Coal quantity detection method, device, storage medium and system

Abstract

The application provides a coal quantity detection method and device, a storage medium and a system. The method combines an ultrasonic sensor with a two-layer stacking deep integration learning model technology to obtain final coal quantity prediction data. Since the cost of the ultrasonic sensor is lower than that of laser scanning and machine vision, and according to the range of the final coal quantity prediction data, it is determined that the coal quantity transportation working condition is normal, or first alarm information is generated to prompt that the belt of the belt conveyor appears to slip, or second alarm information is generated to prompt that the belt of the belt conveyor appears to run off, the phenomenon of the belt running off and the phenomenon of the belt slipping can be predicted, and thus the problem that the coal quantity detection method of the prior art, such as laser scanning and machine vision, has a high operation cost, and the detection result is easily affected by the transportation coal mine environment is solved.

Description

Technical Field

[0001] This application relates to the field of coal transportation technology, and more specifically, to a coal quantity detection method, apparatus, storage medium, and system. Background Technology

[0002] Belt conveyors are the main equipment for coal transportation and are widely used. Energy conservation and consumption reduction have become an important research direction in the coal mining industry. Only by achieving "fast transport when there is plenty of coal, reduced speed when there is little coal, and transport determined by mining schedules" can belt conveyors truly realize energy-saving operation through variable frequency speed regulation. During coal mining, belts often experience periods of no-load operation, resulting in significant energy consumption and machine wear. During coal transportation, insufficient belt pretension or insufficient friction due to damp coal can cause belt slippage, accelerating component wear. Sometimes, belt misalignment occurs during coal transportation. Belt misalignment not only causes uneven coal loading, increasing energy consumption and machine wear, but also leads to material spillage, reducing coal transportation speed and output. Therefore, it is necessary to monitor the coal quantity on the belt conveyor in real time to adjust the belt speed and detect belt slippage and misalignment to improve productivity and reduce energy consumption and wear.

[0003] Existing methods for coal quantity detection, such as laser scanning and machine vision, have high operating costs, and the detection results are also easily affected by the environmental impact of coal transportation in coal mines. Summary of the Invention

[0004] The main objective of this application is to provide a coal quantity detection method, device, storage medium, and system to at least solve the problems of high operating costs and the susceptibility of detection results to the environmental impact of coal transportation in existing coal quantity detection methods such as laser scanning and machine vision.

[0005] To achieve the above objectives, according to one aspect of this application, a coal quantity detection method is provided, the method comprising:

[0006] The ultrasonic coal pile time-series data collected by the ultrasonic sensor is acquired, and the ultrasonic coal pile time-series data is processed based on the ultrasonic ranging principle to obtain coal pile thickness data. The coal pile thickness data is the thickness data of the coal pile at different times, and the ultrasonic coal pile time-series data is the transmission time data of the signal received by the ultrasonic sensor at different times.

[0007] A two-layer stacking deep ensemble learning model is used to process the coal pile thickness data to obtain the final coal quantity prediction data.

[0008] Based on the range of the final coal quantity prediction data, determine that the coal transportation condition is normal, or generate a first alarm message to indicate that the belt of the belt conveyor is slipping, or generate a second alarm message to indicate that the belt of the belt conveyor is running off-track.

[0009] Optionally, before processing the coal pile thickness data using a two-layer Stacking deep ensemble learning model to obtain the final coal quantity prediction data, the method includes: acquiring historical coal pile data and dividing the historical coal pile data into a training set and a validation set, wherein the historical coal pile data includes historical coal pile thickness data and historical actual coal quantity values; training an XGboost model, a LightGMB model, and a Catboost model using the training set to obtain trained XGboost, LightGMB, and Catboost models; validating the prediction capabilities of the trained XGboost, LightGMB, and Catboost models using the validation set, and using the model with the best prediction capability as the first layer model in the two-layer Stacking deep ensemble learning model, processing the output of the first layer model using logistic regression or an SVM model to obtain the final output result, and using the final output result as the output result of the two-layer Stacking deep ensemble learning model.

[0010] Optionally, a two-layer Stacking deep ensemble learning model technique is used to process the coal pile thickness data to obtain the final coal quantity prediction data, including: processing the coal pile thickness data using the first-layer model to obtain the output of the first-layer model; and processing the output of the first-layer model using logistic regression or an SVM model to obtain the final coal quantity prediction data.

[0011] Optionally, based on the range of the final coal quantity prediction data, determining that the coal transportation condition is normal, or generating a first alarm message to indicate that the belt of the belt conveyor is slipping, or generating a second alarm message to indicate that the belt of the belt conveyor is misaligned, includes: determining a first coal quantity threshold and a second coal quantity threshold corresponding to the current model of the belt conveyor, wherein the first coal quantity threshold is greater than the second coal quantity threshold; generating the first alarm message to indicate that the belt of the belt conveyor is slipping when the final coal quantity prediction data is greater than the first coal quantity threshold; generating the second alarm message to indicate that the belt of the belt conveyor is misaligned when the final coal quantity prediction data is less than the second coal quantity threshold; and determining that the coal transportation condition is normal when the final coal quantity prediction data is less than or equal to the first coal quantity threshold and greater than or equal to the second coal quantity threshold.

[0012] Optionally, the method further includes: after generating a first alarm message to indicate that the belt of the belt conveyor is slipping, broadcasting the first alarm message in the form of voice; after generating a second alarm message to indicate that the belt of the belt conveyor is misaligned, controlling the belt conveyor to stop, and broadcasting the second alarm message in the form of voice.

[0013] Optionally, based on the ultrasonic ranging principle, the ultrasonic coal pile time-series data is processed to obtain coal pile thickness data, including: determining the coal pile thickness data according to H = h - d, where H is the coal pile thickness data, h is the installation height of the ultrasonic sensor, and d is the distance between the ultrasonic sensor and the coal pile.

[0014] Optionally, in the process of processing the ultrasonic coal pile time-series data based on the ultrasonic ranging principle to obtain the coal pile thickness data, the method further includes: determining the distance between the ultrasonic sensor and the coal pile according to d = (CT) / 2, where C is the propagation speed of ultrasonic waves in the mine and T is the time required for ultrasonic waves to be emitted and received.

[0015] According to another aspect of this application, a coal quantity detection device is provided, the device comprising:

[0016] The first acquisition unit is used to acquire ultrasonic coal pile time-series data collected by ultrasonic sensors, and to process the ultrasonic coal pile time-series data based on the ultrasonic ranging principle to obtain coal pile thickness data. The coal pile thickness data is the thickness data of the coal pile at different times, and the ultrasonic coal pile time-series data is the transmission time data of the signal received by the ultrasonic sensor at different times.

[0017] The first processing unit is used to process the coal pile thickness data using a two-layer Stacking deep ensemble learning model technology to obtain the final coal quantity prediction data.

[0018] The second processing unit is used to determine whether the coal transportation condition is normal based on the range of the final coal quantity prediction data, or to generate a first alarm message to indicate that the belt of the belt conveyor is slipping, or to generate a second alarm message to indicate that the belt of the belt conveyor is running off-track.

[0019] According to another aspect of this application, a computer-readable storage medium is provided, the computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform any of the methods described.

[0020] According to another aspect of this application, a coal quantity detection system is provided, the system comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs comprising methods for performing any one of the methods described.

[0021] By combining ultrasonic sensors with a two-layer stacking deep integrated learning model, the final coal quantity prediction data can be obtained. Since the cost of using ultrasonic sensors is lower than that of laser scanning and machine vision, and the coal transportation condition can be determined to be normal based on the range of the final coal quantity prediction data, or a first alarm message can be generated to indicate that the belt of the belt conveyor is slipping, or a second alarm message can be generated to indicate that the belt of the belt conveyor is running off-track. This can predict belt running off-track and slipping, thereby solving the problems of high operating costs and easy influence of the coal mining environment on the detection results of existing coal quantity detection methods such as laser scanning and machine vision. Attached Figure Description

[0022] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0023] Figure 1 A schematic flowchart of a coal quantity detection method according to an embodiment of this application is shown;

[0024] Figure 2 A schematic diagram showing the location of a belt conveyor, an ultrasonic sensor, and coal provided in an embodiment according to this application is illustrated.

[0025] Figure 3 A schematic flowchart of another coal quantity detection method provided according to an embodiment of this application is shown;

[0026] Figure 4 A structural block diagram of a coal quantity detection device provided according to an embodiment of this application is shown. Detailed Implementation

[0027] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0028] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0029] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0030] For ease of description, the following explains some of the nouns or terms used in the embodiments of this application:

[0031] XGBoost (eXtreme Gradient Boosting), LightGBM (Light Gradient Boosting Machine), and CatBoost (Categorical Boosting) are all variations of Gradient Boosting Trees. Gradient Boosting Trees are an ensemble learning algorithm that trains multiple decision tree models and combines them for prediction. These models collaborate during training, with each newly generated model attempting to correct the errors of previous models, thereby continuously improving the overall prediction performance.

[0032] XGBoost is a high-efficiency gradient boosting tree algorithm, renowned for its optimized performance and flexible customization capabilities. It supports parallel processing and distributed computing, enabling efficient training and prediction on large-scale datasets.

[0033] LightGBM is a gradient boosting tree algorithm developed by Microsoft. It uses a histogram-based decision tree algorithm and can significantly improve the speed of training and prediction when dealing with large-scale data.

[0034] CatBoost is a gradient boosting tree algorithm developed by Yandex. It is specifically optimized for data with a large number of categorical features, and can automatically process categorical features, avoiding the tedious feature engineering process.

[0035] The SVM model is a supervised learning model used for classification and regression tasks. Its main idea is to find an optimal hyperplane that maximizes the margin between different classes, thereby achieving data classification. The SVM model performs well when handling both linear and non-linear data and is widely used in practical applications.

[0036] Two-layer stacking deep ensemble learning model technology is a machine learning model ensemble method that improves prediction accuracy by combining multiple base models. This technique takes the predictions from multiple base models as input, and then integrates and adjusts these predictions through a meta-model (the second-layer model) to arrive at the final prediction result. This two-layer ensemble learning model can fully utilize the advantages of multiple base models, thereby improving overall prediction performance.

[0037] Five-fold cross-validation is a commonly used data partitioning and model evaluation technique. In this method, the dataset is divided into five equal parts, and the model training and evaluation process is repeated five times. In each training and evaluation iteration, four parts are used to train the model, and the remaining part is used to evaluate the model's performance. Finally, the results of the five training and evaluation iterations are averaged to obtain the final performance evaluation. This method can effectively evaluate model performance and reduce the randomness caused by different data partitions.

[0038] As introduced in the background section, belt conveyors are the main equipment for coal transportation and are widely used. Energy conservation and consumption reduction have become an important research direction in the coal mining industry. Only by achieving "fast transportation when there is more coal, reduced running time when there is less coal, and transportation determined by mining schedules" can belt conveyors truly realize energy-saving operation through variable frequency speed regulation. During coal mining, belts often experience periods of no-load operation, resulting in significant energy consumption and machine wear. During coal transportation, insufficient belt pretension or insufficient friction due to damp coal can cause belt slippage, accelerating component wear. Sometimes, belt misalignment occurs during coal transportation. Belt misalignment not only causes uneven coal loading, increasing energy consumption and machine wear, but also leads to material spillage, reducing coal transportation speed and output. Therefore, it is necessary to monitor the amount of coal on the belt conveyor in real time in order to adjust the belt speed of the belt conveyor and detect belt slippage and deviation, so as to improve production capacity and reduce energy consumption and wear. In order to solve the problems that the existing coal quantity detection methods such as laser scanning and machine vision have high operating costs and the detection results are easily affected by the coal mining environment, the embodiments of this application provide a coal quantity detection method, device, storage medium and system.

[0039] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0040] This embodiment provides a coal quantity detection method. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Also, although the logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0041] Figure 1 This is a schematic flowchart of a coal quantity detection method provided according to an embodiment of this application. Figure 1 As shown, the method includes the following steps:

[0042] Step S101: Obtain the ultrasonic coal pile time-series data collected by the ultrasonic sensor, and process the ultrasonic coal pile time-series data based on the ultrasonic ranging principle to obtain coal pile thickness data. The coal pile thickness data is the thickness data of the coal pile at different times, and the ultrasonic coal pile time-series data is the transmission time data of the signal received by the ultrasonic sensor at different times.

[0043] In one embodiment of this application, the ultrasonic coal pile time series data is processed based on the ultrasonic ranging principle to obtain coal pile thickness data, including: determining the coal pile thickness data according to H = h - d, where H is the coal pile thickness data, h is the installation height of the ultrasonic sensor, and d is the distance between the ultrasonic sensor and the coal pile.

[0044] Specifically, such as Figure 2 As shown, points A, B, and C are three sets of ultrasonic generators arranged perpendicular to the direction of belt travel of the conveyor belt.

[0045] In one embodiment of this application, in the process of processing the above-mentioned ultrasonic coal pile time series data based on the ultrasonic ranging principle to obtain coal pile thickness data, the above method further includes: determining the distance between the ultrasonic sensor and the coal pile according to d = (CT) / 2, where C is the propagation speed of ultrasonic waves in the mine, and T is the time required for ultrasonic waves to be transmitted from emission to reception, which corresponds to the ultrasonic coal pile time series data.

[0046] Specifically, the distance between the ultrasonic sensor and the coal pile is calculated based on the speed of ultrasonic wave propagation in the mine and the time required for the ultrasonic wave to travel from emission to reception. An ultrasonic sensor is a non-contact, precise detection method that utilizes the characteristics of sound waves to detect the state and distance of objects. Ultrasonic sensors have a wide detection range, enabling detection at greater distances, and can be used in harsh environments. They are unaffected by the color of the target object or factors such as dust and water mist in the air. They also have low operating costs, simple operation procedures, straightforward calculations, and are easy to implement in real-time control.

[0047] Furthermore, if we approximate the cross-section of the coal pile on the conveyor belt as a trapezoid, we can use the formula for the cross-sectional area of ​​a coal pile:

[0048] The cross-sectional area S of the coal pile is determined by S = (2L + 2Htanθ)H / 2, where L is the length of the idler roller, H is the thickness of the coal pile, and θ is the included angle of the idler roller.

[0049] The real-time measured coal quantity Q = Svρ, where v is the belt speed and ρ is the coal bulk density. The coal bulk density, i.e., the bulk density of coal blocks ρ, is measured directly by measuring the mass and volume of coal transported on belt conveyors in different coal mines, thereby determining the coal bulk density.

[0050] Step S102: The two-layer Stacking deep ensemble learning model technology is used to process the above coal pile thickness data to obtain the final coal quantity prediction data.

[0051] In one embodiment of this application, before processing the coal pile thickness data using a two-layer Stacking deep ensemble learning model in step S102 to obtain the final coal quantity prediction data, the method includes: acquiring historical coal pile data and dividing the historical coal pile data into a training set and a validation set, wherein the historical coal pile data includes historical coal pile thickness data and historical actual coal quantity values; training an XGboost model, a LightGMB model, and a Catboost model using the training set to obtain trained XGboost, LightGMB, and Catboost models; validating the prediction capabilities of the trained XGboost, LightGMB, and Catboost models using the validation set, and using the model with the best prediction capability as the first layer model in the two-layer Stacking deep ensemble learning model, processing the output of the first layer model using logistic regression or an SVM model to obtain the final output result, and using the final output result as the output result of the two-layer Stacking deep ensemble learning model.

[0052] Specifically, features are extracted from each data point in the ultrasonic database (i.e., historical coal pile data), and the extracted data is used as the training set to establish a two-layer Stacking deep ensemble learning model. In the first-layer Stacking deep ensemble learning model, XGboost, LightGMB, and Catboost base models are trained separately using 80% of the training set data, and the remaining 20% ​​of the training set data is used for validation. The output results of each base model are dynamically filtered based on their accuracy values, and the two base models with the highest scores are selected (based on the training set, the selected base models are trained and validated using a five-fold cross-validation method). The output results of the first-layer model are then input into the second-layer Stacking deep ensemble learning model. The second-layer Stacking deep ensemble learning model is trained using logistic regression or an SVM model on the output results of the first layer. Finally, the model with the best prediction effect on the amount of coal transported by the belt conveyor is output as the coal quantity prediction model.

[0053] In one embodiment of this application, a two-layer Stacking deep ensemble learning model is used to process the coal pile thickness data to obtain the final coal quantity prediction data. This includes: processing the coal pile thickness data using the first-layer model to obtain the output of the first-layer model; and processing the output of the first-layer model using logistic regression or an SVM model to obtain the final coal quantity prediction data.

[0054] Specifically, the coal quantity prediction model is used to process the above coal pile thickness data to obtain the final coal quantity prediction data.

[0055] Step S103: Based on the range of the final coal quantity prediction data, determine that the coal transportation condition is normal, or generate a first alarm message to indicate that the belt of the belt conveyor is slipping, or generate a second alarm message to indicate that the belt of the belt conveyor is running off-track.

[0056] When belt slippage occurs, remind underground workers to adjust the tensioning device to tighten the belt and increase its tension to improve traction. If the belt deviates from its designated path, promptly adjust the tension on both sides to correct the belt. By using ultrasonic ranging to detect coal quantity, non-contact, fixed-point, and continuous measurement of the coal load on the belt conveyor can be achieved. This allows for timely control and adjustment of the belt conveyor's operating speed, reducing energy consumption and increasing coal efficiency.

[0057] In the above steps, the final coal quantity prediction data is obtained by combining ultrasonic sensors with a two-layer stacking deep integrated learning model. Since the cost of using ultrasonic sensors is lower than that of laser scanning and machine vision, and the coal transportation condition is determined to be normal based on the range of the final coal quantity prediction data, a first alarm message is generated to indicate that the belt of the belt conveyor is slipping, or a second alarm message is generated to indicate that the belt of the belt conveyor is running off-track. This can predict belt running off-track and slipping, thereby solving the problems of high operating costs and easy influence of the coal mining environment on the detection results of existing coal quantity detection methods such as laser scanning and machine vision.

[0058] Step S103, which involves determining the normal coal transportation condition based on the range of the final coal quantity prediction data, or generating a first alarm message to indicate belt slippage of the belt conveyor, or generating a second alarm message to indicate belt misalignment of the belt conveyor, includes: determining a first coal quantity threshold and a second coal quantity threshold corresponding to the current model of the belt conveyor, wherein the first coal quantity threshold is greater than the second coal quantity threshold; generating the first alarm message to indicate belt slippage of the belt conveyor when the final coal quantity prediction data is greater than the first coal quantity threshold; generating the second alarm message to indicate belt misalignment of the belt conveyor when the final coal quantity prediction data is less than the second coal quantity threshold; and determining the normal coal transportation condition when the final coal quantity prediction data is less than or equal to the first coal quantity threshold and greater than or equal to the second coal quantity threshold.

[0059] Specifically, a mapping table is established between the first and second coal quantity thresholds and the current model of the belt conveyor. The first and second coal quantity thresholds corresponding to different models are obtained by looking up the table, which improves the accuracy of detection.

[0060] In one embodiment of this application, the method further includes: after generating a first alarm message to indicate that the belt of the belt conveyor is slipping, broadcasting the first alarm message in the form of voice; after generating a second alarm message to indicate that the belt of the belt conveyor is running off-center, controlling the belt conveyor to stop, and broadcasting the second alarm message in the form of voice.

[0061] Specifically, by broadcasting information via voice, staff can be informed of the current working conditions. Once it is determined that the belt of the aforementioned belt conveyor is misaligned, stopping the belt conveyor can prevent the misalignment from worsening.

[0062] To enable those skilled in the art to better understand the technical solution of this application, the implementation process of the coal quantity detection method of this application will be described in detail below with reference to specific embodiments.

[0063] This embodiment relates to a specific method for detecting coal quantity, such as... Figure 3 As shown, it includes the following steps:

[0064] Step S1: Acquire the ultrasonic coal pile time-series data collected by the ultrasonic sensor, and process the ultrasonic coal pile time-series data based on the ultrasonic ranging principle to obtain the coal pile thickness data. The coal pile thickness data is the thickness data of the coal pile at different times, and the ultrasonic coal pile time-series data is the distance between the ultrasonic sensor and the coal pile at different times.

[0065] Step S2: Obtain historical coal pile data and divide the historical coal pile data into training set and validation set. The historical coal pile data includes historical coal pile thickness data and historical actual coal quantity values. Use the training set to train the XGboost model, LightGMB model and Catboost model respectively to obtain the trained XGboost model, trained LightGMB model and trained Catboost model.

[0066] Step S3: Use the validation set to verify the prediction capabilities of the trained XGboost model, the trained LightGMB model, and the trained Catboost model respectively. Use the model with the best prediction capability as the first layer model in the two-layer Stacking deep ensemble learning model. Use logistic regression or SVM model to process the output of the first layer model to obtain the final output result, and use the final output result as the output result of the two-layer Stacking deep ensemble learning model.

[0067] Step S4: Process the coal pile thickness data using the first-layer model to obtain the output of the first-layer model; process the output of the first-layer model using logistic regression or SVM model to obtain the final coal quantity prediction data;

[0068] Step S5: Determine the first coal quantity threshold and the second coal quantity threshold corresponding to the current model of the belt conveyor, wherein the first coal quantity threshold is greater than the second coal quantity threshold; if the final coal quantity prediction data is greater than the first coal quantity threshold, generate a first alarm message to indicate that the belt of the belt conveyor is slipping; if the final coal quantity prediction data is less than the second coal quantity threshold, generate a second alarm message to indicate that the belt of the belt conveyor is misaligned; if the final coal quantity prediction data is less than or equal to the first coal quantity threshold and greater than or equal to the second coal quantity threshold, determine that the coal transportation condition is normal.

[0069] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0070] This application also provides a coal quantity detection device. It should be noted that the coal quantity detection device of this application can be used to execute the coal quantity detection method provided in this application. This device is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0071] The following describes the coal quantity detection device provided in the embodiments of this application.

[0072] Figure 4 This is a structural block diagram of a coal quantity detection device provided according to an embodiment of this application. Figure 4 As shown, the device includes:

[0073] The first acquisition unit 41 is used to acquire ultrasonic coal pile time-series data collected by ultrasonic sensor, and process the ultrasonic coal pile time-series data based on ultrasonic ranging principle to obtain coal pile thickness data. The coal pile thickness data is the thickness data of coal pile at different times, and the ultrasonic coal pile time-series data is the transmission time data of the signal received by ultrasonic sensor at different times.

[0074] The first processing unit 42 is used to process the above coal pile thickness data using a two-layer Stacking deep ensemble learning model technology to obtain the final coal quantity prediction data.

[0075] The second processing unit 43 is used to determine that the coal transportation condition is normal based on the range of the final coal quantity prediction data, or to generate a first alarm message to indicate that the belt of the belt conveyor is slipping, or to generate a second alarm message to indicate that the belt of the belt conveyor is running off-track.

[0076] In the aforementioned device, the final coal quantity prediction data is obtained by combining ultrasonic sensors with a two-layer stacking deep integrated learning model. Since the cost of using ultrasonic sensors is lower than that of laser scanning and machine vision, and the coal transportation condition is determined to be normal based on the range of the final coal quantity prediction data, a first alarm message is generated to indicate that the belt of the belt conveyor is slipping, or a second alarm message is generated to indicate that the belt of the belt conveyor is running off-track. This device can predict belt running off-track and slipping, thereby solving the problems of high operating costs and easy influence of the coal mining environment on the detection results of existing coal quantity detection methods such as laser scanning and machine vision.

[0077] In one embodiment of this application, the above-mentioned device further includes a second acquisition unit, a third processing unit, and a fourth processing unit. Before processing the coal pile thickness data using a two-layer Stacking deep ensemble learning model to obtain the final coal quantity prediction data, the second acquisition unit is used to acquire historical coal pile data and divide the historical coal pile data into a training set and a validation set. The historical coal pile data includes historical coal pile thickness data and historical actual coal quantity values. The third processing unit is used to train the XGboost model, the LightGMB model, and the Catboost model using the training set to obtain the trained XGboost model, the trained LightGMB model, and the trained Catboost model. The fourth processing unit is used to verify the prediction capabilities of the trained XGboost model, the trained LightGMB model, and the trained Catboost model using the validation set. The model with the best prediction capability is used as the first layer model in the two-layer Stacking deep ensemble learning model. The output of the first layer model is processed using logistic regression or an SVM model to obtain the final output result, and the final output result is used as the output result of the two-layer Stacking deep ensemble learning model.

[0078] In one embodiment of this application, the first processing unit includes a first processing module and a second processing module. The first processing module is used to process the coal pile thickness data using the first-layer model to obtain the output of the first-layer model. The second processing module is used to process the output of the first-layer model using logistic regression or an SVM model to obtain the final coal quantity prediction data.

[0079] In one embodiment of this application, the second processing unit includes a first determining module, a first generating module, a second generating module, and a second determining module. The first determining module is used to determine a first coal quantity threshold and a second coal quantity threshold corresponding to the current model of the belt conveyor, wherein the first coal quantity threshold is greater than the second coal quantity threshold. The first generating module is used to generate a first alarm message to indicate that the belt of the belt conveyor is slipping when the final predicted coal quantity data is greater than the first coal quantity threshold. The second generating module is used to generate a second alarm message to indicate that the belt of the belt conveyor is misaligned when the final predicted coal quantity data is less than the second coal quantity threshold. The second determining module is used to determine that the coal transportation condition is normal when the final predicted coal quantity data is less than or equal to the first coal quantity threshold and greater than or equal to the second coal quantity threshold.

[0080] In one embodiment of this application, the above-mentioned device further includes a fifth processing unit and a sixth processing unit. The fifth processing unit is used to broadcast the first alarm information in the form of voice after generating a first alarm information to indicate that the belt of the belt conveyor has slipped. The sixth processing unit is used to control the belt conveyor to stop after generating a second alarm information to indicate that the belt of the belt conveyor has deviated, and to broadcast the second alarm information in the form of voice.

[0081] In one embodiment of this application, the first acquisition unit includes a third determination module, which is used to determine the above-mentioned coal pile thickness data according to H = h - d, wherein H is the above-mentioned coal pile thickness data, h is the installation height of the ultrasonic sensor, and d is the distance between the ultrasonic sensor and the coal pile.

[0082] In one embodiment of this application, the first acquisition unit includes a fourth determination module. In the process of processing the ultrasonic coal pile time series data based on the ultrasonic ranging principle to obtain the coal pile thickness data, the fourth determination module is used to determine the distance between the ultrasonic sensor and the coal pile according to d = (CT) / 2, where C is the propagation speed of ultrasonic waves in the mine and T is the time required for ultrasonic waves to be emitted and received.

[0083] The aforementioned coal quantity detection device includes a processor and a memory. The first acquisition unit, the first processing unit, and the second processing unit are all stored as program units in the memory. The processor executes the program units stored in the memory to achieve the corresponding functions. All of the above modules are located in the same processor; alternatively, the above modules may be located in different processors in any combination.

[0084] The processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured. By adjusting kernel parameters, the high operating costs and susceptibility of existing coal quantity detection methods such as laser scanning and machine vision to environmental factors affecting coal transportation can be addressed.

[0085] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0086] This invention provides a computer-readable storage medium including a stored program, wherein the program, when running, controls the device containing the computer-readable storage medium to execute the coal quantity detection method.

[0087] This invention provides a processor for running a program, wherein the program executes the coal quantity detection method described above.

[0088] This invention provides a device including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs at least the following steps: acquiring ultrasonic coal pile time-series data collected by an ultrasonic sensor, and processing the ultrasonic coal pile time-series data based on the ultrasonic ranging principle to obtain coal pile thickness data, wherein the coal pile thickness data is the thickness of the coal pile at different times, and the ultrasonic coal pile time-series data is the transmission time data of the signals received by the ultrasonic sensor at different times; processing the coal pile thickness data using a two-layer Stacking deep ensemble learning model to obtain final coal quantity prediction data; and determining that the coal transportation condition is normal based on the range of the final coal quantity prediction data, or generating a first alarm message to indicate belt slippage of the belt conveyor, or generating a second alarm message to indicate belt misalignment of the belt conveyor. The device described herein can be a server, PC, PAD, mobile phone, etc.

[0089] This application also provides a computer program product, which, when executed on a data processing device, is suitable for executing an initialization program having at least the following method steps: acquiring ultrasonic coal pile time-series data collected by an ultrasonic sensor, and processing the ultrasonic coal pile time-series data based on the ultrasonic ranging principle to obtain coal pile thickness data, wherein the coal pile thickness data is the thickness data of the coal pile at different times, and the ultrasonic coal pile time-series data is the transmission time data of the signal received by the ultrasonic sensor at different times; processing the coal pile thickness data using a two-layer Stacking deep ensemble learning model technology to obtain final coal quantity prediction data; determining that the coal transportation condition is normal based on the range of the final coal quantity prediction data, or generating a first alarm message to indicate that the belt of the belt conveyor is slipping, or generating a second alarm message to indicate that the belt of the belt conveyor is misaligned.

[0090] This application also provides a coal quantity detection system, which includes: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include methods for performing any of the above-described methods. By combining ultrasonic sensors with a two-layer stacking deep ensemble learning model, final coal quantity prediction data is obtained. Since the cost of using ultrasonic sensors is lower than that of laser scanning and machine vision, and based on the range of the final coal quantity prediction data, the system can determine that the coal transportation condition is normal, or generate a first alarm message to indicate belt slippage of the belt conveyor, or generate a second alarm message to indicate belt misalignment of the belt conveyor, it can predict belt misalignment and slippage. This solves the problems of high operating costs and susceptibility to environmental influences of existing coal quantity detection methods such as laser scanning and machine vision.

[0091] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those described herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0092] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0093] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0094] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0095] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0096] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0097] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0098] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0099] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0100] As can be seen from the above description, the embodiments of this application achieve the following technical effects:

[0101] 1) The coal quantity detection method of this application obtains the final coal quantity prediction data by combining an ultrasonic sensor with a two-layer stacking deep integrated learning model technology. Since the cost of using ultrasonic sensors is lower than that of laser scanning and machine vision, and the coal transportation condition is determined to be normal based on the range of the final coal quantity prediction data, or a first alarm message is generated to indicate that the belt of the belt conveyor is slipping, or a second alarm message is generated to indicate that the belt of the belt conveyor is running off-track, the method can predict belt running off-track and slipping, thereby solving the problems of high operating cost and easy influence of the coal mining environment on the detection results of existing coal quantity detection methods such as laser scanning and machine vision.

[0102] 2) The coal quantity detection device of this application obtains the final coal quantity prediction data by combining an ultrasonic sensor with a two-layer stacking deep integrated learning model technology. Since the cost of using ultrasonic sensors is lower than that of laser scanning and machine vision, and the coal transportation condition is determined to be normal based on the range of the final coal quantity prediction data, or a first alarm message is generated to indicate that the belt of the belt conveyor is slipping, or a second alarm message is generated to indicate that the belt of the belt conveyor is running off-track, the device can predict belt running off-track and slipping, thereby solving the problems of high operating cost and easy influence of the coal mining environment on the detection results of existing coal quantity detection methods such as laser scanning and machine vision.

[0103] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for detecting coal quantity, characterized in that, include: The ultrasonic coal pile time-series data collected by the ultrasonic sensor is acquired, and the ultrasonic coal pile time-series data is processed based on the ultrasonic ranging principle to obtain coal pile thickness data. The coal pile thickness data is the thickness data of the coal pile at different times, and the ultrasonic coal pile time-series data is the transmission time data of the signal received by the ultrasonic sensor at different times. A two-layer stacking deep ensemble learning model is used to process the coal pile thickness data to obtain the final coal quantity prediction data. Based on the range of the final coal quantity prediction data, determine that the coal transportation condition is normal, or generate a first alarm message to indicate that the belt of the belt conveyor is slipping, or generate a second alarm message to indicate that the belt of the belt conveyor is running off-track.

2. The method according to claim 1, characterized in that, Before processing the coal pile thickness data using a two-layer stacking deep ensemble learning model to obtain the final coal quantity prediction data, the method includes: Acquire historical coal pile data and divide the historical coal pile data into a training set and a validation set. The historical coal pile data includes historical coal pile thickness data and historical actual coal quantity values. The XGboost model, LightGMB model, and Catboost model were trained using the training set to obtain the trained XGboost model, trained LightGMB model, and trained Catboost model. The prediction capabilities of the trained XGboost model, the trained LightGMB model, and the trained Catboost model are verified using the validation set. The model with the best prediction capability is used as the first layer in the two-layer Stacking deep ensemble learning model. The output of the first layer model is processed using logistic regression or SVM to obtain the final output result, which is then used as the output result of the two-layer Stacking deep ensemble learning model.

3. The method according to claim 2, characterized in that, A two-layer stacking deep ensemble learning model is used to process the coal pile thickness data to obtain the final coal quantity prediction data, including: The coal pile thickness data is processed using the first-layer model to obtain the output of the first-layer model; The output of the first-layer model is processed using logistic regression or an SVM model to obtain the final coal quantity prediction data.

4. The method according to claim 1, characterized in that, Based on the range of the final coal quantity prediction data, determine that the coal transportation condition is normal, or generate a first alarm message to indicate that the belt of the belt conveyor is slipping, or generate a second alarm message to indicate that the belt of the belt conveyor is misaligned, including: Determine a first coal quantity threshold and a second coal quantity threshold corresponding to the current model of the belt conveyor, wherein the first coal quantity threshold is greater than the second coal quantity threshold; If the final coal quantity prediction data is greater than the first coal quantity threshold, the first alarm message is generated to indicate that the belt of the belt conveyor is slipping. If the final coal quantity prediction data is less than the second coal quantity threshold, a second alarm message is generated to indicate that the belt of the belt conveyor has deviated. If the final coal quantity prediction data is less than or equal to the first coal quantity threshold and the final coal quantity prediction data is greater than or equal to the second coal quantity threshold, the coal transportation condition is determined to be normal.

5. The method according to claim 1, characterized in that, The method further includes: After generating the first alarm message to indicate that the belt of the belt conveyor has slipped, the first alarm message is broadcast in the form of voice. After generating a second alarm message to indicate that the belt of the belt conveyor is misaligned, the belt conveyor is stopped and the second alarm message is broadcast in voice.

6. The method according to claim 1, characterized in that, Based on the principle of ultrasonic ranging, the time-series data of the ultrasonic coal pile is processed to obtain coal pile thickness data, including: The coal pile thickness data is determined according to H = h - d, where H is the coal pile thickness data, h is the installation height of the ultrasonic sensor, and d is the distance between the ultrasonic sensor and the coal pile.

7. The method according to claim 6, characterized in that, In the process of processing the ultrasonic coal pile time-series data based on the ultrasonic ranging principle to obtain the coal pile thickness data, the method further includes: The distance between the ultrasonic sensor and the coal pile is determined by d = (CT) / 2, where C is the speed of ultrasonic wave propagation in the mine and T is the time required for ultrasonic wave to travel from emission to reception.

8. A coal quantity detection device, characterized in that, include: The first acquisition unit is used to acquire ultrasonic coal pile time-series data collected by ultrasonic sensors, and to process the ultrasonic coal pile time-series data based on the ultrasonic ranging principle to obtain coal pile thickness data. The coal pile thickness data is the thickness data of the coal pile at different times, and the ultrasonic coal pile time-series data is the transmission time data of the signal received by the ultrasonic sensor at different times. The first processing unit is used to process the coal pile thickness data using a two-layer Stacking deep ensemble learning model technology to obtain the final coal quantity prediction data. The second processing unit is used to determine whether the coal transportation condition is normal based on the range of the final coal quantity prediction data, or to generate a first alarm message to indicate that the belt of the belt conveyor is slipping, or to generate a second alarm message to indicate that the belt of the belt conveyor is running off-track.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform the method according to any one of claims 1 to 7.

10. A coal quantity detection system, characterized in that, include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs comprising methods for performing any one of claims 1 to 7.

Images