range according to the position of the abnormal sensor. Then acquire the acoustic wave sensors marked as A and B, acquire the distance between the abnormal sensors as L, and calculate the time for the acoustic wave to propagate from the fault point to sensor A as t1=x / v, where v is the speed of acoustic wave propagation, x is the distance between the fault point and sensor A, and calculate the time for the acoustic wave to propagate from the fault point to sensor B as t2=(Lx) / v;

[0021] Then, the time difference of receiving the sound wave is calculated Δt=t2-t1=(Lx) / vx / v=L / v-2x / v, and then the distance between the fault point and sensor A is calculated according to the formula x=(L-vΔt) / 2, and the position of the fault point is determined at the same time, and the fault point information is generated, and then the fault point information is transmitted to the fault point risk analysis module and the pipeline monitoring information output module.

[0022] As a further solution of the present invention: the specific method of calculating the fault point risk value by the fault point risk analysis module is:

[0023] The fault point is obtained and recorded as the analysis target. At the same time, the number of faults in the historical data of the analysis target is obtained and recorded as K, and K = 1, 2, ..., H. Then the fault level of the fault number K is obtained, and the fault level value P is assigned based on different fault levels. K , then calculate all fault level values ​​P K The mean value of is recorded as fault value P1;

[0024] Then obtain the abnormal data change value G of the analysis target and the maintenance frequency F of the analysis target, and substitute the obtained maintenance frequency F, abnormal data change value G and fault value P1 into the formula The risk value Q of the analyzed object is calculated, where Z1, Z2 and Z3 are the weight coefficients of maintenance frequency, abnormal data change value and fault value respectively. Fmax is the maximum value of maintenance frequency, which is used to normalize the maintenance frequency to the interval [0,1]. Gmax is the maximum value of abnormal data change value, which is used for normalization. P1max is the maximum value of fault value, which is used for normalization. Z1+Z2+Z3=1. The weight can be adjusted according to the actual situation.

[0025] As a further solution of the present invention: the specific method in which the fault point risk analysis module performs risk prediction according to the risk value is:

[0026] The calculated risk value Q is compared with the preset value. If the risk value Q is greater than the preset value, the predicted risk information is generated. Otherwise, if the risk value Q is less than the preset value, the normal predicted information is generated. At the same time, the generated predicted risk information and normal predicted information are transmitted to the pipeline monitoring information output module.

[0027] As a further solution of the present invention: the pipeline monitoring information output module is also used to display normal monitoring signals to corresponding operators.

[0028] The present invention provides an intelligent monitoring system for coal mine pipelines based on the Internet of Things. Compared with the prior art, it has the following beneficial effects:

[0029] The present invention can effectively prevent safety accidents caused by pipeline failures by accurately monitoring pipeline data in real time, discovering abnormal situations in time and predicting risks. Accurate monitoring and fault location can reduce downtime caused by pipeline failures. Comprehensive analysis of maintenance frequency, abnormal data change value, fault value and other aspects is performed to calculate the risk value, which is helpful to formulate a more reasonable pipeline maintenance plan. Maintenance resources can be arranged in a targeted manner according to the risk level, high-risk areas or equipment can be given priority maintenance, thereby extending the service life of the pipeline and reducing maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 This is a block diagram of the system principle of the present invention;

[0031] Figure 2 This is a schematic diagram of the coal mine pipeline sensor arrangement of the present invention. DETAILED DESCRIPTION

[0032] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0033] For example, see Figure 1 and Figure 2 The present application provides an intelligent coal mine pipeline monitoring system based on the Internet of Things, including a pipeline data information acquisition module, a pipeline data comparison and analysis module, an abnormal data identification and analysis module, a fault point risk analysis module and a pipeline monitoring information output module. Figure 1It can be known that the above functional modules are electrically connected in a unidirectional manner.

[0034] The pipeline data information acquisition module is used to acquire sensor data of coal mine pipelines and transmit the acquired sensor data to the pipeline data comparison and analysis module. The sensor data includes pressure data, temperature data and flow data, which are acquired by corresponding sensors at the same time. Secondly, the sensors are evenly arranged on the pipeline at a certain distance. For example, the pressure sensor acquires the internal fluid pressure data of the pipeline, the temperature sensor acquires the pipe wall and internal medium temperature data, the flow sensor acquires the medium flow data, etc. At the same time, the timestamp of data acquisition and the corresponding sensor number and other meta-information are recorded.

[0035] Pipeline data comparison and analysis module, which is used to identify the status of coal mine pipelines based on the acquired sensor data, and the specific identification method is as follows:

[0036] Get sensor data and standard thresholds for different sensor data. The standard threshold database should be regularly updated and maintained, and dynamically adjusted according to pipeline design parameters, service life changes, coal mining environment characteristics, and relevant industry standards and specifications. Then compare the sensor data with the standard threshold. If the sensor data is greater than the standard threshold, it means that the corresponding sensor data is abnormal, and an abnormal analysis signal is generated. On the contrary, if the sensor data is less than the threshold, it means that the corresponding sensor data is normal, and a normal monitoring signal is generated. For example, in the coal mine gas extraction pipeline system, the standard threshold range of the pressure sensor is set to 1.2-1.8MPa.

[0037] After the above identification, a pipeline identification result is generated, and the pipeline identification result includes: a normal monitoring signal and an abnormal analysis signal. At the same time, the normal monitoring signal is transmitted to the pipeline monitoring information output module, and the abnormal analysis signal is transmitted to the abnormal data identification and analysis module.

[0038] The pipeline monitoring information output module is used to display the acquired normal monitoring signals to the corresponding operators.

[0039] Embodiment 2, as Embodiment 2 of the present invention, is implemented on the basis of Embodiment 1, and the difference from Embodiment 1 is as follows:

[0040] The abnormal data identification and analysis module is used to process the acquired abnormal analysis signal by identifying the features of the abnormal data. The specific method of identifying the features of the abnormal data is as follows:

[0041] The sensor data corresponding to the abnormal analysis signal is obtained and marked as abnormal data. Then, the abnormal features of the abnormal data are identified and extracted. Here, the abnormal feature identification is based on the change of the abnormal data. The change is identified and recorded as an abnormal feature. For example, the corresponding abnormal data is pressure data. The corresponding pressure data is 1.8MPa, which rises to 2.1MPa within a period of time. The change value of the pressure data is further calculated, and the calculated change value is used as the abnormal feature. At the same time, it is extracted and sorted in combination with historical data. The specific extraction and sorting method is as follows: first, historical data is obtained, and the corresponding abnormal conditions in the historical data are classified and sorted. Specifically, for example, the abnormal conditions include pressure abnormalities, temperature abnormalities and flow abnormalities. Then, all data corresponding to the pressure abnormalities are collected, and the extracted data is feature identified. The data features are further sorted to obtain the corresponding feature intervals, and the corresponding feature matching intervals are obtained. For example, for pipeline leakage failures, multiple sub-intervals are divided according to the size of the leakage, the leakage speed and the different media in the pipeline to correspond to leakage abnormal characteristics of different degrees and natures.

[0042] Then, the abnormal feature is matched with the feature matching interval. If the abnormal feature exists in the feature matching interval, it means that the current abnormal feature has a corresponding fault point situation. At the same time, the fault point information is generated according to the abnormal situation corresponding to the feature matching interval. On the contrary, if the abnormal feature does not exist in the feature matching interval, it means that the current abnormal feature does not have a corresponding fault point situation. At the same time, a secondary analysis signal is generated and analyzed and processed;

[0043] Acquire the abnormal data corresponding to the secondary analysis signal, and determine the corresponding abnormal sensor according to the abnormal data. For example, there are three pressure sensors a, b, and b. A and C are located at both ends of the pipeline respectively, and b is in the middle. First, the pressure obtained by a is normal data, but the pressure data obtained by b and c are abnormal. Then, the b and c sensors are further marked as abnormal sensors, and the fault range is determined according to the position of the abnormal sensors. Then, the distance between the abnormal sensors is obtained by installing the acoustic wave sensors and marking the acoustic wave sensors as A and B. The distance between the abnormal sensors is recorded as L, and the time for the acoustic wave to propagate from the fault point to sensor A is calculated as t1=x / v, where v is the speed of acoustic wave propagation, x is the distance between the fault point and sensor A, and the time for the acoustic wave to propagate from the fault point to sensor B is calculated as t2=(Lx) / v;

[0044] Then, the time difference of receiving the sound wave is calculated Δt=t2-t1=(Lx) / vx / v=L / v-2x / v, and then the distance between the fault point and sensor A is calculated according to the formula x=(L-vΔt) / 2, and the position of the fault point is determined at the same time, and the fault point information is generated, and then the fault point information is transmitted to the fault point risk analysis module and the pipeline monitoring information output module.

[0045] In a specific example, calibrated acoustic wave sensors A and B are installed in a coal mine gas transmission pipeline. The medium in the pipeline is a mixed gas containing gas. After real-time monitoring of parameters such as medium density, the acoustic wave propagation speed v = 340m / s (the speed after considering the actual medium influence) is calculated. After multiple measurements of the acoustic wave signal and filtering, t1 = 0.1s and t2 = 0.4s are obtained. The time difference Δt = 0.3s is calculated, and the distance between the fault point and sensor A is calculated according to the formula x = (100-340×0.3) / 2 = 23m.

[0046] Fault point risk analysis module, which is used to perform risk prediction analysis on the acquired fault point information, and the specific risk prediction analysis method is as follows:

[0047] The fault point is obtained and recorded as the analysis target. At the same time, the number of faults in the historical data of the analysis target is obtained and recorded as K, and K = 1, 2, ..., H. Then the fault level of the fault number K is obtained, and the fault level value P is assigned based on different fault levels. K The specific fault level is set according to the fault conditions corresponding to the historical data. At the same time, the fault levels are classified into low-risk faults, medium-risk faults and high-risk faults, and the values ​​are assigned to 1, 2 and 3 respectively. Then all fault level values ​​P are calculated. K The mean value of is recorded as fault value P1;

[0048] Then obtain the abnormal data change value G of the analysis target, and the change value here is expressed as the change difference of the abnormal data within time t. Taking pressure data as an example, if the pressure data changes from 1.8MPa to 2.1MPa within time t, the further corresponding change difference is 0.3MPa, and obtain the maintenance frequency F of the analysis target, and the calculation method of the maintenance frequency is: obtain the number of failures K of the analysis target in the historical data, and obtain the corresponding usage time at the same time. According to the formula maintenance frequency = usage time ÷ number of failures K, substitute the obtained maintenance frequency F, abnormal data change value G and failure value P1 into the formula The risk value Q of the analyzed object is calculated, where Z1, Z2 and Z3 are weight coefficients of maintenance frequency, abnormal data change value and fault value respectively, Fmax is the maximum value of maintenance frequency, which is used to normalize the maintenance frequency to the interval [0,1], Gmax is the maximum value of abnormal data change value, which is used for normalization, P1max is the maximum value of fault value, which is used for normalization, and Z1+Z2+Z3=1, and the weight can be adjusted according to the actual situation;

[0049] The calculated risk value Q is compared with the preset value, and the preset value here is calculated based on historical data. The specific value is set by the operator through a large amount of historical data (including gas concentration changes, pipeline pressure fluctuations, equipment maintenance records, etc.). If the risk value Q is greater than the preset value, it means that the analysis object is at risk, and predictive risk information is generated. Conversely, if the risk value Q is less than the preset value, it means that the analysis object is temporarily at risk, and normal prediction information is generated. At the same time, the generated predictive risk information and normal prediction information are transmitted to the pipeline monitoring information output module.

[0050] Pipeline monitoring information output module, which is used to display the acquired risk analysis information to the corresponding operators.

[0051] Embodiment 3, as the embodiment 3 of the present invention, focuses on combining the implementation processes of embodiment 1 and embodiment 2 for implementation.

[0052] Some of the data in the above formulas are numerically calculated by removing their dimensions. Meanwhile, the contents not described in detail in this specification belong to the prior art known to those skilled in the art.

[0053] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. The coal mine pipeline intelligent monitoring system based on the Internet of Things is characterized by: include: The pipeline data information acquisition module is used to acquire sensor data of the coal mine pipeline and transmit the acquired sensor data to the pipeline data comparison and analysis module, wherein the sensor data includes pressure data, temperature data, flow data and sound wave data; The pipeline data comparison and analysis module is used to identify the state of the coal mine pipeline according to the sensor data transmitted by the pipeline data information acquisition module, generate pipeline identification results, and transmit the pipeline identification results to the abnormal data identification and analysis module; The abnormal data identification and analysis module is used to process the abnormal analysis signals in the pipeline identification results, generate secondary analysis signals and fault point information by identifying the features of the abnormal data and matching them with historical data, calculate the specific fault point location based on the acoustic wave sensor data, generate fault point information, and transmit the fault point information to the fault point risk analysis module; The fault point risk analysis module is used to perform risk prediction analysis on the fault point according to the fault point information, obtain the risk value of the fault point by calculating the fault value, abnormal data change value and maintenance frequency of the fault point, and perform risk prediction according to the risk value, generate risk analysis information, and then transmit the risk analysis information to the pipeline monitoring information output module; The pipeline monitoring information output module is used to display the acquired risk analysis information to the corresponding operators.

2. The coal mine pipeline intelligent monitoring system based on the Internet of Things according to claim 1 is characterized in that: The specific method for the pipeline data comparison and analysis module to identify the coal mine pipeline status is: Acquire sensor data and standard thresholds of different sensor data at the same time, then compare the sensor data with the standard thresholds, if the sensor data is greater than the standard threshold, generate an abnormal analysis signal, otherwise, if the sensor data is less than the threshold, generate a normal monitoring signal; The normal monitoring signal is transmitted to the pipeline monitoring information output module, and the abnormal analysis signal is transmitted to the abnormal data identification and analysis module.

3. The coal mine pipeline intelligent monitoring system based on the Internet of Things according to claim 1 is characterized in that: The specific method in which the abnormal data identification and analysis module processes the abnormal analysis signal is as follows: The sensor data corresponding to the abnormal analysis signal is obtained and marked as abnormal data. Then, the abnormal features of the abnormal data are identified and extracted, and the abnormal features represent the change values ​​of the corresponding sensor data. At the same time, the historical data is feature extracted and sorted. The specific extraction and sorting method is: the corresponding abnormal situations in the historical data are classified and sorted to obtain the corresponding feature matching interval; The abnormal feature is matched with the feature matching interval. If the abnormal feature exists in the feature matching interval, the fault point information is generated according to the abnormal situation corresponding to the feature matching interval. Otherwise, if the abnormal feature does not exist in the feature matching interval, a secondary analysis signal is generated and analyzed and processed.

4. The coal mine pipeline intelligent monitoring system based on the Internet of Things according to claim 3 is characterized in that: The specific method in which the abnormal data identification and analysis module analyzes and processes the secondary analysis signal is as follows: Acquire the abnormal data corresponding to the secondary analysis signal, determine the corresponding abnormal sensor according to the abnormal data, and determine the fault range according to the position of the abnormal sensor. Then acquire the acoustic wave sensors marked as A and B, acquire the distance between the abnormal sensors as L, and calculate the time for the acoustic wave to propagate from the fault point to sensor A as t1=x / v, where v is the speed of acoustic wave propagation, x is the distance between the fault point and sensor A, and calculate the time for the acoustic wave to propagate from the fault point to sensor B as t2=(Lx) / v; Then, the time difference of receiving the sound wave is calculated Δt=t2-t1=(Lx) / vx / v=L / v-2x / v, and then the distance between the fault point and sensor A is calculated according to the formula x=(L-vΔt) / 2, and the position of the fault point is determined at the same time, and the fault point information is generated, and then the fault point information is transmitted to the fault point risk analysis module and the pipeline monitoring information output module.

5. The coal mine pipeline intelligent monitoring system based on the Internet of Things according to claim 1 is characterized in that: The specific method for the fault point risk analysis module to calculate the fault point risk value is: The fault point is obtained and recorded as the analysis target. At the same time, the number of faults in the historical data of the analysis target is obtained and recorded as K, and K = 1, 2, ..., H. Then the fault level of the fault number K is obtained, and the fault level value P is assigned based on different fault levels. K , then calculate all fault level values ​​P K The mean value of is recorded as fault value P1; Then obtain the abnormal data change value G of the analysis target and the maintenance frequency F of the analysis target, and substitute the obtained maintenance frequency F, abnormal data change value G and fault value P1 into the formula The risk value Q of the analyzed object is calculated, where Z1, Z2 and Z3 are weight coefficients of maintenance frequency, abnormal data change value and fault value respectively, Fmax is the maximum value of maintenance frequency, which is used to normalize the maintenance frequency to the interval [0,1], Gmax is the maximum value of abnormal data change value, which is used for normalization, P1max is the maximum value of fault value, which is used for normalization, and Z1+Z2+Z3=1.

6. The coal mine pipeline intelligent monitoring system based on the Internet of Things according to claim 1 is characterized in that: The specific method of the fault point risk analysis module to perform risk prediction according to the risk value is as follows: The calculated risk value Q is compared with the preset value. If the risk value Q is greater than the preset value, the predicted risk information is generated. Otherwise, if the risk value Q is less than the preset value, the normal predicted information is generated. At the same time, the generated predicted risk information and normal predicted information are transmitted to the pipeline monitoring information output module.

7. The coal mine pipeline intelligent monitoring system based on the Internet of Things according to claim 2 is characterized in that: The pipeline monitoring information output module is also used to display normal monitoring signals to corresponding operators.

Images