Air compressor energy-saving control method, device and equipment based on AI algorithm

Abstract

The invention relates to an air compressor energy-saving control method, device and equipment based on an AI algorithm, and the method comprises the steps: collecting the operation data of an air compressor in real time; the real-time energy efficiency ratio of each air compressor is dynamically calculated according to the energy consumption and the gas production rate, and the air compressors with the energy efficiency ratios lower than 75% are marked as low-efficiency equipment; on the basis of the historical gas consumption data, the production line schedule, the environmental parameters and the equipment state, the gas consumption demand in the future time period and the future efficiency of the air compressor are predicted through the air pressure demand prediction model and the EER prediction model; on the premise of meeting the gas demand in the future period, with the goal of minimizing the total energy consumption and the constraint conditions that the total gas production rate meets the predicted gas demand and the load rate of the frequency converter is limited to be 50%-100%, an optimal switch combination and load distribution scheme is obtained, and a corresponding control instruction is generated and executed, so that the production demand is accurately matched, and meanwhile, the production efficiency is improved. The energy consumption of the system is reduced, the equipment management efficiency is improved, and the purpose of refined and intelligent energy-saving control of the air compression system is achieved.

Description

Technical Field

[0001] The present invention relates to the field of industrial automation and intelligent control technology, and in particular to an air compressor energy-saving control method, device and equipment based on AI algorithm. Background Art

[0002] As an indispensable power source equipment in industrial production, air compressors are widely used in many industries such as manufacturing, chemical industry, mining, food and beverage, etc. By converting mechanical energy into gas pressure energy, they provide compressed air for various production processes, supporting key production links such as pneumatic tool operation, material transportation, equipment purging, etc., and play a vital role in ensuring the continuity and stability of the production process.

[0003] However, under the traditional air compressor operation and management mode, there are many problems that lead to energy waste. On the one hand, most companies adopt a relatively extensive control strategy. Air compressors usually work according to a fixed operation mode and rarely make real-time dynamic adjustments based on actual gas demand and the equipment's own status. For example, when the gas demand on the production line decreases due to process changes or equipment downtime, the air compressor still maintains high-load operation and continues to produce compressed air far exceeding the actual demand. A large amount of compressed air is wasted in the process of decompression, resulting in ineffective energy consumption. On the other hand, there is a lack of a scientific and reasonable collaborative control mechanism in the air supply system composed of multiple air compressors. The on-off decision of each air compressor is often based on manual experience or simple time settings, which cannot accurately match the real-time gas fluctuations of the system, resulting in some air compressors with low energy efficiency running for a long time, while high-efficiency equipment is not fully utilized, further reducing the energy efficiency of the entire air supply system. Summary of the invention

[0004] The main purpose of the present invention is to provide an air compressor energy-saving control method, device and equipment based on AI algorithm, so as to reduce system energy consumption and improve equipment management efficiency while accurately matching production needs, so as to achieve the purpose of refined and intelligent energy-saving control of the air compressor system.

[0005] To achieve the above object, the present invention provides an air compressor energy-saving control method based on AI algorithm, comprising the following steps: Real-time collection of air compressor operation data, including energy consumption, gas output and environmental parameters of the air compressor; Dynamically calculate the real-time energy efficiency ratio of each air compressor based on energy consumption and gas output, and automatically mark air compressors with energy efficiency ratios below 75% as inefficient equipment; Based on historical gas consumption data, production line scheduling, environmental parameters and equipment status, the air compressor demand prediction model and EER prediction model are used to predict future gas demand and future performance of air compressors. On the premise of meeting the gas demand in the future period, with the goal of minimizing total energy consumption, with the total gas production meeting the predicted gas demand and the variable frequency machine load rate limited to 50%-100% as constraints, the prediction results of the air compressor demand prediction model and the EER prediction model are combined to obtain the optimal switch combination and load distribution plan, generate and execute the corresponding control instructions, which include the switching order of each air compressor, the corresponding load setting and the start and stop time points.

[0006] Furthermore, the step of dynamically calculating the real-time energy efficiency ratio of each air compressor according to energy consumption and gas output includes: Based on the collected energy consumption and gas production data, the real-time energy efficiency ratio is calculated by using an energy efficiency ratio calculation formula, where the calculation formula is the ratio of the gas production of a single air compressor to the corresponding energy consumption; When a device is marked as an inefficient device, the use priority of the inefficient device is preferentially reduced.

[0007] Furthermore, before the step of predicting the gas demand in the future period and the future performance of the air compressor, the method further includes: Measure the basic operating parameters of the air compressor, including the maximum energy consumption and full-load gas production of each non-variable frequency air compressor, and the dynamic energy consumption and corresponding gas production at a load rate of 50%-100% for each variable frequency air compressor; Based on the measured basic operating parameters, a mapping relationship between the load rate of the variable frequency air compressor and the energy consumption and gas production is established to obtain a relationship model between energy consumption and gas production. The energy consumption and gas production relationship model is used to predict the dynamic energy consumption and gas production of the variable frequency air compressor under different load rates, and serves as the core input of the EER prediction model.

[0008] Furthermore, the step of predicting the future gas demand and future performance of the air compressor based on the historical gas consumption data, production line schedule, environmental parameters and equipment status through the air pressure demand prediction model and the EER prediction model includes: Integrate historical gas usage data, production line scheduling, environmental parameters and equipment status data. The historical gas usage data is the actual gas usage record of the air compressor in different time periods in the past. The production line scheduling refers to the planning arrangement of each production link on the production line, including production time point, product type and production time. The equipment status refers to the operating status of the air compressor itself, including the service life of the equipment, whether there are hidden dangers of failure and the current operating load; The air pressure demand prediction model is used to analyze the historical air consumption and production line schedule, and the demand for compressed air in the production process in the future period is estimated by combining environmental parameters and equipment status; Based on the historical performance data of the air compressor, combined with the current equipment status and environmental parameters, the EER prediction model is used to predict the energy efficiency ratio of each air compressor in the future period and evaluate the future performance.

[0009] Furthermore, the air compression demand prediction model is a regression model, the input factors include production line scheduling, historical gas consumption, environmental parameters and equipment status, and the prediction error is controlled within a preset threshold; the EER prediction model is based on the historical performance data and real-time operating parameters of the air compressor and is constructed through a machine learning algorithm.

[0010] Furthermore, the steps of obtaining the optimal switch combination and load distribution scheme based on the premise of meeting the gas demand in the future period, minimizing the total energy consumption as the goal, and limiting the total gas production to meet the predicted gas demand and the inverter load rate to 50%-100% as the constraint conditions, and combining the prediction results of the future demand prediction and the equipment efficiency model, include: Based on the future gas demand output by the air pressure demand prediction model, determine the minimum threshold that the total gas production needs to meet; Based on the future performance data of air compressors output by the EER prediction model, high-efficiency equipment is selected as the candidate fleet for priority activation; With the goal of minimizing total energy consumption, an optimization objective function is established. The total energy consumption is the sum of the energy consumption of all running air compressors, including the fixed energy consumption of non-variable frequency air compressors and the dynamic energy consumption of variable frequency air compressors at the corresponding load rate. At the same time, constraints are defined. The constraints include that the total gas output of all running air compressors ≥ the predicted gas demand, the load rate of the variable frequency air compressor ranges from 50% to 100%, and the non-variable frequency air compressor only supports two states: on or off; A combined optimization algorithm is used to solve the objective function with the constraint that the continuous operation time of a single air compressor is not less than the preset minimum start-stop interval, and the optimal air compressor group control scheme that meets the constraint conditions is obtained, including the start-stop state combination of non-variable frequency air compressors, the load rate setting value of variable frequency air compressors, and the start-stop time points and operation priority sequence of each air compressor.

[0011] Furthermore, the step of screening high-efficiency equipment includes: Based on the future performance data output by the EER prediction model, the air compressors with EER values ​​higher than the preset threshold are marked as high-efficiency equipment; On the premise of meeting the total gas production demand, high-efficiency equipment should be used first and the operating time of inefficient equipment should be limited.

[0012] The present invention also provides an air compressor energy-saving control device based on an AI algorithm, comprising: Data acquisition module, used to collect real-time air compressor operation data, including energy consumption, gas production and environmental parameters of the air compressor; Energy efficiency calculation module, which is used to dynamically calculate the real-time energy efficiency ratio of each air compressor based on energy consumption and gas output, and automatically mark air compressors with energy efficiency ratios below 75% as inefficient equipment; Model prediction module, which is used to predict the future gas demand and future performance of the air compressor through the air pressure demand prediction model and EER prediction model based on historical gas consumption data, production line scheduling, environmental parameters and equipment status; The decision-making module is used to meet the gas demand in the future period, with the goal of minimizing total energy consumption, with the total gas production meeting the predicted gas demand and the inverter load rate limited to 50%-100% as constraints, and combines the prediction results of the air compression demand prediction model and the EER prediction model to obtain the optimal switch combination and load distribution plan, generate the corresponding control instructions and execute them.

[0013] The present invention also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the above-mentioned air compressor energy-saving control method based on the AI ​​algorithm are implemented.

[0014] The present invention also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the above-mentioned air compressor energy-saving control method based on the AI ​​algorithm are implemented.

[0015] The air compressor energy-saving control method, device and equipment based on AI algorithm provided by the present invention have the following beneficial effects: (1) The present invention can accurately grasp the operating status of the equipment by collecting the energy consumption, gas output and environmental parameters of the air compressor in real time. The real-time energy efficiency ratio is dynamically calculated using these data, and inefficient equipment is automatically marked to avoid the ineffective operation of low-efficiency air compressors. At the same time, based on the air compressor demand prediction model and the EER prediction model, the future gas demand and air compressor efficiency are predicted, and the optimal switch combination and load distribution plan are generated with the goal of minimizing total energy consumption. This allows the air compressor to minimize energy waste while meeting the production gas demand, effectively reducing the energy consumption cost of the enterprise.

[0016] (2) In the traditional mode, manual experience or simple time setting of on / off decisions are difficult to accurately match real-time gas consumption fluctuations. This energy-saving control method uses AI algorithms to conduct a comprehensive analysis based on historical gas consumption data, production line scheduling, environmental parameters and equipment status, and automatically generates control instructions, including the on / off sequence of each air compressor, corresponding load settings and start / stop time points. This greatly reduces manual intervention, improves the scientificity and accuracy of equipment management, keeps equipment running in the best condition, reduces equipment failure rate, extends equipment service life, and reduces equipment maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a flow chart of an air compressor energy-saving control method based on an AI algorithm in one embodiment of the present invention; Figure 2 It is a structural block diagram of an air compressor energy-saving control device based on an AI algorithm in one embodiment of the present invention; Figure 3 It is a schematic block diagram of the structure of a computer device according to an embodiment of the present invention.

[0018] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0020] Reference Figure 1 , which is a flow chart of an air compressor energy-saving control method based on an AI algorithm proposed by the present invention, comprising the following steps: S1, real-time collection of air compressor operation data, including air compressor energy consumption, gas production and environmental parameters; S2, dynamically calculates the real-time energy efficiency ratio of each air compressor based on energy consumption and gas output, and automatically marks air compressors with energy efficiency ratios below 75% as inefficient equipment; S3, based on historical gas consumption data, production line scheduling, environmental parameters and equipment status, predicts future gas demand and future performance of air compressors through air compression demand prediction model and EER prediction model; S4, under the premise of meeting the gas demand in the future period, with the goal of minimizing the total energy consumption, with the total gas production meeting the predicted gas demand and the variable frequency machine load rate limited to 50%-100% as constraints, combined with the prediction results of the air compressor demand prediction model and the EER prediction model, obtain the optimal switch combination and load distribution plan, generate and execute the corresponding control instructions, which include the switch order of each air compressor, the corresponding load setting and the start and stop time points.

[0021] As described in step S1 above, the operating data of the air compressor is collected in real time through sensors and smart meters (such as smart meters, air flow meters), including: energy consumption (electrical input power, such as fixed energy consumption of non-variable frequency air compressors and dynamic energy consumption of variable frequency air compressors), gas production (compressed air output, measured by flow meters), air compressor operating status (such as load rate, fault code, operating time) and environmental parameters (such as temperature, humidity and other external environmental factors that may affect the efficiency of the air compressor). (non-inverter) or ( )(Dynamic energy consumption of inverter), gas production (Non-inverter full load gas production) or (dynamic gas production of the inverter), environmental parameters and equipment status data are uploaded to the central control system. The relationship between the energy consumption and load rate of the inverter air compressor is:

[0022] in, and are the coefficients fitted by the measured data.

[0023] As described in step S2 above, the real-time energy efficiency ratio of each air compressor is dynamically calculated according to the formula EER = gas output of a single air compressor (m³) / energy consumption of a single air compressor (kWh). If the EER of an air compressor is lower than 75% (preset threshold), it is automatically marked as an inefficient device. In subsequent control, high-efficiency devices (EER ≥ 75%) are enabled first, and the operating time of inefficient devices is limited or they are directly shut down.

[0024] As described in step S3 above, integrate data information, including historical gas consumption data (actual gas consumption records in the past period), production line scheduling (production plan, such as the number of lines opened, product types, and duration), environmental parameters (such as temperature changes), and equipment status (air compressor health, potential faults, and operating load); based on regression analysis or machine learning, combine historical data with production line scheduling to predict the compressed air demand in the future period. Based on the historical performance data, real-time operating parameters, and equipment status of the air compressor, predict the energy efficiency ratio of each air compressor in the future period. Calculate the gas demand based on the total gas demand, and the formula is: ; in, is the energy efficiency parameter of the air compressor; G1_LS2 represents the second production line LS2 of a workshop in a production area G1; Indicates the gas demand on Monday; Indicates the gas demand during the time period of 00:00-01:00.

[0025] As described in step S4 above, the switch combination and load distribution are optimized under the premise of meeting future gas demand. The optimization objective function is: in, Indicates the switch status of the non-variable frequency air compressor. The non-variable frequency air compressor only supports two states: on or off. The value is 1 (on) or 0 (off). Indicates the load rate of the variable frequency air compressor.

[0026] The constraints include gas production constraints, inverter load rate limits, and start-stop interval constraints (to prevent frequent start-stop).

[0027] Gas production constraint formula: ,in is the gas output of non-variable frequency air compressor, is the gas output of the variable frequency air compressor, Gas demand.

[0028] Inverter load rate limit: ; Start-stop interval constraints (to prevent frequent start-stop): ; Use mixed integer linear programming (MILP) or genetic algorithm to generate optimal control instructions, including the switch state combination of non-inverter machines , inverter load factor setting value As well as the start and stop time points and priority sequence of each device (high EER devices are enabled first).

[0029] In one embodiment, the air compression system group control energy-saving optimization based on AI algorithm is applied in a leading new energy enterprise. The air compression system consists of air compressor units: 3 centrifugal air compressors (frequency control), 5 screw air compressors (non-frequency control); auxiliary equipment: 3 cold dryers, 5 dryers, 3 water pumps, and 6 cooling towers. Total gas supply demand: maximum gas production 1200 m³ / min, average daily power consumption 15,000 kWh.

[0030] A smart meter (accuracy ±0.5%) is installed at the power input end of each air compressor to collect energy consumption data (unit: kWh) in real time. A high-precision flow meter (range 0-500 m³ / min, accuracy ±1%) is installed at the compressed air output end to monitor gas production. Temperature and humidity sensors (range -40℃~80℃) and vibration sensors are deployed to collect environmental parameters and equipment health status.

[0031] Non-inverter screw machine (Example: No. 1 screw machine): ; Variable frequency centrifuge (example: centrifuge No. 1, load rate 80%): ; Finally, it was determined that the EER of 3 screw compressors was < 1.2 (below the 75% threshold) and they were marked as inefficient equipment.

[0032] Input data: historical gas consumption, gas consumption records by time period in the past 30 days (time granularity: 15 minutes); production line scheduling, production plan for the next 72 hours (including the opening time of 8 battery assembly lines and production capacity requirements); environmental parameters, predicted temperature (25℃~35℃), humidity (60%~80%).

[0033] Construct an air pressure demand prediction model through multiple linear regression: ; in, is the number of production lines opened, is the temperature correction factor.

[0034] The EER prediction model is constructed using the random forest algorithm, with the input features being load rate, equipment operating hours, and ambient temperature and humidity; the predicted EER of each air compressor in the next 4 hours is output (with an error of ±3%).

[0035] The final forecast is that the gas demand during the future peak period (10:00-12:00) will be 950 m³ / min, and 4 air compressors (including 2 variable frequency centrifugal compressors) will need to be started.

[0036] Optimization objective function (minimize total energy consumption): ; Among them, the energy consumption formula of variable frequency centrifuge is fitted through actual measurement: ; The constraints are: total gas production ≥ 950 m³ / min; variable frequency centrifuge load rate∈ [50%, 100%]; non-variable frequency screw compressor start-stop interval ≥ 30 minutes.

[0037] The optimized equipment combination is: start 2 variable frequency centrifuges (load rate 85% and 90%), total gas production: 300×0.85+300×0.90=525 m³ / min; start 2 high-efficiency screw compressors (EER > 1.5), total gas production: 150×2=300m³ / min; cold dryer and dryer linkage: dynamically adjust the operating quantity according to gas consumption (3 cold dryers are fully opened, and 4 dryers are opened).

[0038] In this embodiment, the total energy consumption in the traditional mode is 2×200+2×110=620 kW; the total energy consumption after optimization is (0.9×85+50)+(0.9×90+50)+2×110=565 kW; the energy saving rate is (620−565) / 620×100%=8.9%(620−565) / 620×100%=8.9%.

[0039] Reference Figure 2 , is a structural block diagram of an air compressor energy-saving control device based on an AI algorithm in one embodiment of the present invention, comprising: Data acquisition module, used to collect real-time air compressor operation data, including energy consumption, gas production and environmental parameters of the air compressor; Energy efficiency calculation module, which is used to dynamically calculate the real-time energy efficiency ratio of each air compressor based on energy consumption and gas output, and automatically mark air compressors with energy efficiency ratios below 75% as inefficient equipment; Model prediction module, which is used to predict the future gas demand and future performance of the air compressor through the air pressure demand prediction model and EER prediction model based on historical gas consumption data, production line scheduling, environmental parameters and equipment status; The decision-making module is used to meet the gas demand in the future period, with the goal of minimizing total energy consumption, with the total gas production meeting the predicted gas demand and the inverter load rate limited to 50%-100% as constraints, and combines the prediction results of the air compression demand prediction model and the EER prediction model to obtain the optimal switch combination and load distribution plan, generate the corresponding control instructions and execute them.

[0040] For the specific implementation of each module in the above device example, please refer to the above method embodiment, which will not be repeated here.

[0041] Reference Figure 3 In an embodiment of the present invention, a computer device is also provided. The computer device may be a server, and its internal structure may be as follows: Figure 3 As shown. The computer device includes a processor, a memory, a display screen, an input device, a network interface and a database connected through a system bus. Among them, the processor designed by the computer is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the corresponding data in this embodiment. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the above method is implemented.

[0042] Those skilled in the art will understand that Figure 3 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied.

[0043] An embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the above method is implemented. It can be understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0044] In summary, an air compressor energy-saving control method, device and equipment based on AI algorithm, wherein the method includes real-time collection of air compressor operation data, including energy consumption, gas production and environmental parameters of the air compressor; dynamically calculating the real-time energy efficiency ratio of each air compressor according to energy consumption and gas production, and automatically marking air compressors with energy efficiency ratios lower than 75% as inefficient equipment; based on historical gas consumption data, production line scheduling, environmental parameters and equipment status, predicting the gas demand in future periods and the future performance of the air compressor through an air compressor demand prediction model and an EER prediction model; on the premise of meeting the gas demand in future periods, with the goal of minimizing total energy consumption, with the total gas production meeting the predicted gas demand and the inverter load rate limited to 50%-100% as constraints, combining the prediction results of the air compressor demand prediction model and the EER prediction model, obtaining the optimal switch combination and load distribution plan, generating and executing corresponding control instructions, so as to achieve precise matching of production needs while reducing system energy consumption and improving equipment management efficiency, so as to achieve the purpose of refined and intelligent energy-saving control of the air compressor system.

[0045] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided by the present invention and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-speed data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM.

[0046] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0047] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. An air compressor energy-saving control method based on AI algorithm, characterized in that: The following steps are involved: Real-time collection of air compressor operation data, including energy consumption, gas output and environmental parameters of the air compressor; Dynamically calculate the real-time energy efficiency ratio of each air compressor based on energy consumption and gas output, and automatically mark air compressors with energy efficiency ratios below 75% as inefficient equipment; Based on historical gas consumption data, production line scheduling, environmental parameters and equipment status, the air compressor demand prediction model and EER prediction model are used to predict future gas demand and future performance of air compressors. On the premise of meeting the gas demand in the future period, with the goal of minimizing total energy consumption, with the total gas production meeting the predicted gas demand and the variable frequency machine load rate limited to 50%-100% as constraints, the prediction results of the air compressor demand prediction model and the EER prediction model are combined to obtain the optimal switch combination and load distribution plan, generate and execute the corresponding control instructions, which include the switching order of each air compressor, the corresponding load setting and the start and stop time points.

2. The air compressor energy-saving control method based on AI algorithm according to claim 1 is characterized in that: The step of dynamically calculating the real-time energy efficiency ratio of each air compressor according to energy consumption and gas production includes: Based on the collected energy consumption and gas production data, the real-time energy efficiency ratio is calculated by using an energy efficiency ratio calculation formula, where the calculation formula is the ratio of the gas production of a single air compressor to the corresponding energy consumption; When a device is marked as an inefficient device, the use priority of the inefficient device is preferentially reduced.

3. The air compressor energy-saving control method based on AI algorithm according to claim 1 is characterized in that: Before the step of predicting the gas demand in the future period and the future performance of the air compressor, the method further includes: Measure the basic operating parameters of the air compressor, including the maximum energy consumption and full-load gas production of each non-variable frequency air compressor, and the dynamic energy consumption and corresponding gas production at a load rate of 50%-100% for each variable frequency air compressor; Based on the measured basic operating parameters, a mapping relationship between the load rate of the variable frequency air compressor and the energy consumption and gas production is established to obtain a relationship model between energy consumption and gas production. The energy consumption and gas production relationship model is used to predict the dynamic energy consumption and gas production of the variable frequency air compressor under different load rates, and serves as the core input of the EER prediction model.

4. The air compressor energy-saving control method based on AI algorithm according to claim 1 is characterized in that: The steps of predicting the future gas demand and future performance of the air compressor based on the historical gas consumption data, production line schedule, environmental parameters and equipment status through the air pressure demand prediction model and the EER prediction model include: Integrate historical gas usage data, production line scheduling, environmental parameters and equipment status data. The historical gas usage data is the actual gas usage record of the air compressor in different time periods in the past. The production line scheduling refers to the planning arrangement of each production link on the production line, including production time point, product type and production time. The equipment status refers to the operating status of the air compressor itself, including the service life of the equipment, whether there are hidden dangers of failure and the current operating load; The air pressure demand prediction model is used to analyze the historical air consumption and production line schedule, and the demand for compressed air in the production process in the future period is estimated by combining environmental parameters and equipment status; Based on the historical performance data of the air compressor, combined with the current equipment status and environmental parameters, the EER prediction model is used to predict the energy efficiency ratio of each air compressor in the future period and evaluate the future performance.

5. The air compressor energy-saving control method based on AI algorithm according to claim 4 is characterized in that: The air compression demand prediction model is a regression model, the input factors include production line scheduling, historical gas consumption, environmental parameters and equipment status, and the prediction error is controlled within the preset threshold; the EER prediction model is based on the historical performance data and real-time operating parameters of the air compressor and is constructed through a machine learning algorithm.

6. The air compressor energy-saving control method based on AI algorithm according to claim 1 is characterized in that: The steps of obtaining the optimal switch combination and load distribution scheme under the premise of meeting the gas demand in the future period, minimizing the total energy consumption as the goal, taking the total gas production to meet the predicted gas demand and limiting the inverter load rate to 50%-100% as the constraint conditions, combining the prediction results of the future demand prediction and the equipment efficiency model, include: Based on the future gas demand output by the air pressure demand prediction model, determine the minimum threshold that the total gas production needs to meet; Based on the future performance data of air compressors output by the EER prediction model, high-efficiency equipment is selected as the candidate fleet for priority activation; With the goal of minimizing total energy consumption, an optimization objective function is established. The total energy consumption is the sum of the energy consumption of all running air compressors, including the fixed energy consumption of non-variable frequency air compressors and the dynamic energy consumption of variable frequency air compressors at the corresponding load rate. At the same time, constraints are defined. The constraints include that the total gas output of all running air compressors ≥ the predicted gas demand, the load rate of the variable frequency air compressor ranges from 50% to 100%, and the non-variable frequency air compressor only supports two states: on or off; A combined optimization algorithm is used to solve the objective function with the constraint that the continuous operation time of a single air compressor is not less than the preset minimum start-stop interval, and the optimal air compressor group control scheme that meets the constraint conditions is obtained, including the start-stop state combination of non-variable frequency air compressors, the load rate setting value of variable frequency air compressors, and the start-stop time points and operation priority sequence of each air compressor.

7. The air compressor energy-saving control method based on AI algorithm according to claim 6 is characterized in that: The step of screening high-efficiency equipment includes: Based on the future performance data output by the EER prediction model, the air compressors with EER values ​​higher than the preset threshold are marked as high-efficiency equipment; On the premise of meeting the total gas production demand, high-efficiency equipment should be used first and the operating time of inefficient equipment should be limited.

8. An air compressor energy-saving control device based on AI algorithm, characterized in that: include: Data acquisition module, used to collect real-time air compressor operation data, including energy consumption, gas production and environmental parameters of the air compressor; Energy efficiency calculation module, which is used to dynamically calculate the real-time energy efficiency ratio of each air compressor based on energy consumption and gas output, and automatically mark air compressors with energy efficiency ratios below 75% as inefficient equipment; Model prediction module, which is used to predict the future gas demand and future performance of the air compressor through the air pressure demand prediction model and EER prediction model based on historical gas consumption data, production line scheduling, environmental parameters and equipment status; The decision-making module is used to meet the gas demand in the future period, with the goal of minimizing total energy consumption, with the total gas production meeting the predicted gas demand and the inverter load rate limited to 50%-100% as constraints, and combines the prediction results of the air compression demand prediction model and the EER prediction model to obtain the optimal switch combination and load distribution plan, generate the corresponding control instructions and execute them.

9. A computer device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the computer program, the steps of the air compressor energy-saving control method based on the AI ​​algorithm described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the air compressor energy-saving control method based on the AI ​​algorithm described in any one of claims 1 to 7 are implemented.

Images