Method for predicting production electricity consumption of factory, control device and storage medium

Abstract

The embodiment of the invention provides a method for predicting factory production electricity consumption, a control device and a storage medium, and belongs to the technical field of factory energy management. The method comprises the following steps: acquiring historical power consumption data of each power consumption unit; determining the correlation between the historical electricity consumption and the electricity consumption influence factors; based on the determined correlation, determining a power utilization quantitative analysis strategy of each power utilization unit through the historical power utilization amount and the value of the power utilization influence factor; and predicting the production power consumption of each power consumption unit and the production power consumption of the factory through the power consumption quantitative analysis strategy of each power consumption unit. According to the embodiment of the invention, the corresponding power consumption quantitative analysis strategy is determined through the correlation between the power consumption and the power consumption influence factors, so that the factory production power consumption in days, months, years and the like can be accurately predicted. And the power utilization energy cost of the production line can be effectively managed and controlled, energy key points and waste points can be identified, and energy conservation and consumption reduction actions can be carried out in a targeted manner.

Description

Technical Field

[0001] The present invention relates to the technical field of factory energy management, and in particular to a method, a control device and a storage medium for predicting factory production power consumption. Background Art

[0002] As the world's demand for low carbon, energy conservation and emission reduction continues to increase, the measurement and monitoring of electricity consumption in my country's factory production lines and the comprehensive forecasting and budget management of energy costs in production costs have become particularly important.

[0003] However, the existing prediction of factory electricity consumption is based on the rated power of the factory's electrical equipment. As a result, the accuracy of electricity cost prediction management in factory production is not high, and it is impossible to effectively control the electricity energy cost of the production line, nor to identify key energy points and waste points, making it impossible to carry out targeted energy-saving and consumption-reduction actions. Summary of the invention

[0004] The purpose of the embodiment of the present invention is to provide a method for predicting factory production power consumption, which can improve the prediction and management accuracy of factory production power consumption.

[0005] In order to achieve the above-mentioned purpose, an embodiment of the present invention provides a method for predicting factory production power consumption, and the method for predicting factory production power consumption includes: obtaining historical power consumption data of each power consumption unit, and the historical power consumption data includes historical power consumption and values ​​of power consumption influencing factors; determining the correlation between the historical power consumption and the power consumption influencing factors; based on the determined correlation and through the historical power consumption and the values ​​of the power consumption influencing factors, determining a quantitative power consumption analysis strategy for each power consumption unit; and predicting the production power consumption of each power consumption unit and the production power consumption of the factory through the quantitative power consumption analysis strategy of each power consumption unit.

[0006] Optionally, each power consumption unit includes one or more electricity meters. Before obtaining the historical electricity consumption data of each power consumption unit, the method for predicting factory production electricity consumption also includes: according to the type of production equipment, the electricity meters corresponding to the same type of production equipment are divided into one power consumption unit, or according to the distribution of electricity meters, the electricity meters in the same area are divided into one power consumption unit.

[0007] Optionally, the power consumption influencing factors include the output or ambient temperature of the production equipment corresponding to the power consumption unit.

[0008] Optionally, determining the correlation between the historical power consumption and the power consumption influencing factors includes: dividing the N operating modes of each power consumption unit into corresponding N production time periods, where N≥1; for the historical power consumption data of each production time period, counting the values ​​of historical power consumption and power consumption influencing factors of each unit time period; and obtaining the correlation coefficient between the historical power consumption and power consumption influencing factors of the production time period by using part or all of the data in the counted values ​​of historical power consumption and power consumption influencing factors of each unit time period.

[0009] Optionally, the operating modes include non-production mode, production mode, and warm-up idle cycle mode.

[0010] Optionally, determining the correlation between the historical electricity consumption and the electricity consumption influencing factors also includes: when the obtained correlation coefficient between the historical electricity consumption and the electricity consumption influencing factors of the production time period is less than a first threshold value, determining that the correlation between the historical electricity consumption and the electricity consumption influencing factors of the production time period is irrelevant; when the obtained correlation coefficient between the historical electricity consumption and the electricity consumption influencing factors of the production time period is between the first threshold value and the second threshold value, determining that the correlation between the historical electricity consumption and the electricity consumption influencing factors of the production time period is weakly correlated; and when the obtained correlation coefficient between the historical electricity consumption and the electricity consumption influencing factors of the production time period is greater than the second threshold value, determining that the correlation between the historical electricity consumption and the electricity consumption influencing factors of the production time period is strongly correlated.

[0011] Optionally, the quantitative analysis strategy for electricity consumption of each electricity consumption unit is determined based on the determined correlation and through the historical electricity consumption and the values ​​of the electricity consumption influencing factors, including: when the correlation between the historical electricity consumption and the electricity consumption influencing factors of the production time period is strongly correlated, a corresponding linear regression model is established through the statistical values ​​of the historical electricity consumption and the electricity consumption influencing factors of each unit time period, so as to obtain the predicted value of electricity consumption of the production time period through the linear regression model; when the correlation between the historical electricity consumption and the electricity consumption influencing factors of the production time period is weakly correlated, a corresponding probability distribution model graph is established through the statistical historical electricity consumption of each unit time period, so as to obtain the predicted value of electricity consumption of the production time period through the characterization value determined by the discreteness of the probability distribution model graph; and when the correlation between the historical electricity consumption and the electricity consumption influencing factors of the production time period is uncorrelated, the predicted value of electricity consumption of the production time period is obtained through the average value of the statistical historical electricity consumption of each unit time period.

[0012] Optionally, the production power consumption of each power consuming unit and the production power consumption of the factory are predicted through the power consumption quantitative analysis strategy of each power consuming unit, including: for each power consuming unit, based on the power consumption quantitative analysis strategy, the production power consumption of the power consuming unit is predicted by setting the value of the power consumption influencing factor; and the production power consumption of the factory is predicted by summing the predicted production power consumption of each power consuming unit.

[0013] An embodiment of the present invention also provides a control device for a method for predicting factory production electricity consumption, the control device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the computer program to implement the above-mentioned method for predicting factory production electricity consumption.

[0014] An embodiment of the present invention further provides a machine-readable storage medium, on which instructions are stored, and the instructions enable a machine to execute the above-mentioned method for predicting factory production electricity consumption.

[0015] Through the above technical solution, the embodiment of the present invention determines the corresponding quantitative analysis strategy of electricity consumption through the correlation between electricity consumption and factors affecting electricity consumption, so as to accurately predict the daily, monthly, annual and other factory production electricity consumption. It can also effectively control the electricity energy cost of the production line, identify key energy points and waste points, and carry out targeted energy-saving and consumption-reducing actions.

[0016] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings:

[0018] Figure 1 It is a schematic flow chart of a method for predicting factory production power consumption provided by an embodiment of the present invention;

[0019] Figure 2 It is a schematic diagram of a linear regression model with strong correlation of output under the production mode of an example power consumption unit;

[0020] Figure 3 It is a schematic diagram of a probability distribution model diagram of weakly correlated output under the production mode of an example power consumption unit. DETAILED DESCRIPTION

[0021] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present invention, and is not used to limit the embodiment of the present invention.

[0022] Figure 1 This is a flow chart of a method for predicting factory production power consumption provided by an embodiment of the present invention. Please refer to Figure 1 The method for predicting factory production power consumption may include the following steps:

[0023] Step S110: Acquire historical power consumption data of each power consumption unit, wherein the historical power consumption data includes historical power consumption and values ​​of power consumption influencing factors.

[0024] The electric meters of the factory may be divided into a plurality of electric units, each of which may include one or more electric meters. The historical electric data is the historical electric data of a preset time period, for example, the historical electric data of three months, one year or three years.

[0025] Preferably, before step S110, the method for predicting factory production electricity consumption may further include: dividing the electricity meters corresponding to the same type of production equipment into one electricity consumption unit according to the type of production equipment, or dividing the electricity meters in the same area into one electricity consumption unit according to the distribution of electricity meters.

[0026] To illustrate by way of example, the electric meters corresponding to the same type of production equipment can be divided into one power unit according to the type of production equipment, and the divided power units include, for example, PU power unit, SCR power unit, cooling system power unit, other power units, etc.; the electric meters can also be divided into multiple power units according to the distribution of the electric meters, and the divided power units include, for example, A zone power unit, P zone power unit, T zone power unit, etc.; the electric meters can also be partitioned according to the distribution of the electric meters, and then the electric meters corresponding to the same type of production equipment in each partition can be divided into one power unit according to the type of production equipment, and the divided power units include, for example, A zone power unit, T zone stand power unit, T zone SCR power unit, T zone cooling system power unit, PU zone power unit, etc.

[0027] In the embodiment of the present invention, the power consumption influencing factors preferably include the output of the production equipment corresponding to the power consumption unit or the ambient temperature.

[0028] Among them, the output of the production equipment is equivalent to the economic influencing factor of electricity consumption, which is the output of the products produced by the production equipment (for example, the number of finished, semi-finished or assembled engines produced), and the ambient temperature is equivalent to the environmental influencing factor of electricity consumption. For example, the electricity consumption influencing factor of the PU power unit, SCR power unit, etc. is the output of the production equipment, and the electricity consumption influencing factor of the cooling system power unit, high-temperature hazardous waste treatment system power unit, etc. is the ambient temperature.

[0029] Step S120: Determine the correlation between the historical power consumption and the power consumption influencing factors.

[0030] Preferably, step S120 may include steps S121-S123: step S121, dividing into corresponding N production time periods according to the N operating modes of each power consumption unit, wherein N≥1; step S122, for the historical power consumption data of each production time period, counting the historical power consumption and the values ​​of power consumption influencing factors for each unit time period; step S123, obtaining the correlation coefficient between the historical power consumption and the power consumption influencing factors of the production time period by using part or all of the data in the counted values ​​of the historical power consumption and the power consumption influencing factors for each unit time period.

[0031] The working mode of the power unit can be classified by day (24 hours) according to the working condition of the corresponding production equipment. The working mode preferably includes a non-production mode, a production mode, a warm-up idle cycle mode, etc.

[0032] Step S121, for each power unit's N operating modes, they can be divided into N production time periods. By way of example, each power unit can include different operating modes, for example, the operating mode of power unit A includes a production mode (e.g., 8:00-17:00 every day) and a non-production mode (e.g., other times of the day), the operating mode of power unit B includes a production mode (e.g., 8:00-17:00 every day) and a warm-up empty circulation mode (e.g., other times of the day), the operating mode of power unit C includes a production mode (e.g., 8:00-17:00 every day), a warm-up empty circulation mode (e.g., 6:00-8:00 and 17:00-22:00 every day) and a non-production mode (e.g., other times of the day), and the operating mode of power unit D includes only a production mode (e.g., 24 hours). According to the working mode of each power consumption unit, it is divided into corresponding N production time periods. For example, the time periods divided in the above brackets can be marked as non-production time periods, production time periods, warm-up idle cycle time periods, etc.

[0033] Step S122, for each production time period, the historical power consumption and the value of the power consumption influencing factor are counted for each unit time period. The unit time period is preferably an hour, which is helpful to identify the differences in power consumption peaks and troughs and the impact of 24-hour temperature changes on power consumption. For example, for the production period of power unit A, based on the historical power consumption data of a preset time period (for example, three months, one year, or three years), the sum of the historical power consumption per hour is calculated, and the value of the power consumption influencing factor is calculated (for example, the output per hour or the average temperature per hour).

[0034] Step S123, preferably, according to the Pearson correlation, the correlation coefficient between the historical power consumption and the power consumption influencing factors of the production time period is obtained. For example, for the production period of the power unit A, the correlation coefficient r(X,Y) between the historical power consumption X and the output Y or the ambient temperature Y of the production time period is calculated by the following formula:

[0035]

[0036] Where X represents the array vector of historical electricity consumption per hour, Y represents the array vector of output or ambient temperature per hour in the production time period, Cov(X, Y) represents the covariance of X and Y, and Var represents the variance.

[0037] Preferably, the correlation coefficient r(X,Y) can be calculated by using part of the data in the historical power consumption and the power consumption influencing factors of each unit time period to quickly obtain the correlation coefficient. For example, for the production period of power unit A, the correlation coefficient between the historical power consumption and the power consumption influencing factors of the production period can be calculated by summing the historical power consumption per hour calculated for any three days and calculating the value of the power consumption influencing factors through formula (1).

[0038] Preferably, step S120 may also include: when the correlation coefficient between the historical electricity consumption of the production time period and the factors affecting electricity consumption is less than a first threshold value, determining that the correlation between the historical electricity consumption of the production time period and the factors affecting electricity consumption is irrelevant; when the correlation coefficient between the historical electricity consumption of the production time period and the factors affecting electricity consumption is between the first threshold value and the second threshold value, determining that the correlation between the historical electricity consumption of the production time period and the factors affecting electricity consumption is weakly correlated; and when the correlation coefficient between the historical electricity consumption of the production time period and the factors affecting electricity consumption is greater than the second threshold value, determining that the correlation between the historical electricity consumption of the production time period and the factors affecting electricity consumption is strongly correlated.

[0039] Continuing with the above example, for the production time period of power consumption unit A, if the correlation coefficient is greater than the first threshold value (for example, threshold A), the historical power consumption of the production time period and the factors affecting power consumption (output or ambient temperature) are strongly correlated; if the correlation coefficient is between the first threshold value and the second threshold value (for example, between threshold A and threshold B), the historical power consumption of the production time period and the factors affecting power consumption (output or ambient temperature) are weakly correlated; if the correlation coefficient is less than the second threshold value (for example, threshold B), the historical power consumption of the production time period and the factors affecting power consumption (output or ambient temperature) are uncorrelated.

[0040] Preferably, before step S120, the method for predicting factory production power consumption further includes: determining a power consumption influencing factor of each power consumption unit, that is, the power consumption influencing factor of the power consumption unit is output or ambient temperature.

[0041] Step S130: Based on the determined correlation and through the historical power consumption and the values ​​of the power consumption influencing factors, a power consumption quantitative analysis strategy for each power consumption unit is determined.

[0042] Preferably, step S130 may include: 1) when the correlation between the historical electricity consumption of the production time period and the electricity consumption influencing factors is strongly correlated, a corresponding linear regression model is established through the statistical values ​​of the historical electricity consumption and the electricity consumption influencing factors of each unit time period, so as to obtain the predicted value of the electricity consumption of the production time period through the linear regression model; 2) when the correlation between the historical electricity consumption of the production time period and the electricity consumption influencing factors is weakly correlated, a corresponding probability distribution model graph is established through the statistical values ​​of the historical electricity consumption of each unit time period, so as to obtain the predicted value of the electricity consumption of the production time period through the characterization value determined by the discreteness of the probability distribution model graph; 3) when the correlation between the historical electricity consumption of the production time period and the electricity consumption influencing factors is uncorrelated, the predicted value of the electricity consumption of the production time period is obtained through the average value of the statistical historical electricity consumption of each unit time period.

[0043] Take an example to illustrate, 1) for an electrical unit (such as Figure 2 As shown in the figure, the production mode (corresponding to the production period) of the T-zone bench is strongly correlated with the output. The corresponding linear regression model can be established through the statistical hourly historical power consumption Z and output M values. For example, the statistical hourly historical power consumption Z and output M values ​​are input into matlab, and the following can be obtained: Figure 2 The linear regression model of the hourly historical electricity consumption Z and output M is shown in the figure. After linear fitting, it can be expressed as follows:

[0044] Z=C1M+ C0 (2)

[0045] Among them, C0 and C1 are the coefficients obtained by matlab fitting.

[0046] The above linear regression model or formula (2) shows the relationship between electricity consumption (for each unit time period) and the factors affecting electricity consumption. Therefore, the output per hour in the production time period can be input into the above linear regression model or formula (2) to predict the electricity consumption per hour in the production time period. The above linear regression model or formula (2) can also be used to characterize the relationship between electricity consumption and the factors affecting electricity consumption in the production time period. Therefore, the output per hour in the production time period can be input into the above linear regression model or formula (2) to predict the electricity consumption in the production time period; further, the output per year in the production time period can be input into the above linear regression model or formula (2) to predict the electricity consumption in the production time period for one year, etc.

[0047] If the production mode (corresponding to the production period) of the power unit A is strongly correlated with the ambient temperature, a linear regression model or formula (2) similar to the above can also be obtained, where M is the ambient temperature. Preferably, the relationship between the power consumption of each unit time period and each unit time period (ambient temperature) can also be obtained through a nested model. For example, the relationship between the hourly power consumption and the ambient temperature (for example, the average value of the ambient temperature per hour) is determined by the first model, and the relationship between the hourly power consumption and the hourly ambient temperature is obtained by nesting the first model through the second model. That is, the time (for example, May 15, May or July-September, etc.) can be input into the nested module to directly predict the power consumption of the production time period.

[0048] 2) For power consumption units (such as Figure 3 As shown in the figure, the production mode (corresponding to the production period) of the PU power unit is weakly correlated with the output. The corresponding probability distribution model diagram can be established through the statistical hourly historical power consumption Z and output M values, as shown in Figure 3 shown.

[0049] Preferably, the characterization value determined by the dispersion of the probability distribution model graph is the median or average value of the probability distribution model graph.

[0050] Figure 3 The straight line shown shows the average value R of the hourly electricity consumption in the production time period, which is used as the predicted value of hourly electricity consumption. The predicted value of electricity consumption in the production time period T (for example, T = 8 hours) can be obtained by the predicted value of hourly electricity consumption, i.e., G = T*R. Furthermore, the electricity consumption in the production time period of one month, three months, or one year can be predicted.

[0051] 3) Similar to 2), when the correlation between the historical electricity consumption of the production time period and the factors affecting electricity consumption is uncorrelated, the average hourly electricity consumption in the production time period is calculated by counting the historical electricity consumption of each unit time period, which is used as the predicted value of hourly electricity consumption. The predicted value of electricity consumption for the production time period can be obtained through the predicted value of hourly electricity consumption.

[0052] Step S140: predicting the production power consumption of each power consumption unit and the production power consumption of the factory through the power consumption quantitative analysis strategy of each power consumption unit.

[0053] Preferably, step S140 may include: for each power consumption unit, based on the power consumption quantitative analysis strategy, by setting the value of the power consumption influencing factor, predicting the production power consumption of the power consumption unit; and predicting the production power consumption of the factory by summing the predicted production power consumption of each power consumption unit.

[0054] As described above, based on the quantitative analysis strategy of electricity consumption of each electricity consumption unit obtained in step S130, the production electricity consumption of each electricity consumption unit can be predicted by setting the value of the electricity consumption influencing factor, and further, the production electricity consumption of the factory can be predicted. By way of example, for each electricity consumption unit, the relationship between the electricity consumption of the electricity consumption unit and the electricity consumption influencing factor can be obtained through the above-mentioned prediction method corresponding to each production time period (or production condition). For example, the operating mode of electricity unit A includes a production mode (for example, 8:00-17:00 every day) and a non-production mode (for example, other times of the day), wherein the production mode is strongly correlated with the output, and the non-production mode is unrelated to the output, then the predicted value of electricity consumption of the electricity consumption unit (every day) is Z=T1(C1M+C0)+T2*R, wherein T1=9 (hours), T2=15, C1 and C0 are parameters of formula (2), and R is the above Figure 3 The fitting parameters of the example. By setting the value of M, the power consumption forecast value can be obtained. M can be, for example, the output of one day, one month, three months or one year. For example, Table 1 shows the forecast of the production power consumption of each power unit in a certain year. Then, the sum of each column is the forecast value of the production power consumption of each power unit in one year, the sum of each row (i.e., ATPU) is the forecast value of the production power consumption of the factory every month, and the sum of the whole table is the forecast value of the production power consumption of the factory in one year.

[0055] Table 1 Forecast of electricity consumption of each electricity-consuming unit in a certain year

[0056] Label Area A PU SCR Cooling system T zone T zone other ATPU 2301 108720 218880 174960 154080 409680 81360 737280 2302 113040 259200 184320 210960 479520 83520 844560 2303 95040 226080 174240 147600 400320 78480 721440 2304 110160 236880 173520 84240 341280 83520 689040 2305 122400 234000 164880 50400 299520 84960 655920 2306 96480 195120 162000 86400 330480 81360 622080 2307 116640 208080 141840 86400 309600 80640 633600 2308 123840 239040 210240 81360 303120 84240 665280 2309 113760 236160 231840 72720 303120 77760 652320 2310 118080 197280 162720 89280 337680 85680 653040 2311 113760 182880 178560 97200 359280 83520 655920 2312 105840 205920 165600 112320 282960 77760 666720 Mean 111600 217440 164160 109440 354960 81360 684000

[0057] As shown in Table 1, the embodiment of the present invention can obtain energy key points and waste points based on analysis. For example, energy key points (for example, T zone) are obtained by sorting the power consumption of each power consuming unit, and waste points are determined through horizontal comparison (for example, comparison of power consumption of each power consuming unit in different years and the same month) or vertical comparison (for example, comparison of the value of each column in Table 1 with the mean), so as to formulate effective power-saving measures and carry out targeted energy-saving and consumption-reducing actions.

[0058] Preferably, the actual power consumption data of each power consumption unit may continue to be obtained to optimize the parameters (or characterization values) of the calculation model in the power consumption quantitative analysis strategy of step S130.

[0059] Based on this, the embodiment of the present invention determines the corresponding quantitative analysis strategy of electricity consumption through the correlation between electricity consumption and factors affecting electricity consumption, so as to accurately predict the daily, monthly, and annual factory production electricity consumption. It can also effectively control the energy cost of production line electricity consumption, identify key energy points and waste points, and carry out targeted energy-saving and consumption-reducing actions.

[0060] An embodiment of the present invention also provides a control device for a method for predicting factory production electricity consumption, the control device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the computer program to implement the above-mentioned method for predicting factory production electricity consumption.

[0061] An embodiment of the present invention further provides a machine-readable storage medium, on which instructions are stored, and the instructions enable a machine to execute the above-mentioned method for predicting factory production electricity consumption.

[0062] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0063] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0064] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0065] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0066] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0067] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0068] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0069] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0070] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for predicting factory production electricity consumption, characterized in that: The method for predicting the power consumption of a factory comprises: Acquire historical power consumption data of each power consumption unit, wherein the historical power consumption data includes historical power consumption and values ​​of power consumption influencing factors; Determining the correlation between the historical power consumption and the power consumption influencing factors; Based on the determined correlation and through the historical power consumption and the values ​​of the power consumption influencing factors, determining a power consumption quantitative analysis strategy for each power consumption unit; and The power consumption of each power consuming unit and the power consumption of the factory are predicted by means of the power consumption quantitative analysis strategy of each power consuming unit.

2. The method for predicting factory production power consumption according to claim 1, characterized in that: Each power consumption unit includes one or more power meters. Before acquiring the historical power consumption data of each power consumption unit, the method for predicting the power consumption of a factory production further includes: According to the type of production equipment, the electric meters corresponding to the same type of production equipment are divided into one power consumption unit, or According to the distribution of electricity meters, electricity meters in the same area are divided into one electricity consumption unit.

3. The method for predicting factory production power consumption according to claim 1, characterized in that: The power consumption influencing factors include the output or the ambient temperature of the production equipment corresponding to the power consumption unit.

4. The method for predicting factory production power consumption according to claim 1, characterized in that: Determining the correlation between the historical power consumption and the power consumption influencing factor includes: According to the N working modes of each power consumption unit, the power consumption units are divided into corresponding N production time periods, where N≥1; For each production time period, the historical electricity consumption data is counted and the values ​​of the factors affecting electricity consumption are calculated for each unit time period; and By counting part or all of the historical power consumption and the values ​​of the power consumption influencing factors in each unit time period, the correlation coefficient between the historical power consumption and the power consumption influencing factors in the production time period is obtained.

5. The method for predicting factory production power consumption according to claim 4, characterized in that: The operating modes include a non-production mode, a production mode, and a warm-up idle cycle mode.

6. The method for predicting factory production power consumption according to claim 4, characterized in that: The determining the correlation between the historical power consumption and the power consumption influencing factor further includes: When the obtained correlation coefficient between the historical power consumption and the power consumption influencing factor in the production time period is less than the first threshold, it is determined that the correlation between the historical power consumption and the power consumption influencing factor in the production time period is irrelevant; When the obtained correlation coefficient between the historical power consumption and the power consumption influencing factor in the production time period is between the first threshold and the second threshold, determining that the correlation between the historical power consumption and the power consumption influencing factor in the production time period is weakly correlated; and When the obtained correlation coefficient between the historical power consumption of the production time period and the power consumption influencing factors is greater than the second threshold, it is determined that the correlation between the historical power consumption of the production time period and the power consumption influencing factors is a strong correlation.

7. The method for predicting factory production power consumption according to claim 6, characterized in that: The determining of the power consumption quantitative analysis strategy of each power consumption unit based on the determined correlation and through the historical power consumption and the value of the power consumption influencing factor includes: When the correlation between the historical power consumption and the power consumption influencing factors of the production time period is strongly correlated, a corresponding linear regression model is established through the statistical values ​​of the historical power consumption and the power consumption influencing factors of each unit time period, so as to obtain the predicted value of the power consumption of the production time period through the linear regression model; When the correlation between the historical power consumption of the production time period and the power consumption influencing factors is weakly correlated, a corresponding probability distribution model diagram is established through the statistical historical power consumption of each unit time period, and a predicted value of power consumption in the production time period is obtained by a characterization value determined by the discreteness of the probability distribution model diagram; and When the correlation between the historical power consumption in the production time period and the power consumption influencing factors is uncorrelated, the predicted value of the power consumption in the production time period is obtained by counting the average value of the historical power consumption in each unit time period.

8. The method for predicting factory production power consumption according to claim 1, characterized in that: The method of predicting the production power consumption of each power consumption unit and the production power consumption of the factory through the power consumption quantitative analysis strategy of each power consumption unit includes: For each power consumption unit, based on the power consumption quantitative analysis strategy, by setting the value of the power consumption influencing factor, predicting the production power consumption of the power consumption unit; and The power consumption of the factory is predicted by summing the predicted power consumption of each power-consuming unit.

9. A control device for a method for predicting factory production power consumption, characterized in that: The control device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor executes the computer program to implement the method for predicting factory production electricity consumption according to any one of claims 1-8.

10. A machine-readable storage medium, characterized in that: The machine-readable storage medium stores instructions, which enable the machine to execute the method for predicting factory production electricity consumption according to any one of claims 1-8.

Images