Engineering optimization method and system based on multidimensional features
Through the analysis and optimization of historical data of production equipment, the problem of equipment overload operation is solved, and the effects of energy consumption reduction, cost control and equipment life extension are achieved.
Patent Information
- Application Number
- CN202411696282.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-25
- Publication Date
- 2025-02-28
AI Technical Summary
In order to pursue the shortest time of production, existing production equipment will produce products, resulting in long-term overload work, reducing service life and increasing energy consumption and cost.
By obtaining and cleaning the historical data of production equipment, extracting production capacity and energy consumption data, analyzing data abnormalities, designing optimization solutions to avoid overload operation and extending the service life of the equipment.
It effectively avoids overload operation of production equipment, reduces energy consumption and costs, extends the service life of the equipment, and improves production efficiency.
Smart Images
Figure 00000000_0000_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of engineering optimization, and in particular to an engineering optimization method and system based on multi-dimensional features. Background Art
[0002] Engineering optimization is a systematic approach that aims to improve the performance, efficiency or cost-effectiveness of engineering projects, products or processes by improving design, processes or systems. It covers multiple fields and methods, usually including the following aspects: performance optimization, cost optimization, quality optimization, time optimization, and sustainable optimization.
[0003] In order to produce products in the shortest possible time, existing production equipment is often overloaded for a long time, which reduces its service life. Long-term overload operation causes the production equipment to overheat and abnormally increase energy consumption, which reduces profits and increases costs. Summary of the invention
[0004] In order to solve the above technical problems, an engineering optimization method and system based on multidimensional features are provided. The technical solution solves the problem proposed in the above background technology that the existing production equipment, in order to produce products in the shortest time, causes the production equipment to work at overload for a long time, thereby reducing its service life, and long-term overload operation causes the production equipment to have excessively high temperature, abnormally increase energy consumption, reduce profits and increase costs.
[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:
[0006] An engineering optimization method based on multi-dimensional features, comprising:
[0007] Obtain historical data of production equipment;
[0008] Perform data cleaning based on the historical data of production equipment to obtain complete historical data;
[0009] Extract features based on complete historical data to obtain relevant data, including production capacity data and energy consumption data;
[0010] Analyze relevant data to determine the first optimization plan for production equipment and obtain data anomalies;
[0011] Analyze data anomalies based on complete historical data and design the second optimization plan for production equipment;
[0012] The production equipment is produced according to the production equipment optimization plan, wherein the production equipment optimization plan is any one of the first production equipment optimization plan or the second production equipment optimization plan.
[0013] Preferably, the data cleaning is performed based on the historical data of the production equipment to obtain complete historical data, specifically comprising the following steps:
[0014] Classify the historical data of production equipment into different types to obtain different types of historical data;
[0015] Set up a heat map, use the heat map to find missing values for different types of historical data, and determine the location and type of missing values;
[0016] Calculate the mean of different types of historical data based on the missing value type to obtain filling data;
[0017] Fill in the missing value positions based on the filled data to obtain complete historical data;
[0018] The specific calculation formula for obtaining the filling data is:
[0019]
[0020] Where Di is the filling data; i is the number of filling data; Dj is different types of historical data; n is the number of different types of historical data.
[0021] Preferably, the feature extraction based on the complete historical data and obtaining the relevant data specifically include the following steps:
[0022] Use capacity information as a feature to extract features from complete historical data and obtain capacity data;
[0023] The energy consumption information is used as a feature to extract features from the complete historical data and obtain energy consumption data.
[0024] Preferably, the analysis based on the relevant data to determine the first optimization plan for the production equipment and obtaining the data abnormal points specifically comprises the following steps:
[0025] Normalizing the capacity data and the energy consumption data respectively to obtain normalized capacity data and normalized energy consumption data;
[0026] Draw curves based on the normalized capacity data and the normalized energy consumption data to obtain a normalized capacity curve and a normalized energy consumption curve;
[0027] Analyze and process based on the normalized capacity curve and the normalized energy consumption curve to obtain the approximate value of capacity-energy consumption;
[0028] Analyze and judge based on the approximate value of capacity-energy consumption to obtain data anomalies;
[0029] The specific calculation formula for obtaining the normalized data of production capacity and energy consumption is as follows:
[0030]
[0031] In the formula, Aα is the normalized capacity data or the normalized energy consumption data; Aβ is the capacity data or the energy consumption data; Amin is the minimum value of the capacity data or the energy consumption data; Amax is the maximum value of the capacity data or the energy consumption data; α is the number of normalized capacity data or the energy consumption data; β is the number of capacity data or the energy consumption data.
[0032] Preferably, the analysis and judgment based on the capacity-energy consumption approximate value to obtain data abnormal points specifically includes the following steps:
[0033] Setting a first threshold and a second threshold;
[0034] Determine the capacity-energy consumption approach value and the first threshold and the second threshold;
[0035] If the capacity-energy consumption approach value is greater than the first threshold or less than the second threshold, the data abnormal point is output;
[0036] If the capacity-energy consumption approximate value is less than or equal to the first threshold and greater than or equal to the second threshold, the capacity-energy consumption approximate value is normal, and the first optimization plan for the production equipment is designed.
[0037] Preferably, the first optimization scheme for designing production equipment specifically includes the following steps:
[0038] Get order information;
[0039] Analyze order information based on production capacity data and energy consumption data to obtain profit data;
[0040] Perform feature extraction on the complete historical data to obtain the temperature data corresponding to the production capacity data;
[0041] Analyze profit data based on temperature data to determine the best profit;
[0042] The specific calculation formula for obtaining the profit data is:
[0043]
[0044] In the formula, Mγ is the profit data; γ is the number of profit data under different energy consumption; M is the total order price; D is the order data; v is the number of products produced per unit time; Ec is the energy consumption of the production equipment per unit time; m1 is the price corresponding to the energy consumption of the production equipment per unit time; m2 is the price of the raw materials required for the order.
[0045] Preferably, the analyzing the profit data based on the temperature data to determine the optimal profit specifically comprises the following steps:
[0046] Based on the profit data, filter and process to obtain the maximum profit, that is:
[0047] Mmax=max(Mγ);
[0048] In the formula, Mmax is the maximum profit; max() is the maximum value function; Mγ is the profit data;
[0049] Determine the energy consumption data and production capacity data of the production equipment corresponding to the maximum profit;
[0050] The complete historical data is retrieved based on the energy consumption data and production capacity data of the production equipment corresponding to the maximum profit to obtain the temperature data corresponding to the maximum profit;
[0051] The best profit is determined based on the temperature data corresponding to the maximum profit.
[0052] Preferably, the determination of the optimum profit by judging the temperature data corresponding to the maximum profit specifically comprises the following steps:
[0053] Make a judgment based on the temperature data corresponding to the maximum profit and the set third threshold;
[0054] If the temperature data corresponding to the maximum profit is greater than the set third threshold, the production equipment is overloaded, and the maximum profit is re-selected for secondary judgment to determine the best profit;
[0055] If the temperature data corresponding to the maximum profit is less than or equal to the set third threshold value, the output production equipment is working normally, and the maximum profit is determined to be the optimal profit.
[0056] Preferably, the analyzing of data anomalies based on complete historical data and designing a second optimization plan for production equipment specifically comprises the following steps:
[0057] Based on the data anomaly point, the complete historical data is retrieved at any time to determine the time when the data anomaly point occurred;
[0058] Analyze the status of production equipment based on the time when data anomalies occur and determine the processing method of production equipment;
[0059] Inspect and repair production equipment according to its processing mode and identify equipment abnormalities;
[0060] Replace or repair parts of production equipment based on equipment abnormalities and obtain parts status;
[0061] Analyze production equipment based on parts status to determine revised energy consumption data and revised production capacity data;
[0062] A second optimization plan for production equipment is designed based on the corrected energy consumption data and the corrected production capacity data.
[0063] Furthermore, an engineering optimization system based on multidimensional features is proposed, which is used to implement the above-mentioned engineering optimization method based on multidimensional features, including:
[0064] A data storage module, wherein the data storage module is used to store historical data of production equipment;
[0065] A data processing module, wherein the data processing module is used to process the historical data of the production equipment to obtain complete historical data;
[0066] A data normalization module, wherein the data normalization module is used to normalize the capacity data and the energy consumption data to obtain normalized capacity data and normalized energy consumption data;
[0067] A curve drawing module, wherein the curve drawing module draws a curve according to the normalized capacity data and the normalized energy consumption data to obtain a normalized capacity curve and a normalized energy consumption curve;
[0068] A data calculation module, wherein the data calculation module performs calculations according to a normalized capacity curve and an energy consumption normalized curve to obtain an approximate value of capacity-energy consumption;
[0069] A data analysis module, wherein the data analysis module performs analysis based on the capacity-energy consumption approximate value to obtain a first optimization plan for production equipment and a second optimization plan for production equipment;
[0070] A control module is used to control data transmission and information interaction between modules.
[0071] Compared with the prior art, the present invention provides an engineering optimization method and system based on multi-dimensional features, which has the following beneficial effects:
[0072] The present invention obtains energy consumption data and production capacity data by analyzing historical data of production equipment, and combines and analyzes the energy consumption data and production capacity data to design an optimized production plan, determine the maximum profit of an order, avoid overloading of production equipment, and extend the service life of production equipment. In addition, the data abnormal points of production equipment are analyzed and the production equipment is repaired, which reduces energy consumption, improves production capacity, and extends its service life. BRIEF DESCRIPTION OF THE DRAWINGS
[0073] Figure 1 This is a flow chart of steps S100-S600 in an engineering optimization method based on multi-dimensional features proposed by the present invention;
[0074] Figure 2 This is a flow chart of steps S201-S204 in an engineering optimization method based on multi-dimensional features proposed by the present invention;
[0075] Figure 3 This is a flow chart of steps S301-S302 in an engineering optimization method based on multi-dimensional features proposed by the present invention;
[0076] Figure 4 This is a flow chart of steps S401-S404 in an engineering optimization method based on multi-dimensional features proposed by the present invention;
[0077] Figure 5 This is a flow chart of steps S4041-S4044 in an engineering optimization method based on multi-dimensional features proposed by the present invention;
[0078] Figure 6 This is a flow chart of steps S40441-S40444 in an engineering optimization method based on multi-dimensional features proposed by the present invention;
[0079] Figure 7 This is a flow chart of steps S404441-S404444 in an engineering optimization method based on multidimensional features proposed by the present invention;
[0080] Figure 8 This is a flow chart of steps S4044441-S4044443 in an engineering optimization method based on multidimensional features proposed in the present invention;
[0081] Fig. 9 This is a flow chart of steps S501-S506 in an engineering optimization method based on multi-dimensional features proposed by the present invention;
[0082] Fig.10 This is a structural block diagram of an engineering optimization system based on multidimensional features proposed by the present invention. DETAILED DESCRIPTION
[0083] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.
[0084] Reference Figure 1 As shown, an engineering optimization method based on multi-dimensional features includes:
[0085] S100, obtaining historical data of production equipment;
[0086] S200, performing data cleaning based on historical data of production equipment to obtain complete historical data;
[0087] S300, extracting features based on the complete historical data to obtain relevant data, where the relevant data includes production capacity data and energy consumption data;
[0088] S400, analyzing the relevant data, determining the first optimization plan for the production equipment, and obtaining data abnormal points;
[0089] S500, analyzing data anomalies based on complete historical data and designing a second optimization plan for production equipment;
[0090] S600, producing the production equipment according to the production equipment optimization plan, wherein the production equipment optimization plan is any one of the first production equipment optimization plan or the second production equipment optimization plan;
[0091] Those skilled in the art can understand that the capacity data and the energy consumption data are a pair of related features. Therefore, the historical data of the production equipment is extracted to obtain the capacity data and the energy consumption data, and the approximate values between the capacity data and the energy consumption data are analyzed to determine whether there are any abnormalities in the production equipment. If there are no abnormalities, the production equipment is optimized based on the relationship between the capacity and the energy consumption to select the best profit. If there are abnormalities, the abnormalities are repaired and then the production equipment is optimized to select the best profit.
[0092] Reference Figure 2 As shown, data cleaning is performed based on the historical data of the production equipment, and obtaining complete historical data specifically includes the following steps:
[0093] S201, classifying historical data of production equipment into different types to obtain different types of historical data;
[0094] S202, setting a heat map, searching for missing values for different types of historical data through the heat map, and determining the location and type of missing values;
[0095] Heatmaps represent missing values with special colors or marks (such as white or gray) to contrast with the colors of normal data. By observing the color distribution of the heatmap, you can find patterns or areas of missing data. If some areas are more uniform in color while other areas are more sparse, it may mean that the latter has more missing data;
[0096] S203, calculating the mean of different types of historical data based on the missing value type to obtain filling data;
[0097] S204, filling in the missing value positions based on the filling data to obtain complete historical data;
[0098] The specific calculation formula for obtaining the filling data is:
[0099]
[0100] Where Di is the filling data; i is the number of filling data; Dj is different types of historical data; n is the number of different types of historical data.
[0101] Reference Figure 3 As shown, feature extraction based on complete historical data and obtaining relevant data specifically include the following steps:
[0102] S301, extracting features from complete historical data using capacity information as features to obtain capacity data;
[0103] S302: Extract features from the complete historical data using the energy consumption information as features to obtain energy consumption data.
[0104] Reference Figure 4 As shown, based on the analysis of relevant data, determining the first optimization plan for production equipment and obtaining data anomalies specifically include the following steps:
[0105] S401, normalizing the capacity data and the energy consumption data respectively to obtain normalized capacity data and normalized energy consumption data;
[0106] S402, plotting curves according to the normalized capacity data and the normalized energy consumption data to obtain a normalized capacity curve and a normalized energy consumption curve;
[0107] S403, analyzing and processing based on the normalized capacity curve and the normalized energy consumption curve to obtain an approximate capacity-energy consumption value;
[0108] S404, analyzing and judging based on the capacity-energy consumption approximate value to obtain data abnormal points;
[0109] The specific calculation formula for obtaining the normalized data of production capacity and energy consumption is as follows:
[0110]
[0111] In the formula, Aα is the normalized capacity data or energy consumption data; Aβ is the capacity data or energy consumption data; Amin is the minimum value of the capacity data or energy consumption data; Amax is the maximum value of the capacity data or energy consumption data; α is the number of normalized capacity data or energy consumption data; β is the number of capacity data or energy consumption data;
[0112] It will be understood by those skilled in the art that the numerical values of production capacity and energy consumption may differ too greatly to observe their corresponding relationship in the same coordinate system. Therefore, through normalization calculation, the production capacity data and energy consumption data are limited to between 0 and 1, and then the normalized production capacity curve and the normalized energy consumption curve are drawn. The data anomalies are determined by analyzing the degree of convergence between the two curves.
[0113] Reference Figure 5 As shown in the figure, based on the capacity-energy consumption approximate value, analysis and judgment are performed to obtain data anomalies, which specifically includes the following steps:
[0114] S4041. Setting a first threshold and a second threshold;
[0115] S4042, judging the capacity-energy consumption approach value and the first threshold and the second threshold;
[0116] S4043, if the capacity-energy consumption approximate value is greater than the first threshold or less than the second threshold, output the data abnormal point;
[0117] S4044. If the capacity-energy consumption approximate value is less than or equal to the first threshold and greater than or equal to the second threshold, the capacity-energy consumption approximate value is normal, and a first optimization plan for production equipment is designed.
[0118] Reference Figure 6 As shown, the first optimization scheme for designing production equipment specifically includes the following steps:
[0119] S40441. Obtain order information;
[0120] S40442. Analyze order information based on production capacity data and energy consumption data to obtain profit data;
[0121] S40443. Extract features from the complete historical data to obtain temperature data corresponding to the production capacity data;
[0122] S40444. Analyze profit data based on temperature data to determine the best profit;
[0123] The specific calculation formula for obtaining the profit data is:
[0124]
[0125] In the formula, Mγ is the profit data; γ is the number of profit data under different energy consumption; M is the total order price; D is the order data; v is the number of products produced per unit time; Ec is the energy consumption of the production equipment per unit time; m1 is the price corresponding to the energy consumption of the production equipment per unit time; m2 is the price of the raw materials required for the order;
[0126] Those skilled in the art can understand that when the production capacity is increased, energy consumption will also increase and the profit may also decrease, but there is a balance value between production capacity and energy consumption, which enables the ordered products to be produced within the specified time with high profits. At the same time, the production equipment will not be overloaded, which extends the service life of the production equipment. Therefore, the best profit is determined by analyzing the temperature data. It should be noted that the best profit is not the maximum profit. The selection of the best profit is based on the protection of production equipment and the reduction of costs.
[0127] Reference Figure 7 As shown, the profit data is analyzed based on the temperature data to determine the optimal profit, which specifically includes the following steps:
[0128] S404441. Screening and processing based on profit data to obtain maximum profit, namely:
[0129] Mmax=max(M γ );
[0130] In the formula, Mmax is the maximum profit; max() is the maximum value function; M γ For profit data;
[0131] S404442. Determine the energy consumption data and production capacity data of the production equipment corresponding to the maximum profit;
[0132] S404443. Retrieve the complete historical data based on the energy consumption data and production capacity data of the production equipment corresponding to the maximum profit to obtain the temperature data corresponding to the maximum profit;
[0133] S404444. Perform judgment and processing based on the temperature data corresponding to the maximum profit to determine the optimal profit.
[0134] Reference Figure 8 As shown, based on the temperature data corresponding to the maximum profit, the judgment process is performed to determine the optimal profit, which specifically includes the following steps:
[0135] S4044441. Making a judgment based on the temperature data corresponding to the maximum profit and the set third threshold value;
[0136] S4044442. If the temperature data corresponding to the maximum profit is greater than the set third threshold value, the production equipment is overloaded, and the maximum profit is re-selected for secondary judgment to determine the best profit;
[0137] S4044443. If the temperature data corresponding to the maximum profit is less than or equal to the set third threshold value, the output production equipment is operating normally, and the maximum profit is determined to be the optimal profit;
[0138] In this embodiment, when the temperature of the production equipment is too high, it means that the production equipment is overloaded. Although the product is produced very quickly, the service life of the production equipment is reduced, the energy consumption will also increase, and the profit will also decrease. Therefore, by comparing the temperature data, it is determined whether the production equipment is overloaded.
[0139] Reference Fig. 9 As shown, based on the complete historical data, the data anomalies are analyzed and the second optimization plan for production equipment is designed, which specifically includes the following steps:
[0140] S501, based on the data anomaly point, perform a time search on the complete historical data to determine the time when the data anomaly point occurred;
[0141] S502, analyzing the state of the production equipment according to the time when the data abnormal point occurs, and determining the processing mode of the production equipment;
[0142] S503, inspect and repair the production equipment according to the processing method of the production equipment, and determine the abnormal points of the equipment;
[0143] S504, replace or repair parts of the production equipment according to the abnormal point of the equipment, and obtain the status of the parts;
[0144] S505, analyzing the production equipment based on the parts status, and determining the corrected energy consumption data and the corrected production capacity data;
[0145] S506, designing a second optimization plan for production equipment based on the corrected energy consumption data and the corrected production capacity data;
[0146] Those skilled in the art can understand that the equipment abnormality point may be that some parts of the production equipment are damaged or deformed, resulting in abnormality in the approximate value of production capacity-energy consumption. Therefore, through analysis of the approximate value of production capacity-energy consumption, it is determined what the processing method of the production equipment is when the data abnormality point appears at a certain moment. The abnormal parts of the production equipment are judged according to the processing method, and they are replaced. The production equipment after the replacement of parts is analyzed to determine the corrected energy consumption data and the corrected production capacity data, and to design a second optimization plan for the production equipment.
[0147] Reference Fig.10 As shown, an engineering optimization system based on multidimensional features is used to implement the above-mentioned engineering optimization method based on multidimensional features, including:
[0148] A data storage module, wherein the data storage module is used to store historical data of production equipment;
[0149] A data processing module, wherein the data processing module is used to process the historical data of the production equipment to obtain complete historical data;
[0150] A data normalization module, wherein the data normalization module is used to normalize the capacity data and the energy consumption data to obtain normalized capacity data and normalized energy consumption data;
[0151] A curve drawing module, wherein the curve drawing module draws a curve according to the normalized capacity data and the normalized energy consumption data to obtain a normalized capacity curve and a normalized energy consumption curve;
[0152] A data calculation module, wherein the data calculation module performs calculations according to a normalized capacity curve and an energy consumption normalized curve to obtain an approximate value of capacity-energy consumption;
[0153] A data analysis module, wherein the data analysis module performs analysis based on the capacity-energy consumption approximate value to obtain a first optimization plan for production equipment and a second optimization plan for production equipment;
[0154] A control module is used to control data transmission and information interaction between modules.
[0155] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.
Claims
1. An engineering optimization method based on multidimensional features, characterized in that: include: Obtain historical data of production equipment; Perform data cleaning based on the historical data of production equipment to obtain complete historical data; Extract features based on complete historical data to obtain relevant data, including production capacity data and energy consumption data; Analyze relevant data to determine the first optimization plan for production equipment and obtain data anomalies; Analyze data anomalies based on complete historical data and design the second optimization plan for production equipment; The production equipment is produced according to the production equipment optimization plan, wherein the production equipment optimization plan is any one of the first production equipment optimization plan or the second production equipment optimization plan.
2. The engineering optimization method based on multidimensional features according to claim 1, characterized in that: The data cleaning based on the historical data of the production equipment to obtain complete historical data specifically includes the following steps: Classify the historical data of production equipment into different types to obtain different types of historical data; Set up a heat map, use the heat map to find missing values for different types of historical data, and determine the location and type of missing values; Calculate the mean of different types of historical data based on the missing value type to obtain filling data; Fill in the missing value positions based on the filled data to obtain complete historical data; The specific calculation formula for obtaining the filling data is: Where Di is the filling data; i is the number of filling data; Dj is different types of historical data; n is the number of different types of historical data.
3. The engineering optimization method based on multidimensional features according to claim 2, characterized in that: The feature extraction based on the complete historical data and obtaining the relevant data specifically include the following steps: Use capacity information as a feature to extract features from complete historical data and obtain capacity data; The energy consumption information is used as a feature to extract features from the complete historical data and obtain energy consumption data.
4. The engineering optimization method based on multidimensional features according to claim 3 is characterized in that: The analysis based on the relevant data to determine the first optimization plan for the production equipment and obtain the data abnormal points specifically includes the following steps: Normalizing the capacity data and the energy consumption data respectively to obtain normalized capacity data and normalized energy consumption data; Draw curves based on the normalized capacity data and the normalized energy consumption data to obtain a normalized capacity curve and a normalized energy consumption curve; Analyze and process based on the normalized capacity curve and the normalized energy consumption curve to obtain the approximate value of capacity-energy consumption; Analyze and judge based on the approximate value of capacity-energy consumption to obtain data anomalies; The specific calculation formula for obtaining the normalized data of production capacity and energy consumption is as follows: In the formula, Aα is the normalized capacity data or the normalized energy consumption data; Aβ is the capacity data or the energy consumption data; Amin is the minimum value of the capacity data or the energy consumption data; Amax is the maximum value of the capacity data or the energy consumption data; α is the number of normalized capacity data or the energy consumption data; β is the number of capacity data or the energy consumption data.
5. The engineering optimization method based on multidimensional features according to claim 4 is characterized in that: The analysis and judgment based on the capacity-energy consumption approximation value to obtain data anomaly points specifically includes the following steps: Setting a first threshold and a second threshold; Determine the capacity-energy consumption approach value and the first threshold and the second threshold; If the capacity-energy consumption approach value is greater than the first threshold or less than the second threshold, the data abnormal point is output; If the capacity-energy consumption approximate value is less than or equal to the first threshold and greater than or equal to the second threshold, the capacity-energy consumption approximate value is normal, and the first optimization plan for the production equipment is designed.
6. The engineering optimization method based on multidimensional features according to claim 5, characterized in that: The first optimization scheme for designing production equipment specifically includes the following steps: Get order information; Analyze order information based on production capacity data and energy consumption data to obtain profit data; Perform feature extraction on the complete historical data to obtain the temperature data corresponding to the production capacity data; Analyze profit data based on temperature data to determine the best profit; The specific calculation formula for obtaining the profit data is: In the formula, Mγ is the profit data; γ is the number of profit data under different energy consumption; M is the total order price; D is the order data; v is the number of products produced per unit time; Ec is the energy consumption of the production equipment per unit time; m1 is the price corresponding to the energy consumption of the production equipment per unit time; m2 is the price of the raw materials required for the order.
7. The engineering optimization method based on multidimensional features according to claim 6 is characterized in that: The analysis of profit data based on temperature data to determine the optimal profit specifically includes the following steps: Based on the profit data, filter and process to obtain the maximum profit, that is: Mmax=max(Mγ); In the formula, Mmax is the maximum profit; max() is the maximum value function; Mγ is the profit data; Determine the energy consumption data and production capacity data of the production equipment corresponding to the maximum profit; The complete historical data is retrieved based on the energy consumption data and production capacity data of the production equipment corresponding to the maximum profit to obtain the temperature data corresponding to the maximum profit; The best profit is determined based on the temperature data corresponding to the maximum profit.
8. The engineering optimization method based on multidimensional features according to claim 7 is characterized in that: The determination of the optimal profit based on the temperature data corresponding to the maximum profit specifically includes the following steps: Make a judgment based on the temperature data corresponding to the maximum profit and the set third threshold; If the temperature data corresponding to the maximum profit is greater than the set third threshold, the production equipment is overloaded, and the maximum profit is re-selected for secondary judgment to determine the best profit; If the temperature data corresponding to the maximum profit is less than or equal to the set third threshold value, the output production equipment is working normally, and the maximum profit is determined to be the optimal profit.
9. The engineering optimization method based on multidimensional features according to claim 1, characterized in that: The analysis of data anomalies based on complete historical data and the design of a second optimization plan for production equipment specifically include the following steps: Based on the data anomaly point, the complete historical data is retrieved at any time to determine the time when the data anomaly point occurred; Analyze the status of production equipment based on the time when data anomalies occur and determine the processing method of production equipment; Inspect and repair production equipment according to its processing mode and identify equipment abnormalities; Replace or repair parts of production equipment based on equipment abnormalities and obtain parts status; Analyze production equipment based on parts status to determine revised energy consumption data and revised production capacity data; A second optimization plan for production equipment is designed based on the corrected energy consumption data and the corrected production capacity data.
10. An engineering optimization system based on multidimensional features, used to implement an engineering optimization method based on multidimensional features as claimed in any one of claims 1 to 9, characterized in that: include: A data storage module, wherein the data storage module is used to store historical data of production equipment; A data processing module, wherein the data processing module is used to process the historical data of the production equipment to obtain complete historical data; A data normalization module, wherein the data normalization module is used to normalize the capacity data and the energy consumption data to obtain normalized capacity data and normalized energy consumption data; A curve drawing module, wherein the curve drawing module draws a curve according to the normalized capacity data and the normalized energy consumption data to obtain a normalized capacity curve and a normalized energy consumption curve; A data calculation module, wherein the data calculation module performs calculations according to a normalized capacity curve and an energy consumption normalized curve to obtain an approximate value of capacity-energy consumption; A data analysis module, wherein the data analysis module performs analysis based on the capacity-energy consumption approximate value to obtain a first optimization plan for production equipment and a second optimization plan for production equipment; A control module is used to control data transmission and information interaction between modules.