CN115310705A - Method and device for determining gas emission quantity and computer readable storage medium - Google Patents
Method and device for determining gas emission quantity and computer readable storage medium Download PDFInfo
- Publication number
- CN115310705A CN115310705A CN202210957594.XA CN202210957594A CN115310705A CN 115310705 A CN115310705 A CN 115310705A CN 202210957594 A CN202210957594 A CN 202210957594A CN 115310705 A CN115310705 A CN 115310705A
- Authority
- CN
- China
- Prior art keywords
- gas
- information
- emission quantity
- average
- historical
- 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
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000012549 training Methods 0.000 claims abstract description 40
- 238000010801 machine learning Methods 0.000 claims abstract description 29
- 239000003245 coal Substances 0.000 claims description 20
- 238000012360 testing method Methods 0.000 claims description 16
- 238000000605 extraction Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 13
- 238000007781 pre-processing Methods 0.000 claims description 13
- 238000001914 filtration Methods 0.000 claims description 6
- 230000000737 periodic effect Effects 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 6
- 230000006872 improvement Effects 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 7
- 238000012544 monitoring process Methods 0.000 description 9
- 238000013528 artificial neural network Methods 0.000 description 8
- 238000004519 manufacturing process Methods 0.000 description 5
- 239000011159 matrix material Substances 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000002265 prevention Effects 0.000 description 3
- 238000009423 ventilation Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000005034 decoration Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000010586 diagram 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
- 230000008569 process Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 206010003497 Asphyxia Diseases 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000002203 pretreatment Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Software Systems (AREA)
- Computational Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Databases & Information Systems (AREA)
- Algebra (AREA)
- Operations Research (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Computing Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Health & Medical Sciences (AREA)
- Agronomy & Crop Science (AREA)
- Mining & Mineral Resources (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Animal Husbandry (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Marine Sciences & Fisheries (AREA)
- Probability & Statistics with Applications (AREA)
- Development Economics (AREA)
Abstract
The invention discloses a method and a device for determining gas emission quantity and a computer readable storage medium. Wherein, the method comprises the following steps: acquiring historical gas characteristic information in a preset period; acquiring a gas average emission quantity sequence based on the gas concentration historical information, wherein the gas average emission quantity sequence is a sequence based on the gas average emission quantity under the time step within a preset period; performing machine learning training on a predetermined model based on the gas average emission quantity sequence and the gas historical characteristic information to obtain a first model; and inputting the current characteristic information of the gas into the first model to obtain the gas emission prediction quantity. The invention solves the technical problem that the prediction of gas leakage in the related technology is lack of accuracy.
Description
Technical Field
The invention relates to the field of data processing, in particular to a method and a device for determining gas emission quantity and a computer readable storage medium.
Background
According to the latest statistics of the national mine safety supervision bureau, in China, 4600 underground coal mines exist at present, all underground coal mines face the threat of gas, and no matter high gas mines or low gas mines or outburst mines have the risks of gas accumulation and overrun so as to cause gas explosion, gas combustion or gas suffocation. The gas emission quantity is important basic data of coal mine gas control, gas extraction design and ventilation design, and directly influences the gas concentration of a working face and the gas overrun danger. The traditional gas emission quantity prediction method comprises a source-based prediction method, a mine statistical method and a gas geological method, and the methods have the characteristics of regional and staticized prediction. The prediction result can only represent the whole gas emission level in the production period of a mine or a working face, the change of the gas emission amount of the working face cannot be dynamically reflected in real time, the defects of poor pertinence and low timeliness exist, and the prediction result cannot reflect the gas emission condition of the working face in a certain space at a certain time. With the rapid development of data mining technology and artificial intelligence, artificial intelligence and big data analysis are applied more and more, and a new method is provided for prediction of gas emission quantity. Therefore, a machine learning method in artificial intelligence is introduced into the field of gas emission quantity prediction, deep mining analysis is carried out on gas emission quantity data and gas emission influence factor indexes thereof by using a machine learning thinking method, a correlation model between the interior of historical gas emission quantity data and gas emission factors is obtained, real-time dynamic prediction of the gas emission quantity of a working face is realized, reasonable arrangement of production and gas prevention and control of a mine is guided, and efficient and safe production of a coal mine is guaranteed.
In view of the above problems, no effective solution has been proposed.
Disclosure of Invention
The embodiment of the invention provides a method and a device for determining gas emission quantity and a computer readable storage medium, which are used for at least solving the technical problem that the prediction quantity of gas leakage in the related technology is lack of accuracy.
According to an aspect of the embodiments of the present invention, there is provided a method for determining a gas emission amount, including: acquiring historical characteristic information of gas in a preset period, wherein the historical characteristic information of the gas at least comprises the following steps: historical information of gas concentration and gas concentration influence information, the gas concentration influence information at least includes: the number of coal produced in each shift in the preset period, geological structure information, period pressure coming condition, extraction pure quantity and mine pressure information; acquiring a gas average emission quantity sequence based on the gas concentration historical information, wherein the gas average emission quantity sequence is a sequence based on the gas average emission quantity at a time step within the preset period; performing machine learning training on a preset model based on the gas average emission quantity sequence and the gas historical characteristic information to obtain a first model; and inputting the current characteristic information of the gas into the first model to obtain the gas emission prediction quantity.
Optionally, obtaining a gas average emission quantity sequence based on the gas concentration history information includes: preprocessing the gas concentration historical information, wherein the preprocessing method at least comprises the following steps: filtering gas adjustment data, power-off test data and invalid data caused by sensor faults in the gas concentration historical information; and sequencing the preprocessed gas concentration historical information to generate the gas average emission quantity sequence.
Optionally, obtaining the gas average emission quantity sequence includes: by using
And calculating the gas average emission quantity sequence, wherein F is the average air quantity of a working face, xi is the historical information of the gas concentration at the moment i, u is the number of gas concentration samples at the time step in the preset period, and Q is the gas average emission quantity sequence.
Optionally, performing machine learning training on a predetermined model based on the gas average emission quantity sequence and the gas historical characteristic information to obtain a first model, including: inputting the gas average emission quantity sequence and the gas historical characteristic information into a preset model to obtain training prediction data samples through a forward direction propagation algorithm of a machine learning algorithm, and calculating deviation errors of prediction data and actual data based on the training prediction data samples; and improving the preset model by utilizing a time back propagation algorithm based on the deviation error, so that the deviation error is gradually reduced until the error is smaller than an expected value, and acquiring the first model.
According to another aspect of the embodiments of the present invention, there is also provided a device for determining a gas emission amount, including: the first acquisition module is used for acquiring historical gas characteristic information in a preset period, wherein the historical gas characteristic information at least comprises: historical information of gas concentration and gas concentration influence information, the gas concentration influence information at least includes: the number of coal produced in each shift in the preset period, geological structure information, period pressure coming condition, extraction pure quantity and mine pressure information; a second obtaining module, configured to obtain a gas average emission quantity sequence based on the gas concentration history information, where the gas average emission quantity sequence is a sequence based on gas average emission quantities at a time step within the predetermined period; the third acquisition module is used for performing machine learning training on a preset model based on the gas average emission quantity sequence and the gas historical characteristic information to obtain a first model; and the fourth acquisition module is used for inputting the current characteristic information of the gas into the first model and acquiring the gas emission prediction quantity.
Optionally, the second obtaining module includes: the preprocessing unit is used for preprocessing the gas concentration historical information, wherein the preprocessing method at least comprises the following steps: filtering gas adjusting data, power-off test data and invalid data caused by sensor faults in the gas concentration historical information; and the generating unit is used for sequencing the preprocessed gas concentration historical information and generating the gas average emission quantity sequence.
Optionally, the second obtaining module includes: a computing unit for employing
And calculating the gas average emission quantity sequence, wherein F is the average air quantity of a working surface, xi is the historical information of the gas concentration at the moment i, u is the number of gas concentration samples at the time step in the preset period, and Q is the gas average emission quantity sequence.
Optionally, the third obtaining module includes: the input unit is used for inputting the gas average emission quantity sequence and the gas historical characteristic information into a preset model to obtain training prediction data samples through a forward direction propagation algorithm of a machine learning algorithm, and calculating deviation errors of prediction data and actual data based on the training prediction data samples; and the improvement unit is used for improving the preset model by utilizing a time back propagation algorithm based on the deviation error, so that the deviation error is gradually reduced until the error is smaller than an expected value, and acquiring the first model.
According to another aspect of the embodiment of the present invention, there is also provided a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is executed by a processor, the computer program controls a device in which the computer-readable storage medium is located to execute any one of the above methods for determining gas emission quantity.
According to another aspect of the embodiment of the present invention, there is also provided a processor, configured to execute a computer program, where the computer program executes to perform the method for determining a gas emission amount according to any one of the above.
In the embodiment of the present invention, historical characteristic information of gas in a predetermined period is obtained, where the historical characteristic information of gas at least includes: historical information of gas concentration and gas concentration influence information, the gas concentration influence information includes at least: the method comprises the steps of obtaining coal quantity, geological structure information, periodic incoming pressure condition, extraction pure quantity and mine pressure information in a predetermined period in a shift mode; acquiring a gas average emission quantity sequence based on the gas concentration historical information, wherein the gas average emission quantity sequence is a sequence based on the gas average emission quantity under the time step within a preset period; performing machine learning training on a predetermined model based on the gas average emission quantity sequence and the gas historical characteristic information to obtain a first model; and inputting the current characteristic information of the gas into the first model to obtain the gas emission prediction quantity. By the method for determining the gas emission quantity, the purpose of predicting the gas emission prediction quantity by utilizing a deep learning training gas prediction model after obtaining the average gas emission quantity sequence based on the historical characteristic information of the gas in the preset period is achieved, so that the technical effect of improving the accuracy of the gas leakage prediction quantity is achieved, and the technical problem that the accuracy of the gas leakage prediction quantity in the related technology is poor is solved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
fig. 1 is a flowchart of a determination method of a gas emission amount according to an embodiment of the present invention;
fig. 2 is a flow chart of a preferred method of determining gas emission in accordance with an embodiment of the present invention;
fig. 3 is a schematic diagram of a gas emission amount determination device according to an embodiment of the present invention.
Detailed Description
In order to make those skilled in the art better understand the technical solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in other sequences than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
According to an embodiment of the present invention, there is provided a method for determining a gas emission amount, where the steps shown in the flowchart of the attached drawings can be executed in a computer system, such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown or described herein.
Fig. 1 is a flowchart of a method for determining a gas emission amount according to an embodiment of the present invention, as shown in fig. 1, the method including the steps of:
step S102, acquiring historical characteristic information of gas in a preset period, wherein the historical characteristic information of gas at least comprises the following steps: historical information of gas concentration and gas concentration influence information, the gas concentration influence information at least includes: the method comprises the steps of obtaining coal quantity, geological structure information, periodic incoming pressure condition, extraction pure quantity and mine pressure information in a predetermined period in a shift mode;
in the above steps, the gas history characteristic information includes, but is not limited to: the system comprises a gas content index, a gas pressure index, a gas emission quantity index, a geological structure index, a coal seam occurrence index, a gas extraction index, a gas concentration index, a mine pressure monitoring index, a stress monitoring index, an outburst prevention prediction index, a coal body strength index, a ventilation monitoring index, an atmospheric pressure index, a production strength index and the like.
Step S104, acquiring a gas average emission quantity sequence based on the gas concentration historical information, wherein the gas average emission quantity sequence is a sequence based on the gas average emission quantity under the time step within a preset period;
as an optional embodiment, the obtaining of the gas average emission quantity sequence based on the gas concentration historical information includes: preprocessing the gas concentration historical information, wherein the preprocessing method at least comprises the following steps: filtering gas adjustment data, power-off test data and invalid data caused by sensor faults in the historical information of the gas concentration; and sequencing the preprocessed gas concentration historical information to generate a gas average emission quantity sequence.
As an alternative embodiment, the step of obtaining the gas average emission quantity sequence comprises the following steps: by using
And calculating a gas average emission quantity sequence, wherein F is the average air quantity of the working face, xi is the history information of the gas concentration at the moment i, u is the number of gas concentration samples at the time step within a preset period, and Q is the gas average emission quantity sequence.
It should be noted that, the gas concentration sample number acquisition time is assumed to be the same as the gas concentration acquisition time interval.
For example, a stope face early shift 8 to 16: the gas concentration data during 00 period is: 0.05%, 0.13%, 0.39%, 0.26%, 0.14%, 0.32%, 0.15%, 0.11%, 0.07%, 0.11%, the gas concentration data acquisition interval time is the same, the average air volume of the working face is 450m3/min, and then the average gas emission amount of the shift is Q =450/100 (0.05 +0.13+0.39+0.26+0.14+0.32+0.15+0.11+0.07+ 0.11)/10 =0.82m3/min
Step S106, performing machine learning training on a preset model based on the gas average emission quantity sequence and the gas historical characteristic information to obtain a first model;
as an optional embodiment, the machine learning training is performed on the predetermined model based on the gas average emission quantity sequence and the gas historical characteristic information, so as to obtain a first model, and the method includes: inputting the average gas emission quantity sequence and the historical gas characteristic information into a preset model to obtain training prediction data samples through a forward direction propagation algorithm of a machine learning algorithm, and calculating deviation errors of prediction data and actual data based on the training prediction data samples; and improving the preset model by using a time back propagation algorithm based on the deviation error, so that the deviation error is gradually reduced until the error is smaller than an expected value, and acquiring the first model.
It should be noted that the machine learning algorithm mainly includes, but is not limited to: LSTM artificial neural network, RNN artificial neural network, SVM support vector machine, K-means algorithm and naive Bayes algorithm.
S1062: inputting the training data samples (Z, Y) into a machine learning algorithm, such as a long-short time artificial neural network (LSTM), obtaining training prediction data samples Yp through forward propagation of the long-short time neural network, and calculating deviation errors of prediction data and actual data.
And S1064, continuously improving parameters of the prediction model by using a time back propagation algorithm, so as to enable the error between the predicted value and the actual value to be gradually reduced until the error is smaller than an expected value, stopping training, and obtaining a gas emission quantity prediction model.
A gas emission quantity prediction method based on machine learning is characterized in that prediction errors in step S8 include average absolute errors, average relative errors and root mean square errors.
Wherein the average absolute error Sa can be calculated by the following formula:
wherein: ai is the actual gas concentration time value at the ith moment,
and the predicted value is the gas concentration at the ith moment.
The average relative error Sb can be calculated by the following equation:
the root mean square error Sc is calculated using the following equation:
and S108, inputting the current characteristic information of the gas into the first model to obtain the gas emission prediction quantity.
Fig. 2 is a flowchart of a preferred method for determining a gas emission amount according to an embodiment of the present invention, and as shown in fig. 2, the method for determining a gas emission amount is described in detail below:
s1: obtaining a working surfaceMonitoring time series data of gas concentration in the last half year, and preprocessing the gas concentration data to form a gas concentration time series
Wherein
The method is characterized in that the method represents the sampling time of the gas concentration, x1, x2, \ 8230;, xv represents the gas concentration, and v represents the number of gas concentration samples.
S2: collecting the characteristic information of gas emission influence factors such as the working face shift coal output amount, the geological structure condition, the period incoming pressure condition, the extraction pure amount, the mine pressure monitoring and the like in the last half year, and forming a gas influence characteristic time sequence matrix B = { (T1, B1, c1, d1, \8230;) T, (T2, B2, c2, d2, \8230;) T, \8230; (tj, bj, cj, dj, \8230;) T), }. Wherein t1, t2, \8230andtj represent different operation shifts; b1, b2, c1, c2, bj, c 8230, cj, d1, d2, 8230, and dj respectively represent characteristic values of different types of gas emission influence factors at different times.
S3: and (3) sorting and classifying the gas concentration data according to the operation shifts, and calculating the average gas emission amount of the shift to form a gas emission amount time sequence C = { (t 1, a 1), (t 2, a 2) \8230 } (tn, an) }. Wherein a1, a2, \ 8230and an indicates the average gas emission amount of each shift corresponding to different time shifts.
S4: the gas emission quantity time sequence and the characteristic information of the gas emission influence factor of each operation shift of the working surface are collated to form a gas emission quantity prediction basic data matrix X, and a characteristic time sequence of the historical gas emission quantity of the working surface is formed, wherein,
s5: setting a gas emission quantity prediction time step l, constructing a gas emission quantity prediction time sequence Y, wherein,
and S6, dividing the basic data sequence X of the characteristic prediction of the gas emission quantity into training data and testing data according to the proportion of 8. And recording basic training data of gas emission quantity prediction as Z and test data as W, wherein m =0.8n, wherein,
s7: and taking the test data set as a model input layer, and training the gas emission quantity prediction model by using a machine learning algorithm to obtain the gas emission quantity prediction model.
S8: and applying the trained gas emission quantity prediction model to a test data set (W, Z), calculating the prediction error of the test data set, and obtaining a final gas emission quantity prediction model if the error is smaller than an expected value. And if the error is larger than the expected value, returning to the fifth step for retraining.
S9: and predicting the gas emission quantity of the working face by using the obtained gas emission quantity prediction model.
As can be seen from the above, in the embodiment of the present invention, first, historical characteristic information of the gas in a predetermined period may be obtained, where the historical characteristic information of the gas at least includes: historical information of gas concentration and gas concentration influence information, the gas concentration influence information at least includes: the method comprises the steps of obtaining coal quantity, geological structure information, periodic incoming pressure condition, extraction pure quantity and mine pressure information in a predetermined period in a shift mode; then, a gas average emission quantity sequence can be obtained based on the gas concentration historical information, wherein the gas average emission quantity sequence is a sequence based on the gas average emission quantity under the time step within a preset period; then, machine learning training can be carried out on the preset model based on the gas average emission quantity sequence and the gas historical characteristic information to obtain a first model; and finally, inputting the current characteristic information of the gas into the first model to obtain the gas emission prediction quantity. By the method for determining the gas emission quantity, the purpose of predicting the gas emission prediction quantity by utilizing a deep learning training gas prediction model after obtaining the average gas emission quantity sequence based on the historical characteristic information of the gas in the preset period is achieved, so that the technical effect of improving the accuracy of the gas leakage prediction quantity is achieved, and the technical problem that the accuracy of the gas leakage prediction quantity in the related technology is poor is solved.
According to another aspect of the embodiment of the present invention, there is also provided a device for determining a gas emission amount, and fig. 3 is a schematic diagram of the device for determining a gas emission amount according to the embodiment of the present invention, as shown in fig. 3, including: a first obtaining module 31, a second obtaining module 33, a third obtaining module 35 and a fourth obtaining module 37. The following describes a device for determining the gas emission amount.
A first obtaining module 31, configured to obtain historical gas characteristic information in a predetermined period, where the historical gas characteristic information at least includes: historical information of gas concentration and gas concentration influence information, the gas concentration influence information at least includes: the method comprises the steps of obtaining coal quantity, geological structure information, periodic incoming pressure condition, extraction pure quantity and mine pressure information in a predetermined period in a shift mode;
in the above steps, the gas history characteristic information includes, but is not limited to: the system comprises a gas content index, a gas pressure index, a gas emission quantity index, a geological structure index, a coal seam occurrence index, a gas extraction index, a gas concentration index, a mine pressure monitoring index, a stress monitoring index, an outburst prevention prediction index, a coal body strength index, a ventilation monitoring index, an atmospheric pressure index, a production strength index and the like.
A second obtaining module 33, configured to obtain a gas average emission quantity sequence based on the gas concentration history information, where the gas average emission quantity sequence is a sequence based on the gas average emission quantity at a time step within a predetermined period;
as an alternative embodiment, the second obtaining module includes: the pretreatment unit is used for pretreating the gas concentration historical information, wherein the pretreatment method at least comprises the following steps: filtering gas adjustment data, power-off test data and invalid data caused by sensor faults in the historical information of the gas concentration; and the generating unit is used for sequencing the preprocessed gas concentration historical information to generate a gas average emission quantity sequence.
As an alternative embodiment, the second obtaining module includes: a computing unit for employing
And calculating a gas average emission quantity sequence, wherein F is the average air quantity of the working face, xi is the historical information of the gas concentration at the moment i, u is the number of gas concentration samples at the time step within a preset period, and Q is the gas average emission quantity sequence.
A third obtaining module 35, configured to perform machine learning training on the predetermined model based on the gas average emission quantity sequence and the gas historical characteristic information, to obtain a first model;
as an alternative embodiment, the third obtaining module includes: the input unit is used for inputting the gas average emission quantity sequence and the gas historical characteristic information into a preset model to obtain training prediction data samples through a forward direction propagation algorithm of a machine learning algorithm, and calculating deviation errors of prediction data and actual data based on the training prediction data samples; and the improvement unit is used for improving the preset model by utilizing a time back propagation algorithm based on the deviation error, so that the deviation error is gradually reduced until the error is smaller than an expected value, and obtaining the first model.
It should be noted that the machine learning algorithm mainly includes, but is not limited to: LSTM artificial neural network, RNN artificial neural network, SVM support vector machine, K-means algorithm and naive Bayes algorithm.
S1062: inputting the training data samples (Z, Y) into a machine learning algorithm, such as a long-short time artificial neural network (LSTM), obtaining training prediction data samples Yp through forward propagation of the long-short time artificial neural network, and calculating deviation errors of prediction data and actual data.
And S1064, continuously improving parameters of the prediction model by using a time back propagation algorithm, so as to enable the error between the predicted value and the actual value to be gradually reduced until the error is smaller than an expected value, stopping training, and obtaining a gas emission quantity prediction model.
A gas emission quantity prediction method based on machine learning is characterized in that prediction errors in step S8 include average absolute errors, average relative errors and root mean square errors.
Wherein the average absolute error Sa can be calculated by the following formula:
wherein: ai is the actual gas concentration time value at the ith moment,
and (4) the gas concentration predicted value at the ith moment.
The average relative error Sb can be calculated by the following equation:
the root mean square error Sc is calculated using the following equation:
and a fourth obtaining module 37, configured to input the current characteristic information of the gas into the first model, and obtain the gas emission prediction amount.
It should be noted that the first acquiring module 31, the second acquiring module 33, the third acquiring module 35, and the fourth acquiring module 37 correspond to steps S102 to S108 in embodiment 1, and the modules are the same as the corresponding steps in the implementation example and the application scenario, but are not limited to the disclosure in embodiment 1. It should be noted that the modules described above as part of the apparatus may be implemented in a computer system such as a set of computer executable instructions.
Fig. 2 is a flowchart of a preferred method for determining a gas emission amount according to an embodiment of the present invention, and as shown in fig. 2, the method for determining a gas emission amount is described in detail below:
s1: last half year of face acquisitionThe gas concentration monitoring time sequence data are preprocessed to form a gas concentration time sequence
Wherein
The method comprises the steps of sampling time of gas concentration, x1, x2, \8230, wherein xv represents gas concentration, and v represents the number of gas concentration samples.
S2: collecting the characteristic information of gas emission influence factors such as the working face shift coal output amount, the geological structure condition, the period incoming pressure condition, the extraction pure amount, the mine pressure monitoring and the like in the last half year, and forming a gas influence characteristic time sequence matrix B = { (T1, B1, c1, d1, \8230;) T, (T2, B2, c2, d2, \8230;) T, \8230; (tj, bj, cj, dj, \8230;) T), }. Wherein t1, t2, \8230andtj represent different operation shifts; b1, b2, c1, c2, 8230, cj, d1, d2, 8230and dj respectively represent characteristic values of different types of gas emission influence factors at different times.
S3: and (3) sorting and classifying the gas concentration data according to the operation shifts, and calculating the average gas emission amount of the shift to form a gas emission amount time sequence C = { (t 1, a 1), (t 2, a 2) \8230 { (tn, an) }. Wherein a1, a2, \8230andan represents average gas emission quantity of different time shifts.
S4: the gas emission quantity time sequence and the characteristic information of the gas emission influence factor of each operation shift of the working surface are collated to form a gas emission quantity prediction basic data matrix X, and a characteristic time sequence of the historical gas emission quantity of the working surface is formed, wherein,
s5: setting a gas emission quantity prediction time step l, constructing a gas emission quantity prediction time sequence Y, wherein,
and S6, dividing the basic data sequence X of the characteristic prediction of the gas emission quantity into training data and testing data according to the proportion of 8. And recording basic training data of gas emission quantity prediction as Z and test data as W, wherein m =0.8n, wherein,
s7: and (4) taking the test data set as a model input layer, and training the gas emission quantity prediction model by using a machine learning algorithm to obtain the gas emission quantity prediction model.
S8: and applying the trained gas emission quantity prediction model to a test data set (W, Z), calculating the prediction error of the test data set, and obtaining a final gas emission quantity prediction model if the error is smaller than an expected value. And if the error is larger than the expected value, returning to the fifth step for retraining.
S9: and predicting the gas emission quantity of the working face by using the obtained gas emission quantity prediction model.
As can be seen from the above, in the embodiment of the present invention, first, the first obtaining module 21 may obtain the gas history characteristic information in a predetermined period, where the gas history characteristic information at least includes: historical information of gas concentration and gas concentration influence information, the gas concentration influence information at least includes: the method comprises the steps of obtaining coal quantity, geological structure information, periodic incoming pressure condition, extraction pure quantity and mine pressure information in a predetermined period in a shift mode; then, acquiring a gas average emission quantity sequence based on the gas concentration historical information by means of a second acquisition module 23, wherein the gas average emission quantity sequence is a sequence based on the gas average emission quantity at a time step within a preset period; then, machine learning training is carried out on the preset model based on the gas average emission quantity sequence and the gas historical characteristic information by means of a third acquisition module 25, and a first model is obtained; and finally, inputting the current characteristic information of the gas into the first model by means of a fourth acquisition module 27 to acquire the gas emission prediction quantity. By the method for determining the gas emission quantity, the purpose of predicting the gas emission prediction quantity by utilizing the deep learning training gas prediction model after obtaining the average gas emission quantity sequence based on the historical characteristic information of the gas in the preset period is achieved, so that the technical effect of improving the accuracy of the gas leakage prediction quantity is achieved, and the technical problem that the accuracy of the gas leakage prediction quantity in the related technology is poor is solved.
In summary, the method provided by the embodiment of the invention can obtain the internal part of the historical gas emission quantity data and the correlation model between the internal part and the gas emission factor of the historical gas emission quantity data by deep mining analysis of the gas emission quantity data and the gas emission influence factor indexes thereof on the premise of not increasing the mine gas sensor and the gas emission prediction engineering quantity, thereby realizing real-time dynamic prediction of the gas emission quantity of the working face. The utilization value of the gas emission quantity and historical data of relevant gas emission influence factors is greatly improved, the coal mine can be effectively guided to be reasonably produced and deployed, a gas control plan is made in advance, and gas overrun and gas disaster accidents are avoided.
According to another aspect of the embodiments of the present invention, there is also provided a computer-readable storage medium including a stored computer program, wherein when the computer program is executed by a processor, the apparatus on which the computer-readable storage medium is located is controlled to execute the method for determining the gas emission amount in any one of the above.
According to another aspect of the embodiment of the present invention, there is also provided a processor, configured to execute a computer program, where the computer program executes to perform the method for determining the gas emission amount in any one of the above.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described apparatus embodiments are merely illustrative, and for example, the division of the units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or may not be executed. In addition, the shown or discussed coupling or direct coupling or communication connection between each other may be an indirect coupling or communication connection through some interfaces, units or modules, and may be electrical or in other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one position, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (10)
1. A method for determining a gas emission quantity is characterized by comprising the following steps:
acquiring historical characteristic information of gas in a preset period, wherein the historical characteristic information of the gas at least comprises the following steps: historical information of gas concentration and gas concentration influence information, the gas concentration influence information at least includes: the number of coal produced in each shift in the preset period, geological structure information, period pressure coming condition, extraction pure quantity and mine pressure information;
acquiring a gas average emission quantity sequence based on the gas concentration historical information, wherein the gas average emission quantity sequence is a sequence based on the gas average emission quantity at a time step within the preset period;
performing machine learning training on a preset model based on the gas average emission quantity sequence and the gas historical characteristic information to obtain a first model;
and inputting the current characteristic information of the gas into the first model to obtain the gas emission prediction quantity.
2. The method of claim 1, wherein obtaining a gas average emission quantity sequence based on the gas concentration historical information comprises:
preprocessing the gas concentration historical information, wherein the preprocessing method at least comprises the following steps: filtering gas adjustment data, power-off test data and invalid data caused by sensor faults in the gas concentration historical information;
and sequencing the preprocessed gas concentration historical information to generate the gas average emission quantity sequence.
3. The method of claim 1, wherein obtaining the sequence of average gas emission quantities comprises:
by using
Calculating the average gas emission quantity sequence, wherein F is the average air quantity of the working face, and x i And the historical information of the gas concentration at the moment i, u is the number of gas concentration samples in the time step in the preset period, and Q is the average gas emission quantity sequence.
4. The method of claim 1, wherein performing machine learning training on a predetermined model based on the gas average emission quantity sequence and the gas historical characteristic information to obtain a first model comprises:
inputting the gas average emission quantity sequence and the gas historical characteristic information into a preset model to obtain training prediction data samples through a forward direction propagation algorithm of a machine learning algorithm, and calculating deviation errors of prediction data and actual data based on the training prediction data samples;
and improving the preset model by utilizing a time back propagation algorithm based on the deviation error, so that the deviation error becomes smaller gradually until the error is smaller than an expected value, and obtaining the first model.
5. A gas emission amount determination device is characterized by comprising:
the first acquisition module is used for acquiring historical characteristic information of gas in a preset period, wherein the historical characteristic information of gas at least comprises the following components: historical information of gas concentration and gas concentration influence information, the gas concentration influence information at least includes: the number of coal produced in each shift, geological structure information, periodic incoming pressure condition, extraction pure quantity and mine pressure information in the preset period;
a second obtaining module, configured to obtain a gas average emission quantity sequence based on the gas concentration history information, where the gas average emission quantity sequence is a sequence based on gas average emission quantities at a time step within the predetermined period;
the third acquisition module is used for performing machine learning training on a preset model based on the gas average emission quantity sequence and the gas historical characteristic information to obtain a first model;
and the fourth acquisition module is used for inputting the current characteristic information of the gas into the first model and acquiring the gas emission prediction quantity.
6. The apparatus of claim 5, wherein the second obtaining module comprises:
the preprocessing unit is used for preprocessing the gas concentration historical information, wherein the preprocessing method at least comprises the following steps: filtering gas adjusting data, power-off test data and invalid data caused by sensor faults in the gas concentration historical information;
and the generating unit is used for sequencing the preprocessed gas concentration historical information and generating the gas average emission quantity sequence.
7. The apparatus of claim 5, wherein the second obtaining module comprises:
a computing unit for employing
Calculating the average gas emission quantity sequence, wherein F is the average air quantity of the working face, and x i And the historical information of the gas concentration at the moment i, u is the number of gas concentration samples in the time step within the preset period, and Q is the average gas emission quantity sequence.
8. The apparatus of claim 5, wherein the third obtaining module comprises:
the input unit is used for inputting the gas average emission quantity sequence and the gas historical characteristic information into a preset model to obtain training prediction data samples through a forward direction propagation algorithm of a machine learning algorithm, and calculating deviation errors of prediction data and actual data based on the training prediction data samples;
and the improvement unit is used for improving the preset model by utilizing a time back propagation algorithm based on the deviation error, so that the deviation error is gradually reduced until the error is smaller than an expected value, and acquiring the first model.
9. A computer-readable storage medium, comprising a stored computer program, wherein when the computer program is executed by a processor, the computer-readable storage medium controls an apparatus to execute the method for determining a gas emission amount according to any one of claims 1 to 4.
10. A processor for executing a computer program, wherein the computer program executes to perform the method for determining a gas emission amount according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210957594.XA CN115310705A (en) | 2022-08-10 | 2022-08-10 | Method and device for determining gas emission quantity and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210957594.XA CN115310705A (en) | 2022-08-10 | 2022-08-10 | Method and device for determining gas emission quantity and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115310705A true CN115310705A (en) | 2022-11-08 |
Family
ID=83861381
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210957594.XA Pending CN115310705A (en) | 2022-08-10 | 2022-08-10 | Method and device for determining gas emission quantity and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115310705A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116738226A (en) * | 2023-05-26 | 2023-09-12 | 北京龙软科技股份有限公司 | Gas emission quantity prediction method based on self-interpretable attention network |
-
2022
- 2022-08-10 CN CN202210957594.XA patent/CN115310705A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116738226A (en) * | 2023-05-26 | 2023-09-12 | 北京龙软科技股份有限公司 | Gas emission quantity prediction method based on self-interpretable attention network |
| CN116738226B (en) * | 2023-05-26 | 2024-03-12 | 北京龙软科技股份有限公司 | Gas emission quantity prediction method based on self-interpretable attention network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107463633B (en) | A kind of real time data rejecting outliers method based on EEMD- neural network | |
| CN112528519A (en) | Method, system, readable medium and electronic device for engine quality early warning service | |
| CN111814956B (en) | Multi-task learning air quality prediction method based on multi-dimensional secondary feature extraction | |
| CN110874744B (en) | Data anomaly detection method and device | |
| CN109739905A (en) | A kind of pipe gallery fire alarm method and system | |
| CN112308306A (en) | Multi-mode input coal and gas outburst risk prediction method | |
| CN116341901B (en) | Integrated evaluation method for landslide surface domain-monomer hazard early warning | |
| CN115310705A (en) | Method and device for determining gas emission quantity and computer readable storage medium | |
| CN109254219A (en) | A kind of distribution transforming transfer learning method for diagnosing faults considering multiple factors Situation Evolution | |
| CN113807951A (en) | Transaction data trend prediction method and system based on deep learning | |
| CN113723535A (en) | CycleGAN deep learning-based cell micronucleus image processing method and storage medium | |
| CN112668749B (en) | Coal mine gas early warning method based on class mark weighting extreme learning machine | |
| CN116861306A (en) | Abnormal electricity utilization detection method based on electricity utilization trend quantification network | |
| CN115033591A (en) | Intelligent detection method and system for electricity charge data abnormity, storage medium and computer equipment | |
| CN112101482B (en) | Method for detecting abnormal parameter mode of missing satellite data | |
| CN116738214B (en) | Data dimension reduction preprocessing method based on high-order tensor | |
| CN117152918A (en) | Dangerous dynamic early warning method applied to regional landslide disaster | |
| CN111210085A (en) | Coal mine gas concentration early warning method based on multi-view ensemble learning | |
| CN116562120A (en) | RVE-based turbine engine system health condition assessment method and RVE-based turbine engine system health condition assessment device | |
| CN115659271A (en) | Sensor abnormality detection method, model training method, system, device, and medium | |
| CN113987929A (en) | Coal seam permeability change prediction method based on FA-SSA-SVM algorithm | |
| CN113792828A (en) | Power grid load prediction method, system, equipment and medium based on deep learning | |
| CN113569324A (en) | Slope deformation monitoring abnormal data analysis and optimization method | |
| CN112560252A (en) | Prediction method for residual life of aircraft engine | |
| CN116611004B (en) | Coal mine safety disaster prediction model training method, early warning method and early warning system |
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 |