Energy-saving control method and device for industrial low-temperature air conditioner

Abstract

The application provides an energy-saving control method and device for an industrial low-temperature air conditioner, and applies to the technical field of data processing. In the application, core operation, load and environment data of a compressor are acquired, dynamic calibration, fluctuation filtering and precision grading setting are performed, and a precise compressor data set is generated. Then, a rotating speed-air supply volume coupling model is constructed, parameters of the compressor and an air supply system are associated, and a low-energy-consumption basic data mechanism is formed. Subsequently, optimized collaborative data transmission is performed, and a transmission system containing safety verification is constructed. Then, visualized fusion data and superimposed key indexes are generated, and collaborative control data suitable for a scene are generated. Finally, in combination with the response delay characteristics of equipment, dynamic adaptation control instructions are generated, and grading energy-saving instructions and scene-specific operation information are generated, so that efficient collaborative energy saving of a magnetic suspension compressor and grading air supply is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to an energy-saving control method and device for an industrial low-temperature air conditioner. BACKGROUND

[0002] In the current field of industrial low-temperature air conditioners, the control of magnetic suspension compressors and staged air supply systems mostly adopts an "independent adjustment" mode, that is, the operating parameters (such as speed and pressure) of the compressor and the parameters (such as air volume and air speed) of the air supply system are controlled individually, and no collaborative correlation mechanism is established between the two, resulting in the following technical status:

[0003] The existing technology mostly uses simple filtering means to process the original parameters (such as discharge pressure and suction temperature) of the magnetic suspension compressor, without setting precision levels in combination with the priority of refrigeration requirements in industrial scenarios, nor optimizing the parameter acquisition frequency for high-load conditions, which is prone to parameter error exceeding problems, thereby affecting the stability of the refrigeration effect. For example, a precision manufacturing workshop requires a temperature control precision of ±0.1℃, but the existing non-graded parameter processing method is prone to cause the compressor parameter fluctuation amplitude to exceed ±0.5℃, which cannot meet the process requirements.

[0004] The existing technology does not construct a coupling correlation model of the compressor speed and the air supply volume, but only sets the parameters of the two according to experience values, which is prone to the contradiction of "high compressor speed but mismatched air supply volume" or "excessive air supply volume but insufficient compressor refrigeration capacity", resulting in energy waste. For example, in a stable load period of a low-temperature warehouse workshop, the compressor maintains a high speed of 3600r / min, but the air supply volume is only 1800m³ / h, resulting in excessive refrigeration capacity, and the energy consumption is 15%-20% higher per hour than the reasonable matching state.

[0005] The existing data display interface does not layout in combination with the operation habits of industrial scenarios, and the core parameters (such as energy consumption and refrigeration efficiency) are mixed with auxiliary data, and no customized display logic is provided for different industrial scenarios (such as precision manufacturing and low-temperature warehouse). At the same time, the adaptability of the control instructions and the real-time working condition data is insufficient, and the response delay characteristics (such as 2-5 seconds of compressor speed adjustment delay and 3-6 seconds of air supply system air volume response delay) of the magnetic suspension compressor and the air supply system are not considered, which is prone to the problem of "instruction disconnection from working condition", such as in the load fluctuation period, the control instruction is not adapted to the device response delay, resulting in a process temperature fluctuation exceeding ±1℃.

[0006] It should be noted that the information disclosed in the above background section is only used to strengthen the understanding of the background of the present disclosure, and therefore can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0007] Other features and advantages of the present application will become apparent from the following detailed description, taken in conjunction with the accompanying drawings, or parts of the application.

[0008] According to an aspect of the present application, an energy-saving control method for an industrial low-temperature air conditioner is provided, comprising: obtaining core operation data, load data, and environmental data required for collaborative control of the industrial low-temperature air conditioner; dynamically calibrating and filtering magnetic suspension compressor parameters in the core operation data, setting parameter accuracy based on priority of refrigeration demand in an industrial scene, applying constraint information of compressor operation parameter and process temperature threshold adaptation, and parameter collection frequency improvement under high load conditions, to generate a pre-processed compressor accurate operation data set; performing collaborative correlation processing on the pre-processed compressor operation data set and hierarchical air supply system parameters, realizing parameter matching by establishing a compressor speed-air supply amount coupling model, and generating a low-energy consumption collaborative control basic data mechanism; performing transmission optimization on the correlated collaborative data, applying constraint and control instruction safety verification constraint information of data compression transmission and key parameter priority transmission based on abnormal transmission state, and generating a collaborative data transmission system; performing visual fusion processing on the transmitted collaborative data, laying out a data display interface based on industrial scene operation habits, and simultaneously superimposing real-time monitoring curves of energy consumption, refrigeration efficiency coefficient, and load matching degree index; applying constraints of data display accuracy and control response speed adaptation, and multi-region working condition data partition display, to generate collaborative control data; dynamically adapting the energy-saving control instructions issued by the control host and the collaborative control data, combining the response delay characteristics of the magnetic suspension compressor and the hierarchical air supply system, to generate real-time hierarchical energy-saving control instructions and scene-specific device collaborative operation information.

[0009] In another aspect of the present application, an energy-saving control device for an industrial low-temperature air conditioner comprises: an acquisition module for acquiring core operating data, load data, and environmental data required for coordinated control of the industrial low-temperature air conditioner; a processing module for performing dynamic calibration and fluctuation filtering on magnetic suspension compressor parameters in the core operating data, performing hierarchical setting on parameter accuracy based on industrial scene refrigeration demand priority, applying constraint information of compressor operating parameter and process temperature threshold adaptation, and parameter collection frequency improvement under high load conditions, and generating a pre-processed compressor accurate operating data set; performing coordinated association processing on the pre-processed compressor operating data set and hierarchical air supply system parameters, realizing parameter matching through establishment of a compressor speed-air supply amount coupling model, generating a low-energy-consumption coordinated control basic data mechanism; performing transmission optimization on the associated coordinated data, applying constraint and control instruction safety verification constraint information of data compression transmission and key parameter priority transmission under abnormal transmission state, and generating a coordinated data transmission system; performing visual fusion processing on the transmitted coordinated data, laying out a data display interface based on industrial scene operation habits, and simultaneously superimposing real-time energy consumption monitoring curves, refrigeration efficiency coefficients, and load matching degree indexes; applying constraints of data display accuracy and control response speed adaptation, and multi-region working condition data partition display, and generating coordinated control data; performing dynamic adaptation processing on the energy-saving control instructions and coordinated control data issued by the control host, combining the response delay characteristics of the magnetic suspension compressor and the hierarchical air supply system, and generating real-time hierarchical energy-saving control instructions and scene-specific device coordinated operation information.

[0010] According to still another aspect of the present application, an electronic device comprises: a first processor; and a memory for storing executable instructions of the first processor; wherein the first processor is configured to execute the energy-saving control method for an industrial low-temperature air conditioner by executing the executable instructions.

[0011] According to still another aspect of the present application, a computer-readable storage medium is provided, which stores a computer program, and the computer program is executed by a second processor to implement the energy-saving control method for an industrial low-temperature air conditioner.

[0012] The energy-saving control method and device of the industrial low-temperature air conditioner provided by the application are used for the industrial low-temperature air conditioner, and energy saving is realized through a closed loop process of "data driving-collaborative control-precise execution". First, core operation data of a magnetic suspension compressor, hierarchical air supply parameters, load and environmental data are acquired, and the precise compressor data set is generated through dynamic calibration, sliding window filtering and scene-based precision grading. Then, the standardized integrated data is imported into an energy consumption simulation software for simulation, a compressor speed-air supply amount coupling model is constructed by using a multivariate regression algorithm, and a low-energy consumption basic data mechanism is generated in combination with a scene-based collaborative characteristic library. Subsequently, data transmission is optimized, priority is divided, and an abnormal emergency system is established, and the collaborative control data of the adaptive scene is generated by visualizing and fusing the data. Finally, in combination with the device response delay, the key factors are screened by using a random forest algorithm, a dynamic adaptive model is constructed, hierarchical energy-saving instructions and scene-based operation information are generated, collaborative energy saving is realized, and the refrigeration efficiency is improved and the energy consumption is reduced.

[0013] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, and are not limiting to the present disclosure. BRIEF DESCRIPTION OF DRAWINGS

[0014] Figure 1 A flowchart of an energy-saving control method of an industrial low-temperature air conditioner provided by an embodiment of the application is shown.

[0015] Figure 2 A structural schematic diagram of an energy-saving control device of an industrial low-temperature air conditioner provided by an embodiment of the application is shown. DETAILED DESCRIPTION

[0016] The preferred embodiments of the application are described below in conjunction with the accompanying drawings, and it should be understood that the preferred embodiments described herein are only used to illustrate and explain the application, and are not used to limit the application.

[0017] The energy-saving control method of the industrial low-temperature air conditioner according to the exemplary embodiments of the application is described below in conjunction with Figure 1 It should be noted that the following application scenarios are only shown for the purpose of facilitating the understanding of the spirit and principles of the application, and the embodiments of the application are not limited in this respect. On the contrary, the embodiments of the application are applicable to any applicable scenario.

[0018] In an embodiment, Figure 1 A flowchart of an energy-saving control method of an industrial low-temperature air conditioner according to an embodiment of the application is shown.

[0019] S101, core operation data, load data and environmental data required for collaborative control of the industrial low-temperature air conditioner are acquired.

[0020] In one embodiment, around the industrial low-temperature air conditioner cooperative control demand, three types of core data to be obtained are determined, which are core operation data, load data and environmental data, to ensure that the data covers the three key dimensions of equipment operation state, load demand and external environmental influence, and provides comprehensive data support for subsequent cooperative control. The core operation data focuses on the core equipment of the industrial low-temperature air conditioner, i.e. the magnetic suspension compressor and the staged air supply system, and real-time parameters are collected through the sensors (such as pressure sensor, temperature sensor, speed sensor, power sensor) of the equipment. Among them, the magnetic suspension compressor parameters include exhaust pressure (collected by the compressor exhaust port pressure sensor, data range 0.8-1.2 MPa, collection frequency 1 time / minute), suction temperature (collected by the compressor suction port temperature sensor, data range 5-15℃, collection frequency 1 time / minute), motor speed (collected by the motor speed encoder, data range 2000-5000 r / min, collection frequency 1 time / 10 seconds), input power (collected by the power metering module, data range 5-30 kW, collection frequency 1 time / minute); The staged air supply system parameters include the air supply temperature of each area (collected by the air supply branch pipe temperature sensor, such as the air supply temperature target of 5-8℃ in the precision manufacturing workshop A area, the collection frequency is 1 time / minute), the air speed (collected by the air supply air outlet air speed sensor, the data range is 2-5 m / s, the collection frequency is 1 time / minute), and the air volume distribution ratio (calculated based on the air speed and air outlet area of each area, such as the air volume proportion of 30% in the workshop A area and 25% in the workshop B area, updated every 5 minutes).

[0021] The load data focuses on the load demand of the industrial low-temperature air conditioner, and the heat dissipation power of the process equipment and the process demand temperature threshold are collected. Among them, the heat dissipation power of the process equipment is calculated by the heat metering device or the rated power of the equipment combined with the heat dissipation coefficient (the rated power of a certain precision numerical control machine tool is 15 kW, the heat dissipation coefficient is 0.6, and the heat dissipation power is calculated to be 9 kW, which is recalculated every 30 minutes); The process demand temperature threshold is determined according to the production process requirements of different industrial scenes (the process demand temperature threshold of the precision manufacturing workshop is set to 5-8℃ to ensure product accuracy; the process demand temperature threshold of the low-temperature warehouse workshop is set to-5-0℃ to ensure the quality of goods storage, which is determined by the production process file and stored in the control host as a fixed reference data).

[0022] The environmental data focuses on external environmental factors that affect the operation of the air conditioner in the industrial workshop, mainly collecting the temperature and humidity of the workshop environment. By arranging temperature and humidity sensors in different areas of the workshop (such as equipment-intensive areas, personnel operation areas, and storage areas), data collection is achieved (the collected temperature in the equipment-intensive area of the workshop is 25-30°C, and the relative humidity is 40%-60%; the collected temperature in the personnel operation area is 22-26°C, and the relative humidity is 45%-55%), with a collection frequency of 1 time / minute, ensuring coverage of different environmental areas of the workshop and reflecting the actual impact of the environment on the air conditioning load.

[0023] The collection time stamp format of all types of data is unified (using the "year-month-day hour: minute: second" format, such as 2025-10-2214:30:00), ensuring that the core operating data, load data, and environmental data at the same time node can be correlated and matched; at the same time, the collection equipment is calibrated regularly (the precision of the pressure sensor and temperature sensor is calibrated every month, and the error is corrected in time when it exceeds ±0.5%), avoiding data deviation caused by collection equipment error and ensuring the accuracy of subsequent data processing and collaborative control.

[0024] In one implementation, the magnetic suspension compressor parameters in the core operating data are dynamically calibrated and filtered, the parameter precision is set based on the priority of the industrial scene refrigeration demand, the constraint information of the compressor operating parameter and the process temperature threshold is applied, and the parameter collection frequency is improved under high load conditions, to generate the pre-processed compressor accurate operating data set.

[0025] In one implementation, the magnetic suspension compressor original parameters in the core operating data are extracted, combined with the historical operating parameter benchmark value of the industrial low-temperature air conditioner, a parameter dynamic calibration model is constructed, and the compressor parameter calibration benchmark data is generated. From the core operating data of the industrial low-temperature air conditioner, the key original parameters of the magnetic suspension compressor are selected, including exhaust pressure, suction temperature, motor speed, and input power, to ensure that the parameters cover the core dimensions of the compressor operating state. The original parameters of the magnetic suspension compressor in a certain precision manufacturing workshop at 9:00 am are extracted, which are exhaust pressure 1.05 MPa, suction temperature 12°C, motor speed 3800 r / min, and input power 22 kW.

[0026] The historical operating parameters of the same type of magnetic suspension compressor of the industrial low-temperature air conditioner in the past 3 months are retrieved, the mean and standard deviation of each parameter are calculated daily, and the historical operating parameter benchmark value is determined. The historical mean of the exhaust pressure of the compressor in the past 3 months is 1.0 MPa, and the standard deviation is ±0.05 MPa; the historical mean of the suction temperature is 10°C, and the standard deviation is ±1°C; the historical mean of the motor speed is 3500 r / min, and the standard deviation is ±200 r / min; the historical mean of the input power is 20 kW, and the standard deviation is ±1.5 kW.

[0027] With the historical operation parameter benchmark value as the reference, a linear regression calibration model is constructed in combination with the current working condition (such as the workshop environment temperature and process load), the theoretical benchmark value of each parameter under the current working condition is calculated through the model, and the compressor parameter calibration benchmark data is generated. Based on the current workshop environment temperature of 28°C (higher than the historical average environment temperature of 25°C), the calibration model is corrected, and the exhaust pressure calibration benchmark value under the current working condition is 1.02 MPa, the suction temperature calibration benchmark value is 11°C, the motor speed calibration benchmark value is 3600 r / min, and the input power calibration benchmark value is 21 kW.

[0028] The original parameters of the magnetic suspension compressor are subjected to fluctuation filtering processing, and a sliding window filtering algorithm is used to identify abnormal fluctuation values of the parameters in real time. When the fluctuation amplitude exceeds the preset threshold, the filtering mechanism is automatically triggered, the transient interference data is removed, and the initial parameter set of the compressor is generated. The size of the sliding window is set to 5 (i.e. 5 groups of parameter data are continuously collected as a window), the average value of the parameters in the window is calculated, and the original parameters collected at present are compared with the window average value to identify abnormal fluctuation values. The fluctuation amplitude preset threshold of each parameter is set, wherein the exhaust pressure fluctuation threshold is ±0.08 MPa, the suction temperature fluctuation threshold is ±3°C, the motor speed fluctuation threshold is ±300 r / min, and the input power fluctuation threshold is ±3 kW; when the difference between the original parameters and the window average value exceeds the corresponding threshold, the filtering mechanism is automatically triggered, the transient interference data is removed, and the abnormal value is replaced by the window average value. Five groups of exhaust pressure data are continuously collected as 1.05 MPa, 1.03 MPa, 1.2 MPa, 1.04 MPa and 1.02 MPa, and the window average value is 1.068 MPa. Among them, 1.2 MPa and the average value difference is 0.132 MPa, which exceeds the threshold of ±0.08 MPa, and is determined as transient interference data, which is removed and replaced by 1.068 MPa. The final generated compressor initial parameter set is that the exhaust pressure at this moment is 1.068 MPa, and the remaining parameters are processed in the same way to form a complete initial parameter set.

[0029] Based on the priority of the refrigeration demand in the industrial scene, the accuracy of the smoothed compressor initial parameters is classified and set, and the accuracy classified parameter set is generated. The industrial scene is divided into three levels of high priority (such as precision manufacturing workshop, which needs to strictly control temperature accuracy to ensure product quality), medium priority (such as low-temperature warehouse workshop, which needs to stabilize temperature to ensure goods storage), and low priority (such as ordinary industrial workshop, which has relatively loose requirements on temperature accuracy).

[0030] For different priority scenarios, set the corresponding parameter accuracy standards. In the high-priority scenario (precision manufacturing workshop), the exhaust pressure accuracy is ±0.02 MPa, the suction temperature accuracy is ±0.5°C, the motor speed accuracy is ±50 r / min, and the input power accuracy is ±0.5 kW. In the medium-priority scenario (low-temperature warehouse workshop), the exhaust pressure accuracy is ±0.05 MPa, the suction temperature accuracy is ±1°C, the motor speed accuracy is ±100 r / min, and the input power accuracy is ±1 kW. In the low-priority scenario (ordinary industrial workshop), the exhaust pressure accuracy is ±0.1 MPa, the suction temperature accuracy is ±2°C, the motor speed accuracy is ±200 r / min, and the input power accuracy is ±2 kW. According to the current industrial scene priority, adjust the smoothed compressor initial parameters according to the corresponding accuracy standards to generate a precision classification parameter set. The current is a precision manufacturing workshop (high priority), the initial parameter set exhaust pressure is 1.068 MPa, and the ±0.02 MPa accuracy is corrected to 1.07 MPa (retaining two decimal places, meeting the accuracy requirements). The remaining parameters are adjusted in the same way to form a precision classification parameter set.

[0031] Apply compressor operating parameter and process temperature threshold adaptation constraints to match and verify each parameter in the precision classification parameter set with the corresponding process temperature threshold of the industrial scene, eliminate abnormal parameters that exceed the adaptation range, and generate a threshold adaptation parameter set. According to the production process requirements of different industrial scenes, the corresponding process temperature threshold is determined, which is directly related to the reasonable range of compressor operating parameters. The process temperature threshold of the precision manufacturing workshop is 5-8°C, and the corresponding reasonable range of compressor operating parameters is: exhaust pressure 0.95-1.05 MPa, suction temperature 8-12°C, motor speed 3400-3800 r / min, input power 19-23 kW.

[0032] Parameter matching and verification and abnormality elimination: compare each parameter in the precision classification parameter set with the corresponding parameter reasonable range of the process temperature threshold of the current scene, if the parameter exceeds the range, it is determined as an abnormal parameter and is eliminated, the parameters within the reasonable range are retained, and a threshold adaptation parameter set is generated. The motor speed in the precision classification parameter set at a certain time is 3900 r / min, which exceeds the reasonable range of 3400-3800 r / min in the precision manufacturing workshop, and is determined as an abnormal parameter and is eliminated. The remaining parameters (exhaust pressure 1.07 MPa, suction temperature 10°C, input power 21.5 kW) are within the reasonable range and are retained to form a threshold adaptation parameter set.

[0033] The parameter collection frequency is increased under the constraint of high load working condition, the input power of the compressor and the heat dissipation power of the process equipment are monitored in real time, and a high-frequency collection parameter set under high load working condition is generated. The input power of the compressor and the heat dissipation power of the process equipment are monitored in real time, and a high-frequency collection parameter set under high load working condition is generated. The input power of the compressor is more than 80% of the rated power, or the heat dissipation power of the process equipment is more than 120% of the historical average heat dissipation power, the high load working condition is determined. The rated input power of the compressor is 30kW, 80% of the rated power is 24kW; the historical average heat dissipation power of the process equipment is 15kW, 120% of the historical average is 18kW; when the real-time monitoring of the input power of the compressor is 25kW (more than 24kW), or the heat dissipation power of the process equipment is 19kW (more than 18kW), it is determined that the high load working condition is entered.

[0034] Under non-high load working condition, the parameter collection frequency is 1 time / minute; after entering high load working condition, the collection frequency is automatically increased to 1 time / 10 seconds, the compressor operating parameters are collected in real time, and a high-frequency collection parameter set under high load working condition is generated. After determining that the high load working condition is entered, the collection frequency is adjusted from 1 time / minute to 1 set of parameters every 10 seconds, and the exhaust pressure is continuously collected to obtain 1.04MPa (10:00:00), 1.05MPa (10:00:10), 1.06MPa (10:00:20) and other data, forming a high-frequency collection parameter set.

[0035] Fusion threshold value adaptation parameter set and high-frequency collection parameter set, through parameter consistency verification, generate preprocessed compressor accurate operation data set. The threshold value adaptation parameter set (covering the accurate parameters under the conventional working condition) and the high-frequency collection parameter set (covering the high-frequency parameters under the high load working condition) are integrated, the data are aligned according to the time stamp, and the fused parameter set is formed. The threshold value adaptation parameters (exhaust pressure 1.07MPa, suction temperature 10℃) collected at 10:00 under the conventional working condition are integrated with the high-frequency parameters collected at 10:00:00-10:00:20 under the high load working condition, and a time-continuous parameter set is formed.

[0036] Verify the logic consistency of the parameters in the fused parameter set at the same time node or adjacent time node (such as the exhaust pressure and the input power should be positively correlated, and the suction temperature and the motor speed should be negatively correlated), if there are logical contradictory parameters (such as the exhaust pressure increases but the input power decreases), the abnormal data is removed and the reasonable data is supplemented, and finally the preprocessed compressor accurate operation data set is generated. It is found that the parameters at 10:00:15 have logical contradictions, the exhaust pressure is 1.08MPa (higher than the previous time) but the input power is 20kW (lower than the previous time 21kW), the data is removed, the interpolation of the previous and subsequent time parameters (exhaust pressure 1.075MPa, input power 21.2kW) is supplemented, and the accurate operation data set is formed.

[0037] S103, the pre-processed compressor operation data set and the hierarchical air supply system parameters are associated and processed, the parameter matching is realized by establishing a compressor speed-air supply amount coupling model, and a low-energy consumption collaborative control basic data mechanism is generated.

[0038] In an embodiment, the pre-processed compressor operation data set and the hierarchical air supply system parameters are standardized and integrated, the compressor and air supply associated data sequence is constructed, and the collaborative association basic data set is generated. The pre-processed compressor operation data set (including exhaust pressure, suction temperature, motor speed, input power) and the hierarchical air supply system parameters (including air supply temperature, air speed, air volume distribution ratio of each region) are standardized and processed respectively, and the influence of different parameter unit differences is eliminated. The "mean-standard deviation standardization" method is used to convert each parameter into standardized data with a mean of 0 and a standard deviation of 1. The mean of the pre-processed compressor motor speed of a certain precision manufacturing workshop is 3600 r / min, and the standard deviation is 200 r / min. The speed at a certain time is 3800 r / min, and the standardized data is (3800-3600) / 200=1. The air supply volume of the A region of the hierarchical air supply system has a mean of 2000 m³ / h and a standard deviation of 150 m³ / h. The air supply volume at a certain time is 2200 m³ / h, and the standardized data is (2200-2000) / 150≈1.33.

[0039] The standardized compressor parameters and air supply system parameters are aligned according to the time stamp, the associated data sequence of "time stamp-compressor standardized parameter-air supply system standardized parameter" is constructed, it is ensured that the two types of parameters at the same time node are one-to-one corresponding, and finally the collaborative association basic data set is generated. The associated data sequence corresponding to the time stamp "2025-10-2210:00:00" is: time stamp 10:00:00, compressor standardized exhaust pressure 0.8, standardized suction temperature-0.5, standardized motor speed 1, standardized input power 0.6; air supply system standardized A region air supply temperature-0.3, standardized A region air speed 0.4, standardized A region air volume distribution ratio 0.2, standardized B region air supply temperature 0.1, and the associated data sequence of all time nodes is integrated to form the collaborative association basic data set.

[0040] The compressor and the air supply associated basic data set is imported into the industrial low-temperature air conditioner energy consumption simulation software for simulation calculation, the refrigeration efficiency and energy consumption under different compressor speed and air supply combination are simulated, and multi-dimensional cooperative working condition simulation data is generated. Select the industrial low-temperature air conditioner special energy consumption simulation software (such as TRNSYS, EnergyPlus), the core parameter combination of "compressor speed-air supply" in the cooperative associated basic data set is selected as the input condition, the simulation boundary condition (such as workshop environment temperature and humidity, process temperature threshold, equipment running time) is set. Select TRNSYS software, set the simulation time to 24 hours, the workshop environment temperature is constant 28℃, the relative humidity is 50%, the process temperature threshold is 5-8℃, and the compressor speed (3400-3800r / min) and air supply (1800-2200m³ / h) combination data at different time nodes in the basic data set is imported.

[0041] The refrigeration efficiency (represented by refrigeration coefficient COP) and energy consumption (represented by hourly power consumption kW・h) under different "compressor speed-air supply" combinations are simulated by simulation software, the simulation results corresponding to each combination are recorded, and multi-dimensional cooperative working condition simulation data is generated. When the compressor speed is 3600r / min and the air supply is 2000m³ / h, the simulation results are COP 4.2 and hourly energy consumption 18kW・h; when the speed is 3800r / min and the air supply is 2200m³ / h, the COP is 4.0 and the hourly energy consumption is 22kW・h; when the speed is 3400r / min and the air supply is 1800m³ / h, the COP is 3.8 and the hourly energy consumption is 15kW・h, and the simulation results of all combinations are integrated into multi-dimensional cooperative working condition simulation data.

[0042] The multi-variable regression analysis algorithm is used to subdivide the matching relationship between the compressor speed and the air supply in the multi-dimensional cooperative working condition simulation data, and scene parameter matching data is generated. The multi-variable regression analysis algorithm decomposes the parameter correlation logic from the refrigeration demand, energy consumption cost and equipment load dimensions, and establishes a regression model for the parameter adaptation demand and energy consumption optimization target in different working conditions of high load stable period, low load fluctuation period and intermittent operation period. Based on the multi-dimensional cooperative working condition simulation data, "compressor speed" and "air supply" are used as independent variables, and "refrigeration efficiency (COP)" and "energy consumption" are used as dependent variables, and the parameter correlation logic is decomposed from three dimensions of refrigeration demand (COP minimum value meeting process temperature threshold), energy consumption cost (hourly energy consumption maximum value) and equipment load (80% of compressor rated load as upper limit).

[0043] The air conditioner operation is divided into high load stable period (process equipment full load operation, heat dissipation power exceeds 18 kW), low load fluctuation period (process equipment partial operation, heat dissipation power 12-18 kW), intermittent operation period (process equipment start-stop alternation, heat dissipation power is less than 12 kW), and a multivariate regression model is established for parameter adaptation requirements and energy consumption optimization targets in different working conditions. The high load stable period needs to meet COP ≥ 4.0, energy consumption ≤ 22 kW·h, and the regression model is "air supply volume = 0.5 × speed - 1600" (when the speed is 3600 r / min, the air supply volume = 0.5 × 3600 - 1600 = 200 m³ / h, corresponding to COP 4.2, energy consumption 18 kW·h, meeting the requirements); the low load fluctuation period needs COP ≥ 3.9, energy consumption ≤ 18 kW·h, and the regression model is "air supply volume = 0.4 × speed - 1240" (when the speed is 3400 r / min, the air supply volume = 0.4 × 3400 - 1240 = 120 m³ / h, corresponding to COP 3.9, energy consumption 16 kW·h); the intermittent operation period needs COP ≥ 3.8, energy consumption ≤ 15 kW·h, and the regression model is "air supply volume = 0.3 × speed - 900" (when the speed is 3400 r / min, the air supply volume = 0.3 × 3400 - 900 = 120 m³ / h, corresponding to COP 3.8, energy consumption 15 kW·h), and the regression models and parameter matching results of all working conditions are integrated into scene-based parameter matching data.

[0044] The characteristic parameters of compressor speed regulation response speed, air supply system air volume change delay time, and refrigeration capacity supply-demand balance threshold in different industrial scenes are collected, a scene-based collaborative characteristic library is constructed, and parameter collaborative constraint data is generated, wherein the scene-based collaborative characteristic library is customized according to the parameter adjustment accuracy requirement of precision manufacturing workshop, the air volume stability requirement of low-temperature warehouse workshop, and the energy consumption control requirement of ordinary industrial workshop. For different industrial scenes (precision manufacturing workshop, low-temperature warehouse workshop, and ordinary industrial workshop), three types of characteristic parameters are collected, including compressor speed regulation response speed (time from issuing an order to stabilizing the speed), air supply system air volume change delay time (time from issuing an order to stabilizing the air volume), and refrigeration capacity supply-demand balance threshold (matching error allowed range of refrigeration capacity and workshop heat dissipation power).

[0045] According to the scene requirement customization parameters, the scene-based collaborative characteristic library is constructed, and parameter collaborative constraint data is generated. The precision manufacturing workshop needs high-precision adjustment. The compressor speed regulation response speed collected is ≤2 seconds, the air supply system air volume change delay time is ≤3 seconds, and the refrigerating capacity supply-demand balance threshold is ±5%. The low-temperature warehouse workshop needs stable air volume. The speed regulation response speed collected is ≤3 seconds, the air volume change delay time is ≤2 seconds, and the refrigerating capacity supply-demand balance threshold is ±8%. The ordinary industrial workshop needs to prioritize energy consumption. The speed regulation response speed collected is ≤5 seconds, the air volume change delay time is ≤5 seconds, and the refrigerating capacity supply-demand balance threshold is ±10%. The characteristic parameters of all scenes are integrated into the scene-based collaborative characteristic library, and parameter collaborative constraint data is generated.

[0046] The scene-based parameter matching data and the parameter collaborative constraint data are fused, the compressor speed and the air supply volume coupling model is constructed, and the low-energy consumption collaborative control basic data mechanism is generated through model iterative optimization. The scene-based parameter matching data (including regression models and parameter combinations under different working conditions) and the parameter collaborative constraint data (including scene characteristic parameters) are fused. The compressor speed and the air supply volume coupling model is constructed with the target of "lowest energy consumption under the scene constraint condition". For the high-load stable period of the precision manufacturing workshop, the matching data "air supply volume = 0.5 × speed - 1600" and the constraint data "speed response ≤2 seconds, air volume delay ≤3 seconds, supply-demand threshold ±5%" are fused, and the coupling model is constructed as "air supply volume = 0.5 × speed - 1600, and speed regulation time ≤2 seconds, air volume regulation time ≤3 seconds, refrigerating capacity error ≤5%".

[0047] The accuracy of the coupling model is verified through historical operation data. If the parameter combination output by the model causes the energy consumption to exceed the simulation value or does not meet the constraint condition, the model coefficient is adjusted (such as correcting the coefficient 0.5 in the regression model to 0.48), and the iteration is repeated until the model error is ≤3%. The initial model outputs the speed 3600 r / min and the air supply volume 2000 m³ / h in the high-load period of the precision manufacturing workshop, and the actual running energy consumption is 19 kW·h (exceeding the simulation value 18 kW·h). The adjustment coefficient is 0.48, and the new model "air supply volume = 0.48 × speed - 1580". When the speed is 3600 r / min, the air supply volume = 0.48 × 3600 - 1580 = 1900 m³ / h, and the actual energy consumption is 18.2 kW·h (error 1.1%, meeting the requirements). The optimized coupling model and the corresponding parameter combination and constraint condition are integrated into the low-energy consumption collaborative control basic data mechanism.

[0048] S104, the collaborative data after the association processing is transmitted and optimized, the constraint and control instruction safety verification constraint information are applied based on the abnormal transmission state, and the collaborative data transmission system is generated.

[0049] In one embodiment, the transmission priority classification processing is performed on the associated processed collaborative data, and a collaborative data set with priority labels is generated according to the influence degree of the parameters on the air conditioner control. The data is divided into high, medium and low priority levels according to the influence degree of the collaborative data on the control of the industrial low-temperature air conditioner. The high-priority data is the key parameter that directly affects the safety and refrigeration effect of the equipment operation, the medium-priority data is the important parameter that affects the energy consumption optimization, and the low-priority data is the non-core parameter for auxiliary reference.

[0050] The priority of the associated processed collaborative data (including compressor speed, air supply, refrigeration efficiency, energy consumption value, and environmental temperature and humidity) is labeled one by one, and a collaborative data set with priority labels is formed. The compressor speed (which directly determines the refrigeration capacity and affects the process temperature stability) and the air supply (which is related to the refrigeration effect of the region) are labeled as high priority; the refrigeration efficiency coefficient (COP) and the hourly energy consumption value (which affect the energy saving target) are labeled as medium priority; and the workshop environmental temperature and humidity (which only assist in judging the load change) are labeled as low priority. All labeled data is integrated into a collaborative data set with priority labels.

[0051] The collaborative data set with priority labels and the transmission scenario are dynamically matched, a transmission strategy matrix is constructed by mapping the data priority in the row dimension and the transmission scenario in the column dimension, the matrix elements are calibrated combined with historical transmission stability data, and a dynamic transmission strategy matrix with scene attributes is generated. The transmission scenario is divided into three categories: normal transmission scenario (sufficient network bandwidth, delay ≤100ms), mild abnormal scenario (bandwidth fluctuation, delay 100-300ms), and severe abnormal scenario (insufficient bandwidth, delay >300ms); the data priority (high, medium, and low) is mapped in the row dimension, and the transmission scenario (normal, mild abnormal, and severe abnormal) is corresponded in the column dimension to construct an initial transmission strategy matrix, and the matrix elements are the initially determined transmission methods (such as real-time direct transmission for high-priority data in normal scenario).

[0052] Call the historical transmission stability data of different transmission scenarios in the past three months (such as the success rate of 98% of high-priority data direct transmission in normal scenarios, and the success rate of 95% of high-priority data compression transmission in mild abnormal scenarios), calibrate the initial matrix elements, and determine the optimal initial transmission mode of different priority data in each scenario. Generate a dynamic transmission strategy matrix with scene attributes. After calibration, the "high priority-normal scenario" element in the matrix is "real-time direct transmission, transmission interval 1 second", the "high priority-mild abnormal scenario" element is "LZ4 compression transmission, transmission interval 1 second", and the "high priority-severe abnormal scenario" element is "LZ4 compression + key frame priority transmission, transmission interval 2 seconds"; the "medium priority-normal scenario" element is "real-time direct transmission, transmission interval 5 seconds", the "medium priority-mild abnormal scenario" element is "GZIP compression transmission, transmission interval 5 seconds", and so on. Form a complete matrix.

[0053] The dynamic transmission strategy matrix and the abnormal transmission state judgment standard are calculated and processed cooperatively, the threshold comparison algorithm is used to operate the real-time transmission data, and the transmission state judgment result in each scene is generated. Different abnormal judgment thresholds are set for different transmission scenarios. In normal scenarios, transmission delay is more than 100 ms and data packet loss rate is more than 1% are judged as abnormal; in mild abnormal scenarios, delay is more than 300 ms and packet loss rate is more than 3% are judged as abnormal; in severe abnormal scenarios, delay is more than 500 ms and packet loss rate is more than 5% are judged as abnormal.

[0054] Real-time transmission data such as delay and packet loss rate are collected, compared with the judgment criteria of the dynamic transmission strategy matrix corresponding to the scene, and the transmission state judgment result (normal or abnormal) in each scene is generated. In the mild abnormal scenario, the real-time monitoring of the high-priority data transmission delay is 280 ms (not more than 300 ms threshold) and the packet loss rate is 2% (not more than 3% threshold). Through the threshold comparison algorithm, it is judged that the current transmission state in this scene is "normal". If the subsequent monitoring delay is 320 ms and the packet loss rate is 3.5%, it is judged as "abnormal".

[0055] The judgment result is compared and screened with the transmission constraint rules, and the transmission scheme set with the adaptation degree label is generated by eliminating the transmission scheme that does not meet the constraints and marking the rule adaptation degree. Two types of core constraint rules are set, one is parameter transmission constraint (data compression transmission is required in abnormal transmission state, and high-priority parameters are transmitted first), and the other is safety constraint (control instructions need to be attached with check code to prevent tampering).

[0056] The transmission state determination results in each scenario are compared with the constraint rules, transmission schemes that do not meet the constraints are removed, and the degree of adaptation is calculated according to the number of constraint clauses that meet the constraints / the total number of constraint clauses, and is marked on the reserved scheme to generate a set of transmission constraint candidate schemes with an adaptation label. In the mild abnormal scenario, a certain candidate scheme is "high-priority data direct transmission without compression, medium-priority data delayed transmission", which does not meet the "abnormal state data compression" constraint and is removed; another scheme is "high-priority data LZ4 compression priority transmission, medium-priority data GZIP compression transmission, control instruction with CRC32 check code", which meets all 2 constraint rules, and the adaptation degree is marked as "100%"; if a certain scheme only meets 1 constraint, the adaptation degree is marked as "50%", and finally the schemes with an adaptation degree of ≥80% are reserved to form a candidate set.

[0057] Based on the compression efficiency, transmission delay, and data integrity of the transmission constraint candidate scheme set, a genetic algorithm is used to optimize the combination, with low delay and high integrity as the optimization target, and the control instruction safety verification rule is integrated to generate the optimal transmission scheme that adapts to different transmission scenarios. With "low delay (target delay ≤200ms) + high integrity (target data integrity ≥99.5%)" as the core optimization target, and the compression efficiency (target compression ratio ≥2:1) as the auxiliary index, the control instruction safety verification rule (such as the instruction needs to pass RSA encryption + check code verification) is integrated.

[0058] Each scheme in the transmission constraint candidate scheme set is used as the initial population, and the delay, integrity, and compression efficiency are used as the fitness function, and the selection, crossover, and mutation operations of the genetic algorithm are iteratively optimized to finally generate the optimal transmission scheme that adapts to different transmission scenarios. For the mild abnormal scenario, the initial candidate scheme has "LZ4 compression transmission" with a delay of 180ms and an integrity of 99.2%, and "GZIP compression transmission" with a delay of 220ms and an integrity of 99.8%; after iterative optimization by the genetic algorithm, the advantages of the two are integrated to generate the optimal scheme of "high-priority data LZ4 compression (delay 170ms, integrity 99.6%), medium-priority data GZIP compression (delay 190ms, integrity 99.7%), control instruction with RSA encryption and CRC32 check", which meets the requirements of low delay, high integrity, and safety verification.

[0059] By integrating optimal transmission schemes and security verification mechanisms, a collaborative data transmission system covering the entire process from normal transmission to anomaly response and security verification is constructed. This system clarifies data transmission methods, constraint execution logic, and security verification processes for different scenarios, generating a collaborative data transmission system. The optimal transmission schemes for different scenarios (real-time direct transmission in normal scenarios, compressed transmission in minor anomaly scenarios, and compressed + prioritized transmission in severe anomaly scenarios) are integrated with security verification mechanisms (command encryption, data verification, and anomaly retries), clarifying the transmission process logic for each scenario.

[0060] This paper outlines the entire process of "normal transmission - abnormal response - security verification," clarifying the data transmission methods (e.g., high-priority data is transmitted directly every second in normal scenarios, and compressed data is transmitted in abnormal scenarios), the constraint execution logic (e.g., automatically switching compression algorithms when an abnormality is triggered), and the security verification process (e.g., verifying the checksum before executing the command). This ultimately generates a collaborative data transmission system covering the entire process. In normal transmission scenarios, high-priority data is transmitted directly in real-time at 1-second intervals, and control commands are accompanied by CRC32 verification. When a minor abnormality is triggered, the system automatically switches to LZ4 / GZIP compressed transmission while retaining the priority transmission logic for high-priority data. In severe abnormality scenarios, the high-priority data transmission interval is further shortened to 2 seconds, and only critical parameters are transmitted. In all scenarios, the command receiver must first verify the checksum; if verification fails, data retransmission is triggered, forming a complete collaborative data transmission system.

[0061] S105 performs visualization and fusion processing on the transmitted collaborative data, lays out the data display interface based on industrial scenario operation habits, and overlays real-time energy consumption monitoring curves, cooling efficiency coefficient and load matching index; applies constraints on data display accuracy and control response speed adaptation, and multi-region operating condition data partition display, and generates collaborative control data.

[0062] In one implementation, the transmitted collaborative data, industrial scenario operation habit parameters, and multi-region operating condition zoning information are extracted and processed to generate standardized data visualization components, regional operating condition mapping tables, and operation habit adaptation templates. The data types to be extracted and processed are clearly defined, including transmitted collaborative data (compressor speed, air volume, energy consumption value, cooling efficiency coefficient, etc.), industrial scenario operation habit parameters (the order in which maintenance personnel frequently view data and their interface interaction preferences), and multi-region operating condition zoning information (workshop area division and process requirements for each area).

[0063] The extracted data is standardized to generate three types of core achievements. The visualization styles of parameters such as compressor speed and air supply volume are unified into the form of "value + trend chart", and standardized data visualization components (such as circular speed instrument panel component, line energy consumption trend chart component) are generated; according to the format of "region number-region name-process temperature threshold-current working condition parameter", the information of precision manufacturing workshop A / B / C region and low-temperature warehouse workshop 1 / 2 region is sorted out, and the region working condition mapping table is generated; according to the operation habit of the operation and maintenance personnel "first look at core parameters (speed / air supply volume), then look at energy consumption index (energy consumption / COP), and finally look at environmental data", the layout order of the interface module is designed, and the operation habit adaptation template is generated.

[0064] The standardized data visualization components, region working condition mapping table, operation habit adaptation template and transmitted collaborative data are integrated, the data display interface is laid out based on the operation habit of the industrial scene, and the energy consumption real-time monitoring curve, refrigeration efficiency coefficient dynamic value and load matching degree trend chart are superimposed, to generate the intermediate visualization data set containing interface layout framework, core parameter visualization elements and multi-region working condition initial display data. The standardized data visualization components, region working condition mapping table and operation habit adaptation template are used as the basic framework, the transmitted collaborative data is embedded, the interface is laid out according to the operation habit of the industrial scene, and the key index visualization elements are superimposed.

[0065] Based on the operation habit adaptation template, the interface layout of the precision manufacturing workshop is set as "top core parameter area-middle energy consumption index area-bottom region working condition area"; the compressor speed instrument panel component (displaying real-time speed 3600r / min) and air supply volume value component (displaying real-time air supply volume 2000m³ / h) are embedded in the top core parameter area; the 24-hour energy consumption real-time monitoring curve (horizontal axis time, vertical axis energy consumption value, current 18kW・h is marked), refrigeration efficiency coefficient dynamic value (displaying COP 4.2) and load matching degree trend chart (horizontal axis time, vertical axis matching degree, current 92% is displayed) are superimposed in the middle energy consumption index area; according to the region working condition mapping table, the data such as A region air supply temperature 7℃ and B region air supply temperature 6.5℃ are displayed in the bottom region working condition area, and finally the intermediate visualization data set containing interface layout framework, core parameter visualization elements and multi-region working condition initial display data is formed.

[0066] Based on the data display precision requirement, control response speed standard and multi-region working condition data partition rule of the intermediate visualization data set, the abnormal data in the intermediate visualization data set is marked and screened to generate visualization abnormal record. The quality standard of the intermediate visualization data set is clarified, the data display precision requirement (compressor speed accuracy ±50r / min, energy consumption value accuracy ±0.1kW・h), control response speed standard (data refresh delay ≤1 second) and multi-region working condition data partition rule (each region data is independently displayed, and does not cross region confusion).

[0067] Compared with the intermediate visualization data and the set standard, the screening abnormal data is marked and the record is generated. The compressor speed in the intermediate data set is displayed as 3680 r / min (the actual calibrated value is 3600 r / min, exceeding the accuracy requirement of ±50 r / min), which is determined as an accuracy abnormality; the data refresh delay at a certain moment is up to 1.8 seconds (exceeding the response standard of 1 second), which is determined as a response delay abnormality; the data of the low-temperature warehouse workshop 1 area is misdisplayed in the precision manufacturing workshop B area plate, which is determined as a partition confusion abnormality; the abnormal type, abnormal data value, abnormal position, and influence range (such as the accuracy abnormality only affects the speed display, and the partition confusion affects the area working condition judgment) are arranged into a visualization abnormal record.

[0068] The intermediate visualization data set and the visualization abnormal record are checked and fused, the data display accuracy and the control response speed adaptation constraint, and the multi-area working condition data partition display constraint are applied, the abnormal data is corrected, and the interface layout is improved, and the collaborative control data is generated. The intermediate visualization data set and the visualization abnormal record are cross-checked to confirm the authenticity and influence degree of the abnormal data; then the data display accuracy and the control response speed adaptation constraint (such as optimizing the data rendering logic to reduce the refresh delay) and the multi-area working condition data partition display constraint (such as increasing the area data boundary identification) are applied to correct the abnormality and improve the interface.

[0069] For the speed accuracy abnormality, the display value 3680 r / min is corrected to 3600 r / min (consistent with the accuracy of ±50 r / min); for the response delay abnormality, the data fragmentation rendering technology is used to reduce the refresh delay to 0.6 seconds (satisfying the requirement of ≤1 second); for the partition confusion abnormality, the interface plate boundary is adjusted, and the attribution of each area is clearly marked; at the same time, the “abnormal data correction prompt” module (such as marking “the speed has been corrected, the original display deviation is 80 r / min”) is supplemented, and finally the collaborative control data containing the corrected visualization data, the improved interface layout, and the abnormal correction record is generated.

[0070] S106, the energy-saving control instruction issued by the control host and the collaborative control data are dynamically adapted and processed, the response delay characteristics of the magnetic suspension compressor and the staged air supply system are combined, the real-time staged energy-saving control instruction and the device collaborative operation information in different scenes are generated.

[0071] In an embodiment, the energy-saving control scenes are grouped based on classification dimensions of industrial scene type, air conditioner running stage and energy-saving target level to generate a scene grouping result. The three classification dimensions and corresponding subdivision rules are determined. The industrial scene type is divided into precision manufacturing workshop (high-precision temperature control required), low-temperature warehouse workshop (stable temperature control required) and ordinary industrial workshop (energy saving preferred) according to process requirements. The air conditioner running stage is divided into start-up stage (initial stage of device start-stop), stable running stage (constant load), load fluctuation stage (dynamic load change) and shutdown stage (before device shutdown) according to load change. The energy-saving target level is divided into basic energy-saving level (energy-saving rate 8%-12%), deep energy-saving level (energy-saving rate 13%-18%) and dynamic optimization level (energy-saving rate 19% or more) according to energy-saving rate requirements.

[0072] The energy-saving control scenes are grouped according to the combination logic of "industrial scene type-air conditioner running stage-energy-saving target level" to generate a scene grouping result. The combinations form scene groups such as "precision manufacturing workshop-stable running stage-deep energy-saving level", "low-temperature warehouse workshop-load fluctuation stage-basic energy-saving level" and "ordinary industrial workshop-stable running stage-dynamic optimization level". All combination results are integrated into the scene grouping result.

[0073] The random forest algorithm is used to screen and process key influence factors of the collaborative control data and the response delay characteristic parameters of the magnetic suspension compressor and the staged air supply system. Through classification and regression analysis of the characteristic variables by the algorithm, low-correlation factors are eliminated, and factors that play a core role in energy-saving control are retained to generate a key influence factor set. The input data of the random forest algorithm is determined, including collaborative control data (compressor speed, air supply amount, energy consumption value, refrigeration efficiency coefficient, etc.), and response delay characteristic parameters of the magnetic suspension compressor and the staged air supply system (compressor speed regulation delay time, air supply system air volume response period).

[0074] The input parameters are classified and regressed by the random forest algorithm to calculate the correlation degree (represented by feature importance value) of each parameter to the energy-saving control effect. Low-correlation factors with a feature importance value lower than 0.2 are eliminated, and high-correlation factors are retained to generate a key influence factor set. The calculation results show that the feature importance values of compressor speed (0.82), air supply amount (0.78), refrigeration efficiency coefficient (0.65) and compressor speed regulation delay time (0.52) are all higher than 0.2, and they are retained as core factors. The feature importance values of workshop environment temperature and humidity (0.15) and air supply system air volume response period (0.18) are lower than 0.2, and they are eliminated. Finally, a key influence factor set containing four core factors is generated.

[0075] The key influence factor set, energy-saving control instruction execution time limit, device operation load constraint and process temperature threshold standard information are data fused and processed to establish the association mapping relationship between each element and generate the fused feature data set. The data to be fused includes the key influence factor set (compressor speed, air supply, etc.), the energy-saving control instruction execution time limit (such as the instruction needs to be executed within 5 seconds), the device operation load constraint (such as the compressor load is not more than 85% of the rated load), and the process temperature threshold standard information (such as 5-8℃ in the precision manufacturing workshop).

[0076] The association mapping relationship between each data element (such as the compressor speed needs to match the process temperature threshold and the air supply needs to meet the device load constraint) is constructed and integrated to form the fused feature data set. For the “precision manufacturing workshop-stable operation stage-depth energy-saving level” scene group, the mapping relationship is established as “compressor speed 3400-3600r / min (matching 5-8℃ process threshold), air supply 1900-2100m³ / h (complying with the compressor load ≤85% constraint), instruction execution time limit ≤5 seconds, and refrigeration efficiency coefficient ≥4.0”. The mapping relationships of all scene groups are integrated into the fused feature data set.

[0077] Based on the fused feature data set, a personalized energy-saving control dynamic adaptation model is constructed, taking the scene grouping result as the input dimension of the model, the key influence factor as the core parameter, and the multiple constraint information as the boundary condition, to realize the personalized adaptation of the energy-saving control instruction in different scenes and generate real-time hierarchical energy-saving control instructions. Taking the scene grouping result as the input dimension (determining the model adaptation scene), the key influence factor as the core parameter (supporting model operation), and the multiple constraint information (execution time limit, load constraint, etc.) as the boundary condition, a personalized energy-saving control dynamic adaptation model is constructed, and the energy-saving control instruction adapted to different scenes is output through model operation.

[0078] For the “precision manufacturing workshop-stable operation stage-depth energy-saving level” scene group, the model takes the compressor speed and air supply as the core parameters, combines the “load ≤85%, instruction ≤5 seconds execution” constraint, and outputs the depth energy-saving instruction of “compressor speed 3500r / min, air supply 2000m³ / h”. For the “ordinary industrial workshop-stable operation stage-dynamic optimization level” scene group, the dynamic optimization instruction of “compressor speed 3200r / min, air supply 1800m³ / h” is output. The instructions of all scene groups are integrated into real-time hierarchical energy-saving control instructions.

[0079] According to the device cooperation requirements of different scenes, the operation flow of the real-time hierarchical energy-saving control instruction is disassembled, the device adjustment sequence, the parameter adjustment step and the abnormal response measures are determined, and scene-specific device cooperation operation information is generated. According to three dimensions of device adjustment sequence (compressor first, then air supply system or vice versa), parameter adjustment step (parameter change amount of each adjustment), and abnormal response measures (handling method when parameter exceeds limit), the real-time hierarchical energy-saving control instruction is disassembled.

[0080] For the "compressor speed 3300r / min, air supply volume 1950m³ / h" instruction of the "low-temperature warehouse workshop-load fluctuation stage-basic energy-saving level" scene group, the device adjustment sequence is "first reduce the compressor speed from the current 3500r / min to 3300r / min, and then reduce the air supply volume from 2100m³ / h to 1950m³ / h after the speed is stable (about 2 seconds, matching the response delay characteristic)"; the parameter adjustment step is "reduce the compressor speed by 50r / min each time, and reduce the air supply volume by 50m³ / h each time"; the abnormal response measure is "if the process temperature exceeds 8℃ (threshold upper limit) after adjustment, immediately adjust the compressor speed by 50r / min and the air supply volume by 50m³ / h", and the disassembly results of all scene groups are integrated into scene-specific device cooperation operation information.

[0081] In an embodiment, as shown in Figure 2 The energy-saving control device of the industrial low-temperature air conditioner comprises:

[0082] The acquisition module 201 is configured to acquire core operation data, load data and environmental data required for cooperative control of the industrial low-temperature air conditioner.

[0083] The processing module 202 is configured to perform dynamic calibration and fluctuation filtering on the magnetic suspension compressor parameters in the core operation data, perform hierarchical setting on the parameter precision based on the priority of the refrigeration demand of the industrial scene, apply constraint information such as parameter adaptation of the compressor operation parameter and the process temperature threshold, parameter collection frequency improvement under high load conditions, generate a pre-processed compressor accurate operation data set, perform collaborative correlation processing on the pre-processed compressor operation data set and the hierarchical air supply system parameters, realize parameter matching by establishing a compressor speed-air supply amount coupling model, generate a low-energy-consumption collaborative control basic data mechanism, perform transmission optimization on the collaborative data after correlation processing, apply constraint and control instruction safety verification constraint information such as data compression transmission and key parameter priority transmission under abnormal transmission state, generate a collaborative data transmission system, perform visual fusion processing on the collaborative data after transmission, layout a data display interface based on the operation habit of the industrial scene, and simultaneously superimpose real-time monitoring curves of energy consumption, refrigeration efficiency coefficient, and load matching degree index, apply constraints such as data display precision and control response speed adaptation and multi-region working condition data partition display, and generate collaborative control data, perform dynamic adaptation processing on the energy-saving control instructions and collaborative control data issued by the control host, combine the response delay characteristics of the magnetic suspension compressor and the hierarchical air supply system, and generate real-time hierarchical energy-saving control instructions and scene-specific device collaborative operation information.

[0084] The computer-readable storage medium provided by the above-mentioned embodiments of the present application and the energy-saving control method of the industrial low-temperature air conditioner provided by the embodiments of the present application have the same beneficial effects as the method adopted, run or implemented by the application program stored therein.

[0085] Each of the embodiments in the present application is described in a related manner, and the same or similar parts between the embodiments can be referred to each other. Each embodiment mainly describes the difference from other embodiments. In particular, the energy-saving control method of the industrial low-temperature air conditioner, the electronic device, the electronic equipment, and the readable storage medium are basically similar to the above-mentioned embodiments of the energy-saving control method of the industrial low-temperature air conditioner, so the description is relatively simple, and the relevant parts can be referred to the above-mentioned embodiments of the energy-saving control method of the industrial low-temperature air conditioner.

Claims

1. An energy-saving control method for industrial low-temperature air conditioning, characterized in that, include: Acquire the core operational data, load data, and environmental data required for the coordinated control of industrial cryogenic air conditioning; Dynamic calibration and fluctuation filtering are performed on the magnetic levitation compressor parameters in the core operating data. The parameter accuracy is set in a graded manner based on the priority of cooling demand in industrial scenarios. Constraint information such as the adaptation of compressor operating parameters to process temperature thresholds and the increase of parameter acquisition frequency under high load conditions are applied to generate a pre-processed accurate compressor operating dataset. The preprocessed compressor operation dataset is collaboratively correlated with the parameters of the staged air supply system. Parameter matching is achieved by establishing a compressor speed-air volume coupling model, thereby generating a low-energy collaborative control basic data mechanism. The collaborative data after association processing is optimized for transmission. Based on the constraints of data compression transmission and priority transmission of key parameters in abnormal transmission states, as well as the constraint information of security verification of control instructions, a collaborative data transmission system is generated. The transmitted collaborative data is visualized and fused, and the data display interface is laid out based on the operational habits of industrial scenarios. At the same time, real-time energy consumption monitoring curves, cooling efficiency coefficient and load matching index are superimposed. Constraints are applied to match the data display accuracy with the control response speed and to display multi-regional operating condition data in partitions to generate collaborative control data. The system dynamically adapts and processes energy-saving control commands and collaborative control data issued by the control host. Combining the response delay characteristics of the magnetic levitation compressor and the tiered air supply system, it generates real-time tiered energy-saving control commands and scenario-specific equipment collaborative operation information. This includes grouping energy-saving control scenarios based on industrial scenario type, air conditioning operation stage, and energy-saving target level, generating scenario grouping results. A random forest algorithm is used to screen key influencing factors in the collaborative control data and the response delay characteristic parameters of the magnetic levitation compressor and the tiered air supply system. Through classification and regression analysis of feature variables, low-correlation factors are eliminated, retaining factors that play a core role in energy-saving control, generating a set of key influencing factors. Finally, the set of key influencing factors is fused with energy-saving control command execution time limits, equipment operating load constraints, and process temperature threshold standards to establish correlation mapping relationships between various elements, generating a fused feature dataset. A personalized energy-saving control dynamic adaptation model is constructed based on a fusion feature dataset. The model uses scenario grouping results as the input dimension, key influencing factors as the core parameters, and multiple constraint information as boundary conditions to achieve personalized adaptation of energy-saving control commands under different scenarios and generate real-time hierarchical energy-saving control commands. Combining the equipment collaboration requirements of different scenarios, the operation process of the real-time hierarchical energy-saving control commands is decomposed to clarify the equipment adjustment sequence, parameter adjustment step size, and anomaly response measures, and generate equipment collaboration operation information for different scenarios.

2. The method as described in claim 1, characterized in that, Dynamic calibration and fluctuation filtering are performed on the magnetic levitation compressor parameters in the core operating data. Parameter accuracy is tiered based on the priority of cooling needs in industrial scenarios. Constraints are applied to adapt compressor operating parameters to process temperature thresholds and to increase the parameter acquisition frequency under high-load conditions. This generates a pre-processed, precise compressor operating dataset, including: Extract the original parameters of the magnetic levitation compressor from the core operating data, combine them with the historical operating parameter benchmark values ​​of industrial low temperature air conditioners, construct a dynamic parameter calibration model, and generate compressor parameter calibration benchmark data; The original parameters of the magnetic levitation compressor are subjected to fluctuation filtering. A sliding window filtering algorithm is used to identify abnormal fluctuation values ​​of parameters in real time. When the fluctuation amplitude exceeds the preset threshold, the filtering mechanism is automatically triggered to remove instantaneous interference data and generate the initial parameter set of the compressor. Based on the priority of cooling demand in industrial scenarios, the accuracy of the initial parameters of the stabilized compressor is set in a graded manner to generate a set of accuracy graded parameters. Apply the compressor operating parameters and process temperature threshold adaptation constraints, match and verify each parameter in the accuracy classification parameter set with the corresponding process temperature threshold of the industrial scenario, remove abnormal parameters that exceed the adaptation range, and generate a threshold adaptation parameter set; Apply constraints to increase the parameter acquisition frequency under high load conditions, monitor the compressor input power and the heat dissipation power of process equipment in real time, and generate a high-frequency acquisition parameter set under high load conditions; By fusing the threshold adaptation parameter set and the high-frequency acquisition parameter set, and through parameter consistency verification, a preprocessed accurate compressor operation dataset is generated.

3. The method as described in claim 1, characterized in that, The preprocessed compressor operation dataset is collaboratively correlated with the parameters of the staged air supply system. Parameter matching is achieved by establishing a compressor speed-air volume coupling model, generating a low-energy-consumption collaborative control basic data mechanism, including: The preprocessed compressor operation dataset is standardized and integrated with the parameters of the staged air supply system to construct a compressor-air supply association data sequence and generate a collaborative association basic dataset. Import the basic dataset of compressor and air supply association into industrial low temperature air conditioning energy consumption simulation software for simulation calculation, simulate the cooling efficiency and energy consumption under different combinations of compressor speed and air volume, and generate multi-dimensional collaborative working condition simulation data. Multivariate regression analysis algorithm is used to subdivide the matching relationship between compressor speed and air volume in multidimensional collaborative working condition simulation data, and generate scenario-based parameter matching data. Among them, the multivariate regression analysis algorithm decomposes the parameter association logic from the dimensions of cooling demand, energy consumption cost and equipment load, and establishes regression models for parameter adaptation requirements and energy consumption optimization objectives for different working conditions such as high load stable period, low load fluctuating period and intermittent operation period. The system collects characteristic parameters such as compressor speed adjustment response speed, air volume change delay time of air supply system, and cooling capacity supply and demand balance threshold under different industrial scenarios, constructs a scenario-based collaborative characteristic library, and generates parameter collaborative constraint data. Among them, the scenario-based collaborative characteristic library customizes parameters for the parameter adjustment accuracy requirements of precision manufacturing workshops, the air volume stability requirements of low temperature storage workshops, and the energy consumption control requirements of general industrial workshops. By integrating scenario-based parameter matching data and parameter coordination constraint data, a coupled model of compressor speed and air volume is constructed. Through iterative optimization of the model, a basic data mechanism for low-energy collaborative control is generated.

4. The method as described in claim 1, characterized in that, The collaborative data after correlation processing is optimized for transmission. Based on constraints such as data compression transmission and priority transmission of key parameters during abnormal transmission states, as well as constraints on the security verification of control instructions, a collaborative data transmission system is generated, including: The collaborative data after association processing is prioritized for transmission, and a collaborative data set with priority labels is generated based on the degree of influence of parameters on air conditioning control. The collaborative data set with priority labels is dynamically matched with the transmission scenario. The data priority is mapped by row dimension and the transmission scenario is corresponding to column dimension to construct a transmission strategy matrix. The matrix elements are calibrated by combining historical transmission stability data to generate a dynamic transmission strategy matrix with scenario attributes. The dynamic transmission strategy matrix and the abnormal transmission status judgment criteria are jointly calculated and processed. The threshold comparison algorithm is used to calculate the real-time transmission data and generate the transmission status judgment results for each scenario. The judgment results are compared and filtered with the transmission constraint rules. Transmission schemes that do not meet the constraints are eliminated and the rule fit is marked to generate a set of candidate transmission constraint schemes with fit labels. Combining and optimizing compression efficiency, transmission latency, and data integrity based on the candidate scheme set with transmission constraints, a genetic algorithm is used to find the optimal solution with low latency and high integrity as the goal, while incorporating control command security verification rules to generate the optimal transmission scheme that is suitable for different transmission scenarios. By integrating the optimal transmission scheme and security verification mechanism, a collaborative data transmission system covering the entire process of normal transmission, abnormal response, and security verification is constructed. The data transmission methods, constraint execution logic, and security verification process under different scenarios are clarified, and a collaborative data transmission system is generated.

5. The method as described in claim 1, characterized in that, The transmitted collaborative data undergoes visual fusion processing. The data display interface is laid out based on industrial scenario operating habits, while overlaying real-time energy consumption monitoring curves, cooling efficiency coefficients, and load matching indicators. Constraints are applied to match data display accuracy with control response speed and to partition data across multiple operating areas, generating collaborative control data, including: Extract and process the transmitted collaborative data, industrial scenario operation habit parameters, and multi-regional working condition zoning information to generate standardized data visualization components, regional working condition mapping tables, and operation habit adaptation templates. The standardized data visualization components, regional operating condition mapping tables, operation habit adaptation templates and transmitted collaborative data are integrated. The data display interface is laid out based on the operation habits of industrial scenarios. At the same time, real-time energy consumption monitoring curves, dynamic values ​​of cooling efficiency coefficients and load matching degree trend charts are overlaid to generate an intermediate visualization dataset that includes an interface layout framework, core parameter visualization elements and initial display data of multi-region operating conditions. Based on the data display accuracy requirements, control response speed standards, and multi-region operating condition data partitioning rules of the intermediate visualization dataset, abnormal data in the intermediate visualization dataset is marked and filtered to generate visualized abnormal records. The intermediate visualization dataset and visualization anomaly records are verified and merged. Constraints are applied on the matching of data display accuracy and control response speed, and constraints on the partitioned display of multi-region operating condition data. Abnormal data is corrected and the interface layout is improved to generate collaborative control data.

6. An energy-saving control device for an industrial low-temperature air conditioner, characterized in that, The apparatus for implementing the method of claim 1 includes: The acquisition module is used to acquire the core operating data, load data, and environmental data required for the collaborative control of industrial cryogenic air conditioning. The processing module dynamically calibrates and filters fluctuations in the magnetic levitation compressor parameters from the core operational data. It prioritizes parameter accuracy based on the cooling needs of industrial scenarios, applies constraints to adapt compressor operating parameters to process temperature thresholds, and increases parameter acquisition frequency under high-load conditions, generating a pre-processed, precise compressor operation dataset. It then performs collaborative correlation processing between the pre-processed compressor operation dataset and the parameters of the tiered air supply system, achieving parameter matching by establishing a compressor speed-airflow coupling model, and generating a low-energy-consumption collaborative control basic data mechanism. Finally, it optimizes the transmission of the correlated collaborative data, applying data compression during abnormal transmission states. The system prioritizes the transmission of key parameters and verifies the security of control commands to generate a collaborative data transmission system. It then performs visual fusion processing on the transmitted collaborative data, designing a data display interface based on industrial operating habits, while overlaying real-time energy consumption monitoring curves, cooling efficiency coefficients, and load matching indicators. Constraints are applied to match data display accuracy with control response speed and to partition data across multiple operating areas, generating collaborative control data. Finally, it dynamically adapts energy-saving control commands issued by the control host to the collaborative control data, combining the response delay characteristics of the magnetic levitation compressor and the staged air supply system to generate real-time, staged energy-saving control commands and scenario-specific equipment collaborative operation information.

7. An electronic device, characterized in that, include: First processor; and memory for storing executable instructions of the first processor; The first processor is configured to execute the energy-saving control method of the industrial cryogenic air conditioner according to any one of claims 1 to 5 by executing the executable instructions.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the second processor, it implements the energy-saving control method of the industrial low-temperature air conditioner according to any one of claims 1 to 5.

Images