CN116841269A - Process adjustment method, system and storage medium based on coal tar production flow - Google Patents
Process adjustment method, system and storage medium based on coal tar production flow Download PDFInfo
- Publication number
- CN116841269A CN116841269A CN202310920043.0A CN202310920043A CN116841269A CN 116841269 A CN116841269 A CN 116841269A CN 202310920043 A CN202310920043 A CN 202310920043A CN 116841269 A CN116841269 A CN 116841269A
- Authority
- CN
- China
- Prior art keywords
- coal tar
- model
- real
- completion
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 299
- 239000011280 coal tar Substances 0.000 title claims abstract description 174
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 58
- 238000003860 storage Methods 0.000 title claims abstract description 16
- 238000012545 processing Methods 0.000 claims abstract description 105
- 238000012549 training Methods 0.000 claims abstract description 89
- 238000005516 engineering process Methods 0.000 claims abstract description 45
- 239000002994 raw material Substances 0.000 claims abstract description 45
- 238000012544 monitoring process Methods 0.000 claims abstract description 29
- 238000007670 refining Methods 0.000 claims abstract description 7
- 238000004364 calculation method Methods 0.000 claims description 45
- 238000012795 verification Methods 0.000 claims description 18
- 238000013528 artificial neural network Methods 0.000 claims description 17
- 238000007405 data analysis Methods 0.000 claims description 11
- 238000001514 detection method Methods 0.000 claims description 7
- 238000013507 mapping Methods 0.000 claims description 3
- 239000000047 product Substances 0.000 abstract description 69
- 238000005265 energy consumption Methods 0.000 abstract description 3
- 230000007613 environmental effect Effects 0.000 abstract description 3
- 239000012467 final product Substances 0.000 abstract description 3
- 238000004821 distillation Methods 0.000 description 4
- 239000000571 coke Substances 0.000 description 3
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 2
- 238000003763 carbonization Methods 0.000 description 2
- 239000003245 coal Substances 0.000 description 2
- 238000004132 cross linking Methods 0.000 description 2
- 230000010365 information processing Effects 0.000 description 2
- 210000003127 knee Anatomy 0.000 description 2
- 239000004484 Briquette Substances 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000011230 binding agent Substances 0.000 description 1
- 239000006229 carbon black Substances 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005194 fractionation Methods 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 239000000295 fuel oil Substances 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 238000002347 injection Methods 0.000 description 1
- 239000007924 injection Substances 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 239000003921 oil Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
- 239000003171 wood protecting agent Substances 0.000 description 1
Classifications
-
- C—CHEMISTRY; METALLURGY
- C10—PETROLEUM, GAS OR COKE INDUSTRIES; TECHNICAL GASES CONTAINING CARBON MONOXIDE; FUELS; LUBRICANTS; PEAT
- C10C—WORKING-UP PITCH, ASPHALT, BITUMEN, TAR; PYROLIGNEOUS ACID
- C10C1/00—Working-up tar
- C10C1/04—Working-up tar by distillation
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/41885—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by modeling, simulation of the manufacturing system
-
- 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
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/32—Operator till task planning
- G05B2219/32339—Object oriented modeling, design, analysis, implementation, simulation language
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Oil, Petroleum & Natural Gas (AREA)
- Manufacturing & Machinery (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Organic Chemistry (AREA)
- Materials Engineering (AREA)
- Quality & Reliability (AREA)
- Automation & Control Theory (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a process adjustment method, a system and a storage medium based on a coal tar production flow, which relate to the technical field of coal tar production and comprise the following steps: acquiring performance parameters of coal tar raw materials; determining a coal tar processing technology; training and determining a prediction model of a distillate product of a coal tar processing technology; carrying out coal tar production; monitoring the coal tar production process in real time to obtain real-time monitoring data; acquiring real-time process completion data; comprehensively analyzing the quality of each distilled product; and adjusting the subsequent refining processing technology of each distillate product based on the quality of each distillate product. The invention has the advantages that: by combining the operation of workers and the process parameters in the coal tar production process, the quality stability of the final product produced by the coal tar can be effectively ensured, and the production and processing of various coal tar with high quality, low energy consumption and high environmental protection are realized.
Description
Technical Field
The invention relates to the technical field of coal tar production, in particular to a process adjustment method, a process adjustment system and a storage medium based on a coal tar production flow.
Background
Coal tar is black or black brown viscous liquid with pungent odor generated during carbonization of coal. The coal tar can be divided into low-temperature coal tar, medium-temperature coal tar and high-temperature coal tar according to carbonization temperature, and the coal tar obtained in coke production belongs to the high-temperature coal tar. It is one of coke oven gas purifying products condensed and separated in the course of cooling raw gas. Coal tar is generally used as a raw material for processing and refining to prepare various chemical products, can be directly used as a material component of a binder for industrial briquette, formed coke and coal activated carbon, and can also be used as a raw material of fuel oil, blast furnace injection fuel, wood preservative oil and carbon black.
Coal tar is a complex mixture of tens of thousands of components from which about 500 or more individual compounds have been isolated and identified. The main research directions of coal tar processing are increasing product variety, improving product quality grade, saving energy and protecting environment, in the process of coal tar fractionation, the operation steps of each procedure can affect the quality of the distilled product, the prior art lacks to comprehensively analyze the quality of the distilled product aiming at each parameter in the coal tar production flow, and is difficult to pertinently adjust the subsequent refining processing technology aiming at the components of the distilled product, so that the quality of the product produced by the coal tar is unstable.
Disclosure of Invention
In order to solve the technical problems, the technical scheme provides a process adjustment method, a system and a storage medium based on a coal tar production flow, and solves the problems that the prior art lacks to comprehensively analyze the quality of a distilled product aiming at various parameters in the coal tar production flow, and is difficult to purposefully adjust a subsequent refining processing process aiming at the components of the distilled product, so that the quality of the product produced by the coal tar is unstable.
In order to achieve the above purpose, the invention adopts the following technical scheme:
a process adjustment method based on a coal tar production flow comprises the following steps:
performing performance detection on the coal tar raw material to obtain performance parameters of the coal tar raw material;
determining the grade of the coal tar raw material based on the performance parameters of the coal tar raw material, and determining the coal tar processing technology based on the grade of the coal tar raw material;
training based on historical processing parameters of a coal tar processing process to determine a prediction model of a distillate product of the coal tar processing process, wherein the prediction model of the distillate product of the coal tar processing process takes process completion data in a coal tar production flow as input and the quality of each distillate product as output;
carrying out coal tar production according to a determined coal tar processing technology;
monitoring the coal tar production process in real time to obtain real-time monitoring data;
comprehensively analyzing and calculating process completion data based on the real-time monitoring data to obtain real-time process completion data;
inputting real-time process completion data into a prediction model of a distillate product of the coal tar processing process, and comprehensively analyzing the quality of each distillate product;
and adjusting the subsequent refining processing technology of each distillate product based on the quality of each distillate product.
Preferably, the process completion degree data calculating method comprises the following steps:
performing comprehensive calculation on the completion weight index of the process procedure based on the acquired real-time operation images of operators in each procedure;
substituting the acquired real-time process parameters of the process and the standard parameters of the process into a parameter fitting degree calculation formula to calculate parameter fitting indexes of the process;
based on the completion weight index of the process and the parameter fitting index of the process, comprehensively calculating the process completion of the process according to a completion calculation formula;
the parameter fitting degree calculation formula specifically comprises the following steps:
wherein C is the process completion of the process, n is the total number of parameters of the process, alpha i Is the important weight value of the ith parameter of the process procedure, x i Real-time process parameter, x, being the ith parameter of the process sequence i0 Is a standard parameter for the ith parameter of the process.
Preferably, the step of performing comprehensive calculation on the completion weight index of the process based on the collected real-time operation image of the operator in each process specifically includes:
determining a standard operation image of an operator in each procedure, and extracting standard action skeleton points of the operator from the standard operation image;
extracting real-time action skeleton points of an operator from a real-time operation image of the operator;
based on a matching weight formula, calculating the matching weight between the real-time action skeleton points of the operators and the standard action skeleton points of the operators, namely, the completion weight index of the process procedure;
the matching weight formula specifically comprises the following steps:
wherein K is the completion weight index of the process, m is the total number of action skeleton points, and delta (P j ,P j0 ) The value range of the fitting function between the j-th real-time action skeleton point of the operator and the j-th standard action skeleton point of the operator is [0,1 ]]The j-th real-time action skeleton point P of the operator is described as the larger the function value of the fitting function j J standard action skeleton point P with operator j0 The greater the distance between them.
Preferably, the completion degree calculation formula specifically includes:
J=K×C
wherein J is the process completion of the process.
Preferably, the prediction model for training and determining the distillate product of the coal tar processing technology based on the historical processing parameters of the coal tar processing technology specifically comprises the following steps:
randomly retrieving a plurality of model training sample data from historical processing parameters of a coal tar processing technology;
respectively obtaining the components of the distilled products of a plurality of each process based on model training sample data, and the process completion degree of each process corresponding to the components;
training a neural network based on model training sample data, taking the process completion degree of each process procedure as a neural network input layer, taking a distillate product corresponding to each procedure as a neural network output layer, and performing node mapping logic of an implicit layer of the training neural network to obtain a preliminary training model;
randomly retrieving a plurality of model verification sample data from historical processing parameters of a coal tar processing technology;
and verifying the preliminary training model by using model verification sample data, judging whether the preliminary training model can meet the component quality prediction of the distilled product, if so, taking the preliminary training model as a prediction model of the distilled product of the coal tar processing technology, and if not, returning to randomly retrieving a plurality of model training sample data from the historical processing parameters of the coal tar processing technology, and retraining the preliminary training model.
Preferably, the number of model verification sample data and the number of model training sample data should satisfy:
wherein N is Verification Verifying the number of sample data for the model, N Training The number of sample data is trained for the model.
Preferably, the verifying the preliminary training model by using model verification sample data, and judging whether the preliminary training model can meet the component quality prediction of the distillate product specifically includes:
calculating regression determination coefficients of the preliminary training model based on the model verification sample data;
judging whether the regression determination coefficient of the preliminary training model is larger than a preset determination coefficient threshold value, if so, judging that the preliminary training model can meet the component quality prediction of the distilled product, and if not, judging that the preliminary training model cannot meet the component quality prediction of the distilled product;
the calculation formula of the regression determination coefficient is as follows:
wherein R is 2 Determining coefficients for the regression; RSS is the sum of squares of residuals of the preliminary training model; TSS is the sum of the total squares of the preliminary training models.
Further, a process adjustment system based on a coal tar production process is provided, which is used for implementing the process adjustment method based on the coal tar production process, and the process adjustment system comprises:
the raw material detection module is used for detecting the performance of the coal tar raw material and obtaining the performance parameters of the coal tar raw material;
the process determining module is electrically connected with the raw material detecting module and is used for determining the grade of the coal tar raw material based on the performance parameter of the coal tar raw material and determining the coal tar processing process based on the grade of the coal tar raw material;
the storage module is used for storing historical processing parameters of the coal tar processing technology;
the model training module is electrically connected with the storage module and is used for training and determining a prediction model of a distillate product of the coal tar processing technology based on historical processing parameters of the coal tar processing technology;
the real-time monitoring module is used for monitoring the coal tar production flow in real time to obtain real-time monitoring data;
the data analysis module is electrically connected with the real-time monitoring module and is used for comprehensively analyzing and calculating process completion data based on the real-time monitoring data to acquire real-time process completion data;
the prediction module is electrically connected with the model training module and the data analysis module, and is used for inputting real-time process completion data into a prediction model of a distillate product of the coal tar processing process to comprehensively analyze the quality of each distillate product.
Optionally, the data analysis module is integrated with:
the first calculation unit is used for comprehensively calculating the completion weight index of the process procedure based on the acquired real-time operation images of the operators in each procedure;
the second calculation unit is used for substituting a parameter fitting degree calculation formula based on the acquired real-time process parameters of the process and the standard parameters of the process to calculate the parameter fitting index of the process;
and the third calculation unit is used for comprehensively calculating the process completion degree of the process procedure according to a completion degree calculation formula based on the completion weight index of the process procedure and the parameter fitting index of the process procedure.
Still further, a computer readable storage medium is provided, on which a computer readable program is stored, wherein the computer readable program when called performs the process adjustment method based on the coal tar production process as described above.
Compared with the prior art, the invention has the beneficial effects that:
according to the invention, a process adjustment scheme based on a coal tar production flow is provided, comprehensive analysis of process completion data is carried out by combining with operation and process parameters of workers in the coal tar production process, a prediction model of a distilled product of the coal tar processing process is determined by training based on historical processing parameters of the coal tar processing process, and the components of the distilled product are predicted by inputting the process completion data, so that a data basis is provided for the subsequent refinement processing process of the distilled product, so that the stability of the components during refinement processing of the distilled product can be effectively ensured, the quality stability of a final product produced by the coal tar is effectively ensured, and the coal tar production processing with multiple varieties, high quality, low energy consumption and high environmental friendliness is realized.
Drawings
FIG. 1 is a flow chart of a process adjustment method based on a coal tar production flow provided by the invention;
FIG. 2 is a flow chart of a method for calculating process completion data according to the present invention;
FIG. 3 is a flowchart of a method for calculating a completion weight index for a comprehensive calculation process in the present invention;
FIG. 4 is a flow chart of a method for training to determine a predictive model of a distillate product of a coal tar processing process in accordance with the present invention;
FIG. 5 is a flow chart of a method of determining whether a preliminary training model can meet the component quality prediction of a distillate product in the present invention;
fig. 6 is a block diagram of a process adjustment system based on a coal tar production process according to the present invention.
Detailed Description
The following description is presented to enable one of ordinary skill in the art to make and use the invention. The preferred embodiments in the following description are by way of example only and other obvious variations will occur to those skilled in the art.
Referring to fig. 1, a process adjustment method based on a coal tar production process includes:
performing performance detection on the coal tar raw material to obtain performance parameters of the coal tar raw material;
determining the grade of the coal tar raw material based on the performance parameters of the coal tar raw material, and determining the coal tar processing technology based on the grade of the coal tar raw material;
training based on historical processing parameters of the coal tar processing technology to determine a prediction model of a distillate product of the coal tar processing technology, wherein the prediction model of the distillate product of the coal tar processing technology takes process completion data in a coal tar production flow as input and the quality of each distillate product as output;
carrying out coal tar production according to a determined coal tar processing technology;
monitoring the coal tar production process in real time to obtain real-time monitoring data;
comprehensively analyzing and calculating process completion data based on the real-time monitoring data to obtain real-time process completion data;
inputting real-time process completion data into a prediction model of a distillate product of the coal tar processing process, and comprehensively analyzing the quality of each distillate product;
and adjusting the subsequent refining processing technology of each distillate product based on the quality of each distillate product.
According to the scheme, the operation of workers and the process parameters in the coal tar production process are combined to comprehensively analyze process completion data, a prediction model of a distillation product of the coal tar processing process is determined by training based on the historical processing parameters of the coal tar processing process, the components of the distillation product are predicted by inputting the process completion data, and a data basis is provided for the subsequent refinement processing process of the distillation product in a targeted adjustment mode, so that the component stability in the refinement processing of the distillation product can be effectively guaranteed.
Referring to fig. 2, the process completion data calculating method includes:
performing comprehensive calculation on the completion weight index of the process procedure based on the acquired real-time operation images of operators in each procedure;
substituting the acquired real-time process parameters of the process and the standard parameters of the process into a parameter fitting degree calculation formula to calculate parameter fitting indexes of the process;
based on the completion weight index of the process and the parameter fitting index of the process, comprehensively calculating the process completion of the process according to a completion calculation formula;
the parameter fitting degree calculation formula specifically comprises the following steps:
wherein C is the process completion of the process, n is the total number of parameters of the process, alpha i Is the important weight value of the ith parameter of the process procedure, x i Real-time process parameter, x, being the ith parameter of the process sequence i0 Is a standard parameter for the ith parameter of the process.
And comprehensively calculating parameter fitting indexes of the process procedures based on vector distances between real-time parameters and standard parameters in the coal tar production process, wherein the larger the parameter fitting indexes of the process procedures are, the closer the parameters representing the process procedures are to the standard parameters of the process procedures, and the higher the parameter completion degree of the process procedures is.
Referring to fig. 3, the method for performing comprehensive calculation on the completion weight index of the process based on the collected real-time operation images of the operators in each process specifically includes:
determining a standard operation image of an operator in each procedure, and extracting standard action skeleton points of the operator from the standard operation image;
extracting real-time action skeleton points of an operator from a real-time operation image of the operator;
based on a matching weight formula, calculating the matching weight between the real-time action skeleton points of the operators and the standard action skeleton points of the operators, namely, the completion weight index of the process procedure;
the matching weight formula specifically comprises the following steps:
wherein K is the completion weight index of the process, m is the total number of action skeleton points, and delta (P j ,P j0 ) For the fitting function between the j-th real-time action skeleton point of the operator and the j-th standard action skeleton point of the operator, the value range of the fitting function is [0,1]The j-th real-time action skeleton point P of the operator is described as the function value of the fitting function is larger j J standard action skeleton point P with operator j0 The greater the distance between them.
The completion degree calculation formula is specifically as follows:
J=K×C
wherein J is the process completion of the process.
It can be understood that during the coal tar production process, the operation of the staff can also affect the quality of each distilled product, when the staff performs the operation in the coal tar production process, the more the action flow approaches to the standard action flow, the less the impurities in the distilled products, and the higher the quality of the distilled products, so in the scheme, the matching weight between the real-time action skeleton point of the staff and the standard action skeleton point of the staff is calculated by adopting a skeleton point matching mode, and specifically, the skeleton point can select one or more of the left ear, the left eye, the left shoulder, the left elbow, the left head, the left waist, the left hip, the left knee, the left foot head, the right ear, the right eye, the right shoulder, the right elbow, the right head, the right waist, the right hip, the left knee and the right foot head according to the actual operation action.
Referring to fig. 4, the prediction model for training and determining the distillate product of the coal tar processing technology based on the historical processing parameters of the coal tar processing technology specifically includes:
randomly retrieving a plurality of model training sample data from historical processing parameters of a coal tar processing technology;
respectively obtaining the components of the distilled products of a plurality of each process based on model training sample data, and the process completion degree of each process corresponding to the components;
training a neural network based on model training sample data, taking the process completion degree of each process procedure as a neural network input layer, taking a distillate product corresponding to each procedure as a neural network output layer, and performing node mapping logic of an implicit layer of the training neural network to obtain a preliminary training model;
randomly retrieving a plurality of model verification sample data from historical processing parameters of a coal tar processing technology;
and verifying the preliminary training model by using model verification sample data, judging whether the preliminary training model can meet the component quality prediction of the distilled product, if so, taking the preliminary training model as a prediction model of the distilled product of the coal tar processing technology, and if not, returning to randomly retrieving a plurality of model training sample data from the historical processing parameters of the coal tar processing technology, and retraining the preliminary training model.
In the embodiment, a training neural computing network Model is adopted to train a prediction Model of a distillate product of a coal tar processing technology, an artificial neural network (Artificial Neural Networks, abbreviated as ANNs) is also called a Neural Network (NNs) or a Connection Model (Connection Model) for short, and the Model is an algorithm mathematical Model which simulates the behavior characteristics of an animal neural network and carries out distributed parallel information processing; according to the network, the aim of information processing is achieved by adjusting the relation of interconnection among a large number of internal nodes according to the complexity of the system.
It will be appreciated that in other embodiments, other ways of training predictive models of distillate products of coal tar processing may be selected.
The number of model verification sample data and the number of model training sample data should satisfy:
wherein N is Verification Verifying the number of sample data for the model, N Training The number of sample data is trained for the model.
Referring to fig. 5, verifying the preliminary training model with model verification sample data, determining whether the preliminary training model can satisfy component quality prediction of the distillate product specifically includes:
calculating regression determination coefficients of the preliminary training model based on the model verification sample data;
judging whether the regression determination coefficient of the preliminary training model is larger than a preset determination coefficient threshold value, if so, judging that the preliminary training model can meet the component quality prediction of the distilled product, and if not, judging that the preliminary training model cannot meet the component quality prediction of the distilled product;
the calculation formula of the regression determination coefficient is as follows:
wherein R is 2 Determining coefficients for the regression; RSS is the sum of squares of residuals of the preliminary training model; TSS is the sum of the total squares of the preliminary training models.
Regression determination coefficient R 2 As a relative measure of interpretation variance, a larger value represents a closer relationship between the cross-linking represented by the preliminary training model and the cross-linking in reality, in particular, if R 2 =0.7, then 70% of the representative model validation sample data satisfies the preliminary training model, and in some embodiments, the determination coefficient threshold is set to 0.85.
Further, referring to fig. 6, based on the same inventive concept as the process adjustment method based on the coal tar production process, the present disclosure further provides a process adjustment system based on the coal tar production process, including:
the raw material detection module is used for detecting the performance of the coal tar raw material and obtaining the performance parameters of the coal tar raw material;
the process determining module is electrically connected with the raw material detecting module and is used for determining the grade of the coal tar raw material based on the performance parameter of the coal tar raw material and determining the coal tar processing process based on the grade of the coal tar raw material;
the storage module is used for storing historical processing parameters of the coal tar processing technology;
the model training module is electrically connected with the storage module and is used for training and determining a prediction model of a distillate product of the coal tar processing technology based on historical processing parameters of the coal tar processing technology;
the real-time monitoring module is used for monitoring the coal tar production flow in real time to obtain real-time monitoring data;
the data analysis module is electrically connected with the real-time monitoring module and is used for comprehensively analyzing and calculating process completion data based on the real-time monitoring data to acquire real-time process completion data;
the prediction module is electrically connected with the model training module and the data analysis module, and is used for inputting real-time process completion data into a prediction model of the distillate products of the coal tar processing process to comprehensively analyze the quality of each distillate product.
Wherein, the data analysis module is integrated with:
the first calculation unit is used for comprehensively calculating the completion weight index of the process procedure based on the acquired real-time operation images of the operators in each procedure;
the second calculation unit is used for substituting a parameter fitting degree calculation formula based on the acquired real-time process parameters of the process and the standard parameters of the process to calculate the parameter fitting index of the process;
and the third calculation unit is used for comprehensively calculating the process completion degree of the process procedure according to a completion degree calculation formula based on the completion weight index of the process procedure and the parameter fitting index of the process procedure.
The use process of the process adjustment system based on the coal tar production flow comprises the following steps:
step one: the raw material detection module detects the performance of the coal tar raw material to obtain the performance parameter of the coal tar raw material, and the process determination module determines the grade of the coal tar raw material based on the performance parameter of the coal tar raw material and determines the coal tar processing process based on the grade of the coal tar raw material;
step two: the model training module is used for calling historical processing parameters of the coal tar processing technology from the storage module, and training and determining a prediction model of a distillate product of the coal tar processing technology based on the historical processing parameters of the coal tar processing technology;
step three: the real-time monitoring module monitors the coal tar production process in real time to obtain real-time monitoring data;
step four: the data analysis module is used for comprehensively analyzing and calculating process completion data based on the real-time monitoring data to obtain the real-time process completion data, wherein the process completion data analysis and calculation specifically comprises the following steps: the first calculation unit carries out comprehensive calculation on the completion weight index of the process procedure based on the acquired real-time operation image of the operator of each procedure; the second calculation unit substitutes a parameter fitting degree calculation formula based on the acquired real-time process parameters of the process and the standard parameters of the process to calculate parameter fitting indexes of the process; the third calculation unit is used for comprehensively calculating the process completion degree of the process procedure according to a completion degree calculation formula based on the completion weight index of the process procedure and the parameter fitting index of the process procedure;
step five: and the prediction module inputs the real-time process completion data into a prediction model of the distillate products of the coal tar processing process, and comprehensively analyzes the components of each distillate product.
Still further, the present invention also provides a computer readable storage medium, on which a computer readable program is stored, which executes the above-mentioned process adjustment method based on the coal tar production process when being called;
it is understood that the computer readable storage medium may be a magnetic medium, e.g., floppy disk, hard disk, tape; optical media such as DVD; or a semiconductor medium such as a solid state disk SolidStateDisk, SSD, etc.
In summary, the invention has the advantages that: by combining the operation of workers and the process parameters in the coal tar production process, the quality stability of the final product produced by the coal tar can be effectively ensured, and the production and processing of various coal tar with high quality, low energy consumption and high environmental protection are realized.
The foregoing has shown and described the basic principles, principal features and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that the above embodiments and descriptions are merely illustrative of the principles of the present invention, and various changes and modifications may be made therein without departing from the spirit and scope of the invention, which is defined by the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (10)
1. The process adjustment method based on the coal tar production flow is characterized by comprising the following steps of:
performing performance detection on the coal tar raw material to obtain performance parameters of the coal tar raw material;
determining the grade of the coal tar raw material based on the performance parameters of the coal tar raw material, and determining the coal tar processing technology based on the grade of the coal tar raw material;
training based on historical processing parameters of a coal tar processing process to determine a prediction model of a distillate product of the coal tar processing process, wherein the prediction model of the distillate product of the coal tar processing process takes process completion data in a coal tar production flow as input and the quality of each distillate product as output;
carrying out coal tar production according to a determined coal tar processing technology;
monitoring the coal tar production process in real time to obtain real-time monitoring data;
comprehensively analyzing and calculating process completion data based on the real-time monitoring data to obtain real-time process completion data;
inputting real-time process completion data into a prediction model of a distillate product of the coal tar processing process, and comprehensively analyzing the quality of each distillate product;
and adjusting the subsequent refining processing technology of each distillate product based on the quality of each distillate product.
2. The process adjustment method based on the coal tar production flow according to claim 1, wherein the process completion data calculation method is as follows:
performing comprehensive calculation on the completion weight index of the process procedure based on the acquired real-time operation images of operators in each procedure;
substituting the acquired real-time process parameters of the process and the standard parameters of the process into a parameter fitting degree calculation formula to calculate parameter fitting indexes of the process;
based on the completion weight index of the process and the parameter fitting index of the process, comprehensively calculating the process completion of the process according to a completion calculation formula;
the parameter fitting degree calculation formula specifically comprises the following steps:
wherein C is the process completion of the process, n is the total number of parameters of the process, alpha i Is the important weight value of the ith parameter of the process procedure, x i Real-time process parameter, x, being the ith parameter of the process sequence i0 Is a standard parameter for the ith parameter of the process.
3. The process adjustment method based on the coal tar production process according to claim 2, wherein the step of performing comprehensive calculation on the completion weight index of the process based on the acquired real-time operation image of the operator in each process specifically comprises the following steps:
determining a standard operation image of an operator in each procedure, and extracting standard action skeleton points of the operator from the standard operation image;
extracting real-time action skeleton points of an operator from a real-time operation image of the operator;
based on a matching weight formula, calculating the matching weight between the real-time action skeleton points of the operators and the standard action skeleton points of the operators, namely, the completion weight index of the process procedure;
the matching weight formula specifically comprises the following steps:
wherein K is the completion weight index of the process, m is the total number of action skeleton points, and delta (P j ,P j0 ) The value range of the fitting function between the j-th real-time action skeleton point of the operator and the j-th standard action skeleton point of the operator is [0,1 ]]The j-th real-time action skeleton point P of the operator is described as the larger the function value of the fitting function j J standard action skeleton point P with operator j0 The greater the distance between them.
4. The process adjustment method based on the coal tar production process according to claim 3, wherein the completion degree calculation formula specifically comprises:
J=K×C
wherein J is the process completion of the process.
5. The process adjustment method based on the coal tar production process according to claim 4, wherein the prediction model for determining the distillate product of the coal tar processing process based on training of the historical processing parameters of the coal tar processing process specifically comprises:
randomly retrieving a plurality of model training sample data from historical processing parameters of a coal tar processing technology;
respectively obtaining the components of the distilled products of a plurality of each process based on model training sample data, and the process completion degree of each process corresponding to the components;
training a neural network based on model training sample data, taking the process completion degree of each process procedure as a neural network input layer, taking a distillate product corresponding to each procedure as a neural network output layer, and performing node mapping logic of an implicit layer of the training neural network to obtain a preliminary training model;
randomly retrieving a plurality of model verification sample data from historical processing parameters of a coal tar processing technology;
and verifying the preliminary training model by using model verification sample data, judging whether the preliminary training model can meet the component quality prediction of the distilled product, if so, taking the preliminary training model as a prediction model of the distilled product of the coal tar processing technology, and if not, returning to randomly retrieving a plurality of model training sample data from the historical processing parameters of the coal tar processing technology, and retraining the preliminary training model.
6. The process adjustment method based on the coal tar production process according to claim 5, wherein the number of model verification sample data and the number of model training sample data should satisfy:
wherein N is Verification Verifying the number of sample data for the model, N Training The number of sample data is trained for the model.
7. The process adjustment method based on the coal tar production flow according to claim 5, wherein verifying the preliminary training model by the model verification sample data, and judging whether the preliminary training model can meet the component quality prediction of the distillate product specifically comprises:
calculating regression determination coefficients of the preliminary training model based on the model verification sample data;
judging whether the regression determination coefficient of the preliminary training model is larger than a preset determination coefficient threshold value, if so, judging that the preliminary training model can meet the component quality prediction of the distilled product, and if not, judging that the preliminary training model cannot meet the component quality prediction of the distilled product;
the calculation formula of the regression determination coefficient is as follows:
wherein R is 2 Determining coefficients for the regression; RSS is the sum of squares of residuals of the preliminary training model; TSS is the sum of the total squares of the preliminary training models.
8. A process adjustment system based on a coal tar production process for implementing the process adjustment method based on a coal tar production process according to any one of claims 1 to 7, comprising:
the raw material detection module is used for detecting the performance of the coal tar raw material and obtaining the performance parameters of the coal tar raw material;
the process determining module is electrically connected with the raw material detecting module and is used for determining the grade of the coal tar raw material based on the performance parameter of the coal tar raw material and determining the coal tar processing process based on the grade of the coal tar raw material;
the storage module is used for storing historical processing parameters of the coal tar processing technology;
the model training module is electrically connected with the storage module and is used for training and determining a prediction model of a distillate product of the coal tar processing technology based on historical processing parameters of the coal tar processing technology;
the real-time monitoring module is used for monitoring the coal tar production flow in real time to obtain real-time monitoring data;
the data analysis module is electrically connected with the real-time monitoring module and is used for comprehensively analyzing and calculating process completion data based on the real-time monitoring data to acquire real-time process completion data;
the prediction module is electrically connected with the model training module and the data analysis module, and is used for inputting real-time process completion data into a prediction model of a distillate product of the coal tar processing process to comprehensively analyze the quality of each distillate product.
9. The process adjustment system based on a coal tar production process according to claim 8, wherein the data analysis module is internally integrated with:
the first calculation unit is used for comprehensively calculating the completion weight index of the process procedure based on the acquired real-time operation images of the operators in each procedure;
the second calculation unit is used for substituting a parameter fitting degree calculation formula based on the acquired real-time process parameters of the process and the standard parameters of the process to calculate the parameter fitting index of the process;
and the third calculation unit is used for comprehensively calculating the process completion degree of the process procedure according to a completion degree calculation formula based on the completion weight index of the process procedure and the parameter fitting index of the process procedure.
10. A computer-readable storage medium having a computer-readable program stored thereon, wherein the computer-readable program when invoked performs the coal tar production process-based process adjustment method according to any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310920043.0A CN116841269B (en) | 2023-07-26 | 2023-07-26 | Process adjustment method, system and storage medium based on coal tar production flow |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310920043.0A CN116841269B (en) | 2023-07-26 | 2023-07-26 | Process adjustment method, system and storage medium based on coal tar production flow |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116841269A true CN116841269A (en) | 2023-10-03 |
CN116841269B CN116841269B (en) | 2024-01-23 |
Family
ID=88160034
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310920043.0A Active CN116841269B (en) | 2023-07-26 | 2023-07-26 | Process adjustment method, system and storage medium based on coal tar production flow |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116841269B (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108717506A (en) * | 2018-06-25 | 2018-10-30 | 华北理工大学 | A method of prediction coke hot strength |
CN111950854A (en) * | 2020-07-14 | 2020-11-17 | 包头钢铁(集团)有限责任公司 | Coke quality index prediction method based on multilayer neural network |
CN115630847A (en) * | 2022-12-07 | 2023-01-20 | 四川省华盾防务科技股份有限公司 | Transceiving assembly detection method and system based on data prediction and storage medium |
CN115880271A (en) * | 2022-12-29 | 2023-03-31 | 保定景欣电气有限公司 | Identification and detection method for seed crystal single crystal line edge angle in crystal growth process |
CN116307289A (en) * | 2023-05-19 | 2023-06-23 | 苏州益诚隆纺织科技有限公司 | Textile processing procedure parameter detection and prediction method, system and storage medium |
CN116434859A (en) * | 2023-04-13 | 2023-07-14 | 中冶赛迪信息技术(重庆)有限公司 | Blast furnace gas production consumption prediction method and device, electronic equipment and storage medium |
-
2023
- 2023-07-26 CN CN202310920043.0A patent/CN116841269B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108717506A (en) * | 2018-06-25 | 2018-10-30 | 华北理工大学 | A method of prediction coke hot strength |
CN111950854A (en) * | 2020-07-14 | 2020-11-17 | 包头钢铁(集团)有限责任公司 | Coke quality index prediction method based on multilayer neural network |
CN115630847A (en) * | 2022-12-07 | 2023-01-20 | 四川省华盾防务科技股份有限公司 | Transceiving assembly detection method and system based on data prediction and storage medium |
CN115880271A (en) * | 2022-12-29 | 2023-03-31 | 保定景欣电气有限公司 | Identification and detection method for seed crystal single crystal line edge angle in crystal growth process |
CN116434859A (en) * | 2023-04-13 | 2023-07-14 | 中冶赛迪信息技术(重庆)有限公司 | Blast furnace gas production consumption prediction method and device, electronic equipment and storage medium |
CN116307289A (en) * | 2023-05-19 | 2023-06-23 | 苏州益诚隆纺织科技有限公司 | Textile processing procedure parameter detection and prediction method, system and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN116841269B (en) | 2024-01-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105117602B (en) | A kind of metering device running status method for early warning | |
CN109814513B (en) | Catalytic cracking unit optimization method based on data model | |
CN111614491A (en) | Power monitoring system oriented safety situation assessment index selection method and system | |
CN110636066B (en) | Network security threat situation assessment method based on unsupervised generative reasoning | |
CN103927412A (en) | Real-time learning debutanizer soft measurement modeling method on basis of Gaussian mixture models | |
CN112231980B (en) | Engine life prediction method, storage medium and computing device | |
CN109389325B (en) | Method for evaluating state of electronic transformer of transformer substation based on wavelet neural network | |
CN112418682B (en) | Safety evaluation method for fusion of multi-source information | |
CN112906764A (en) | Communication safety equipment intelligent diagnosis method and system based on improved BP neural network | |
CN112684295A (en) | Power distribution network fault line selection method and system under high permeability based on similarity separation degree | |
CN116841269B (en) | Process adjustment method, system and storage medium based on coal tar production flow | |
CN108399284A (en) | It is a kind of about subtracted based on deviation big data Trading Model analysis and restorative procedure | |
WO2024045377A1 (en) | Deep-learning-based method for predicting residual life of aero-engine | |
CN116521495A (en) | System performance bottleneck detection method based on reinforcement learning | |
CN115375077A (en) | Submarine pipeline failure risk evaluation method based on Bidamgo fuzzy weighting method | |
CN113807715A (en) | Chemical device risk dynamic early warning method | |
CN113849479A (en) | Comprehensive energy supply station oil tank leakage detection method based on instant learning and self-adaptive threshold | |
Tang et al. | Octane number prediction of blend gasoline based on improved particle swarm optimization | |
Mo et al. | Trial risk index model and assessment system based on extended TOPSIS method | |
Chen | The application of data mining in data analysis | |
Okitsu et al. | Cause analysis of representative troubles at distillation tower using discriminant analysis | |
Zhao | Digital Economy Development, Technological Innovation and Export Technology Complexity from the Perspective of big Data | |
Lu et al. | A quality evaluation model for diesel engine using RBF neural network based on trial run data | |
CN117764705A (en) | Risk analysis method based on stock clients | |
CN117495199A (en) | Power distribution network running state evaluation method, 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 |