Coal transportation monitoring method and device, electronic equipment and storage medium

Abstract

The invention provides a coal transportation monitoring method and device, electronic equipment and a storage medium, and relates to the technical field of data processing, and the main technical scheme comprises the steps: obtaining the monitoring data of to-be-monitored equipment, inputting the monitoring data into a trained monitoring model for feature extraction processing, and obtaining a feature extraction result of the to-be-monitored equipment; obtaining a target coal flow area and a belt edge line of the to-be-monitored equipment; determining a belt area of the to-be-monitored equipment according to the belt edge line, and performing ratio calculation according to the target coal flow area and the belt area to obtain target coal flow; performing distance calculation according to the belt edge line and a preset reference edge line to obtain a belt deviation value of the to-be-monitored equipment; and under the condition that the belt deviation value is larger than or equal to a preset deviation threshold value, first alarm information is sent, and operation of the to-be-monitored equipment is stopped. Compared with the prior art, according to the embodiment of the invention, the functions of belt deviation detection and coal flow detection can be realized through a trained monitoring model, and the occupation of server resources is reduced.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, and in particular to a monitoring method and device, electronic equipment and storage medium for coal transportation. Background Art

[0002] At present, the main transportation equipment for coal in coal mines is belt conveyor, which is one of the main equipment for coal transportation. Mining operations usually use belt conveyors to transport the mined coal from the working face to the processing plant over long distances. During long-term operation of belt conveyors, the belts may deviate, resulting in material overflow and damage to transportation equipment.

[0003] In order to solve this problem, it is necessary to perform belt deviation detection and coal flow detection on the belt conveyor during coal transportation. The purpose of coal flow detection is to regulate the speed of the belt conveyor. When the coal flow is small, the belt transportation speed of the belt conveyor is small. When the coal flow is large, the belt transportation speed of the belt conveyor is large to reduce energy consumption. Due to the different identification targets, belt deviation detection and coal flow detection are often completed as two independent tasks. The method for belt deviation detection and coal flow detection is to use different models for each, train them separately, and then perform detection separately through the trained models.

[0004] However, in the prior art, when belt deviation detection and coal flow detection are run simultaneously with other models on a server or edge computing device, belt deviation detection and coal flow detection will occupy two resources in the server, which may easily cause the server to crash when the model is relatively large. Summary of the invention

[0005] The present disclosure provides a coal transportation monitoring method and device, electronic device and storage medium. The main purpose is to solve the problem in the prior art that when belt deviation detection and coal flow detection are run on a server or edge computing device at the same time as other models, the belt deviation detection and coal flow detection will occupy two resources in the server, and when the model is relatively large, it is easy to cause the server to crash.

[0006] According to a first aspect of the present disclosure, a method for monitoring coal transportation is provided, comprising:

[0007] Acquire monitoring data of the equipment to be monitored, and input the monitoring data into a trained monitoring model for feature extraction processing to obtain a target coal flow area and a belt edge line of the equipment to be monitored; wherein the target coal flow area is the area occupied by the coal transported by the equipment to be monitored;

[0008] Determine the belt area of ​​the device to be monitored according to the belt edge line, and calculate the ratio between the target coal flow area and the belt area to obtain the target coal flow rate;

[0009] Calculate the distance between the belt edge line and the preset reference edge line to obtain the belt deviation value of the device to be monitored;

[0010] When the belt deviation value is greater than or equal to a preset deviation threshold, a first alarm message is sent and the operation of the device to be monitored is stopped.

[0011] Optionally, the calculating a ratio between the target coal flow area and the belt area to obtain a target coal flow rate includes:

[0012] Performing data division processing on the monitoring data to obtain first monitoring data, and determining a first coal flow area according to the first monitoring data and the target coal flow area;

[0013] The first belt area is determined according to the first monitoring data and the belt area, and the target coal flow rate is obtained by calculating the ratio of the first coal flow area to the first belt area.

[0014] Optionally, the calculating the distance between the belt edge line and a preset reference edge line to obtain the belt deviation value of the device to be monitored includes:

[0015] Dividing the belt edge line to obtain a plurality of first belt edge lines;

[0016] Calculating the distance between each of the plurality of first belt edge lines and the preset reference edge line respectively to obtain a plurality of first deviation values;

[0017] An average value is calculated for the multiple first deviation values ​​to obtain the belt deviation value.

[0018] Optionally, after calculating the ratio between the target coal flow area and the belt area to obtain the target coal flow rate, the method further includes:

[0019] Determining whether the target coal flow rate is less than a preset coal flow threshold;

[0020] If the target coal flow rate is less than the preset coal flow threshold, adjusting the belt speed of the device to be monitored according to the target coal flow rate;

[0021] If the target coal flow rate is greater than or equal to the preset coal flow threshold, a second alarm message is sent and the operation of the equipment to be monitored is stopped.

[0022] Optionally, the step of inputting the monitoring data into a trained monitoring model for feature extraction processing to obtain the target coal flow area and the belt edge line of the equipment to be monitored includes:

[0023] Based on the trained monitoring model, feature extraction processing is performed from the monitoring data to obtain the target coal flow area;

[0024] Based on the trained monitoring model, determining the line area in the monitoring data, and extracting the center line of the line area by a preset pixel algorithm;

[0025] The center line is subjected to straight line fitting processing to obtain the belt edge line.

[0026] Optionally, before acquiring the monitoring data of the device to be monitored, the method further includes:

[0027] Acquire a preset amount of training monitoring data, and extract and process the training monitoring data using a preset extraction algorithm to obtain first training data;

[0028] Performing data enhancement processing on the first training data by using a preset enhancement algorithm to obtain second training data;

[0029] The training belt edge line and the training coal flow area in the second training data are labeled using a preset labeling algorithm to obtain target training data.

[0030] Optionally, after labeling the training belt edge line and the training coal flow area in the second training data by a preset labeling algorithm to obtain target training data, the method further includes:

[0031] Performing data division processing on the target training data to obtain a training data set, a verification data set, and a test data set;

[0032] Inputting the training data set into the monitoring model for model training processing to obtain a first monitoring model;

[0033] Performing model verification processing on the first monitoring model using the verification data set to obtain a second monitoring model;

[0034] The second monitoring model is subjected to model testing processing using the test data set to obtain the trained monitoring model.

[0035] According to a second aspect of the present disclosure, a monitoring device for coal transportation is provided, comprising:

[0036] A first acquisition unit, used to acquire monitoring data of a device to be monitored;

[0037] An input unit, used to input the monitoring data into a trained monitoring model for feature extraction processing to obtain a target coal flow area and a belt edge line of the equipment to be monitored; wherein the target coal flow area is an area occupied by the coal transported by the equipment to be monitored;

[0038] A first determining unit, configured to determine a belt area of ​​the device to be monitored according to the belt edge line;

[0039] A first calculation unit, configured to calculate a ratio between the target coal flow area and the belt area to obtain a target coal flow rate;

[0040] A second calculation unit is used to calculate the distance between the belt edge line and a preset reference edge line to obtain the belt deviation value of the device to be monitored;

[0041] The processing unit is used to send a first alarm message and stop the operation of the device to be monitored when the belt deviation value is greater than or equal to a preset deviation threshold.

[0042] Optionally, the first computing unit includes:

[0043] A division module, used for performing data division processing on the monitoring data to obtain first monitoring data;

[0044] A determination module, configured to determine a first coal flow area according to the first monitoring data and the target coal flow area;

[0045] The determination module is further used to determine a first belt area according to the first monitoring data and the belt area;

[0046] A calculation module is used to calculate the ratio of the first coal flow area to the first belt area to obtain the target coal flow rate.

[0047] Optionally, the second computing unit includes:

[0048] A division module, used for dividing the belt edge line to obtain a plurality of first belt edge lines;

[0049] A calculation module, used for respectively calculating the distance between each of the plurality of first belt edge lines and the preset reference edge line to obtain a plurality of first deviation values;

[0050] The calculation module is further used to calculate an average value of the multiple first deviation values ​​to obtain the belt deviation value.

[0051] Optionally, the device further comprises:

[0052] A second determination unit, configured to determine whether the target coal flow rate is less than a preset coal flow threshold;

[0053] an adjusting unit, configured to adjust the belt speed of the device to be monitored according to the target coal flow rate when the target coal flow rate is less than the preset coal flow rate threshold;

[0054] The processing unit is also used to send a second alarm message and stop the operation of the device to be monitored when the target coal flow rate is greater than or equal to the preset coal flow threshold.

[0055] Optionally, the input unit includes:

[0056] An extraction module, used for performing feature extraction processing from the monitoring data based on the trained monitoring model to obtain the target coal flow area;

[0057] A determination module, used to determine the line area in the monitoring data based on the trained monitoring model;

[0058] The extraction module is also used to extract the center line of the line area through a preset pixel algorithm;

[0059] The fitting module is used to perform straight line fitting processing on the center line to obtain the belt edge line.

[0060] Optionally, the device further comprises:

[0061] A second acquisition unit is used to acquire a preset amount of training monitoring data, and extract and process the training monitoring data using a preset extraction algorithm to obtain first training data;

[0062] an enhancement unit, configured to perform data enhancement processing on the first training data by using a preset enhancement algorithm to obtain second training data;

[0063] The labeling unit is used to label the training belt edge line and the training coal flow area in the second training data by using a preset labeling algorithm to obtain target training data.

[0064] Optionally, the device further comprises:

[0065] A partitioning unit, used to perform data partitioning processing on the target training data to obtain a training data set, a verification data set, and a test data set;

[0066] A training unit, used for inputting the training data set into the monitoring model for model training processing to obtain a first monitoring model;

[0067] A verification unit, configured to perform model verification processing on the first monitoring model using the verification data set to obtain a second monitoring model;

[0068] The testing unit is used to perform model testing on the second monitoring model through the test data set to obtain the trained monitoring model.

[0069] According to a third aspect of the present disclosure, there is provided an electronic device, including:

[0070] at least one processor; and

[0071] a memory communicatively connected to the at least one processor; wherein,

[0072] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect.

[0073] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the method described in the first aspect.

[0074] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the method as described in the first aspect above.

[0075] The coal transportation monitoring method and device, electronic device and storage medium provided in the present disclosure obtain monitoring data of the equipment to be monitored, and input the monitoring data into a trained monitoring model for feature extraction processing to obtain a target coal flow area and a belt edge line of the equipment to be monitored; wherein the target coal flow area is the area occupied by the coal transported by the equipment to be monitored; the belt area of ​​the equipment to be monitored is determined according to the belt edge line, and a ratio calculation is performed between the target coal flow area and the belt area to obtain a target coal flow rate; a distance calculation is performed between the belt edge line and a preset reference edge line to obtain a belt deviation value of the equipment to be monitored; when the belt deviation value is greater than or equal to a preset deviation threshold, a first alarm message is sent and the operation of the equipment to be monitored is stopped. Compared with the related art, the embodiment of the present disclosure monitors and processes the monitoring data through a trained monitoring model, and detects whether the belt is deviating by calculating the distance between the real-time edge line (belt edge line) and the set belt edge line (preset reference line) or the safety area. At the same time, the size of the coal flow is calculated according to the proportion of the extracted coal flow area in the entire belt area (belt area). The functions of belt deviation detection and coal flow detection can be realized through a trained monitoring model, reducing the occupancy of server resources.

[0076] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0078] Figure 1 A schematic diagram of a flow chart of a method for monitoring coal transportation provided by an embodiment of the present disclosure;

[0079] Figure 2 A schematic diagram of a belt edge and a coal flow area provided by an embodiment of the present disclosure;

[0080] Figure 3 A schematic diagram of a flow chart for calculating a target coal flow rate provided by an embodiment of the present disclosure;

[0081] Figure 4 A schematic diagram of a flow chart of calculating a belt deviation value provided by an embodiment of the present disclosure;

[0082] Figure 5 A schematic diagram of a coal transportation monitoring system provided by an embodiment of the present disclosure;

[0083] Figure 6 A schematic diagram of the structure of a monitoring device for coal transportation provided by an embodiment of the present disclosure;

[0084] Figure 7 A schematic diagram of the structure of another monitoring device for coal transportation provided by an embodiment of the present disclosure;

[0085] Figure 8 A schematic block diagram of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0086] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0087] The following describes the coal transportation monitoring method and device, electronic device and storage medium according to the embodiments of the present disclosure with reference to the accompanying drawings.

[0088] Figure 1 A schematic flow chart of a method for monitoring coal transportation provided in an embodiment of the present disclosure.

[0089] like Figure 1 As shown, the method comprises the following steps:

[0090] Step 101, obtain monitoring data of the equipment to be monitored, and input the monitoring data into a trained monitoring model for feature extraction processing to obtain a target coal flow area and a belt edge line of the equipment to be monitored; wherein the target coal flow area is the area occupied by the coal transported by the equipment to be monitored.

[0091] In the embodiment of the present disclosure, the equipment to be monitored is equipment for coal transportation, including but not limited to: belt conveyors, scraper conveyors, bucket elevators, etc. Specifically, the embodiment of the present disclosure does not limit the type of the equipment to be monitored.

[0092] The trained monitoring model is a pre-trained model, and the structure of the trained monitoring model is a custom selected model structure, for example: an improved DeepLab V3+ network, etc. Specifically, the structure of the trained monitoring model can be selected according to actual conditions, and the embodiments of the present disclosure do not limit it.

[0093] The monitoring data is the data collected in real time during the coal transportation process of the monitored equipment. The types of the monitoring data include but are not limited to: videos, pictures, etc. The belt deviation and coal flow size of the monitored equipment during the coal transportation process can be monitored in real time through the monitoring data. Among them, the belt edge line is the edge of the belt of the monitored equipment, including two lines, namely the two edges of the belt.

[0094] Step 102, determining the belt area of ​​the device to be monitored according to the belt edge line, and calculating the ratio between the target coal flow area and the belt area to obtain the target coal flow rate.

[0095] In the disclosed embodiment, when determining the belt area, it can be determined directly based on the belt edge line. When calculating the target coal flow, the target coal flow can be obtained by performing a ratio calculation based on the pixel area occupied by the target coal flow area and the pixel area occupied by the belt area.

[0096] It should be noted that when calculating the target coal flow, the monitoring data needs to be divided before calculation. For example, the video image (monitoring data) is divided into three equal parts, and the image in the middle part is taken as the coal flow size calculation part. Dividing the monitoring data before calculating the coal flow size can improve the accuracy of the coal flow size calculation.

[0097] Step 103, calculating the distance between the belt edge line and a preset reference edge line to obtain the belt deviation value of the device to be monitored.

[0098] In the disclosed embodiment, the preset reference edge line is the position of the edge of the belt of the monitored device when the belt is not deviated. The deviation of the belt can be intuitively determined by the distance between the belt edge line and the preset reference edge line.

[0099] At the same time, in order to reduce the error, the belt edge line can be divided into a preset number of equal parts, and the distance between each part and the preset reference edge line can be calculated, and finally the average value can be taken to determine the belt deviation value. For example: divide the belt edge line into five equal parts, measure the distances of the four middle positions, and average the distances between the left and right edge lines. Then, average the distance results of the left and right edge lines to obtain the distance detected at a certain moment.

[0100] Step 104: When the belt deviation value is greater than or equal to a preset deviation threshold, a first alarm message is sent and the operation of the device to be monitored is stopped.

[0101] In the embodiment of the present disclosure, the preset deviation threshold is a custom-set value, for example, 10 cm, 15 cm, etc. Specifically, the preset deviation threshold can be set according to actual conditions, and the embodiment of the present disclosure does not limit it.

[0102] When it is detected that the belt deviation value is greater than or equal to the preset deviation threshold, the belt is determined to be deviated, and a first alarm message needs to be issued and transmitted to a preset location (for example: a monitoring room, a mobile terminal, etc.). At the same time, the controller will automatically stop the operation of the monitored equipment to prevent more serious accidents.

[0103] Specifically, regarding the position of the coal flow area and the belt edge line, the present disclosure provides a schematic diagram of the belt edge and the coal flow area, such as Figure 2 As shown, when the belt edge appears outside the belt deviation safety range, it means that the belt deviation value is greater than or equal to the preset deviation threshold, and the belt is determined to be deviated.

[0104] The coal transportation monitoring method provided by the present disclosure obtains monitoring data of the equipment to be monitored, and inputs the monitoring data into a trained monitoring model for feature extraction processing to obtain a target coal flow area and a belt edge line of the equipment to be monitored; wherein the target coal flow area is the area occupied by the coal transported by the equipment to be monitored; the belt area of ​​the equipment to be monitored is determined according to the belt edge line, and a ratio calculation is performed based on the target coal flow area and the belt area to obtain a target coal flow rate; a distance calculation is performed based on the belt edge line and a preset reference edge line to obtain a belt deviation value of the equipment to be monitored; when the belt deviation value is greater than or equal to a preset deviation threshold, a first alarm message is sent and the operation of the equipment to be monitored is stopped. Compared with the related art, the embodiment of the present disclosure monitors and processes the monitoring data through a trained monitoring model, and detects whether the belt is deviating by calculating the distance between the real-time edge line (belt edge line) and the set belt edge line (preset reference line) or the safety area. At the same time, the size of the coal flow is calculated according to the proportion of the extracted coal flow area in the entire belt area (belt area). The functions of belt deviation detection and coal flow detection can be realized through a trained monitoring model, reducing the occupancy of server resources.

[0105] In one possible implementation of the embodiment of the present disclosure, regarding the calculation of the target coal flow rate, the embodiment of the present disclosure provides a flow chart of the calculation of the target coal flow rate, such as Figure 3 As shown, including:

[0106] Step 301 : performing data division processing on the monitoring data to obtain first monitoring data, and determining a first coal flow area according to the first monitoring data and the target coal flow area.

[0107] In the embodiments of the present disclosure, when the monitoring data is divided, the monitoring data is divided evenly, for example: the video image (monitoring data) is divided into three equal parts, the video image is divided into four equal parts, etc. The first monitoring data is a part of the data selected after the monitoring data is divided evenly, for example: the video image is divided into three equal parts, and the image of the middle part is taken as the first monitoring data, the video image is divided into four equal parts, and the images of the two middle parts are taken as the first monitoring data, etc. Specifically, the division of the monitoring data and the selection of the first monitoring data can be determined according to actual conditions, and the embodiments of the present disclosure do not limit it.

[0108] The first coal flow area is a coal flow area obtained after data division of the monitoring data, that is, a coal flow area or a part of the coal flow area in the first monitoring data.

[0109] Step 302: determine the first belt area according to the first monitoring data and the belt area, and calculate the ratio between the first coal flow area and the first belt area to obtain the target coal flow rate.

[0110] In the embodiment of the present disclosure, the first belt area is a belt area obtained after data division is performed on the monitoring data, that is, a belt area or a part of a belt area in the first monitoring data.

[0111] Specifically, when calculating the target coal flow, for example: the size of the video image (monitoring data) is 1920*1080, the video picture is divided into three equal parts, that is, the image of the 360-720 pixel part in the vertical 1080 pixels, and the proportion of the coal flow to the entire belt is determined according to the ratio of the identified first coal flow area to the first belt area to obtain the target coal flow.

[0112] The target coal flow rate can be calculated by, but not limited to, formula (1):

[0113]

[0114] Among them, S pi is the pixel area of ​​the first coal flow area, S pj The pixel area of ​​the first belt area, the pixel area of ​​the first coal flow area, and the pixel area of ​​the first belt area can be directly obtained through the trained monitoring model.

[0115] In one possible implementation of the embodiment of the present disclosure, regarding the calculation of the belt deviation value, the embodiment of the present disclosure provides a flowchart of the calculation of the belt deviation value, such as Figure 4 As shown, including:

[0116] Step 401, dividing the belt edge line to obtain a plurality of first belt edge lines.

[0117] In the embodiment of the present disclosure, when dividing the belt edge line, the belt edge line is divided equally, for example: dividing the belt edge line into three equal parts, dividing the belt edge line into five equal parts, etc. Specifically, the embodiment of the present disclosure does not limit the number of parts into which the belt edge line is divided.

[0118] The multiple first belt edge lines are all edge lines obtained after the belt edge line is evenly divided. For example, dividing the belt edge line into three equal parts will result in three first belt edge lines, dividing the belt edge line into five equal parts will result in five belt edge lines, and so on.

[0119] It should be noted here that the belt edge line represents two edges of the belt of the device to be monitored. Similarly, the first belt edge line represents two edges of the belt of the device to be monitored after division.

[0120] Step 402 , respectively calculating the distance between each of the plurality of first belt edge lines and the preset reference edge line to obtain a plurality of first deviation values.

[0121] In the disclosed embodiment, each first belt edge line needs to be calculated with a preset reference edge line to determine the distance between each first belt edge line and the preset reference edge line, i.e., a plurality of first deviation values. Each of the first deviation values ​​includes the deviation values ​​of the two edges of the belt of the device to be monitored, i.e., the distance between the left and right belt edges and the left and right standard edge lines.

[0122] Since the first belt edge line represents two edges (left and right belt edges) of the belt of the device to be monitored, similarly, the preset reference edge line represents two edges (left and right standard edges). When calculating the distance value, the left edge of the first belt edge line is calculated with the left edge of the preset reference edge line, and the right edge of the first belt edge line is calculated with the right edge of the preset reference edge line.

[0123] Step 403: Calculate the average value of the multiple first deviation values ​​to obtain the belt deviation value.

[0124] In the embodiment of the present disclosure, the belt deviation value may be calculated by, but not limited to, formula (2):

[0125]

[0126] Among them, d i ,d j They are the distances between the left and right belt edges and the standard edge line. In order to reduce the error, the belt edge line is divided into n equal parts, and the distances of n positions are measured to get the average distance between the left and right edge lines. Then the distance results of the left and right edge lines are averaged to get the distance detected at a certain moment.

[0127] In one implementable method of the embodiment of the present disclosure, after performing coal flow detection to determine the target coal flow, it is necessary to determine whether the target coal flow is too large. When the target coal flow is too large, it is also necessary to alarm and stop the operation of the monitored equipment to avoid accidents. When the target coal flow is not too large, the belt speed can be adjusted according to the size of the target coal flow to save energy. Therefore, for safety and energy saving during coal transportation, the following method can also be used but is not limited to: determine whether the target coal flow is less than a preset coal flow threshold; if the target coal flow is less than the preset coal flow threshold, adjust the belt speed of the monitored equipment according to the target coal flow; if the target coal flow is greater than or equal to the preset coal flow threshold, send a second alarm message and stop the operation of the monitored equipment.

[0128] In the embodiment of the present disclosure, the preset coal flow threshold is a custom-set value, for example: 1000t / h, 1500t / h, etc. Specifically, the setting of the preset coal flow threshold can be determined based on the design capacity of the monitored equipment, bandwidth, speed, inclination, coal characteristics (such as particle size, humidity, shape, etc.) and other conditions, and the embodiment of the present disclosure is not limited.

[0129] When it is detected that the target coal flow rate is greater than or equal to the preset coal flow threshold, it is determined that the monitored equipment is overloaded, and a second alarm message needs to be issued and transmitted to a preset location (for example: monitoring room, mobile terminal, etc.). At the same time, the controller will automatically stop the operation of the monitored equipment to prevent more serious accidents.

[0130] In one implementable method of the embodiment of the present disclosure, when obtaining the belt edge line, it can also be implemented by but not limited to the following methods: based on the trained monitoring model, feature extraction processing is performed from the monitoring data to obtain the target coal flow area; based on the trained monitoring model, the line area in the monitoring data is determined, and the center line of the line area is extracted through a preset pixel algorithm; the center line is fitted with a straight line to obtain the belt edge line.

[0131] In the embodiment of the present disclosure, the preset pixel algorithm is a custom-set algorithm, such as the Steger algorithm, etc. Specifically, the embodiment of the present disclosure does not limit the setting of the preset pixel algorithm.

[0132] Among them, the Steger algorithm is used to extract the center line of the line area in the image at the sub-pixel level, and then fit it into a straight line, which is the edge line of the belt.

[0133] In one implementable manner of the disclosed embodiment, in order to accurately perform belt deviation detection and coal flow detection, it is necessary to train a monitoring model. When training the model, it is necessary to pre-produce a data set to enhance the processing capability of the trained model. Therefore, in order to train a model with stronger processing capability, the following method may be used but is not limited to: obtaining a preset number of training monitoring data, and extracting and processing the training monitoring data through a preset extraction algorithm to obtain first training data; performing data enhancement processing on the first training data through a preset enhancement algorithm to obtain second training data; and labeling the training belt edge line and the training coal flow area in the second training data through a preset labeling algorithm to obtain target training data.

[0134] In the embodiment of the present disclosure, the preset extraction algorithm is a custom algorithm, such as OpenCV, etc., and the preset enhancement algorithm is also a custom algorithm, such as horizontal flip, vertical flip, salt and pepper noise, Gaussian blur, etc. The preset labeling algorithm is also a custom algorithm, such as Labelme, etc. Specifically, the preset extraction algorithm, the preset enhancement algorithm, and the preset labeling algorithm are not limited in the embodiment of the present disclosure.

[0135] The acquisition of the target training data can be achieved by, but not limited to, the following methods: video data is collected from the coal transportation site, and 1,000 valid coal transportation images are extracted using OpenCV, with an average size of 1920*1080 pixels. The larger the training data set, the stronger the generalization ability of the trained model; therefore, the training data can be increased by expanding the data set to 5,000 images through data enhancement methods such as horizontal flipping, vertical flipping, salt and pepper noise, and Gaussian blur. Labelme is used to annotate the coal transportation images. When annotating, the annotation software Labelme is used to outline the edge of the belt in each image with a white line with a width of 1 pixel and classified as the edge (belt edge line) label, and then the multi-segment line is drawn to classify the coal flow area as the coal (target coal flow area) label, and the target training data is obtained by completing the data set production. Among them, the annotated original image will generate a corresponding json file, which contains annotation information such as annotation labels and annotation point coordinates.

[0136] In one implementable manner of the embodiment of the present disclosure, after the target training data is acquired, model training is required. Regarding the model training process, the following method may also be used but is not limited to: performing data division processing on the target training data to obtain a training data set, a verification data set and a test data set; inputting the training data set into the monitoring model for model training processing to obtain a first monitoring model; performing model verification processing on the first monitoring model through the verification data set to obtain a second monitoring model; performing model testing processing on the second monitoring model through the test data set to obtain the trained monitoring model.

[0137] In the disclosed embodiment, when the model is trained, the dataset can be randomly divided into a training dataset, a validation dataset, and a test dataset in a ratio of 8:1:1, and the dataset is randomly divided into 4,000 training images and 500 test images. At the same time, the training images are cross-validated five times, and the remaining 500 images are tested.

[0138] In one possible implementation of the embodiment of the present disclosure, in order to implement the above-mentioned coal transportation monitoring method, a corresponding coal transportation monitoring system is also provided, the system comprising: an image acquisition device, a light source, an information processing computer, a programmable controller, etc. Figure 5 As shown, Figure 5 A schematic diagram of a coal transportation monitoring system provided in an embodiment of the present disclosure, wherein an image acquisition device is mounted directly above the middle position of a device to be monitored (belt conveyor), and a light source is used as fill light for the image acquisition device.

[0139] The system consists of three parts: a feature extraction module, a measurement and detection module, and an early warning module. When executing the monitoring method for coal transportation, firstly, a semantic segmentation data set is annotated (target training data is determined), and the belt edge area and the coal flow area are annotated for classification and annotation, and then the annotated training data set is input into the improved DeepLab V3+ network for model training to obtain a belt semantic segmentation model (trained monitoring model); the real-time acquired video image (monitoring data) is input into the belt semantic segmentation model, and the belt edge area and the coal flow area (target coal flow area) can be identified in real time, and then the segmented belt edge is subjected to regional centerline extraction, and the obtained centerline (belt edge line) is detected by calculating the distance or safety area between the real-time belt edge line and the set belt edge line (preset reference edge line) to detect whether the belt is deviating, and at the same time, the size of the coal flow can be calculated according to the proportion of the segmented coal flow area in the belt area, and when the belt is detected to be deviating, an alarm is given in time, and the belt deviation is synchronously displayed on the monitoring monitor and the machine is automatically shut down, and at the same time, the speed of the belt can be controlled according to the size of the detected coal flow.

[0140] Among them, the purpose of the feature extraction module is to train the network to automatically segment and identify the belt edge area and coal flow area;

[0141] The principle of the measurement and detection module is to detect whether the belt is deviating by comparing the belt edge line extracted by features with whether it exceeds the designated safety area line. At the same time, the entire belt area is determined based on the identified belt edge area. The proportion of the coal flow area identified by the DeepLab V3+ model to the entire belt area can determine the coal flow rate.

[0142] The early warning module mainly sets a safety threshold and compares the belt deviation with the belt deviation alarm threshold to determine whether the current transport belt is deviating. It determines whether the coal volume is too large by calculating the coal flow rate to the belt area. When the coal volume ratio is higher than the coal volume threshold, an alarm is issued. When deviation is detected, an alarm message is issued and the information is transmitted to the monitoring room. The controller will automatically stop the operation of the belt conveyor to prevent more serious accidents. When the coal volume is detected to be too large, an alarm message is issued to inform the staff and the belt speed is increased.

[0143] In summary, the embodiments of the present disclosure can achieve the following effects:

[0144] The disclosed embodiment monitors and processes the monitoring data through a trained monitoring model, and detects whether the belt is deviating by calculating the distance between the real-time edge line (belt edge line) and the set belt edge line (preset reference line) or the safety area. At the same time, the size of the coal flow is calculated according to the proportion of the extracted coal flow area in the entire belt area (belt area). The functions of belt deviation detection and coal flow detection can be realized through a trained monitoring model, thereby reducing the occupancy of server resources.

[0145] Corresponding to the above-mentioned coal transportation monitoring method, the present invention also provides a coal transportation monitoring device. Since the device embodiment of the present invention corresponds to the above-mentioned method embodiment, the details not disclosed in the device embodiment can be referred to the above-mentioned method embodiment, and will not be repeated in the present invention.

[0146] Figure 6 A schematic diagram of the structure of a monitoring device for coal transportation provided by an embodiment of the present disclosure is shown in FIG. Figure 6 As shown, including:

[0147] The first acquisition unit 601 is used to acquire monitoring data of the device to be monitored;

[0148] The input unit 602 is used to input the monitoring data into the trained monitoring model for feature extraction processing to obtain the target coal flow area and the belt edge line of the equipment to be monitored; wherein the target coal flow area is the area occupied by the coal transported by the equipment to be monitored;

[0149] A first determining unit 603 is used to determine the belt area of ​​the device to be monitored according to the belt edge line;

[0150] A first calculation unit 604 is used to calculate a ratio between the target coal flow area and the belt area to obtain a target coal flow rate;

[0151] A second calculation unit 605 is used to calculate the distance between the belt edge line and a preset reference edge line to obtain the belt deviation value of the device to be monitored;

[0152] The processing unit 606 is used to send a first alarm message and stop the operation of the device to be monitored when the belt deviation value is greater than or equal to a preset deviation threshold.

[0153] The coal transportation monitoring device provided in the present disclosure obtains monitoring data of the equipment to be monitored, and inputs the monitoring data into a trained monitoring model for feature extraction processing to obtain a target coal flow area and a belt edge line of the equipment to be monitored; wherein the target coal flow area is the area occupied by the coal transported by the equipment to be monitored; the belt area of ​​the equipment to be monitored is determined according to the belt edge line, and a ratio calculation is performed between the target coal flow area and the belt area to obtain a target coal flow rate; a distance calculation is performed between the belt edge line and a preset reference edge line to obtain a belt deviation value of the equipment to be monitored; when the belt deviation value is greater than or equal to a preset deviation threshold, a first alarm message is sent and the operation of the equipment to be monitored is stopped. Compared with the related art, the embodiment of the present disclosure monitors and processes the monitoring data through a trained monitoring model, and detects whether the belt is deviating by calculating the distance between the real-time edge line (belt edge line) and the set belt edge line (preset reference line) or the safety area. At the same time, the size of the coal flow is calculated according to the proportion of the extracted coal flow area in the entire belt area (belt area). The functions of belt deviation detection and coal flow detection can be realized through a trained monitoring model, reducing the occupancy of server resources.

[0154] Furthermore, in a possible implementation of the embodiment of the present disclosure, as Figure 7 As shown, the first calculation unit 604 includes:

[0155] A division module 6041 is used to perform data division processing on the monitoring data to obtain first monitoring data;

[0156] A determination module 6042, configured to determine a first coal flow area according to the first monitoring data and the target coal flow area;

[0157] The determination module 6042 is further used to determine a first belt area according to the first monitoring data and the belt area;

[0158] The calculation module 6043 is used to calculate the ratio of the first coal flow area to the first belt area to obtain the target coal flow rate.

[0159] Furthermore, in a possible implementation of the embodiment of the present disclosure, as Figure 7 As shown, the second calculation unit 605 includes:

[0160] A division module 6051 is used to divide the belt edge line to obtain a plurality of first belt edge lines;

[0161] A calculation module 6052 is used to respectively calculate the distance between each of the plurality of first belt edge lines and the preset reference edge line to obtain a plurality of first deviation values;

[0162] The calculation module 6052 is further used to calculate the average value of the multiple first deviation values ​​to obtain the belt deviation value.

[0163] Furthermore, in a possible implementation of the embodiment of the present disclosure, as Figure 7 As shown, the device also includes:

[0164] A second determination unit 607 is used to determine whether the target coal flow rate is less than a preset coal flow threshold;

[0165] An adjusting unit 608, configured to adjust the belt speed of the device to be monitored according to the target coal flow rate when the target coal flow rate is less than the preset coal flow rate threshold;

[0166] The processing unit 606 is further configured to send a second alarm message and stop the operation of the device to be monitored when the target coal flow rate is greater than or equal to the preset coal flow threshold.

[0167] Furthermore, in a possible implementation of the embodiment of the present disclosure, as Figure 7 As shown, the input unit 602 includes:

[0168] An extraction module 6021 is used to perform feature extraction processing from the monitoring data based on the trained monitoring model to obtain the target coal flow area;

[0169] A determination module 6022, configured to determine a line area in the monitoring data based on the trained monitoring model;

[0170] The extraction module 6021 is also used to extract the center line of the line area by a preset pixel algorithm;

[0171] The fitting module 6023 is used to perform straight line fitting processing on the center line to obtain the belt edge line.

[0172] Furthermore, in a possible implementation of the embodiment of the present disclosure, as Figure 7 As shown, the device also includes:

[0173] A second acquisition unit 609 is used to acquire a preset amount of training monitoring data, and extract and process the training monitoring data using a preset extraction algorithm to obtain first training data;

[0174] An enhancement unit 610 is configured to perform data enhancement processing on the first training data by using a preset enhancement algorithm to obtain second training data;

[0175] The labeling unit 611 is used to label the training belt edge line and the training coal flow area in the second training data by using a preset labeling algorithm to obtain target training data.

[0176] Furthermore, in a possible implementation of the embodiment of the present disclosure, as Figure 7 As shown, the device also includes:

[0177] A partitioning unit 612 is used to perform data partitioning processing on the target training data to obtain a training data set, a verification data set, and a test data set;

[0178] A training unit 613 is used to input the training data set into the monitoring model for model training processing to obtain a first monitoring model;

[0179] A verification unit 614 is used to perform model verification processing on the first monitoring model through the verification data set to obtain a second monitoring model;

[0180] The testing unit 615 is used to perform model testing processing on the second monitoring model through the test data set to obtain the trained monitoring model.

[0181] It should be noted that the above explanation of the method embodiment is also applicable to the device of the embodiment of the present disclosure, and the principle is the same, which is no longer limited in the embodiment of the present disclosure.

[0182] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0183] Figure 8A schematic block diagram of an example electronic device 800 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0184] like Figure 8 As shown, the device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a ROM (Read-Only Memory) 802 or a computer program loaded from a storage unit 808 to a RAM (Random Access Memory) 803. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An I / O (Input / Output) interface 805 is also connected to the bus 804.

[0185] A number of components in the device 800 are connected to the I / O interface 805, including: an input unit 806, such as a keyboard, a mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a disk, an optical disk, etc.; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the device 800 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0186] The computing unit 801 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a CPU (Central Processing Unit), a GPU (Graphic Processing Units), various dedicated AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, a DSP (Digital Signal Processor), and any appropriate processor, controller, microcontroller, etc. The computing unit 801 performs the various methods and processes described above, such as a monitoring method for coal transportation. For example, in some embodiments, the monitoring method for coal transportation may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the method described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to execute the aforementioned coal transportation monitoring method in any other appropriate manner (eg, by means of firmware).

[0187] Various embodiments of the systems and techniques described above herein may be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application Specific Standard Products), SOCs (System On Chips), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs that may be executed and / or interpreted on a programmable system including at least one programmable processor that may be a special purpose or general purpose programmable processor that may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0188] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0189] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. More specific examples of machine-readable storage media may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a RAM, a ROM, an EPROM (Electrically Programmable Read-Only-Memory) or a flash memory, an optical fiber, a CD-ROM (Compact Dis sc Read-Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0190] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball), through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0191] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: LAN (Local Area Network), WAN (Wide Area Network), the Internet, and blockchain networks.

[0192] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server may also be a server of a distributed system, or a server combined with a blockchain.

[0193] It should be noted that artificial intelligence is a discipline that studies how computers can simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.), and includes both hardware-level and software-level technologies. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, and big data processing; artificial intelligence software technologies mainly include computer vision technology, speech recognition technology, natural language processing technology, as well as machine learning / deep learning, big data processing technology, knowledge graph technology, and other major directions.

[0194] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0195] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for monitoring coal transportation, characterized in that: include: Acquire monitoring data of the equipment to be monitored, and input the monitoring data into a trained monitoring model for feature extraction processing to obtain a target coal flow area and a belt edge line of the equipment to be monitored; wherein the target coal flow area is the area occupied by the coal transported by the equipment to be monitored; Determine the belt area of ​​the device to be monitored according to the belt edge line, and calculate the ratio between the target coal flow area and the belt area to obtain the target coal flow rate; Calculate the distance between the belt edge line and the preset reference edge line to obtain the belt deviation value of the device to be monitored; When the belt deviation value is greater than or equal to a preset deviation threshold, a first alarm message is sent and the operation of the device to be monitored is stopped.

2. The method according to claim 1, characterized in that: The target coal flow rate is obtained by calculating the ratio between the target coal flow area and the belt area, comprising: Performing data division processing on the monitoring data to obtain first monitoring data, and determining a first coal flow area according to the first monitoring data and the target coal flow area; The first belt area is determined according to the first monitoring data and the belt area, and the target coal flow rate is obtained by calculating the ratio of the first coal flow area to the first belt area.

3. The method according to claim 1, characterized in that The step of calculating the distance between the belt edge line and the preset reference edge line to obtain the belt deviation value of the device to be monitored includes: Dividing the belt edge line to obtain a plurality of first belt edge lines; Calculating the distance between each of the plurality of first belt edge lines and the preset reference edge line respectively to obtain a plurality of first deviation values; An average value is calculated for the multiple first deviation values ​​to obtain the belt deviation value.

4. The method according to claim 1, characterized in that: After calculating the ratio between the target coal flow area and the belt area to obtain the target coal flow rate, the method further includes: Determining whether the target coal flow rate is less than a preset coal flow threshold; If the target coal flow rate is less than the preset coal flow threshold, adjusting the belt speed of the device to be monitored according to the target coal flow rate; If the target coal flow rate is greater than or equal to the preset coal flow threshold, a second alarm message is sent and the operation of the equipment to be monitored is stopped.

5. The method according to claim 1, characterized in that The monitoring data is input into the trained monitoring model for feature extraction processing to obtain the target coal flow area and the belt edge line of the equipment to be monitored, including: Based on the trained monitoring model, feature extraction processing is performed from the monitoring data to obtain the target coal flow area; Based on the trained monitoring model, determining the line area in the monitoring data, and extracting the center line of the line area by a preset pixel algorithm; The center line is subjected to straight line fitting processing to obtain the belt edge line.

6. The method according to claim 1, characterized in that Before obtaining the monitoring data of the device to be monitored, the method further includes: Acquire a preset amount of training monitoring data, and extract and process the training monitoring data using a preset extraction algorithm to obtain first training data; Performing data enhancement processing on the first training data by using a preset enhancement algorithm to obtain second training data; The training belt edge line and the training coal flow area in the second training data are labeled using a preset labeling algorithm to obtain target training data.

7. The method according to claim 6, characterized in that After labeling the training belt edge line and the training coal flow area in the second training data by a preset labeling algorithm to obtain target training data, the method further includes: Performing data division processing on the target training data to obtain a training data set, a verification data set, and a test data set; Inputting the training data set into the monitoring model for model training processing to obtain a first monitoring model; Performing model verification processing on the first monitoring model using the verification data set to obtain a second monitoring model; The second monitoring model is subjected to model testing processing using the test data set to obtain the trained monitoring model.

8. A monitoring device for coal transportation, characterized in that: include: A first acquisition unit, used to acquire monitoring data of a device to be monitored; An input unit, used to input the monitoring data into a trained monitoring model for feature extraction processing to obtain a target coal flow area and a belt edge line of the equipment to be monitored; wherein the target coal flow area is an area occupied by the coal transported by the equipment to be monitored; A first determining unit, configured to determine a belt area of ​​the device to be monitored according to the belt edge line; A first calculation unit, configured to calculate a ratio between the target coal flow area and the belt area to obtain a target coal flow rate; A second calculation unit is used to calculate the distance between the belt edge line and a preset reference edge line to obtain the belt deviation value of the device to be monitored; The processing unit is used to send a first alarm message and stop the operation of the device to be monitored when the belt deviation value is greater than or equal to a preset deviation threshold.

9. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-7.

Images