Multi-hydraulic support load model training method and multi-hydraulic support load prediction method

Abstract

A multi-hydraulic support load model training method and a multi-hydraulic support load prediction method. The multi-hydraulic support load model training method comprises: acquiring leg pressure data, top beam pitch angle data, top beam roll angle data, coal mining machine cutting position data, coal mining machine traction speed data, and an initial hydraulic support pressure regression prediction model; preprocessing the data to generate a dataset; generating a training dataset and a verification dataset on the basis of the dataset; and training the initial hydraulic support pressure regression prediction model on the basis of the training dataset and the verification dataset, so as to generate a target hydraulic support pressure regression prediction model of a target fully-mechanized coal mining face hydraulic support. By taking into account four dimensions of the top beam pitch angle data, the top beam roll angle data, the coal mining machine cutting position data, and the coal mining machine traction speed data, the target hydraulic support pressure regression prediction model is established and generated by training, so that the support pressure prediction effect can be improved; in addition, by means of model prediction, the prediction efficiency can be improved, and the prediction costs can be reduced.

Description

Multi-hydraulic support load model training and multi-hydraulic support load prediction method

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application is based on the Chinese patent application with application number 202410052401.5 and application date of January 15, 2024, and claims the priority of the Chinese patent application. The entire content of the Chinese patent application is hereby introduced into this application as a reference. Technical Field

[0003] The present disclosure relates to the technical field of coal mining, and in particular to a multi-hydraulic support load model training and multi-hydraulic support load prediction method. Background Art

[0004] The hydraulic support group is an important equipment group for supporting the roof of the fully-mechanized mining face and maintaining the safe working space. The law of its pressure change reflects the law of fracture and migration of the overlying rock strata on the working face. Therefore, by collecting the pressure of the hydraulic support and conducting data-driven predictive analysis, it is possible to achieve advance prediction and early warning of the pressure on the roof of the fully-mechanized mining face, which plays an important role in the subsequent judgment of the initial pressure and periodic pressure of the roof rock strata.

[0005] At present, the pressure prediction of hydraulic supports in fully mechanized mining working faces is generally based on the time series prediction method, that is, a series of pressure data is collected for a certain support in chronological order, and the pressure value at a future moment is predicted using the multiple historical pressure data of the support. In essence, it is to use the change pattern of its own value to predict its own future value. However, the support pressure prediction based on the time series prediction method has fewer input features, the number of historical data directly affects the prediction accuracy, the long-term prediction effect is poor, and it is difficult to achieve advanced intelligent and accurate prediction of the pressure data of the hydraulic support. Therefore, it is necessary to combine the changes in the mining environment and process characteristics of the fully mechanized mining working face, select appropriate input variables, integrate the change characteristics of other parameters, and convert the time series prediction into a multi-input regression prediction to improve the prediction effect of the hydraulic support pressure.

[0006] Summary of the Invention

[0007] The present disclosure aims to solve one of the technical problems in the related art at least to a certain extent.

[0008] To this end, one purpose of the present disclosure is to propose a multi-hydraulic support load model training method.

[0009] The second objective of the present disclosure is to provide a method for predicting the load of multiple hydraulic supports.

[0010] The third objective of the present disclosure is to provide a multi-hydraulic support load model training device.

[0011] The fourth objective of the present disclosure is to provide a multi-hydraulic support load prediction device.

[0012] A fifth objective of the present disclosure is to provide an electronic device.

[0013] A sixth object of the present disclosure is to provide a non-transitory computer-readable storage medium.

[0014] A seventh object of the present disclosure is to provide a computer program product.

[0015] To achieve the above-mentioned purpose, the first embodiment of the present disclosure proposes a multi-hydraulic support load model training method, including: obtaining the column pressure data, top beam pitch angle data, top beam roll angle data, coal mining machine cutting position data and coal mining machine traction speed data of the target comprehensive mining working face hydraulic support, and obtaining the initial hydraulic support pressure regression prediction model to be trained; preprocessing the column pressure data, the top beam pitch angle data, the top beam roll angle data, the coal mining machine cutting position data and the coal mining machine traction speed data to generate a hydraulic support pressure regression prediction model data set; generating a training data set and a verification data set based on the hydraulic support pressure regression prediction model data set; training the initial hydraulic support pressure regression prediction model based on the training data set and the verification data set until the training is completed, thereby generating a target hydraulic support pressure regression prediction model of the target comprehensive mining working face hydraulic support.

[0016] According to one embodiment of the present disclosure, the initial hydraulic support pressure regression prediction model is trained based on the training data set and the verification data set until the training is completed to generate a target hydraulic support pressure regression prediction model, including: inputting the training samples in the training data set into the initial hydraulic support pressure regression prediction model, and adjusting the initial hydraulic support pressure regression prediction model based on the model output result to generate a target training model; verifying the target training model based on the verification data set, and generating the target hydraulic support pressure regression prediction model in response to passing the verification.

[0017] According to one embodiment of the present disclosure, the training samples in the training data set are input into the initial hydraulic support pressure regression prediction model, and the initial hydraulic support pressure regression prediction model is adjusted based on the model output result to generate a target training model, including: calculating the training loss value based on the model output result and the column pressure data of the training sample; adjusting the model parameters of the initial hydraulic support pressure regression prediction model based on the training loss value; repeating the above steps until the training loss value meets the requirement of being less than the loss threshold, thereby generating the target training model.

[0018] According to one embodiment of the present disclosure, the target training model is verified based on the verification data set, and in response to the verification being passed, the target hydraulic support pressure regression prediction model is generated, including: inputting the verification sample in the verification data set into the target training model; determining the model accuracy based on the output result of the target training model and the verification sample column pressure data; in response to the model accuracy being greater than a preset accuracy threshold, determining that the verification is passed, and generating the target hydraulic support pressure regression prediction model.

[0019] According to one embodiment of the present disclosure, the method further includes: in response to the model accuracy being less than or equal to the preset accuracy threshold, determining that the verification fails, inputting the training samples in the training data set into the target training model, and adjusting the target training model based on the model output results to generate an updated target training model, verifying the updated target training model based on the verification data set, and obtaining the model accuracy of the updated target training model; repeating the above steps until the verification passes, and generating the target hydraulic support pressure regression prediction model.

[0020] To achieve the above-mentioned purpose, the second embodiment of the present disclosure proposes a multi-hydraulic support load prediction method, including: obtaining the top beam pitch angle data, top beam roll angle data, coal mining machine cutting position data and coal mining machine traction speed data to be predicted of the target comprehensive mining working face hydraulic support, and obtaining a target hydraulic support pressure regression prediction model, wherein the target hydraulic support pressure regression prediction model is trained by the multi-hydraulic support load model training method shown in the first embodiment; the top beam pitch angle data, the top beam roll angle data, the coal mining machine cutting position data and the coal mining machine traction speed data are input into the target hydraulic support pressure regression prediction model to obtain the predicted support pressure of the target comprehensive mining working face hydraulic support.

[0021] According to one embodiment of the present disclosure, before obtaining the target hydraulic support pressure regression prediction model, it also includes: obtaining the establishment time of the target hydraulic support pressure regression prediction model; in response to the establishment time being greater than a preset time threshold, retraining to obtain a new target hydraulic support pressure regression prediction model through the multi-hydraulic support load model training method shown in the first aspect embodiment.

[0022] To achieve the above-mentioned purpose, the third aspect embodiment of the present disclosure proposes a multi-hydraulic support load model training device, including: an acquisition module, used to obtain the column pressure data, top beam pitch angle data, top beam roll angle data, coal mining machine cutting position data and coal mining machine traction speed data of the target comprehensive mining working face hydraulic support, and obtain the initial hydraulic support pressure regression prediction model to be trained; a generation module, used to pre-process the column pressure data, the top beam pitch angle data, the top beam roll angle data, the coal mining machine cutting position data and the coal mining machine traction speed data to generate a hydraulic support pressure regression prediction model data set; a division module, used to generate a training data set and a verification data set based on the hydraulic support pressure regression prediction model data set; a training module, used to train the initial hydraulic support pressure regression prediction model based on the training data set and the verification data set until the training is completed, and generate the target hydraulic support pressure regression prediction model of the target comprehensive mining working face hydraulic support.

[0023] According to one embodiment of the present disclosure, the training module is also used to: input the training samples in the training data set into the initial hydraulic support pressure regression prediction model, and adjust the initial hydraulic support pressure regression prediction model based on the model output results to generate a target training model; verify the target training model based on the verification data set, and generate the target hydraulic support pressure regression prediction model in response to passing the verification.

[0024] According to one embodiment of the present disclosure, the training module is also used to: calculate the training loss value based on the model output result and the column pressure data of the training sample; adjust the model parameters of the initial hydraulic support pressure regression prediction model based on the training loss value; repeat the above steps until the training loss value meets the loss threshold, thereby generating the target training model.

[0025] According to one embodiment of the present disclosure, the training module is also used to: input the verification samples in the verification data set into the target training model; determine the model accuracy based on the output results of the target training model and the column pressure data of the verification samples; in response to the model accuracy being greater than a preset accuracy threshold, determine that the verification is passed, and generate the target hydraulic support pressure regression prediction model.

[0026] According to one embodiment of the present disclosure, the training module is also used to: in response to the model accuracy being less than or equal to the preset accuracy threshold, determine that the verification fails, input the training samples in the training data set into the target training model, and adjust the target training model based on the model output results to generate an updated target training model, verify the updated target training model based on the verification data set, and obtain the model accuracy of the updated target training model; repeat the above steps until the verification passes, and generate the target hydraulic support pressure regression prediction model.

[0027] To achieve the above-mentioned purpose, the fourth embodiment of the present disclosure proposes a multi-hydraulic support load prediction device, including: a calling module, used to obtain the top beam pitch angle data, top beam roll angle data, coal mining machine cutting position data and coal mining machine traction speed data to be predicted of the target comprehensive mining working face hydraulic support, and obtain the target hydraulic support pressure regression prediction model, wherein the target hydraulic support pressure regression prediction model is trained by the multi-hydraulic support load model training method shown in the first embodiment; a prediction module, used to input the top beam pitch angle data, the top beam roll angle data, the coal mining machine cutting position data and the coal mining machine traction speed data into the target hydraulic support pressure regression prediction model to obtain the predicted support pressure of the target comprehensive mining working face hydraulic support.

[0028] According to one embodiment of the present disclosure, the calling module is also used to: obtain the establishment time of the target hydraulic support pressure regression prediction model; in response to the establishment time being greater than a preset time threshold, retrain and obtain a new target hydraulic support pressure regression prediction model through the multi-hydraulic support load model training method as described in the first aspect embodiment.

[0029] To achieve the above-mentioned purpose, the fifth aspect embodiment of the present disclosure proposes an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to implement the multi-hydraulic support load model training method as described in the first aspect embodiment of the present disclosure, or the multi-hydraulic support load prediction method as described in the second aspect embodiment of the present disclosure.

[0030] To achieve the above-mentioned purpose, the sixth embodiment of the present disclosure proposes a non-transitory computer-readable storage medium on which computer instructions are stored, wherein when the computer instructions are executed by a processor, the multi-hydraulic support load model training method as described in the first embodiment of the present disclosure, or the multi-hydraulic support load prediction method as described in the second embodiment of the present disclosure is implemented.

[0031] To achieve the above-mentioned purpose, the seventh embodiment of the present disclosure proposes a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the multi-hydraulic support load model training method as described in the first embodiment of the present disclosure, or the multi-hydraulic support load prediction method as described in the second embodiment of the present disclosure.

[0032] Therefore, by considering the four dimensions of top beam pitch angle data, top beam roll angle data, coal mining machine cutting position data and coal mining machine traction speed data, a target hydraulic support pressure regression prediction model is established and trained to improve the prediction effect of the support pressure. At the same time, through model prediction, the prediction efficiency can be improved and the prediction cost can be reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] FIG1 is a schematic diagram of a multi-hydraulic support load model training method according to an embodiment of the present disclosure;

[0034] FIG2 is a schematic diagram of another method for predicting loads of multiple hydraulic supports according to an embodiment of the present disclosure;

[0035] FIG3 is a schematic flow chart of a method for predicting loads of multiple hydraulic supports disclosed herein;

[0036] FIG4 is a schematic diagram of a multi-hydraulic support load model training device according to one embodiment of the present disclosure;

[0037] FIG5 is a schematic diagram of a multi-hydraulic support load prediction device according to one embodiment of the present disclosure;

[0038] FIG6 is a schematic diagram of an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0039] The following describes in detail embodiments of the present disclosure, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present disclosure, and should not be construed as limiting the present disclosure.

[0040] The acquisition, storage, use, and processing of data in this disclosed technical solution comply with the relevant provisions of relevant laws and regulations.

[0041] FIG1 is a schematic diagram of a method for training a load model of multiple hydraulic supports according to an embodiment of the present disclosure. As shown in FIG1 , the method for training a load model of multiple hydraulic supports includes the following steps:

[0042] S101, obtaining the column pressure data, top beam pitch angle data, top beam roll angle data, shearer cutting position data and shearer traction speed data of the target fully mechanized mining working face hydraulic support, and obtaining the initial hydraulic support pressure regression prediction model to be trained.

[0043] The multi-hydraulic support load model training method of the embodiment of the present disclosure can be applied to the support pressure prediction scenario of the downhole hydraulic support. The executor of the multi-hydraulic support load model training of the embodiment of the present disclosure can be the multi-hydraulic support load model training device of the embodiment of the present disclosure, and the multi-hydraulic support load model training device can be set on an electronic device.

[0044] In the disclosed embodiment, there are many methods for obtaining the column pressure data, top beam pitch angle data, top beam roll angle data, coal mining machine cutting position data and coal mining machine traction speed data of the target comprehensive mining working face hydraulic support, and no limitation is made here.

[0045] In one possible implementation method, the column pressure data, top beam pitch angle data, top beam roll angle data, coal mining machine cutting position data and coal mining machine traction speed data of the target comprehensive mining working face hydraulic support can be the historical working condition data of the target comprehensive mining working face hydraulic support.

[0046] In one possible implementation, the column pressure data, top beam pitch angle data, top beam roll angle data, coal mining machine cutting position data and coal mining machine traction speed data of the target fully mechanized mining working face hydraulic support can also be manually established.

[0047] In the embodiment of the present disclosure, the initial hydraulic support pressure regression prediction model can be various, which is not limited herein. For example, the initial hydraulic support pressure regression prediction model can be a neural network model, a gray prediction model, etc.

[0048] In one possible implementation, the initial hydraulic support pressure regression prediction model is a deep neural network whose input is top beam pitch angle data, top beam roll angle data, coal mining machine cutting position data and coal mining machine traction speed data, and whose output is column pressure data, wherein the weight parameters in the network are randomly generated.

[0049] In one possible implementation, data can be collected according to a preset collection cycle, which can be changed according to actual design needs and is not limited here. In one possible implementation, if the data collection cycle is 1 minute, the data volume of the column pressure data of multiple hydraulic supports, the top beam pitch angle data of multiple hydraulic supports, the top beam roll angle data of multiple hydraulic supports, the coal shearer cutting position data, and the coal shearer traction speed data should be at least 5760 pieces each. If the data collection cycle is 5 minutes, the data volume of the column pressure data of multiple hydraulic supports, the top beam pitch angle data of multiple hydraulic supports, the top beam roll angle data of multiple hydraulic supports, the coal shearer cutting position data, and the coal shearer traction speed data should be at least 1152 pieces each.

[0050] It should be noted that the hydraulic support pressure regression prediction model disclosed herein can be a multi-input single-output model or a multi-input multiple-output model, and the specific limitation can be determined based on actual design requirements. Multi-input single-output refers to the input being a specified number of sets of top beam pitch angles, top beam roll angles, shearer cutting positions, and shearer traction speeds for a single support, and the output being a set of pressures for a single support; multi-input multiple-output refers to the input being a specified number of sets of top beam pitch angles, top beam roll angles, shearer cutting positions, and shearer traction speeds for multiple supports, and the output being a set of pressures for multiple supports.

[0051] S102 , pre-processing the column pressure data, top beam pitch angle data, top beam roll angle data, shearer cutting position data, and shearer traction speed data to generate a hydraulic support pressure regression prediction model data set.

[0052] It should be noted that the hydraulic support pressure regression prediction model data set includes multiple data samples, and each data sample is divided according to the timestamp. That is, the column pressure data, top beam pitch angle data, top beam roll angle data, coal mining machine cutting position data and coal mining machine traction speed data of the same timestamp can be used to generate a data sample.

[0053] In the disclosed embodiments, various preprocessing methods are possible, without limitation. For example, preprocessing can include one or more of data screening, data completion, and format normalization. Preprocessing column pressure data, top beam pitch angle data, top beam roll angle data, shearer cutting position data, and shearer traction speed data can improve the efficiency and accuracy of subsequent data processing, thereby enhancing the effectiveness of the final model training.

[0054] S103, generating a training data set and a validation data set based on the hydraulic support pressure regression prediction model data set.

[0055] After obtaining the hydraulic support pressure regression prediction model data set, the hydraulic support pressure regression prediction model data set can be divided into a training data set and a validation data set according to a certain ratio. The ratio can be set in advance and can be changed according to actual design needs. No limitation is made here.

[0056] In one possible implementation, the ratio of the training dataset to the validation dataset can be 6:1, ensuring that the training dataset accounts for more than 70% of the entire dataset.

[0057] S104: Training the initial hydraulic support pressure regression prediction model based on the training data set and the validation data set until the training is completed, thereby generating a target hydraulic support pressure regression prediction model for the target fully mechanized mining working face hydraulic support.

[0058] It should be noted that the target hydraulic support pressure regression prediction model in the present disclosure is a model that predicts the target hydraulic support pressure of the future target comprehensive mining working face hydraulic support through the working condition data of the current target comprehensive mining working face hydraulic support. The predicted future time period or future moment is not limited here, and can be specifically limited according to actual design needs.

[0059] It is understood that model training is an iterative process, which involves continuously adjusting the model's network parameters until the overall model loss function value is less than a preset value, or the overall model loss function value no longer changes or changes slowly, the model converges, and a trained model is obtained, or the preset number of training times is reached. After obtaining the trained model, the trained model can be verified using a validation dataset to ultimately generate a target hydraulic support pressure regression prediction model.

[0060] In the embodiment disclosed herein, first, the column pressure data, top beam pitch angle data, top beam roll angle data, coal mining machine cutting position data and coal mining machine traction speed data of the target fully-mechanized mining working face hydraulic support are obtained, and the initial hydraulic support pressure regression prediction model to be trained is obtained, and then the column pressure data, top beam pitch angle data, top beam roll angle data, coal mining machine cutting position data and coal mining machine traction speed data are preprocessed to generate a hydraulic support pressure regression prediction model data set, and then a training data set and a verification data set are generated based on the hydraulic support pressure regression prediction model data set, and finally, the initial hydraulic support pressure regression prediction model is trained based on the training data set and the verification data set until the training is completed, and a target hydraulic support pressure regression prediction model of the target fully-mechanized mining working face hydraulic support is generated. Thus, by considering the four dimensions of top beam pitch angle data, top beam roll angle data, coal mining machine cutting position data and coal mining machine traction speed data to establish and train the target hydraulic support pressure regression prediction model, the prediction effect of the support pressure can be improved, and at the same time, the prediction efficiency can be improved and the prediction cost can be reduced through model prediction.

[0061] In the above embodiment, the initial hydraulic support pressure regression prediction model is trained based on the training data set and the validation data set until the training is completed to generate a target hydraulic support pressure regression prediction model. This can be further explained by FIG2 , which is a schematic diagram of another method for predicting the load of multiple hydraulic supports according to one embodiment of the present disclosure. The method includes:

[0062] S201: Input the training samples in the training data set into the initial hydraulic support pressure regression prediction model, and adjust the initial hydraulic support pressure regression prediction model based on the model output result to generate a target training model.

[0063] In the embodiment of the present disclosure, the training loss value can be first calculated based on the model output results and the column pressure data of the training sample, and then the model parameters of the initial hydraulic support pressure regression prediction model can be adjusted based on the training loss value. Finally, the above steps are repeated until the training loss value meets the loss threshold and generates the target training model.

[0064] It should be noted that the loss function in the present disclosure can be multiple, and no limitation is made here. The specific limitation can be made according to actual design needs.

[0065] The loss threshold is the maximum loss value at which the current initial hydraulic support pressure regression prediction model is considered to have completed training. The loss threshold is set in advance and can be changed according to actual design needs.

[0066] S202 , verifying the target training model based on the verification data set, and generating a target hydraulic support pressure regression prediction model in response to passing the verification.

[0067] In the embodiment of the present disclosure, after obtaining the target training model, the verification samples in the verification data set can be first input into the target training model, and then the model accuracy is determined based on the output results of the target training model and the verification sample column pressure data. Finally, in response to the model accuracy being greater than the preset accuracy threshold, it is determined that the verification is passed and the target hydraulic support pressure regression prediction model is generated.

[0068] The precision value is a value that describes the difference between the output of the current target training model and the actual result. The greater the precision, the smaller the difference between the output of the current target training model and the actual result.

[0069] It should be noted that the preset accuracy threshold is the minimum accuracy value for the current target training model to be considered verified. It is set in advance and can be changed according to actual design needs. No limitation is given here. In one possible implementation, the preset accuracy threshold can be 90%.

[0070] In the disclosed embodiment, training samples from a training dataset are first input into an initial hydraulic support pressure regression prediction model. Based on the model output, the initial hydraulic support pressure regression prediction model is adjusted to generate a target training model. The target training model is then validated based on a validation dataset. Upon successful validation, a target hydraulic support pressure regression prediction model is generated. By setting a loss threshold and an accuracy threshold, the accuracy of the resulting target hydraulic support pressure regression prediction model can be controlled, thereby increasing the practicality of the disclosed target hydraulic support pressure regression prediction model in different scenarios.

[0071] In the disclosed embodiment of the present work, in response to the model accuracy being less than or equal to the preset accuracy threshold, it is determined that the verification has failed, the training samples in the training data set are input into the target training model, and the target training model is adjusted based on the model output results to generate an updated target training model, the updated target training model is verified based on the verification data set, and the model accuracy of the updated target training model is obtained, and the above steps are repeated until the verification passes, thereby generating a target hydraulic support pressure regression prediction model.

[0072] FIG3 is a flow chart of a method for predicting loads of multiple hydraulic supports disclosed herein, the method comprising:

[0073] S301, obtaining the top beam pitch angle data, top beam roll angle data, shearer cutting position data and shearer traction speed data of the target fully mechanized mining working face hydraulic support to be predicted, and obtaining the target hydraulic support pressure regression prediction model.

[0074] It should be noted that the target hydraulic support pressure regression prediction model in the embodiment of the present disclosure is obtained by training using the multi-hydraulic support load model training method shown in FIG1 and FIG2 .

[0075] The top beam pitch angle data, top beam roll angle data, coal mining machine cutting position data and coal mining machine traction speed data to be predicted for the target comprehensive mining working face hydraulic support in the present disclosure can be the current working condition data of the target comprehensive mining working face hydraulic support, or can be manually input, and no limitation is made here.

[0076] S302, input the top beam pitch angle data, top beam roll angle data, shearer cutting position data and shearer traction speed data into the target hydraulic support pressure regression prediction model to obtain the predicted support pressure of the target fully mechanized mining working face hydraulic support.

[0077] In the disclosed embodiment, first, the top beam pitch angle data, top beam roll angle data, coal mining machine cutting position data and coal mining machine traction speed data of the target fully-mechanized mining working face hydraulic support to be predicted are obtained, and the target hydraulic support pressure regression prediction model is obtained. Then, the top beam pitch angle data, top beam roll angle data, coal mining machine cutting position data and coal mining machine traction speed data are input into the target hydraulic support pressure regression prediction model to obtain the predicted support pressure of the target fully-mechanized mining working face hydraulic support. Thus, by considering the four dimensions of top beam pitch angle data, top beam roll angle data, coal mining machine cutting position data and coal mining machine traction speed data to establish and train the target hydraulic support pressure regression prediction model, the prediction effect of the support pressure can be improved. At the same time, through the model prediction method, the prediction efficiency can be improved and the prediction cost can be reduced.

[0078] It should be noted that since downhole operations are a continuous operation, in the face of this dynamically changing downhole situation, the target hydraulic support pressure regression prediction model cannot continuously support this dynamic downhole working condition, so it needs to be updated according to actual conditions.

[0079] In an embodiment of the present disclosure, before obtaining the target hydraulic support pressure regression prediction model, the establishment time of the target hydraulic support pressure regression prediction model can be first obtained. In response to the establishment time being greater than a preset time threshold, a new target hydraulic support pressure regression prediction model is obtained by retraining through the multi-hydraulic support load model training method shown in Figures 1 and 2.

[0080] In this way, it can be ensured that the current prediction model conforms to the actual working conditions of the hydraulic support of the current target comprehensive mining working face, thereby improving the accuracy of the prediction.

[0081] Corresponding to the multi-hydraulic support load model training method provided in the above-mentioned embodiments, an embodiment of the present disclosure also provides a multi-hydraulic support load model training device. Since the multi-hydraulic support load model training device provided in the embodiment of the present disclosure corresponds to the multi-hydraulic support load model training method provided in the above-mentioned embodiments, the implementation method of the above-mentioned multi-hydraulic support load model training method is also applicable to the multi-hydraulic support load model training device provided in the embodiment of the present disclosure, and will not be described in detail in the following embodiments.

[0082] Figure 4 is a schematic diagram of a multi-hydraulic support load model training device according to an embodiment of the present disclosure. As shown in Figure 4 , the multi-hydraulic support load model training device 400 includes: an acquisition module 410, a generation module 420, a division module 430 and a training module 440.

[0083] The acquisition module 410 is used to obtain the column pressure data, top beam pitch angle data, top beam roll angle data, shearer cutting position data and shearer traction speed data of the target fully mechanized mining face hydraulic support, and obtain the initial hydraulic support pressure regression prediction model to be trained;

[0084] A generation module 420 is used to pre-process the column pressure data, the top beam pitch angle data, the top beam roll angle data, the shearer cutting position data, and the shearer traction speed data to generate a hydraulic support pressure regression prediction model data set;

[0085] A partitioning module 430 is configured to generate a training data set and a validation data set based on the hydraulic support pressure regression prediction model data set;

[0086] The training module 440 is used to train the initial hydraulic support pressure regression prediction model based on the training data set and the verification data set until the training is completed, and generate a target hydraulic support pressure regression prediction model for the target fully mechanized mining working face hydraulic support.

[0087] In one embodiment of the present disclosure, the training module 440 is also used to: input the training samples in the training data set into the initial hydraulic support pressure regression prediction model, and adjust the initial hydraulic support pressure regression prediction model based on the model output results to generate a target training model; verify the target training model based on the verification data set, and generate a target hydraulic support pressure regression prediction model in response to passing the verification.

[0088] In one embodiment of the present disclosure, the training module 440 is further used to: calculate a training loss value based on the model output results and the column pressure data of the training sample; adjust the model parameters of the initial hydraulic support pressure regression prediction model based on the training loss value; repeat the above steps until the training loss value satisfies a loss threshold value to generate a target training model.

[0089] In one embodiment of the present disclosure, the training module 440 is further used to: input the verification samples in the verification data set into the target training model; determine the model accuracy based on the output results of the target training model and the verification sample column pressure data; in response to the model accuracy being greater than a preset accuracy threshold, determine that the verification is passed, and generate a target hydraulic support pressure regression prediction model.

[0090] In one embodiment of the present disclosure, the training module 440 is further used to: in response to the model accuracy being less than or equal to the preset accuracy threshold, determine that the verification fails, input the training samples in the training data set into the target training model, and adjust the target training model based on the model output results to generate an updated target training model, verify the updated target training model based on the verification data set, and obtain the model accuracy of the updated target training model; repeat the above steps until the verification passes, and generate the target hydraulic support pressure regression prediction model.

[0091] By considering the four dimensions of top beam pitch angle data, top beam roll angle data, coal mining machine cutting position data and coal mining machine traction speed data, a target hydraulic support pressure regression prediction model is established and trained to improve the prediction effect of the support pressure. At the same time, through model prediction, the prediction efficiency can be improved and the prediction cost can be reduced.

[0092] Corresponding to the multi-hydraulic support load prediction method provided in the above-mentioned embodiments, an embodiment of the present disclosure also provides a multi-hydraulic support load prediction device. Since the multi-hydraulic support load prediction device provided in the embodiment of the present disclosure corresponds to the multi-hydraulic support load prediction method provided in the above-mentioned embodiments, the implementation method of the above-mentioned multi-hydraulic support load prediction method is also applicable to the multi-hydraulic support load prediction device provided in the embodiment of the present disclosure, and will not be described in detail in the following embodiments.

[0093] FIG5 is a schematic diagram of a multi-hydraulic support load prediction device according to an embodiment of the present disclosure. As shown in FIG5 , the multi-hydraulic support load prediction device 500 includes a calling module 510 and a prediction module 520 .

[0094] Among them, calling module 510 is used to obtain the top beam pitch angle data, top beam roll angle data, coal mining machine cutting position data and coal mining machine traction speed data to be predicted of the target fully mechanized mining working face hydraulic support, and obtain the target hydraulic support pressure regression prediction model.

[0095] The prediction module 520 is used to input the top beam pitch angle data, top beam roll angle data, coal mining machine cutting position data and coal mining machine traction speed data into the target hydraulic support pressure regression prediction model to obtain the predicted support pressure of the target fully mechanized mining working face hydraulic support.

[0096] In one embodiment of the present disclosure, the calling module 510 is also used to: obtain the establishment time of the target hydraulic support pressure regression prediction model; in response to the establishment time being greater than a preset time threshold, retrain and obtain a new target hydraulic support pressure regression prediction model through a multi-hydraulic support load model training method.

[0097] By considering the four dimensions of top beam pitch angle data, top beam roll angle data, coal mining machine cutting position data and coal mining machine traction speed data, a target hydraulic support pressure regression prediction model is established and trained to improve the prediction effect of the support pressure. At the same time, through model prediction, the prediction efficiency can be improved and the prediction cost can be reduced.

[0098] In order to implement the above-mentioned embodiments, the embodiments of the present disclosure also propose an electronic device 600. Figure 6 is a schematic diagram of an electronic device of an embodiment of the present disclosure. As shown in Figure 6, the electronic device 600 includes: a processor 602 and a memory 601 communicatively connected to the processor, the memory 601 stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor 602 to implement the multi-hydraulic support load model training method of the embodiments of Figures 1-2 of the present disclosure, or the multi-hydraulic support load prediction method of the embodiment of Figure 3.

[0099] In order to implement the above embodiments, the embodiments of the present disclosure also propose a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable the computer to implement the multi-hydraulic support load model training method as shown in the embodiments of Figures 1-2 of the present disclosure, or the multi-hydraulic support load prediction method as shown in the embodiment of Figure 3.

[0100] In order to implement the above embodiments, the embodiments of the present disclosure also propose a computer program product, including a computer program, which, when executed by a processor, implements the multi-hydraulic support load model training method of the embodiments of Figures 1-2 of the present disclosure, or the multi-hydraulic support load prediction method of the embodiment of Figure 3.

[0101] It is important to note that personal information collected from users should be used for legitimate and reasonable purposes and should not be shared or sold beyond these legitimate uses. Furthermore, such collection / sharing should be conducted only after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign an agreement / authorization that includes the relevant user information before using the feature. Furthermore, any necessary steps must be taken to safeguard and secure access to such personal information and ensure that others with access to personal information comply with its privacy policy and procedures.

[0102] This disclosure contemplates providing implementations that allow users to selectively block the use or access of personal information data. Specifically, this disclosure contemplates providing hardware and / or software to prevent or block access to such personal information data. Risks can be minimized by limiting data collection and deleting data once it is no longer needed. Furthermore, where applicable, such personal information can be de-identified to protect user privacy.

[0103] In the descriptions of the aforementioned embodiments, the reference terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" mean that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present disclosure. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are mutually inconsistent.

[0104] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. Throughout the present disclosure, "plurality" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0105] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present disclosure includes additional implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present disclosure belong.

[0106] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and a portable compact disc read-only memory (CDROM). Furthermore, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing it in another suitable manner if necessary, and then storing it in a computer memory.

[0107] It should be understood that various parts of the present disclosure can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0108] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0109] In addition, the functional units in the various embodiments of the present disclosure may be integrated into a single processing module, or each unit may exist physically separately, or two or more units may be integrated into a single module. The aforementioned integrated modules may be implemented in the form of hardware or in the form of software functional modules. If the integrated modules are implemented in the form of software functional modules and sold or used as independent products, they may also be stored in a computer-readable storage medium.

[0110] The storage medium mentioned above may be a read-only memory, a magnetic disk, or an optical disk, etc. Although the embodiments of the present disclosure have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present disclosure. A person of ordinary skill in the art may make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present disclosure.

Claims

1. A method for training a multi-hydraulic support load model, wherein, Including: Obtain the column pressure data, roof beam pitch angle data, roof beam roll angle data, shearer cutting position data, and shearer traction speed data of the hydraulic supports in the target fully-mechanized coal mining face, and obtain the initial hydraulic support pressure regression prediction model to be trained; Preprocess the column pressure data, roof beam pitch angle data, roof beam roll angle data, shearer cutting position data, and shearer traction speed data to generate a hydraulic support pressure regression prediction model dataset; Generate a training dataset and a validation dataset based on the hydraulic support pressure regression prediction model dataset; Train the initial hydraulic support pressure regression prediction model based on the training dataset and the validation dataset until the training is completed, and generate the target hydraulic support pressure regression prediction model for the hydraulic supports in the target fully-mechanized coal mining face.

2. The method according to claim 1, wherein The training of the initial hydraulic support pressure regression prediction model based on the training dataset and the validation dataset until the training is completed to generate the target hydraulic support pressure regression prediction model for the hydraulic supports in the target fully-mechanized coal mining face includes: Input the training samples in the training dataset into the initial hydraulic support pressure regression prediction model, and adjust the initial hydraulic support pressure regression prediction model based on the model output results to generate a target training model; Validate the target training model based on the validation dataset, and in response to passing the validation, generate the target hydraulic support pressure regression prediction model.

3. The method according to claim 2, wherein The inputting the training samples in the training dataset into the initial hydraulic support pressure regression prediction model and adjusting the initial hydraulic support pressure regression prediction model based on the model output results to generate a target training model includes: Calculate the training loss value based on the model output results and the column pressure data of the training samples; Adjust the model parameters of the initial hydraulic support pressure regression prediction model based on the training loss value; Repeat the above steps until the training loss value meets the condition of being less than the loss threshold to generate the target training model.

4. The method according to claim 2, wherein, The validating the target training model based on the validation dataset and in response to passing the validation to generate the target hydraulic support pressure regression prediction model includes: Input the validation samples in the validation dataset into the target training model; Determine the model accuracy based on the output results of the target training model and the column pressure data of the validation samples; In response to the model accuracy being greater than the preset accuracy threshold, determine that the validation is passed and generate the target hydraulic support pressure regression prediction model.

5. The method according to claim 4, wherein The method further includes: In response to the model accuracy being less than or equal to the preset accuracy threshold, determine that the validation fails, input the training samples in the training dataset into the target training model, and adjust the target training model based on the model output results to generate an updated target training model, validate the updated target training model based on the validation dataset, and obtain the model accuracy of the updated target training model. Repeat the above steps until the verification is passed to generate the target hydraulic support pressure regression prediction model.

6. A method for predicting the loads of multiple hydraulic supports, wherein, It includes: Obtain the data of the top beam pitch angle, the top beam roll angle, the cutting position data of the shearer, and the traction speed data of the shearer of the hydraulic support to be predicted in the target fully-mechanized mining face, and obtain the target hydraulic support pressure regression prediction model, where the target hydraulic support pressure regression prediction model is trained by the multi-hydraulic support load model training method described in any one of claims 1 to 5; Input the data of the top beam pitch angle, the top beam roll angle, the cutting position data of the shearer, and the traction speed data of the shearer into the target hydraulic support pressure regression prediction model to obtain the predicted support pressure of the hydraulic support in the target fully-mechanized mining face.

7. The method according to claim 6, wherein Before obtaining the target hydraulic support pressure regression prediction model, it further includes: Obtain the establishment time of the target hydraulic support pressure regression prediction model; In response to the establishment time being greater than the preset time threshold, retrain through the multi-hydraulic support load model training method described in any one of claims 1 to 5 to obtain a new target hydraulic support pressure regression prediction model.

8. A training device for a multi-hydraulic support load model, wherein, It includes: An acquisition module, configured to acquire the column pressure data, the top beam pitch angle data, the top beam roll angle data, the cutting position data of the shearer, and the traction speed data of the hydraulic support in the target fully-mechanized mining face, and acquire the initial hydraulic support pressure regression prediction model to be trained; A generation module, configured to preprocess the column pressure data, the top beam pitch angle data, the top beam roll angle data, the cutting position data of the shearer, and the traction speed data to generate a hydraulic support pressure regression prediction model data set; A division module, configured to generate a training data set and a verification data set based on the hydraulic support pressure regression prediction model data set; A training module, configured to train the initial hydraulic support pressure regression prediction model based on the training data set and the verification data set until the training is completed to generate the target hydraulic support pressure regression prediction model of the hydraulic support in the target fully-mechanized mining face.

9. The device according to claim 8, wherein The training module is further configured to: Input the training samples in the training data set into the initial hydraulic support pressure regression prediction model, and adjust the initial hydraulic support pressure regression prediction model based on the model output result to generate a target training model; Verify the target training model based on the verification data set, and in response to the verification being passed, generate the target hydraulic support pressure regression prediction model.

10. The apparatus according to claim 9, wherein, The training module is further configured to: Calculate a training loss value based on the model output result and the column pressure data of the training sample; Adjust the model parameters of the initial hydraulic support pressure regression prediction model based on the training loss value; Repeat the above steps until the training loss value satisfies being less than the loss threshold to generate the target training model.

11. The device according to claim 9, wherein, The training module is further configured to: Input the verification samples in the verification data set into the target training model; Determine the model accuracy based on the output result of the target training model and the column pressure data of the verification sample. In response to the model accuracy being greater than a preset accuracy threshold, it is determined that the verification is passed, and the target hydraulic support pressure regression prediction model is generated.

12. The apparatus according to claim 11, wherein, The training module is further configured to: In response to the model accuracy being less than or equal to the preset accuracy threshold, it is determined that the verification fails, the training samples in the training data set are input into the target training model, and the target training model is adjusted based on the model output result to generate an updated target training model. The updated target training model is verified based on the verification data set, and the model accuracy of the updated target training model is obtained; Repeat the above steps until the verification is passed, and the target hydraulic support pressure regression prediction model is generated.

13. A multi-hydraulic support load prediction device, wherein, It includes: A calling module, configured to obtain the data of the top beam pitch angle, the top beam roll angle, the cutting position data of the shearer, and the traction speed data of the shearer to be predicted for the hydraulic supports in the target fully-mechanized coal mining face, and obtain the target hydraulic support pressure regression prediction model, where the target hydraulic support pressure regression prediction model is trained by the multi-hydraulic support load model training method according to any one of claims 1 to 5; A prediction module, configured to input the data of the top beam pitch angle, the top beam roll angle, the cutting position data of the shearer, and the traction speed data of the shearer into the target hydraulic support pressure regression prediction model to obtain the predicted support pressure of the hydraulic supports in the target fully-mechanized coal mining face.

14. The apparatus according to claim 13, wherein, The calling module is further configured to: Obtain the establishment time of the target hydraulic support pressure regression prediction model; In response to the establishment time being greater than a preset time threshold, retrain through the multi-hydraulic support load model training method according to any one of claims 1 to 5 to obtain a new target hydraulic support pressure regression prediction model.

15. An electronic device, wherein, It includes a memory and a processor; Wherein, the processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to be used to implement the multi-hydraulic support load model training method according to any one of claims 1 to 5, or the multi-hydraulic support load prediction method according to claim 6 or 7.

16. A non-transitory computer-readable storage medium having computer instructions stored thereon, wherein, When the computer instruction is executed by the processor, it implements the multi-hydraulic support load model training method according to any one of claims 1 to 5, or the multi-hydraulic support load prediction method according to claim 6 or 7.

17. A computer program product, wherein, It includes a computer program, and when the computer program is executed by the processor, it implements the multi-hydraulic support load model training method according to any one of claims 1 to 5, or the multi-hydraulic support load prediction method according to claim 6 or 7.

Images