Intelligent energy consumption management method and system for smart factory

Abstract

The invention discloses a smart factory-oriented energy consumption intelligent management method and system, and relates to the technical field of semiconductor smart factory energy consumption management, and the system can monitor and predict the energy consumption condition in the cleaning and cutting process in real time, timely discover the abnormality and early warn the production management personnel, and improve the production efficiency. And reduction of energy waste and environmental risks in production is promoted. Due to the establishment of the digital energy consumption model, the system can analyze energy consumption data more accurately, and then the cleaning and cutting processes are optimized. Through comparison and evaluation, the system can comprehensively consider a plurality of energy consumption factors in the cleaning and cutting processes, generate a first evaluation result and a second evaluation result, and generate a corresponding control strategy in real time, so that the system can guide production personnel to take effective measures at key moments, reduce energy consumption and cost, and improve production efficiency. And production management is facilitated to timely formulate long-term and short-term production optimization strategies, and a factory is promoted to develop towards a more intelligent, green and sustainable direction.

Description

Technical Field

[0001] The present invention relates to the technical field of energy consumption management of semiconductor smart factories, and specifically to an intelligent energy consumption management method and system for smart factories. Background Art

[0002] As an emerging model in the industrial field, smart factories have improved production efficiency and quality by introducing advanced information technology and automation equipment, but they also face the challenge of energy management. In the semiconductor production process, water waste is an important and common problem. Semiconductor manufacturing involves multiple process steps, including cleaning and cutting, which require a great deal of high-purity water and also pose a great risk of waste. Traditional energy management methods usually rely on experience and manual intervention, making it difficult to achieve real-time monitoring and intelligent management, leading to problems such as energy waste and environmental pollution.

[0003] Another problem is that traditional energy consumption management methods are not good at differentiating different production links. In smart factories, the energy consumption characteristics of different links such as cleaning and cutting are quite different, and because of different environments, targeted management and optimization are required. Traditional methods are usually difficult to accurately grasp these differences, resulting in insufficient overall control of energy consumption. Therefore, it is urgent to propose an intelligent energy consumption management method and system for smart factories that can divide and analyze the energy consumption of different links in detail and provide targeted optimization measures. Summary of the invention

[0004] 1. Technical issues to be resolved In view of the deficiencies in the prior art, the present invention provides an intelligent energy consumption management method and system for smart factories, which solves the problems mentioned in the background technology.

[0005] (II) Technical solution To achieve the above objectives, the present invention is implemented through the following technical solutions: an intelligent energy consumption management system for smart factories, comprising a first monitoring module, a second monitoring module, a digital energy consumption model module, an evaluation module and a control module; The first monitoring module is used to install a camera and a first integrated sensor in the semiconductor cleaning area to monitor pollution data on the surface of the equipment, water resource cleaning data and current real-time environmental data in real time to establish a first data set; The second monitoring module is used to install a second integrated sensor in the semiconductor cutting area to collect cutting data, water resource and energy consumption data, waste data and current real-time environmental data in the cutting area in real time to establish a second data set; The digital energy consumption model module is used to establish a three-dimensional model based on the panoramic cloud of the smart factory, and integrate the digital model to establish a digital energy consumption model, analyze and calculate the first data set and the second data set to obtain: cleaning pollution coefficient Qxw, cleaning area environmental coefficient Hjx1, real-time cleaning energy consumption coefficient Qxn2, real-time cutting energy consumption coefficient Qgx2 and cutting area environmental coefficient Hjx2; and associate the cleaning pollution coefficient Qxw, the cleaning area environmental coefficient Hjx1, and the real-time cleaning energy consumption coefficient Qxn2 to obtain the first evaluation consumption coefficient PG1; associate the real-time cutting energy consumption coefficient Qgx2 with the cutting area environmental coefficient Hjx2 to obtain the second evaluation consumption coefficient PG2; The evaluation module is used to compare the first evaluation consumption coefficient PG1 with the first threshold value X1 to obtain a first evaluation result, and compare the second evaluation consumption coefficient PG2 with the second threshold value X2 to obtain a second evaluation result; The control module is used to generate a corresponding control strategy according to the first evaluation result and the second evaluation result.

[0006] Preferably, the first data set includes but is not limited to the following data: semiconductor substrate surface contamination particle concentration klnd, semiconductor substrate total area zmj, contamination area wrmj, semiconductor substrate charge adsorption rate xfl, first air particle concentration kq1, first air humidity sd1, first air temperature wd1, VOCs volatile concentration hfwnd, cleaning equipment power sbgl, cleaning liquid flow qxyll, cleaning liquid concentration qxnd, cleaning liquid temperature qwd, water flow slll, wastewater treatment equipment power fsgl and cleaning time qxsj; The semiconductor substrate surface contamination particle concentration klnd is measured and obtained by a laser particle counter; the semiconductor substrate total area zmj and the contaminated area wrmj are measured and obtained by an image sensor; the semiconductor substrate charge adsorption rate xfl is measured and obtained by a charge sensor; the first air particle concentration kq1 is measured and obtained by a particle concentration sensor; the first air humidity sd1 is measured and obtained by a humidity sensor; the first air temperature wd1 is measured and obtained by a temperature sensor; the VOCs volatile concentration hfwnd is measured and obtained by a VOCs concentration sensor; the cleaning equipment power sbgl is measured by a power sensor to obtain the power consumption of the cleaning equipment; the cleaning liquid flow qxyll is measured and obtained by a flowmeter; the cleaning liquid concentration qxnd is measured and obtained by a concentration sensor; the cleaning liquid temperature qwd is measured by a temperature sensor to obtain the cleaning liquid temperature; the water flow slll is measured and obtained by a flowmeter; the wastewater treatment equipment power fsgl is measured by a power sensor to obtain the power consumption of the wastewater treatment equipment; the cleaning time qxsj is measured and obtained by a time sensor.

[0007] Preferably, the second data set includes but is not limited to the following data: cutting equipment power qggl, cutting rate qgsl, real-time cutting temperature qgwd, real-time cleaning liquid usage sssyl, cleaning liquid concentration qxnd, cutting liquid concentration qgynd, cutting liquid recovery amount qgyhs, cutting time qgsc, ventilation wind speed tffs, second air humidity sd2, second air temperature wd2, second air particle concentration kq2 and cutting liquid flow rate qgyls; The cutting equipment power qggl is obtained by collecting the power consumption of the cutting equipment through an electric power sensor; the cutting rate qgsl is obtained by measuring and obtaining through a speed sensor or an encoder; the real-time cutting temperature qgwd is obtained by measuring the tool surface temperature through a temperature sensor; the real-time usage of the cleaning fluid sssyl is obtained by measuring and obtaining through a flow meter; the cleaning fluid concentration qxnd and the cutting fluid concentration qgynd are obtained by measuring and obtaining through a concentration sensor; the cutting fluid recovery amount qgyhs is obtained by collecting and obtaining through a flow meter; the cutting time qgsc is obtained by measuring and obtaining through a time sensor; the ventilation wind speed tffs is obtained by measuring and obtaining through a wind speed sensor; the second air humidity sd2 is obtained by measuring and obtaining through a temperature sensor; the second air temperature wd2 is obtained by measuring and obtaining through a humidity sensor; the second air particle concentration kq2 is obtained by measuring and obtaining through a particle concentration sensor; the cutting fluid flow rate qgyls is obtained by measuring and obtaining through a flow rate sensor.

[0008] Preferably, the digital energy consumption model module includes a first calculation unit and a second calculation unit; the first calculation unit is used to input the first data set through the digital energy consumption model to analyze and calculate: the cleaning pollution coefficient Qxw, the cleaning area environment coefficient Hjx1 and the real-time cleaning energy consumption coefficient Qxn2; The cleaning pollution coefficient Qxw is obtained by extracting the semiconductor substrate surface pollution particle concentration klnd, the semiconductor substrate total area zmj, the pollution area wrmj and the semiconductor substrate charge adsorption rate xfl in the first data set; the substrate charge adsorption rate xfl is calculated by the following formula:

[0009] In the formula, Expressed as the surface charge density of the semiconductor substrate; It represents the total charge density, which indicates the total amount of charge on the substrate surface, including adsorbed particles, impurities and defects; The semiconductor substrate surface contamination particle concentration klnd, the semiconductor substrate total area zmj, the contamination area wrmj and the semiconductor substrate charge adsorption rate xfl are dimensionlessly processed to generate the cleaning contamination coefficient Qxw through the following formula:

[0010] in, , , ,and , w1, w2, w3 are weight values, and their specific values ​​are adjusted and set by the user is the first constant correction coefficient; The cleaning area environmental coefficient Hjx1 is obtained by extracting the first air particle concentration kq1, the first air humidity sd1, the first air temperature wd1 and the VOCs volatile matter concentration hfwnd in the first data set; after dimensionless processing, the cleaning area environmental coefficient Hjx1 is generated by the following formula:

[0011] In the formula, , , ,and , w1, w2, w3 are weight values, and their specific values ​​are adjusted and set by the user is the second constant correction coefficient; Indicates logarithmic operation with base 2; The real-time cleaning energy consumption coefficient Qxn2 is obtained by extracting the cleaning equipment power sbgl, cleaning liquid flow qxyll, cleaning liquid concentration qxnd, cleaning liquid temperature qwd, water flow slll, wastewater treatment equipment power fsgl and cleaning time qxsj in the first data set; after dimensionless processing, the real-time cleaning consumption coefficient Qxn2 is generated by the following formula:

[0012] Wherein, d, s, w, p and j represent the preset proportional coefficients of water flow slll, cleaning equipment power sbgl, cleaning liquid flow qxyll, cleaning liquid concentration qxnd and cleaning liquid temperature qwd respectively, z represents the preset proportional coefficient of the sum of wastewater treatment equipment power fsgl and cleaning time qxsj; 0.35≤d≤0.45, 0.05≤s≤0.10, 0.07≤w≤0.16, 0.05≤p≤0.10, 0.02≤j≤0.08, 0.04≤z≤0.11, and 0.58≤d+s+w+p+j+z≤1.0, is the third constant correction coefficient.

[0013] Preferably, the second calculation unit is used to input the second data set through a digital energy consumption model for analysis and calculation to obtain: a real-time cutting energy consumption coefficient Qgx2 and a cutting area environment coefficient Hjx2; The real-time cutting energy consumption coefficient Qgx2 is obtained by extracting the cutting equipment power qggl, cutting rate qgsl, real-time cutting temperature qgwd, real-time cleaning liquid usage sssyl, cleaning liquid concentration qxnd, cutting liquid concentration qgynd, cutting liquid recovery amount qgyhs and cutting time qgsc in the second data set; after dimensionless processing, the real-time cutting energy consumption coefficient Qgx2 is generated by the following formula:

[0014] Wherein, x, c, v, b, m and o represent the preset proportional coefficients of the real-time usage of cleaning fluid sssyl, the power of cutting equipment qggl, the cutting rate qgsl, the real-time cutting temperature qgwd, the recovery amount of cutting fluid qgyhs and the cutting time qgsc, respectively; n represents the preset proportional coefficient of the sum of the cleaning fluid concentration qxnd and the cutting fluid concentration qgynd; 0.25≤x≤0.35, 0.06≤c≤0.10, 0.08≤v≤0.12, 0.05≤b≤0.10, 0.07≤n≤0.13, 0.09≤m≤0.20, and 0.60≤x+c+v+b+n+m≤1.0, is the fourth constant correction coefficient; The cutting area environmental coefficient Hjx2 is obtained by extracting the ventilation wind speed tffs, the second air humidity sd2, the second air temperature wd2, the second air particle concentration kq2 and the cutting fluid flow rate qgyls in the second data set; after dimensionless processing, the cutting area environmental coefficient Hjx2 is generated by the following formula:

[0015] In the formula, , , , ,and , w7, w8, w9 and w10 are weight values, and their specific values ​​are adjusted and set by the user is the fifth constant correction coefficient; Represents the base-2 logarithm operation.

[0016] Preferably, the digital energy consumption model module further includes a first association unit and a second association unit; The first association unit is used to associate the cleaning pollution coefficient Qxw, the cleaning area environment coefficient Hjx1, and the real-time cleaning energy consumption coefficient Qxn2, and obtain the first evaluation consumption coefficient PG1 through the following association formula:

[0017] In the formula, , ,and , is the weight, It is a logarithm operation with 2 natural numbers as base; The second association unit is used to associate the real-time cutting energy consumption coefficient Qgx2 with the cutting area environment coefficient Hjx2, and obtain the second evaluation consumption coefficient PG2 through the following association formula:

[0018] In the formula, , ,and , is the weight, It is a logarithm operation with base 2 as natural number.

[0019] Preferably, the evaluation module comprises a first evaluation unit; The first evaluation unit is used to use the evaluation module to compare the first evaluation consumption coefficient PG1 with the first threshold value X1 to obtain a first evaluation result, including: When the first evaluation consumption coefficient PG1 is greater than the first threshold value X1*120%, it means that the energy consumption exceeds the threshold value significantly, and a first energy consumption unqualified result is generated; When the first evaluation consumption coefficient PG1> the first threshold value X1 and does not reach the first threshold value X1*120%, it means that the energy consumption fluctuation exceeds the threshold value, and a second energy consumption unqualified result is generated; When the first evaluation consumption coefficient PG1 = the first threshold value X1, it indicates that the energy consumption is normal and is in a qualified state, and a first energy consumption qualified result is generated; When the first evaluation consumption coefficient PG1 is less than the first threshold value X1, it indicates that the energy consumption is low, and a second energy consumption qualified result is generated.

[0020] Preferably, the evaluation module comprises a second evaluation unit; The second evaluation unit is used to compare the second evaluation consumption coefficient PG2 with the second threshold value X2 to obtain a second evaluation result, including: When the second evaluation consumption coefficient PG2 is greater than the second threshold value X2*120%, it indicates that the energy consumption exceeds the threshold value significantly, and a third energy consumption unqualified result is generated; When the second evaluation consumption coefficient PG2> the second threshold value X2 and does not reach the second threshold value X2*120%, it means that the energy consumption fluctuation exceeds the threshold value, and a fourth energy consumption unqualified result is generated; When the second evaluation consumption coefficient PG2 = the second threshold value X2, it indicates that the energy consumption is normal and is in a qualified state, and a third energy consumption qualified result is generated; When the second evaluation consumption coefficient PG2 is less than the second threshold value X2, it indicates that the energy consumption is low, and a fourth energy consumption qualified result is generated.

[0021] Preferably, the control module includes an alarm unit, a visualization unit and a control unit; The alarm unit is used to generate a first warning information, a second warning information, a third warning information and a fourth warning information according to the first energy consumption unqualified result, the second energy consumption unqualified result, the third energy consumption unqualified result and the fourth energy consumption unqualified result, and to make the first warning information, the second warning information, the third warning information and the fourth warning information be marked prominently on the visualization screen through the visualization unit; to perform first priority intervention processing on the first warning information and the third warning information; and to perform second priority access processing on the second warning information and the fourth warning information; The control unit generates a first control strategy according to the first energy consumption unqualified result, and the first control strategy includes: emergency intervention, stopping or slowing down the cleaning process, checking the equipment status, adjusting the process parameters, purifying the indoor air, controlling the indoor temperature between 10-20°C, controlling the humidity between 40%-60%, and controlling the energy consumption to be equal to the first threshold value X1; A second control strategy is generated according to the second energy consumption failure result, wherein the second control strategy includes: performing cleaning equipment inspection and maintenance, increasing the cleaning liquid concentration to 3-5%, increasing the cleaning time by 20%, and increasing the wastewater treatment power by 10%, and controlling the energy consumption until it is equal to the first threshold value X1; A third control strategy is generated according to the third energy consumption unqualified result, and the third control strategy includes: emergency intervention of the cutting equipment to stop or slow down the cutting process, optimize the cutting rate, cutting fluid flow rate and cutting fluid concentration parameters, check the cutting equipment tool wear, and replace new tools when necessary to control friction resistance, control the concentration and temperature of the coolant and the cleaning fluid; and increase the ventilation speed to 0.3m / s to 0.5m / s, purify the indoor air, control the indoor temperature between 10-20°C, control the humidity between 40%-60%, and control the energy consumption to be equal to the second threshold value X2; A fourth control strategy is generated according to the fourth energy consumption unqualified result, and the fourth control strategy includes: upgrading the cutting equipment, a real-time cutting fluid recycling system, increasing the filtering power processing of the used cutting fluid, and recycling it for secondary use, adjusting the cutting parameters in real time, and increasing the ventilation speed to 0.1m / s to 0.3m / s, and controlling the energy consumption to be equal to the second threshold value X2; Based on the first energy consumption qualified result, the second energy consumption qualified result, the third energy consumption qualified result and the fourth energy consumption qualified result, continuous monitoring and regular inspections are carried out.

[0022] An intelligent energy consumption management method for a smart factory comprises the following steps: Step 1, data monitoring: Install a camera and a first integrated sensor in the semiconductor cleaning area to monitor the pollution data on the surface of the equipment, the water resource cleaning data and the current real-time environmental data to form a first data set; install a second integrated sensor in the semiconductor cutting area to collect cutting data, water resource energy consumption data, waste data and the current real-time environmental data in real time to form a second data set; Step 2, establishment of digital energy consumption model: establish a three-dimensional model through panoramic cloud, integrate the digital model, and construct a digital energy consumption model; use the digital energy consumption model to analyze and calculate the first data set and the second data set to obtain the cleaning pollution coefficient Qxw, the cleaning area environmental coefficient Hjx1, the real-time cleaning energy consumption coefficient Qxn2, the real-time cutting energy consumption coefficient Qgx2 and the cutting area environmental coefficient Hjx2; and associate the cleaning pollution coefficient Qxw, the cleaning area environmental coefficient Hjx1, and the real-time cleaning energy consumption coefficient Qxn2 to obtain the first evaluation consumption coefficient PG1; associate the real-time cutting energy consumption coefficient Qgx2 with the cutting area environmental coefficient Hjx2 to obtain the second evaluation consumption coefficient PG2; Step 3, comparative evaluation: compare the first evaluation consumption coefficient PG1 with the first threshold value X1 to obtain a first evaluation result, and compare the second evaluation consumption coefficient PG2 with the second threshold value X2 to obtain a second evaluation result; Step 4: Generate control strategies: Generate corresponding control strategies and execute different control strategies based on the first evaluation results and the second evaluation results.

[0023] (III) Beneficial effects The present invention provides an intelligent energy consumption management method and system for smart factories, which has the following beneficial effects: (1) This is an intelligent energy consumption management method and system for smart factories. By installing cameras and sensors in the cleaning and cutting areas, the system can monitor the pollution conditions, energy consumption data and environmental changes in key areas of the semiconductor production process in real time. This enables the system to achieve fine-grained monitoring of production links and helps implement targeted optimization measures in specific areas, thereby minimizing resource waste.

[0024] (2) This is an intelligent energy consumption management method and system for smart factories. The establishment of a digital energy consumption model enables energy consumption factors in the cleaning and cutting processes to be analyzed and calculated more accurately. The parameters obtained, such as the cleaning pollution coefficient, cleaning area environmental coefficient, real-time cleaning energy consumption coefficient, and real-time cutting energy consumption coefficient, improve the accuracy of energy consumption assessment. This accuracy helps to detect potential problems in a timely manner and adopt targeted improvement strategies in the shortest time.

[0025] (3) This is an intelligent energy consumption management method and system for smart factories. Through comparative evaluation, the system can generate a first evaluation result and a second evaluation result in real time, and generate corresponding early warning information for energy consumption exceeding the threshold. This enables production managers to obtain key information in a timely manner and take emergency intervention measures to minimize potential losses. At the same time, the optimization strategy generated by the system can help achieve real-time production process optimization and improve production efficiency.

[0026] (4) This is an intelligent energy consumption management method and system for smart factories. The generated control strategy is flexible and can implement different control schemes according to different evaluation results. For example, if the energy consumption exceeds the standard during the cleaning process, the system can recommend emergency intervention, stop or slow down the cleaning process, and adjust environmental parameters. For energy consumption problems in the cutting process, the system may recommend checking tool wear, optimizing cutting parameters, etc. This targeted control strategy helps to improve production efficiency and reduce energy consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 This is a schematic diagram of a flow chart of an energy consumption intelligent management system for a smart factory according to the present invention; Figure 2 This is a schematic diagram of the steps of an intelligent energy consumption management method for a smart factory according to the present invention. DETAILED DESCRIPTION

[0028] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0029] Example 1 See also Figure 1 , the present invention provides an intelligent energy consumption management system for smart factories, comprising a first monitoring module, a second monitoring module, a digital energy consumption model module, an evaluation module and a control module; The first monitoring module is used to install a camera and a first integrated sensor in the semiconductor cleaning area to monitor pollution data on the surface of the equipment, water resource cleaning data and current real-time environmental data in real time to establish a first data set; The second monitoring module is used to install a second integrated sensor in the semiconductor cutting area to collect cutting data, water resource and energy consumption data, waste data and current real-time environmental data in the cutting area in real time to establish a second data set; The digital energy consumption model module is used to establish a three-dimensional model based on the panoramic cloud of the smart factory, and integrate the digital model to establish a digital energy consumption model, analyze and calculate the first data set and the second data set to obtain: cleaning pollution coefficient Qxw, cleaning area environmental coefficient Hjx1, real-time cleaning energy consumption coefficient Qxn2, real-time cutting energy consumption coefficient Qgx2 and cutting area environmental coefficient Hjx2; and associate the cleaning pollution coefficient Qxw, the cleaning area environmental coefficient Hjx1, and the real-time cleaning energy consumption coefficient Qxn2 to obtain the first evaluation consumption coefficient PG1; associate the real-time cutting energy consumption coefficient Qgx2 with the cutting area environmental coefficient Hjx2 to obtain the second evaluation consumption coefficient PG2; The evaluation module is used to compare the first evaluation consumption coefficient PG1 with the first threshold value X1 to obtain a first evaluation result, and compare the second evaluation consumption coefficient PG2 with the second threshold value X2 to obtain a second evaluation result; The control module is used to generate a corresponding control strategy according to the first evaluation result and the second evaluation result.

[0030] In this embodiment, the first data set is located in the semiconductor cleaning area, and the pollution data, water resource cleaning data and current real-time environmental data on the surface of the equipment are monitored in real time by installing a camera and a first integrated sensor. This helps to establish the first data set and provide real-time information and environmental information of the cleaning link. The second data set is located in the semiconductor cutting area, and the cutting data, water resource energy consumption data, waste data and current real-time environmental data in the cutting area are collected in real time by the second integrated sensor. The second data set is established to provide detailed information and environmental information of the cutting link. Through the fusion of the three-dimensional model and the digital model based on the panoramic cloud, the system establishes a digital energy consumption model. This helps to more comprehensively understand the energy consumption characteristics of the cleaning and cutting links, and quantify the energy consumption through parameters such as the cleaning pollution coefficient and the environmental coefficient. According to the energy consumption characteristics of different links, the system calculates the correlation coefficients of cleaning and cutting respectively, and compares the consumption coefficients through the evaluation module. This helps to refine management and better understand and deal with the energy consumption differences in different production links. According to the first evaluation and the second evaluation results, the control module generates the corresponding control strategy. This means that the system can intelligently adjust production parameters, equipment operation, etc. to reduce energy consumption, reduce water waste, and find a balance between environmental protection and economic benefits. By carefully dividing and analyzing energy consumption at different stages, we can significantly reduce water waste and reduce environmental burden. This will also help companies achieve more sustainable production.

[0031] Example 2: This example is an explanation of Example 1. Figure 1Specifically, the first data set includes but is not limited to the following data: semiconductor substrate surface contamination particle concentration klnd, semiconductor substrate total area zmj, contamination area wrmj, semiconductor substrate charge adsorption rate xfl, first air particle concentration kq1, first air humidity sd1, first air temperature wd1, VOCs volatile concentration hfwnd, cleaning equipment power sbgl, cleaning liquid flow qxyll, cleaning liquid concentration qxnd, cleaning liquid temperature qwd, water flow slll, wastewater treatment equipment power fsgl and cleaning time qxsj; The semiconductor substrate surface contamination particle concentration klnd is measured and obtained by a laser particle counter; the semiconductor substrate total area zmj and the contaminated area wrmj are measured and obtained by an image sensor; the semiconductor substrate charge adsorption rate xfl is measured and obtained by a charge sensor; the first air particle concentration kq1 is measured and obtained by a particle concentration sensor; the first air humidity sd1 is measured and obtained by a humidity sensor; the first air temperature wd1 is measured and obtained by a temperature sensor; the VOCs volatile concentration hfwnd is measured and obtained by a VOCs concentration sensor; the cleaning equipment power sbgl is measured by a power sensor to obtain the power consumption of the cleaning equipment; the cleaning liquid flow qxyll is measured and obtained by a flowmeter; the cleaning liquid concentration qxnd is measured and obtained by a concentration sensor; the cleaning liquid temperature qwd is measured by a temperature sensor to obtain the cleaning liquid temperature; the water flow slll is measured and obtained by a flowmeter; the wastewater treatment equipment power fsgl is measured by a power sensor to obtain the power consumption of the wastewater treatment equipment; the cleaning time qxsj is measured and obtained by a time sensor.

[0032] In this embodiment, the concentration of contaminated particles on the surface of the semiconductor substrate klnd: measured by a laser particle counter, which helps to understand the contamination of the substrate surface before and after cleaning, and provides real-time data for the evaluation of the cleaning effect; the total area of ​​the semiconductor substrate and the contaminated area zmj, wrmj: measured by an image sensor, provide geometric information of the cleaning area, help the system calculate the efficiency of cleaning and the area of ​​wastewater generation. The charge adsorption rate of the semiconductor substrate xfl: measured by a charge sensor, the charge state of the substrate surface can be understood, and data support is provided for the consideration of electrostatic effects during the cleaning process. The first air particle concentration kq1, the first air humidity sd1 and the first air temperature wd1: these parameters are measured by corresponding sensors, providing air quality, humidity and temperature information of the cleaning environment, which is essential for condition monitoring of the cleaning process. VOCs are volatile organic compounds, and the monitoring of their concentration helps to evaluate the potential impact of volatiles in the cleaning liquid on the environment and take corresponding control measures. Through the measurement of power sensors, real-time power consumption data of the cleaning equipment is provided, which is helpful for energy management and cost control. Parameters such as cleaning liquid flow qxyll, cleaning liquid concentration qxnd and cleaning liquid temperature qwd provide information on the use of cleaning liquid, which helps to control the amount, concentration and temperature of the cleaning liquid and maximize the cleaning effect. Water flow slll: measured by a flow meter, it provides flow information of cleaning liquid and wastewater, helping the system monitor and adjust the utilization efficiency of water resources. Wastewater treatment equipment power fsgl: measured by a power sensor, it provides real-time power consumption data of wastewater treatment equipment, which helps energy management of wastewater treatment. Cleaning time qxsj: measured by a time sensor, it provides the duration of the cleaning process, which helps to calculate energy efficiency and optimize the cleaning process.

[0033] Example 3, this example is explained in Example 1, please refer to Figure 1 Specifically, the second data set includes but is not limited to the following data: cutting equipment power qggl, cutting rate qgsl, real-time cutting temperature qgwd, real-time cleaning liquid usage sssyl, cleaning liquid concentration qxnd, cutting liquid concentration qgynd, cutting liquid recovery amount qgyhs, cutting time qgsc, ventilation wind speed tffs, second air humidity sd2, second air temperature wd2, second air particle concentration kq2 and cutting liquid flow rate qgyls; The cutting equipment power qggl is obtained by collecting the power consumption of the cutting equipment through an electric power sensor; the cutting rate qgsl is obtained by measuring and obtaining through a speed sensor or an encoder; the real-time cutting temperature qgwd is obtained by measuring the tool surface temperature through a temperature sensor; the real-time usage of the cleaning fluid sssyl is obtained by measuring and obtaining through a flow meter; the cleaning fluid concentration qxnd and the cutting fluid concentration qgynd are obtained by measuring and obtaining through a concentration sensor; the cutting fluid recovery amount qgyhs is obtained by collecting and obtaining through a flow meter; the cutting time qgsc is obtained by measuring and obtaining through a time sensor; the ventilation wind speed tffs is obtained by measuring and obtaining through a wind speed sensor; the second air humidity sd2 is obtained by measuring and obtaining through a temperature sensor; the second air temperature wd2 is obtained by measuring and obtaining through a humidity sensor; the second air particle concentration kq2 is obtained by measuring and obtaining through a particle concentration sensor; the cutting fluid flow rate qgyls is obtained by measuring and obtaining through a flow rate sensor.

[0034] In this embodiment, the power of the cutting equipment qggl: measured by the power sensor, provides real-time power consumption data of the cutting equipment, which is helpful for energy management and cost control. Cutting rate qgsl: measured by the speed sensor or encoder, provides key data for the evaluation of cutting efficiency, helps to optimize the cutting process and improve production efficiency. Real-time cutting temperature qgwd: measured by the temperature sensor, provides real-time data of the surface temperature of the tool, helps to monitor the tool status, avoid overheating damage, and improve cutting quality and life. Real-time usage of cleaning fluid sssyl: measured by the flow meter, provides real-time usage of the cleaning fluid, helps to control the usage of the cleaning fluid and maximize the cleaning effect. Cleaning fluid concentration qxnd and cutting fluid concentration qgynd: measured by the concentration sensor, provides concentration data of the cleaning fluid and cutting fluid, helps to adjust the liquid ratio and optimize the cleaning and cutting effects. Cutting fluid recovery volume qgyhs: collected by the flow meter, provides cutting fluid recovery volume data, which is helpful for environmental protection and resource conservation. Cutting time qgsc: measured by the time sensor, provides time data of the cutting process, which is helpful to calculate energy efficiency and optimize the cutting process. Ventilation wind speed tffs: measured by wind speed sensor, provides wind speed data of ventilation system, helps to ensure ventilation effect of cutting area and improve safety of working environment. Second air humidity sd2 and second air temperature wd2: measured by humidity sensor and temperature sensor, provides humidity and temperature information of cutting environment, helps to create suitable working environment and improve equipment performance. Second air particle concentration kq2: measured by particle concentration sensor, provides air quality information of cutting environment, helps to monitor cleanliness of working environment. Cutting fluid flow rate qgyls: measured by flow rate sensor, provides flow rate data of cutting fluid, helps to control liquid flow rate and ensure uniform supply of cutting fluid.

[0035] Example 4: This example is an explanation of Example 1. Figure 1 Specifically, the digital energy consumption model module includes a first calculation unit and a second calculation unit; the first calculation unit is used to input the first data set through the digital energy consumption model to analyze and calculate: the cleaning pollution coefficient Qxw, the cleaning area environment coefficient Hjx1 and the real-time cleaning energy consumption coefficient Qxn2; The cleaning pollution coefficient Qxw is obtained by extracting the semiconductor substrate surface pollution particle concentration klnd, the semiconductor substrate total area zmj, the pollution area wrmj and the semiconductor substrate charge adsorption rate xfl in the first data set; the substrate charge adsorption rate xfl is calculated by the following formula:

[0036] In the formula, Expressed as the surface charge density of the semiconductor substrate; It represents the total charge density, which indicates the total amount of charge on the substrate surface, including adsorbed particles, impurities and defects; The semiconductor substrate surface contamination particle concentration klnd, the semiconductor substrate total area zmj, the contamination area wrmj and the semiconductor substrate charge adsorption rate xfl are dimensionlessly processed to generate the cleaning contamination coefficient Qxw through the following formula:

[0037] in, , , ,and , w1, w2, w3 are weight values, and their specific values ​​are adjusted and set by the user is the first constant correction coefficient; The cleaning area environmental coefficient Hjx1 is obtained by extracting the first air particle concentration kq1, the first air humidity sd1, the first air temperature wd1 and the VOCs volatile matter concentration hfwnd in the first data set; after dimensionless processing, the cleaning area environmental coefficient Hjx1 is generated by the following formula:

[0038] In the formula, , , ,and , w1, w2, w3 are weight values, and their specific values ​​are adjusted and set by the user is the second constant correction coefficient; Indicates logarithmic operation with base 2; The real-time cleaning energy consumption coefficient Qxn2 is obtained by extracting the cleaning equipment power sbgl, cleaning liquid flow qxyll, cleaning liquid concentration qxnd, cleaning liquid temperature qwd, water flow slll, wastewater treatment equipment power fsgl and cleaning time qxsj in the first data set; after dimensionless processing, the real-time cleaning consumption coefficient Qxn2 is generated by the following formula:

[0039] Wherein, d, s, w, p and j represent the preset proportional coefficients of water flow slll, cleaning equipment power sbgl, cleaning liquid flow qxyll, cleaning liquid concentration qxnd and cleaning liquid temperature qwd respectively, z represents the preset proportional coefficient of the sum of wastewater treatment equipment power fsgl and cleaning time qxsj; 0.35≤d≤0.45, 0.05≤s≤0.10, 0.07≤w≤0.16, 0.05≤p≤0.10, 0.02≤j≤0.08, 0.04≤z≤0.11, and 0.58≤d+s+w+p+j+z≤1.0, is the third constant correction coefficient.

[0040] In this embodiment, the cleaning pollution coefficient Qxw provides a quantitative assessment of pollutants in the cleaning process, so that the system can better understand the pollution situation in the cleaning process. Through weight adjustment, it can flexibly adapt to the needs of different users or environments, improving the versatility and adaptability of the model; the cleaning area environmental coefficient Hjx1 provides a comprehensive assessment of the cleaning area environment, which helps the system to better understand the working conditions of the cleaning process; the introduction of logarithmic operations can effectively handle the nonlinear relationship between environmental factors and improve the accuracy of the model. The real-time cleaning energy consumption coefficient Qxn2 provides a real-time energy consumption assessment of the cleaning process, which helps the system to manage energy and optimize efficiency; the introduction of preset proportional coefficients can adjust parameters according to actual conditions, increasing the flexibility and adaptability of the model. The comprehensive calculation and processing of these coefficients provide scientific and accurate support for the energy consumption management of smart factories, and help achieve the goals of energy conservation, emission reduction and efficient use of resources.

[0041] Example 5: This example is explained in Example 1. Figure 1 Specifically, the second calculation unit is used to input the second data set through the digital energy consumption model to analyze and calculate to obtain: real-time cutting energy consumption coefficient Qgx2 and cutting area environment coefficient Hjx2; The real-time cutting energy consumption coefficient Qgx2 is obtained by extracting the cutting equipment power qggl, cutting rate qgsl, real-time cutting temperature qgwd, real-time cleaning liquid usage sssyl, cleaning liquid concentration qxnd, cutting liquid concentration qgynd, cutting liquid recovery amount qgyhs and cutting time qgsc in the second data set; after dimensionless processing, the real-time cutting energy consumption coefficient Qgx2 is generated by the following formula:

[0042] Wherein, x, c, v, b, m and o represent the preset proportional coefficients of the real-time usage of cleaning fluid sssyl, the power of cutting equipment qggl, the cutting rate qgsl, the real-time cutting temperature qgwd, the recovery amount of cutting fluid qgyhs and the cutting time qgsc, respectively; n represents the preset proportional coefficient of the sum of the cleaning fluid concentration qxnd and the cutting fluid concentration qgynd; 0.25≤x≤0.35, 0.06≤c≤0.10, 0.08≤v≤0.12, 0.05≤b≤0.10, 0.07≤n≤0.13, 0.09≤m≤0.20, and 0.60≤x+c+v+b+n+m≤1.0, is the fourth constant correction coefficient; The cutting area environmental coefficient Hjx2 is obtained by extracting the ventilation wind speed tffs, the second air humidity sd2, the second air temperature wd2, the second air particle concentration kq2 and the cutting fluid flow rate qgyls in the second data set; after dimensionless processing, the cutting area environmental coefficient Hjx2 is generated by the following formula:

[0043] In the formula, , , , ,and , w7, w8, w9 and w10 are weight values, and their specific values ​​are adjusted and set by the user is the fifth constant correction coefficient; Represents the base-2 logarithm operation.

[0044] In this embodiment, the real-time cutting energy consumption coefficient Qgx2 provides a real-time energy consumption assessment of the cutting process, which helps the system to perform real-time energy management and efficiency optimization. The cutting area environment coefficient Hjx2 provides a comprehensive assessment of the cutting area environment, allowing the system to better understand the working conditions of the cutting link; by obtaining these two coefficients, the digital energy consumption model can comprehensively analyze the energy consumption characteristics of the cutting link and provide a more accurate and personalized energy consumption management strategy for the smart factory. This detailed link division and analysis helps to optimize the production process and improve energy efficiency.

[0045] Example 6: This example is explained in Example 1. Figure 1 Specifically, the digital energy consumption model module also includes a first association unit and a second association unit; The first association unit is used to associate the cleaning pollution coefficient Qxw, the cleaning area environment coefficient Hjx1, and the real-time cleaning energy consumption coefficient Qxn2, and obtain the first evaluation consumption coefficient PG1 through the following association formula:

[0046] In the formula, , ,and , is the weight, It is a logarithm operation with 2 natural numbers as base; The second association unit is used to associate the real-time cutting energy consumption coefficient Qgx2 with the cutting area environment coefficient Hjx2, and obtain the second evaluation consumption coefficient PG2 through the following association formula:

[0047] In the formula, , ,and , is the weight, It is a logarithm operation with base 2 as natural number.

[0048] In this embodiment, the first evaluation consumption coefficient PG1 provides a comprehensive energy consumption evaluation of the cleaning process. The weight adjustment and logarithmic operation enable the model to better reflect the influence of various factors. The first evaluation consumption coefficient PG1 provides an overall reference for the cleaning process for subsequent energy consumption management. The second evaluation coefficient PG2 provides a comprehensive energy consumption evaluation of the cutting process. The weight adjustment and logarithmic operation make the model more flexible and more adaptable to different working conditions. The second evaluation coefficient PG2 provides a key evaluation indicator for the overall energy consumption of the cutting process.

[0049] Example 7, this example is explained in Example 1, please refer to Figure 1 ,Specifically, the evaluation module includes a first evaluation unit; The first evaluation unit is used to use the evaluation module to compare the first evaluation consumption coefficient PG1 with the first threshold value X1 to obtain a first evaluation result, including: When the first evaluation consumption coefficient PG1 is greater than the first threshold value X1*120%, it means that the energy consumption exceeds the threshold value significantly, and a first energy consumption unqualified result is generated; When the first evaluation consumption coefficient PG1> the first threshold value X1 and does not reach the first threshold value X1*120%, it means that the energy consumption fluctuation exceeds the threshold value, and a second energy consumption unqualified result is generated; When the first evaluation consumption coefficient PG1 = the first threshold value X1, it indicates that the energy consumption is normal and is in a qualified state, and a first energy consumption qualified result is generated; When the first evaluation consumption coefficient PG1 is less than the first threshold value X1, it indicates that the energy consumption is low, and a second energy consumption qualified result is generated.

[0050] In this embodiment, the first evaluation unit is used to compare the first evaluation consumption coefficient PG1 with the preset first threshold value X1, so as to determine the state of energy consumption in the cleaning area. The first evaluation result provides a detailed determination of the energy consumption state and classifies different energy consumption situations, so that managers can have a clearer understanding of the energy consumption status of the factory. Through the setting of thresholds and the judgment logic, abnormal energy consumption can be discovered in a timely manner, providing guidance for further optimization and adjustment. The classification judgment results enable factory managers to take corresponding measures in a targeted manner to ensure that energy consumption is within a controllable range.

[0051] Example 8: This example is explained in Example 1. Figure 1 ,Specifically, the evaluation module includes a second evaluation unit; The second evaluation unit is used to compare the second evaluation consumption coefficient PG2 with the second threshold value X2 to obtain a second evaluation result, including: When the second evaluation consumption coefficient PG2 is greater than the second threshold value X2*120%, it indicates that the energy consumption exceeds the threshold value significantly, and a third energy consumption unqualified result is generated; When the second evaluation consumption coefficient PG2> the second threshold value X2 and does not reach the second threshold value X2*120%, it means that the energy consumption fluctuation exceeds the threshold value, and a fourth energy consumption unqualified result is generated; When the second evaluation consumption coefficient PG2 = the second threshold value X2, it indicates that the energy consumption is normal and is in a qualified state, and a third energy consumption qualified result is generated; When the second evaluation consumption coefficient PG2 is less than the second threshold value X2, it indicates that the energy consumption is low, and a fourth energy consumption qualified result is generated.

[0052] In this embodiment, the function of the second evaluation unit is to compare the second evaluation consumption coefficient PG2 with the preset second threshold value X2 to determine the energy consumption status of the cutting area; the second evaluation result provides a detailed energy consumption status judgment and classifies different energy consumption situations, so that managers can understand the energy consumption status of the cutting area of ​​the factory more clearly.

[0053] Example 9: This example is an explanation of Example 8. Figure 1,Specifically, the control module includes an alarm unit, a visualization unit and a control unit; The alarm unit is used to generate a first warning information, a second warning information, a third warning information and a fourth warning information according to the first energy consumption unqualified result, the second energy consumption unqualified result, the third energy consumption unqualified result and the fourth energy consumption unqualified result, and to make the first warning information, the second warning information, the third warning information and the fourth warning information be marked prominently on the visualization screen through the visualization unit; to perform first priority intervention processing on the first warning information and the third warning information; and to perform second priority access processing on the second warning information and the fourth warning information; The control unit generates a first control strategy according to the first energy consumption unqualified result, and the first control strategy includes: emergency intervention, stopping or slowing down the cleaning process, checking the equipment status, adjusting the process parameters, purifying the indoor air, controlling the indoor temperature between 10-20°C, controlling the humidity between 40%-60%, and controlling the energy consumption to be equal to the first threshold value X1; A second control strategy is generated according to the second energy consumption failure result, wherein the second control strategy includes: performing cleaning equipment inspection and maintenance, increasing the cleaning liquid concentration to 3-5%, increasing the cleaning time by 20%, and increasing the wastewater treatment power by 10%, and controlling the energy consumption until it is equal to the first threshold value X1; A third control strategy is generated according to the third energy consumption unqualified result, and the third control strategy includes: emergency intervention of the cutting equipment to stop or slow down the cutting process, optimize the cutting rate, cutting fluid flow rate and cutting fluid concentration parameters, check the cutting equipment tool wear, and replace new tools when necessary to control friction resistance, control the concentration and temperature of the coolant and the cleaning fluid; and increase the ventilation speed to 0.3m / s to 0.5m / s, purify the indoor air, control the indoor temperature between 10-20°C, control the humidity between 40%-60%, and control the energy consumption to be equal to the second threshold value X2; A fourth control strategy is generated according to the fourth energy consumption unqualified result, and the fourth control strategy includes: upgrading the cutting equipment, a real-time cutting fluid recycling system, increasing the filtering power processing of the used cutting fluid, and recycling it for secondary use, adjusting the cutting parameters in real time, and increasing the ventilation speed to 0.1m / s to 0.3m / s, and controlling the energy consumption to be equal to the second threshold value X2; Based on the first energy consumption qualified result, the second energy consumption qualified result, the third energy consumption qualified result and the fourth energy consumption qualified result, continuous monitoring and regular inspections are carried out.

[0054] In this embodiment, corresponding warning information is generated according to the first energy consumption unqualified result, the second energy consumption unqualified result, the third energy consumption unqualified result and the fourth energy consumption unqualified result.

[0055] The visual unit prominently marks the warning information on the screen so that abnormal situations can be quickly noticed.

[0056] Carry out priority intervention to ensure timely measures are taken for serious energy consumption issues.

[0057] Generate corresponding control strategies based on different energy consumption failure results. The clear setting of each control strategy provides operators with specific guidance and operation steps for easy implementation. Continuous monitoring and regular inspections help to detect potential problems in a timely manner and improve the stability and reliability of the system.

[0058] Example 10, please refer to Figure 2 , an intelligent energy consumption management method for a smart factory, comprising the following steps, Step 1, data monitoring: Install a camera and a first integrated sensor in the semiconductor cleaning area to monitor the pollution data on the surface of the equipment, the water resource cleaning data and the current real-time environmental data to form a first data set; install a second integrated sensor in the semiconductor cutting area to collect cutting data, water resource energy consumption data, waste data and the current real-time environmental data in real time to form a second data set; Step 2, establishment of digital energy consumption model: establish a three-dimensional model through panoramic cloud, integrate the digital model, and construct a digital energy consumption model; use the digital energy consumption model to analyze and calculate the first data set and the second data set to obtain the cleaning pollution coefficient Qxw, the cleaning area environmental coefficient Hjx1, the real-time cleaning energy consumption coefficient Qxn2, the real-time cutting energy consumption coefficient Qgx2 and the cutting area environmental coefficient Hjx2; and associate the cleaning pollution coefficient Qxw, the cleaning area environmental coefficient Hjx1, and the real-time cleaning energy consumption coefficient Qxn2 to obtain the first evaluation consumption coefficient PG1; associate the real-time cutting energy consumption coefficient Qgx2 with the cutting area environmental coefficient Hjx2 to obtain the second evaluation consumption coefficient PG2; Step 3, comparative evaluation: compare the first evaluation consumption coefficient PG1 with the first threshold value X1 to obtain a first evaluation result, and compare the second evaluation consumption coefficient PG2 with the second threshold value X2 to obtain a second evaluation result; Step 4: Generate control strategies: Generate corresponding control strategies and execute different control strategies based on the first evaluation results and the second evaluation results.

[0059] The method of this embodiment can achieve real-time feedback on the production process through real-time monitoring and execution of control strategies.

[0060] The generation and implementation of continuous optimization strategies ensure that energy consumption issues are resolved in a timely manner and provide support for the sustainable development of the factory. In smart factories, real-time monitoring, accurate evaluation, targeted control and continuous optimization of energy consumption are achieved, thereby improving production efficiency, reducing energy waste, and significantly promoting environmental friendliness and economic feasibility.

[0061] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent energy consumption management system for smart factories, characterized by: It includes a first monitoring module, a second monitoring module, a digital energy consumption model module, an evaluation module and a control module; The first monitoring module is used to install a camera and a first integrated sensor in the semiconductor cleaning area to monitor pollution data on the surface of the equipment, water resource cleaning data and current real-time environmental data in real time to establish a first data set; The second monitoring module is used to install a second integrated sensor in the semiconductor cutting area to collect cutting data, water resource and energy consumption data, waste data and current real-time environmental data in the cutting area in real time to establish a second data set; The digital energy consumption model module is used to establish a three-dimensional model based on the panoramic cloud of the smart factory, and integrate the digital model to establish a digital energy consumption model, analyze and calculate the first data set and the second data set to obtain: cleaning pollution coefficient Qxw, cleaning area environmental coefficient Hjx1, real-time cleaning energy consumption coefficient Qxn2, real-time cutting energy consumption coefficient Qgx2 and cutting area environmental coefficient Hjx2; and associate the cleaning pollution coefficient Qxw, the cleaning area environmental coefficient Hjx1, and the real-time cleaning energy consumption coefficient Qxn2 to obtain the first evaluation consumption coefficient PG1; associate the real-time cutting energy consumption coefficient Qgx2 with the cutting area environmental coefficient Hjx2 to obtain the second evaluation consumption coefficient PG2; The evaluation module is used to compare the first evaluation consumption coefficient PG1 with the first threshold value X1 to obtain a first evaluation result, and compare the second evaluation consumption coefficient PG2 with the second threshold value X2 to obtain a second evaluation result; The control module is used to generate a corresponding control strategy according to the first evaluation result and the second evaluation result.

2. According to claim 1, the energy consumption intelligent management system for smart factories is characterized by: The first data set includes but is not limited to the following data: semiconductor substrate surface contamination particle concentration klnd, semiconductor substrate total area zmj, contamination area wrmj, semiconductor substrate charge adsorption rate xfl, first air particle concentration kq1, first air humidity sd1, first air temperature wd1, VOCs volatile concentration hfwnd, cleaning equipment power sbgl, cleaning liquid flow qxyll, cleaning liquid concentration qxnd, cleaning liquid temperature qwd, water flow slll, wastewater treatment equipment power fsgl and cleaning time qxsj; The semiconductor substrate surface contamination particle concentration klnd is measured and obtained by a laser particle counter; the semiconductor substrate total area zmj and the contaminated area wrmj are measured and obtained by an image sensor; the semiconductor substrate charge adsorption rate xfl is measured and obtained by a charge sensor; the first air particle concentration kq1 is measured and obtained by a particle concentration sensor; the first air humidity sd1 is measured and obtained by a humidity sensor; the first air temperature wd1 is measured and obtained by a temperature sensor; the VOCs volatile concentration hfwnd is measured and obtained by a VOCs concentration sensor; the cleaning equipment power sbgl is measured by a power sensor to obtain the power consumption of the cleaning equipment; the cleaning liquid flow qxyll is measured and obtained by a flowmeter; the cleaning liquid concentration qxnd is measured and obtained by a concentration sensor; the cleaning liquid temperature qwd is measured by a temperature sensor to obtain the cleaning liquid temperature; the water flow slll is measured and obtained by a flowmeter; the wastewater treatment equipment power fsgl is measured by a power sensor to obtain the power consumption of the wastewater treatment equipment; the cleaning time qxsj is measured and obtained by a time sensor.

3. According to claim 1, the energy consumption intelligent management system for smart factories is characterized by: The second data set includes but is not limited to the following data: cutting equipment power qggl, cutting rate qgsl, real-time cutting temperature qgwd, real-time cleaning liquid usage sssyl, cleaning liquid concentration qxnd, cutting liquid concentration qgynd, cutting liquid recovery amount qgyhs, cutting time qgsc, ventilation wind speed tffs, second air humidity sd2, second air temperature wd2, second air particle concentration kq2 and cutting liquid flow rate qgyls; The cutting equipment power qggl is obtained by collecting the power consumption of the cutting equipment through an electric power sensor; the cutting rate qgsl is obtained by measuring and obtaining through a speed sensor or an encoder; the real-time cutting temperature qgwd is obtained by measuring the tool surface temperature through a temperature sensor; the real-time usage of the cleaning fluid sssyl is obtained by measuring and obtaining through a flow meter; the cleaning fluid concentration qxnd and the cutting fluid concentration qgynd are obtained by measuring and obtaining through a concentration sensor; the cutting fluid recovery amount qgyhs is obtained by collecting and obtaining through a flow meter; the cutting time qgsc is obtained by measuring and obtaining through a time sensor; the ventilation wind speed tffs is obtained by measuring and obtaining through a wind speed sensor; the second air humidity sd2 is obtained by measuring and obtaining through a temperature sensor; the second air temperature wd2 is obtained by measuring and obtaining through a humidity sensor; the second air particle concentration kq2 is obtained by measuring and obtaining through a particle concentration sensor; the cutting fluid flow rate qgyls is obtained by measuring and obtaining through a flow rate sensor.

4. According to claim 1, the energy consumption intelligent management system for smart factories is characterized by: The digital energy consumption model module includes a first calculation unit and a second calculation unit; the first calculation unit is used to input the first data set through the digital energy consumption model to analyze and calculate: the cleaning pollution coefficient Qxw, the cleaning area environment coefficient Hjx1 and the real-time cleaning energy consumption coefficient Qxn2; The cleaning pollution coefficient Qxw is obtained by extracting the semiconductor substrate surface pollution particle concentration klnd, the semiconductor substrate total area zmj, the pollution area wrmj and the semiconductor substrate charge adsorption rate xfl in the first data set; the substrate charge adsorption rate xfl is calculated by the following formula: In the formula, Expressed as the surface charge density of the semiconductor substrate; It represents the total charge density, which indicates the total amount of charge on the substrate surface, including adsorbed particles, impurities and defects; The semiconductor substrate surface contamination particle concentration klnd, the semiconductor substrate total area zmj, the contamination area wrmj and the semiconductor substrate charge adsorption rate xfl are dimensionlessly processed to generate the cleaning contamination coefficient Qxw through the following formula: in, , , ,and , w1, w2, w3 are weight values, and their specific values ​​are adjusted and set by the user is the first constant correction coefficient; The cleaning area environmental coefficient Hjx1 is obtained by extracting the first air particle concentration kq1, the first air humidity sd1, the first air temperature wd1 and the VOCs volatile matter concentration hfwnd in the first data set; after dimensionless processing, the cleaning area environmental coefficient Hjx1 is generated by the following formula: In the formula, , , ,and , w1, w2, w3 are weight values, and their specific values ​​are adjusted and set by the user is the second constant correction coefficient; Indicates logarithmic operation with base 2; The real-time cleaning energy consumption coefficient Qxn2 is obtained by extracting the cleaning equipment power sbgl, cleaning liquid flow qxyll, cleaning liquid concentration qxnd, cleaning liquid temperature qwd, water flow slll, wastewater treatment equipment power fsgl and cleaning time qxsj in the first data set; after dimensionless processing, the real-time cleaning consumption coefficient Qxn2 is generated by the following formula: Wherein, d, s, w, p and j represent the preset proportional coefficients of the water flow rate slll, the cleaning equipment power sbgl, the cleaning liquid flow rate qxyll, the cleaning liquid concentration qxnd and the cleaning liquid temperature qwd, respectively, and z represents the preset proportional coefficient of the sum of the wastewater treatment equipment power fsgl and the cleaning time qxsj; 0.35≤d≤0.45, 0.05≤s≤0.10, 0.07≤w≤0.16, 0.05≤p≤0.10, 0.02≤j≤0.08, 0.04≤z≤0.11, and 0.58≤d+s+w+p+j+z≤1.0, is the third constant correction coefficient.

5. According to claim 4, the energy consumption intelligent management system for smart factories is characterized by: The second calculation unit is used to input the second data set through the digital energy consumption model to analyze and calculate to obtain: the real-time cutting energy consumption coefficient Qgx2 and the cutting area environment coefficient Hjx2; The real-time cutting energy consumption coefficient Qgx2 is obtained by extracting the cutting equipment power qggl, cutting rate qgsl, real-time cutting temperature qgwd, real-time cleaning liquid usage sssyl, cleaning liquid concentration qxnd, cutting liquid concentration qgynd, cutting liquid recovery amount qgyhs and cutting time qgsc in the second data set; after dimensionless processing, the real-time cutting energy consumption coefficient Qgx2 is generated by the following formula: Wherein, x, c, v, b, m and o represent the preset proportional coefficients of the real-time usage of cleaning fluid sssyl, the power of cutting equipment qggl, the cutting rate qgsl, the real-time cutting temperature qgwd, the recovery amount of cutting fluid qgyhs and the cutting time qgsc, respectively; n represents the preset proportional coefficient of the sum of the cleaning fluid concentration qxnd and the cutting fluid concentration qgynd; 0.25≤x≤0.35, 0.06≤c≤0.10, 0.08≤v≤0.12, 0.05≤b≤0.10, 0.07≤n≤0.13, 0.09≤m≤0.20, and 0.60≤x+c+v+b+n+m≤1.0, is the fourth constant correction coefficient; The cutting area environmental coefficient Hjx2 is obtained by extracting the ventilation wind speed tffs, the second air humidity sd2, the second air temperature wd2, the second air particle concentration kq2 and the cutting fluid flow rate qgyls in the second data set; after dimensionless processing, the cutting area environmental coefficient Hjx2 is generated by the following formula: In the formula, , , , ,and , w7, w8, w9 and w10 are weight values, and their specific values ​​are adjusted and set by the user is the fifth constant correction coefficient; Represents the base-2 logarithm operation.

6. According to claim 1, the energy consumption intelligent management system for smart factories is characterized by: The digital energy consumption model module also includes a first association unit and a second association unit; The first association unit is used to associate the cleaning pollution coefficient Qxw, the cleaning area environment coefficient Hjx1, and the real-time cleaning energy consumption coefficient Qxn2, and obtain the first evaluation consumption coefficient PG1 through the following association formula: In the formula, , ,and , is the weight, It is a logarithm operation with 2 natural numbers as base; The second association unit is used to associate the real-time cutting energy consumption coefficient Qgx2 with the cutting area environment coefficient Hjx2, and obtain the second evaluation consumption coefficient PG2 through the following association formula: In the formula, , ,and , is the weight, It is a logarithm operation with base 2 as natural number.

7. The energy consumption intelligent management system for smart factories according to claim 1 is characterized by: The evaluation module includes a first evaluation unit; The first evaluation unit is used to use the evaluation module to compare the first evaluation consumption coefficient PG1 with the first threshold value X1 to obtain a first evaluation result, including: When the first evaluation consumption coefficient PG1 is greater than the first threshold value X1*120%, it means that the energy consumption exceeds the threshold value significantly, and a first energy consumption unqualified result is generated; When the first evaluation consumption coefficient PG1> the first threshold value X1 and does not reach the first threshold value X1*120%, it means that the energy consumption fluctuation exceeds the threshold value, and a second energy consumption unqualified result is generated; When the first evaluation consumption coefficient PG1 = the first threshold value X1, it indicates that the energy consumption is normal and is in a qualified state, and a first energy consumption qualified result is generated; When the first evaluation consumption coefficient PG1 is less than the first threshold value X1, it indicates that the energy consumption is low, and a second energy consumption qualified result is generated.

8. The energy consumption intelligent management system for smart factories according to claim 1 is characterized by: The evaluation module includes a second evaluation unit; The second evaluation unit is used to compare the second evaluation consumption coefficient PG2 with the second threshold value X2 to obtain a second evaluation result, including: When the second evaluation consumption coefficient PG2 is greater than the second threshold value X2*120%, it indicates that the energy consumption exceeds the threshold value significantly, and a third energy consumption unqualified result is generated; When the second evaluation consumption coefficient PG2> the second threshold value X2 and does not reach the second threshold value X2*120%, it means that the energy consumption fluctuation exceeds the threshold value, and a fourth energy consumption unqualified result is generated; When the second evaluation consumption coefficient PG2 = the second threshold value X2, it indicates that the energy consumption is normal and is in a qualified state, and a third energy consumption qualified result is generated; When the second evaluation consumption coefficient PG2 is less than the second threshold value X2, it indicates that the energy consumption is low, and a fourth energy consumption qualified result is generated.

9. The energy consumption intelligent management system for smart factories according to claim 1 is characterized by: The control module includes an alarm unit, a visualization unit and a control unit; The alarm unit is used to generate a first warning message, a second warning message, a third warning message and a fourth warning message according to the first energy consumption unqualified result, the second energy consumption unqualified result, the third energy consumption unqualified result and the fourth energy consumption unqualified result, and to make the first warning message, the second warning message, the third warning message and the fourth warning message prominently marked on the visualization screen through the visualization unit; Performing first priority intervention processing on the first warning information and the third warning information; Performing second priority access processing on the second warning information and the fourth warning information; The control unit generates a first control strategy according to the first energy consumption unqualified result, and the first control strategy includes: emergency intervention, stopping or slowing down the cleaning process, checking the equipment status, adjusting the process parameters, purifying the indoor air, controlling the indoor temperature between 10-20°C, controlling the humidity between 40%-60%, and controlling the energy consumption to be equal to the first threshold value X1; A second control strategy is generated according to the second energy consumption failure result, wherein the second control strategy includes: performing cleaning equipment inspection and maintenance, increasing the cleaning liquid concentration to 3-5%, increasing the cleaning time by 20%, and increasing the wastewater treatment power by 10%, and controlling the energy consumption until it is equal to the first threshold value X1; A third control strategy is generated according to the third energy consumption unqualified result, and the third control strategy includes: emergency intervention of the cutting equipment to stop or slow down the cutting process, optimize the cutting rate, cutting fluid flow rate and cutting fluid concentration parameters, check the cutting equipment tool wear, and replace new tools when necessary to control friction resistance, control the concentration and temperature of the coolant and the cleaning fluid; and increase the ventilation speed to 0.3m / s to 0.5m / s, purify the indoor air, control the indoor temperature between 10-20°C, control the humidity between 40%-60%, and control the energy consumption to be equal to the second threshold value X2; A fourth control strategy is generated according to the fourth energy consumption unqualified result, and the fourth control strategy includes: upgrading the cutting equipment, a real-time cutting fluid recycling system, increasing the filtering power processing of the used cutting fluid, and recycling it for secondary use, adjusting the cutting parameters in real time, and increasing the ventilation speed to 0.1m / s to 0.3m / s, and controlling the energy consumption to be equal to the second threshold value X2; Based on the first energy consumption qualified result, the second energy consumption qualified result, the third energy consumption qualified result and the fourth energy consumption qualified result, continuous monitoring and regular inspections are carried out.

10. An intelligent energy consumption management method for a smart factory, comprising the intelligent energy consumption management system for a smart factory as claimed in any one of claims 1 to 9, characterized in that: The following steps are included: Step 1, data monitoring: Install a camera and a first integrated sensor in the semiconductor cleaning area to monitor the pollution data on the surface of the equipment, the water resource cleaning data and the current real-time environmental data to form a first data set; install a second integrated sensor in the semiconductor cutting area to collect cutting data, water resource energy consumption data, waste data and the current real-time environmental data in real time to form a second data set; Step 2, establishment of digital energy consumption model: establish a three-dimensional model through panoramic cloud, integrate the digital model, and construct a digital energy consumption model; use the digital energy consumption model to analyze and calculate the first data set and the second data set to obtain the cleaning pollution coefficient Qxw, the cleaning area environmental coefficient Hjx1, the real-time cleaning energy consumption coefficient Qxn2, the real-time cutting energy consumption coefficient Qgx2 and the cutting area environmental coefficient Hjx2; and associate the cleaning pollution coefficient Qxw, the cleaning area environmental coefficient Hjx1, and the real-time cleaning energy consumption coefficient Qxn2 to obtain the first evaluation consumption coefficient PG1; associate the real-time cutting energy consumption coefficient Qgx2 with the cutting area environmental coefficient Hjx2 to obtain the second evaluation consumption coefficient PG2; Step 3, comparative evaluation: compare the first evaluation consumption coefficient PG1 with the first threshold value X1 to obtain a first evaluation result, and compare the second evaluation consumption coefficient PG2 with the second threshold value X2 to obtain a second evaluation result; Step 4: Generate control strategies: Generate corresponding control strategies and execute different control strategies based on the first evaluation results and the second evaluation results.

Images