Intelligent inspection and detection system for coal conveying belt conveyor in coal conveying bin area

Abstract

The invention discloses an intelligent inspection and detection system for a coal conveying belt conveyor in a coal conveying bin area, and relates to the technical field of intelligent inspection, the intelligent inspection and detection system comprises a belt conveyor anomaly analysis module and a deviation fault warning module, firstly, the belt conveyor anomaly analysis module sets a belt conveyor collection period according to a belt conveyor anomaly model by analyzing abnormal data of the belt conveyor; the environment data of each belt conveyor area is further collected, the environment data of each belt conveyor area is analyzed by using an environment abnormity model, belt conveyor early warning is performed, an inspection period is set, then transportation data of each belt area is collected through a deviation fault warning module in the inspection process, and a transportation fault model is used for performing early warning on the belt conveyor. According to the method, the conveying abnormity level of each belt area is obtained through analysis, belt data of each belt area is analyzed, and when an output result of the belt abnormity model exceeds a threshold value, an early warning prompt is given out, so that the safety of the coal conveying belt conveyor is improved, and the inspection cost is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent inspection, and particularly relates to an intelligent inspection and detection system for a coal conveying belt conveyor in a coal conveying bunker area. Background Art

[0002] During the energy production process, the coal conveying belt conveyor undertakes the important task of transporting fuels such as coal from the coal storage yard to belt conveyors such as boilers. However, the accuracy of traditional inspections is difficult to guarantee, and situations such as missed inspections and misinspections are likely to occur. The emergence of intelligent inspection systems has greatly reduced the labor intensity of workers, reduced labor risks, and at the same time can promptly detect problems that occur, avoid the expansion of accidents, greatly reduce the abnormal shutdown time during the production process, and improve the production efficiency and safety.

[0003] The prior art, such as the invention patent application with the publication number CN114104653A, discloses an intelligent inspection and detection method for a coal conveying belt conveyor in a coal conveying bunker area, including a single-track, a mobile robot, an automatic rotating pan-tilt, a sound sensor, a gas detector, a temperature and humidity sensor, four independent charging stations, a field wireless communication deployment system, and a background processing server. This invention effectively avoids the low integration and intelligence level of traditional inspection systems, and it is difficult to realize the intelligent processing and judgment of various on-site information, especially the artificial intelligence detection of on-site belt defects; it avoids the subjectivity, lag, and possible accident omissions brought by relying on monitoring personnel for interpretation in traditional inspections. Through belt defect detection, major losses caused by external belt breaks are avoided.

[0004] Regarding the above solution, it has at least the following deficiencies: The above solution only simply analyzes the environmental data of the belt conveyor, and does not predict the belt conveyor failure based on the environmental data of the belt conveyor. Therefore, it is impossible to give an early warning for the belt conveyor. On the other hand, the above solution does not analyze the key parts of the belt conveyor. For example, it does not analyze the center of the drum and the center of the idler, but only simply analyzes from the environmental data, which reduces the authenticity of the data and the effectiveness of the analysis results. Summary of the Invention

[0005] Aiming at the above existing technical deficiencies, the purpose of the present invention is to provide an intelligent inspection and detection system for a coal conveying belt conveyor in a coal conveying bunker area.

[0006] To solve the above technical problems, the present invention adopts the following technical solutions: The present invention provides an intelligent inspection and detection system for coal conveying belt conveyors in a coal bunker area, including the following modules: A belt conveyor anomaly analysis module, which is used to collect the anomaly data of each belt conveyor, and then based on the belt conveyor anomaly model, analyze the anomaly data of each belt conveyor to obtain each abnormal belt conveyor, and then reset the sensor data collection period of each abnormal belt conveyor, so as to collect the environmental data of each belt conveyor area. According to the environmental anomaly model, analyze the environmental data of each belt conveyor area to obtain the anomaly level of each belt conveyor area, give an early warning based on the anomaly level of each belt conveyor area and the historical anomaly level data in the database, and at the same time set the inspection period of the coal bunker area according to the anomaly level of each belt conveyor area.

[0007] A deviation fault warning module, which is used to collect the transportation data of each belt area according to the inspection period, and then based on the transportation fault model, analyze the transportation data of each belt area to obtain the transportation anomaly level of each belt area, set the corresponding belt sensor collection period according to the transportation anomaly level of each belt area, so as to collect the belt data of each belt area. According to the belt anomaly model, analyze the belt data of each belt area to give an early warning.

[0008] Preferably, the analysis of the environmental data of each belt conveyor area is as follows: The environmental data of each belt conveyor area includes the dust concentration and environmental temperature of each belt conveyor area. Input the dust concentration and environmental temperature of each belt conveyor area into the environmental anomaly model to obtain the output result of the environmental anomaly model of each belt conveyor area. The value c of the output result is recorded as the environmental anomaly level of each belt conveyor area, c = 1, 2......i, i > 2, and i is the maximum environmental anomaly level.

[0009] If the environmental anomaly level of a certain belt conveyor area is 0, it indicates that there is no need for early warning in this area. If the environmental anomaly level of a certain belt conveyor area is greater than 0, obtain the historical environmental anomaly levels of this belt conveyor area within a preset time period from the database, perform weighted calculation on the historical environmental anomaly levels of this belt conveyor area within the preset time period to obtain the actual anomaly level of this belt conveyor area. If the actual anomaly level of a certain belt conveyor area is greater than or equal to the preset standard anomaly level, give an early warning, so as to perform early warning analysis on each belt conveyor area.

[0010] Count the environmental anomaly levels of each belt conveyor area to obtain the number of belt conveyor areas with each environmental anomaly level, perform weighted calculation on the number of belt conveyor areas with each environmental anomaly level to obtain the environmental anomaly level of the coal bunker area, and obtain the inspection period corresponding to the environmental anomaly level of the coal bunker area from the database.

[0011] Preferably, the analysis of the belt data for each belt area is as follows: The belt data for each belt area includes the offset of the center of the roller in each belt area, the offset of the center of the idler, and the stress in each acquisition area. The offset of the center of the roller, the offset of the center of the idler, and the stress in each acquisition area of each belt area are input into the belt anomaly model to obtain the output result of the belt anomaly model for each belt area. The value t of the output result is recorded as the environmental anomaly level of each belt conveyor area, where t = 1, 2......y, y > 2, and y is the maximum environmental anomaly level.

[0012] If the output result of the belt anomaly model for a certain belt area is greater than 0, obtain the historical belt anomaly levels for each inspection cycle of this belt area from the database, count the historical belt anomaly levels for each inspection cycle of this belt area to obtain the occurrence times of each historical anomaly level in this belt area, perform weighted calculation to obtain the anomaly index of this belt area. If the anomaly level of this belt area is greater than the preset anomaly level or the anomaly index is greater than the preset standard anomaly index, give an early warning prompt.

[0013] The beneficial effects of the present invention are as follows: 1. First, the belt conveyor anomaly analysis module of the present invention analyzes the belt conveyor anomaly data, sets the acquisition cycle of the belt conveyor according to the belt conveyor anomaly model, and then acquires the environmental data of each belt conveyor area. The environmental anomaly model is used to analyze the environmental data of each belt conveyor area for belt conveyor early warning and setting the inspection cycle. Then, during the inspection process, the transportation data of each belt area is acquired through the deviation fault warning module, and the transportation anomaly level of each belt area is analyzed using the transportation fault model. When the output result of the belt anomaly model exceeds the threshold, an early warning prompt will be issued. The present invention improves the safety of the coal conveying belt conveyor and reduces the inspection cost.

[0014] 2. On the one hand, the present invention analyzes the environment of the belt conveyor, sets the inspection cycle, and at the same time gives an early warning, reducing the inspection cost and increasing the safety of the belt conveyor. On the other hand, the present invention analyzes the center of the roller, the center of the idler, and the stress on the belt surface, increasing the diversity of data and at the same time increasing the effectiveness of the data. Through the analysis of the center of the roller, the center of the idler, and the stress on the belt surface, it can effectively give an early warning of the belt deviation fault, increasing the safety of the coal bunker and improving the transportation efficiency. Description of the Drawings

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0016] Figure 1 This is a schematic diagram of the system structure connection of the present invention. Specific embodiments

[0017] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0018] According to Figure 1 As shown, the present invention provides a safety inspection system based on artificial intelligence, including the following modules: a belt conveyor anomaly analysis module, a deviation fault warning module, and a database.

[0019] The belt conveyor anomaly analysis module is respectively connected to the deviation fault warning module and the database.

[0020] The belt conveyor anomaly analysis module is used to collect the anomaly data of each belt conveyor, and then based on the belt conveyor anomaly model, analyze the anomaly data of each belt conveyor to obtain each abnormal belt conveyor, and then reset the sensor data collection period of each abnormal belt conveyor, so as to collect the environmental data of each belt conveyor area. According to the environmental anomaly model, analyze the environmental data of each belt conveyor area to obtain the anomaly level of each belt conveyor area, give an early warning according to the anomaly level of each belt conveyor area and the historical anomaly level data in the database, and at the same time set the inspection period of the coal conveying bunker area according to the anomaly level of each belt conveyor area.

[0021] In a specific embodiment, the process of collecting the anomaly data of each belt conveyor is as follows: place a temperature sensor and a vibration sensor inside the belt conveyor of each belt conveyor, collect the temperature of each collection of each belt conveyor within a preset time period through the temperature sensor, and collect the vibration amplitude and vibration frequency of each collection of each belt conveyor within a preset time period through the vibration sensor.

[0022] In a specific embodiment, the process of analyzing the anomaly data of each belt conveyor is as follows: the anomaly data of each belt conveyor includes the temperature, vibration amplitude, and vibration frequency of each collection of each belt conveyor within a preset time period. If the temperature of a certain collection of a certain belt conveyor within the preset time period is greater than the preset temperature, or the vibration amplitude of this collection is greater than the preset vibration amplitude, or the vibration frequency of this collection is greater than the preset vibration frequency, record this collection of the belt conveyor within the preset time period as an abnormal collection, and obtain the abnormal collections of each belt conveyor within the preset time period, and then obtain the temperature, vibration amplitude, and vibration frequency of each abnormal collection of each belt conveyor within the preset time period.

[0023] Divide the highest temperature abnormally collected by each belt conveyor within the preset time period by the standard abnormal temperature to obtain the temperature deviation rate of each belt conveyor within the preset time period. Analyze the vibration amplitude data and vibration frequency data according to the method of temperature data analysis to obtain the vibration amplitude deviation rate and vibration frequency deviation rate of each belt conveyor within the preset time period.

[0024] Input the temperature of each abnormal collection, the vibration amplitude of each abnormal collection, the vibration frequency of each abnormal collection, the abnormal temperature deviation rate, the abnormal vibration amplitude deviation rate, and the abnormal vibration frequency deviation rate corresponding to each belt conveyor within the preset time period into the belt conveyor abnormality model to obtain the output result of the belt conveyor abnormality model for each belt conveyor. The output result includes values of 0 and 1.

[0025] If the output result of the belt conveyor abnormality model for a certain belt conveyor is 0, it indicates that the belt conveyor is normal, and the sensor data collection period of each belt conveyor is the preset collection period. If the output result of the belt conveyor abnormality model for a certain belt conveyor is 1, it indicates that the belt conveyor is abnormal, which is recorded as an abnormal belt conveyor. After obtaining each abnormal belt conveyor, substitute the abnormal temperature deviation rate r′ a , the abnormal vibration amplitude deviation rate r″ a and the abnormal vibration frequency deviation rate r″′ a into the calculation formula for the sensor data collection period of the belt conveyor to obtain the sensor data collection period L of belt conveyor a a , where a is the number of the belt conveyor, a = 1, 2......m, m > 2, and m is the value of the total number of belt conveyors. ε 1 , ε 2 and ε 3 are the weight factors of the preset temperature, vibration amplitude, and vibration frequency respectively. ε 1 > 0, ε 2 > 0, ε 3 > 0, ε 1 + ε 2 + ε 3 = 1, which is the preset collection period of belt conveyor a. According to the sensor data collection periods of each belt conveyor, enable the sensor data collection periods of each belt conveyor to collect the environmental data of each belt conveyor area.

[0026] It should be noted that the weight factors ε 1 , ε 2 and ε 3 are all set by the staff. For example, ε 1 is 0.3, ε 2 is 0.4, and ε 3It is 0.4. By analyzing the conveyor belt data collected by the sensors in the conveyor belt, the environmental data collection period for the corresponding conveyor belt area is set, saving the analysis cost while ensuring the effectiveness of the data.

[0027] In a specific embodiment, the abnormal model expression of the conveyor belt is as follows:

[0028]

[0029] where α a is the output result of the abnormal model of conveyor belt a, T ab , A ab and f ab are respectively the temperature, vibration amplitude and vibration frequency of b abnormal collections of conveyor belt a within a preset time period, b is the number of abnormal collections, b = 1, 2......n, n > 2, r′ a , r″ a and r″′ a are respectively the abnormal temperature deviation rate, abnormal vibration amplitude deviation rate and abnormal vibration frequency deviation rate of conveyor belt a within a preset time period, T′ a , A′ a and f′ a are respectively the standard temperature, standard vibration amplitude and standard vibration frequency of preset conveyor belt a, r′, r″ and r″′ are respectively the preset standard abnormal temperature deviation rate, standard abnormal vibration amplitude deviation rate and standard abnormal vibration frequency deviation rate, and M is the preset standard conveyor belt abnormal index.

[0030] It should be noted that the standard parameters T′ a , A′ a , f′ a , r′, r″, r″′ and M are all set by the staff. For example, T′ a is 34.5, A′ a is 1.3, f′ a is 0.2, r′ is 0.72, r″ is 0.43, r″′ is 0.52 and M is 1.5.

[0031] In a specific embodiment, for collecting the environmental data of each conveyor belt area, the specific collection process is as follows: Smoke sensors and temperature sensors are set on each conveyor belt. Taking the sensor as the center and the preset length as the radius to make a circle, the area inside the circle is recorded as the conveyor belt area. The dust concentration of each conveyor belt area is collected by the smoke sensor, and the environmental temperature of each conveyor belt area is collected by the temperature sensor.

[0032] In a specific embodiment, the analysis of the environmental data of each belt conveyor area is as follows: The environmental data of each belt conveyor area includes the dust concentration and environmental temperature of each belt conveyor area. The dust concentration and environmental temperature of each belt conveyor area are input into the environmental anomaly model, and the output result of the environmental anomaly model of each belt conveyor area is obtained. The numerical value c of the output result is recorded as the environmental anomaly level of each belt conveyor area, where c = 1, 2... i, i > 2, and i is the maximum environmental anomaly level.

[0033] If the environmental anomaly level of a certain belt conveyor area is 0, it indicates that no warning is required for this area. If the environmental anomaly level of a certain belt conveyor area is greater than 0, the historical environmental anomaly levels of this belt conveyor area within a preset time period are obtained from the database, and the historical environmental anomaly levels of this belt conveyor area within the preset time period are weighted and calculated to obtain the actual anomaly level of this belt conveyor area. If the actual anomaly level of a certain belt conveyor area is greater than or equal to the preset standard anomaly level, a warning is issued, and thus warning analysis is performed on each belt conveyor area.

[0034] It should be noted that in the weighted calculation, the greater the time interval from the current data collection time point, the smaller the weight factor.

[0035] The number of belt conveyor areas with each environmental anomaly level is counted for each belt conveyor area, and the number of belt conveyor areas with each environmental anomaly level is weighted and calculated to obtain the environmental anomaly level of the coal conveying bunker area. The inspection cycle corresponding to the environmental anomaly level of the coal conveying bunker area is obtained from the database.

[0036] It should be noted that in the weighted calculation, the greater the environmental anomaly level, the greater the weight factor.

[0037] In a specific embodiment, the expression of the environmental anomaly model is:

[0038] Among them, β a is the output result of the environmental anomaly model of belt conveyor area a. Each belt conveyor corresponds to each belt conveyor area. B a and C a are respectively the dust concentration and environmental temperature of belt conveyor area a. B' and C' are respectively the preset standard dust concentration and standard environmental temperature. φ 1 and φ 2 are respectively the weight factor of the preset dust concentration and the weight factor of the environmental temperature. φ 1 > 0, φ 2 > 0, φ 1 + φ 2 = 1, N 1 、N 2 、N c 、N c+1and N i are respectively the first environmental anomaly index, the second environmental anomaly index, the c-th environmental anomaly index, the (c + 1)-th environmental anomaly index, and the i-th environmental anomaly index.

[0039] It should be noted that the standard parameters B′, C′, N 1 , N 2 , N c , N c+1 and N i are set in the same process as the above-mentioned standard parameter T′ a . For example, B′ is 5.2, C′ is 30.5, N 1 is 1.2, N 2 is 1.6, N c is 2.4, N c+1 is 2.5, and N i is 4.2. The weight factors φ 1 and φ 2 are set in the same process as the above-mentioned weight factor ε 1 . For example, φ 1 is 0.2 and φ 2 is 0.8.

[0040] The deviation fault warning module is used to collect the transportation data of each belt area according to the inspection cycle, and then analyze the transportation data of each belt area according to the transportation fault model to obtain the transportation anomaly level of each belt area. The corresponding belt sensor acquisition cycle is set according to the transportation anomaly level of each belt area, and the belt data of each belt area is collected accordingly. The belt data of each belt area is analyzed according to the belt anomaly model for early warning.

[0041] In a specific embodiment, the process of collecting the transportation data of each belt area is as follows: The belt transportation area of each belt conveyor is recorded as each belt area. Quality sensors are arranged at the starting point and the ending point of each belt area respectively. At the same time, a camera is set on the unmanned aerial vehicle. When the coal pile is being transported, the weight of each starting collection point and the weight of each ending collection point of each coal pile in each belt area are collected through the quality sensor. At the same time, the starting image and the ending image of each coal pile in each belt area are collected through the camera. The height of each starting collection point and the height of each ending collection point of each coal pile in each belt area are obtained from the starting image and the ending image of each coal pile in each belt area.

[0042] In a specific embodiment, the analysis of the transportation data for each belt area is as follows: The transportation data for each belt area includes the weights of the starting collection points of each coal pile in each belt area, the weights of the ending collection points, the heights of the starting collection points, and the heights of the ending collection points. Calculate the uniformity of the weights of the starting collection points and the ending collection points of each coal pile in each belt area to obtain the uniformity of each coal pile in each belt area. Calculate the deviation rate of the heights of the starting collection points and the ending collection points corresponding to each coal pile in each belt area to obtain the deviation correction rate of each coal pile in each belt area. Input the uniformity and deviation correction rate of each coal pile in each belt area into the transportation fault model to obtain the output result of the transportation fault model for each belt area. The value e of the output result is recorded as the transportation anomaly level of each belt area, where e = 1, 2......x, x > 2, and x is the maximum environmental anomaly level.

[0043] Obtain the basic belt sensor collection period for each belt area from the database. If the transportation anomaly level of a certain belt area is 0, the belt sensor collection period of this belt area is the corresponding basic belt sensor collection period. If the transportation anomaly level of a certain belt area is greater than 0, obtain the period correction rate corresponding to the transportation anomaly level of this belt area from the database, and multiply the basic belt sensor collection period of this belt area by the corresponding period correction rate to obtain the belt sensor collection period for each belt area, thereby obtaining the belt sensor collection period for each belt area.

[0044] In a specific embodiment, the expression of the transportation fault model is:

[0045] where γd is the output result of the transportation fault model for belt area d, d is the number of the belt area, d = 1, 2......j, j > 2, G dg and H dg are the uniformity and deviation correction rate corresponding to coal pile g in belt area d, g is the number of the coal pile, g = 1, 2......s, s > 2, s is the value of the total amount of coal piles, G′ and H′ are the preset standard uniformity and standard deviation correction rate respectively, and are the preset weight factors for uniformity and deviation correction rate respectively, W 1 、W 2 、W e 、W e+1 and W x are the preset first transportation fault index, second transportation fault index, e-th transportation fault index, (e + 1)-th transportation fault index, and x-th transportation fault index respectively.

[0046] It should be noted that the standard parameters G′, H′, W 1 , W 2 , W e , W e+1 and W x are set in the same process as the above-mentioned standard parameter T′ a . For example, G′ is 1.5, H′ is 1.7, W 1 is 1.3, W 2 is 1.6, W e is 3.4, W e+1 is 3.7 and W x is 4.9. The weighting factors and are set in the same process as the above-mentioned weighting factor ε 1 . For example is 4.3 and is 5.7.

[0047] In a specific embodiment, the belt data of each belt area is collected as follows: the drum pictures and idler pictures are collected through the camera of the drone, the drum center offset and idler center offset of each belt area are obtained from the drum pictures and idler pictures, a stress sensor is set under the belt of the belt conveyor, a circle is drawn with the stress sensor as the center and a preset length as the radius, and the area inside the circle is recorded as the collection area, so as to obtain each collection area, and the stress of each collection area corresponding to each belt area is collected through the stress sensor.

[0048] In a specific embodiment, the analysis of the belt data of each belt area is as follows: the belt data of each belt area includes the drum center offset, idler center offset and stress of each collection area of each belt area. The drum center offset, idler center offset and stress of each collection area of each belt area are input into the belt anomaly model to obtain the output result of the belt anomaly model of each belt area. The value t of the output result is recorded as the environmental anomaly level of each belt conveyor area, t = 1, 2......y, y > 2, and y is the maximum environmental anomaly level.

[0049] If the output result of the belt anomaly model of a certain belt area is greater than 0, the belt historical anomaly levels of each inspection cycle of this belt area are obtained from the database, the belt historical anomaly levels of each inspection cycle of this belt area are statistically analyzed to obtain the occurrence times of each historical anomaly level of this belt area, and weighted calculation is performed to obtain the anomaly index of this belt area. If the anomaly level of this belt area is greater than the preset anomaly level or the anomaly index is greater than the preset standard anomaly index, a warning prompt is given.

[0050] It should be noted that in the process of weighted calculation, the higher the historical anomaly level, the greater the weighting factor of the occurrence times of the historical anomaly level.

[0051] In a specific embodiment, the expression of the belt anomaly model is:

[0052] where ρ d is the output result of the belt anomaly model for the belt area d, and are the offset of the center of the roller and the offset of the center of the idler in the belt area d, respectively, and are the preset standard offset of the center of the roller and the standard offset of the center of the idler, respectively. F dp is the stress of the acquisition area p in the belt area d, p is the acquisition area number, p = 1, 2... q, q > 2, q is the value of the total number of acquisition areas, and F′ d is the preset standard stress of the belt area d. η 1 、η 2 and η 3 are the preset weight factors of the offset of the center of the roller, the weight factor of the offset of the center of the idler, and the weight factor of the stress. V 1 、V 2 、V t 、V t+1 and V y are the preset first belt anomaly index, second belt anomaly index, t-th belt anomaly index, (t + 1)-th belt anomaly index, and y-th belt anomaly index, respectively.

[0053] It should be noted that the standard parameters F′ d 、V 1 、V 2 、V t 、V t+1 and V y are set in the same process as the above standard parameter T′ a . For example is 1.2, is 0.75, F′ d is 1.23, V 1 is 1.45, V 2 is 1.56, V t is 2.58, V t+1 is 2.63, and V y is 3.75. The weight factors η 1 、η 2 and η 3 are set in the same process as the above weight factor ε 1 . For example, η 1 is 0.35, η 2 is 0.35, and η 3 is 0.3.

[0054] A database for storing historical anomaly level data, the historical levels of various environmental anomalies in the belt conveyor area within a preset duration, the acquisition periods of the basic belt sensors in each belt area, the cycle correction rates corresponding to each transportation anomaly level, and the historical anomaly levels of each belt in each belt area.

[0055] The above content is only an example and illustration of the concept of the present invention. Those skilled in the art of the present technology can make various modifications or supplements to the described specific embodiments or use similar methods for substitution, as long as they do not deviate from the concept of the invention or exceed the scope defined in this specification, they shall fall within the protection scope of the present invention.

Claims

1. An intelligent inspection and detection system for coal conveyor belt conveyors in coal bunker areas, characterized in that: Includes the following modules: The belt conveyor abnormality analysis module is used to collect abnormal data of each belt conveyor, and then analyze the abnormal data of each belt conveyor based on the belt conveyor abnormality model to obtain each abnormal belt conveyor, and then reset the sensor data collection cycle of each abnormal belt conveyor to collect environmental data of each belt conveyor area. According to the environmental abnormality model, the environmental data of each belt conveyor area is analyzed to obtain the abnormal level of each belt conveyor area, and an early warning is issued according to the abnormal level of each belt conveyor area and the historical abnormal level data in the database. At the same time, the inspection cycle of the coal bunker area is set according to the abnormal level of each belt conveyor area; The deviation fault warning module is used to collect the transportation data of each belt area according to the inspection cycle, and then analyze the transportation data of each belt area according to the transportation fault model to obtain the transportation abnormality level of each belt area. According to the transportation abnormality level of each belt area, the corresponding belt sensor collection cycle is set to collect the belt data of each belt area, and according to the belt abnormality model, the belt data of each belt area is analyzed and early warning is issued.

2. The intelligent inspection and detection system for coal conveyor belt conveyor in coal conveyor bunker area according to claim 1 is characterized in that: The abnormal data of each belt conveyor is analyzed, and the specific analysis process is as follows: The abnormal data of each belt conveyor includes the temperature, vibration amplitude and vibration frequency of each belt conveyor collected within the preset time. If the temperature of a certain belt conveyor collected within the preset time is greater than the preset temperature, or the vibration amplitude of the collection is greater than the preset vibration amplitude, or the vibration frequency of the collection is greater than the preset vibration frequency, the collection of the belt conveyor within the preset time is recorded as abnormal collection, and the abnormal collection of each belt conveyor within the preset time is obtained, and then the temperature, vibration amplitude and vibration frequency of each abnormal collection of each belt conveyor within the preset time are obtained; The highest temperature of the abnormal collection of each belt conveyor within the preset time is divided by the standard abnormal temperature to obtain the temperature deviation rate of each belt conveyor within the preset time, and the vibration amplitude data and the vibration frequency data are analyzed according to the method of analyzing the temperature data to obtain the vibration amplitude deviation rate and the vibration frequency deviation rate of each belt conveyor within the preset time; Input the temperature of each abnormal collection, the vibration amplitude of each abnormal collection, the vibration frequency of each abnormal collection, the abnormal temperature deviation rate, the abnormal vibration amplitude deviation rate and the abnormal vibration frequency deviation rate corresponding to each belt conveyor within a preset time into the belt conveyor abnormal model, and obtain the belt conveyor abnormal model output result of each belt conveyor, and the output result includes the values ​​of 0 and 1; If the output result of the belt conveyor abnormality model of a certain belt conveyor is 0, it means that the belt conveyor is normal, and the sensor data collection period of each belt conveyor is the preset collection period. If the output result of the belt conveyor abnormality model of a certain belt conveyor is 1, it means that the belt conveyor is abnormal and is recorded as an abnormal belt conveyor. The abnormal belt conveyors are obtained abnormally, and the abnormal temperature offset rate, abnormal vibration amplitude offset rate and abnormal vibration frequency offset rate corresponding to each abnormal belt conveyor within the preset time are substituted into the calculation formula of the belt conveyor sensor data collection period to obtain the sensor data collection period of each belt conveyor. According to the sensor data collection period of each belt conveyor, the sensor data collection period of each belt conveyor is enabled to collect the environmental data of each belt conveyor area.

3. The intelligent inspection and detection system for coal conveyor belt conveyor in coal conveyor bunker area according to claim 2 is characterized in that: The belt conveyor abnormal model expression is: ， where α a is the output result of the belt conveyor abnormal model of belt conveyor a, a is the belt conveyor number, a=1,2......m, m>2, m is the total value of the belt conveyor, T ab , A ab and f ab are the temperature, vibration amplitude and vibration frequency of belt conveyor a for b times of abnormal collection within the preset time, b is the number of abnormal collection, b=1,2......n, n>2, r′ a , r″ a and r″′ a are the abnormal temperature deviation rate, abnormal vibration amplitude deviation rate and abnormal vibration frequency deviation rate of belt conveyor a within the preset time, T′ a , A′ a and f′ a are respectively the preset standard temperature, standard vibration amplitude and standard vibration frequency of belt conveyor a, r′, r″ and r″′ are respectively the preset standard abnormal temperature deviation rate, standard abnormal vibration amplitude deviation rate and standard abnormal vibration frequency deviation rate, ε1, ε2 and ε3 are respectively the weight factors of the preset temperature, the weight factor of the vibration amplitude and the weight factor of the vibration frequency, ε1>0, ε2>0, ε3>0, ε1+ε2+ε3=1, and M is the preset standard belt conveyor abnormality index.

4. The intelligent inspection and detection system for coal conveyor belt conveyor in coal conveyor bunker area according to claim 1 is characterized in that: The environmental data of each belt conveyor area is analyzed, and the specific analysis process is as follows: The environmental data of each belt conveyor area includes the dust concentration and the ambient temperature of each belt conveyor area. The dust concentration and the ambient temperature of each belt conveyor area are input into the environmental anomaly model to obtain the output result of the environmental anomaly model of each belt conveyor area. The value c of the output result is recorded as the environmental anomaly level of each belt conveyor area, c=1,2......i, i>2, i is the maximum environmental anomaly level; If the environmental anomaly level of a belt conveyor area is 0, it indicates that no early warning is required for the area. If the environmental anomaly level of a belt conveyor area is greater than 0, the historical levels of environmental anomalies of the belt conveyor area within a preset time period are obtained from the database, and the historical levels of environmental anomalies of the belt conveyor area within the preset time period are weighted to obtain the actual abnormality level of the belt conveyor area. If the actual abnormality level of a belt conveyor area is greater than or equal to the preset standard abnormality level, an early warning is issued, thereby performing early warning analysis on each belt conveyor area. Statistics are collected on each belt conveyor area for each environmental abnormality level to obtain the number of belt conveyor areas with each environmental abnormality level. Weighted calculation is performed on the number of belt conveyor areas with each environmental abnormality level to obtain the environmental abnormality level of the coal conveyor bunker area. The inspection cycle corresponding to the environmental abnormality level of the coal conveyor bunker area is obtained from the database.

5. The intelligent inspection and detection system for coal conveyor belt conveyor in coal conveyor bunker area according to claim 4 is characterized in that: The environmental anomaly model expression is: Among them, β a is the output result of the environmental anomaly model of belt conveyor area a. Each belt conveyor corresponds to each belt conveyor area. B a and C a are the dust concentration and ambient temperature of belt conveyor area a, B′ and C′ are the preset standard dust concentration and standard ambient temperature, φ1 and φ2 are the preset weight factors of dust concentration and ambient temperature, φ1>0, φ2>0, φ1+φ2=1, N1, N2, N c 、N c+1 and Ni are the first environmental anomaly index, the second environmental anomaly index, the cth environmental anomaly index, the c+1th environmental anomaly index and the ith environmental anomaly index respectively.

6. The intelligent inspection and detection system for coal conveyor belt conveyors in coal bunker area according to claim 1 is characterized in that: The transportation data of each belt area is analyzed, and the specific analysis process is as follows: The transportation data of each belt area includes the weight of each starting collection point of each coal pile in each belt area, the weight of each end collection point, the height of each starting collection point and the height of each end collection point. The weight of each starting collection point and the weight of each end collection point of each coal pile in each belt area are uniformly calculated to obtain the uniformity of each coal pile in each belt area. The height of each starting collection point and the height of each end collection point corresponding to each coal pile in each belt area are offset calculated to obtain the offset correction rate of each coal pile in each belt area. The uniformity and offset correction rate of each coal pile in each belt area are input into the transportation fault model to obtain the output result of the transportation fault model of each belt area. The output value e is recorded as the transportation abnormality level of each belt area, e=1,2...x, x>2, x is the maximum environmental abnormality level; The basic belt sensor acquisition period of each belt area is obtained from the database. If the transportation abnormality level of a belt area is 0, the belt sensor acquisition period of the belt area is the corresponding basic belt sensor acquisition period. If the transportation abnormality level of a belt area is greater than 0, the period correction rate corresponding to the transportation abnormality level of the belt area is obtained from the database, and the basic belt sensor acquisition period of the belt area is multiplied by the corresponding period correction rate to obtain the belt sensor acquisition period of each belt area.

7. The intelligent inspection and detection system for coal conveyor belt conveyors in coal bunker area according to claim 6 is characterized in that: The transportation failure model expression is: Where γd is the output result of the transport fault model of belt area d, d is the number of the belt area, d=1,2......j, j>2, G dg and H dg is the uniformity and deviation correction rate corresponding to the coal pile g in the belt area d, g is the number of the coal pile, g = 1, 2...s, s> 2, s is the total value of the coal pile, G' and H' are the preset standard uniformity and standard deviation correction rate, respectively. and are the preset uniformity weight factor and offset correction rate weight factor, respectively. W1, W2, W e , W e+1 and W x They are respectively the preset first transport failure index, the second transport failure index, the e-th transport failure index, the e+1-th transport failure index and the x-th transport failure index.

8. The intelligent inspection and detection system for coal conveyor belt conveyors in coal bunker area according to claim 1 is characterized in that: The belt data of each belt area is analyzed, and the specific analysis process is as follows: The belt data of each belt area include the center offset of the drum, the center offset of the idler and the stress of each collection area of ​​each belt area. The center offset of the drum, the center offset of the idler and the stress of each collection area of ​​each belt area are input into the belt anomaly model to obtain the output result of the belt anomaly model of each belt area. The value t of the output result is recorded as the environmental anomaly level of each belt conveyor area. t=1,2......y, y>2, y is the maximum environmental abnormality level; If the output result of the belt abnormality model of a certain belt area is greater than 0, the historical belt abnormality levels of each inspection cycle of the belt area are obtained from the database, and the historical belt abnormality levels of each inspection cycle of the belt area are counted to obtain the number of occurrences of each historical abnormality level of the belt area, and weighted calculation is performed to obtain the abnormality index of the belt area. If the abnormality level of the belt area is greater than the preset abnormality level or the abnormality index is greater than the preset standard abnormality index, an early warning prompt is issued.

9. The intelligent inspection and detection system for coal conveyor belt conveyors in coal bunker area according to claim 8 is characterized in that: The belt abnormality model expression is: ， where ρ d is the output result of the belt anomaly model for belt area d, and are the center offset of the drum and the center offset of the idler in belt area d, and They are the preset standard drum center offset and standard roller center offset, F dp is the stress of the collection area p of the belt area d, p is the collection area number, p=1,2......q,q>2, q is the value of the total amount of the collection area, F′ d is the standard stress of the preset belt area d, η1, η2 and η3 are the preset weight factors of the drum center offset, the roller center offset and the stress, V1, V2, V t 、V t+1 and V y They are respectively the preset first belt abnormality index, the second belt abnormality index, the tth belt abnormality index, the t+1th belt abnormality index and the yth belt abnormality index.

10. The intelligent inspection and detection system for coal conveyor belt conveyors in coal bunker area according to claim 1, characterized in that: It also includes a database for storing historical abnormality level data, historical environmental abnormality levels of the belt conveyor area within a preset time period, basic belt sensor collection cycles of each belt area, cycle correction rates corresponding to each transport abnormality level, and historical abnormality levels of each belt in each belt area.

Images