A smart factory energy efficiency optimization method, system, electronic device and storage medium

Abstract

A smart factory energy efficiency optimization method and system, electronic equipment and storage medium, relate to the technical field of data processing. The method comprises: obtaining energy consumption parameters and energy consumption correlation variables of a plurality of production units in a target factory; for each production unit, dividing the energy consumption parameters into energy consumption data sequences corresponding to a plurality of time scales according to a preset time interval, and adjusting the baseline energy consumption threshold based on the energy consumption correlation variables to obtain the target energy consumption threshold corresponding to the production unit; according to the energy consumption data sequence corresponding to each time scale, calculating the energy consumption trend characteristic value of the production unit, and combining the energy consumption trend characteristic value of the production unit and the target energy consumption threshold to determine the energy distribution level of the production unit; based on the energy distribution level of each production unit and the total energy quota of the target factory, dividing the available energy quota corresponding to each production unit. The technical scheme provided in the application achieves the effect of improving the efficiency of smart factory energy efficiency optimization.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a smart factory energy efficiency optimization method and system, an electronic device and a storage medium. BACKGROUND

[0002] With the development of industrial automation and information technology, smart factories have become a key solution for manufacturing to pursue high efficiency, low cost and sustainability. Smart factories use advanced data analysis and automation technology to optimize production processes and maximize energy use efficiency.

[0003] Currently, the existing factory energy efficiency optimization method mainly compares and analyzes the collected smart factory data by setting a fixed threshold, so as to evaluate the energy consumption of the smart factory. However, in actual application, since the energy consumption of the factory in the production process is affected by many factors, it is often difficult to dynamically adjust the fixed energy consumption threshold to reflect the actual energy consumption of the factory under different production conditions, thereby reducing the efficiency of the smart factory energy efficiency optimization. SUMMARY

[0004] The present application provides a smart factory energy efficiency optimization method and system, an electronic device and a storage medium, which can improve the efficiency of smart factory energy efficiency optimization.

[0005] In a first aspect, the present application provides a smart factory energy efficiency optimization method, comprising:

[0006] obtaining energy consumption parameters and energy consumption correlation variables of a plurality of production units in a target factory;

[0007] For each of the production units, dividing the energy consumption parameters into energy consumption data sequences corresponding to a plurality of time scales according to a preset time interval, and adjusting a baseline energy consumption threshold based on the energy consumption correlation variables to obtain a target energy consumption threshold corresponding to the production unit;

[0008] According to the energy consumption data sequences corresponding to each of the time scales, calculating energy consumption trend characteristic values of the production units, and combining the energy consumption trend characteristic values of the production units with the target energy consumption threshold to determine an energy distribution level of the production units;

[0009] Based on the energy distribution level of each of the production units and the total energy quota of the target factory, dividing the available energy quota corresponding to each of the production units.

[0010] In a second aspect of the present application, a smart factory energy efficiency optimization system is provided, comprising:

[0011] a data acquisition module for obtaining energy consumption parameters and energy consumption correlation variables of a plurality of production units in a target factory;

[0012] a data processing module, configured to, for each of the production units, divide the energy consumption parameter into energy consumption data sequences corresponding to a plurality of time scales according to a preset time interval, and adjust a benchmark energy consumption threshold based on the energy consumption correlation variable to obtain a target energy consumption threshold corresponding to the production unit;

[0013] an energy distribution level determination module, configured to calculate energy consumption trend characteristic values of the production units according to the energy consumption data sequences corresponding to the plurality of time scales, and determine energy distribution levels of the production units in combination with the energy consumption trend characteristic values and the target energy consumption threshold of the production units;

[0014] an energy quota division module, configured to divide available energy quotas corresponding to the production units based on the energy distribution levels of the production units and a total energy quota of the target factory.

[0015] In a third aspect of the present application, an electronic device is provided, which includes a memory, a processor, and a program stored in the memory and executable on the processor, and the program can be loaded and executed by the processor to implement the method for optimizing energy efficiency of a smart factory.

[0016] In a fourth aspect of the present application, a computer readable storage medium is provided, which stores a computer program, and the computer program, when executed by a processor, causes the processor to implement the method for optimizing energy efficiency of a smart factory.

[0017] To sum up, the one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0018] By adopting the above technical solutions, the energy consumption parameters and the energy consumption correlation variables of a plurality of production units in a target factory are obtained, the energy consumption parameters are divided into energy consumption data sequences of a plurality of time scales according to a preset time interval, the benchmark energy consumption threshold is dynamically adjusted based on the energy consumption correlation variables to obtain target energy consumption thresholds of the production units. Then, the method calculates energy consumption trend characteristic values of the production units according to the energy consumption data sequences of the plurality of time scales, and accurately determines energy distribution levels of the production units in combination with the characteristic values and the target energy consumption thresholds. Finally, the available energy quotas of the production units are reasonably divided based on the energy distribution levels and a total energy quota of the target factory. The multi-level detailed analysis of energy consumption data is realized, the changes in the production environment are dynamically adapted, and the energy consumption status under actual production conditions is effectively reflected, so that the energy distribution is optimized, the best energy use state can be maintained under different production conditions, and the overall energy efficiency optimization efficiency of the smart factory is improved. BRIEF DESCRIPTION OF DRAWINGS

[0019] Figure 1 is a flowchart of a method for optimizing energy efficiency of a smart factory provided in the embodiments of the present application;

[0020] Figure 2 is a structural schematic diagram of a smart factory energy efficiency optimization system provided by an embodiment of the present application.

[0021] Figure 3 is a structural schematic diagram of an electronic device provided by an embodiment of the present application.

[0022] Legend: 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION

[0023] In order for those skilled in the art to better understand the technical solutions in the specification, the technical solutions in the specification will be clearly and completely described below in conjunction with the drawings in the embodiments of the specification. Obviously, the described embodiments are only some of the embodiments of the present application, not all the embodiments.

[0024] In the description of the embodiments of the present application, the words such as "for example" or "for instance" are used to represent an example, illustration or description. Any embodiment or design scheme described as "for example" or "for instance" in the embodiments of the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the words such as "for example" or "for instance" are intended to present the relevant concept in a specific manner.

[0025] In the description of the embodiments of the present application, the term "a plurality of" means two or more. For example, a plurality of systems means two or more systems, and a plurality of screen terminals means two or more screen terminals. In addition, the terms "first" and "second" are used for description purposes only and should not be interpreted as indicating or implying relative importance or implicitly indicating the indicated technical features. Therefore, the features defined with "first" and "second" can explicitly or implicitly include one or more of the features. The terms "include", "contain", "have" and their variants mean "include but are not limited to", unless otherwise specifically emphasized.

[0026] The embodiments of the present application provide a smart factory energy efficiency optimization method. In one embodiment, please refer to Figure 1 , Figure 1 is a flowchart of a smart factory energy efficiency optimization method provided by an embodiment of the present application. The method can be implemented by relying on a computer program, which can be integrated in an application or run as an independent tool class application. The method can also be implemented by relying on a single chip microcomputer or run on a smart factory energy efficiency optimization system based on the von Neumann system. Specifically, the method can include the following steps:

[0027] Step 101: Obtain energy consumption parameters and energy consumption related variables of multiple production units in a target factory.

[0028] In the embodiments of the present application, a production unit refers to each production line or production equipment in a factory, which is the basic unit of factory energy consumption.

[0029] In the embodiments of the present application, energy consumption parameters refer to parameters reflecting the actual energy consumption level of a production unit, such as directly measured energy consumption data such as power consumption data and peak power data.

[0030] In the embodiments of the present application, energy consumption related variables refer to other related parameters that affect the energy consumption of a production unit, such as environmental or process parameters that indirectly affect energy consumption, such as production environment temperature and equipment running time.

[0031] Specifically, by installing various sensing devices and data collection terminals in the factory, the power consumption data, peak power data and other energy consumption parameters of each production unit are monitored and recorded in real time. At the same time, it is also necessary to obtain related variables that affect energy consumption, such as environmental parameters such as temperature and humidity in the production workshop, and actual running time of production equipment. These data can be automatically collected by environmental monitors, time counters and other devices. In addition, for different types of production units, other specific related parameters such as production load and raw material types may also need to be obtained to fully reflect various factors affecting energy consumption. The energy consumption parameter and related variable data obtained through this process provides a complete data basis for subsequent analysis and optimization of energy efficiency. With comprehensive parameter information, energy consumption evaluation standards can be dynamically adjusted according to different production conditions, avoiding the shortcomings of using fixed thresholds, so as to achieve more accurate energy efficiency optimization.

[0032] Step 102: For each production unit, divide the energy consumption parameters into energy consumption data sequences corresponding to multiple time scales according to a preset time interval, and adjust the baseline energy consumption threshold based on the energy consumption related variables to obtain the target energy consumption threshold corresponding to the production unit.

[0033] In the embodiments of the present application, the energy consumption data sequence refers to a plurality of time scale corresponding data sequences obtained by sampling the energy consumption parameters (such as power consumption and peak power) of a production unit according to different time intervals (second level, minute level, hour level), which respectively reflect the energy consumption fluctuations in different time dimensions.

[0034] In the embodiments of the present application, the baseline energy consumption threshold refers to the energy consumption reference value or allowable range of a production unit under standard working conditions, which is a baseline reference.

[0035] The target energy consumption threshold in the embodiments of the present application refers to an energy consumption evaluation standard value that is more close to actual working conditions, obtained by dynamically adjusting and correcting the benchmark energy consumption threshold based on actual production environment temperature, equipment running time and other related variables.

[0036] Specifically, after obtaining the energy consumption parameters and related variables of the production unit, the energy consumption parameters need to be divided into data sequences of multiple time scales according to preset different time intervals, and the benchmark energy consumption threshold is dynamically adjusted according to the related variables to obtain the target energy consumption threshold corresponding to each production unit. The reason for this is that the actual energy consumption of the production unit presents different fluctuation characteristics on different time scales. For example, on the time scale of seconds, the energy consumption data reflects the instantaneous power fluctuation of the equipment; on the time scale of minutes, it reflects the load change of the equipment; on the time scale of hours, it reflects the energy consumption trend of the entire production process. Only by dividing the energy consumption parameters into data sequences of multiple time scales, can the energy consumption behavior characteristics of the production unit on different time dimensions be comprehensively analyzed and grasped. Specifically, the power consumption data and peak power data are extracted from the energy consumption parameters, and then these data are segmented and sampled according to different time intervals such as seconds, minutes and hours, to obtain data sequences corresponding to multiple time scales such as second-level energy consumption sequence, minute-level energy consumption sequence and hour-level energy consumption sequence. On the other hand, since the changes of the production environment temperature, equipment running time and other related variables will affect the actual energy consumption level of the production unit, it is necessary to dynamically adjust the benchmark energy consumption threshold based on these variables. A correction coefficient mapping table can be established in advance to determine the correction coefficients corresponding to different temperatures and running times, and then the benchmark threshold is multiplied by these correction coefficients to obtain the dynamically adjusted target energy consumption threshold. In this way, both the standard energy consumption level and the influence of actual production conditions are considered, so that the target energy consumption threshold is more close to the actual situation.

[0037] On the basis of the above embodiments, as an optional embodiment, in step 102: dividing the energy consumption parameters into energy consumption data sequences corresponding to multiple time scales according to preset time intervals, this step can further include the following steps:

[0038] Step 201: extracting power consumption data and peak power data from the energy consumption parameters; sampling the power consumption data and peak power data according to the time interval of seconds to obtain a second-level energy consumption sequence.

[0039] Specifically, in the energy efficiency optimization scheme of the smart factory, it is necessary to extract the power consumption data and peak power data from the energy consumption parameters of the production unit, because the power consumption and peak power are the key parameters that directly reflect the real-time energy consumption level of the equipment. Next, the extracted power consumption and peak power data are sampled according to the preset second-level time interval to obtain the second-level energy consumption sequence. This second-level time scale data sequence can accurately capture the energy consumption fluctuation and peak characteristics of the equipment in the instantaneous running process. Specifically, the data acquisition device continuously records the power consumption readings and power readings of the production equipment every second. Then, according to the pre-set sampling time interval (such as every 1 second, 5 seconds or 10 seconds, etc.), the original data is segmented and extracted, and the power consumption sequence and peak power sequence with second as the time unit are obtained, which together constitute the second-level energy consumption sequence. The reason for collecting this second-level time precision energy consumption sequence data is that it can accurately reflect the power consumption and load change of the equipment in the instantaneous running process. For the smart factory using a large number of high-power equipment, these devices will have short-term power fluctuations and energy consumption peaks when starting, accelerating or load mutation. Only the energy consumption sequence with second-level resolution can accurately capture these instantaneous energy consumption characteristics and provide data support for optimizing device operation mode and peak load shifting.

[0040] Step 202: Sampling the power consumption data and peak power data according to the minute-level time interval to obtain the minute-level energy consumption sequence.

[0041] Specifically, after obtaining the original second-level power consumption and peak power data, the data is resampled and grouped according to the preset minute-level time interval (such as every 1 minute, 5 minutes or 10 minutes, etc.), thereby generating power consumption sequence and peak power sequence with minute as the unit, which together constitute the minute-level energy consumption sequence. For example, the average power consumption and average power value in each preset minute interval can be calculated as the representative data point of the minute interval, thereby forming the minute-level power consumption and power sequence. The maximum value in the minute interval can also be taken as the data point. Different statistical methods can be determined according to specific needs. The reason for collecting the minute-level energy consumption sequence data is that compared with the second-level sequence, it can better reflect the load fluctuation law of the production equipment on a longer time scale. The load of many production equipment changes periodically, and there are obvious energy consumption fluctuation characteristics on the minute-level time scale. Only by obtaining the minute-level sequence can the influence of factors such as device start-stop and production rhythm on energy consumption be comprehensively analyzed, so as to optimize the production plan and process.

[0042] Step 203: Sampling the power consumption data and peak power data according to the hour-level time interval to obtain the hour-level energy consumption sequence.

[0043] Specifically, from the original second-level power consumption and peak power data, the data is re-grouped and counted according to the preset hour-level time interval (such as every 1 hour, 2 hours or 4 hours, etc.), to obtain the power consumption sequence and the peak power sequence in hours, which together constitute the hour-level energy consumption sequence. For example, the total power consumption and the average power value in each preset time interval can be calculated as the data points of the time interval, and then the hour-level power consumption and power sequence are formed. Other statistical quantities such as the maximum value or the median value in the time interval can also be taken as data points, and the method can be determined according to specific needs. The reason why the hour-level energy consumption sequence data needs to be collected is that compared with second-level and minute-level, it can better reflect the overall energy consumption situation and change trend of the production equipment on a longer time scale. The overall operation mode and rhythm of many production lines will be reflected on the hour-level time scale, such as the start and stop of the equipment, the high and low load cycle, etc., which will show regular characteristics in the hour-level energy consumption data.

[0044] Step 204: Taking the second-level energy consumption sequence, the energy consumption sequence and the hour-level energy consumption sequence as energy consumption data sequences corresponding to multiple time scales.

[0045] Specifically, the obtained second-level energy consumption sequence (including second-level power consumption sequence and peak power sequence), the obtained minute-level energy consumption sequence, and the obtained hour-level energy consumption sequence are uniformly classified and stored as energy consumption data sequences representing different time scales. The reason why the sequence data of the three time accuracies needs to be unified is that they reflect the energy consumption behavior characteristics of the production equipment on different time dimensions. Only by analyzing them together can the energy consumption of the equipment be fully grasped. The second-level energy consumption sequence can capture instantaneous power fluctuations and energy consumption peaks; the minute-level sequence reveals the regular characteristics of device start and stop and load fluctuations; and the hour-level sequence reflects the overall operation mode and energy consumption trend of the device. By integrating the three types of energy consumption data sequences, complete energy consumption data samples of the device at each time scale can be obtained.

[0046] On the basis of the above embodiment, as an optional embodiment, in step 102: based on the energy consumption related variable, the baseline energy consumption threshold is adjusted to obtain the target energy consumption threshold corresponding to the production unit. This step can also include the following steps:

[0047] Step 205: Obtain the production environment temperature and the device running time length in the energy consumption related variable; in the preset correction coefficient mapping table, determine the first correction coefficient corresponding to the production environment temperature and the second correction coefficient corresponding to the device running time length.

[0048] Specifically, after obtaining the energy consumption data sequences corresponding to multiple time scales, the intelligent factory energy efficiency optimization scheme needs to dynamically correct the standard energy consumption threshold in combination with the associated variables in the actual production environment to obtain a target energy consumption evaluation standard closer to the actual working condition. First, the real-time values of the two key factors of production environment temperature and equipment running time are obtained from the energy consumption associated variables. This is because temperature and running time will significantly affect the actual energy consumption level of the equipment. Next, in the pre-established correction coefficient mapping table, according to the obtained real-time temperature value and running time value, the corresponding first correction coefficient and second correction coefficient are respectively found. This correction coefficient mapping table is usually obtained through a large amount of historical data analysis and modeling, which quantitatively reflects the influence of temperature, running time and other factors on equipment energy consumption. Taking temperature as an example, temperature rise will increase the heat dissipation load of the equipment, thereby increasing the energy consumption; when the temperature is too low, additional heating energy consumption is required to ensure the normal operation of precision equipment. The mapping table gives the correction coefficient corresponding to different temperature ranges, which is used to quantitatively correct the standard energy consumption threshold. For running time, long-time continuous operation of the equipment often consumes more energy, while intermittent operation is relatively energy-saving. The correction coefficient of running time in the mapping table reflects this regular influence. Finally, the temperature correction coefficient and the running time correction coefficient found are multiplied to obtain a comprehensive correction factor. Using this factor to adjust and correct the standard energy consumption threshold, the target energy consumption evaluation standard close to the actual production working condition can be obtained. The key role of this dynamic correction mechanism is to make the evaluation standard self-adaptive adjustment, and change with the real-time changes of temperature, running time and other factors, so as to be closer to the actual energy consumption performance, and improve the accuracy and pertinence of the evaluation.

[0049] Step 206: multiply the reference energy consumption threshold by the first correction coefficient and the second correction coefficient in turn to obtain the target energy consumption threshold corresponding to the production unit.

[0050] Specifically, first, the standard benchmark energy consumption threshold of the type of production equipment or production line is obtained. The benchmark threshold is usually an energy consumption reference value obtained by statistical analysis of a large amount of historical data under standard working conditions. Next, the obtained first correction coefficient (corresponding to the production environment temperature) and the second correction coefficient (corresponding to the equipment running time) are multiplied by the benchmark energy consumption threshold respectively. The purpose of this step is to quantify and convert the influence of factors such as temperature and running time into the benchmark threshold. Taking the benchmark threshold of 1000 degrees of electricity, the temperature correction coefficient of 1.05, and the running time correction coefficient of 1.1 as an example. Then, by multiplying these two correction coefficients respectively, the final corrected target energy consumption threshold is 1155 degrees of electricity. This correction process reflects that under actual working conditions, the environmental temperature and running time faced by the equipment are different from the standard working conditions, which will cause the actual energy consumption to deviate from the standard benchmark value. By multiplying the correction coefficient, these differences can be quantified and dynamically adjusted into the evaluation standard. The reason for this dynamic correction process is to make the final target energy consumption threshold close to the actual production, and to truly reflect the reasonable energy consumption level of the production unit under the current specific working conditions, which provides more accurate and targeted reference for subsequent energy consumption evaluation and optimization.

[0051] Step 103: According to the energy consumption data sequence corresponding to each time scale, the energy consumption trend characteristic value of the production unit is calculated, and the energy distribution level of the production unit is determined by combining the energy consumption trend characteristic value of the production unit and the target energy consumption threshold.

[0052] Among them, the energy consumption trend characteristic value refers to a series of characteristic parameters calculated according to the energy consumption data sequence corresponding to different time scales (second level, minute level, hour level), which is used to describe and reflect the key information of the production unit in each time dimension, such as energy consumption fluctuation, peak and valley distribution, load change law, etc.

[0053] The energy distribution level is a level index determined according to the comparison between the energy consumption trend characteristic value of the production unit and its target energy consumption threshold, according to the preset evaluation rule. This energy distribution level reflects the current energy-saving state and optimization priority of the unit, such as high energy consumption level, which represents a large energy-saving space and needs to be prioritized.

[0054] Specifically, first, a series of energy consumption trend characteristic values are calculated according to the energy consumption data sequences corresponding to different time scales such as second level, minute level and hour level, respectively. These characteristic values reflect key information such as energy consumption fluctuation, peak-valley distribution, load change rule of the production unit in each time dimension. For example, in the second level dimension, peak power, power fluctuation frequency and other characteristic values can be calculated; in the minute level dimension, production rhythm energy consumption fluctuation period, fluctuation amplitude and other characteristic values can be calculated; and in the hour level dimension, daily energy consumption total amount, peak period distribution, load utilization rate and other characteristic values can be calculated. Next, the multi-dimensional energy consumption trend characteristic values calculated are compared and analyzed comprehensively with the target energy consumption threshold corresponding to the production unit. According to the deviation degree of the characteristic values from the threshold, the energy distribution level of the production unit is determined according to the pre-set evaluation rule. This energy distribution level reflects the current energy saving potential and optimization demand of the unit. For example, if the characteristic values are all above the threshold, it can be evaluated as a high energy consumption level, which represents that there is a large energy saving space and the energy scheduling of the unit needs to be prioritized; and if the characteristic values are generally below the threshold, it can be evaluated as an energy saving level, which corresponds to a reasonable energy distribution. The reason why this comprehensive evaluation process is needed is that there are often many complex factors affecting energy consumption in the production site, and relying solely on the energy consumption performance in a certain time scale cannot fully reflect the true situation. Only by combining multi-dimensional data and comparing with the corrected target threshold, a comprehensive and accurate evaluation can be made.

[0055] On the basis of the above embodiment, as an optional embodiment, in step 103: according to the energy consumption data sequences corresponding to each time scale, the energy consumption trend characteristic values of the production unit are calculated, and this step can further include the following steps:

[0056] Step 301: The energy consumption data sequences corresponding to each time scale are processed by using the sliding window method to obtain the energy consumption data in a plurality of time windows.

[0057] Specifically, first, a predefined time window length is set on the energy consumption sequence of different time scales, such as 30 seconds on the second level sequence, and 2 hours on the hour level. Next, the time window is used to slide through the sequence of each time scale. For example, sliding a 30-second window on the second-level sequence, the first window covers data from 1 to 30 seconds, the second window covers data from 2 to 31 seconds, and so on, moving one sampling time interval each time. In each time window, the sequence data within the window coverage is extracted as an independent energy consumption data subset. Through the continuous sliding of the window, multiple continuous energy consumption data subsets covering the entire time interval can be obtained. The purpose of this sliding window segmentation is to be able to analyze different time periods of the production process, and find energy consumption anomalies or regular changes in a specific time period. For example, in the 30-second window of the second-level sequence, it may be found that there is a short power peak anomaly when a cooling device starts; and in the 2-hour window of the hour-level sequence, it may be found that the energy consumption of the device is higher from 10am to 12pm. By segmenting the data through the sliding window method, the energy consumption performance of each time period can be analyzed in detail, so as to accurately evaluate the factors affecting energy consumption and provide targeted data support for energy saving optimization.

[0058] Step 302: Calculate the mean and standard deviation of the energy consumption data in each time window; based on the mean of any two adjacent time windows, calculate the energy consumption growth rate; based on the standard deviation of each time window, calculate the energy consumption stability index.

[0059] Specifically, first, the mean and standard deviation of the energy consumption data in each time window are calculated. The mean reflects the average energy consumption level of the time period, while the standard deviation characterizes the degree of discrete fluctuation of the energy consumption data. Taking a 30-second time window as an example, assuming there are 30 second-level energy consumption sampling values in the window, then the arithmetic mean of the 30 values is calculated as the mean, and the standard deviation of the 30 values relative to the mean is calculated as the standard deviation indicator of the window. Next, based on the means of any two adjacent time windows, the energy consumption growth rate is calculated. The growth rate reflects the trend of the energy consumption level between different time periods. Taking the previous and subsequent 30-second windows as an example, if the subsequent window mean is 1200 watts and the previous window mean is 1000 watts, then the growth rate of the subsequent window relative to the previous window is (1200-1000) / 1000=20%. By calculating the growth rate of each two adjacent windows, the growth rate curve of the entire time interval can be obtained. And for the standard deviation value in each time window, the energy consumption stability indicator of the window is calculated. The stability indicator reflects the fluctuation degree of energy consumption in the time period, and the smaller the standard deviation, the higher the stability. These mean, standard deviation, growth rate and stability indicators and other features can quantitatively describe the energy consumption performance in the production process from different dimensions. By analyzing these indicators, key information such as abnormal energy consumption, energy consumption fluctuation source, and energy consumption difference between different production stages can be found.

[0060] Step 303: superimpose the energy consumption growth rate and the energy consumption stability indicator after normalization to obtain the energy consumption trend feature value.

[0061] Specifically, first, the energy consumption growth rate sequence and the stability index sequence are normalized respectively to map them to the range of 0-1. This step is to eliminate the numerical difference of the two different dimension indicators, so that they can be weighted and superimposed on the same order of magnitude. Taking Min-Max normalization as an example, assuming that the maximum value of the growth rate sequence is 30% and the minimum value is -10%, and the maximum and minimum values of the stability index sequence are 0.25 and 0.05 respectively. Then the growth rate sequence can be scaled to the [0, 1] interval, that is, (original value-minimum value) / (maximum value-minimum value); similarly, the stability index sequence is scaled to the [0, 1] interval. After normalization, the two sequences can be weighted and superimposed. The purpose of weighted superposition is to fuse the feature information of growth rate and stability of different dimensions to form a comprehensive energy consumption trend evaluation index. When superimposing, the weight distribution ratio of the two features needs to be determined in advance, for example, the weight of the growth rate sequence can be set to 0.6 and the weight of the stability index sequence can be set to 0.4. Then the normalized two sequences are linearly added according to the weight, and the final energy consumption trend feature value sequence can be obtained. Through this fusion step, the energy consumption trend feature value can reflect both the growth trend and the volatility of energy consumption in the production process, thereby more comprehensively depicting the dynamic change trend characteristics of energy consumption.

[0062] On the basis of the above embodiment, as an optional embodiment, in step 103: combining the energy consumption trend feature value of the production unit and the target energy consumption threshold, the energy distribution level of the production unit is determined. This step can also include the following steps:

[0063] Step 304: Obtain the production activity type of the production unit, and determine the energy consumption fluctuation range corresponding to the production activity type in the database.

[0064] Specifically, first, through the factory manufacturing execution system or other field data acquisition terminal, the specific production activity type currently being executed by the production unit is known, such as casting, stamping, welding, assembly, and other different manufacturing links. Different production activity types correspond to different energy consumption characteristics. For example, in the casting process, a large number of high-energy consumption equipment will be put into use, and there is a high basic energy consumption; while stamping is more characterized by a staged peak energy consumption; the energy consumption of the assembly link may be relatively stable, etc. Therefore, before evaluating whether the same energy consumption trend characteristic value is abnormal, a reasonable energy consumption floating range needs to be determined as a reference for comparison according to the current production activity type. This step will access the production knowledge base database of the system, and find the standard energy consumption floating range data corresponding to the current production activity type in the database. This database is pre-established through a large number of field energy consumption sampling and analysis during the system design and debugging stage. Taking casting as an example, assuming that the energy consumption floating range corresponding to the casting activity in the database is within ±20% of the average energy consumption, then this 20% floating range is temporarily locked as the reference standard for this evaluation. Only by comparing the actually calculated energy consumption trend characteristic value with this specific floating range, can it be determined whether the characteristic value has abnormal fluctuations, and then the optimization level and subsequent optimization strategy of the production unit are determined.

[0065] Step 305: Based on the energy consumption floating range of the production unit and the energy consumption trend characteristic value, determine the predicted energy consumption fluctuation range of the production unit.

[0066] Specifically, first, the standard energy consumption floating range is taken as the reference value, and the upper and lower boundaries of the range are taken as the initial upper and lower limit values. Next, the energy consumption trend characteristic value sequence calculated before is analyzed to identify the peak interval. This step can be implemented using peak detection, pattern matching, and other data analysis algorithms. Taking a continuous 24-hour energy consumption trend characteristic value sequence as an example, the system may find that there are large peak intervals in the 6th-8th hour and the 18th-20th hour. For the detected peak intervals, the system will take the maximum value of the interval as the adjustment reference to appropriately relax the original upper and lower limit values. If the maximum value of the peak interval is 120% of the original upper limit, then the new upper limit is adjusted to 120% of the original upper limit; similarly, if the maximum value is 80% of the original lower limit, then the new lower limit is adjusted to 80% of the original lower limit. Through this dynamic adjustment process, the standard floating range can be effectively widened to cover possible temporary peak fluctuations, avoiding misjudgment due to peak values being judged as abnormal values.

[0067] Step 306: Calculate the offset of the predicted energy consumption fluctuation range from the target energy consumption threshold, and determine the energy distribution level corresponding to the offset in the preset energy distribution level mapping table.

[0068] Specifically, first, the upper and lower limit values of the predicted energy consumption fluctuation range are taken, and compared with the target energy consumption threshold respectively to obtain the absolute values of two offsets. With the positive offset of the upper limit value of the range and the threshold as a reference, between the positive offset and the negative offset of the lower limit value of the range and the threshold, the absolute value of the larger one is selected as the final evaluation offset. For example, assuming that the upper and lower limits of the predicted range are 1200 and 800 respectively, and the target threshold is 1000. Then the positive offset is 1200-1000=200, and the negative offset is 1000-800=200. Since the absolute values of the two are equal, the system will select 200 as the final evaluation offset. Next, the system will access the pre-established energy allocation level mapping table to find the energy allocation level corresponding to the current offset value. This mapping table is developed during the system design and debugging phase based on a large amount of field data analysis and expert experience summary. It establishes a mapping relationship between the range of possible offset values and different optimization levels. Assuming that the mapping table specifies that the offset is 0-100, the optimization level is level 1, 100-300 is level 2, 300-500 is level 3, and so on. Then in this example, since the offset is 200, it will be mapped to level 2 optimization. The purpose of determining the optimization level is to guide the subsequent fine energy efficiency optimization and resource allocation of the production unit. Different optimization levels correspond to different degrees of energy saving potential and different optimization strategy schemes. The higher the level, the greater the actual energy consumption of the unit deviates from the target threshold, the greater the energy saving potential, and the more computing power and resources will be invested in subsequent optimization; on the contrary, the lower the level, the more relaxed the corresponding light optimization strategy can be executed. By discretizing the offset into levels, the complexity of the evaluation calculation can be reduced, and the optimization decision basis possessed by the system can be avoided, thereby avoiding blind optimization and resource waste.

[0069] Step 104: Based on the energy allocation level of each production unit and the total energy quota of the target factory, the available energy quota corresponding to each production unit is divided.

[0070] The total energy quota refers to the maximum total energy that the factory as a whole is allowed to consume within a certain time period (such as a day). This total amount can be the upper limit of energy use agreed upon by the factory and the superior supervisory department, or the upper limit of energy demand estimated according to the production plan and budget cost of the day. It reflects the total energy budget that the factory can reasonably use within that time period.

[0071] The available energy quota refers to the energy quota allocated to the unit for use, which is divided from the total energy quota according to the energy allocation level of each production unit. Different priority units will have different available quotas.

[0072] Specifically, first, the system needs to know the total energy quota of the current target factory, which can be the upper limit of daily electricity consumption agreed by the factory and the superior unit, or the upper limit of energy consumption estimated according to the daily operation cost budget, etc. Next, the system will analyze the optimization level of each production unit one by one. For the units with higher priority level, that is, the units with greater energy saving potential, the system will allocate larger available energy quota to them, so as to have enough resource space to realize fine control in subsequent optimization. For the units with lower priority level and lower energy saving potential, the system will appropriately compress their available quota to avoid wasting optimization resources. The specific quota allocation principle can be set as a mapping relationship table between levels and quotas in the system configuration in advance. For example, level 1 units can be allocated 20% of the total quota, level 2 units 15%, level 3 units 10%, and so on. After the allocation proportion of each unit is determined, the system will complete the quota splitting according to these proportions. If there is a remaining amount after splitting, it can be allocated to all level units on average; or it can be allocated to high-level units first, further amplifying the focusing effect of optimization resources. In this way, not only the hard limit of the total energy quota of the factory is met, but more importantly, the effective layering and efficient allocation of optimization resources are realized, so that the optimization efficiency is maximized.

[0073] On the basis of the above embodiment, as an optional embodiment, in step 104: based on the energy allocation level of each production unit and the total energy quota of the target factory, the available energy quota corresponding to each production unit is divided. This step can further include the following steps:

[0074] Step 401: based on the energy allocation level of each production unit, determine the energy allocation proportion corresponding to each production unit.

[0075] Specifically, the system will access the pre-established energy quota mapping table, and find the corresponding quota proportion value in the mapping table according to the allocation level of each unit. This quota mapping table is actually an empirical value table developed through a large amount of field data analysis and expert experience summary during the system design and debugging stage. It establishes a mapping relationship between different energy allocation levels and reasonable energy quota proportions. For example, the mapping table may stipulate that the quota proportion corresponding to the 1st priority level unit is 20%, the 2nd level is 15%, the 3rd level is 12%, the 4th level is 10%, and so on. The quota proportion reflects the relative weight of the system's investment in optimization resources for different units. After determining the corresponding quota proportion of each unit, in the subsequent actual allocation of energy, the system can cut out a reasonable energy use index for each unit according to these quota values. Taking the total energy budget of a factory in a certain time period as 1000 units for example, assuming there are two production units A and B, A is the 2nd priority level and B is the 4th level. Then according to the mapping table, the quota proportion of A is 15% and that of B is 10%. The actual allocation result will be that the energy index of A unit is 1000x15%=150 units and that of B unit is 1000x10%=100 units. In this way, the system well balances the energy saving potential differences and optimization resource investment of each unit. For the high-priority and high-potential A unit, more energy index is given, creating conditions for more aggressive optimization strategies. Although the low-priority B unit has relatively less index, it also retains the necessary optimization space. If the energy index is simply allocated equally without considering the differences in energy saving potential of the units, it is likely to lead to inefficient use of optimization resources, with high-potential units being limited by the index and not being able to fully optimize, wasting benefits, and low-potential units being allocated excessive index that they cannot digest.

[0076] Step 402: Multiply the energy quota proportion corresponding to each production unit with the total energy quota of the target factory to obtain the available energy quota corresponding to each production unit.

[0077] Specifically, first, the system needs to know the total energy quota value of the target factory in a certain time period, which can be the energy use upper limit agreed upon by the factory and the superior supervisory department, or the estimated energy demand based on the daily operation cost budget. Taking the total energy quota of a certain daily production day as 1000 units for example, the system has evaluated the energy quota proportions of two production units A and B as 20% and 15% respectively. Then, for unit A, the system will directly multiply the 20% quota proportion by the total quota of 1000 units to obtain the available quota of A unit as 1000x20%=200 units, and similarly, the available quota of B unit is 1000x15%=150 units. In this way, the system not only reasonably allocates the relative quota weights among the units, but more importantly, it converts these weights into available energy index values, providing a clear resource constraint basis for subsequent fine optimization of each unit.

[0078] On the basis of the above-mentioned embodiments, as an optional embodiment, in step 104: based on the energy distribution level of each production unit and the total energy quota of the target factory, the available energy quota corresponding to each production unit is divided. This step can also include the following steps:

[0079] Step 501: Obtain the cooling tower backwater temperature and current energy consumption data of the target factory; calculate the energy consumption deviation between the current energy consumption data and the preset energy consumption benchmark value, and calculate the temperature deviation between the backwater temperature and the benchmark temperature.

[0080] Specifically, the system first obtains the real-time value of the current backwater temperature of the cooling tower from the field data acquisition terminal, and also obtains the real-time data of the current total energy consumption of the factory. Then, the system will access two pre-configured benchmark values respectively: one is the benchmark backwater temperature value of the cooling tower, and the other is the energy consumption benchmark value of the factory under this operating state. These two benchmark values are usually reasonable expected values formulated during the system design and debugging stage, based on a large amount of historical data, on-site expert experience and relevant industry standards. After determining the four data, the system compares the current backwater temperature with the benchmark backwater temperature value, and calculates the temperature deviation value of the two. At the same time, it also compares the current total energy consumption data with the energy consumption benchmark value, and obtains an energy consumption deviation value. Taking a certain time point as an example, assuming that the current backwater temperature is 32℃ and the benchmark temperature is 30℃, then the temperature deviation is 32-30=2℃. Similarly, if the current energy consumption data is 2.8 million kilowatt-hours, and the energy consumption benchmark is 2.5 million kilowatt-hours, then the energy consumption deviation is 280-250=30 million kilowatt-hours. The acquisition of these two deviation values lays a data foundation for subsequent formulation of fine energy-saving optimization strategies.

[0081] Step 502: When the temperature deviation is less than the temperature deviation threshold value, and the energy consumption deviation is greater than the energy consumption deviation threshold value, reduce the fan speed of the target factory according to the preset speed reduction step.

[0082] Specifically, when the temperature deviation is small (below the preset threshold) but the energy consumption deviation is large (above the preset threshold), the system will moderately reduce the speed of the fan according to the pre-set speed reduction step. The purpose of reducing the speed of the fan is to reduce the energy consumption of the refrigeration system. The fan is the main power equipment of the refrigeration device, and its speed directly determines the operating load and energy consumption level of the refrigeration system. When the energy consumption deviation is too high, moderately reducing the speed of the fan can quickly reduce the energy consumption of the system. The setting of the speed reduction step needs to be repeatedly tested according to a large amount of field data during system debugging to find an optimal value that can effectively reduce energy consumption without affecting normal refrigeration effect. Generally speaking, the smaller the step value, the smaller the impact on the refrigeration effect, but the slower the energy consumption decreases. Taking a certain time point as an example, assuming that the current temperature deviation is 1℃ (below the threshold of 2℃), the energy consumption deviation is 400,000 kilowatt-hours (above the threshold of 300,000 kilowatt-hours), and the pre-set speed reduction step is 5%. Then the optimization system will command to reduce the current speed of the fan by 5%. If the current speed of the fan is 2800 revolutions per minute, then after the speed reduction, it will be adjusted to 2660 revolutions per minute. Thus, moderate energy saving can be achieved, and because the temperature deviation is within the controllable range, it will not have a significant impact on the refrigeration effect. If the energy consumption cannot still be effectively reduced, the system will continue to reduce the speed of the fan according to the step in the next adjustment period until the energy consumption deviation is reduced to below the threshold. Compared with not making any adjustment or directly making a large-scale speed adjustment to the fan, this gradual small-step adjustment is more stable and precise, avoiding sharp fluctuations in energy consumption and temperature, and making the operation of the entire refrigeration system more stable and efficient. If the temperature deviation has exceeded the threshold, in order to ensure the refrigeration effect, the system will no longer continue to reduce the speed of the fan, but will adjust other parameters for optimization to fix the problem of excessive temperature deviation. In this way, the scheme of the present application realizes a closed-loop intelligent optimization control, which makes targeted adjustments according to the on-site deviation value at all times, dynamically tracks the system state, and achieves a balance between energy efficiency and refrigeration effect.

[0083] Reference Figure 2 A smart factory energy efficiency optimization system is provided for the embodiments of the present application, and the system comprises a data acquisition module, a data processing module, an energy distribution level determination module, an energy quota division module, wherein:

[0084] The data acquisition module is configured to acquire energy consumption parameters and energy consumption associated variables of a plurality of production units in a target factory.

[0085] The data processing module is configured to divide the energy consumption parameters into energy consumption data sequences corresponding to a plurality of time scales according to a preset time interval for each production unit, and adjust a reference energy consumption threshold based on the energy consumption associated variables to obtain a target energy consumption threshold corresponding to the production unit.

[0086] The energy distribution level determination module is configured to calculate energy consumption trend characteristic values of the production units according to the energy consumption data sequences corresponding to the time scales, and determine the energy distribution levels of the production units in combination with the energy consumption trend characteristic values of the production units and the target energy consumption threshold.

[0087] The energy quota division module is configured to divide the available energy quotas corresponding to the production units based on the energy distribution levels of the production units and the total energy quota of the target factory.

[0088] On the basis of the above embodiment, the data processing module is further configured to extract power consumption data and peak power data from the energy consumption parameters, sample the power consumption data and the peak power data at a second-level time interval to obtain a second-level energy consumption sequence, sample the power consumption data and the peak power data at a minute-level time interval to obtain a minute-level energy consumption sequence, sample the power consumption data and the peak power data at a hour-level time interval to obtain a hour-level energy consumption sequence, and take the second-level energy consumption sequence, the energy consumption sequence and the hour-level energy consumption sequence as the energy consumption data sequences corresponding to the time scales.

[0089] On the basis of the above embodiment, the data processing module is further configured to obtain a production environment temperature and a device running time length in the energy consumption correlation variables, determine a first correction coefficient corresponding to the production environment temperature and a second correction coefficient corresponding to the device running time length in a preset correction coefficient mapping table, and multiply the baseline energy consumption threshold by the first correction coefficient and the second correction coefficient in sequence to obtain the target energy consumption threshold corresponding to the production unit.

[0090] On the basis of the above embodiment, the energy distribution level determination module is further configured to process the energy consumption data sequences corresponding to the time scales by using a sliding window method to obtain energy consumption data in a plurality of time windows, calculate a mean value and a standard deviation of the energy consumption data in each time window, calculate an energy consumption growth rate based on the mean values of any two adjacent time windows, calculate an energy consumption stability index based on the standard deviations of the time windows, and superimpose the energy consumption growth rate and the energy consumption stability index after normalization processing to obtain the energy consumption trend characteristic values.

[0091] On the basis of the above embodiment, the energy distribution level determination module obtains a production activity type of the production unit, and determines an energy consumption floating range corresponding to the production activity type in a database, determines a predicted energy consumption fluctuation range of the production unit based on the energy consumption floating range of the production unit and the energy consumption trend characteristic values, calculates a deviation between the predicted energy consumption fluctuation range and the target energy consumption threshold, and determines an energy distribution level corresponding to the deviation in a preset energy distribution level mapping table.

[0092] On the basis of the above-mentioned embodiments, the energy quota division module is further configured to determine, based on the energy distribution level of each production unit, an energy quota proportion corresponding to each production unit; and multiply the energy quota proportion corresponding to each production unit by the total energy quota of the target factory to obtain an available energy quota corresponding to each production unit.

[0093] On the basis of the above-mentioned embodiments, the energy quota division module is further configured to obtain the cooling tower backwater temperature and the current energy consumption data of the target factory; calculate an energy consumption deviation between the current energy consumption data and a preset energy consumption reference value, and calculate a temperature deviation between the backwater temperature and a reference temperature; and when the temperature deviation is less than a temperature deviation threshold value and the energy consumption deviation is greater than an energy consumption deviation threshold value, reduce the fan rotating speed of the target factory according to a preset speed reduction step.

[0094] It should be noted that: the device provided in the above-mentioned embodiments is only exemplified by the division of the above-mentioned functional modules when realizing its functions, and in actual application, the above-mentioned functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the above-described functions. In addition, the device and method embodiments provided in the above-mentioned embodiments belong to the same concept, and the specific implementation process is detailed in the method embodiments, which will not be described here.

[0095] The present application also discloses an electronic device. Referring to Figure 3 , Figure 3 is a structural schematic diagram of an electronic device disclosed by the embodiments of the present application. The electronic device 300 can include at least one processor 301, at least one network interface 304, a user interface 303, a memory 305, and at least one communication bus 302.

[0096] The communication bus 302 is configured to realize the connection and communication between the components.

[0097] The user interface 303 can include a display interface and a camera interface. Optionally, the user interface 303 can further include a standard wired interface and a wireless interface.

[0098] Optionally, the network interface 304 can include a standard wired interface and a wireless interface (such as a WI-FI interface).

[0099] The processor 301 can include one or more processing cores. The processor 301 connects various parts within the server through various interfaces and lines, performs various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Alternatively, the processor 301 can be implemented in at least one of a hardware form of a digital signal processing (DSP), a field-programmable gate array (FPGA), and a programmable logic array (PLA). The processor 301 can integrate a combination of one or more of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. Among them, the CPU mainly processes operating systems, user interface graphs, and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; and the modem is used for processing wireless communication. It can be understood that the above-mentioned modem can also not be integrated into the processor 301, but can be realized by a separate chip.

[0100] The memory 305 can include a random access memory (RAM) and a read-only memory (ROM). Alternatively, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 can include a program storage area and a data storage area, wherein the program storage area can store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area can store data involved in the above-mentioned various method embodiments, etc. The memory 305 can alternatively be at least one storage device located away from the aforementioned processor 301. Referring to Figure 3 The memory 305 as a computer storage medium can include an operating system, a network communication module, a user interface module, and an application program of a smart factory energy efficiency optimization method.

[0101] In Figure 3In the electronic device 300 shown, the user interface 303 is mainly used to provide an interface for the user to input, and obtain data input by the user; and the processor 301 can be used to invoke an application program stored in the memory 305 and storing a smart factory energy efficiency optimization method, which, when executed by one or more processors 301, causes the electronic device 300 to perform the method of one or more of the above-described embodiments. It should be noted that, for the foregoing method embodiments, in order to simply describe, they are all described as a combination of a series of actions, but those skilled in the art should know that the present application is not limited to the order of the actions described, because according to the present application, certain steps can be performed in other order or at the same time. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0102] In the above embodiments, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0103] In several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic. The division of units is only a logical function division. There can be another division manner in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some services interfaces, devices or units, and can be electrical or other forms.

[0104] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the present embodiment.

[0105] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically independently, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0106] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable memory. Based on such understanding, the technical solutions of the present application essentially or say the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a memory and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the embodiments of the present application. The aforementioned memory includes: a U disk, a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0107] The above are only exemplary embodiments of the present disclosure, and cannot limit the scope of the present disclosure. That is, any equivalent changes and modifications made in accordance with the teachings of the present disclosure are still within the scope of the present disclosure. Other embodiments of the present disclosure will be readily apparent to those skilled in the art upon considering the specification and practicing the disclosure.

[0108] The present application is intended to cover any variations, uses or adaptive changes of the present disclosure that follow the general principles of the present disclosure and include common knowledge or conventional technical means in the technical field not described in the present disclosure. The specification and examples are only considered as exemplary.

Claims

1. A method for optimizing energy efficiency in a smart factory, characterized in that, include: Obtain energy consumption parameters and energy consumption-related variables for multiple production units within the target factory; For each production unit, the energy consumption parameters are divided into multiple time scales corresponding to energy consumption data sequences according to a preset time interval, and the baseline energy consumption threshold is adjusted based on the energy consumption correlation variable to obtain the target energy consumption threshold corresponding to the production unit. Based on the energy consumption data sequence corresponding to each time scale, calculate the energy consumption trend characteristic value of the production unit, and combine the energy consumption trend characteristic value of the production unit with the target energy consumption threshold to determine the energy allocation level of the production unit. Based on the energy allocation level of each production unit and the total energy quota of the target factory, the available energy quota corresponding to each production unit is divided. The step of adjusting the baseline energy consumption threshold based on the energy consumption correlation variable to obtain the target energy consumption threshold corresponding to the production unit includes: Obtain the production environment temperature and equipment operating time from the energy consumption-related variables; In a preset correction coefficient mapping table, a first correction coefficient corresponding to the production environment temperature and a second correction coefficient corresponding to the equipment running time are determined. The benchmark energy consumption threshold is multiplied sequentially by the first correction coefficient and the second correction coefficient to obtain the target energy consumption threshold corresponding to the production unit; The step of determining the energy allocation level of the production unit by combining the energy consumption trend characteristic value and the target energy consumption threshold includes: Obtain the production activity type of the production unit and determine the energy consumption fluctuation range corresponding to the production activity type in the database; Based on the energy consumption fluctuation range and energy consumption trend characteristic value of the production unit, the expected energy consumption fluctuation range of the production unit is determined. Calculate the offset between the expected energy consumption fluctuation range and the target energy consumption threshold, and determine the energy allocation level corresponding to the offset in a preset energy allocation level mapping table.

2. The smart factory energy efficiency optimization method according to claim 1, characterized in that, The preset time intervals include second-level time intervals, minute-level time intervals, and hour-level time intervals. Dividing the energy consumption parameters into multiple time-scale corresponding energy consumption data sequences according to the preset time intervals includes: Extract electricity consumption data and peak power data from the energy consumption parameters; The power consumption data and peak power data are sampled according to the second-level time interval to obtain the second-level energy consumption sequence; The power consumption data and peak power data are sampled according to the minute-level time interval to obtain the minute-level energy consumption sequence; The electricity consumption data and peak power data are sampled according to the hourly time interval to obtain the hourly energy consumption sequence; The second-level energy consumption sequence, the energy consumption sequence, and the hour-level energy consumption sequence are used as energy consumption data sequences corresponding to multiple time scales.

3. The smart factory energy efficiency optimization method according to claim 1, characterized in that, The step of calculating the energy consumption trend characteristic value of the production unit based on the energy consumption data sequence corresponding to each time scale includes: The energy consumption data sequence corresponding to each time scale is processed using the sliding window method to obtain energy consumption data within multiple time windows; Calculate the mean and standard deviation of energy consumption data within each time window; Calculate the energy consumption growth rate based on the average of any two adjacent time windows; Based on the standard deviation of each time window, the energy consumption stability index is calculated. The energy consumption growth rate and energy consumption stability index are normalized and then superimposed to obtain the energy consumption trend characteristic value.

4. The smart factory energy efficiency optimization method according to claim 1, characterized in that, The allocation of available energy quotas for each production unit based on its energy allocation level and the total energy quota of the target factory includes: Based on the energy allocation level of each production unit, determine the energy quota ratio corresponding to each production unit; The energy quota ratio corresponding to each production unit is multiplied by the total energy quota of the target factory to obtain the available energy quota corresponding to each production unit.

5. The smart factory energy efficiency optimization method according to claim 1, characterized in that, After allocating the available energy quota for each production unit based on its energy allocation level and the total energy quota of the target factory, the method further includes: Obtain the cooling tower return water temperature and current energy consumption data of the target factory; Calculate the energy consumption deviation between the current energy consumption data and the preset energy consumption benchmark value, and calculate the temperature deviation between the return water temperature and the benchmark temperature; When the temperature deviation is less than the temperature deviation threshold and the energy consumption deviation is greater than the energy consumption deviation threshold, the fan speed of the target factory is reduced according to the preset deceleration step size.

6. A smart factory energy efficiency optimization system, characterized in that, The system includes: The data acquisition module is used to acquire energy consumption parameters and energy consumption-related variables of multiple production units within the target factory; The data processing module is used to divide the energy consumption parameters of each production unit into energy consumption data sequences corresponding to multiple time scales according to a preset time interval, and adjust the benchmark energy consumption threshold based on the energy consumption correlation variable to obtain the target energy consumption threshold corresponding to the production unit. The energy allocation level determination module is used to calculate the energy consumption trend characteristic value of the production unit based on the energy consumption data sequence corresponding to each time scale, and determine the energy allocation level of the production unit by combining the energy consumption trend characteristic value of the production unit and the target energy consumption threshold. An energy quota allocation module is used to allocate the available energy quota for each production unit based on the energy allocation level of each production unit and the total energy quota of the target factory. The step of adjusting the baseline energy consumption threshold based on the energy consumption correlation variable to obtain the target energy consumption threshold corresponding to the production unit includes: Obtain the production environment temperature and equipment operating time from the energy consumption-related variables; In a preset correction coefficient mapping table, a first correction coefficient corresponding to the production environment temperature and a second correction coefficient corresponding to the equipment running time are determined. The benchmark energy consumption threshold is multiplied sequentially by the first correction coefficient and the second correction coefficient to obtain the target energy consumption threshold corresponding to the production unit; The step of determining the energy allocation level of the production unit by combining the energy consumption trend characteristic value and the target energy consumption threshold includes: Obtain the production activity type of the production unit and determine the energy consumption fluctuation range corresponding to the production activity type in the database; Based on the energy consumption fluctuation range and energy consumption trend characteristic value of the production unit, the expected energy consumption fluctuation range of the production unit is determined. Calculate the offset between the expected energy consumption fluctuation range and the target energy consumption threshold, and determine the energy allocation level corresponding to the offset in a preset energy allocation level mapping table.

7. An electronic device, characterized in that, The device includes a processor, a memory, a user interface, and a network interface. The memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory to enable the electronic device to perform the smart factory energy efficiency optimization method as described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed, perform the smart factory energy efficiency optimization method as described in any one of claims 1-5.

Images