Prediction method for coal caving attitude of hydraulic support and related device

Abstract

The invention provides a hydraulic support coal caving attitude prediction method and related device.The prediction method comprises the steps that multiple hydraulic support state parameters are obtained to serve as related factors, and the hydraulic support state parameters at least comprise support attitude data and oil cylinder liquid supply data; inputting the correlation factors into a trained prediction model, wherein the prediction model is constructed based on a long and short term neural network; and outputting the coal caving posture of the tail beam of the hydraulic support through the prediction model. According to the embodiment of the invention, the posture of the coal caving mechanism at the tail part of the hydraulic support can be accurately predicted through the trained prediction model based on the data related to the movement of the tail beam, so that the top coal caving mining process is accurately controlled.

Description

Technical Field

[0001] This disclosure relates to the technical field of mine hydraulic support control, specifically to a method and related device for predicting the coal discharge posture of a hydraulic support. Background Technology

[0002] In engineering applications, the coal feeding attitude is often sensed in real time by means of attitude angle sensors installed at the tail of hydraulic supports. However, the underground mining environment is complex and subject to factors such as noise, vibration, and magnetic fields, which can cause abnormal data drift and data loss in the sensor data acquisition results. Especially in complex and harsh environments, sensor damage is unavoidable, and the area where the coal feeding mechanism is located is relatively dangerous, and personnel are not allowed to enter the area for maintenance work according to operating procedures.

[0003] In addition to using sensors to collect data, manual observation or setting up cameras can also be used. However, due to factors such as the confined underground environment and the obstruction of vision by the support equipment structure, there are still a large number of blind spots in the field of vision, whether it is human observation or camera monitoring, and it is still impossible to obtain the posture of the coal feeding mechanism in real time and accurately.

[0004] Because the accurate posture of the coal feeding mechanism cannot be obtained, it is impossible to accurately control the top coal caving mining process, thus making it impossible to effectively manage the coal feeding speed and determine whether there are large amounts of gangue (impurities). Summary of the Invention

[0005] The purpose of this disclosure is to provide a method and related apparatus for predicting the coal discharge posture of a hydraulic support, so as to solve the above-mentioned problems existing in the prior art.

[0006] To address the aforementioned technical problems, embodiments of this disclosure provide, in one aspect, a method for predicting the coal discharge posture of a hydraulic support, comprising:

[0007] Multiple hydraulic support status parameters are acquired as relevant factors, and the hydraulic support status parameters include at least support posture data and cylinder fluid supply data.

[0008] The relevant factors are input into a trained prediction model, which is constructed based on a long short-term neural network;

[0009] The prediction model outputs the coal discharge posture of the tail beam of the hydraulic support.

[0010] In some embodiments, the support posture data is at least one of the following:

[0011] The absolute spatial position of the hydraulic support, the relative spatial position of the hydraulic support, the height of the hydraulic support, the attitude angle of the hydraulic support, and the angle of the top beam.

[0012] In some embodiments, the hydraulic cylinder supply data is at least one of the following:

[0013] Pump station outlet flow rate, pump station outlet pressure, pipeline pressure, column pressure, cylinder pressure, tail beam extension time, tail beam retraction time, push-pull time, and column lowering time.

[0014] In some embodiments, the number of hydraulic support status parameters is 4-8.

[0015] In some embodiments, the prediction model is constructed based on a long short-term neural network.

[0016] In some embodiments, the prediction model is trained in the following manner:

[0017] The collected relevant factors are input into the prediction model to obtain the prediction results;

[0018] Collect real data corresponding to the relevant factors;

[0019] The prediction model is deemed to meet the evaluation requirements when the mean absolute error between the predicted result and the actual data is less than the first threshold, the root mean square error is less than the second threshold, and the linear regression coefficient is greater than the third threshold.

[0020] Another embodiment of this disclosure provides a device for predicting the coal discharge posture of a hydraulic support, comprising:

[0021] The acquisition module is used to acquire multiple hydraulic support status parameters as relevant factors. The hydraulic support status parameters include at least support posture data and cylinder fluid supply data.

[0022] A prediction module is used to input the relevant factors into a trained prediction model, which is constructed based on a long short-term neural network;

[0023] The output module is used to output the coal discharge posture of the tail beam of the hydraulic support through the prediction model.

[0024] Another aspect of the embodiments of this disclosure provides a hydraulic support that includes a tail beam and the aforementioned predictive device.

[0025] This disclosure also provides a storage medium storing a computer program that, when executed by a processor, implements the steps of the prediction method described above.

[0026] This disclosure also provides an electronic device, which includes at least a memory and a processor. The memory stores a computer program, and the processor executes the computer program in the memory to implement the steps of the prediction method described above.

[0027] The embodiments disclosed herein can accurately predict the attitude of the coal release mechanism at the tail of the hydraulic support by using a trained prediction model based on data related to the tail beam movement, which enables precise control of the top coal caving mining process.

[0028] The apparatus, storage medium, and electronic equipment disclosed herein have all the beneficial effects of the prediction method described above, which will not be repeated here. Attached Figure Description

[0029] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0030] Figure 1 This is a schematic diagram of the structure of the hydraulic support involved in the embodiments of this disclosure;

[0031] Figure 2 This is a schematic diagram illustrating the steps of the method for predicting the coal discharge posture of a hydraulic support in an embodiment of this disclosure;

[0032] Figure 3 This is a schematic diagram of the architecture of a long short-term neural network in the method for predicting the coal discharge posture of a hydraulic support in this embodiment of the present disclosure.

[0033] Figure 4 This is a schematic diagram illustrating the training of the prediction model in the method for predicting the coal discharge posture of the hydraulic support in this embodiment of the present disclosure.

[0034] Figure label:

[0035] 1-Top beam; 2-Shielding beam; 3-Column; 4-Connecting rod; 5-Base; 6-Connecting part; 7-Tail beam; 8-Scraper conveyor. Detailed Implementation

[0036] Various embodiments and features of this disclosure are described herein with reference to the accompanying drawings.

[0037] It should be understood that various modifications can be made to the embodiments described herein. Therefore, the above description should not be considered as limiting, but merely as an example of embodiments. Other modifications within the scope and spirit of this disclosure will be apparent to those skilled in the art.

[0038] The accompanying drawings, which are included in and form part of this specification, illustrate embodiments of the present disclosure and, together with the general description of the disclosure given above and the detailed description of the embodiments given below, serve to explain the principles of the disclosure.

[0039] These and other features of this disclosure will become apparent from the following description of preferred forms of embodiments given as non-limiting examples, with reference to the accompanying drawings.

[0040] It should also be understood that although this disclosure has been described with reference to some specific examples, those skilled in the art can certainly implement many other equivalent forms of this disclosure, which have the features described in the claims and are therefore all within the scope of protection defined herein.

[0041] The above and other aspects, features and advantages of this disclosure will become more apparent when taken in conjunction with the accompanying drawings and in view of the following detailed description.

[0042] Specific embodiments of this disclosure are described thereafter with reference to the accompanying drawings; however, it should be understood that the claimed embodiments are merely examples of this disclosure, which may be implemented in various ways. Well-known and / or repeated functions and structures are not described in detail to avoid unnecessary or redundant details that could obscure this disclosure. Therefore, the specific structural and functional details claimed herein are not intended to be limiting, but merely to serve as the basis and representative basis for the claims to teach those skilled in the art to use this disclosure in a variety of substantially any suitable detailed structures.

[0043] This specification may use the phrases “in one embodiment,” “in another embodiment,” “in yet another embodiment,” or “in still another embodiment,” all of which may refer to one or more of the same or different embodiments according to this disclosure.

[0044] The first embodiment of this disclosure provides a method for predicting the coal release posture of a hydraulic support. The hydraulic support is a key device in fully mechanized filling coal mining technology used on a longwall face to realize the coal release operation, which can effectively fill the goaf and also handle solid waste such as gangue to control surface subsidence.

[0045] In one implementation, such as Figure 1 As shown, the hydraulic support includes a top beam 1, a shield beam 2, a column 3, a connecting rod 4, a base 5, and a tail beam 7. The top beam 1, the shield beam 2, and the tail beam 7 are connected in sequence. The column 3 is the pressure-bearing component of the hydraulic support. It is under high pressure for a long time. In addition to having reasonable working resistance and reliable working characteristics, it must also have sufficient compressive and bending strength and good sealing performance.

[0046] The end of the tail beam 7 is hinged to the shield beam 2 and supported by the tail beam jack on the shield beam 2. After the hydraulic support moves forward, the collapsed top coal and roof directly act on the tail beam 7. The tail beam 7 is a key component of the hydraulic support used for shielding and realizing top coal caving. The function of the tail beam 7 is to support the loose top coal and roof rock, maintain a good working space, and thus create conditions for realizing top coal caving.

[0047] Furthermore, a dual-purpose lifting scraper conveyor 8 is provided below the tail beam 7. A coal discharge port is opened in the middle of the top surface of the tail beam 7. A lifting mechanism controlled by a pump-hydraulic pipeline and a control system is provided on the inner side of the tail beam 7. The lifting mechanism includes a power system and a transmission device. The power system includes a hydraulic cylinder, which provides hydraulic pressure to support the tail beam 7 through the connecting part 6, allowing the tail beam 7 to swing up and down as needed. This, together with, for example, the shield beam 2, ensures sufficient coal discharge and passage space at the rear of the hydraulic support. The lifting mechanism is connected to the scraper conveyor 8 to control the raising and lowering of the scraper conveyor 8, coordinating the coal discharge and filling processes to realize the coal transportation and gangue filling work in the top coal caving face.

[0048] Furthermore, the tail beam 7 of the hydraulic support is used to perform the rear coal release operation. In the top coal caving mining process, the change in the inclination angle of the tail beam 7 causes the coal seam above the shield beam 2 to fall into the rear of the hydraulic support, thereby realizing the tail coal release operation. However, due to the limitations of the production environment and mechanical structure, underground operators cannot intuitively see the coal and gangue falling during the coal release at the rear of the hydraulic support, and often rely on the sound and time of the coal falling to judge. In addition, in remote coal release operation and automatic coal release, the timing of the coal release action and the inclination angle of the tail beam 7 are often set based on production experience for conventional coal release operations, but there is a lack of effective status perception means, making it impossible to accurately obtain the status of the mining area and equipment execution, and impossible to adjust the coal release control in real time, resulting in coal loss and gangue falling. If only an inclination sensor is installed on the tail beam 7, there are also problems such as sensor data distortion and serious equipment damage. Moreover, in the mechanical structure analysis of the hydraulic support, there are problems such as the variety of support models and the difficulty in applying calculation methods.

[0049] The method for predicting the coal-releasing posture of the hydraulic support described in this embodiment is used to predict the performance of the hydraulic support when it autonomously performs coal-releasing operations. Figure 2 As shown, it includes:

[0050] S101, acquire multiple hydraulic support status parameters as relevant factors, wherein the hydraulic support status parameters include at least support posture data and cylinder fluid supply data.

[0051] In this step, multiple hydraulic support state parameters are acquired as correlation factors. In this embodiment, to predict the attitude of the tail beam 7, such as its tilt angle, it is necessary to acquire the hydraulic support state parameters. These hydraulic support state parameters are parameters related to the movement of the tail beam 7. This facilitates selecting a portion of the hydraulic support state parameters related to the movement of the tail beam 7 and grouping them into a set of correlation factors. Each set of correlation factors corresponds to a tilt angle data point of the tail beam 7 in time sequence. In this step, a set of correlation data reflecting the state of the hydraulic support from different dimensions is collected, including support attitude data, cylinder fluid supply data, etc.

[0052] It should be noted that the type and quantity of data included in the relevant factors mentioned here are not fixed and can be adjusted according to actual needs. Specifically, the relevant factors can be dynamically adjusted and selected based on the available data on site, and multiple hydraulic support state parameters can be reasonably grouped. Ideally, each group of relevant factors should include 4-8 hydraulic support state parameters; that is, the optimal number of hydraulic support state parameters in each group of relevant factors is 4-8. Setting the above-mentioned number of hydraulic support state parameters can improve the prediction accuracy of the prediction model.

[0053] Furthermore, the posture data of the support and the hydraulic cylinder fluid supply data, which are selected as the state parameters of the hydraulic support, are acquired by sensors, such as position sensors, height sensors, and angle sensors installed on the hydraulic support, such as angle sensors installed on the top beam 1 of the hydraulic support, and flow sensors, pressure sensors, etc., installed on the hydraulic cylinder, pump station, or pipeline, as well as time sensors used to monitor working time.

[0054] Therefore, the support posture data mentioned here includes, but is not limited to, the absolute spatial position of the hydraulic support, the relative spatial position of the hydraulic support, the height of the hydraulic support, the posture angle of the hydraulic support, and the angle of the top beam, etc., wherein the posture angle may include at least one of pitch angle, tilt angle, and roll angle. The hydraulic cylinder fluid supply data mentioned here includes, but is not limited to, the pump station outlet flow rate, the pump station outlet pressure, the pipeline pressure, the column pressure, the cylinder pressure, the tail beam extension time, the tail beam retraction time, the push-pull time, and the column lowering time, etc.

[0055] S102, the relevant factors are input into the trained prediction model, which is constructed based on a long short-term neural network.

[0056] After obtaining multiple hydraulic support state parameters as correlation factors through step S101, this step inputs these correlation factors into a trained prediction model, which is constructed based on a Long Short-Term Neural Network (LSTN). The LSTN is a type of neural network that outperforms traditional Recurrent Neural Networks (RNNs) in handling time-series data and prediction. By introducing a gate control structure to filter neurons, the LSTN can continuously update and train the neural network, and it also solves problems encountered by RNNs such as gradient explosion, gradient vanishing, and long-term dependency.

[0057] Specifically, such as Figure 3 As shown, the long short-term neural network unit includes at least neurons, a forget gate, an input gate, and an output gate. The long short-term neural network can filter neurons carrying data information through its gate control structure, effectively handling gradient problems and long-term dependency problems. Specifically, the forget gate is used to calculate the output data from the previous time step to determine whether the calculated data should be retained; the input gate is used to filter and compare the outputs from adjacent time steps, activating and adding memory units (cells); and the output gate is used to output the data information of the current time step through computation.

[0058] To improve the accuracy of predictions using the long short-term neural network (LSN), the LSN needs to be pre-trained. Training the LSN involves using the collected tilt angle data of the tail beam 7 as a basis, selecting data related to the movement of the tail beam 7, such as support posture data and hydraulic cylinder fluid supply data, as grouped into relevant factors, and combining them with the tilt angle data for training. Each relevant factor corresponds to a tilt angle data point of the tail beam in time sequence. The relevant factors over a continuous time period are input into the LSN to predict the attitude of the tail beam 7 using the LSN algorithm.

[0059] like Figure 4 As shown, the training of the Long Short-Term Neural Network (LSTN) mainly includes a data preprocessing stage and a data training stage. The data preprocessing stage includes data acquisition, which not only verifies the rationality of the data but also removes outliers. Furthermore, the data preprocessing stage requires dividing the relevant factors related to the motion of the tail beam 7 and the tilt angle data of the tail beam 7 into three datasets: a training set, a test set, and a validation set. The division ratio is as follows: largest for the training set, second largest for the test set, and smallest for the validation set. Finally, data normalization is also performed during the data preprocessing stage.

[0060] During the model training phase, the training set is sequentially processed through RNN layers, LSTM layers, and fully connected layers to achieve iterative training, ultimately obtaining the training results. The RNN layers perform convolutional calculations, and the LSTM layers filter data to remove outliers. Furthermore, the training results are evaluated using a test set, comparing the current training result with the previous one to continuously reduce the error between the training result and the actual result, retaining the training result with the smallest error as the prediction model. After a certain number of model iterations, when the model's test results meet the quality requirements, it can be considered to meet the requirements for a prediction model for coal feeding posture. Different evaluation parameters can be set according to the quality requirements to obtain prediction models with different accuracy quality requirements.

[0061] The prediction model described here is trained in the following way: relevant factors are collected and input into the prediction model to obtain prediction results; real data corresponding to the relevant factors are collected; when the mean absolute error between the prediction results and the real data is less than a first threshold, the root mean square error is less than a second threshold, and the linear regression coefficient is greater than a third threshold, the prediction model is determined to meet the evaluation requirements.

[0062] Specifically, for example, mathematical methods can be used to evaluate the training results. Taking the inclination angle of the tail beam 7 as an example, the predicted results are compared with the actual data. When the average absolute error between the predicted results and the actual data is less than 1.8, the root mean square error is less than 2.4, and the linear regression coefficient is greater than 0.99, it is determined that the prediction model for predicting the coal feeding posture meets the prediction requirements.

[0063] Furthermore, the accuracy of the prediction model can be verified using the validation set. For example, the prediction model can be applied to the field, and multiple hydraulic supports can be tracked and compared based on a 2% error. Verification is considered successful if the weighted accuracy is higher than 98%. Here, the prediction model has different failure times within different error ranges; the larger the error range, the longer the failure time.

[0064] S103, the coal discharge posture of the tail beam of the hydraulic support is output through the prediction model.

[0065] After inputting the relevant factors into the trained prediction model through step S102, which is constructed based on a long short-term neural network, this step outputs the coal discharge posture of the tail beam of the hydraulic support through the prediction model. Here, the relevant factors are input into the prediction model to output the coal discharge posture data of the tail beam. The coal discharge posture data can be, for example, the inclination angle data of the tail beam 7. In this way, the inclination angle data of the tail beam 7 can be directly predicted through the relevant factors related to the movement of the tail beam 7.

[0066] Of course, the method for predicting the coal discharge posture of the hydraulic support in this embodiment can also predict the state of other mechanisms on the hydraulic support.

[0067] The embodiments disclosed herein can accurately predict the attitude of the coal release mechanism at the tail of the hydraulic support by using a trained prediction model based on data related to the tail beam movement, which enables precise control of the top coal caving mining process.

[0068] Based on the same inventive concept, a second aspect of this disclosure provides a device for predicting the coal discharge posture of a hydraulic support, comprising a mutually coupled acquisition module, a prediction module, and an output module, wherein:

[0069] The acquisition module is used to acquire multiple hydraulic support status parameters as relevant factors. The hydraulic support status parameters include at least support posture data and cylinder fluid supply data.

[0070] The prediction module is used to input the relevant factors into a trained prediction model, which is constructed based on a long short-term neural network.

[0071] The output module is used to output the coal discharge posture of the tail beam of the hydraulic support through the prediction model.

[0072] Furthermore, the support posture data is at least one of the following:

[0073] The absolute spatial position of the hydraulic support, the relative spatial position of the hydraulic support, the height of the hydraulic support, the attitude angle of the hydraulic support, and the angle of the top beam.

[0074] Furthermore, the hydraulic cylinder fluid supply data is at least one of the following:

[0075] Pump station outlet flow rate, pump station outlet pressure, pipeline pressure, column pressure, cylinder pressure, tail beam extension time, tail beam retraction time, push-pull time, and column lowering time.

[0076] Furthermore, the number of state parameters of the hydraulic support is 4-8.

[0077] Furthermore, the prediction model is constructed based on a long short-term neural network.

[0078] Furthermore, the prediction model is trained in the following manner:

[0079] The collected relevant factors are input into the prediction model to obtain the prediction results;

[0080] Collect real data corresponding to the relevant factors;

[0081] The prediction model is deemed to meet the evaluation requirements when the mean absolute error between the predicted result and the actual data is less than the first threshold, the root mean square error is less than the second threshold, and the linear regression coefficient is greater than the third threshold.

[0082] The embodiments disclosed herein can accurately predict the attitude of the coal release mechanism at the tail of the hydraulic support by using a trained prediction model based on data related to the tail beam movement, which enables precise control of the top coal caving mining process.

[0083] A third aspect of this disclosure provides a storage medium storing a computer program, which, when executed by a processor, implements the steps of the prediction method described above, including:

[0084] S11, acquire multiple hydraulic support status parameters as relevant factors, the hydraulic support status parameters include at least support posture data and cylinder fluid supply data;

[0085] S12, The relevant factors are input into the trained prediction model, which is constructed based on a long short-term neural network;

[0086] S13, the coal discharge posture of the tail beam of the hydraulic support is output through the prediction model.

[0087] The storage medium of this disclosure stores a computer program that, when executed by a processor, can implement the methods in different embodiments of the first embodiment described above.

[0088] The embodiments disclosed herein can accurately predict the attitude of the coal release mechanism at the tail of the hydraulic support by using a trained prediction model based on data related to the tail beam movement, which enables precise control of the top coal caving mining process.

[0089] A fourth aspect of this disclosure provides an electronic device, which includes at least a memory and a processor. The memory stores a computer program, and the processor, when executing the computer program in the memory, implements the steps of the prediction method described above, specifically including:

[0090] S21, acquire multiple hydraulic support status parameters as relevant factors, wherein the hydraulic support status parameters include at least support posture data and cylinder fluid supply data;

[0091] S22, The relevant factors are input into a trained prediction model, which is constructed based on a long short-term neural network;

[0092] S23, the coal discharge posture of the tail beam of the hydraulic support is output through the prediction model.

[0093] The electronic device disclosed herein has a memory storing a computer program, and the processor implements the methods of other embodiments described in the first embodiment when executing the computer program in the memory.

[0094] The embodiments disclosed herein can accurately predict the attitude of the coal release mechanism at the tail of the hydraulic support by using a trained prediction model based on data related to the tail beam movement, which enables precise control of the top coal caving mining process.

[0095] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0096] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0097] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0098] In the embodiments provided in this application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling or direct coupling or communication connection may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0099] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0100] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0101] If the integrated module is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the above method embodiments. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0102] Furthermore, the features of the embodiments shown in the accompanying drawings or the various embodiments mentioned in this specification should not be construed as independent embodiments. Rather, each feature described in one example of an embodiment can be combined with one or more other desired features from other embodiments to produce other embodiments not described in words or with reference to the accompanying drawings.

[0103] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for predicting the coal discharge posture of a hydraulic support, characterized in that, include: Multiple hydraulic support status parameters are acquired as relevant factors, and the hydraulic support status parameters include at least support posture data and cylinder fluid supply data. The relevant factors are input into a trained prediction model, which is constructed based on a long short-term neural network; The prediction model outputs the coal discharge posture of the tail beam of the hydraulic support.

2. The prediction method according to claim 1, characterized in that, The support posture data is at least one of the following: The absolute spatial position of the hydraulic support, the relative spatial position of the hydraulic support, the height of the hydraulic support, the attitude angle of the hydraulic support, and the angle of the top beam.

3. The prediction method according to claim 1, characterized in that, The hydraulic cylinder fluid supply data is at least one of the following: Pump station outlet flow rate, pump station outlet pressure, pipeline pressure, column pressure, cylinder pressure, tail beam extension time, tail beam retraction time, push-pull time, and column lowering time.

4. The prediction method according to claim 1, characterized in that, The number of status parameters for the hydraulic support is 4-8.

5. The prediction method according to claim 1, characterized in that, The prediction model is built based on a long short-term neural network.

6. The prediction method according to claim 5, characterized in that, The prediction model is trained in the following way: The collected relevant factors are input into the prediction model to obtain the prediction results; Collect real data corresponding to the relevant factors; The prediction model is deemed to meet the evaluation requirements when the mean absolute error between the predicted result and the actual data is less than the first threshold, the root mean square error is less than the second threshold, and the linear regression coefficient is greater than the third threshold.

7. A device for predicting the coal discharge posture of a hydraulic support, characterized in that, include: The acquisition module is used to acquire multiple hydraulic support status parameters as relevant factors. The hydraulic support status parameters include at least support posture data and cylinder fluid supply data. A prediction module is used to input the relevant factors into a trained prediction model, which is constructed based on a long short-term neural network; The output module is used to output the coal discharge posture of the tail beam of the hydraulic support through the prediction model.

8. A hydraulic support, comprising a tail beam, characterized in that, Includes the prediction device as described in claim 7.

9. A storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the prediction method according to any one of claims 1 to 6.

10. An electronic device, comprising at least a memory and a processor, wherein the memory stores a computer program, characterized in that, The processor implements the steps of the prediction method according to any one of claims 1 to 6 when executing the computer program on the memory.

Images