CN111930601A - Deep learning-based database state comprehensive scoring method and system - Google Patents
Deep learning-based database state comprehensive scoring method and system Download PDFInfo
- Publication number
- CN111930601A CN111930601A CN202010409687.XA CN202010409687A CN111930601A CN 111930601 A CN111930601 A CN 111930601A CN 202010409687 A CN202010409687 A CN 202010409687A CN 111930601 A CN111930601 A CN 111930601A
- Authority
- CN
- China
- Prior art keywords
- database
- model
- comprehensive scoring
- scoring
- training
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3447—Performance evaluation by modeling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Abstract
The invention discloses a deep learning-based database state comprehensive scoring method, which comprises the following steps of: (1) collecting operation and maintenance data of a database, and scoring the state of the database by using an expert model; (2) preprocessing data, and dividing a training set and a test set according to a proportion; (3) constructing a database state comprehensive scoring model based on deep learning; (4) analyzing the current or future operation and maintenance data of the database by using a comprehensive scoring model to obtain the current or future database state comprehensive scoring; the database state comprehensive scoring system comprises a database operation and maintenance data acquisition module, an expert model scoring module, a data preprocessing module and a database comprehensive scoring module. According to the invention, the operation and maintenance data of the database are analyzed, the operation state of the database is comprehensively scored, and the operation and maintenance efficiency is improved; the probability of human misoperation is reduced; a deep learning-based database state comprehensive scoring method is provided.
Description
Technical Field
The invention relates to a database state comprehensive scoring method and a database state comprehensive scoring system, in particular to a database state comprehensive scoring method and a database state comprehensive scoring system based on deep learning.
Background
Currently, the mainstream database products are MySQL, Oracle and the like. The operation and maintenance of the database system mainly depend on a database management system, and a database administrator analyzes and manages the state of the database through the database management system. Along with the scale expansion of the database, the operation and maintenance data are various, the cost of manual operation and maintenance is high, and the operation and maintenance efficiency is low.
Disclosure of Invention
The purpose of the invention is as follows: the invention aims to provide a database state comprehensive scoring method based on deep learning, which has high operation and maintenance efficiency and reduces the probability of human misoperation.
The technical scheme is as follows: the invention discloses a database state comprehensive scoring method, which comprises the following steps: (1) collecting operation and maintenance data of a database, and scoring the state of the database by using an expert model; (2) preprocessing data, and dividing a training set and a test set according to a proportion; (3) constructing a database state comprehensive scoring model based on deep learning; (4) and analyzing the current or future operation and maintenance data of the database by using a comprehensive scoring model to obtain the current or future database state comprehensive scoring.
The operation state data in the step (1) comprises: CPU, internal memory, magnetic disk, storage utilization rate, I/O bandwidth, server temperature, link temperature and humidity; collecting various operation and maintenance data of the database, and grading the state of the database through an expert model grading model.
And (2) carrying out preprocessing such as data cleaning and normalization on a sample data set consisting of the collected database operation and maintenance data and expert model scores, and dividing the sample data set into a training set and a test set according to a proportion.
Training the comprehensive grading model by using a training set training model, and testing the prediction capability of the grading model by using a test set; the deep neural network algorithm is adopted to construct a deep neural network-based database comprehensive scoring model, the database comprehensive scoring model utilizes a training set to train the model, model parameters are adjusted, the prediction capability of the test set inspection model is utilized, and the training process is as follows:
(3.1) defining a deep neural network, and setting a function of the neuron, a learning rate, a batch _ size batch size, a maximum training time and an expected error. Defining an error calculation function and selecting an optimization algorithm;
(3.2) inputting training samples, randomly disordering, and calculating the error between the expected output value and the actual output value of the training samples;
(3.3) calculating and updating each neuron parameter in the deep neural network classification prediction model by using a back propagation algorithm according to the error;
(3.4) repeating steps (3.2) and (3.3) until the error is less than or equal to the expected error or the maximum number of training times is reached.
The comprehensive grading system for the database state comprises a database operation and maintenance data acquisition module, an expert model grading module, a data preprocessing module and a database comprehensive grading module; the database operation and maintenance data acquisition module acquires various operation and maintenance data of the database and scores the state of the database through the expert model scoring module; the data preprocessing module carries out data cleaning and normalization preprocessing on a sample data set consisting of the collected database operation and maintenance data and expert model scores, and the sample data set is processed according to the following steps of 7: 3, dividing the ratio into a training set and a test set; and the database comprehensive scoring module utilizes the training set training model to adjust the model parameters and utilizes the test set to test the prediction capability of the model.
Has the advantages that: compared with the prior art, the invention has the following remarkable effects: 1. the operation and maintenance efficiency is improved by analyzing the operation and maintenance data of the database and comprehensively scoring the operation state of the database; 2. the probability of human misoperation is reduced; 3. a deep learning-based database state comprehensive scoring method is provided.
Drawings
Fig. 1 is a flowchart of a database state composite scoring method according to the present invention.
Detailed Description
The invention is described in further detail below with reference to the drawings and the detailed description.
In the implementation process of the database state comprehensive scoring method, each item of operation and maintenance data is scored for the state of the database state comprehensive scoring module through an expert model scoring module; preprocessing a sample data set consisting of the collected database operation and maintenance data and expert model scores, such as data cleaning, normalization and the like, and processing the sample data set according to the following steps of 7: 3, dividing the ratio into a training set and a test set; database comprehensive grading the database comprehensive grading model utilizes the training set training model, adjusts the model parameters, and utilizes the test set to test the prediction capability of the model.
The expert model adopted in the invention is the prior art, the operation and maintenance of a large Database system are mainly maintained by a high-end DBA (Database Administrator), and the DBA can score the health degree of the whole operation condition of the Database by checking various indexes of the Database, and the method is called as the expert model. The expert model is an expert with years of database operation and maintenance experience, indexes which have the largest influence on the health degree of the database are manually selected, all the indexes are scored by adopting a manually set threshold value, and all the scores are finally summed up to obtain the final database comprehensive state score.
Fig. 1 is a schematic flow chart of the database state comprehensive scoring method of the present invention, and the method is implemented in detail as follows:
step 1, collecting running state data of a database, and then scoring the state of the database by using an expert model; the collected operation and maintenance data comprises: 180 indexes such as CPU, memory, storage utilization rate, I/O bandwidth, server temperature, link temperature, humidity and the like; the expert model scores the composite score for the database state as [0, 100 ].
And collecting operation and maintenance data of a plurality of event nodes in a preset time period from the database, wherein the time intervals among the time nodes are the same.
Step 2, carrying out data preprocessing such as data cleaning and normalization on the collected data set, and dividing the data set into a training set and a testing set according to a certain proportion (7: 3);
and performing data cleaning on the data set, wherein the data cleaning comprises consistency check, invalid value processing and missing value processing.
Step 3, constructing a database state comprehensive scoring model based on deep learning, training the comprehensive scoring model by using a training set, and testing the prediction capability of the scoring model by using a test set;
the training process of the deep learning-based database state comprehensive scoring system is as follows:
(3.1) defining a deep neural network, setting the function of the neuron, learning rate, batch _ size, maximum training times and expected error. Defining an error calculation function as a cross entropy loss calculation function, and an optimization algorithm as Adam;
(3.2) inputting training samples, randomly disordering, and calculating the error between the expected output value and the actual output value of the training samples;
and (3.3) calculating and updating each neuron parameter in the deep neural network classification prediction model by using a back propagation algorithm according to the error.
(3.4) repeating the steps (3.2) and (3.3) until the error is less than or equal to the expected error (set in advance according to the requirement) or the maximum training times are reached.
And constructing a comprehensive scoring model of the deep neural network database by adopting a deep neural network algorithm. The deep neural network database comprehensive scoring model comprises 1 input layer, 5 hidden layers and 1 output layer;
m hidden layers L1, L2, … and Lm are arranged, each hidden layer is provided with n neurons, the neurons in the L1 layer are S1(1), S1(2), … and S1(n),
the output of the ith neuron of the first hidden layer is,
each of the 5 hidden layers comprises 256 neurons, and a ReLU activation function is adopted; the output layer adopts sigmoid activation function.
The ReLU activation function is then:
V(t)＝max(0,t) (2)
in equation (2), V is the ReLU activation function, and t is the input to the activation function.
The deep neural network can gradually update the parameters of a plurality of neurons in the training process until the input signals can be correctly mapped to the classification result. The relationship between the error and the weight is
"E" is Error, and "W" is Weight, and the change degree of the Error after Weight adjustment is measured. The chain rule formula for calculus is:
in deep neural networks, the relationship between error, weight and activation function is as follows:
and estimating the inconsistency degree of the predicted value and the actual value of the model by using a cross entropy loss function, wherein the smaller the loss function value is, the smaller the robustness of the model is.
And training the model by using a training set, adjusting the parameters of the model, and testing the prediction capability of the model by using a test set.
And 4, analyzing the current or future operation and maintenance data of the database by using a scoring model to obtain the current or future database state comprehensive score. And (3) collecting operation and maintenance data of the database in a certain period of time, performing data preprocessing by adopting the same method as the step (2), taking the processed data as the input of a database comprehensive scoring model, and taking the output of the model as the comprehensive scoring of the database state.
The overall architecture of the deep learning-based database state comprehensive scoring system comprises a database operation and maintenance data acquisition module, an expert model scoring module, a data preprocessing module and a database comprehensive scoring module. The database operation and maintenance data acquisition module acquires various operation and maintenance data of the database, and scores the state of the database through the expert model scoring module; the data preprocessing module carries out data cleaning and normalization preprocessing on a sample data set consisting of the collected database operation and maintenance data and expert model scores, and the preprocessed sample data set is processed according to the following steps of 7: 3, dividing the ratio into a training set and a test set; the database comprehensive scoring module utilizes the training set training model to adjust model parameters and utilizes the test set to test the prediction capability of the model; the database comprehensive scoring system executes part or all of the steps of the database comprehensive scoring method to complete comprehensive scoring of the database state.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting the same, and although the present invention is described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications and equivalents may be made to the embodiments of the invention without departing from the spirit and scope of the invention, which is to be covered by the claims.
Claims (7)
1. A database state comprehensive scoring method based on deep learning is characterized in that: the method comprises the following steps: (1) collecting operation and maintenance data of a database, and comprehensively scoring the state of the database based on the collected data; (2) preprocessing data, and dividing a training set and a test set according to a proportion; (3) constructing a database state comprehensive scoring model based on deep learning; (4) and analyzing the current or future operation and maintenance data of the database by using a comprehensive scoring model to obtain the current or future database state comprehensive scoring.
2. The deep learning-based database state comprehensive scoring method according to claim 1, wherein the operation and maintenance data in step (1) comprises: CPU, internal memory, magnetic disk, storage utilization rate, I/O bandwidth, server temperature, link temperature and humidity.
3. The deep learning-based database state comprehensive scoring method according to claim 1, wherein the step (1) collects various operation and maintenance data of the database, and scores the state of the database through an expert model scoring model.
4. The deep learning-based database state comprehensive scoring method according to claim 1, wherein the step (2) performs data cleaning and normalization preprocessing on a sample data set consisting of the collected database operation and maintenance data and expert model scoring, and divides the sample data set into a training set and a test set in proportion.
5. The deep learning-based database state comprehensive scoring method according to claim 1, wherein the step (3) trains the comprehensive scoring model by using a training set training model, and tests the predictive ability of the scoring model by using a test set.
6. The deep learning-based database state comprehensive scoring method according to claim 1 or 5, wherein the deep neural network algorithm is adopted in the step (3) to construct a deep neural network-based database comprehensive scoring model, the database comprehensive scoring model utilizes a training set training model to adjust model parameters, the prediction capability of the model is tested by utilizing a test set, and the training process is as follows:
(3.1) defining a deep neural network, and setting a function, a learning rate, a batch _ size batch size, a maximum training time and an expected error of a neuron; defining an error calculation function and selecting an optimization algorithm;
(3.2) inputting training samples, randomly disordering, and calculating the error between the expected output value and the actual output value of the training samples;
(3.3) calculating and updating each neuron parameter in the deep neural network classification prediction model by using a back propagation algorithm according to the error;
(3.4) repeating steps (3.2) and (3.3) until the error is less than or equal to the expected error or the maximum number of training times is reached.
7. The utility model provides a database state comprehensive scoring system based on deep learning which characterized in that: the system comprises a database operation and maintenance data acquisition module, an expert model scoring module, a data preprocessing module and a database comprehensive scoring module; the database operation and maintenance data acquisition module acquires various operation and maintenance data of the database and scores the state of the database through the expert model scoring module; the data preprocessing module carries out data cleaning and normalization preprocessing on a sample data set consisting of the collected database operation and maintenance data and expert model scores, and the sample data set is processed according to the following steps of 7: 3, dividing the ratio into a training set and a test set; and the database comprehensive scoring module utilizes the training set training model to adjust the model parameters and utilizes the test set to test the prediction capability of the model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010409687.XA CN111930601A (en) | 2020-05-14 | 2020-05-14 | Deep learning-based database state comprehensive scoring method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010409687.XA CN111930601A (en) | 2020-05-14 | 2020-05-14 | Deep learning-based database state comprehensive scoring method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111930601A true CN111930601A (en) | 2020-11-13 |
Family
ID=73316371
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010409687.XA Pending CN111930601A (en) | 2020-05-14 | 2020-05-14 | Deep learning-based database state comprehensive scoring method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111930601A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112365186A (en) * | 2020-11-27 | 2021-02-12 | 中国电建集团海外投资有限公司 | Health degree evaluation method and system for electric power information system |
| CN113342758A (en) * | 2021-08-06 | 2021-09-03 | 联想凌拓科技有限公司 | Metadata management method, device, equipment and medium of file system |
| CN113806453A (en) * | 2021-09-18 | 2021-12-17 | 广东电网有限责任公司 | Automatic confirmation method, device, terminal and medium for scheduling operation ticket comprehensive order |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160350919A1 (en) * | 2015-06-01 | 2016-12-01 | Virtual Radiologic Corporation | Medical evaluation machine learning workflows and processes |
| WO2018090657A1 (en) * | 2016-11-18 | 2018-05-24 | 同济大学 | Bp_adaboost model-based method and system for predicting credit card user default |
| CN108388503A (en) * | 2018-02-13 | 2018-08-10 | 中体彩科技发展有限公司 | Data-base performance monitoring method, system, equipment and computer readable storage medium |
| CN109194423A (en) * | 2018-08-13 | 2019-01-11 | 中国人民解放军陆军工程大学 | The single-frequency point spectrum prediction method of shot and long term memory models based on optimization |
| CN109271374A (en) * | 2018-10-19 | 2019-01-25 | 国网江苏省电力有限公司信息通信分公司 | A kind of database health scoring method and scoring system based on machine learning |
| US20190188065A1 (en) * | 2017-12-15 | 2019-06-20 | International Business Machines Corporation | Computerized high-speed anomaly detection |
| CN110378035A (en) * | 2019-07-19 | 2019-10-25 | 南京工业大学 | It is a kind of that soft-measuring modeling method is hydrocracked based on deep learning |
| CN110705283A (en) * | 2019-09-06 | 2020-01-17 | 上海交通大学 | Deep learning method and system based on matching of text laws and regulations and judicial interpretations |
| US20200027026A1 (en) * | 2018-07-23 | 2020-01-23 | Caci, Inc. - Federal | Methods and apparatuses for detecting tamper using machine learning models |
| CN111144499A (en) * | 2019-12-27 | 2020-05-12 | 北京工业大学 | Fan blade early icing fault detection method based on deep neural network |
-
2020
- 2020-05-14 CN CN202010409687.XA patent/CN111930601A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160350919A1 (en) * | 2015-06-01 | 2016-12-01 | Virtual Radiologic Corporation | Medical evaluation machine learning workflows and processes |
| WO2018090657A1 (en) * | 2016-11-18 | 2018-05-24 | 同济大学 | Bp_adaboost model-based method and system for predicting credit card user default |
| US20190188065A1 (en) * | 2017-12-15 | 2019-06-20 | International Business Machines Corporation | Computerized high-speed anomaly detection |
| CN108388503A (en) * | 2018-02-13 | 2018-08-10 | 中体彩科技发展有限公司 | Data-base performance monitoring method, system, equipment and computer readable storage medium |
| US20200027026A1 (en) * | 2018-07-23 | 2020-01-23 | Caci, Inc. - Federal | Methods and apparatuses for detecting tamper using machine learning models |
| CN109194423A (en) * | 2018-08-13 | 2019-01-11 | 中国人民解放军陆军工程大学 | The single-frequency point spectrum prediction method of shot and long term memory models based on optimization |
| CN109271374A (en) * | 2018-10-19 | 2019-01-25 | 国网江苏省电力有限公司信息通信分公司 | A kind of database health scoring method and scoring system based on machine learning |
| CN110378035A (en) * | 2019-07-19 | 2019-10-25 | 南京工业大学 | It is a kind of that soft-measuring modeling method is hydrocracked based on deep learning |
| CN110705283A (en) * | 2019-09-06 | 2020-01-17 | 上海交通大学 | Deep learning method and system based on matching of text laws and regulations and judicial interpretations |
| CN111144499A (en) * | 2019-12-27 | 2020-05-12 | 北京工业大学 | Fan blade early icing fault detection method based on deep neural network |
Non-Patent Citations (1)
| Title |
|---|
| 刘瑞芳: "《程序设计实践（第2版）》", 北京邮电大学出版社, pages: 292 - 295 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112365186A (en) * | 2020-11-27 | 2021-02-12 | 中国电建集团海外投资有限公司 | Health degree evaluation method and system for electric power information system |
| CN113342758A (en) * | 2021-08-06 | 2021-09-03 | 联想凌拓科技有限公司 | Metadata management method, device, equipment and medium of file system |
| CN113342758B (en) * | 2021-08-06 | 2021-11-19 | 联想凌拓科技有限公司 | Metadata management method, device, equipment and medium of file system |
| CN113806453A (en) * | 2021-09-18 | 2021-12-17 | 广东电网有限责任公司 | Automatic confirmation method, device, terminal and medium for scheduling operation ticket comprehensive order |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109271374B (en) | Database health degree scoring method and system based on machine learning | |
| CN112149316B (en) | Aero-engine residual life prediction method based on improved CNN model | |
| CN109492830B (en) | Mobile pollution source emission concentration prediction method based on time-space deep learning | |
| CN111930601A (en) | Deep learning-based database state comprehensive scoring method and system | |
| CN110688288B (en) | Automatic test method, device, equipment and storage medium based on artificial intelligence | |
| CN108009674A (en) | Air PM2.5 concentration prediction methods based on CNN and LSTM fused neural networks | |
| CN108776683A (en) | A kind of electric power operation/maintenance data cleaning method based on isolated forest algorithm and neural network | |
| CN116108758B (en) | Landslide susceptibility evaluation method | |
| CN102609612B (en) | Data fusion method for calibration of multi-parameter instruments | |
| CN109858714B (en) | Tobacco shred quality inspection index prediction method, device and system based on improved neural network | |
| CN112396234A (en) | User side load probability prediction method based on time domain convolutional neural network | |
| CN112418498A (en) | Temperature prediction method and system for intelligent greenhouse | |
| CN113871009A (en) | Sepsis prediction system, storage medium and apparatus in intensive care unit | |
| CN111353640B (en) | Method for constructing wind speed prediction model by combination method | |
| CN114169374A (en) | Cable-stayed bridge stay cable damage identification method and electronic equipment | |
| CN113554213A (en) | Natural gas demand prediction method, system, storage medium and equipment | |
| CN113257425B (en) | Influenza prediction system, storage medium and device for optimizing LSTM and LightGBM parameters | |
| CN113842135A (en) | BilSTM-based sleep breathing abnormality automatic screening method | |
| CN113673774A (en) | Aero-engine remaining life prediction method based on self-encoder and time sequence convolution network | |
| CN111524023A (en) | Greenhouse adjusting method and system | |
| CN111242347A (en) | Bridge management and maintenance aid decision-making system based on historical weight updating | |
| CN113743461B (en) | Unmanned aerial vehicle cluster health degree assessment method and device | |
| CN115512780B (en) | PaCO2 real-time early warning model establishing method and system | |
| CN113688989B (en) | Deep learning network acceleration method, device, equipment and storage medium | |
| CN115856204B (en) | Tunneling working face gas concentration prediction method based on three-dimensional echo state network |
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 |