Process energy consumption management and control health degree evaluation method and system, and storage medium

Abstract

The invention provides a process energy consumption management and control health degree assessment method and system, and a storage medium. The method comprises the steps of collecting historical data, constructing a process energy consumption data set, and sorting an overhaul period energy consumption data set M and a production state data set Z from the process energy consumption data set; performing grouping analysis according to the data set M and the maintenance type to establish a maintenance reference model corresponding to each maintenance working condition so as to construct a dynamic reference model A based on the maintenance type; according to variety specifications, energy consumption associated data of corresponding procedures are extracted from the data set Z in a grouping mode, energy consumption control references are established in each group, a category reference model is established according to an optimization target, and a dynamic reference model B based on the variety specifications is constructed; and extracting current actual performance data, and respectively and correspondingly matching the reference model A and the reference model B so as to calculate a comprehensive weight score to evaluate the health degree. Therefore, whether the process energy consumption is abnormal or not can be accurately sensed according to the collected data.

Description

Technical Field

[0001] The present invention relates to energy management and control technology, and in particular to a process energy consumption management and health assessment method and system, and a storage medium. Background Art

[0002] In the modern industrial manufacturing process, the energy management level of each manufacturing process is crucial to optimizing manufacturing costs, saving energy and reducing emissions. In typical manufacturing processes, such as large furnaces and production lines in the metallurgical industry, energy costs account for a high proportion, and energy utilization efficiency directly affects the operating benefits of the enterprise.

[0003] At present, most companies are equipped with necessary energy metering facilities and data collection equipment. For example, metallurgical blast furnace production lines often involve the use, recovery, and transfer of more than a dozen energy media, involving 200 to 500 energy collection instruments and more than 500 to 1,000 collection signals.

[0004] For typical processes, important energy efficiency monitoring indicators include process energy consumption, energy consumption per unit, etc. If refined management is required, managers must also conduct comprehensive energy analysis and diagnosis based on production conditions (output, variety, etc.) and operating parameters (such as fuel ratio and other energy performance parameters).

[0005] However, considering that the process energy management personnel of most enterprises have different abilities, observing the process energy consumption indicators can only reflect the daily energy consumption of the process and track the energy consumption changes of the process. However, if it is impossible to identify changes in production scale, product switching, maintenance, energy consumption structure, etc., it is easy to misjudge the fluctuations of related data, and even impossible to objectively evaluate whether the current production process energy consumption is normal through data, thereby weakening the management's control over energy management.

[0006] Therefore, how to enable process energy management personnel to quickly perceive problems in the energy system is of great value in improving management efficiency and level. Summary of the invention

[0007] To this end, the main purpose of the present invention is to provide a process energy consumption control health assessment method and system, and a storage medium, so as to accurately perceive whether the process energy consumption is abnormal based on the collected data.

[0008] In order to achieve the above object, according to one aspect of the present invention, a method for evaluating the health of process energy consumption control is provided, the steps comprising:

[0009] Collect historical data, build process energy consumption data set, and select maintenance period energy consumption data set M and production status data set Z;

[0010] According to the data set M, group analysis is performed according to the maintenance type to establish a maintenance benchmark model corresponding to each maintenance condition, thereby constructing a dynamic benchmark model A based on maintenance categories;

[0011] According to the product specifications, the energy consumption related data of the corresponding process are extracted from the data set Z in groups, and the energy consumption control benchmark is established in each group. The category benchmark model is established with the optimization goal, so as to construct the dynamic benchmark model B based on product specifications;

[0012] The current performance data is extracted and matched to the benchmark model A and benchmark model B respectively to calculate the comprehensive weighted score to evaluate the health status.

[0013] In a possible preferred embodiment, the step of constructing a dynamic benchmark model A based on maintenance categories includes:

[0014] The particle swarm optimization algorithm is used to find an optimal process energy consumption discount interval per unit time for each maintenance condition, and output the control interval combination of each production energy consumption unit based on the maintenance type.

[0015] In a possible preferred embodiment, the step of constructing a dynamic benchmark model B based on variety specifications includes:

[0016] Based on the category benchmark model, find the optimal control range of each production unit energy consumption parameter in the energy consumption performance, and output the control range combination of each production unit energy consumption parameter based on the variety specifications.

[0017] In a possible preferred embodiment, the step of calculating the comprehensive weight includes:

[0018] According to the energy consumption performance data of the current maintenance period, match the dynamic benchmark model A based on the maintenance category to calculate the evaluation score ;

[0019] According to the energy consumption performance data of the current production status, match the dynamic benchmark model B based on product specifications to calculate the evaluation score ;

[0020] Comprehensive evaluation score, calculate comprehensive weight score :

[0021]

[0022] in, They represent the scoring weights of maintenance and production energy consumption respectively.

[0023] In a possible preferred embodiment, the evaluation score The calculation steps include:

[0024] Assume that the energy consumption per unit of each production unit in the energy consumption performance data set during the maintenance period is ,set up For the i-th energy consumption data point in the set, define its score function as ,in, Represents data points The corresponding lower bound, upper bound, and average value of the benchmark interval;

[0025] Calculate the total evaluation score for the maintenance period:

[0026]

[0027] Where n is the number of data points in the energy consumption performance data set during the maintenance period;

[0028] Will Normalization processing, calculation:

[0029]

[0030] Among them, k is the adjustment parameter that controls the rising speed of the curve.

[0031] In a possible preferred embodiment, the evaluation score The calculation steps include:

[0032] Assume that the energy consumption per unit of each production in the production status energy consumption performance data set is , where j represents the variety and specification, let For the i-th data point of the j-th variety specification in the set, define its score function as ,in Represents data points The corresponding lower bound, upper bound, and average value of the benchmark interval;

[0033] Calculate the total evaluation score for the production period:

[0034]

[0035] Among them, K is the total number of varieties and specifications in the current data set, is the number of data points contained in each variety specification j;

[0036] Will Normalization processing, calculation:

[0037]

[0038] Where n' is the total number of data points in the production state energy consumption performance data set, and k' is the adjustment parameter for controlling the rising speed of the curve.

[0039] In a possible preferred embodiment, the step of calculating the comprehensive weight includes:

[0040] According to the energy consumption performance data of the current maintenance period, match the dynamic benchmark model A based on the maintenance category to calculate the evaluation score ;

[0041] According to the energy consumption performance data of the current production status, match the dynamic benchmark model B based on product specifications to calculate the evaluation score ;

[0042] Calculate the evaluation score of the current indicator achievement status based on the current indicator performance data ;

[0043] Comprehensive evaluation score, calculate comprehensive weight score :

[0044]

[0045] in, They respectively represent the scoring weights of maintenance, production energy consumption, and indicator compliance.

[0046] In a possible preferred implementation, the current indicator achievement score The calculation steps include:

[0047] According to the indicator performance data set, the initial score is determined by the achievement rate of the i-th indicator , calculate the initial score In the corresponding weight The following indicator scores:

[0048] ;

[0049] Calculate the total score of the indicator evaluation:

[0050]

[0051] Where M is the number of indicators in the indicator performance data set;

[0052] Normalization Obtain the evaluation score of the current indicator achievement status .

[0053] In order to achieve the above-mentioned purpose, corresponding to the above-mentioned method example, according to another aspect of the present invention, a process energy consumption control health assessment system is also provided, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the system implements the steps of any of the process energy consumption control health assessment methods described above.

[0054] In order to achieve the above-mentioned purpose, corresponding to the above-mentioned method example, according to another aspect of the present invention, a computer-readable storage medium is also provided, and the computer-readable storage medium stores a computer program, wherein when the computer program is executed, the steps of the process energy consumption control health assessment method as described in any of the above are implemented.

[0055] Through the process energy consumption control health assessment method and system, and storage medium provided by the present invention, a health evaluation scheme is proposed to incorporate the standardized production and energy consumption of the enterprise into tracking management. By comprehensively evaluating the process energy consumption performance data, managers can objectively and quickly perceive the operation of the entire energy system based on the evaluation scores, which helps to improve the overall control ability and management level of managers for energy management. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] The drawings constituting a part of this application are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0057] Figure 1 It is a schematic diagram of the steps of the process energy consumption control health evaluation method of the present invention;

[0058] Figure 2 It is a logical flow diagram of the process energy consumption control health evaluation method of the present invention;

[0059] Figure 3 It is a curve diagram of logarithmic normalization processing in the process energy consumption control health assessment method of the present invention;

[0060] Figure 4 It is a structural schematic diagram of the process energy consumption control health assessment system of the present invention. DETAILED DESCRIPTION

[0061] In order to enable those skilled in the art to better understand the technical solution of the present invention, the specific technical solution of the present invention will be clearly and completely described in conjunction with the embodiments below to help those skilled in the art further understand the present invention. Obviously, the embodiments described in this case are only embodiments of a part of the present invention, not all of the embodiments. It should be pointed out that for those of ordinary skill in the art, the embodiments in this application and the features in the embodiments can be combined with each other without departing from the concept of the present invention and without conflicting with each other. Based on the embodiments in the present invention, all other embodiments obtained without creative work by those of ordinary skill in the art should belong to the disclosure and protection scope of the present invention.

[0062] In addition, the terms "first", "second", "S100", "S200", etc. in the specification, claims and drawings of the present invention are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the features used in this way can be interchanged where appropriate, so that the embodiments of the present invention described here can be implemented in an order other than those described here. At the same time, the stages recorded in each step are not mandatory to be implemented in the same step. It should be understood that the implementation order of the contents in each step stage can be adjusted and interchanged without violating the inventive concept, so that the step embodiments of the present invention described here can be implemented in an order other than those described here. In addition, the terms "including" and "having" and any of their variations in the present invention are intended to cover non-exclusive inclusions. Unless otherwise clearly specified and limited, the terms "set", "layout", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected, or indirectly connected through an intermediate medium, or it can be the internal connection of two components. For ordinary technicians in this field, the specific meanings of the above terms in this case can be understood according to specific circumstances and in combination with the prior art.

[0063] In order to accurately perceive whether the process energy consumption is abnormal based on the collected process energy consumption correlation data, such as Figure 1 to Figure 2 As shown, the present invention provides a method for evaluating the health of process energy consumption control, and its exemplary steps include:

[0064] Step S100 collects historical data, constructs a process energy consumption data set, and selects a maintenance period energy consumption data set M and a production status data set Z from the data.

[0065] Specifically, in the metallurgical industry, each production enterprise will collect and record some energy consumption data according to its own production situation to provide an analysis basis for subsequent production management. Therefore, in this example, it is necessary to first find data related to process energy consumption in such data to construct a process energy consumption data set. For example, based on the process daily data, the data of the process energy consumption data set includes:

[0066] Process energy consumption data: data such as energy usage, recovery, unit consumption and unit cost obtained through calculation, allocation and totalization based on process measurement data.

[0067] Process production data: including process input and output data, as well as maintenance-related data, covering output, variety specifications, raw material input and maintenance plans / performance of each process unit.

[0068] Process indicator data: Energy efficiency evaluation indicators formed by summarizing various types of data, including process energy consumption, gas recovery rate, emission rate, etc.

[0069] Process production operation parameters: a set of parameters that reflect the production process of each section or area, including fuel ratio, temperature, pressure, etc.

[0070] At the same time, in terms of process energy consumption data, due to the large differences in data fluctuations and changes during the maintenance period and the normal production period, in this example, for fine management, it is preferred to divide the data in the process energy consumption data set into maintenance period energy consumption data and production status data according to the time period. The two contain data with different characteristics, for example:

[0071] Based on the maintenance performance in the process energy consumption data, a maintenance energy consumption feature set for a period of time is extracted from the data set, and the maintenance performance, energy consumption performance at the corresponding time, and energy consumption index data are integrated to form a maintenance period energy consumption data set M. Typically, this type of feature data should include: maintenance type, process hourly energy consumption conversion, maintenance duration, and corresponding electricity consumption, water consumption, gas consumption, compressed air consumption and other energy medium consumption data.

[0072] The process energy consumption data set excluding the maintenance period can be used as the production status data set Z for subsequent data analysis.

[0073] Step S200 performs group analysis based on the data set M according to the maintenance type to establish a maintenance benchmark model corresponding to each maintenance condition, thereby constructing a dynamic benchmark model A based on the maintenance category.

[0074] The group analysis example is to set a specific maintenance condition for each maintenance type so as to group the maintenance conditions and establish a maintenance benchmark model based on the data set of the condition.

[0075] For example, for each group, set an objective function , whose goal is to find an interval for each energy medium consumption data [ X * - ∆ X , X * + ∆ X ] , so that the hourly energy consumption of the process is minimized. Typically, the preferred example uses a particle swarm optimization algorithm to achieve this process.

[0076] Specifically, assume that the objective function is to minimize the function For a single particle i, let its position at any time be , its single point fitness function for:

[0077]

[0078] In the process of energy consumption analysis, this solution hopes to find the control range of various energy consumption data, rather than a certain value. Therefore, it is also necessary to check and evaluate the interval near the optimal point and expand the optimal point to the optimal interval. , used to detect the gradient near the optimal point of a particle i, and expand the optimal point to the optimal interval:

[0079]

[0080] When looking for the optimal interval, first Set an initial change , and then dynamically adjust the interval according to the fitness change through iteration , that is, to obtain a new , until it exceeds The reasonable value range or fitness function reaches the termination condition. It is related to the variation range of the feature, and its variation range is set based on experience. Assuming there is an adjustment coefficient k, its value range is (0.05, 0.3), which means that based on the maximum and minimum value range of the feature, the target interval length ratio is between 0.05 and 0.3.

[0081]

[0082]

[0083]

[0084] Among them, k is used to adjust the current particle value according to the change range ratio. scale is used to dynamically adjust The value is usually in the range of (0.5, 1.5). When the fitness increases, the scale can be reduced, such as 0.8; otherwise, it can be increased.

[0085] Combining the two optimization objectives, the comprehensive fitness function is:

[0086]

[0087] in, As the balance factor, 0,1], which is used to comprehensively consider the performance of the particle at a single point and the average performance in the nearby interval.

[0088] Assume that the historical optimal value is , then each particle compares the current individual fitness and , to update the optimal position of the particle until the global optimal solution is obtained , the solution corresponding to for .

[0089]

[0090]

[0091] At the same time, set the termination condition to reach the maximum number of iterations And the comprehensive fitness function reaches the convergence condition.

[0092]

[0093] in is the convergence value of the comprehensive fitness.

[0094] After the optimization is completed, the maximum number of iterations is output The optimal solution when and its optimal interval for:

[0095]

[0096] That is, the optimal range of particles (energy consumption characteristics) is: [ X * - ∆ X , X * + ∆ X ] This interval is the control benchmark range of each energy consumption. Under given maintenance type working conditions, it is used to set the control benchmark for maintenance workers to standardize energy consumption during maintenance to avoid waste such as not stopping when necessary and often opening.

[0097] Finally, based on the maintenance benchmark model corresponding to each maintenance condition established in the above example, the combination of energy consumption control intervals of each production unit based on the maintenance type is output, so as to construct a dynamic benchmark model A based on the maintenance category through the above steps.

[0098] Step S300 extracts the energy consumption related data of the corresponding process from the data set Z in groups according to the product specifications, establishes an energy consumption control benchmark in each group, and establishes a category benchmark model with the optimization goal, thereby constructing a dynamic benchmark model B based on product specifications.

[0099] Specifically, in this example, firstly, according to the variety and specifications of each product, data in the data set Z of the corresponding time period is extracted according to the production period, and then grouped according to the variety and specifications, and energy consumption and operation control benchmarks under normal production conditions are established within the group.

[0100] Secondly, within the group, the optimization goals are to minimize process energy consumption and maximize output, and a category benchmark model is established to find the optimal control range of each energy medium unit consumption, energy indicators, and production operation parameters in the energy consumption performance.

[0101] For example, suppose the dataset is the data set Z corresponding to the variety specification i. Typically, this example uses a clustering algorithm to perform regional division for multi-objective optimization.

[0102] According to user experience, the optimization target control range of process output, process energy consumption, etc. is set, and the data set is Screen and extract the sample set that meets the optimization goal.

[0103]

[0104] in, Represents the process energy consumption value in the data set, and its user-defined value range is [ , ]. Represents the production value of any group of data in the data set, and its user-defined value range is [ , ].

[0105] Using DBSCAN algorithm Clustering can be performed to automatically identify the number of clusters based on the silhouette coefficient method. Through clustering operations, some special conditions or outlier data can be separated.

[0106] In order to find the best group among all the clusters, it is also necessary to combine user experience and select the most representative cluster in the data set as the best. Typically, the number of sample points and silhouette coefficient of each cluster can be weighted and sorted to select the best cluster. .

[0107]

[0108]

[0109]

[0110]

[0111] in, is the i-th cluster, is the number of sample points in the ith cluster, represents the silhouette coefficient, is the average distance from the sample point to other points in the cluster, is the average distance from a sample point to the nearest cluster. is a weighted score based on the number of sample points and the silhouette coefficient, is the coefficient weight.

[0112]

[0113] According to the optimal clustering The minimum / maximum values ​​of each feature in the control benchmark can be obtained .

[0114] Finally, the energy consumption per unit of production, energy indicators, and production operation parameter control range combinations based on product varieties and specifications are output, which sets the energy consumption benchmark for the production and manufacturing of products with different product varieties and specifications. Based on this, the above steps are carried out to construct a dynamic benchmark model B based on product varieties and specifications.

[0115] In fact, the energy consumption benchmark set by the model requires production operators to control the unit energy consumption and energy indicators within the benchmark range based on given production operation parameters when producing a certain variety and specification of products. Therefore, it is also to achieve the purpose of reducing consumption.

[0116] Step S400 extracts the current performance data and matches them to the benchmark model A and the benchmark model B respectively, so as to calculate the comprehensive weight score to evaluate the health.

[0117] The steps for calculating the comprehensive weight include:

[0118] Step S410 matches the dynamic benchmark model A based on the maintenance category according to the energy consumption performance data of the current maintenance period to calculate the evaluation score .

[0119] The evaluation score The calculation steps include:

[0120] Step S411: Set the energy consumption per unit of each production unit in the energy consumption performance data set during the maintenance period to ,set up For the i-th energy consumption data point in the set, define its score function as .

[0121] For example, in this example, the score function is defined as:

[0122]

[0123] in, Represents data points The corresponding lower bound, upper bound, and average value of the benchmark interval,

[0124]

[0125] Step S412: Calculate the total evaluation score of the maintenance period , which is used to reflect the degree of compliance with the energy production and consumption benchmark during the maintenance process.

[0126]

[0127] Where n is the number of data points in the energy consumption performance data set during the maintenance period;

[0128] Step S412: To facilitate subsequent weighting, the scores Perform normalization to obtain the normalized score To ensure that both minor and major overshoots are observed, the example uses a logarithmic approach:

[0129]

[0130] Among them, k is the adjustment parameter for controlling the rising speed of the curve. It is used to control the rising speed of the curve. When the k value is large, Will be When it is smaller, it rises faster and then becomes flat. The recommended value is 10. Figure 3 shown.

[0131] Step S420 matches the dynamic benchmark model B based on product specifications according to the current production status energy consumption performance data to calculate the evaluation score ;

[0132] The evaluation score The calculation steps include:

[0133] Step S421: Set the energy consumption per unit of each production unit in the production status energy consumption performance data set to , where j represents the variety and specification, let For the i-th data point of the j-th variety specification in the set, define its score function as .

[0134] For example, in this example, the score function is defined as:

[0135]

[0136] in Represents data points The corresponding lower bound, upper bound, and average value of the benchmark interval,

[0137]

[0138] Step S422 calculates the total evaluation score of the production period to reflect the degree of compliance with the production and energy consumption benchmark during the maintenance process.

[0139]

[0140] Among them, K is the total number of varieties and specifications in the current data set, is the number of data points contained in each variety specification j;

[0141] Step S423: To facilitate subsequent weighting, the scores Perform normalization to obtain the normalized score In order to ensure that both minor and major overshoots can be observed, the logarithmic method is used.

[0142]

[0143] Where n' is the total number of data points in the production state energy consumption performance data set, and k' is the adjustment parameter for the control curve rising speed. Will be When it is smaller, it rises faster and then becomes flat. The recommended value is 10. Figure 3 shown.

[0144] Step S440 Comprehensive evaluation score, calculate comprehensive weight score , in order to evaluate the health of energy consumption control.

[0145]

[0146] in, They represent the scoring weights of maintenance and production energy consumption respectively.

[0147] The final score is based on the comprehensive weight , the health of energy consumption control can be evaluated, so that energy management personnel can quantitatively perceive the data status of the entire energy system, rather than perceiving it based on their own individual subjective experience, thereby improving the scientific level of management and facilitating timely subsequent management decisions.

[0148] In addition, in order to be able to combine the cumulative data of the KPI indicators of the month with the management and control objectives for evaluation, in another optional implementation, the step of calculating the comprehensive weight includes:

[0149] Step S410 matches the dynamic benchmark model A based on the maintenance category according to the energy consumption performance data of the current maintenance period to calculate the evaluation score , related examples can be implemented by referring to the same steps as above.

[0150] Step S420 matches the dynamic benchmark model B based on product specifications according to the current production status energy consumption performance data to calculate the evaluation score , related examples can be implemented by referring to the same steps as above.

[0151] Step S430: Calculate the current indicator achievement evaluation score based on the current indicator performance data. , example steps include:

[0152] Step S431 determines the preliminary score based on the achievement rate of the ith indicator in the indicator performance data set. , calculate the initial score In the corresponding weight The following indicator scores:

[0153] ;

[0154] Among them, the indicator performance data set can be the data of the cumulative indicators of the current month, which is used to reflect the deviation between the cumulative value of the current month and the control target value. Therefore, the score can be increased or decreased in combination with the enterprise KPI performance evaluation plan.

[0155] Assume that the KPI performance evaluation table for a typical process is as follows:

[0156]

[0157] Among them, the target value is the assessment target value of the current indicator. The indicator scoring method is used for evaluation based on manual or performance systems. Each indicator is measured as 100 points to calculate the indicator score. The weight is the weight of the indicator in the entire assessment indicator set. The sum of the weights of each process should be 1. The product of the score of each indicator in the process KPI indicator set and the weight coefficient is the weighted score of the indicator, which can be added up to get the total score of the department or position.

[0158] Accordingly, the result data after monthly evaluation are as follows:

[0159]

[0160] Step S432 Based on the above, the total score of the KPI indicator compliance of the process in the current month is:

[0161]

[0162] Where M is the number of indicators in the indicator performance dataset.

[0163] Step S433: Normalization processing Obtain the evaluation score of the current indicator achievement status .

[0164]

[0165] For example, according to the example above, the final score is 98.

[0166] S440 comprehensive evaluation score, calculate the comprehensive weight score , in order to evaluate the health of energy consumption control.

[0167]

[0168] in, They respectively represent the scoring weights of maintenance, production energy consumption, and indicator compliance.

[0169] The final score is based on the comprehensive weight , the health of energy consumption control can be evaluated, so that energy management personnel can quantitatively perceive the data status of the entire energy system, rather than perceiving it based on their own individual subjective experience, thereby improving the scientific level of management and facilitating timely subsequent management decisions.

[0170] On the other hand, corresponding to the above method, Figure 4 As shown, the present invention also provides a process energy consumption control health assessment system, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the system implements the steps of any of the process energy consumption control health assessment methods described above.

[0171] On the other hand, corresponding to the above method, the present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein when the computer program is executed, the steps of the process energy consumption control health assessment method as described in any of the above are implemented.

[0172] To sum up, through the process energy consumption control health assessment method and system, and storage medium provided by the present invention, a health evaluation scheme is proposed to incorporate the enterprise's standardized production and energy consumption into tracking management, and through a comprehensive evaluation of the process energy consumption performance data, managers can objectively and quickly perceive the operation of the entire energy system based on the evaluation scores, which helps to improve managers' overall control over energy management and management level.

[0173] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is only limited by the claims and their full scope and equivalents. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

[0174] Those skilled in the art can understand that, in addition to implementing the system, device, unit and its various modules provided by the present invention in a purely computer-readable program code, it is entirely possible to implement the same program in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers and embedded microcontrollers by logically programming the method steps. Therefore, the system, device and its various modules provided by the present invention can be considered as a hardware component, and the modules included therein for implementing various programs can also be regarded as structures within the hardware component; the modules for implementing various functions can also be regarded as both software programs for implementing the method and structures within the hardware component.

[0175] In addition, all or part of the steps in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a program, and the program is stored in a storage medium, including a number of instructions to enable a single-chip microcomputer, a chip or a processor to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), disk or optical disk and other media that can store program codes.

[0176] In addition, various implementations of the embodiments of the present invention may be arbitrarily combined, and as long as they do not violate the concept of the embodiments of the present invention, they should also be regarded as the contents disclosed in the embodiments of the present invention.

Claims

1. A method for evaluating the health of process energy consumption control, comprising the following steps: Collect historical data, build process energy consumption data set, and select maintenance period energy consumption data set M and production status data set Z; According to the data set M, group analysis is performed according to the maintenance type to establish a maintenance benchmark model corresponding to each maintenance condition, thereby constructing a dynamic benchmark model A based on maintenance categories; According to the product specifications, the energy consumption related data of the corresponding process are extracted from the data set Z in groups, and the energy consumption control benchmark is established in each group. The category benchmark model is established with the optimization goal, so as to construct the dynamic benchmark model B based on product specifications; The current performance data is extracted and matched to the benchmark model A and benchmark model B respectively to calculate the comprehensive weighted score to evaluate the health status.

2. According to the process energy consumption control health assessment method of claim 1, the step of constructing a dynamic benchmark model A based on maintenance categories comprises: The particle swarm optimization algorithm is used to find an optimal process energy consumption discount interval per unit time for each maintenance condition, and output the control interval combination of each production energy consumption unit based on the maintenance type.

3. According to the process energy consumption control health assessment method of claim 1, the step of constructing a dynamic benchmark model B based on product specifications comprises: Based on the category benchmark model, find the optimal control range of each production unit energy consumption parameter in the energy consumption performance, and output the control range combination of each production unit energy consumption parameter based on the variety specifications.

4. The process energy consumption control health assessment method according to claim 1, wherein the step of calculating the comprehensive weight comprises: According to the energy consumption performance data of the current maintenance period, match the dynamic benchmark model A based on the maintenance category to calculate the evaluation score ; According to the energy consumption performance data of the current production status, match the dynamic benchmark model B based on product specifications to calculate the evaluation score ; Comprehensive evaluation score, calculate comprehensive weight score : ， in, They represent the scoring weights of maintenance and production energy consumption respectively.

5. The process energy consumption control health evaluation method according to claim 4, wherein the evaluation score The calculation steps include: Assume that the energy consumption per unit of each production unit in the energy consumption performance data set during the maintenance period is ,set up For the i-th energy consumption data point in the set, define its score function as ,in, Represents data points The corresponding lower bound, upper bound, and average of the benchmark interval; Calculate the total evaluation score for the maintenance period: ， Where n is the number of data points in the energy consumption performance data set during the maintenance period; Will Normalization processing, calculation: ， Among them, k is the adjustment parameter that controls the rising speed of the curve.

6. The process energy consumption control health evaluation method according to claim 4, wherein the evaluation score The calculation steps include: Assume that the energy consumption per unit of each production in the production status energy consumption performance data set is , where j represents the variety and specification, let For the i-th data point of the j-th variety specification in the set, define its score function as ,in Represents data points The corresponding lower bound, upper bound, and average of the benchmark interval; Calculate the total evaluation score for the production period: ， Among them, K is the total number of varieties and specifications in the current data set, is the number of data points contained in each variety specification j; Will Normalization processing, calculation: ， Where n' is the total number of data points in the production state energy consumption performance data set, and k' is the adjustment parameter for controlling the rising speed of the curve.

7. The process energy consumption control health assessment method according to claim 1, wherein the step of calculating the comprehensive weight comprises: According to the energy consumption performance data of the current maintenance period, match the dynamic benchmark model A based on the maintenance category to calculate the evaluation score ; According to the energy consumption performance data of the current production status, match the dynamic benchmark model B based on product specifications to calculate the evaluation score ; Calculate the evaluation score of the current indicator achievement status based on the current indicator performance data ; Comprehensive evaluation score, calculate comprehensive weight score : ， in, They respectively represent the scoring weights of maintenance, production energy consumption, and indicator compliance.

8. The process energy consumption control health evaluation method according to claim 7, wherein the current indicator compliance evaluation score The calculation steps include: According to the indicator performance data set, the initial score is determined by the achievement rate of the i-th indicator , calculate the initial score In the corresponding weight The following indicator scores: ； Calculate the total score of the indicator evaluation: ； Where M is the number of indicators in the indicator performance data set; Normalization Obtain the evaluation score of the current indicator achievement status .

9. A process energy consumption control health assessment system, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the system implements the steps of the process energy consumption control health assessment method as described in any one of claims 1 to 8.

10. A computer-readable storage medium storing a computer program, wherein when the computer program is executed, the steps of the process energy consumption control health assessment method as described in any one of claims 1 to 8 are implemented.

Images