Green factory energy efficiency dynamic regulation and control model

Abstract

The invention discloses a green factory energy efficiency dynamic regulation and control model, and relates to the technical field of factory energy efficiency dynamic regulation and control, and the model comprises the following steps: S1, sensor layout and data collection; s2, production line scheduling; s3, energy efficiency analysis; and S4, safety regulation and control. According to the green factory energy efficiency dynamic regulation and control model, a virtual mirror image of a physical system is established through an AI large model intelligent algorithm in combination with equipment operation power consumption data, factory temperature and humidity data and productivity order data collected by a sensor, and the model is used for achieving all-around simulation and monitoring of the production process; the AI large-model intelligent algorithm can automatically generate an optimal control strategy on the basis of considering actual operation conditions, and is provided with a feedback mechanism to detect multiple detection work such as production safety, process safety and equipment safety by taking an optimal scheduling plan of production line scheduling as a reference, so that the detection efficiency is improved. The response speed, the adaptive capacity and the safety production of the system can be improved, and the energy utilization efficiency and the environmental performance can be remarkably improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of factory energy efficiency dynamic regulation, in particular to a green factory energy efficiency dynamic regulation model. BACKGROUND

[0002] Green factory is the main body of green manufacturing and the core support unit of green manufacturing system, focusing on the greening of production process. The energy consumption level of green factory is better than the benchmark level. With the emphasis on environmental protection and sustainable development worldwide, green manufacturing has become one of the key directions of modern industrial development. In this context, improving factory energy efficiency, reducing energy consumption and reducing carbon emissions have become important challenges for manufacturing industry.

[0003] At present, most factories use energy efficiency management systems that mainly rely on historical data and empirical rules for decision support. These systems usually include basic energy consumption monitoring and analysis tools, which can provide statistical information about energy use. However, they generally lack real-time and accuracy, making it difficult to achieve fine-tuned regulation of production equipment and process flow. Therefore, we propose a green factory energy efficiency dynamic regulation model. SUMMARY

[0004] In view of the shortcomings of the prior art, the present application provides a green factory energy efficiency dynamic regulation model, which solves the problems raised in the background art.

[0005] To achieve the above purpose, the present application realizes the following technical scheme, a green factory energy efficiency dynamic regulation model, comprising the following steps: S1, sensor layout and data collection The sensors are laid in each area of the factory, and the sensors are used to capture daily energy efficiency data of the factory, including equipment running power consumption data, factory temperature and humidity data, and production order data. The collected data is aggregated through the edge gateway; S2, line scheduling Based on the collected data and the mechanism of the line equipment, an AI large model system is constructed to convert the scheduling problem into a semantic-mathematical dual paradigm, understand natural language instructions and generate scheduling suggestions, while balancing delivery time, cost and other targets. The input is the production order data recorded in S1, which enters the AI large model system, so that it can automatically allocate factory lines and reasonably allocate factory resources; S3, energy efficiency analysis The AI large model system constructed in S2 is adjusted after scheduling the line work and multi-dimensionally evaluates the current scheduling work environment, obtains energy efficiency data and analyzes it, and obtains the optimal scheduling plan of the line scheduling under the condition of safe production; S4, safety regulation A feedback system mechanism is established according to the production line scheduling optimal scheduling plan obtained in the above S3 step, and the production line scheduling optimal scheduling plan is used as a benchmark to detect production safety, process safety, and equipment safety, and the production line scheduling optimal scheduling plan is converted into a standard control signal and executed to each device in the production line; S5, execution and adjustment The production line scheduling optimal scheduling plan obtained in the above S3 step and passed through the multiple safety detection of the above S4 step is implemented and executed, and at the same time, the real-time energy consumption and equipment state after the safety production are detected according to the sensor group laid in the S1 step.

[0006] Further, the sensors laid in the S1 include temperature sensors, humidity sensors, air sensors, voltage and current sensors, and compressor start-stop state sensors, which record data and are registered through a gateway to the system Further, in the S2, the required production capacity order data is input into the AI large model system, which is automatically allocated to the factory line, so that the devices that do not need to participate in production are stopped, the area devices of the required production equipment are concentrated, and the air compressor and air conditioner are started according to the factory temperature and humidity data in the concentrated area to ensure the production of suitable temperature and humidity, and the long line to be produced is standby for reducing energy consumption.

[0007] Further, the data in the multi-dimensional evaluation in the S3 includes the implementation energy consumption of the factory line production equipment and the energy consumption of the started air compressor and air conditioner, and the energy consumption analysis diagram of the key equipment is calculated, wherein min*(a+b labor cost), wherein min is minute, a is energy efficiency cost, and b is labor cost.

[0008] Further, in the S4, the feedback system mechanism detects the production safety, process safety, and equipment safety, and the unqualified and substandard feedback is input back to the S3 step for implementation adjustment, and the manual adjustment is performed at any time.

[0009] Further, in the S5, the real-time energy consumption and equipment state are input into the AI large model system for analysis and comparison, and a curve diagram is output for real-time viewing by the staff, and when the actual deviation is too large, it is used to remind the staff to fine-tune, ensure safe production, and reduce energy consumption.

[0010] The application provides a green factory energy efficiency dynamic regulation model, which has the following beneficial effects: the green factory energy efficiency dynamic regulation model establishes a virtual mirror of the physical system by combining AI large model intelligent algorithm with equipment operation power consumption data, factory temperature and humidity data, and production capacity order data collected by sensors, for realizing all-around simulation and monitoring of the production process; the AI large model intelligent algorithm can automatically generate an optimal control strategy based on consideration of actual operation conditions, and a feedback mechanism is also provided, with the optimal scheduling plan of the production line scheduling as the benchmark, detection of production safety, process safety, and equipment safety, and multiple detection work, which can not only improve the response speed, adaptability, and safety production of the system, but also significantly improve energy utilization efficiency and environmental performance. DETAILED DESCRIPTION

[0011] A green factory energy efficiency dynamic regulation model, comprising the following steps: S1, sensor arrangement and data acquisition Sensors are laid in each area of the factory, and sensors are used to capture daily energy efficiency data of the factory, including equipment operation power consumption data, factory temperature and humidity data, and production capacity order data, and the collected data is aggregated through an edge gateway; S2, production line scheduling An AI large model system is constructed based on the collected data and production line equipment mechanism to convert the scheduling problem into a semantic-mathematical dual norm, understand natural language instructions, and generate scheduling suggestions, while balancing due date, cost, and other targets, wherein the production capacity order data recorded in S1 is input into the AI large model system, so that the factory line can be automatically allocated and the factory resources can be reasonably allocated; S3, energy efficiency analysis The production line work adjusted after scheduling of the AI large model system constructed in S2 is evaluated in multiple dimensions, and energy efficiency data is obtained for analysis, and the optimal scheduling plan of the production line scheduling under safe production is obtained; S4, safety regulation A feedback system mechanism is established, the optimal scheduling plan of the production line scheduling obtained in S3 is taken as the benchmark, multiple detection work such as production safety, process safety, and equipment safety is detected, and the optimal scheduling plan of the production line scheduling is converted into a standard control signal and executed to each device in the production line; S5, execution and adjustment The optimal scheduling plan of the production line scheduling obtained in S3 and passed through multiple safety detection in S4 is implemented, and at the same time, the real-time energy consumption and equipment state after safety production are detected according to the sensor group laid in S1.

[0012] Furthermore, the sensors installed in S1 include temperature sensors, humidity sensors, air sensors, voltage and current sensors, and compressor start / stop status sensors. Data is recorded and registered using these sensors and transmitted to the system via a gateway.

[0013] Furthermore, in S2, the required production capacity order data is input into the AI ​​large model system and automatically allocated to the factory production lines to various regions. Equipment that does not need to participate in production is shut down, while the equipment in the regions that need to produce is concentrated. Based on the temperature and humidity data of the concentrated regions, the air compressors and air conditioners are turned on to ensure suitable temperature and humidity for production. The long production lines waiting to be produced are put on standby to reduce energy consumption.

[0014] Furthermore, the data in the multidimensional assessment in S3 includes the energy consumption of the production line equipment and the energy consumption of the air compressor and air conditioner. Based on this, an energy consumption analysis chart of the key equipment is calculated, where min*(a+b labor cost), where min is minutes, a is energy efficiency cost, and b is labor cost.

[0015] Furthermore, in step S4, if the production safety, process safety, and equipment safety detected by the feedback system mechanism are found to be unqualified or substandard, the feedback will be sent back to step S3 for adjustment, during which manual adjustments can be made at any time.

[0016] Furthermore, in S5, the real-time energy consumption and equipment status are input into the AI ​​large model system for analysis and comparison, and the implementation curve is output for staff to view in real time. When the actual deviation is too large, it is used to remind staff to make fine adjustments, so as to ensure safe production while reducing low energy efficiency.

[0017] In summary, the application of this green factory energy efficiency dynamic control model includes the following specific steps: S1. Sensor Deployment and Data Acquisition: Sensors are deployed in various areas of the factory to capture daily energy efficiency data, including equipment operating power consumption data, factory temperature and humidity data, and production capacity and order data. The collected data is aggregated through an edge gateway. The deployed sensors include temperature sensors, humidity sensors, air sensors, voltage and current sensors, and compressor start / stop status sensors. The data is recorded and registered by the above sensors and transmitted to the system through the gateway. S2, Production Line Scheduling: Based on the collected data and the mechanism of production line equipment, an AI large-scale model system is built to transform the scheduling problem into a semantic-mathematical dual-track paradigm. It understands natural language instructions and generates scheduling suggestions, while balancing objectives such as delivery time and cost. The input is the capacity order data recorded in S1 above, which enters the AI ​​large-scale model system, enabling it to automatically allocate factory lines and rationally allocate factory resources. Specifically, based on the required capacity order data input into the AI ​​large-scale model system, it automatically allocates factory lines to various areas, shuts down equipment that does not participate in production, concentrates equipment in areas that require production, and turns on air compressors and air conditioners based on the temperature and humidity data of the concentrated areas to ensure suitable temperature and humidity for production. Long production lines waiting to be produced are put on standby to reduce energy consumption. S3. Energy Efficiency Analysis: Based on the AI ​​large model system constructed in S2 above, the production line work is adjusted after scheduling, and the current scheduling working environment is evaluated in multiple dimensions to obtain energy efficiency data. This data is then analyzed to obtain the optimal scheduling plan for the production line under safe production conditions. The data in the multi-dimensional evaluation includes the actual energy consumption of the production line equipment and the energy consumption of starting the air compressor and air conditioner. Based on this, the energy consumption analysis diagram of key equipment is calculated, where min*(a+b labor cost), where min is minutes, a is energy efficiency cost, and b is labor cost. S4. Safety Control: Establish a feedback system mechanism. Based on the optimal production line scheduling plan obtained in step S3 above, use the optimal production line scheduling plan as a benchmark to perform multiple checks on production safety, process safety, and equipment safety. Then, convert the optimal production line scheduling plan into standard control signals and execute them on each piece of equipment on the production line. If any production safety, process safety, or equipment safety issues detected by the feedback system mechanism are found to be unqualified or substandard, they will be fed back to step S3 for implementation and adjustment. Manual adjustments can be made at any time during this process. S5. Execution and Adjustment: The optimal production line scheduling plan obtained in step S3 above, after passing multiple safety checks in step S4 above, is executed. At the same time, the real-time energy consumption and equipment status after safe production are detected based on the sensor group deployed in step S1. The real-time energy consumption and equipment status are input into the AI ​​large model system for analysis and comparison, and the implementation curve is output for staff to view in real time. When the actual deviation is too large, it is used to remind staff to make fine adjustments, so as to ensure safe production while reducing low energy efficiency.

Claims

1. A dynamic energy efficiency control model for green factories, characterized in that, Includes the following steps: S1. Sensor Deployment and Data Acquisition Sensors are deployed throughout the factory to capture daily energy efficiency data, including equipment power consumption, factory temperature and humidity, and production capacity and order data. The collected data is then aggregated through an edge gateway. S2, Production Line Scheduling Based on the collected data and the mechanism of production line equipment, the AI ​​big model system is built to transform the scheduling problem into a semantic-mathematical dual-track paradigm. It understands natural language instructions and generates scheduling suggestions, while balancing objectives such as delivery time and cost. The input is the production capacity order data recorded in S1 above, which enters the AI ​​big model system so that it can automatically allocate factory lines and rationally allocate factory resources. S3, Energy Efficiency Analysis Based on the AI ​​large model system constructed by S2 above, the production line work is adjusted after scheduling and the current scheduling work environment is evaluated in multiple dimensions. Energy efficiency data is obtained and analyzed to obtain the optimal scheduling plan for production line scheduling under safe production conditions. S4, Safety Control Establish a feedback system mechanism. Based on the optimal production line scheduling plan obtained in step S3 above, use the optimal production line scheduling plan as a benchmark to perform multiple checks such as production safety, process safety, and equipment safety, and convert the optimal production line scheduling plan into standard control signals to be executed on each piece of equipment in the production line. S5. Implementation and Adjustment The optimal production line scheduling plan obtained in step S3 above is implemented after passing multiple safety checks in step S4 above. At the same time, the real-time energy consumption and equipment status after safe production are detected based on the sensor group deployed in step S1.

2. The green factory energy efficiency dynamic control model according to claim 1, characterized in that: The sensors installed in S1 include temperature sensors, humidity sensors, air sensors, voltage and current sensors, and compressor start / stop status sensors. Data is recorded and registered using these sensors and transmitted to the system via a gateway.

3. The green factory energy efficiency dynamic control model according to claim 1, characterized in that: In S2, the required production capacity order data is input into the AI ​​large model system and automatically allocated to the factory production lines to various regions. Equipment that does not need to participate in production is shut down, while the equipment in the regions that need to produce is concentrated. Based on the temperature and humidity data of the concentrated regions, the air compressors and air conditioners are turned on to ensure suitable temperature and humidity for production. Long production lines waiting to be produced are put on standby to reduce energy consumption.

4. The green factory energy efficiency dynamic control model according to claim 1, characterized in that: The data in the multidimensional assessment in S3 includes the energy consumption of the production line equipment and the energy consumption of the air compressor and air conditioner. Based on this, the energy consumption analysis chart of the key equipment is calculated, where min*(a+b labor cost), where min is minutes, a is energy efficiency cost, and b is labor cost.

5. The green factory energy efficiency dynamic control model according to claim 1, characterized in that: If any production safety, process safety, or equipment safety issues detected by the feedback system mechanism in step S4 are found to be substandard or unqualified, the feedback will be sent back to step S3 for adjustment. During this process, adjustments can be made manually at any time.

6. The green factory energy efficiency dynamic control model according to claim 1, characterized in that: In S5, real-time energy consumption and equipment status are input into the AI ​​large model system for analysis and comparison, and the implementation curve is output for staff to view in real time. When the actual deviation is too large, it is used to remind staff to make fine adjustments, so as to ensure safe production while reducing low energy efficiency.