Intelligent power supply and distribution system for generators to coordinate power demand of cooling circulation system

Abstract

The present invention provides an intelligent power supply and distribution system for generators that coordinates the power demand of a cooling circulation system, comprising: a power consumption record acquisition module that extracts historical power consumption data of a heat treatment furnace and a cooling circulation system; a power consumption inertia analysis module that performs multi-dimensional correlation periodic analysis on first power consumption data and second power consumption data to obtain multi-dimensional power consumption inertia data; a personalized inertia analysis module that analyzes multi-dimensional personalized power consumption inertia data based on the multi-dimensional power consumption inertia data and corresponding input conditions; a power supply and distribution plan generation module that generates a generator coordinated power supply and distribution plan based on the target input condition of the current production instance; and an intelligent power supply and distribution module that performs power supply and distribution based on the generator coordinated power supply and distribution plan, so as to realize intelligent and flexible power supply and distribution of the generator to the heat treatment furnace and the cooling circulation system to meet the corresponding power demand when the heat treatment furnace and the cooling circulation system have different input conditions, thereby reducing redundant occupancy of the generator and reducing waste.

Description

Technical Field

[0001] The present invention relates to the technical field of generator power supply and distribution, and in particular to an intelligent generator power supply and distribution system for coordinating power demand of a cooling circulation system. Background Art

[0002] At present, graphene thermal conductive film undergoes two heat treatments during the production process: carbonization and graphitization. During the heat treatment process, the temperature inside the heat treatment furnace is increased, and the temperature outside the furnace is kept below the safe temperature through the cooling circulation system. The normal operation of the heat treatment furnace and the cooling circulation system requires sufficient power supply. If the power supply to the heat treatment furnace is insufficient, the temperature inside the furnace will decrease, causing air to enter the heat treatment furnace, and then causing the processed products in the heat treatment furnace to oxidize at high temperatures. If the power supply to the cooling circulation system is insufficient, the cooling effect of the cooling circulation system will be reduced, resulting in extremely high temperatures in the workshop, leading to serious safety accidents. Therefore, in order to avoid the above situation, the existing heat treatment workshop of graphene thermal conductive film will prepare multiple generators to ensure the normal operation of the heat treatment furnace and the cooling circulation system.

[0003] However, since the power requirements of different heat treatment furnaces and cooling circulation systems in different production instances are different and difficult to calculate accurately, a large number of generators used as backup power sources are redundantly occupied in actual production, resulting in a waste of resources and an increase in production costs.

[0004] Therefore, the present invention proposes an intelligent power supply and distribution system for generators that coordinates the power demand of a cooling circulation system. Summary of the invention

[0005] The present invention provides an intelligent power supply and distribution system for generators that coordinates the power demand of a cooling circulation system, which is used to determine the multi-dimensional power inertia data of the heat treatment furnace and the cooling circulation system in the production process without input based on the multi-dimensional correlation periodic analysis of the historical power consumption data of each heat treatment furnace and the cooling circulation system in each production instance, and further generate a reasonable power supply and distribution plan for the generator based on the target input situation and the multi-dimensional power inertia data, so as to realize intelligent and flexible power supply and distribution based on the generator to meet the corresponding power demand under different input situations of the heat treatment furnace and the cooling circulation system, thereby reducing the redundant occupancy of the generator and reducing waste.

[0006] The present invention provides a generator intelligent power supply and distribution system for coordinating the power demand of a cooling circulation system, comprising:

[0007] An electricity consumption record acquisition module is used to extract the first historical electricity consumption data of each heat treatment furnace and the second historical electricity consumption data of each cooling circulation system from the historical electricity consumption data of each production instance;

[0008] An electricity consumption inertia analysis module is used to perform multi-dimensional correlation periodic analysis on the first electricity consumption data and the second electricity consumption data of each production instance to obtain multi-dimensional electricity consumption inertia data;

[0009] The personalized inertia analysis module is used to analyze the multi-dimensional personalized power inertia data of each complete combination of hot and cold equipment based on the multi-dimensional power inertia data and the input of the heat treatment furnace and cooling circulation system in each production instance;

[0010] The power supply and distribution plan generation module is used to generate a generator coordinated power supply and distribution plan based on the target input of the current production instance;

[0011] The intelligent power supply and distribution module is used to supply and distribute power based on the generator coordinated power supply and distribution plan to obtain intelligent power supply and distribution results.

[0012] Preferably, the electrical inertia analysis module includes:

[0013] The cycle division submodule is used to perform associated cycle division on the first power consumption data of the heat treatment furnace and the second power consumption data of the cooling cycle system used in combination in the same production instance, and obtain the first single-cycle power consumption data of multiple cycles of the heat treatment furnace and the second single-cycle power consumption data of the cooling cycle system;

[0014] The inertia analysis submodule is used to average all single-cycle power consumption data of the same power-consuming object in the same production instance to obtain the power consumption inertia data of each power-consuming object in each production instance;

[0015] The association analysis submodule is used to treat the linear relationship between the first single-cycle power consumption data of the heat treatment furnace and the second single-cycle power consumption data of the cooling circulation system used in combination in each production instance as the power consumption coordination association inertia data of the heat treatment furnace and the cooling circulation system used in combination in the corresponding production instance;

[0016] Among them, electricity users include: heat treatment furnace and cooling circulation system;

[0017] The single-cycle power consumption data includes: first single-cycle power consumption data and second single-cycle power consumption data;

[0018] The multi-dimensional electricity consumption inertia data includes: electricity consumption inertia data and electricity consumption coordination associated inertia data.

[0019] Preferably, the period division submodule includes:

[0020] An equipment association unit, used to associate the heat treatment furnace and the cooling circulation system used in combination in the same production instance to obtain at least one group of hot and cold equipment;

[0021] A cycle analysis unit, used to periodically analyze the first power consumption data of the heat treatment furnace and the second power consumption data of the cooling circulation system included in the cold and hot equipment group, and determine the first power consumption cycle of the heat treatment furnace and the second power consumption cycle of the cooling circulation system;

[0022] The comprehensive cycle determination unit is used to take the least common multiple of the first power usage cycle and the second power usage cycle as the comprehensive power usage cycle of the corresponding cold and hot equipment group in the corresponding production instance.

[0023] Preferably, the cycle analysis unit comprises:

[0024] A target determination subunit, configured to use a power consumption variation curve corresponding to the first power consumption data of the heat treatment furnace included in the cold and hot equipment group and a power consumption variation curve corresponding to the second power consumption data of the cooling circulation system as target curves;

[0025] The precision determination subunit is used to determine the first interval time of all adjacent peaks and the second interval time of all adjacent valleys in the target curve, perform correlation denoising on the first interval time and the second interval time to obtain multiple comprehensive interval times, and determine the local division interval based on the mean value and analysis precision of all comprehensive interval times in the target curve;

[0026] The cycle determination subunit is used to locally divide the target curve based on the local division interval and perform adjacent cluster analysis to determine the first power consumption cycle of the heat treatment furnace or the second power consumption cycle of the cooling circulation system.

[0027] Preferably, the accuracy determination subunit comprises:

[0028] A change point detection end, used for determining the first mutation points in all first intervals of the target curve and the second mutation points in all second intervals of the target curve based on a change point detection algorithm;

[0029] An ordinal number determination terminal is used to determine the first ordinal number of the peak value with a later order among the adjacent peak values ​​corresponding to the first mutation point among all the peak values ​​of the target curve, and at the same time, determine the second ordinal number of the valley value with a later order among the adjacent valley values ​​corresponding to the second mutation point among all the valley values ​​of the target curve;

[0030] The associated denoising end is used to determine whether the ordinal difference between the first ordinal number and the second ordinal number which is greater than the first ordinal number and has the smallest difference with the first ordinal number is within the ordinal difference threshold, and if so, the first interval time corresponding to the corresponding first mutation point and the second gradual change time corresponding to the corresponding second mutation point are deleted at the same time, and all the remaining first interval times and second interval times are regarded as all comprehensive interval times;

[0031] The sequence generation end is used to determine the common factors of the mean values ​​of all comprehensive interval times and the durations of all target curves, and sort the common factors from large to small to obtain a common factor sequence;

[0032] The interval determination end is used to take the common factor in the common factor sequence whose sorting order is the same as the preset minimum number of clustering analyses as the maximum duration, and the ratio of the mean of the comprehensive interval time to the duration corresponding to the analysis accuracy as the minimum duration, and determine the local division interval based on the minimum duration and the maximum interval time.

[0033] Preferably, the period determination subunit comprises:

[0034] The local analysis end is used to locally divide the target curve based on the local division interval, obtain multiple sub-target curves and corresponding local division intervals, and calculate the first-order derivative integral value of each sub-target curve in the corresponding local division interval;

[0035] The cluster analysis end is used to perform adjacent cluster analysis on the first-order derivative integral values ​​of all sub-target curves in the target curve to obtain adjacent cluster division results;

[0036] The cycle determination end is used to connect the local division intervals of the sub-target curves corresponding to the first-order derivative integral values ​​belonging to the same cluster in the adjacent clustering division results to obtain the single-cycle division interval, and regard the duration of the single-cycle division interval of each target curve as the first power consumption cycle of the corresponding heat treatment furnace or the second power consumption cycle of the cooling circulation system.

[0037] Preferably, the cluster analysis end includes:

[0038] The sequential summary sub-terminal is used to summarize the first-order derivative integral values ​​of all sub-target curves in the target curve in sequence to obtain an integral value sequence;

[0039] The cluster analysis sub-terminal is used to divide the integral value sequence in sequence based on the division multiples in the preset increasing division multiples sequence to obtain multiple integral value clusters for each division multiple, and at the same time, calculate the similarity of all integral value clusters for each division multiple, until the similarity obtained in this division process is less than the similarity obtained in the previous division process, then the integral value cluster obtained in the previous division process is regarded as the adjacent cluster division result.

[0040] Preferably, the personalized inertia analysis module includes:

[0041] The first analysis submodule is used to analyze the first personalized power consumption inertia data of each heat treatment furnace object when the complete cold and hot equipment corresponding to the corresponding production instance is put into use based on the first power consumption inertia data of each heat treatment furnace in each production instance;

[0042] The second analysis submodule is used to analyze the second personalized power consumption inertia data of each cooling cycle system object when the complete cold and hot equipment corresponding to the corresponding production instance is put into use based on the second power consumption inertia data of each cooling cycle system in each production instance;

[0043] The third analysis submodule is used to analyze the personalized power consumption coordination associated inertia data of each cold and hot equipment group in each complete cold and hot equipment investment combination based on the power consumption coordination associated inertia data of each cold and hot equipment group in the corresponding production instance;

[0044] Among them, the multi-dimensional personalized electricity consumption inertia data includes: first personalized electricity consumption inertia data, second personalized electricity consumption inertia data, and personalized electricity consumption coordination associated inertia data.

[0045] Preferably, the power supply and distribution plan generation module includes:

[0046] The input situation determination submodule is used to determine the target complete cold and hot equipment input combination of the target input situation of the current production instance;

[0047] A first power consumption prediction submodule is used to retrieve the first personalized power consumption inertia data of each heat treatment furnace object in the heat treatment furnace input combination consistent with the target heat treatment furnace input combination from the multi-dimensional personalized power consumption inertia data, and use it as the first predicted power consumption data corresponding to the target heat treatment furnace object;

[0048] The second power consumption prediction submodule is used to retrieve the second personalized power consumption inertia data of each cooling cycle system object in the cooling cycle system input combination consistent with the target cooling cycle system input combination from the multi-dimensional personalized power consumption inertia data, and use it as the second predicted power consumption data corresponding to the target cooling cycle system;

[0049] A bidirectional correction submodule is used to bidirectionally correct the first predicted power consumption data and the second predicted power consumption data based on the personalized power consumption coordination associated inertia data of each cold and hot equipment group in the target complete cold and hot equipment investment combination in the multi-dimensional personalized power consumption inertia data, so as to obtain the final predicted power consumption data of each target heat treatment furnace and the target cooling cycle system;

[0050] The power supply and distribution plan generation submodule is used to generate a generator coordinated power supply and distribution plan based on the final predicted power consumption data.

[0051] Preferably, the bidirectional correction submodule includes:

[0052] The first calculation unit is used to substitute the first predicted power consumption data of each target heat treatment furnace into the linear relationship corresponding to the personalized power consumption coordination associated inertia data of the corresponding cold and hot equipment group in the target complete cold and hot equipment investment combination, and obtain the third predicted power consumption data of the corresponding target cooling cycle system;

[0053] The second calculation unit is used to substitute the second predicted power consumption data corresponding to each target cooling cycle system into the linear relationship corresponding to the personalized power consumption coordination associated inertia data of the corresponding cooling and heating equipment group in the target complete cooling and heating equipment investment combination, so as to obtain the fourth predicted power consumption data corresponding to the target cooling cycle system;

[0054] The final prediction unit is used to take the larger value of the first predicted power consumption data and the fourth predicted power consumption data of each target heat treatment furnace as the final predicted power consumption data of the corresponding target heat treatment furnace, and at the same time, take the larger value of the second predicted power consumption data and the third predicted power consumption data of each cooling circulation system as the final predicted power consumption data of the corresponding cooling circulation system.

[0055] The beneficial effects of the present invention compared with the prior art are as follows: based on a multi-dimensional correlation periodic analysis of the historical power consumption data of each heat treatment furnace and cooling cycle system in each production instance, the multi-dimensional power consumption inertia data of the heat treatment furnace and the cooling cycle system under different input conditions in the generation process are determined, and the multi-dimensional power consumption inertia data is further analyzed based on the complete hot and cold equipment input combination corresponding to the same input condition, and the personalized power consumption inertia data of different heat treatment furnaces and cooling cycle systems in different complete hot and cold equipment input combinations (i.e., multi-dimensional personalized power consumption inertia data) are obtained, and further based on the target input condition and the multi-dimensional personalized power consumption inertia data, a reasonable power supply and distribution plan of the generator is generated, so as to realize the intelligent and flexible power supply and distribution of the generator to the heat treatment furnace and the cooling cycle system, so as to meet the corresponding power demand under different input conditions of the heat treatment furnace and the cooling cycle system, thereby reducing the redundant occupancy of the generator and reducing waste.

[0056] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings.

[0057] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0059] Figure 1 A schematic diagram of an intelligent power supply and distribution system for a generator that coordinates power demand of a cooling circulation system in an embodiment of the present invention;

[0060] Figure 2 A schematic diagram of another intelligent power supply and distribution system for a generator for coordinating power demand of a cooling circulation system in an embodiment of the present invention;

[0061] Figure 3 Schematic diagram of another intelligent power supply and distribution system for a generator for coordinating the power demand of a cooling circulation system in an embodiment of the present invention. DETAILED DESCRIPTION

[0062] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0063] Embodiment 1:

[0064] The present invention provides a generator intelligent power supply and distribution system for coordinating the power demand of the cooling circulation system, referring to Figure 1 ,include:

[0065] An electricity consumption record acquisition module is used to extract the first historical electricity consumption data of each heat treatment furnace and the second historical electricity consumption data of each cooling circulation system from the historical electricity consumption data of each production instance;

[0066] An electricity consumption inertia analysis module is used to perform multi-dimensional correlation periodic analysis on the first electricity consumption data and the second electricity consumption data of each production instance to obtain multi-dimensional electricity consumption inertia data;

[0067] The personalized inertia analysis module is used to analyze the multi-dimensional personalized power inertia data of each complete hot and cold equipment investment combination (that is, the combination of all heat treatment furnaces and cooling circulation systems invested in the production process in a single production instance) based on the multi-dimensional power inertia data and the investment status of the heat treatment furnace and cooling circulation system in each production instance (that is, the heat treatment furnace object and cooling circulation system object invested in the production process in each production instance. Because there are different power demands between heat treatment furnaces and different power demands between cooling circulation systems, the heat treatment furnace object and the cooling circulation system object represent a specific heat treatment furnace and cooling circulation system.

[0068] The power supply and distribution plan generation module is used to generate a generator coordinated power supply and distribution plan based on the target input of the current production instance;

[0069] The intelligent power supply and distribution module is used to supply and distribute power based on the generator coordinated power supply and distribution plan to obtain intelligent power supply and distribution results.

[0070] In this embodiment, the production workshop of the graphene thermal conductive film in the present invention includes multiple heat treatment furnaces with high heating power, and each heat treatment furnace needs to be equipped with a cooling circulation system to cool the outer surface temperature of the furnace during the production process. Because the production requirements of each production instance are different, the heat treatment furnace and cooling circulation system invested in each production instance are different. Among them, the cooling circulation system can adopt a cooling circulation method such as circulating cooling water.

[0071] In this embodiment, the dimensions in the multi-dimensional correlation periodicity analysis include: a heat treatment furnace dimension, a cooling cycle system dimension, and a correlation relationship dimension between the heat treatment furnace dimension and the cooling cycle system dimension;

[0072] The correlation periodicity analysis is to align the first power consumption data of the heat treatment furnace and the second power consumption data of the cooling circulation system, consider the periodicity of both at the same time, determine the period that satisfies the periodic change characteristics of both, and regard the change characteristics of the first power consumption data and the second power consumption data within a single cycle and the change characteristics of the linear relationship between the first power consumption data and the second power consumption data within a single cycle as multi-dimensional power consumption inertia data.

[0073] In this embodiment, the production instance is an instance record of relevant data of the production plan of the entire graphene thermal conductive film. The completed production instance will record the electricity consumption data of each heat treatment furnace and each cooling circulation system. The unfinished production instance does not have the electricity consumption data of each heat treatment furnace and each cooling circulation system, but there are heat treatment furnace objects and cooling circulation system objects that need to be put into production in the production instance.

[0074] In this embodiment, the multi-dimensional personalized power inertia data includes: the power inertia data corresponding to each heat treatment furnace when each complete cold and hot equipment investment combination is put into operation, the power inertia data corresponding to each cooling cycle system when each complete cold and hot equipment investment combination is put into operation, and the inertia data corresponding to the linear relationship between each group of heat treatment furnaces and cooling cycle systems used in combination when each complete cold and hot equipment investment combination is put into operation;

[0075] In this embodiment, the inertial data are all the average values ​​of all original sample data of the corresponding type, for example:

[0076] The power consumption inertia data corresponding to each heat treatment furnace under the conditions corresponding to each complete combination of cold and hot equipment is: the curve data obtained by aligning, adding and averaging the power consumption curves corresponding to all the first historical power consumption data of each heat treatment furnace under the conditions corresponding to each complete combination of cold and hot equipment.

[0077] In this embodiment, the current production instance requires the use of the steps in this embodiment to generate in advance its generator coordinated power supply and distribution plan, and then power supply and distribution are performed based on the generator coordinated power supply and distribution plan to complete the current production instance.

[0078] In this embodiment, the target input situation is the heat treatment furnace object and cooling cycle system object that need to be put into production to complete the current production instance determined based on the current production instance.

[0079] In this embodiment, the generator coordinated power supply and distribution plan is: a real-time change curve of the amount of electricity that needs to be provided to each heat treatment furnace and each cooling circulation system included in the target input situation in the process of completing the current production instance.

[0080] In this embodiment, the intelligent power supply and distribution result is the result of supplying and distributing power to each heat treatment furnace and each cooling circulation system included in the target input situation based on the generator coordinated power supply and distribution plan.

[0081] The beneficial effects of the above technology are: based on the multi-dimensional correlation periodic analysis of the historical power consumption data of each heat treatment furnace and cooling cycle system in each production instance, the multi-dimensional power consumption inertia data of the heat treatment furnace and the cooling cycle system under different input conditions in the generation process is determined, and the multi-dimensional power consumption inertia data is further analyzed based on the complete hot and cold equipment input combination corresponding to the same input situation, and the personalized power consumption inertia data of different heat treatment furnaces and cooling cycle systems in different complete hot and cold equipment input combinations (i.e., multi-dimensional personalized power consumption inertia data) is obtained, and further based on the target input situation and the multi-dimensional personalized power consumption inertia data, a reasonable power supply and distribution plan of the generator is generated, so as to realize the intelligent and flexible power supply and distribution of the generator to the heat treatment furnace and the cooling cycle system, so as to meet the corresponding power demand under different input conditions of the heat treatment furnace and the cooling cycle system, thereby reducing the redundant occupancy of the generator and reducing waste.

[0082] Embodiment 2:

[0083] Based on Example 1, the electrical inertia analysis module is used, referring to Figure 2 ,include:

[0084] The period division submodule is used to perform associated period division on the first power consumption data of the heat treatment furnace and the second power consumption data of the cooling circulation system used in combination in the same production instance (that is, after aligning the first power consumption data of the heat treatment furnace and the second power consumption data of the cooling circulation system, the periodicity of the two is considered at the same time, and a period that satisfies the periodic change characteristics of the two is determined, and the first power consumption data and the second power consumption data are periodically divided based on the period), to obtain the first single-cycle power consumption data of multiple cycles of the heat treatment furnace (the power consumption data obtained after the first power consumption data is periodically divided) and the second single-cycle power consumption data of the cooling circulation system (the data obtained after the second power consumption data is periodically divided);

[0085] The first power consumption data and the second power consumption data are divided into associated periods so that the time span of the first single-cycle power consumption data and the second single-cycle power consumption data obtained is consistent, which facilitates the subsequent analysis of the linear relationship between the two;

[0086] The inertia analysis submodule is used to average all single-cycle power consumption data of the same power-consuming object in the same production instance (i.e., align the horizontal coordinates of the power consumption change curves corresponding to all single-cycle power consumption data, add the vertical coordinates and average them to obtain a new power consumption curve), and obtain the power consumption inertia data of each power-consuming object in each production instance;

[0087] Based on the average result of all single-cycle power consumption data of the same power-consuming object in the same production instance after period division, the inertial distribution characteristics of the power consumption of the corresponding production instance in a single cycle are realized, wherein the inertial distribution characteristics are general characteristics that can represent the change of its power consumption over time in a single cycle;

[0088] The association analysis submodule is used to treat the linear relationship between the first single-cycle power consumption data of the heat treatment furnace and the second single-cycle power consumption data of the cooling cycle system used in combination in each production instance (expressed by a functional relationship, the power consumption in the first single-cycle power consumption data of the heat treatment furnace is the independent variable of the function corresponding to the linear relationship, and the power consumption in the second single-cycle power consumption data of the cooling cycle system is the dependent variable of the function corresponding to the linear relationship) as the power consumption coordination association inertia data of the heat treatment furnace and the cooling cycle system used in combination in the corresponding production instance;

[0089] Among them, electricity users include: heat treatment furnace and cooling circulation system;

[0090] The single-cycle power consumption data includes: first single-cycle power consumption data and second single-cycle power consumption data;

[0091] The multi-dimensional electricity consumption inertia data includes: electricity consumption inertia data and electricity consumption coordination associated inertia data.

[0092] The beneficial effect of the above technology is: by aligning and averaging the power consumption data of the heat treatment furnace and the cooling cycle system after dividing them into related periods, the general characteristics of their power consumption changes over time in a single cycle (i.e., power inertia data) and the linear relationship between the power consumption data of the heat treatment furnace and the cooling cycle system used in combination in a single cycle can be analyzed.

[0093] Embodiment 3:

[0094] Based on Example 2, the period is divided into submodules, refer to Figure 3 ,include:

[0095] An equipment association unit, used to associate the heat treatment furnace and the cooling circulation system used in combination in the same production instance, to obtain at least one set of hot and cold equipment groups (i.e., an equipment combination including the heat treatment furnace and the cooling circulation system used in combination in the production instance);

[0096] The cycle analysis unit is used to perform periodic analysis on the first power consumption data of the heat treatment furnace and the second power consumption data of the cooling cycle system included in the cold and hot equipment group (analyzing the periodicity of the power consumption change curve corresponding to the power consumption data), and determine the first power consumption cycle of the heat treatment furnace (i.e., the cycle obtained after the periodic analysis of the first power consumption data) and the second power consumption cycle of the cooling cycle system (i.e., the cycle obtained after the periodic analysis of the second power consumption data);

[0097] The comprehensive cycle determination unit is used to take the least common multiple of the first power consumption cycle and the second power consumption cycle as the comprehensive power consumption cycle of the corresponding cold and hot equipment group in the corresponding production instance (that is, the cycle that simultaneously satisfies the periodic change characteristics of the first power consumption data and the second power consumption data).

[0098] The beneficial effect of the above technology is: the common multiple of the first power usage cycle of the first power usage data and the second power usage cycle of the second power usage data is taken as the comprehensive power usage cycle, so that the single-cycle power usage data after the first power usage data and the second power usage data are divided into cycles based on the comprehensive power usage cycle all meet the periodicity of the original power usage data to which they belong.

[0099] Embodiment 4:

[0100] Based on Example 3, the cycle analysis unit includes:

[0101] A target determination subunit, configured to use a power consumption variation curve corresponding to the first power consumption data of the heat treatment furnace included in the cold and hot equipment group and a power consumption variation curve corresponding to the second power consumption data of the cooling circulation system as target curves;

[0102] The precision determination subunit is used to determine the first interval time of all adjacent peaks in the target curve (i.e., the time interval between adjacent power consumption peaks in the target curve) and the second interval time of all adjacent valleys (i.e., the time interval between adjacent power consumption valleys in the target curve), perform correlation denoising on the first interval time and the second interval time (i.e., perform denoising on the first power consumption data and the second power consumption data based on the time series correlation characteristics of the abnormal peak and valley values ​​contained in the power consumption data), obtain multiple comprehensive interval times (i.e., the first interval time and the second interval time remaining after the correlation denoising of all the first interval time and the second interval time in the target curve), and determine the local division interval (the duration of the power consumption data of the minimum time unit divided when the first power consumption data and the second power consumption data are finally analyzed) based on the mean value and analysis precision of all comprehensive interval times in the target curve (i.e., the preset minimum unit division time interval used when performing periodic analysis on the first power consumption data and the second power consumption data, the smaller the time interval corresponding to the analysis precision, the higher the periodic analysis precision of the two, and the higher the periodic analysis accuracy, and vice versa);

[0103] The cycle determination subunit is used to locally divide the target curve based on the local division interval and perform adjacent cluster analysis (the adjacent cluster analysis is based on the existing cluster analysis method, and the objects contained in the clusters obtained in each division process are adjacent to each other, that is, there are always other objects adjacent to the objects contained in the cluster in the same cluster), and determine the first power consumption cycle of the heat treatment furnace or the second power consumption cycle of the cooling circulation system.

[0104] In this embodiment, because when the heat treatment furnace has abnormal power consumption, the cooling circulation system used in combination with it is also likely to have abnormal power consumption. Therefore, the first power consumption data and the second power consumption data can be denoised based on the time series correlation characteristics of the abnormal peak and valley values ​​contained in its power consumption data, thereby ensuring the denoising accuracy.

[0105] The beneficial effects of the above technology are: based on the correlation denoising of the interval time between adjacent peaks and the interval time between adjacent valleys in the first power consumption data and the second power consumption data, accurate denoising of the interval time is achieved, and because the interval time between adjacent peaks or adjacent valleys is highly likely to be within the period obtained by periodic analysis (because if there are peaks or valleys in a period, there must be peaks and valleys in adjacent periods, and their timing values ​​are similar), combined with the preset analysis accuracy, the local division interval of the duration of the power consumption data representing the minimum time unit divided during the periodic analysis is determined, thereby ensuring the accuracy of the subsequent periodic analysis and the accuracy of the periodic division results. Subsequently, the final periodic division of the first power consumption data and the second power consumption data can be achieved based on adjacent clustering analysis.

[0106] Embodiment 5:

[0107] On the basis of Embodiment 4, the precision determination subunit includes:

[0108] A change point detection end, used to determine the first mutation point in all first intervals of the target curve (i.e., the interval time at which a sudden change occurs in the sequence generated by all first intervals of the target curve according to their determined order) and the second mutation point in all second intervals of the target curve (i.e., the interval time at which a sudden change occurs in the sequence generated by all second intervals of the target curve according to their determined order) based on a change point detection algorithm (e.g., using Bayesian Online Changepoint Detection);

[0109] An ordinal number determination terminal is used to determine the first ordinal number of the peak value with a later order among the adjacent peak values ​​corresponding to the first mutation point among all the peak values ​​of the target curve, and at the same time, determine the second ordinal number of the valley value with a later order among the adjacent valley values ​​corresponding to the second mutation point among all the valley values ​​of the target curve;

[0110] The associated denoising end is used to determine whether the ordinal difference between the first ordinal q1 and the second ordinal q2 which is greater than the first ordinal and has the smallest difference with the first ordinal (where q2>q1, and the difference between q1 and q2 is less than the difference between q1 and each other second ordinal) (i.e., the difference between q2 and q1) is within the ordinal difference threshold (when screening the first interval time to be deleted by denoising, the preset maximum value allowed by the ordinal difference between the two interval times) and if so, the first interval time corresponding to the corresponding first mutation point and the second gradual change time corresponding to the corresponding second mutation point are deleted at the same time, and all the remaining first interval times and second interval times are regarded as all comprehensive interval times;

[0111] The sequence generation end is used to determine the common factors of the mean of all comprehensive interval times and the duration of all target curves (the common factors determined here are essentially the values ​​representing the duration), and sort the common factors from large to small to obtain the common factor sequence;

[0112] The interval determination end is used to take the common factor with the same sorting order in the common factor sequence as the preset minimum number of clustering analyses (the minimum number of clustering analyses is preset, and the minimum number of clustering analyses is the minimum number of division processes that need to be performed before the respective power consumption cycles of the two are determined in the periodic analysis process) as the maximum duration, and take the ratio of the mean of the comprehensive interval time to the duration corresponding to the analysis accuracy as the minimum duration, and determine the local division interval based on the minimum duration and the maximum interval time.

[0113] The beneficial effects of the above technology are as follows: the mutation points in all first intervals and all second intervals are detected by the change point detection algorithm, and further based on the ordinal difference between the first interval and the second interval corresponding to the mutation point, the association constraint and denoising of the second interval are realized, and the denoising accuracy is further guaranteed. The common factor of the mean of the interval time and the duration of the target curve is used to ensure that the result of the clustering analysis of the local division interval determined subsequently can accurately constitute the duration of a single cycle, and to ensure that the clustering analysis result of the sub-target curve obtained based on the local division interval can be guaranteed to be evenly divided by the target curve. The common factor with the same ranking ordinal number as the preset minimum number of clustering analyses in the common factor sequence is used as the maximum duration, which ensures that the local division interval finally determined is sufficient for the target curve to be divided through the minimum number of clustering analyses. The ratio of the mean of the comprehensive interval time to the duration corresponding to the analysis accuracy is used as the minimum duration, which can ensure that the determined local division interval meets the preset analysis accuracy, and then the local division interval is reasonably determined based on the above steps.

[0114] Embodiment 6:

[0115] On the basis of Embodiment 4, the period determination subunit includes:

[0116] The local analysis end is used to locally divide the target curve based on the local division interval, obtain multiple sub-target curves (that is, obtained by dividing the target curve, the duration of the sub-target curve is the same as the duration of the local division interval) and the corresponding local division interval (that is, the duration of the sub-target curve), calculate the first-order derivative integral value of each sub-target curve in the corresponding local division interval (that is, the data of the change of power consumption in the sub-target curve with time is represented by the function f(t), where t is the time variable in the sub-target curve, and calculate the integral value of the first-order derivative function f′(t) of the function in the local division interval [t1, t2] Treated as the first-order derivative integral value);

[0117] The cluster analysis end is used to perform adjacent cluster analysis on the first-order derivative integral values ​​of all sub-target curves in the target curve to obtain adjacent clustering division results (the ringing clustering division result contains multiple clusters, the total number of first-order derivative integral values ​​contained in each cluster is the same, and the sub-target curves corresponding to the first-order derivative values ​​contained in each cluster are adjacent in position in the target curve);

[0118] The cycle determination end is used to connect the local division intervals of the sub-target curves corresponding to the first-order derivative integral values ​​belonging to the same cluster in the adjacent cluster division results to obtain the single-cycle division intervals, and regard the duration of the single-cycle division interval of each target curve as the first power consumption cycle of the corresponding heat treatment furnace or the second power consumption cycle of the cooling circulation system (when the target curve is the power consumption change curve corresponding to the first power consumption data, the duration of the single-cycle division interval of the target curve is regarded as the first power consumption cycle of the corresponding heat treatment furnace; when the target curve is the power consumption change curve corresponding to the second power consumption data, the duration of the single-cycle division interval of the target curve is regarded as the second power consumption cycle of the corresponding cooling circulation system).

[0119] The beneficial effects of the above technology are: the target curve is locally divided based on the local division interval to obtain the sub-target curve, and the sub-target curve in the target curve is subjected to adjacent clustering analysis based on the first-order derivative integral value of the sub-target curve in the corresponding local division interval, so that the curve obtained by summarizing all the sub-target curves contained in different clusters in the final result has a high similarity in the characteristics of power consumption changes, which further ensures the accuracy of the final determined power consumption cycle.

[0120] Embodiment 7:

[0121] Based on Example 6, the cluster analysis end includes:

[0122] The sequential summary sub-terminal is used to summarize the first-order derivative integral values ​​of all sub-target curves in the target curve in sequence to obtain an integral value sequence;

[0123] The cluster analysis sub-terminal is used to divide the integral value sequence in sequence (i.e., divide the integral value sequence into equal equal parts with the division multiple, for example, if the division multiple is 3, the integral value sequence is divided into 3 integral value clusters with the same total number of integral values) based on the division multiples (the values ​​of which are the common factors included in the aforementioned preset increasing division multiple sequence) in the preset increasing division multiple sequence (i.e., the sequence in which all common factors from the first common factor to the common factor with the same value as the preset minimum number of cluster analysis times are sorted from small to large), obtain multiple integral value clusters of each division multiple (the total number of integral values ​​included in the integral value cluster is equal to the ratio of the total number of integral values ​​included in the integral value sequence to the division multiple), and at the same time, calculate the similarity of all integral value clusters of each division multiple, until the similarity obtained in the current division process is less than the similarity obtained in the previous division process, then the integral value cluster obtained in the previous division process is regarded as the adjacent cluster division result.

[0124] In this embodiment, the similarity of all integral value clusters of each division multiple is calculated, including:

[0125] Determine the two currently calculated integral value clusters among all integral value clusters of the partition multiple, take the ratio of the difference between two first-order derivative integral values ​​with equal ordinal numbers in the two integral value clusters to the mean of the two first-order derivative integral values ​​as the deviation of the corresponding two first-order derivative integral values, take the difference between 1 and the deviation as the similarity of the corresponding two first-order derivative integral values, take the average of the similarities of all two first-order derivative integral values ​​with equal ordinal numbers in the two integral value clusters as the similarity of the corresponding two integral value clusters, and take the average of the similarities of all two integral value clusters contained in all integral value clusters of the partition multiple as the similarity of all integral value clusters of the current partition multiple.

[0126] The beneficial effect of the above technology is: based on the preset increasing division multiple sequence composed of all common factors in the common factor sequence in Example 5 from the first common factor to the common factor equal to the preset minimum number of clustering analyses, the integral value sequence is divided in turn and the similarities of all integral value clusters obtained by the division are calculated until the similarity reaches a peak value, so that the division result satisfies the periodicity of the target curve to the greatest extent.

[0127] Embodiment 8:

[0128] Based on Example 1, the personalized inertia analysis module includes:

[0129] A first analysis submodule is used to analyze the first personalized power inertia data of each heat treatment furnace object when the complete hot and cold equipment input combination corresponding to the corresponding production instance based on the first power inertia data of each heat treatment furnace in each production instance (that is, to align the power consumption change curves corresponding to all the first power inertia data of the same heat treatment furnace in the production instance with the same complete hot and cold equipment input combination, and take the maximum power consumption at the same time after the alignment as the personalized inertia power consumption of the corresponding heat treatment furnace at the corresponding time, and fit the personalized inertia power consumption change curve based on the personalized inertia power consumption at all times in a single cycle, which is taken as the first personalized power inertia data of the corresponding heat treatment furnace when the corresponding complete hot and cold equipment is put into use);

[0130] A second analysis submodule is used to analyze the second personalized power inertia data of each cooling cycle system object when the complete cold and hot equipment is put into operation in the corresponding production instance based on the second power inertia data of each cooling cycle system in each production instance (that is, to align the power consumption change curves corresponding to all the second power consumption inertia data of the same cooling cycle system in the production instance with the same complete cold and hot equipment input combination, and take the maximum power consumption at the same time after the alignment as the personalized inertia power consumption of the corresponding cooling cycle system at the corresponding time, and fit the personalized inertia power consumption change curve based on the personalized inertia power consumption at all times in a single cycle, which is taken as the second personalized power consumption inertia data of the corresponding cooling cycle system when the corresponding complete cold and hot equipment is put into operation);

[0131] The third analysis submodule is used to analyze the personalized power consumption coordination associated inertia data of each cold and hot equipment group in each complete cold and hot equipment investment combination based on the power consumption coordination associated inertia data of each cold and hot equipment group in the corresponding production instance (that is, to align the function curves corresponding to the linear relationship of all power consumption coordination associated inertia data of the same cold and hot equipment group in the production instance with the same complete cold and hot equipment investment combination, and take the average value of the dependent variable values ​​corresponding to the same independent variable value in all function curves after alignment as the final dependent variable value of the corresponding independent variable value, and fit a new function curve based on the final dependent variable values ​​corresponding to all independent variable values ​​in a single cycle, and take the linear relationship corresponding to the new function curve as the personalized power consumption coordination associated inertia data of the corresponding cold and hot equipment group in the corresponding complete cold and hot equipment investment combination);

[0132] Among them, the multi-dimensional personalized electricity consumption inertia data includes: first personalized electricity consumption inertia data, second personalized electricity consumption inertia data, and personalized electricity consumption coordination associated inertia data.

[0133] The beneficial effects of the above technology are: by aggregating and aligning the first power consumption inertia data and the second power consumption inertia data in the production instance with the same complete cold and hot equipment investment combination to take the maximum value, it is ensured that the first personalized power consumption inertia data and the second personalized power consumption inertia data finally determined can meet all power requirements of the heat treatment furnace, and the power consumption coordination-related inertia data in the production instance with the same complete cold and hot equipment investment combination are averaged, so that the personalized power consumption coordination-related inertia data finally obtained can meet the associated constraint relationship of the power consumption of the heat treatment furnace and the cooling circulation system to the greatest extent.

[0134] Embodiment 9:

[0135] Based on Example 8, the power supply and distribution plan generation module includes:

[0136] The input situation determination submodule is used to determine the target complete hot and cold equipment input combination of the target input situation of the current production instance (i.e., the combination of the heat treatment furnace object and the cooling circulation system object that need to be put into production to complete the current production instance determined in the current production instance);

[0137] A first power consumption prediction submodule is used to retrieve the first personalized power consumption inertia data of each heat treatment furnace object in the heat treatment furnace input combination consistent with the target heat treatment furnace input combination from the multi-dimensional personalized power consumption inertia data, and use it as the first predicted power consumption data corresponding to the target heat treatment furnace object;

[0138] The second power consumption prediction submodule is used to retrieve the second personalized power consumption inertia data of each cooling cycle system object in the cooling cycle system input combination consistent with the target cooling cycle system input combination from the multi-dimensional personalized power consumption inertia data, and use it as the second predicted power consumption data corresponding to the target cooling cycle system;

[0139] A bidirectional correction submodule is used to bidirectionally correct the first predicted power consumption data and the second predicted power consumption data based on the personalized power consumption coordination-associated inertia data of each cold and hot equipment group in the target complete cold and hot equipment investment combination in the multi-dimensional personalized power consumption inertia data, so as to obtain the final predicted power consumption data of each target heat treatment furnace and target cooling circulation system (that is, the predicted power consumption data of each target heat treatment furnace and target cooling circulation system in a single cycle obtained after the bidirectional correction);

[0140] The power supply and distribution plan generation submodule is used to generate a coordinated power supply and distribution plan for generators based on the final predicted power consumption data (determine the operating time of each target heat treatment furnace and target cooling circulation system based on the current production instance, determine the number of operating cycles based on the ratio of the operating time and the comprehensive power consumption cycle, fit the power consumption change curve corresponding to the final predicted power consumption data of the number of operating cycles of the target heat treatment furnace, obtain the power consumption plan of the corresponding target heat treatment furnace, generate a coordinated power supply and distribution plan for generators based on the power consumption plans of all target heat treatment furnaces and target cooling circulation systems, and in the last step, the power supply and distribution loss can be considered to determine the coordinated power supply and distribution plan for generators).

[0141] The beneficial effects of the above technology are: based on the target investment situation of the current production instance, multi-dimensional personalized electricity consumption inertia data is retrieved to achieve preliminary prediction of electricity consumption data, and then further combined with the target cooling cycle system investment combination to achieve two-way correction of the preliminary predicted electricity consumption data, thereby ensuring that the final predicted electricity consumption data determines the premise of meeting its electricity demand while reducing excess occupancy, and further ensuring the rationality of the subsequently generated generator coordinated power supply and distribution plan, reducing standby waste and generator occupancy.

[0142] Embodiment 10:

[0143] Based on Example 9, the bidirectional correction submodule includes:

[0144] The first calculation unit is used to substitute the first predicted power consumption data of each target heat treatment furnace into the linear relationship corresponding to the personalized power consumption coordination associated inertia data of the corresponding cold and hot equipment group in the target complete cold and hot equipment investment combination, and obtain the third predicted power consumption data of the corresponding target cooling cycle system;

[0145] The second calculation unit is used to substitute the second predicted power consumption data corresponding to each target cooling cycle system into the linear relationship corresponding to the personalized power consumption coordination associated inertia data of the corresponding cooling and heating equipment group in the target complete cooling and heating equipment investment combination, so as to obtain the fourth predicted power consumption data corresponding to the target cooling cycle system;

[0146] The final prediction unit is used to take the larger value of the first predicted power consumption data and the fourth predicted power consumption data of each target heat treatment furnace as the final predicted power consumption data of the corresponding target heat treatment furnace, and at the same time, take the larger value of the second predicted power consumption data and the third predicted power consumption data of each cooling circulation system as the final predicted power consumption data of the corresponding cooling circulation system.

[0147] The beneficial effect of the above technology is: by substituting the preliminarily predicted first predicted electricity consumption data and the second predicted electricity consumption data into the linear relationship corresponding to the personalized electricity consumption coordination-related inertia data of the corresponding cold and hot equipment group in the target complete cold and hot equipment investment combination, the new predicted electricity consumption data is determined, and the larger value is taken between it and the preliminarily determined predicted electricity consumption data, so as to further ensure and verify that the determined final predicted electricity consumption data can meet the maximum electricity demand that can actually be achieved.

[0148] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. An intelligent power supply and distribution system for generators that coordinates the power demand of the cooling circulation system, characterized in that: include: An electricity consumption record acquisition module is used to extract the first historical electricity consumption data of each heat treatment furnace and the second historical electricity consumption data of each cooling circulation system from the historical electricity consumption data of each production instance; An electricity consumption inertia analysis module is used to perform multi-dimensional correlation periodic analysis on the first electricity consumption data and the second electricity consumption data of each production instance to obtain multi-dimensional electricity consumption inertia data; The personalized inertia analysis module is used to analyze the multi-dimensional personalized power inertia data of each complete combination of hot and cold equipment based on the multi-dimensional power inertia data and the input of the heat treatment furnace and cooling circulation system in each production instance; The power supply and distribution plan generation module is used to generate a generator coordinated power supply and distribution plan based on the target input of the current production instance; Intelligent power supply and distribution module, used to supply and distribute power based on the generator coordinated power supply and distribution plan to obtain intelligent power supply and distribution results; Among them, the power inertia analysis module includes: The cycle division submodule is used to perform associated cycle division on the first power consumption data of the heat treatment furnace and the second power consumption data of the cooling cycle system used in combination in the same production instance, and obtain the first single-cycle power consumption data of multiple cycles of the heat treatment furnace and the second single-cycle power consumption data of the cooling cycle system; The inertia analysis submodule is used to average all single-cycle power consumption data of the same power-consuming object in the same production instance to obtain the power consumption inertia data of each power-consuming object in each production instance; The association analysis submodule is used to treat the linear relationship between the first single-cycle power consumption data of the heat treatment furnace and the second single-cycle power consumption data of the cooling circulation system used in combination in each production instance as the power consumption coordination association inertia data of the heat treatment furnace and the cooling circulation system used in combination in the corresponding production instance; Among them, electricity users include: heat treatment furnace and cooling circulation system; The single-cycle power consumption data includes: first single-cycle power consumption data and second single-cycle power consumption data; The multi-dimensional power consumption inertia data includes: power consumption inertia data and power consumption coordination-related inertia data; Among them, the period division submodule includes: An equipment association unit, used to associate the heat treatment furnace and the cooling circulation system used in combination in the same production instance to obtain at least one group of hot and cold equipment; A cycle analysis unit, used to periodically analyze the first power consumption data of the heat treatment furnace and the second power consumption data of the cooling circulation system included in the cold and hot equipment group, and determine the first power consumption cycle of the heat treatment furnace and the second power consumption cycle of the cooling circulation system; A comprehensive cycle determination unit, used to take the least common multiple of the first power usage cycle and the second power usage cycle as the comprehensive power usage cycle of the corresponding cold and hot equipment group in the corresponding production instance; Among them, the personalized inertia analysis module includes: The first analysis submodule is used to analyze the first personalized power consumption inertia data of each heat treatment furnace object when the complete cold and hot equipment corresponding to the corresponding production instance is put into use based on the first power consumption inertia data of each heat treatment furnace in each production instance; The second analysis submodule is used to analyze the second personalized power consumption inertia data of each cooling cycle system object when the complete cold and hot equipment corresponding to the corresponding production instance is put into use based on the second power consumption inertia data of each cooling cycle system in each production instance; The third analysis submodule is used to analyze the personalized power consumption coordination associated inertia data of each cold and hot equipment group in each complete cold and hot equipment investment combination based on the power consumption coordination associated inertia data of each cold and hot equipment group in the corresponding production instance; Among them, the multi-dimensional personalized electricity consumption inertia data includes: first personalized electricity consumption inertia data, second personalized electricity consumption inertia data, and personalized electricity consumption coordination associated inertia data.

2. The intelligent power supply and distribution system for generators coordinating the power demand of the cooling circulation system according to claim 1 is characterized in that: Cycle analysis unit, including: A target determination subunit, configured to use a power consumption variation curve corresponding to the first power consumption data of the heat treatment furnace included in the cold and hot equipment group and a power consumption variation curve corresponding to the second power consumption data of the cooling circulation system as target curves; The precision determination subunit is used to determine the first interval time of all adjacent peaks and the second interval time of all adjacent valleys in the target curve, perform correlation denoising on the first interval time and the second interval time to obtain multiple comprehensive interval times, and determine the local division interval based on the mean value and analysis precision of all comprehensive interval times in the target curve; The cycle determination subunit is used to locally divide the target curve based on the local division interval and perform adjacent cluster analysis to determine the first power consumption cycle of the heat treatment furnace or the second power consumption cycle of the cooling circulation system.

3. The intelligent power supply and distribution system for generators coordinating the power demand of the cooling circulation system according to claim 2 is characterized in that: The precision determination subunit includes: A change point detection end, used for determining the first mutation points in all first intervals of the target curve and the second mutation points in all second intervals of the target curve based on a change point detection algorithm; The first ordinal number among all the peaks of the target curve, and at the same time, the second ordinal number of the later valley value among the adjacent valley values ​​corresponding to the second mutation point among all the valley values ​​of the target curve; The associated denoising end is used to determine whether the ordinal difference between the first ordinal number and the second ordinal number which is greater than the first ordinal number and has the smallest difference with the first ordinal number is within the ordinal difference threshold, and if so, the first interval time corresponding to the corresponding first mutation point and the second gradual change time corresponding to the corresponding second mutation point are deleted at the same time, and all the remaining first interval times and second interval times are regarded as all comprehensive interval times; The sequence generation end is used to determine the common factors of the mean values ​​of all comprehensive interval times and the durations of all target curves, and sort the common factors from large to small to obtain a common factor sequence; The interval determination end is used to take the common factor in the common factor sequence whose sorting order is the same as the preset minimum number of clustering analyses as the maximum duration, and the ratio of the mean of the comprehensive interval time to the duration corresponding to the analysis accuracy as the minimum duration, and determine the local division interval based on the minimum duration and the maximum interval time.

4. The intelligent power supply and distribution system for generators coordinating the power demand of the cooling circulation system according to claim 2 is characterized in that: The period determination subunit includes: The local analysis end is used to locally divide the target curve based on the local division interval, obtain multiple sub-target curves and corresponding local division intervals, and calculate the first-order derivative integral value of each sub-target curve in the corresponding local division interval; The cluster analysis end is used to perform adjacent cluster analysis on the first-order derivative integral values ​​of all sub-target curves in the target curve to obtain adjacent cluster division results; The cycle determination end is used to connect the local division intervals of the sub-target curves corresponding to the first-order derivative integral values ​​belonging to the same cluster in the adjacent clustering division results to obtain the single-cycle division interval, and regard the duration of the single-cycle division interval of each target curve as the first power consumption cycle of the corresponding heat treatment furnace or the second power consumption cycle of the cooling circulation system.

5. The intelligent power supply and distribution system for generators coordinating the power demand of the cooling circulation system according to claim 4 is characterized in that: Cluster analysis end, including: The sequential summary sub-terminal is used to summarize the first-order derivative integral values ​​of all sub-target curves in the target curve in sequence to obtain an integral value sequence; The cluster analysis sub-terminal is used to divide the integral value sequence in sequence based on the division multiples in the preset increasing division multiples sequence to obtain multiple integral value clusters for each division multiple, and at the same time, calculate the similarity of all integral value clusters for each division multiple, until the similarity obtained in this division process is less than the similarity obtained in the previous division process, then the integral value cluster obtained in the previous division process is regarded as the adjacent cluster division result.

6. The intelligent power supply and distribution system for generators coordinating the power demand of the cooling circulation system according to claim 1 is characterized in that: The power supply and distribution plan generation module includes: The input situation determination submodule is used to determine the target complete cold and hot equipment input combination of the target input situation of the current production instance; A first power consumption prediction submodule is used to retrieve the first personalized power consumption inertia data of each heat treatment furnace object in the heat treatment furnace input combination consistent with the target heat treatment furnace input combination from the multi-dimensional personalized power consumption inertia data, and use it as the first predicted power consumption data corresponding to the target heat treatment furnace object; The second power consumption prediction submodule is used to retrieve the second personalized power consumption inertia data of each cooling cycle system object in the cooling cycle system input combination consistent with the target cooling cycle system input combination from the multi-dimensional personalized power consumption inertia data, and use it as the second predicted power consumption data corresponding to the target cooling cycle system; A bidirectional correction submodule is used to bidirectionally correct the first predicted power consumption data and the second predicted power consumption data based on the personalized power consumption coordination associated inertia data of each cold and hot equipment group in the target complete cold and hot equipment investment combination in the multi-dimensional personalized power consumption inertia data, so as to obtain the final predicted power consumption data of each target heat treatment furnace and the target cooling cycle system; The power supply and distribution plan generation submodule is used to generate a generator coordinated power supply and distribution plan based on the final predicted power consumption data.

7. The intelligent power supply and distribution system for generators coordinating the power demand of the cooling cycle system according to claim 6 is characterized in that: Bidirectional correction submodule, including: The first calculation unit is used to substitute the first predicted power consumption data of each target heat treatment furnace into the linear relationship corresponding to the personalized power consumption coordination associated inertia data of the corresponding cold and hot equipment group in the target complete cold and hot equipment investment combination, and obtain the third predicted power consumption data of the corresponding target cooling cycle system; The second calculation unit is used to substitute the second predicted power consumption data corresponding to each target cooling cycle system into the linear relationship corresponding to the personalized power consumption coordination associated inertia data of the corresponding cooling and heating equipment group in the target complete cooling and heating equipment investment combination, so as to obtain the fourth predicted power consumption data corresponding to the target cooling cycle system; The final prediction unit is used to take the larger value of the first predicted power consumption data and the fourth predicted power consumption data of each target heat treatment furnace as the final predicted power consumption data of the corresponding target heat treatment furnace, and at the same time, take the larger value of the second predicted power consumption data and the third predicted power consumption data of each cooling circulation system as the final predicted power consumption data of the corresponding cooling circulation system.

Images