CN114819743B - Energy consumption diagnosis and analysis method for chemical enterprises - Google Patents
Energy consumption diagnosis and analysis method for chemical enterprises Download PDFInfo
- Publication number
- CN114819743B CN114819743B CN202210618538.3A CN202210618538A CN114819743B CN 114819743 B CN114819743 B CN 114819743B CN 202210618538 A CN202210618538 A CN 202210618538A CN 114819743 B CN114819743 B CN 114819743B
- Authority
- CN
- China
- Prior art keywords
- energy consumption
- parameter
- parameters
- process parameters
- data
- 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.)
- Active
Links
- 238000005265 energy consumption Methods 0.000 title claims abstract description 78
- 239000000126 substance Substances 0.000 title claims abstract description 24
- 238000004458 analytical method Methods 0.000 title abstract description 19
- 238000003745 diagnosis Methods 0.000 title abstract description 17
- 238000000034 method Methods 0.000 claims abstract description 116
- 230000002159 abnormal effect Effects 0.000 claims description 12
- 230000001419 dependent effect Effects 0.000 claims description 11
- 230000005634 sigma model Effects 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 9
- 238000009826 distribution Methods 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 5
- 238000005315 distribution function Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims 1
- 238000010801 machine learning Methods 0.000 abstract description 7
- QGZKDVFQNNGYKY-UHFFFAOYSA-N Ammonia Chemical compound N QGZKDVFQNNGYKY-UHFFFAOYSA-N 0.000 description 14
- 229910021529 ammonia Inorganic materials 0.000 description 7
- 238000004821 distillation Methods 0.000 description 6
- 230000001105 regulatory effect Effects 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 3
- 239000002585 base Substances 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 239000007788 liquid Substances 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- VHUUQVKOLVNVRT-UHFFFAOYSA-N Ammonium hydroxide Chemical compound [NH4+].[OH-] VHUUQVKOLVNVRT-UHFFFAOYSA-N 0.000 description 1
- 239000003513 alkali Substances 0.000 description 1
- 235000011114 ammonium hydroxide Nutrition 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012824 chemical production Methods 0.000 description 1
- 238000000546 chi-square test Methods 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 239000007791 liquid phase Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 239000010865 sewage Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 239000002351 wastewater Substances 0.000 description 1
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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- 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
- G06Q50/04—Manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Software Systems (AREA)
- Educational Administration (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Manufacturing & Machinery (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Artificial Intelligence (AREA)
- Quality & Reliability (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Operations Research (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses a method for diagnosing and analyzing energy consumption of chemical enterprises, which relates to the technical field of energy consumption diagnosis and analysis and comprises the steps of acquiring a data set of each technological parameter through a database; determining a process parameter related to the energy consumption target amount and a corresponding parameter interval through the data set; acquiring weights corresponding to various technological parameters related to the energy consumption target quantity, and determining combination parameters related to the energy consumption target quantity and corresponding parameter intervals according to the weights; and comparing the acquired real-time data of the process parameters with the parameter interval of the combined parameters to determine the process parameters affecting the energy consumption target quantity. The invention solves the problem of the industrial scene through machine learning and realizes the planning of energy-saving measures.
Description
Technical Field
The invention relates to the technical field of energy consumption diagnosis and analysis, in particular to an energy consumption diagnosis and analysis method for chemical enterprises.
Background
The ammonia distillation system of partial alkali preparation process in chemical production has larger energy consumption, shorter continuous operation time and insufficient separation of ammonia water and liquid phase, thereby leading to waste of steam heat energy, high ammonia content in wastewater and increasing sewage treatment cost. The measurement shows that the temperature of the ammonia distillation waste liquid is higher than 1 ℃, and the heat loss is about 16.25kg/t of steam. The production personnel often judge when the pressure is reduced, what degree is reduced and how much the regulating valve is opened according to experience values, so that abundant experience cannot be inherited, and meanwhile, rough estimation of operation rather than accurate execution exists, and data support cannot be provided for energy conservation.
At present, when the liquid level of the conventional visual measuring flowmeter reaches half, the regulating valve is used for controlling the steam supply, the current working condition and the energy consumption condition are not connected together, the fluctuation of the energy consumption can only know what special operation is performed afterwards, but only the general condition is adopted, the actual data support cannot be obtained, and the energy-saving measures cannot be developed.
Disclosure of Invention
The invention aims to solve the technical problem of overcoming the defects of the prior art and providing an energy consumption diagnosis and analysis method for chemical enterprises.
In order to solve the technical problems, the technical scheme of the invention is as follows:
a method for diagnosing and analyzing the energy consumption of chemical enterprises includes such steps as,
acquiring a data set of each technological parameter through a database;
determining a process parameter related to the energy consumption target amount and a corresponding parameter interval through the data set;
acquiring weights corresponding to various technological parameters related to the energy consumption target quantity, and determining combination parameters related to the energy consumption target quantity and corresponding parameter intervals according to the weights;
and comparing the acquired real-time data of the process parameters with the parameter interval of the combined parameters to determine the process parameters affecting the energy consumption target quantity.
As a preferable scheme of the energy consumption diagnosis and analysis method for the chemical enterprises, the invention comprises the following steps: the determining of the process parameters related to the energy consumption target amount by means of the data set comprises,
determining an abnormal threshold value of the energy consumption target quantity by utilizing a 3 sigma model based on Gaussian distribution, and determining a threshold value range of the energy consumption target quantity according to the abnormal threshold value;
for any process parameter, taking 3 sigma in a 3 sigma model as a threshold value, determining data which is larger than the threshold value in a data set as a label 1, determining data which is smaller than the threshold value in the data set as a label 0, and then grouping the data by using a chi-square box division mode;
and (3) calculating the correlation between the independent variable and the dependent variable by adopting woe on the grouped data, and acquiring the IV value of each group so as to determine the process parameters related to the energy consumption target quantity and the corresponding parameter interval.
As a preferable scheme of the energy consumption diagnosis and analysis method for the chemical enterprises, the invention comprises the following steps: the determining of the abnormal threshold of the energy consumption target amount by using the 3 sigma model based on the Gaussian distribution, and the determining of the threshold range of the energy consumption target amount based on the abnormal threshold range comprises,
gaussian distribution function ofWherein μ is the expected, σ is the standard deviation;
when the threshold exceeds 3σ, it is regarded as an abnormal threshold, and the threshold range of the energy consumption target amount is determined to be [ μ -3σ, μ+3σ ].
As a preferable scheme of the energy consumption diagnosis and analysis method for the chemical enterprises, the invention comprises the following steps: the data after grouping adopts woe to calculate the correlation between the independent variable and the dependent variable, and obtains the IV value of each grouping, thereby determining the technological parameters related to the energy consumption target quantity and the corresponding parameter intervals,
by the formula:calculating the correlation of the independent variable and the dependent variable, wherein #y i For the number of individuals in the group labeled 1, # n i For the number of individuals in the packet with a tag of 0, # y T For the number of individuals with all tags of 1 in the corresponding process parameter, #n T For the number of individuals with all tags of 0 in the corresponding process parameter py i For the proportion of individuals with a label of 1 in the group to the label of 1 in all process parameters, pn i The individual with the label of 0 in the group accounts for the proportion of the label of 0 in all the process parameters;
by the formula:calculating the IV value of the i group;
and determining the process parameters related to the energy consumption target amount and the corresponding parameter intervals according to the calculated IV values of each group in each process parameter.
As a preferable scheme of the energy consumption diagnosis and analysis method for the chemical enterprises, the invention comprises the following steps: the method comprises the steps of acquiring weights corresponding to various technological parameters related to the energy consumption target quantity, determining combination parameters related to the energy consumption target quantity and corresponding parameter intervals according to the weights,
performing correlation verification on all process parameters related to the energy consumption target quantity, and removing part of process parameters with correlation larger than a set value;
training the rest process parameters by adopting an LASSO regression model, and determining the weight corresponding to each process parameter;
by the formula x=w 1 X 1 +W 2 X 2 +…+W n Xn+b determining a combination parameter related to the target amount of energy consumption, wherein X is the combination parameter, xn is the nth process parameter, W n The weight corresponding to the nth process parameter and b is a bias term;
taking 3 sigma in the 3 sigma model as a threshold value, determining data which are larger than the threshold value in the combination parameter as a label 1, determining data which are smaller than the threshold value in the combination parameter as a label 0, and then grouping the data by using a chi-square box dividing mode;
and (3) calculating the correlation between the independent variable and the dependent variable by adopting woe on the data after grouping, and acquiring the IV value of each grouping so as to determine the parameter interval of the combined parameter.
As a preferable scheme of the energy consumption diagnosis and analysis method for the chemical enterprises, the invention comprises the following steps: the step of performing correlation verification on each technological parameter related to the energy consumption target quantity and eliminating part of technological parameters with correlation larger than a set value comprises,
according to the formula:calculating a correlation coefficient between two process parameters, wherein X i For the ith process parameter,/i>Is X i Average value of (2);
and when the correlation coefficient between the two process parameters is larger than a set value, removing one of the process parameters.
As a preferable scheme of the energy consumption diagnosis and analysis method for the chemical enterprises, the invention comprises the following steps: the cost function of the LASSO regression model isWhere w is a vector of length n, the coefficient θ excluding the intercept term 0 θ is a vector of length n+1, including the coefficient of intercept term θ 0 M is the number of process parameters, n is the number of features and is the number of features, i w i 1 Is the L1 norm of the process parameter w.
As a preferable scheme of the energy consumption diagnosis and analysis method for the chemical enterprises, the invention comprises the following steps: comparing the acquired real-time data of the process parameters with the parameter interval of the combined parameters, determining the process parameters affecting the target energy consumption amount, and further comprising,
and periodically collecting technological parameters, training through a regression model, and updating the combined parameters and the corresponding parameter intervals.
As a preferable scheme of the energy consumption diagnosis and analysis method for the chemical enterprises, the invention comprises the following steps: the process parameters are collected regularly, the process parameters are trained through a regression model, and after the combination parameters and the corresponding parameter intervals are updated, the process further comprises the steps of,
periodically acquiring real-time data of various technological parameters;
judging whether the real-time data of the process parameters are in the threshold range of the energy consumption target amount, if so, comparing the real-time data of the process parameters with the parameter interval of the combined parameters, determining the process parameters affecting the energy consumption target amount, and if not, updating the real-time data of the process parameters and the energy consumption data to a database.
As a preferable scheme of the energy consumption diagnosis and analysis method for the chemical enterprises, the invention comprises the following steps: the target amount of energy consumption is the instantaneous flow of steam.
The beneficial effects of the invention are as follows:
the invention solves the problem of the industrial scene through machine learning and realizes the planning of energy-saving measures. The parameter sample data is used as the input of machine learning, so that the training of a model can be realized, and the trained model can be used for diagnosing the ammonia distillation process. Compared with manual analysis, after various production processes are optimized and regulated, machine learning continuously performs data learning capacity through continuous data acquisition, rich knowledge base and model training, and abnormal energy consumption can be diagnosed more quickly and more accurately.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of an energy consumption diagnosis and analysis method for chemical enterprises;
fig. 2 is a schematic diagram of a specific flow of step S102 in the method for diagnosing and analyzing energy consumption of chemical enterprises provided by the present invention.
Detailed Description
In order that the invention may be more readily understood, a more particular description thereof will be rendered by reference to specific embodiments that are illustrated in the appended drawings.
Fig. 1 is a schematic flow chart of an energy consumption diagnosis and analysis method for chemical enterprises according to an embodiment of the present application. The method comprises the steps S101 to S105, and the specific steps are as follows:
step S101: and acquiring a data set of each technological parameter through a database.
Specifically, taking an ammonia distillation system as an example, when the ammonia distillation system works, data of various process parameters under working conditions are collected, the collected data are stored in a database, and a data set of the stored various process parameters can be directly called from the database in the later period. It is understood that the dataset of process parameters includes process parameters acquired at different time periods.
Step S102: a process parameter related to the instantaneous flow of steam (target amount of energy consumption) and a corresponding parameter interval are determined from the data set.
Referring to fig. 2, the steps specifically include the steps of:
step S102a: an abnormal threshold of the steam instantaneous flow is determined by using a 3 sigma model based on Gaussian distribution, and a threshold range of the steam instantaneous flow is determined according to the abnormal threshold.
Specifically, assuming that each time is independent and there is no context correlation, a 3σ model may be employed to detect abnormal intervals. It should be noted that the data is required to follow normal distribution.
Gaussian distribution function ofWhere μ is the expected, σ is the standard deviation. Under the 3σ principle, outliers, such as standard deviations exceeding 3 times, can be considered outliers. In fact, the values are distributed between [ mu-3. Sigma., mu+3. Sigma ]]Is 99.7%, the probability of occurrence of a value other than the average value 3σ is P (|x- μ|)>3σ) =0.03, which belongs to extremely individual small probability times. The threshold range of the instantaneous flow of steam is determined to be [ mu-3 sigma, mu+3 sigma]。
Step S102b: for any process parameter, 3 sigma in the 3 sigma model is taken as a threshold value, data with the data set being larger than the threshold value is designated as a label 1, data with the data set being smaller than the threshold value is designated as a label 0, and then the data are grouped by using a chi-square box division mode.
Specifically, the Chi-Square box division mode is a box division method depending on Chi-Square test, chi-Square statistics (Chi-Square) is selected on statistical indexes to judge, the basic idea of box division is to judge whether two adjacent intervals have distribution differences or not, and bottom-up combination is performed based on the result of the Chi-Square statistics until the limit condition of box division is met.
Step S102c: and (3) calculating the correlation between the independent variable and the dependent variable by adopting woe on the grouped data, and acquiring the IV value of each group so as to determine the process parameters related to the instantaneous flow of the steam and the corresponding parameter interval.
Specifically, after grouping, for group i, the formula is passed:calculating the correlation between independent variables and dependent variablesWherein #y is i For the number of individuals in the group labeled 1, # n i For the number of individuals in the packet with a tag of 0, # y T For the number of individuals with all tags of 1 in the corresponding process parameter, #n T For the number of individuals with all tags of 0 in the corresponding process parameter py i For the proportion of individuals with a label of 1 in the group to the label of 1 in all process parameters, pn i The individuals with a label of 0 in the group are the proportion of the label of 0 in all process parameters.
Then by the formula:IV values for group i are calculated. It will be appreciated that the larger the IV value, the more predictive the group (parameter interval) will be for the dependent variable. Therefore, the process parameters related to the steam instantaneous flow and the corresponding parameter intervals can be determined according to the calculated IV value of each group in each process parameter.
By way of example, the pressure parameters are grouped into three groups of 10 to 50Pa,50 to 100Pa and 100 to 150Pa, wherein the determined pressure parameter interval is the interval of 50 to 100Pa if only 50 to 100Pa has an influence on the instantaneous flow rate of steam.
Step S103: and acquiring weights corresponding to various technological parameters related to the steam instantaneous flow, and determining a combination parameter related to the steam instantaneous flow and a corresponding parameter interval according to the weights.
Specifically, firstly, carrying out correlation verification on all process parameters related to the steam instantaneous flow, and eliminating part of process parameters with correlation larger than a set value.
According to the formula:calculating a correlation coefficient between two process parameters, wherein X i For the ith process parameter,/i>Is X i Average value of (2).
If there is a strong correlation between the two process parameters, there may be multiple collinearity, and some indexes need to be removed, and if the correlation coefficient between the two process parameters is greater than a set value, one of the process parameters is removed.
Then, considering that the Lasso regression can train the parameters of some characteristics with smaller effects to be 0, so as to obtain a lean solution, the LASSO regression model is adopted to train the rest process parameters, and the weights corresponding to the process parameters are determined. Wherein the cost function of the LASSO regression model isWhere w is a vector of length n, the coefficient θ excluding the intercept term 0 θ is a vector of length n+1, including the coefficient of intercept term θ 0 M is the number of process parameters, n is the number of features and is the number of features, i w i 1 Is the L1 norm of the process parameter w.
After determining the weights of the process parameters, the process parameters are determined by the formula x=w 1 X 1 +W 2 X 2 +…+W n Xn+b determining a combination parameter related to the target amount of energy consumption, wherein X is the combination parameter, xn is the nth process parameter, W n And b is a weight corresponding to the nth technological parameter, b is a bias term and is output by the model.
And then taking 3 sigma in the 3 sigma model as a threshold value, determining data which are larger than the threshold value in the combination parameter as a tag 1, determining data which are smaller than the threshold value in the combination parameter as a tag 0, grouping the data of the combination parameter by using a chi-square box division mode, calculating the correlation between the independent variable and the dependent variable by using woe on the grouped data, and acquiring the IV value of each group so as to determine the parameter interval of the combination parameter.
Step S104: and comparing the acquired real-time data of the process parameters with the parameter interval of the combined parameters to determine the process parameters affecting the energy consumption target quantity.
Specifically, the acquired real-time data of the process parameters are compared with the parameter interval of the combined parameters, a comparison result is output, and the process parameters affecting the target energy consumption are determined according to the comparison result.
Step S105: and periodically collecting technological parameters, training through a regression model, and updating the combined parameters and the corresponding parameter intervals.
Step S106: and periodically acquiring real-time data of various technological parameters.
Step S107: judging whether the real-time data of the process parameters are in the threshold range of the energy consumption target amount, if so, comparing the real-time data of the process parameters with the parameter interval of the combined parameters, determining the process parameters affecting the energy consumption target amount, and if not, updating the real-time data of the process parameters and the energy consumption data to a database.
Therefore, the technical scheme solves the problem of the industrial scene through machine learning, and realizes the planning of energy-saving measures. The parameter sample data is used as the input of machine learning, so that the training of a model can be realized, and the trained model can be used for diagnosing the ammonia distillation process. Compared with manual analysis, after various production processes are optimized and regulated, machine learning continuously performs data learning capacity through continuous data acquisition, rich knowledge base and model training, and abnormal energy consumption can be diagnosed more quickly and more accurately.
In addition to the above embodiments, the present invention may have other embodiments; all technical schemes formed by equivalent substitution or equivalent transformation fall within the protection scope of the invention.
Claims (6)
1. A method for diagnosing and analyzing the energy consumption of chemical enterprises is characterized by comprising the steps of,
acquiring a data set of each technological parameter through a database;
determining an abnormal threshold of the energy consumption target amount by using a 3 sigma model based on Gaussian distribution, wherein the Gaussian distribution function is thatWherein μ is an expectation, σ is a standard deviation, and x is an energy consumption target amount;
when the threshold exceeds 3σ, the threshold is regarded as an abnormal threshold, so that the threshold range of the energy consumption target amount is determined to be [ mu-3σ, mu+3σ ];
for any process parameter, taking 3 sigma in a 3 sigma model as a threshold value, determining data which is larger than the threshold value in a data set as a label 1, determining data which is smaller than the threshold value in the data set as a label 0, and then grouping the data by using a chi-square box division mode;
by the formula:calculating the correlation of the independent variable and the dependent variable, wherein #y i For the number of individuals in the group labeled 1, # n i For the number of individuals in the packet with a tag of 0, # y T For the number of individuals with all tags of 1 in the corresponding process parameter, #n T For the number of individuals with all tags of 0 in the corresponding process parameter py i For the proportion of individuals with a label of 1 in the group to the label of 1 in all process parameters, pn i WOE is the ratio of the individual with the label of 0 in the group to the label of 0 in all process parameters i WOE values for the ith set of independent and dependent variables;
by the formula:calculating the IV value of the i group;
determining the technological parameters related to the energy consumption target amount and the corresponding parameter intervals according to the IV values of each group in each technological parameter obtained through calculation;
performing correlation verification on all process parameters related to the energy consumption target quantity, and removing part of process parameters with correlation larger than a set value;
training the rest process parameters by adopting an LASSO regression model, and determining the weight corresponding to each process parameter;
by the formula x=w 1 X 1 +W 2 X 2 +…+W m X m +b 1 Determining a combined process parameter related to the target amount of energy consumption, wherein X represents the combined process parameter, X m Is the mth process parameter, W m Weight corresponding to the mth process parameter, b 1 Is a bias term; taking 3 sigma in the 3 sigma model as a threshold value, determining data which are larger than the threshold value in the combination parameter as a label 1, determining data which are smaller than the threshold value in the combination parameter as a label 0, and then grouping the data by using a chi-square box dividing mode;
for the grouped data, adopting woe to calculate the correlation between the independent variable and the dependent variable, and obtaining the IV value of each group so as to determine the parameter interval of the combined parameter;
and comparing the acquired real-time data of the process parameters with the parameter interval of the combined parameters to determine the process parameters affecting the energy consumption target quantity.
2. The method for diagnosing and analyzing energy consumption of chemical enterprises according to claim 1, wherein the step of performing correlation verification on each process parameter related to the target amount of energy consumption and eliminating part of the process parameters with correlation larger than a set value comprises the steps of:calculating a correlation coefficient between two process parameters, wherein X ia Is the process parameter X i A-th sample value of>Is the process parameter X i Average value of all sample values, X ja Is the process parameter X j A-th sample value of>Is the process parameter X j An average value of all the sample values, n representing the number of samples;
and when the correlation coefficient between the two process parameters is larger than a set value, removing one of the process parameters.
3. The method for diagnosing and analyzing energy consumption of chemical industry as set forth in claim 2, whereinThe method comprises the following steps: the cost function of the LASSO regression model isWhere n is the number of samples, m is the number of parameters, w is the weight vector with dimension m, and coefficient θ excluding intercept term 0 θ is a weight vector of dimension m+1, including the coefficient of intercept term θ 0 ,||w|| 1 Is the L1 norm of the weight vector w.
4. The method for diagnosing and analyzing energy consumption of chemical industry as recited in claim 1, wherein after comparing the acquired real-time data of the process parameters with the parameter interval of the combined parameters to determine the process parameters affecting the target amount of energy consumption, further comprising,
and periodically collecting technological parameters, training through a regression model, and updating the combined parameters and the corresponding parameter intervals.
5. The method for diagnosing and analyzing energy consumption of chemical enterprises according to claim 4, wherein the process parameters are collected periodically and trained by regression models, and after updating the combined parameters and the corresponding parameter intervals, the method further comprises,
periodically acquiring real-time data of various technological parameters;
judging whether the real-time data of the process parameters are in the threshold range of the energy consumption target amount, if so, comparing the real-time data of the process parameters with the parameter interval of the combined parameters, determining the process parameters affecting the energy consumption target amount, and if not, updating the real-time data of the process parameters and the energy consumption data to a database.
6. The method for diagnosing and analyzing energy consumption of chemical enterprises according to any one of claims 1 to 5, wherein the target amount of energy consumption is the instantaneous flow of steam.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210618538.3A CN114819743B (en) | 2022-06-01 | 2022-06-01 | Energy consumption diagnosis and analysis method for chemical enterprises |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210618538.3A CN114819743B (en) | 2022-06-01 | 2022-06-01 | Energy consumption diagnosis and analysis method for chemical enterprises |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114819743A CN114819743A (en) | 2022-07-29 |
CN114819743B true CN114819743B (en) | 2023-08-01 |
Family
ID=82519480
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210618538.3A Active CN114819743B (en) | 2022-06-01 | 2022-06-01 | Energy consumption diagnosis and analysis method for chemical enterprises |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114819743B (en) |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130080135A1 (en) * | 2011-09-28 | 2013-03-28 | Usa As Represented By The Administrator Of The National Aeronautics And Space Administration | System, tool and method for integrated circuit and component modeling |
EP3644267A1 (en) * | 2018-10-26 | 2020-04-29 | Tata Consultancy Services Limited | Method and system for online monitoring and optimization of mining and mineral processing operations |
CN113486520B (en) * | 2021-07-08 | 2023-02-21 | 内蒙古民族大学 | Digital twinning-based dynamic regulation and control method, system and device for cutting technological parameters |
-
2022
- 2022-06-01 CN CN202210618538.3A patent/CN114819743B/en active Active
Non-Patent Citations (1)
Title |
---|
基于卡方分箱法和逻辑回归算法的转炉操作工艺评价模型;陈超;王楠;于海洋;陈敏;;材料与冶金学报(02);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN114819743A (en) | 2022-07-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2022252505A1 (en) | Device state monitoring method based on multi-index cluster analysis | |
Ma et al. | Hierarchical monitoring and root-cause diagnosis framework for key performance indicator-related multiple faults in process industries | |
CN101699477B (en) | Neural network method for accurately predicting dam deformation | |
CN108803520B (en) | Dynamic process monitoring method based on variable nonlinear autocorrelation rejection | |
JP6141235B2 (en) | How to detect anomalies in time series data | |
Jiang et al. | Weighted kernel principal component analysis based on probability density estimation and moving window and its application in nonlinear chemical process monitoring | |
CN105955219A (en) | Distributed dynamic process fault detection method based on mutual information | |
CN104914723B (en) | Industrial process soft-measuring modeling method based on coorinated training partial least square model | |
CN102880905B (en) | Online soft measurement method for normal oil dry point | |
KR100867938B1 (en) | Prediction method for watching performance of power plant measuring instrument by dependent variable similarity and kernel feedback | |
CN105930629B (en) | A kind of on-line fault diagnosis method based on magnanimity service data | |
CN101436057A (en) | Numerical control machining tool heat error Bayes network compensation method | |
Liu et al. | Unevenly sampled dynamic data modeling and monitoring with an industrial application | |
CN107436983A (en) | A kind of O-shaped rubber seal life-span prediction method based on multivariate sample difference | |
CN104714537A (en) | Fault prediction method based on joint relative change analysis and autoregression model | |
EP4160342A1 (en) | Abnormal modulation cause identification device, abnormal modulation cause identification method, and abnormal modulation cause identification program | |
CN114066262A (en) | Method, system and device for estimating cause-tracing reasoning of abnormal indexes after power grid dispatching and storage medium | |
CN111122811A (en) | Sewage treatment process fault monitoring method of OICA and RNN fusion model | |
CN101673096B (en) | Soft-measuring method for density in concentration process of salvia miltiorrhiza injection production | |
CN112395684A (en) | Intelligent fault diagnosis method for high-speed train running part system | |
CN110414086B (en) | Sensitivity-based comprehensive stress acceleration factor calculation method | |
CN108470699B (en) | intelligent control system of semiconductor manufacturing equipment and process | |
WO2021241578A1 (en) | Abnormal modulation cause identifying device, abnormal modulation cause identifying method, and abnormal modulation cause identifying program | |
Wang et al. | What maintenance is worth the money? a data-driven answer | |
CN114819743B (en) | Energy consumption diagnosis and analysis method for chemical enterprises |
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 | ||
CB02 | Change of applicant information | ||
CB02 | Change of applicant information |
Address after: 11-14 / F, tower a, Tengfei building, 88 Jiangmiao Road, yanchuangyuan, Jiangbei new district, Nanjing, Jiangsu Province 210000 Applicant after: Anyuan Technology Co.,Ltd. Address before: 11-14 / F, tower a, Tengfei building, 88 Jiangmiao Road, yanchuangyuan, Jiangbei new district, Nanjing, Jiangsu Province 210000 Applicant before: NANJING ANYUAN TECHNOLOGY Co.,Ltd. |
|
GR01 | Patent grant | ||
GR01 | Patent grant |