CN116777085A - Coal mine water damage prediction system based on data analysis and machine learning technology - Google Patents
Coal mine water damage prediction system based on data analysis and machine learning technology Download PDFInfo
- Publication number
- CN116777085A CN116777085A CN202311061091.5A CN202311061091A CN116777085A CN 116777085 A CN116777085 A CN 116777085A CN 202311061091 A CN202311061091 A CN 202311061091A CN 116777085 A CN116777085 A CN 116777085A
- Authority
- CN
- China
- Prior art keywords
- data
- coal mine
- mine water
- unit
- water damage
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 239000003245 coal Substances 0.000 title claims abstract description 287
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 251
- 238000005516 engineering process Methods 0.000 title claims abstract description 29
- 238000007405 data analysis Methods 0.000 title claims abstract description 21
- 238000010801 machine learning Methods 0.000 title claims abstract description 21
- 238000007726 management method Methods 0.000 claims abstract description 57
- 238000011156 evaluation Methods 0.000 claims abstract description 39
- 238000012549 training Methods 0.000 claims abstract description 36
- 238000012545 processing Methods 0.000 claims abstract description 35
- 238000007781 pre-processing Methods 0.000 claims abstract description 26
- 238000000034 method Methods 0.000 claims abstract description 13
- 238000012544 monitoring process Methods 0.000 claims description 71
- 238000012216 screening Methods 0.000 claims description 45
- 238000012360 testing method Methods 0.000 claims description 38
- 230000008859 change Effects 0.000 claims description 29
- 238000004088 simulation Methods 0.000 claims description 21
- 230000010485 coping Effects 0.000 claims description 18
- 238000010276 construction Methods 0.000 claims description 17
- 238000011161 development Methods 0.000 claims description 17
- 230000007613 environmental effect Effects 0.000 claims description 17
- 238000013528 artificial neural network Methods 0.000 claims description 16
- 238000004140 cleaning Methods 0.000 claims description 12
- 238000010606 normalization Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000013524 data verification Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 238000007667 floating Methods 0.000 claims description 4
- 238000012847 principal component analysis method Methods 0.000 claims description 4
- 230000004044 response Effects 0.000 claims description 4
- 238000004519 manufacturing process Methods 0.000 abstract description 10
- 230000009286 beneficial effect Effects 0.000 description 11
- 230000003993 interaction Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000005553 drilling Methods 0.000 description 1
- 230000008595 infiltration Effects 0.000 description 1
- 238000001764 infiltration Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a coal mine water damage prediction system based on data analysis and machine learning technology, which comprises the following steps: the data acquisition module is used for acquiring the historical accident data of the coal mine water disaster and the historical environment data of the coal mine and acquiring first data; the data processing module is used for preprocessing the first data to obtain preprocessed data; the prediction model training evaluation module is used for training and evaluating a preset coal mine water damage prediction model based on the preprocessing data to obtain a first coal mine water damage prediction model; and the prediction implementation module is used for predicting the coal mine water damage based on the first coal mine water damage prediction model. The method can improve the accuracy of coal mine water damage prediction, reduce false alarm and missing alarm, improve the reliability of prediction results, avoid accidents or reduce the influence of the accidents on mine production, help mine management staff to cope with water damage risks, reduce loss and ensure production safety.
Description
Technical Field
The invention relates to the technical field of coal mine water damage prediction, in particular to a coal mine water damage prediction system based on data analysis and machine learning technology.
Background
The coal mine water damage refers to the flood condition caused by the infiltration and accumulation of underground water in the coal mining process, and the water damage can cause serious consequences such as equipment damage, casualties of workers, production interruption and the like in a mine; the traditional water damage prediction has some limitations and disadvantages in terms of nonlinear relation processing, subjectivity, data processing, real-time performance, multi-factor interaction and the like, and the problems limit the accuracy and reliability in terms of coal mine water damage prediction, and the main problems are as follows:
firstly, the nonlinear relation is difficult to process: conventional water damage prediction systems are generally based on statistical methods or empirical rules, and it is difficult to accurately model complex nonlinear relationships, which results in limited prediction capabilities of conventional models in the face of actual complex coal mine environments and water damage factors;
secondly, depending on human factors and experience rules: some traditional models rely on expert knowledge and empirical rules for modeling and prediction, and such subjectivity and artificial interference may lead to deviation and inaccuracy of the model, and also increase subjectivity and irreproducibility of the model;
thirdly, data processing and feature selection are difficult: the traditional model has certain difficulty in data processing and feature selection, and the traditional method can not effectively process a large amount of complex data or can not extract key feature information from the complex data, so that the performance of the model is reduced;
fourth, lack of real-time and dynamic properties: traditional models tend to model and predict based on historical data and static assumptions. However, coal mine environments and water damage factors may change with time, real-time monitoring and dynamic prediction are required, and the conventional model cannot meet the requirements of real-time performance and dynamic performance;
fifth, multi-factor interaction and complex systems cannot be handled: the coal mine water damage involves complex interactions between multiple factors, which are often difficult for conventional models to fully account for, and simplified assumptions and model structures of conventional methods may not accurately capture the complex behavior of the multi-factor interactions and systems.
Patent document with application number of CN202111022028.1 discloses a system, a method and an application for preventing and controlling water in a coal mine well, comprising the following steps: the advanced exploration and stope face water damage prediction system detects the water containing structure and water guiding condition of the coal mine and determines the stope face water damage prevention and control technical measures; the underground water dynamic monitoring system is used for collecting and analyzing underground water phase data by using the mining area hydrologic dynamic monitoring system; the rapid distinguishing system for the mine water source adopts geophysical prospecting, drilling and chemical prospecting methods to conduct chemical examination and analysis based on the current mine data, determines the background characteristics of mine water chemistry, establishes a mine water chemistry database, establishes distinguishing models of water quality of different aquifers in a well field, and rapidly distinguishes various water-gushing sources. The scheme can timely predict and early warn the water burst of the mine, and can take targeted water control measures in a targeted manner, thereby ensuring the safe, economical and reasonable production of the mine and the comprehensive utilization of water resources; however, the scheme needs to utilize a plurality of excavation methods, the operation implementation is complex, the early warning efficiency is low, and the early warning accuracy is difficult to be effectively ensured.
Accordingly, there is a need for a coal mine water damage prediction system based on data analysis and machine learning techniques.
Disclosure of Invention
The invention provides a coal mine water damage prediction system based on data analysis and machine learning technology, which can improve the accuracy of coal mine water damage prediction, reduce false alarm and missing alarm, improve the reliability of prediction results, avoid accidents or reduce the influence of accidents on mine production, help mine management staff and staff to effectively influence water damage risks, reduce loss and ensure production safety.
The invention provides a coal mine water damage prediction system based on data analysis and machine learning technology, which comprises the following steps:
the data acquisition module is used for acquiring the historical accident data of the coal mine water disaster and the historical environment data of the coal mine and acquiring first data;
the data processing module is used for preprocessing the first data to obtain preprocessed data;
the prediction model training evaluation module is used for training and evaluating a preset coal mine water damage prediction model based on the preprocessing data to obtain a first coal mine water damage prediction model;
and the prediction implementation module is used for predicting the coal mine water damage based on the first coal mine water damage prediction model.
Further, the data acquisition module comprises a data acquisition setting unit and a data acquisition implementation unit;
the data acquisition setting unit is used for setting data acquisition conditions according to the predicted demand of the coal mine water damage; the data acquisition conditions comprise one or more of an acquisition period, an acquisition point position, a data index, an acquisition amount and an acquisition mode;
the data acquisition implementation unit is used for acquiring the historical accident data of the coal mine water disaster and the historical environmental data of the coal mine according to the data acquisition conditions based on the large data platform of the coal mine water disaster information to obtain first data.
Further, the data acquisition implementation unit also comprises a data screening subunit, wherein the data screening subunit comprises a coal mine water hazard historical accident data screening subunit, a coal mine historical environment data screening subunit and a screening data summarizing subunit;
the coal mine water disaster historical accident data screening molecular unit is used for acquiring accident grades in the coal mine water disaster historical accident data, screening typical accident data corresponding to a plurality of accident grades according to the accident grades, and acquiring first coal mine water disaster historical accident data;
the coal mine historical environment data screening molecular unit is used for acquiring the environmental impact value of the coal mine historical environment data on the coal mine water damage historical accident data according to the coal mine historical environment data, and screening the coal mine historical environment data with the environmental impact value being greater than a preset environmental impact value threshold value as first coal mine historical environment data;
and the screening data summarizing molecular unit is used for summarizing the first coal mine water disaster historical accident data and the first coal mine historical environment data to obtain first data.
Further, the data processing module comprises a data preprocessing unit and a data classifying unit;
the data preprocessing unit is used for cleaning, normalizing and standardizing the data and extracting time sequence characteristics to obtain first preprocessed data; the data cleaning comprises default value cleaning, and the normalization and standardization comprise minimum maximum normalization, zero mean standardization and decimal calibration standardization; the time sequence feature extraction comprises the steps of extracting features by adopting a principal component analysis method;
the data classifying unit is used for classifying the first preprocessing data to obtain a data training set, a data verification set and a data testing set, and generating preprocessing data.
Further, the prediction model training evaluation module comprises a prediction model construction unit, a prediction model training verification unit and a prediction model evaluation unit;
the prediction model construction unit is used for constructing and generating a coal mine water damage prediction model by utilizing the two-way long-short-term memory neural network, and carrying out parameter setting on the coal mine water damage prediction model according to a preset parameter database;
the prediction model training and verifying unit is used for training and verifying the coal mine water damage prediction model by utilizing the data training set and the data verifying set;
the prediction model evaluation unit is used for evaluating the coal mine water damage prediction model by utilizing the data test set to obtain a model evaluation result, and screening to obtain a first coal mine water damage prediction model based on the model evaluation result.
Further, the prediction model construction unit also comprises a coal mine water damage prediction model parameter setting subunit;
the coal mine water damage prediction model parameter setting subunit comprises a single parameter optimal value acquisition subunit, a parameter optimal range acquisition subunit and a parameter database setting subunit;
the single parameter optimal value obtaining molecular unit is used for drawing a change schematic coordinate graph of the layer number and the calculation cost of the two-way long-short-term memory neural network, a change schematic coordinate graph of the hidden unit number and the overfitting probability of the layer of the two-way long-short-term memory neural network, and a change schematic coordinate graph of the learning rate and the convergence rate of the two-way long-short-term memory neural network, and obtaining the optimal layer number, the optimal hidden unit number and the optimal learning rate;
the parameter optimal range obtaining molecular unit is used for setting an optimal layer number range, an optimal hiding unit number range and an optimal learning rate range according to the optimal layer number, the optimal hiding unit number and the optimal learning rate based on a preset floating value;
the parameter database is provided with a molecular unit, is used for setting a plurality of data groups consisting of the layer number, the hidden unit number and the learning rate according to the optimal layer number range, the optimal hidden unit number range and the optimal learning rate range, and generates the parameter database according to the data groups.
Further, the prediction model evaluation unit comprises an evaluation result acquisition subunit and a first coal mine water damage prediction model acquisition subunit;
the evaluation result acquisition subunit is used for evaluating the coal mine water damage prediction model by utilizing the data test set to obtain model prediction accuracy;
the first coal mine water damage prediction model acquisition subunit is used for monitoring and analyzing the model prediction accuracy, and when the prediction accuracy reaches a preset prediction accuracy threshold, the corresponding coal mine water damage prediction model is used as the first coal mine water damage prediction model.
Further, the prediction implementation module comprises a real-time data acquisition unit and a prediction implementation unit;
the real-time data acquisition unit is used for acquiring real-time water quantity data of the coal mine and real-time coal mine environment data;
the prediction implementation unit is used for predicting the coal mine water damage according to the real-time water quantity data of the coal mine and the real-time coal mine environment data by using the first coal mine water damage prediction model.
Further, the system also comprises a prediction result processing module, which is used for carrying out coping processing according to the prediction result obtained after the prediction is carried out; the prediction result processing module comprises an influence value acquisition unit, an analog test unit and a response processing unit;
the influence value acquisition unit is used for acquiring a coal mine water disaster occurrence probability value and a water disaster grade value according to the coal mine water disaster prediction result; acquiring change trend data of the real-time coal mine environment data based on weather forecast data according to the real-time coal mine environment data; acquiring influence change data of real-time coal mine environment data on coal mine water damage according to the change trend data;
the simulation test unit is used for carrying out simulation test on the coal mine water disaster development trend based on a preset coal mine water disaster development trend simulation test model according to the coal mine water disaster occurrence probability value, the water disaster grade value and the influence change data to obtain simulation test development trend data;
and the coping processing unit is used for coping the coal mine water damage according to the simulation test development trend data and a preset coping strategy.
Further, the system also comprises a coal mine water disaster safety monitoring and managing module, which is used for constructing a safety monitoring and managing platform based on the internet of things technology to realize the monitoring and management of the coal mine water disaster; the coal mine water disaster safety monitoring management module comprises a monitoring management platform construction unit and a monitoring management unit;
the monitoring management platform building unit is used for communicating the Internet of things equipment, the water discharge equipment and the alarm equipment which are arranged in the coal mine with the remote monitoring management terminal based on the Internet of things technology to build a monitoring management platform for the water disaster safety of the coal mine;
the monitoring management unit is used for implementing monitoring of the water quantity data of the coal mine and the environment data of the coal mine based on the monitoring management platform, transmitting the monitoring data and the environment data of the coal mine to the remote monitoring management terminal, and remotely controlling and managing the water discharge equipment and the alarm equipment to work according to a preset monitoring management strategy.
Compared with the prior art, the invention has the following advantages and beneficial effects: the method can improve the accuracy of coal mine water damage prediction, reduce false alarm and missing alarm, improve the reliability of prediction results, avoid accidents or reduce the influence of the accidents on mine production, help mine management staff and staff to effectively cope with water damage risks, reduce loss and ensure production safety.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention may be realized and attained by the structure particularly pointed out in the written description and drawings.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a schematic diagram of a coal mine water damage prediction system based on data analysis and machine learning technology;
FIG. 2 is a schematic diagram of a data acquisition module of the coal mine water damage prediction system based on the data analysis and machine learning technology;
fig. 3 is a schematic diagram of a data acquisition implementation unit of the coal mine water damage prediction system based on the data analysis and machine learning technology.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
The invention provides a coal mine water damage prediction system based on data analysis and machine learning technology, as shown in figure 1, comprising:
the data acquisition module is used for acquiring the historical accident data of the coal mine water disaster and the historical environment data of the coal mine and acquiring first data;
the data processing module is used for preprocessing the first data to obtain preprocessed data;
the prediction model training evaluation module is used for training and evaluating a preset coal mine water damage prediction model based on the preprocessing data to obtain a first coal mine water damage prediction model;
and the prediction implementation module is used for predicting the coal mine water damage based on the first coal mine water damage prediction model.
The working principle of the technical scheme is as follows: the data acquisition module is used for acquiring the historical accident data of the coal mine water disaster and the historical environment data of the coal mine and acquiring first data;
the data processing module is used for preprocessing the first data to obtain preprocessed data;
the prediction model training evaluation module is used for training and evaluating a preset coal mine water damage prediction model based on the preprocessing data to obtain a first coal mine water damage prediction model;
and the prediction implementation module is used for predicting the coal mine water damage based on the first coal mine water damage prediction model.
The beneficial effects of the technical scheme are as follows: by adopting the scheme provided by the embodiment, the accuracy of coal mine water damage prediction can be improved, the situations of false alarm and missing alarm are reduced, the reliability of prediction results is improved, accidents are avoided or the influence of the accidents on mine production is reduced, mine management staff and staff are helped to effectively cope with water damage risks, loss is reduced, and production safety is guaranteed.
In one embodiment, as shown in fig. 2, the data acquisition module includes a data acquisition setting unit and a data acquisition implementation unit;
the data acquisition setting unit is used for setting data acquisition conditions according to the predicted demand of the coal mine water damage; the data acquisition conditions comprise one or more of an acquisition period, an acquisition point position, a data index, an acquisition amount and an acquisition mode;
the data acquisition implementation unit is used for acquiring the historical accident data of the coal mine water disaster and the historical environmental data of the coal mine according to the data acquisition conditions based on the large data platform of the coal mine water disaster information to obtain first data.
The working principle of the technical scheme is as follows: the data acquisition module comprises a data acquisition setting unit and a data acquisition implementation unit;
the data acquisition setting unit is used for setting data acquisition conditions according to the predicted demand of the coal mine water damage; the data acquisition conditions comprise one or more of an acquisition period, an acquisition point position, a data index, an acquisition amount and an acquisition mode;
the data acquisition implementation unit is used for acquiring the historical accident data of the coal mine water disaster and the historical environmental data of the coal mine according to the data acquisition conditions based on the large data platform of the coal mine water disaster information to obtain first data.
The beneficial effects of the technical scheme are as follows: by adopting the scheme provided by the embodiment, the qualified and available data can be ensured to be acquired through the setting and the implementation of the data acquisition.
In one embodiment, as shown in fig. 3, the data acquisition implementation unit further comprises a data screening subunit, wherein the data screening subunit comprises a coal mine water hazard historical accident data screening subunit, a coal mine historical environment data screening subunit and a screening data summarizing subunit;
the coal mine water disaster historical accident data screening molecular unit is used for acquiring accident grades in the coal mine water disaster historical accident data, screening typical accident data corresponding to a plurality of accident grades according to the accident grades, and acquiring first coal mine water disaster historical accident data;
the coal mine historical environment data screening molecular unit is used for acquiring the environmental impact value of the coal mine historical environment data on the coal mine water damage historical accident data according to the coal mine historical environment data, and screening the coal mine historical environment data with the environmental impact value being greater than a preset environmental impact value threshold value as first coal mine historical environment data;
and the screening data summarizing molecular unit is used for summarizing the first coal mine water disaster historical accident data and the first coal mine historical environment data to obtain first data.
The working principle of the technical scheme is as follows: the data acquisition implementation unit also comprises a data screening subunit, wherein the data screening subunit comprises a coal mine water hazard historical accident data screening subunit, a coal mine historical environment data screening subunit and a screening data summarizing subunit;
the coal mine water disaster historical accident data screening molecular unit is used for acquiring accident grades in the coal mine water disaster historical accident data, screening typical accident data corresponding to a plurality of accident grades according to the accident grades, and acquiring first coal mine water disaster historical accident data;
the coal mine historical environment data screening molecular unit is used for acquiring the environmental impact value of the coal mine historical environment data on the coal mine water damage historical accident data according to the coal mine historical environment data, and screening the coal mine historical environment data with the environmental impact value being greater than a preset environmental impact value threshold value as first coal mine historical environment data;
and the screening data summarizing molecular unit is used for summarizing the first coal mine water disaster historical accident data and the first coal mine historical environment data to obtain first data.
The beneficial effects of the technical scheme are as follows: by adopting the scheme provided by the embodiment, the quality and scientificity of the data can be further ensured through screening the data, and the training verification and test of the prediction model are facilitated.
In one embodiment, the data processing module includes a data preprocessing unit and a data classification unit;
the data preprocessing unit is used for cleaning, normalizing and standardizing the data and extracting time sequence characteristics to obtain first preprocessed data; the data cleaning comprises default value cleaning, and the normalization and standardization comprise minimum maximum normalization, zero mean standardization and decimal calibration standardization; the time sequence feature extraction comprises the steps of extracting features by adopting a principal component analysis method;
the data classifying unit is used for classifying the first preprocessing data to obtain a data training set, a data verification set and a data testing set, and generating preprocessing data.
The working principle of the technical scheme is as follows: the data processing module comprises a data preprocessing unit and a data classifying unit;
the data preprocessing unit is used for cleaning, normalizing and standardizing the data and extracting time sequence characteristics to obtain first preprocessed data; the data cleaning comprises default value cleaning, and the normalization and standardization comprise minimum maximum normalization, zero mean standardization and decimal calibration standardization; the time sequence feature extraction comprises the steps of extracting features by adopting a principal component analysis method;
the data classifying unit is used for classifying the first preprocessing data to obtain a data training set, a data verification set and a data testing set, and generating preprocessing data.
The beneficial effects of the technical scheme are as follows: by adopting the scheme provided by the embodiment, the data can be preprocessed to ensure that the targeted data applied to the prediction model is obtained.
In one embodiment, the prediction model training evaluation module includes a prediction model construction unit, a prediction model training verification unit, and a prediction model evaluation unit;
the prediction model construction unit is used for constructing and generating a coal mine water damage prediction model by utilizing the two-way long-short-term memory neural network, and carrying out parameter setting on the coal mine water damage prediction model according to a preset parameter database;
the prediction model training and verifying unit is used for training and verifying the coal mine water damage prediction model by utilizing the data training set and the data verifying set;
the prediction model evaluation unit is used for evaluating the coal mine water damage prediction model by utilizing the data test set to obtain a model evaluation result, and screening to obtain a first coal mine water damage prediction model based on the model evaluation result.
The working principle of the technical scheme is as follows: the prediction model training evaluation module comprises a prediction model construction unit, a prediction model training verification unit and a prediction model evaluation unit;
the prediction model construction unit is used for constructing and generating a coal mine water damage prediction model by utilizing the two-way long-short-term memory neural network, and carrying out parameter setting on the coal mine water damage prediction model according to a preset parameter database;
the prediction model training and verifying unit is used for training and verifying the coal mine water damage prediction model by utilizing the data training set and the data verifying set;
the prediction model evaluation unit is used for evaluating the coal mine water damage prediction model by utilizing the data test set to obtain a model evaluation result, and screening to obtain a first coal mine water damage prediction model based on the model evaluation result.
The beneficial effects of the technical scheme are as follows: by adopting the scheme provided by the embodiment, the accuracy of the coal mine water damage model can be ensured through construction, training verification and evaluation of the prediction model.
In one embodiment, the prediction model construction unit further comprises a coal mine water damage prediction model parameter setting subunit;
the coal mine water damage prediction model parameter setting subunit comprises a single parameter optimal value acquisition subunit, a parameter optimal range acquisition subunit and a parameter database setting subunit;
the single parameter optimal value obtaining molecular unit is used for drawing a change schematic coordinate graph of the layer number and the calculation cost of the two-way long-short-term memory neural network, a change schematic coordinate graph of the hidden unit number and the overfitting probability of the layer of the two-way long-short-term memory neural network, and a change schematic coordinate graph of the learning rate and the convergence rate of the two-way long-short-term memory neural network, and obtaining the optimal layer number, the optimal hidden unit number and the optimal learning rate;
the parameter optimal range obtaining molecular unit is used for setting an optimal layer number range, an optimal hiding unit number range and an optimal learning rate range according to the optimal layer number, the optimal hiding unit number and the optimal learning rate based on a preset floating value;
the parameter database is provided with a molecular unit, is used for setting a plurality of data groups consisting of the layer number, the hidden unit number and the learning rate according to the optimal layer number range, the optimal hidden unit number range and the optimal learning rate range, and generates the parameter database according to the data groups.
The working principle of the technical scheme is as follows: the prediction model construction unit also comprises a coal mine water damage prediction model parameter setting subunit;
the coal mine water damage prediction model parameter setting subunit comprises a single parameter optimal value acquisition subunit, a parameter optimal range acquisition subunit and a parameter database setting subunit;
the single parameter optimal value obtaining molecular unit is used for drawing a change schematic coordinate graph of the layer number and the calculation cost of the two-way long-short-term memory neural network, a change schematic coordinate graph of the hidden unit number and the overfitting probability of the layer of the two-way long-short-term memory neural network, and a change schematic coordinate graph of the learning rate and the convergence rate of the two-way long-short-term memory neural network, and obtaining the optimal layer number, the optimal hidden unit number and the optimal learning rate;
the parameter optimal range obtaining molecular unit is used for setting an optimal layer number range, an optimal hiding unit number range and an optimal learning rate range according to the optimal layer number, the optimal hiding unit number and the optimal learning rate based on a preset floating value;
the parameter database is provided with a molecular unit, is used for setting a plurality of data groups consisting of the layer number, the hidden unit number and the learning rate according to the optimal layer number range, the optimal hidden unit number range and the optimal learning rate range, and generates the parameter database according to the data groups.
The beneficial effects of the technical scheme are as follows: by adopting the scheme provided by the embodiment, the rationality of parameter setting can be ensured through setting the parameters of the coal mine water damage prediction model, and references are provided for subsequent data application.
In one embodiment, the prediction model evaluation unit comprises an evaluation result acquisition subunit and a first coal mine water damage prediction model acquisition subunit;
the evaluation result acquisition subunit is used for evaluating the coal mine water damage prediction model by utilizing the data test set to obtain model prediction accuracy;
the first coal mine water damage prediction model acquisition subunit is used for monitoring and analyzing the model prediction accuracy, and when the prediction accuracy reaches a preset prediction accuracy threshold, the corresponding coal mine water damage prediction model is used as the first coal mine water damage prediction model.
The working principle of the technical scheme is as follows: the prediction model evaluation unit comprises an evaluation result acquisition subunit and a first coal mine water damage prediction model acquisition subunit;
the evaluation result acquisition subunit is used for evaluating the coal mine water damage prediction model by utilizing the data test set to obtain model prediction accuracy;
the first coal mine water damage prediction model acquisition subunit is used for monitoring and analyzing the model prediction accuracy, and when the prediction accuracy reaches a preset prediction accuracy threshold, the corresponding coal mine water damage prediction model is used as the first coal mine water damage prediction model.
The beneficial effects of the technical scheme are as follows: by adopting the scheme provided by the embodiment, the coal mine water damage prediction model with better performance can be ensured to be obtained through analyzing the model prediction accuracy in the evaluation result.
In one embodiment, the prediction implementation module includes a real-time data acquisition unit and a prediction implementation unit;
the real-time data acquisition unit is used for acquiring real-time water quantity data of the coal mine and real-time coal mine environment data;
the prediction implementation unit is used for predicting the coal mine water damage according to the real-time water quantity data of the coal mine and the real-time coal mine environment data by using the first coal mine water damage prediction model.
The working principle of the technical scheme is as follows: the prediction implementation module comprises a real-time data acquisition unit and a prediction implementation unit;
the real-time data acquisition unit is used for acquiring real-time water quantity data of the coal mine and real-time coal mine environment data;
the prediction implementation unit is used for predicting the coal mine water damage according to the real-time water quantity data of the coal mine and the real-time coal mine environment data by using the first coal mine water damage prediction model.
The beneficial effects of the technical scheme are as follows: by adopting the scheme provided by the embodiment, the coal mine water damage prediction result can be obtained by performing coal mine water damage prediction according to the coal mine real-time water quantity data and the real-time coal mine environment data, and the prediction efficiency is improved.
In one embodiment, the system further comprises a prediction result processing module, which is used for performing coping processing according to a prediction result obtained after prediction implementation; the prediction result processing module comprises an influence value acquisition unit, an analog test unit and a response processing unit;
the influence value acquisition unit is used for acquiring a coal mine water disaster occurrence probability value and a water disaster grade value according to the coal mine water disaster prediction result; acquiring change trend data of the real-time coal mine environment data based on weather forecast data according to the real-time coal mine environment data; acquiring influence change data of real-time coal mine environment data on coal mine water damage according to the change trend data;
the simulation test unit is used for carrying out simulation test on the coal mine water disaster development trend based on a preset coal mine water disaster development trend simulation test model according to the coal mine water disaster occurrence probability value, the water disaster grade value and the influence change data to obtain simulation test development trend data;
and the coping processing unit is used for coping the coal mine water damage according to the simulation test development trend data and a preset coping strategy.
The working principle of the technical scheme is as follows: the system also comprises a prediction result processing module, a prediction result processing module and a prediction result processing module, wherein the prediction result processing module is used for carrying out coping processing according to a prediction result obtained after prediction implementation; the prediction result processing module comprises an influence value acquisition unit, an analog test unit and a response processing unit;
the influence value acquisition unit is used for acquiring a coal mine water disaster occurrence probability value and a water disaster grade value according to the coal mine water disaster prediction result; acquiring change trend data of the real-time coal mine environment data based on weather forecast data according to the real-time coal mine environment data; acquiring influence change data of real-time coal mine environment data on coal mine water damage according to the change trend data;
the simulation test unit is used for carrying out simulation test on the coal mine water disaster development trend based on a preset coal mine water disaster development trend simulation test model according to the coal mine water disaster occurrence probability value, the water disaster grade value and the influence change data to obtain simulation test development trend data;
and the coping processing unit is used for coping the coal mine water damage according to the simulation test development trend data and a preset coping strategy.
The beneficial effects of the technical scheme are as follows: by adopting the scheme provided by the embodiment, the accuracy of prediction analysis is further enhanced and the coping process is performed after the simulation test is performed according to the prediction result obtained after the prediction implementation and the development trend of the environmental data, so that the pertinence and the effectiveness of the coping process can be improved.
In one embodiment, the system also comprises a coal mine water hazard safety monitoring management module, which is used for constructing a safety monitoring management platform based on the internet of things technology to realize the monitoring and management of the coal mine water hazard; the coal mine water disaster safety monitoring management module comprises a monitoring management platform construction unit and a monitoring management unit;
the monitoring management platform building unit is used for communicating the Internet of things equipment, the water discharge equipment and the alarm equipment which are arranged in the coal mine with the remote monitoring management terminal based on the Internet of things technology to build a monitoring management platform for the water disaster safety of the coal mine;
the monitoring management unit is used for implementing monitoring of the water quantity data of the coal mine and the environment data of the coal mine based on the monitoring management platform, transmitting the monitoring data and the environment data of the coal mine to the remote monitoring management terminal, and remotely controlling and managing the water discharge equipment and the alarm equipment to work according to a preset monitoring management strategy.
The working principle of the technical scheme is as follows: the system also comprises a coal mine water disaster safety monitoring and managing module, which is used for constructing a safety monitoring and managing platform based on the internet of things technology to realize the monitoring and management of the coal mine water disaster; the coal mine water disaster safety monitoring management module comprises a monitoring management platform construction unit and a monitoring management unit;
the monitoring management platform building unit is used for communicating the Internet of things equipment, the water discharge equipment and the alarm equipment which are arranged in the coal mine with the remote monitoring management terminal based on the Internet of things technology to build a monitoring management platform for the water disaster safety of the coal mine;
the monitoring management unit is used for implementing monitoring of the water quantity data of the coal mine and the environment data of the coal mine based on the monitoring management platform, transmitting the monitoring data and the environment data of the coal mine to the remote monitoring management terminal, and remotely controlling and managing the water discharge equipment and the alarm equipment to work according to a preset monitoring management strategy.
The beneficial effects of the technical scheme are as follows: by adopting the scheme provided by the embodiment, the safety monitoring management platform is built based on the internet of things technology, so that the monitoring and management of the coal mine water damage are realized, the intelligent level of the monitoring and management of the coal mine water damage can be improved, and the efficiency of the coal mine level management is improved.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (10)
1. Coal mine water damage prediction system based on data analysis and machine learning technology, which is characterized by comprising:
the data acquisition module is used for acquiring the historical accident data of the coal mine water disaster and the historical environment data of the coal mine and acquiring first data;
the data processing module is used for preprocessing the first data to obtain preprocessed data;
the prediction model training evaluation module is used for training and evaluating a preset coal mine water damage prediction model based on the preprocessing data to obtain a first coal mine water damage prediction model;
and the prediction implementation module is used for predicting the coal mine water damage based on the first coal mine water damage prediction model.
2. The coal mine water damage prediction system based on the data analysis and machine learning technology according to claim 1, wherein the data acquisition module comprises a data acquisition setting unit and a data acquisition implementation unit;
the data acquisition setting unit is used for setting data acquisition conditions according to the predicted demand of the coal mine water damage; the data acquisition conditions comprise one or more of an acquisition period, an acquisition point position, a data index, an acquisition amount and an acquisition mode;
the data acquisition implementation unit is used for acquiring the historical accident data of the coal mine water disaster and the historical environmental data of the coal mine according to the data acquisition conditions based on the large data platform of the coal mine water disaster information to obtain first data.
3. The system for predicting the water damage of a coal mine based on the data analysis and machine learning technology as claimed in claim 2, wherein the data acquisition implementation unit further comprises a data screening subunit, and the data screening subunit comprises a coal mine water damage historical accident data screening subunit, a coal mine historical environment data screening subunit and a screening data summarizing subunit;
the coal mine water disaster historical accident data screening molecular unit is used for acquiring accident grades in the coal mine water disaster historical accident data, screening typical accident data corresponding to a plurality of accident grades according to the accident grades, and acquiring first coal mine water disaster historical accident data;
the coal mine historical environment data screening molecular unit is used for acquiring the environmental impact value of the coal mine historical environment data on the coal mine water damage historical accident data according to the coal mine historical environment data, and screening the coal mine historical environment data with the environmental impact value being greater than a preset environmental impact value threshold value as first coal mine historical environment data;
and the screening data summarizing molecular unit is used for summarizing the first coal mine water disaster historical accident data and the first coal mine historical environment data to obtain first data.
4. The coal mine water damage prediction system based on the data analysis and machine learning technology according to claim 1, wherein the data processing module comprises a data preprocessing unit and a data classifying unit;
the data preprocessing unit is used for cleaning, normalizing and standardizing the data and extracting time sequence characteristics to obtain first preprocessed data; the data cleaning comprises default value cleaning, and the normalization and standardization comprise minimum maximum normalization, zero mean standardization and decimal calibration standardization; the time sequence feature extraction comprises the steps of extracting features by adopting a principal component analysis method;
the data classifying unit is used for classifying the first preprocessing data to obtain a data training set, a data verification set and a data testing set, and generating preprocessing data.
5. The coal mine water damage prediction system based on the data analysis and machine learning technology according to claim 4, wherein the prediction model training evaluation module comprises a prediction model construction unit, a prediction model training verification unit and a prediction model evaluation unit;
the prediction model construction unit is used for constructing and generating a coal mine water damage prediction model by utilizing the two-way long-short-term memory neural network, and carrying out parameter setting on the coal mine water damage prediction model according to a preset parameter database;
the prediction model training and verifying unit is used for training and verifying the coal mine water damage prediction model by utilizing the data training set and the data verifying set;
the prediction model evaluation unit is used for evaluating the coal mine water damage prediction model by utilizing the data test set to obtain a model evaluation result, and screening to obtain a first coal mine water damage prediction model based on the model evaluation result.
6. The coal mine water damage prediction system based on the data analysis and machine learning technology according to claim 5, wherein the prediction model construction unit further comprises a coal mine water damage prediction model parameter setting subunit; the coal mine water damage prediction model parameter setting subunit comprises a single parameter optimal value acquisition subunit, a parameter optimal range acquisition subunit and a parameter database setting subunit;
the single parameter optimal value obtaining molecular unit is used for drawing a change schematic coordinate graph of the layer number and the calculation cost of the two-way long-short-term memory neural network, a change schematic coordinate graph of the hidden unit number and the overfitting probability of the layer of the two-way long-short-term memory neural network, and a change schematic coordinate graph of the learning rate and the convergence rate of the two-way long-short-term memory neural network, and obtaining the optimal layer number, the optimal hidden unit number and the optimal learning rate;
the parameter optimal range obtaining molecular unit is used for setting an optimal layer number range, an optimal hiding unit number range and an optimal learning rate range according to the optimal layer number, the optimal hiding unit number and the optimal learning rate based on a preset floating value;
the parameter database is provided with a molecular unit, is used for setting a plurality of data groups consisting of the layer number, the hidden unit number and the learning rate according to the optimal layer number range, the optimal hidden unit number range and the optimal learning rate range, and generates the parameter database according to the data groups.
7. The coal mine water damage prediction system based on the data analysis and machine learning technology according to claim 5, wherein the prediction model evaluation unit comprises an evaluation result acquisition subunit and a first coal mine water damage prediction model acquisition subunit;
the evaluation result acquisition subunit is used for evaluating the coal mine water damage prediction model by utilizing the data test set to obtain model prediction accuracy;
the first coal mine water damage prediction model acquisition subunit is used for monitoring and analyzing the model prediction accuracy, and when the prediction accuracy reaches a preset prediction accuracy threshold, the corresponding coal mine water damage prediction model is used as the first coal mine water damage prediction model.
8. The coal mine water damage prediction system based on the data analysis and machine learning technology according to claim 1, wherein the prediction implementation module comprises a real-time data acquisition unit and a prediction implementation unit;
the real-time data acquisition unit is used for acquiring real-time water quantity data of the coal mine and real-time coal mine environment data;
the prediction implementation unit is used for predicting the coal mine water damage according to the real-time water quantity data of the coal mine and the real-time coal mine environment data by using the first coal mine water damage prediction model.
9. The system for predicting the water damage of a coal mine based on the data analysis and machine learning technology as recited in claim 8, further comprising a prediction result processing module for performing coping process according to a prediction result obtained after the prediction is performed; the prediction result processing module comprises an influence value acquisition unit, an analog test unit and a response processing unit;
the influence value acquisition unit is used for acquiring a coal mine water disaster occurrence probability value and a water disaster grade value according to the coal mine water disaster prediction result; acquiring change trend data of the real-time coal mine environment data based on weather forecast data according to the real-time coal mine environment data; acquiring influence change data of real-time coal mine environment data on coal mine water damage according to the change trend data;
the simulation test unit is used for carrying out simulation test on the coal mine water disaster development trend based on a preset coal mine water disaster development trend simulation test model according to the coal mine water disaster occurrence probability value, the water disaster grade value and the influence change data to obtain simulation test development trend data;
and the coping processing unit is used for coping the coal mine water damage according to the simulation test development trend data and a preset coping strategy.
10. The coal mine water disaster prediction system based on the data analysis and machine learning technology according to claim 1, further comprising a coal mine water disaster safety monitoring and management module, wherein the coal mine water disaster safety monitoring and management module is used for constructing a safety monitoring and management platform based on the internet of things technology to realize monitoring and management of coal mine water disaster; the coal mine water disaster safety monitoring management module comprises a monitoring management platform construction unit and a monitoring management unit;
the monitoring management platform building unit is used for communicating the Internet of things equipment, the water discharge equipment and the alarm equipment which are arranged in the coal mine with the remote monitoring management terminal based on the Internet of things technology to build a monitoring management platform for the water disaster safety of the coal mine;
the monitoring management unit is used for implementing monitoring of the water quantity data of the coal mine and the environment data of the coal mine based on the monitoring management platform, transmitting the monitoring data and the environment data of the coal mine to the remote monitoring management terminal, and remotely controlling and managing the water discharge equipment and the alarm equipment to work according to a preset monitoring management strategy.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311061091.5A CN116777085B (en) | 2023-08-23 | 2023-08-23 | Coal mine water damage prediction system based on data analysis and machine learning technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311061091.5A CN116777085B (en) | 2023-08-23 | 2023-08-23 | Coal mine water damage prediction system based on data analysis and machine learning technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116777085A true CN116777085A (en) | 2023-09-19 |
| CN116777085B CN116777085B (en) | 2023-11-10 |
Family
ID=87991656
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311061091.5A Active CN116777085B (en) | 2023-08-23 | 2023-08-23 | Coal mine water damage prediction system based on data analysis and machine learning technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116777085B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117114206A (en) * | 2023-10-23 | 2023-11-24 | 北京联创高科信息技术有限公司 | Calculation method for coal mine water damage index data trend |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180341876A1 (en) * | 2017-05-25 | 2018-11-29 | Hitachi, Ltd. | Deep learning network architecture optimization for uncertainty estimation in regression |
| CN110288501A (en) * | 2019-07-05 | 2019-09-27 | 华北科技学院 | A kind of mine water disaster accident emergency decision-making technique and system |
| KR102069087B1 (en) * | 2018-12-21 | 2020-01-22 | (주)위세아이텍 | Apparatus and method for predicting train accident risk using fault probability |
| WO2021203491A1 (en) * | 2020-04-07 | 2021-10-14 | 北京科技大学 | Intelligent prediction method and system for ground pressure disasters of wall rock affected by mining |
| WO2022227129A1 (en) * | 2021-04-27 | 2022-11-03 | 山东交通学院 | Road transportation risk assessment method and system for hazardous chemical |
| CN115983488A (en) * | 2023-01-10 | 2023-04-18 | 吉林大学 | Method and device for predicting water inflow of mine |
| CN116028798A (en) * | 2023-02-21 | 2023-04-28 | 煤炭科学技术研究院有限公司 | Water damage early warning data processing method, device, computer equipment and storage medium |
-
2023
- 2023-08-23 CN CN202311061091.5A patent/CN116777085B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180341876A1 (en) * | 2017-05-25 | 2018-11-29 | Hitachi, Ltd. | Deep learning network architecture optimization for uncertainty estimation in regression |
| KR102069087B1 (en) * | 2018-12-21 | 2020-01-22 | (주)위세아이텍 | Apparatus and method for predicting train accident risk using fault probability |
| CN110288501A (en) * | 2019-07-05 | 2019-09-27 | 华北科技学院 | A kind of mine water disaster accident emergency decision-making technique and system |
| WO2021203491A1 (en) * | 2020-04-07 | 2021-10-14 | 北京科技大学 | Intelligent prediction method and system for ground pressure disasters of wall rock affected by mining |
| WO2022227129A1 (en) * | 2021-04-27 | 2022-11-03 | 山东交通学院 | Road transportation risk assessment method and system for hazardous chemical |
| CN115983488A (en) * | 2023-01-10 | 2023-04-18 | 吉林大学 | Method and device for predicting water inflow of mine |
| CN116028798A (en) * | 2023-02-21 | 2023-04-28 | 煤炭科学技术研究院有限公司 | Water damage early warning data processing method, device, computer equipment and storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117114206A (en) * | 2023-10-23 | 2023-11-24 | 北京联创高科信息技术有限公司 | Calculation method for coal mine water damage index data trend |
| CN117114206B (en) * | 2023-10-23 | 2024-01-26 | 北京联创高科信息技术有限公司 | Calculation method for coal mine water damage index data trend |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116777085B (en) | 2023-11-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110148285B (en) | Intelligent oil well parameter early warning system based on big data technology and early warning method thereof | |
| CN108915771B (en) | Cloud control mine comprehensive management system | |
| CN106888205B (en) | Non-invasive PLC anomaly detection method based on power consumption analysis | |
| CN109508827B (en) | Drilling accident early warning method based on time recursion neural network | |
| US9280517B2 (en) | System and method for failure detection for artificial lift systems | |
| CN110619587B (en) | Method and system for foundation pit monitoring intelligent early warning and data evidence storage | |
| CN116777085B (en) | Coal mine water damage prediction system based on data analysis and machine learning technology | |
| CN107194068A (en) | Shale gas fracturing process underground unusual service condition real-time estimate method for early warning and device | |
| CN115239135A (en) | Construction risk identification management and control system and method | |
| CN105608842A (en) | Nuclear reactor fuel failure online monitoring alarm device | |
| RU2745136C1 (en) | Automated system for identification and prediction of complications in the process of construction of oil and gas wells | |
| CN110795888A (en) | Petroleum drilling risk prediction method | |
| CN114251125A (en) | Intelligent early warning system for water damage of coal mine | |
| CN116658246A (en) | Coal mine water damage monitoring and early warning system and method | |
| CN112668873A (en) | Mine safety situation analysis and prediction early warning method | |
| CN116383722A (en) | Fracturing measure process monitoring method based on gate control circulation unit neural network | |
| CN109902265B (en) | Underground early warning method based on hidden Markov model | |
| CN106246226B (en) | A kind of abnormal recognition methods of Mine Gas Gushing | |
| CN102354381A (en) | Dynamic prediction analysis technology of gas emission quantity in coal mine | |
| CN108376293A (en) | A kind of ZJ17 cigarette machines repair intelligent Forecasting based on fuzzy mathematics improved H | |
| Wang et al. | AdaBoost-driven multi-parameter real-time warning of rock burst risk in coal mines | |
| CN114640177A (en) | Electric energy efficiency monitoring method based on electric energy efficiency monitoring device | |
| Bo et al. | Research on the data validity of a coal mine solid backfill working face sensing system based on an improved transformer | |
| CN113685166B (en) | Drilling accident early warning method and system | |
| CN115759351A (en) | Slurry shield tunneling comprehensive early warning method and system and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |