Mine filling pipeline blockage monitoring method and device

By VMD decomposing and neural network processing of the temperature and vibration data of the mine filled pipeline, real-time prediction of blockage situations is achieved, and the problem of inability to detect blockage in time in the existing technology is solved, ensuring the normal production and safety of the mine.

CN119022229AActive Publication Date: 2024-11-26WUHAN UNIV OF TECH

Patent Information

Application Number
CN202411129506.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-16
Publication Date
2024-11-26
Estimated Expiration
2044-08-16

AI Technical Summary

Technical Problem

The existing technology cannot predict the blockage of mine filling pipelines in a timely manner, resulting in production interruptions and safety hazards.

Method used

By obtaining the temperature and vibration data of the mine filled pipeline, using VMD decomposition algorithm and neural network for data processing, initial prediction results are generated, and target predictions are made based on these results to monitor the blockage.

Benefits of technology

Real-time prediction of the blockage of mine filling pipelines is achieved, ensuring timely detection and treatment before the blockage occurs, and ensuring the normal production and safety of the mine.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119022229A_ABST
    Figure CN119022229A_ABST
Patent Text Reader

Abstract

The invention relates to a mine filling pipeline blockage monitoring method and device, and belongs to the technical field of mine filling detection.The method comprises the steps that first temperature vibration data of a mine filling pipeline at the current moment and second temperature vibration data of the mine filling pipeline at the last moment are obtained; processing the first temperature vibration data at the current moment to obtain a plurality of initial prediction results; obtaining a target prediction result according to the plurality of initial prediction results; and monitoring the blockage condition of the mine filling pipeline according to the target prediction result and the second temperature vibration data at the previous moment, so that the blockage condition of the mine filling pipeline can be predicted in real time according to the first temperature vibration data at the current moment and the second temperature vibration data at the previous moment. Therefore, a worker can carry out processing according to the monitoring condition, and normal production and safety of a mine are further ensured.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of mine filling detection, and in particular to a method and device for monitoring pipe blockage in a mine filling pipeline. Background Art

[0002] The backfill mining method is favored by mines because it reduces the potential safety hazards caused by mining activities and improves the reliability of the human living environment and property safety. The transportation of backfill is an important part of the backfill mining method. The blockage of mine backfill pipelines is one of the common problems in the mining process, which seriously affects the normal production and safety of mines. As a key channel for transporting backfill materials, once the backfill pipeline is blocked, it will not only cause the backfilling operation to be interrupted, but also may cause equipment damage, environmental pollution and safety accidents. When the backfill slurry flows in the pipeline, heat generation and heat transfer occur all the time, the temperature change rate of the slurry at different flow positions is different, and the backfill pipeline also vibrates all the time. This will affect the transportation of the backfill slurry, causing the backfill slurry to be retained and thus causing pipe blockage.

[0003] In the prior art, pressure detection method, pulse echo method, resistivity analysis method, acoustic technology and other methods are generally used to detect filling pipes. However, these methods cannot predict the phenomenon of filling pipes in time. They can only detect blockage when it occurs, thus affecting the normal production and safety of mines.

[0004] Therefore, it is urgent to propose a method and device for monitoring blockage of mine filling pipelines to solve the technical problem that the existing methods in the prior art cannot predict the phenomenon of filling pipelines in time and can only detect it when blockage occurs, thus affecting the normal production and safety of mines. Summary of the invention

[0005] In view of this, it is necessary to provide a method and device for monitoring blockage of mine filling pipelines to solve the technical problem that the existing methods in the prior art cannot predict the phenomenon of filling pipelines in time and can only detect blockage when it occurs, thus affecting the normal production and safety of mines.

[0006] In order to solve the above problems, the present invention provides a method for monitoring blockage of a mine filling pipeline, comprising: Obtaining the first temperature and vibration data of the mine filling pipeline at the current moment and the second temperature and vibration data at the previous moment; Processing the first temperature-vibration data to obtain a plurality of initial prediction results; Obtaining a target prediction result according to the multiple initial prediction results; The blockage condition of the mine filling pipeline is monitored according to the target prediction result and the second temperature and vibration data.

[0007] In a possible implementation, the processing of the first temperature-vibration data to obtain a plurality of initial prediction results includes: Decomposing the first temperature-vibration data to obtain multiple sequences; Prediction processing is performed on each sequence separately to obtain multiple initial prediction results.

[0008] In a possible implementation, the multiple sequences include a residual sequence and k modal component IMF sequences, and the first temperature vibration data is decomposed to obtain multiple sequences, including: Based on the preset optimization algorithm, the core parameters of the VMD decomposition algorithm, the modal number k value and the penalty factor, are optimized to obtain the target VMD decomposition algorithm; The first temperature-vibration data is decomposed based on the target VMD decomposition algorithm to obtain k modal component IMF sequences and a residual sequence.

[0009] In a possible implementation, the multiple initial prediction results include multiple subsequence prediction results and residual prediction results, and the prediction process is performed on each sequence to obtain multiple initial prediction results, including: Processing each of the k modal component IMF sequences respectively to obtain multiple subsequence prediction results; The residual sequence is decomposed twice to obtain a residual prediction result.

[0010] In a possible implementation, performing secondary decomposition on the residual sequence to obtain a residual prediction result includes: Performing secondary decomposition on the residual sequence based on a preset number of neural networks to obtain a residual subsequence corresponding to each neural network; Combining a preset number of residual subsequences to obtain a combined prediction model; The combined prediction model is calculated according to the preset number of residual subsequences to obtain a residual prediction result.

[0011] In a possible implementation, obtaining a target prediction result according to the multiple initial prediction results includes: The multiple subsequence prediction results and the residual prediction result are superimposed and reconstructed to obtain a target prediction result.

[0012] In a possible implementation, monitoring the blockage of the mine filling pipeline according to the target prediction result and the second temperature and vibration data includes: Obtaining a pipe diameter change trend value according to the target prediction result and the second temperature-vibration data; The blockage condition of the mine filling pipeline is monitored according to the pipe diameter change trend value.

[0013] In a possible implementation, monitoring the blockage of the mine filling pipeline according to the pipe diameter change trend value includes: Setting the classification level of the pipeline transportation status of the mine filling pipeline; Determining a target level according to the pipeline transportation status classification level and the pipeline diameter change trend value; The blockage of the mine filling pipeline is monitored according to the target level.

[0014] In a possible implementation, combining a preset number of residual subsequences to obtain a combined prediction model includes: Combining a preset number of residual subsequences to obtain an initial combined prediction model; The initial combined prediction model is optimized based on the crow search algorithm to obtain a combined prediction model.

[0015] On the other hand, the present invention also provides a mine filling pipeline blockage monitoring device, comprising: A data acquisition module, used to acquire the first temperature and vibration data of the mine filling pipeline at the current moment and the second temperature and vibration data at the previous moment; A data prediction module, used for processing the first temperature-vibration data to obtain a plurality of initial prediction results; A result prediction module, used to obtain a target prediction result according to the multiple initial prediction results; A pipeline monitoring module is used to monitor the blockage of the mine filling pipeline according to the target prediction result and the second temperature and vibration data.

[0016] The beneficial effect of the present invention is to obtain the first temperature vibration data of the mine filling pipeline at the current moment and the second temperature vibration data at the previous moment; then the first temperature vibration data at the current moment can be processed to obtain multiple initial prediction results; and based on the multiple initial prediction results, the target prediction result is obtained; then the blockage condition of the mine filling pipeline can be monitored according to the target prediction result and the second temperature vibration data at the previous moment, so that the blockage condition of the mine filling pipeline can be predicted in real time according to the first temperature vibration data at the current moment and the second temperature vibration data at the previous moment, so that the abnormality can be detected before the filling pipeline is blocked, so that the staff can deal with it according to the monitoring situation, thereby ensuring the normal production and safety of the mine. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A schematic flow chart of an embodiment of a method for monitoring blockage in a mine filling pipeline provided by the present invention; Figure 2 A schematic diagram of a flow chart of an embodiment of the residual prediction result provided by the present invention; Figure 3 A schematic diagram of an embodiment of the process flow of mine filling pipeline monitoring provided by the present invention; Figure 4 A schematic structural diagram of an embodiment of a mine filling pipeline blockage monitoring device provided by the present invention; Figure 5 A schematic structural diagram of an embodiment of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0018] The preferred embodiments of the present invention are described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not used to limit the scope of the present invention.

[0019] like Figure 1 As shown, a specific embodiment of the present invention discloses a method for monitoring blockage of a mine filling pipeline, comprising: S101, obtaining first temperature and vibration data of a mine filling pipeline at a current moment and second temperature and vibration data at a previous moment; S102, processing the first temperature-vibration data to obtain a plurality of initial prediction results; S103, obtaining a target prediction result according to multiple initial prediction results; S104. Monitor the blockage of the mine filling pipeline according to the target prediction result and the second temperature vibration data.

[0020] It should be understood that: a temperature vibration sensor can be installed on the mine filling pipe, and the temperature vibration data with time series information can be collected by the temperature vibration sensor, such as the first temperature vibration data at the current moment and the second temperature vibration data at the previous moment. The specific acquisition process can be set according to actual conditions, and the embodiments of the present invention are not limited here.

[0021] In a specific embodiment of the present invention, the first temperature vibration data of the mine filling pipeline at the current moment and the second temperature vibration data of the previous moment can be obtained, and then the first temperature vibration data can be processed through VMD decomposition to obtain multiple initial prediction results of multiple subsequences, and then the target prediction result can be obtained based on the multiple initial prediction results, and then the target prediction result and the second temperature vibration data can be calculated and judged, so that detection can be performed based on the judgment result. For example, when the judgment result is that there is an abnormality, it means that it may be blocked or has been blocked. At this time, the staff can process the mine filling pipeline according to the detection results to ensure the normal operation and safety of the mine filling pipeline.

[0022] Compared with the prior art, the present embodiment provides a method for obtaining the first temperature vibration data of the mine filling pipeline at the current moment and the second temperature vibration data of the previous moment; and then the first temperature vibration data at the current moment can be processed to obtain a plurality of initial prediction results; and based on the plurality of initial prediction results, a target prediction result can be obtained; and then the blockage of the mine filling pipeline can be monitored according to the target prediction result and the second temperature vibration data of the previous moment, so that the mine filling pipeline can be monitored in real time according to the first temperature vibration data at the current moment and the second temperature vibration data of the previous moment, so that the abnormality can be detected before the filling pipeline is blocked, so that the staff can handle it according to the monitoring situation at the right time, thereby ensuring the normal production and safety of the mine.

[0023] In some embodiments of the present invention, step S102 includes: Decomposing the first temperature-vibration data to obtain multiple sequences; Prediction processing is performed on each sequence separately to obtain multiple initial prediction results.

[0024] In a specific embodiment of the present invention, the temperature vibration data can be decomposed by a preset algorithm to obtain multiple sequences. The specific preset algorithm can be set according to actual conditions, and the embodiment of the present invention is not limited here. Then, each sequence can be predicted to obtain an initial prediction result corresponding to each sequence, and then multiple sequences can be obtained to obtain multiple initial prediction results.

[0025] In some embodiments of the present invention, the multiple sequences include a residual sequence and k modal component IMF sequences, and the first temperature vibration data is decomposed to obtain multiple sequences, including: Based on the preset optimization algorithm, the core parameters of the VMD decomposition algorithm, the modal number k value and the penalty factor, are optimized to obtain the target VMD decomposition algorithm; The first temperature vibration data is decomposed based on the target VMD decomposition algorithm to obtain k modal component IMF sequences and a residual sequence.

[0026] In a specific embodiment of the present invention, the core parameters of the VMD decomposition algorithm, the modal number k value and the penalty factor, are optimized based on a preset optimization algorithm to obtain the optimal parameter combination of the modal component k value and the penalty factor α, that is, to obtain the target VMD decomposition algorithm, wherein the preset optimization algorithm may be a GOOSE optimization algorithm. The specific optimization process may be: Step 1: Initialize the parameters. The position of the goose is x, and the specific variable is [ k , α ] Initialize the goose flock Xi ( i= 1,2,...,n). When rnd≥0.5, the exploration phase is activated; in the exploration phase, if pro>0.2 and S_W ≥12, perform location exploration, as shown in formula (1): (1) Where: S_W it Indicates the number of iterations, the value range is [5~25]; T_o_A_O it represents the time it takes for a stone to reach the ground when it falls, and it is random, between 1 and the number of dimensions of each iteration in the loop; T_o_A_S it When the object hits the ground, a sound is made and transmitted to each goose in the flock; T_o_A it Indicates the time during the iteration process; T_ T represents the total time required for the sound to propagate through the entire iteration and reach a single goose in the flock; T_A Indicates the average time required; F_F_S represents the free fall speed; S_S Indicates the speed of sound propagation; D_S_T it Distance of sound propagation; D_G it the distance between the guard goose and another goose that is resting or eating; X represents the optimal position solution found.

[0027] When rnd≥0.5, the exploration phase is activated; in the exploration phase, if pro≤0.2 and S_W When <12, the following formula is used for iteration, as shown in formula (2):

[0028]

[0029] (2) All formulas in formula (2) are iterated to find the optimal position solution for the goose.

[0030] When rnd < 0.5, the exploration phase is started directly and iterated as shown in formula (3):

[0031] (3) Where: Best_pos is the best location found in the search area.

[0032] Step 2: If you cross the limit, you will adapt X , evaluate the objective function and return the optimal solution to obtain the optimal k and α Combination, we can get the optimized target VMD decomposition algorithm. X , it will return to step 1 and cycle again.

[0033] Then, the first temperature-vibration data can be decomposed based on the target VMD decomposition algorithm to obtain k The solution is shown in formula (4): Data initialization, IMF sequence set , residual sequence set , Lagrange multipliers , n are all set to 0, where u k , oh k Represents each sub-modal component and center frequency ( k =1,2,⋯, K ); l Represents the Lagrange multiplier and selects the optimal decomposition order k As the default value; updated by introducing the augmented Lagrangian equation and the alternating direction multiplier method u k and oh k ; then update ,Right now ,in, oh represents the angular velocity; the iteration stops when the following convergence conditions are met. The convergence conditions are ; Otherwise, return to step data initialization. When the iteration stops, get The k modal component IMF sequences in A residual sequence in .

[0034] In some embodiments of the present invention, the multiple initial prediction results include multiple subsequence prediction results and residual prediction results, and prediction processing is performed on each sequence to obtain multiple initial prediction results, including: Respectively k Each modal component IMF sequence in the modal component IMF sequence is processed to obtain multiple subsequence prediction results; The residual sequence is decomposed twice to obtain the residual prediction result.

[0035] In a specific embodiment of the present invention, the decomposed kThe IMF sequences of the modal components are sent to LSTM for prediction respectively. The basic formula of LSTM is shown in formula (4): (4) Where: f t , i t , c t , o t express t The forget gate, input gate, cell state and output gate at each moment; Indicates the creation of an alternative c t ; h t Indicates the output result; s Represents the sigmoid function; W f , W i , W c , W o Represent the weight matrices of the forget gate, input gate, cell state, and output gate respectively; h t express t The hidden layer output at time t; x t express t Input of time; b f , b i , b c , b o They represent the bias terms of the forget gate, input gate, cell state and output gate respectively; tanh represents the hyperbolic tangent function.

[0036] Therefore, each subsequence can be predicted through the LSTM prediction neural network, and the subsequence prediction result corresponding to each subsequence can be output.

[0037] In some embodiments of the present invention, Figure 2 As shown, the residual sequence is decomposed twice to obtain the residual prediction results, including: S201, performing secondary decomposition on the residual sequence based on a preset number of neural networks to obtain a residual subsequence corresponding to each neural network; S202, combining a preset number of residual subsequences to obtain a combined prediction model; S203: Calculate the combined prediction model according to a preset number of residual subsequences to obtain a residual prediction result.

[0038] In a specific embodiment of the present invention, the residual sequence can be decomposed twice using the SSA algorithm to obtain a residual subsequence corresponding to each neural network, that is, a preset number of residual subsequences. The preset number of residual subsequences are used to establish a combined prediction model including a preset number of neural networks, wherein the preset number of neural networks may include KAN, SVM and MLP. Then, the combined prediction model can be calculated according to the preset number of residual subsequences to obtain a residual prediction result.

[0039] In some embodiments of the present invention, step S202 includes: Combining a preset number of residual subsequences to obtain an initial combined prediction model; The initial combined prediction model is optimized based on the crow search algorithm to obtain the combined prediction model.

[0040] In a specific embodiment of the present invention, the three neural network models KAN, SVM and MLP are combined through formula (5) to obtain an initial combined prediction model: (5) Where: P i express i Combined prediction value at time; , , Indicates that the three sub-models are i The predicted value at the moment; oh 1 , oh 2 and oh 3 Represents the combination coefficient of the three sub-models.

[0041] Furthermore, the initial combined prediction model can be optimized based on the crow search algorithm. Specifically: 1. Formulate the optimization problem and its decision variables and constraints, and set the value of the adjustable parameter, i.e., the number of crows ( or c ), maximum number of iterations (Niter), flight length ( or l ) and perceived probability ( c AP ).

[0042] 2. Design a or c Line and or d A matrix consisting of columns, where orc , or d are the number of crows and decision variables, respectively. Each crow represents a feasible solution, and the memory of each crow is set. In addition, at the beginning, all crows have no experience, so it is assumed that each crow hides food in a random location.

[0043] 3. Calculate the value of the fitness function.

[0044] 4. Calculate the new position of the crow. First, generate a random number and compare it with c AP Compare, if the random number value is less than c AP , then the crow moves randomly in the search space. Otherwise, the crow (x i ) Randomly select any group of crows ( m j ), followed by m j Determine where it hides its food. i ) is calculated as shown in formula (6): (6) In the formula: r represents a random number; t represents the number of iterations. This process is performed for all η c Repeat for each crow.

[0045] 5. Calculate the fitness of the new position.

[0046] 6. Determine whether the crow's memory is updated based on the fitness values ​​of the new position and the remembered position, that is, if the fitness value of the newly occupied position is better than that of the remembered position, the crow's memory will be updated, otherwise, the crow stays at the current position.

[0047] 7. Repeat steps 4 to 6 until the maximum number of iterations or the termination criterion is met. The best position remembered by the crow will represent the final solution to the optimization problem.

[0048] 8. Solve the combination coefficient in formula (5) according to steps 1-7, and select the root mean square error as the fitness function value of the crow search algorithm. The optimal solution of the crow search algorithm is recorded as: , , , then the optimized combined prediction model is obtained, as shown in formula (7): (7) In some embodiments of the present invention, step S103 includes: Multiple subsequence prediction results and residual prediction results are superimposed and reconstructed to obtain the target prediction result.

[0049] In a specific embodiment of the present invention, multiple subsequence prediction results are reconstructed according to formula (8) to obtain the final target prediction result, as shown in formula (8): (8) In the formula, represents the subsequence prediction result, , and They represent the prediction results of the 1st, 2nd and k+1th subsequences respectively.

[0050] In some embodiments of the present invention, step S104 includes: According to the target prediction result and the second temperature vibration data, the pipe diameter change trend value is obtained; The blockage of mine filling pipelines is monitored based on the trend value of pipe diameter changes.

[0051] In a specific embodiment of the present invention, the change in the diameter of the filling pipeline in the future can be predicted, including: recording the obtained target prediction result as S 0 , the temperature vibration data obtained by setting the interval time t is S t , that is, the second temperature vibration data at the previous moment is S t .pass D p =S 0 / S t To indicate the change trend of pipe diameter, the blockage of mine filling pipeline can be monitored according to the change trend.

[0052] In some embodiments of the present invention, Figure 3 As shown, the blockage of the mine filling pipeline is monitored according to the trend value of the pipe diameter change, including: S301, setting the classification level of the pipeline transportation status of the mine filling pipeline; S302, determining a target level according to the pipeline transportation status classification level and the pipeline diameter change trend value; S303. Monitor the blockage of the mine filling pipeline according to the target level.

[0053] In a specific embodiment of the present invention, the pipeline transportation status classification level of the mine filling pipeline can be set, for example, level one, level two and level three, where level one represents a blocked state, level two represents a blocked state, and level three represents a normal state, wherein greater than 1.2 is level three, between 1.2 and 1.5 is level two, and greater than 1.5 is level one. The specific pipeline transportation status classification level and the corresponding value of each level can be set according to the actual situation, and the embodiment of the present invention is not limited here. Then, according to the calculated pipe diameter change trend value D p , determine the target level in the pipeline transportation status classification level, when D p When the value is less than 1.2, the pipe diameter is normal; when D p When the value is between 1.2 and 1.5, it is classified as Level 2, warning state; when D p When the value is greater than 1.5, it is classified as level 1, which is a blocked state. Based on the pipeline temperature vibration prediction model, the pipe diameter change level is predicted, and the predicted state level is sent to the terminal to complete the filling pipeline temperature vibration monitoring and pipe blockage warning.

[0054] The embodiment of the present invention obtains the time series of temperature vibration data by installing a temperature vibration sensor on the filling pipe, decomposes the temperature vibration data by using the VMD data decomposition method, and solves the optimal K and α The value is used to improve the application scope of the prediction algorithm. The obtained data sequences are sent to the LSTM prediction model, the residual sequence is decomposed twice, and the combined prediction model optimized by the crow algorithm is established for the subsequences of the secondary decomposition, which greatly improves the accuracy of the prediction results. With the help of the prediction results, the quantitative characterization of the change of pipeline diameter is realized, which creates emergency processing time for handling pipe blockage and provides a new idea for mine pipeline monitoring.

[0055] In order to better implement the mine filling pipeline blockage monitoring method in the embodiment of the present invention, based on the mine filling pipeline blockage monitoring method, the embodiment of the present invention also provides a mine filling pipeline blockage monitoring device, such as Figure 4 As shown, the mine filling pipeline blockage monitoring device 400 includes: The data acquisition module 401 is used to acquire the first temperature and vibration data of the mine filling pipeline at the current moment and the second temperature and vibration data at the previous moment; A data prediction module 402 is used to process the first temperature-vibration data to obtain a plurality of initial prediction results; The result prediction module 403 is used to obtain a target prediction result according to a plurality of initial prediction results; The pipeline monitoring module 404 is used to monitor the blockage of the mine filling pipeline according to the target prediction result and the second temperature and vibration data.

[0056] The mine filling pipeline blockage monitoring device 400 provided in the above embodiment can implement the technical solution described in the above mine filling pipeline blockage monitoring method embodiment. The specific implementation principles of the above modules or units can refer to the corresponding contents in the above mine filling pipeline blockage monitoring method embodiment, which will not be repeated here.

[0057] like Figure 5 As shown, the present invention also provides an electronic device 500. The electronic device 500 includes a processor 501, a memory 502 and a display 503. Figure 5 Only some components of the electronic device 500 are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0058] In some embodiments, the memory 502 may be an internal storage unit of the electronic device 500, such as a hard disk or memory of the electronic device 500. In other embodiments, the memory 502 may also be an external storage device of the electronic device 500, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 500.

[0059] Furthermore, the memory 502 may include both an internal storage unit of the electronic device 500 and an external storage device. The memory 502 is used to store application software installed in the electronic device 500 and various data.

[0060] In some embodiments, the processor 501 may be a central processing unit (CPU), a microprocessor or other data processing chip, which is used to run the program code or process data stored in the memory 502, such as the mine filling pipeline blockage monitoring method of the present invention.

[0061] In some embodiments, the display 503 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 503 is used to display information of the electronic device 500 and to display a visual user interface. The components 501-503 of the electronic device 500 communicate with each other through a system bus.

[0062] In some embodiments of the present invention, when the processor 501 executes the mine filling pipeline blockage monitoring program in the memory 502, the following steps may be implemented: Obtaining the first temperature and vibration data of the mine filling pipeline at the current moment and the second temperature and vibration data at the previous moment; Processing the first temperature-vibration data to obtain a plurality of initial prediction results; According to multiple initial prediction results, a target prediction result is obtained; The blockage of the mine filling pipeline is monitored based on the target prediction results and the second temperature and vibration data.

[0063] It should be understood that: when the processor 501 executes the mine filling pipeline blockage monitoring program in the memory 502, in addition to the above functions, other functions can also be implemented. For details, please refer to the description of the corresponding method embodiment above.

[0064] Furthermore, the embodiment of the present invention does not specifically limit the type of the electronic device 500 mentioned, and the electronic device 500 may be a portable electronic device such as a mobile phone, a tablet computer, a personal digital assistant (PDA), a wearable device, a laptop computer, etc. Exemplary embodiments of portable electronic devices include but are not limited to portable electronic devices equipped with IOS, Android, Microsoft or other operating systems. The above-mentioned portable electronic devices may also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the present invention, the electronic device 500 may not be a portable electronic device, but a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0065] Accordingly, an embodiment of the present application also provides a computer-readable storage medium, which is used to store computer-readable programs or instructions. When the program or instructions are executed by a processor, the steps or functions of the mine filling pipeline blockage monitoring method provided in the above-mentioned method embodiments can be implemented.

[0066] Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware (such as a processor, a controller, etc.) through a computer program, and the computer program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0067] The above is a detailed introduction to the mine filling pipeline blockage monitoring method and device provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for monitoring blockage of mine filling pipelines, It is characterized in that include: Obtaining the first temperature and vibration data of the mine filling pipeline at the current moment and the second temperature and vibration data at the previous moment; Processing the first temperature-vibration data to obtain a plurality of initial prediction results; Obtaining a target prediction result according to the multiple initial prediction results; The blockage condition of the mine filling pipeline is monitored according to the target prediction result and the second temperature and vibration data.

2. The method for monitoring blockage of a mine filling pipeline according to claim 1, It is characterized in that The first temperature-vibration data is processed to obtain a plurality of initial prediction results, including: Decomposing the first temperature-vibration data to obtain multiple sequences; Prediction processing is performed on each sequence separately to obtain multiple initial prediction results.

3. The method for monitoring blockage of a mine filling pipeline according to claim 2, It is characterized in that The multiple sequences include a residual sequence and k modal component IMF sequences, and the first temperature vibration data is decomposed to obtain multiple sequences, including: Based on the preset optimization algorithm, the core parameters of the VMD decomposition algorithm, the modal number k value and the penalty factor, are optimized to obtain the target VMD decomposition algorithm; The first temperature-vibration data is decomposed based on the target VMD decomposition algorithm to obtain k modal component IMF sequences and a residual sequence.

4. The method for monitoring blockage of a mine filling pipeline according to claim 3, It is characterized in that The multiple initial prediction results include multiple subsequence prediction results and residual prediction results. The prediction process is performed on each sequence to obtain multiple initial prediction results, including: Processing each of the k modal component IMF sequences respectively to obtain multiple subsequence prediction results; The residual sequence is decomposed twice to obtain a residual prediction result.

5. The method for monitoring blockage of a mine filling pipeline according to claim 4, It is characterized in that The performing secondary decomposition on the residual sequence to obtain a residual prediction result includes: Performing secondary decomposition on the residual sequence based on a preset number of neural networks to obtain a residual subsequence corresponding to each neural network; Combining a preset number of residual subsequences to obtain a combined prediction model; The combined prediction model is calculated according to the preset number of residual subsequences to obtain a residual prediction result.

6. The method for monitoring blockage of a mine filling pipeline according to claim 4, It is characterized in that The step of obtaining a target prediction result according to the multiple initial prediction results includes: The multiple subsequence prediction results and the residual prediction result are superimposed and reconstructed to obtain a target prediction result.

7. The mine filling pipeline blockage monitoring method according to claim 1, It is characterized in that The monitoring of the blockage condition of the mine filling pipeline according to the target prediction result and the second temperature vibration data includes: Obtaining a pipe diameter change trend value according to the target prediction result and the second temperature-vibration data; The blockage condition of the mine filling pipeline is monitored according to the pipe diameter change trend value.

8. The method for monitoring blockage of a mine filling pipeline according to claim 7, It is characterized in that The monitoring of the blockage of the mine filling pipeline according to the pipe diameter change trend value includes: Setting the classification level of the pipeline transportation status of the mine filling pipeline; Determining a target level according to the pipeline transportation status classification level and the pipeline diameter change trend value; The blockage of the mine filling pipeline is monitored according to the target level.

9. The method for monitoring blockage of a mine filling pipeline according to claim 5, It is characterized in that The combining of the preset number of residual subsequences to obtain a combined prediction model includes: Combining a preset number of residual subsequences to obtain an initial combined prediction model; The initial combined prediction model is optimized based on the crow search algorithm to obtain a combined prediction model.

10. A mine filling pipeline blockage monitoring device, It is characterized in that include: A data acquisition module, used to acquire the first temperature and vibration data of the mine filling pipeline at the current moment and the second temperature and vibration data at the previous moment; A data prediction module, used for processing the first temperature-vibration data to obtain a plurality of initial prediction results; A result prediction module, used to obtain a target prediction result according to the multiple initial prediction results; A pipeline monitoring module is used to monitor the blockage of the mine filling pipeline according to the target prediction result and the second temperature and vibration data.

Citation Information

Patent Citations

  • Pipeline multi-point leakage positioning method based on improved VMD

    CN110454687A

  • Limestone slurry supply pipeline blockage condition prediction method and prediction device

    CN114066044A

  • Method and device for predicting blockage of filling pipeline

    CN117709519A

  • Pipeline leakage detection method and inspection trolley

    CN117906083A

  • Pipeline network solving using decomposition procedure

    US20210397764A1

Cited By

  • Mine cemented filling parameter optimization method based on predictive modeling and improved NSGA-III algorithm

    CN120508881A

  • Soil organic matter content inversion method and system based on improved GOOSE-SVM

    CN121075473A