A load prediction-based energy-saving cooperative control method for a magnetic suspension air compressor

Abstract

The present application provides a kind of magnetic suspension air compressor energy-saving collaborative control method based on load prediction, the present application includes: acquisition compressor group during operation process multi-source operation data;According to the multi-source operation data and production plan information, the load demand of compressed air system in future period is predicted;According to the load demand, the compression parameters of compressor and the operating parameters of magnetic suspension bearing are adjusted;In the process of adjusting the compression parameters of the compressor, the cooling parameters of the cooling system are adjusted to balance the compression heat and cooling energy consumption.In power plant application, system realizes comprehensive energy saving 10.5%, exhaust pressure fluctuation ≤±0.08bar, maintenance efficiency is improved by 40%, significantly release magnetic suspension air compressor energy-saving potential, applicable to high energy consumption industrial scene such as thermal power, chemical industry, medicine etc..

Description

Technical Field

[0001] This invention relates to the field of intelligent control technology for air compression equipment, and in particular to an energy-saving and coordinated control method for a magnetic levitation air compressor based on load prediction. Background Technology

[0002] Magnetic levitation air compressors, as important energy-saving equipment in industrial compressed air systems, are widely used in high-energy-consuming scenarios with stable air pressure requirements of 7 bar or higher, such as thermal power, sewage treatment, papermaking, and pharmaceutical and chemical industries. Among related technologies, core technologies such as contactless operation of magnetic levitation bearings and direct drive by high-speed permanent magnet motors have constructed a collaborative operating system for the compressor, cooling system, and intake filtration system. Specifically, this technology covers the entire process from load monitoring and pressure ratio distribution to temperature control, including key aspects such as pressure feedback regulation, bearing displacement correction, and cooling energy consumption management. With the improvement of industrial automation, the "constant speed + constant pressure valve overflow" control mode used in traditional oil-free screw compressors is no longer sufficient to meet the energy efficiency optimization requirements. While magnetic levitation technology can reduce no-load energy consumption by more than 30%, its control method still has systemic defects.

[0003] However, existing magnetic levitation air compressor control methods directly adopt factory-preset pressure ratio distribution and constant speed without establishing a dynamic adaptation mechanism with load rate. This may lead to "overcompression" under low load conditions, causing the compressor's variable efficiency to drop from the design value of 78% to 70%-72%. Specifically, existing technologies typically employ independent control modes, lacking coordinated operation between the compressor, cooling system, and intake filtration system. For example, when the intake air temperature rises, it relies solely on the cooling system for passive heat dissipation without synchronously adjusting compression parameters, resulting in an increase in cooling energy consumption of 1.2 kW / h. Consequently, when the load changes abruptly, the existing "pressure feedback-hysteresis adjustment" mechanism exhibits a pressure fluctuation range of ±0.3 bar, requiring additional energy consumption to maintain system stability. Furthermore, these technologies do not correlate potential faults such as filter blockage with abnormal energy consumption, causing fault warnings to lag behind the energy efficiency degradation process, ultimately leading to shortened equipment lifespan and increased maintenance costs. Summary of the Invention

[0004] The present invention aims to at least partially solve one of the technical problems in the related art.

[0005] Therefore, the first objective of this invention is to propose an energy-saving collaborative control method for magnetic levitation air compressors based on load prediction.

[0006] Another objective of this invention is to propose an energy-saving collaborative control device for a magnetic levitation air compressor based on load prediction.

[0007] The third objective of this invention is to provide a computer device.

[0008] A fourth objective of this invention is to provide a non-transitory computer-readable storage medium.

[0009] To achieve the above objectives, a first aspect of the present invention proposes an energy-saving coordinated control method for a magnetic levitation air compressor based on load prediction, comprising:

[0010] S1 collects multi-source operating data during the operation of the compressor unit; S2, based on the multi-source operating data and production plan information, predict the load demand of the compressed air system in the future period; S3, adjust the compression parameters of the compressor and the operating parameters of the magnetic levitation bearing according to the load requirements; S4. During the process of adjusting the compression parameters of the compressor, the cooling parameters of the cooling system are adjusted in coordination to balance the compression heat and cooling energy consumption.

[0011] In one embodiment of the present invention, predicting the load demand of the compressed air system in future time periods includes: Extract load-related time features, operating condition features, and production features from historical operating data, and train the prediction model based on these features; The multi-source operational data and production planning information are input into the trained prediction model to obtain prediction results for future loads.

[0012] In one embodiment of the present invention, the step of dynamically adjusting the compression parameters of the compressor and the operating parameters of the magnetic levitation bearing according to the load demand includes: When the load demand is lower than the set threshold, reduce the compressor's compression ratio and / or speed, and reduce the electromagnetic force output of the magnetic levitation bearing; When the load demand exceeds the set threshold, increase the compressor's compression ratio and / or speed, and increase the displacement control frequency of the magnetic levitation bearing.

[0013] In one embodiment of the present invention, the cooling parameters of the collaboratively regulating cooling system include: Monitor the compressor's exhaust temperature; When the exhaust temperature exceeds a preset threshold, the cooling capacity of the air-cooling system is increased first. If the exhaust temperature still exceeds the threshold after the cooling capacity of the air-cooled system reaches its upper limit, the cooling capacity of the water-cooled system will be activated and adjusted.

[0014] In one embodiment of the present invention, the step of collecting multi-source operating data during the operation of the compressor unit further includes: Based on the multi-source operating data, the deviation between the actual energy consumption of the compressor and the theoretical energy consumption benchmark is analyzed. When the deviation exceeds the preset range, an energy consumption anomaly is determined, and the cause of the anomaly is located based on the multi-source operation data.

[0015] To achieve the above objectives, a second aspect of the present invention provides an energy-saving collaborative control device for a magnetic levitation air compressor based on load prediction, comprising: The multi-source data acquisition module is used to collect multi-source operating data during the operation of the compressor unit; The load prediction and calculation module is used to predict the load demand of the compressed air system in future periods based on the multi-source operating data and production plan information. The dynamic adjustment and control module is used to adjust the compression parameters of the compressor and the operating parameters of the magnetic levitation bearing according to the load requirements. The cooling parameter coordination adjustment module is used to coordinately adjust the cooling parameters of the cooling system during the adjustment of the compressor's compression parameters in order to balance compression heat and cooling energy consumption.

[0016] The present invention discloses an energy-saving collaborative control method and device for a magnetic levitation air compressor based on load prediction, which can realize dynamic adaptation and adjustment of compression parameters and magnetic levitation bearings, effectively eliminate over-compression phenomenon under low load, improve variable efficiency and reduce energy consumption, while enhancing pressure stability and fault prediction capability, and significantly improve the operating energy efficiency of the magnetic levitation air compressor under 7 bar conditions.

[0017] To achieve the above objectives, a third aspect of this application provides a computer device comprising a processor and a memory; wherein the processor runs a program corresponding to the executable program code stored in the memory, for implementing a load-prediction-based energy-saving coordinated control method for a magnetic levitation air compressor as described in the first aspect embodiment.

[0018] To achieve the above objectives, a fourth aspect of this application provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements an energy-saving coordinated control method for a magnetic levitation air compressor based on load prediction as described in the first aspect embodiment.

[0019] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0020] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1This is a flowchart of an energy-saving collaborative control method for a magnetic levitation air compressor based on load prediction, according to an embodiment of the present invention. Figure 2 This is an overall architecture diagram of the intelligent control method according to an embodiment of the present invention; Figure 3 This is a structural diagram of an energy-saving collaborative control device for a magnetic levitation air compressor based on load prediction, according to an embodiment of the present invention. Figure 4 It is a computer device according to an embodiment of the present invention. Detailed Implementation

[0021] It should be noted that, unless otherwise specified, the embodiments and features described in the present invention can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0022] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0023] The following description, with reference to the accompanying drawings, describes an energy-saving collaborative control method and apparatus for a magnetic levitation air compressor based on load prediction, according to an embodiment of the present invention.

[0024] Example 1 Figure 1 This is a flowchart of an energy-saving coordinated control method for a magnetic levitation air compressor based on load prediction, according to an embodiment of the present invention. Figure 1 As shown, it includes: S1 collects multi-source operating data during the operation of the compressor unit.

[0025] Specifically, in this invention, collecting multi-source real-time data during compressor operation is a fundamental step in achieving intelligent control and energy-saving optimization. This step involves using a sensor array deployed on the compressor to acquire real-time operating parameters including temperature, pressure, flow rate, and filter differential pressure at the intake end; inlet and outlet temperatures and pressures at each stage of the compression process; cooling water temperature, airflow, and pump power of the cooling system; and displacement, vibration, motor current, voltage, speed, and temperature of the magnetic levitation bearing.

[0026] Furthermore, this data acquisition system adopts a distributed sensing architecture. Each sensor connects to the PLC control unit via a standard industrial communication protocol, achieving high-speed, low-latency data transmission. The intake temperature sensor is typically a PT100 type, with an accuracy of ±0.3℃; the pressure sensor uses a high-precision absolute pressure sensor, covering a range of 0~10 bar, with an accuracy of ±0.5%FS; the flow sensor is a vortex or ultrasonic type, suitable for gaseous media, with a measurement accuracy of ±1.5%. The filter differential pressure sensor is used to monitor the degree of clogging of the intake filter, with a range of 0~2000Pa and an accuracy of ±2%FS.

[0027] Furthermore, temperature and pressure sensors at the inlet and outlet of each stage of the compression process are arranged before and after each compression chamber to monitor the thermodynamic state in real time during compression. For the cooling system, cooling water temperature sensors are located at the cooling water inlet and outlet, and the airflow sensor is a hot-wire or ultrasonic anemometer with an accuracy of ±2%. The water pump power is acquired via a frequency converter output signal with an accuracy of ±1%. Monitoring parameters for the magnetic levitation bearing include displacement sensors (eddy current type, accuracy ±1μm), vibration sensors (acceleration type, range 0~10g, accuracy ±0.5%), motor current and voltage sensors (Hall effect or shunt type, accuracy ±0.2%), speed sensors (photoelectric encoder or magnetoelectric type, accuracy ±0.1%), and temperature sensors (PT100 or thermocouple, accuracy ±0.5℃).

[0028] Furthermore, this step requires all sensor data acquisition frequencies to be no less than 1Hz to ensure the system's responsiveness to dynamic changes. The data undergoes preprocessing via a PLC control unit, including filtering, normalization, and outlier removal, to improve the quality of subsequent model input data. The acquired data will serve as input features for the LSTM load prediction model and will also be used to determine the compressor's operating status and fault trends in real time.

[0029] Furthermore, this step is applicable to magnetic levitation air compressor systems with pressure ratings above 7 bar, especially in industrial environments such as thermal power, wastewater treatment, papermaking, and pharmaceuticals / chemicals where compressed air demand fluctuates significantly and energy consumption is sensitive. Through real-time acquisition of multi-source data, the system can accurately reflect the compressor's operating characteristics under different load conditions, providing reliable data support for subsequent load prediction, parameter adjustment, coordinated control, and fault early warning.

[0030] Furthermore, this step enables comprehensive perception of the compressor's operating status, providing real-time feedback for dynamic control strategies. Through high-precision, high-frequency data acquisition, the system can effectively identify efficiency declines, changes in cooling demand, and potential fault signals during the compression process, thereby significantly improving control accuracy and energy-saving effects. For example, in the early stages of filter clogging, the differential pressure sensor can detect abnormal trends, providing early warning for subsequent maintenance scheduling and preventing increased energy consumption due to blockage. In addition, the displacement and vibration data of the magnetic levitation bearing can reflect the rotor status in real time, providing input for dynamic adjustment of electromagnetic force and further reducing bearing energy consumption.

[0031] S2, based on the multi-source operating data and production plan information, predict the load demand of the compressed air system in the future period.

[0032] Specifically, in some implementations, based on multi-source real-time data and production planning information, a long short-term memory neural network (LSTM) model is used to predict the intake flow rate for the next hour and calculate the corresponding load rate. By integrating real-time operating parameters and production scheduling information, a predictive model with time-series memory capability is constructed, thereby providing data support for subsequent dynamic parameter adjustment and system collaborative control.

[0033] Furthermore, the input features of the LSTM model include time features (such as current hour, weekday / holiday identification, production shift status), operating condition features (such as intake air temperature, pressure, flow rate, and outlet pressure), and production plan features (such as production line start / stop status and production cycle time). The model makes a prediction every 10 minutes, taking the current time, real-time operating condition data, and production plan information for the next hour as input, and outputting the predicted average intake air flow rate for the next hour.

[0034] Furthermore, the model training uses historical operating data from the previous two months as the training set. By adjusting hyperparameters such as the number of hidden layer nodes, learning rate, and training epochs of the LSTM, the prediction error is controlled within 5%. In actual operation, the prediction error is typically 4.2%, meeting the accuracy requirements of industrial control. The calculated load rate will serve as the basis for adjusting compression parameters, and its accuracy directly affects the execution effect of subsequent control strategies.

[0035] Furthermore, this step is applicable to industrial scenarios with stable demand for compressed air above 7 bar, such as conventional thermal power, wastewater treatment, papermaking, and pharmaceutical and chemical industries. By predicting load changes one hour in advance, the system can reduce the compressor speed and pressure ratio before the load decreases to avoid overcompression; and increase operating parameters in advance before the load increases to ensure pressure stability and reduce the sudden increase in energy consumption caused by adjustment lag.

[0036] Furthermore, this step enables proactive judgment of the compressor's operating status, providing a time margin for adjusting compression parameters and thus significantly reducing ineffective energy consumption. Combined with the production planning forecasting mechanism, the 7-bar discharge pressure fluctuation can be controlled within... This improves system stability. Simultaneously, the predictive model provides a data foundation for subsequent fault prediction and maintenance scheduling, contributing to the intelligent and refined control of the compression system.

[0037] S3, adjust the compression parameters of the compressor and the operating parameters of the magnetic levitation bearing according to the load requirements.

[0038] Specifically, this step involves multi-parameter coordinated adjustment of the compressor based on load rate. Its technical implementation principle is based on the dynamic optimization of key operating parameters of the compression system (pressure ratio, motor speed, electromagnetic force of magnetic levitation bearing) to match real-time load demand, thereby reducing ineffective energy consumption and improving the overall energy efficiency of the system while ensuring stable exhaust pressure.

[0039] Furthermore, this step involves the PLC control unit receiving the load rate signal output from the LSTM load prediction model and making real-time decisions based on the current compressor operating status (such as intake flow rate, outlet pressure, motor speed, etc.). When the load rate falls below a set threshold (e.g., 50%), the system will reduce the pressure ratio distribution of each compression stage of the compressor, for example, by changing the original fixed pressure ratio. , , The pressure ratio combination will be adjusted to a lower value to avoid energy waste caused by over-compression. Simultaneously, the motor speed will be reduced according to a gradient adjustment strategy, with the rate of change controlled within a certain range. This is to prevent mechanical vibration and system instability caused by sudden changes in rotational speed.

[0040] Furthermore, the electromagnetic force output of the magnetic levitation bearing will also be reduced accordingly. Under low-load conditions, the accuracy requirements for bearing displacement control are relatively relaxed, so the electromagnetic force output can be appropriately reduced, thereby reducing the power consumption of the bearing system. Under high-load conditions, the system increases the compression stage pressure ratio and motor speed to meet higher air output demands, and maintains the control accuracy of the magnetic levitation system by increasing the bearing displacement correction frequency (e.g., from once per second to three times per second), preventing the displacement deviation from expanding due to increased load.

[0041] Furthermore, this step has broad application value in practical industrial scenarios, especially suitable for applications such as thermal power, sewage treatment, and pharmaceutical and chemical industries where compressed air demand fluctuates significantly and energy consumption is sensitive. By dynamically adjusting compression parameters, the system can respond quickly to load changes, avoiding the ineffective energy consumption caused by constant speed operation and lagging adjustment in traditional control methods.

[0042] Furthermore, this step significantly improves the compressor's variable efficiency, reduces no-load energy consumption at low loads, and decreases overclocking time under high loads. In practice, this method reduces energy consumption by approximately 13.79% under low load conditions and 6.25% under full load conditions, achieving a comprehensive energy saving effect of 10.5%. In addition, through coordinated control of pressure ratio and speed, the exhaust pressure fluctuation range is reduced from ±0.25 bar to ±0.08 bar, significantly improving system stability and control accuracy.

[0043] S4. During the process of adjusting the compression parameters of the compressor, the cooling parameters of the cooling system are adjusted in coordination to balance the compression heat and cooling energy consumption.

[0044] Specifically, the steps of this invention achieve a dynamic balance between compression heat and cooling energy consumption by limiting the rate of change of motor speed to no more than a preset gradient threshold and combining this with a coordinated strategy of "air cooling priority and water cooling assistance" in the cooling system. This ensures that the variable efficiency of the compressor is not lower than the preset target value. This step is a key link in the entire control method to achieve system stability and energy efficiency optimization.

[0045] Furthermore, the motor speed regulation employs a rate limiting mechanism, meaning that at any given moment, the rate of change of speed is limited. This limitation is implemented through the speed regulation module in the PLC control unit. Specifically, upon receiving a new target speed command, the system first calculates the difference between the current speed and the target speed, and then determines whether the gradient threshold is met based on the time interval. If not, linear interpolation is used to gradually adjust the speed, avoiding increased mechanical vibration and motor energy consumption fluctuations caused by sudden speed changes. This mechanism effectively suppresses the dynamic response oscillations of the compressor during load changes, improving the stability of system operation.

[0046] Furthermore, the coordinated control strategy of the cooling system is based on the exhaust temperature threshold setting, for example, if the exhaust temperature of a certain stage exceeds... When doing so, prioritize increasing the air-cooled fan speed; for every increase... Exhaust temperature is controlled, and fan speed is increased by 5%. If the temperature still cannot be controlled within the threshold after the fan runs at full speed, the water cooling system is activated. By adjusting the water pump speed to control the cooling water flow, the temperature is further reduced. This strategy ensures compressor efficiency through a parameter linkage correction mechanism. This also reduces the overall energy consumption of the cooling system.

[0047] Furthermore, this step is applicable to magnetic levitation air compressor systems with pressure ratings above 7 bar, especially in industrial scenarios with frequent load fluctuations (such as thermal power, wastewater treatment, and pharmaceutical and chemical industries), where it can effectively address the contradiction between compression heat accumulation and cooling system response lag. By dynamically adjusting cooling parameters, the system avoids overheating shutdown under high loads and reduces unnecessary cooling energy consumption under low loads, thereby achieving a balance between compressor operating efficiency and energy-saving goals.

[0048] Furthermore, the technical benefits of this step are reflected in the stable control of the compressor's variable efficiency. By limiting the rate of change of rotational speed and coordinating with the cooling system, the system can respond quickly to load changes and maintain the thermodynamic efficiency of the compression process, avoiding efficiency drops caused by over-compression or insufficient cooling. Experimental data show that this strategy can keep the compressor's variable efficiency above 78% under 7 bar conditions, an improvement of 6%-8% compared to traditional control methods, significantly enhancing the energy-saving performance and operational reliability of the magnetic levitation compressor.

[0049] The energy-saving and coordinated control method for the magnetic levitation air compressor of this invention can effectively reduce the energy consumption of the magnetic levitation air compressor under operating conditions above 7 bar, improve pressure stability and extend the service life of the equipment, and achieve coordinated control of energy saving and high efficiency.

[0050] Example 2 This invention aims to solve the problems of "high energy consumption due to load fluctuations, insufficient multi-system coordination, poor pressure stability, and increased energy consumption due to faults" in the control of existing 7bar magnetic levitation air compressors, and provides an intelligent control system for 7bar magnetic levitation air compressors oriented towards energy-saving operation, such as... Figure 2 As shown: Specifically, the compression parameters and magnetic levitation bearing parameters are dynamically adjusted to adapt to load changes and avoid over-compression; The compressor unit and cooling system work together to reduce cooling energy consumption and maintain compression efficiency; the load is predicted in conjunction with the production plan, and parameters are adjusted in advance to reduce pressure fluctuations and sudden increases in energy consumption; potential faults are predicted based on abnormal energy consumption to avoid long-term energy waste and equipment damage.

[0051] This invention relates to an energy-saving and coordinated control method for magnetic levitation air compressors based on load prediction. The method aims to address technical problems such as lack of load adaptability and high energy consumption caused by disjointed control of multiple systems during the operation of magnetic levitation air compressors. It achieves energy-efficient operation of the compressor system through an integrated approach of multi-source data acquisition, load demand prediction, dynamic adjustment of multi-component parameters, and coordinated control of the cooling system. The method first comprehensively collects multi-source operating data throughout the entire compressor unit operation process, acquiring various parameters reflecting the unit's intake, compression, cooling, and core component operating status. Then, combining the collected multi-source operating data with production plan information, it predicts the load demand of the compressed air system for future periods, providing a forward-looking basis for subsequent parameter adjustments. Subsequently, based on the predicted load demand, it specifically adjusts the compressor's compression parameters and the magnetic levitation bearing's operating parameters to achieve dynamic adaptation between operating parameters and load demand. The adjustment of compression parameters is based on the compression ratio. The core control parameters are rotational speed n and electromagnetic force F and displacement control frequency f for magnetic levitation bearings. Finally, during the adjustment of compressor compression parameters, the cooling parameters of the cooling system are simultaneously and collaboratively adjusted using the heat balance formula. This method achieves a dynamic balance between the heat of compression generated during the compression process and the cooling energy consumption of the cooling system, avoiding energy loss caused by unilateral adjustment. As one implementation method, this approach can be applied to magnetic levitation air compressors with pressure ratings above 7 bar. Load prediction is achieved through an LSTM model, combined with a load rate threshold. Adjust the compressor pressure ratio, speed, electromagnetic force of the magnetic levitation bearing, and displacement control frequency, and adjust the cooling parameters by using air cooling as the priority and water cooling as the auxiliary method.

[0052] Furthermore, when forecasting the load demand of the compressed air system in the future, the time characteristics, operating condition characteristics, and production characteristics related to the load are first comprehensively extracted from the historical operating data of the compressor. The time characteristics include dimensions such as operating time, weekday and holiday attributes, and production shifts, while the operating condition characteristics include intake air temperature. ,pressure ,flow The operating parameters of the generating units are used, while the production characteristics are parameters related to the compressed air demand in the production process. These extracted characteristics are then used as the training basis to train and optimize the load prediction model, ensuring that the model's prediction error meets the requirements. To ensure the model has accurate load prediction capabilities, after the prediction model is trained, real-time collected multi-source operating data of the compressor unit and actual production plan information are input into the trained prediction model. Through the model's calculation and processing, the predicted value of the compressed air system's intake flow rate for future periods is directly obtained, and then calculated using the load rate formula. The calculated load demand prediction results provide data support for subsequent parameter adjustments. After the model training is completed, the hyperparameters can be continuously optimized according to the actual operating conditions to ensure that the prediction accuracy always meets the requirements of industrial control.

[0053] Furthermore, when dynamically adjusting the compressor's compression parameters and the magnetic levitation bearing's operating parameters according to load demand, a clear threshold range is first set for the compressed air system's load demand. When the predicted load rate is monitored Simultaneously, parameter adjustments are made to both the compressor and the magnetic levitation bearing, specifically by reducing the compressor's compression ratio. and / or rotational speed And the speed regulation satisfies the gradient constraint. At the same time, the electromagnetic force output of the magnetic levitation bearing is reduced. Reduce ineffective energy consumption under low load conditions; when the predicted load rate is monitored At that time, parameter adjustments are made, specifically increasing the compressor's compression ratio. and / or rotational speed This is to meet the high-load compressed air requirements while increasing the displacement control frequency of the magnetic levitation bearing. This enhances the control precision of the magnetic levitation bearing, ensuring stable compressor operation under high loads, and minimizing the deviations between the compression ratio and speed adjustment range and the load rate and threshold. Positive correlation.

[0054] Furthermore, in the process of coordinating and adjusting the cooling parameters of the cooling system, the first step is to adjust the compressor's exhaust temperature. Real-time continuous monitoring is performed, and a preset threshold range is set for the exhaust temperature. This serves as the basis for determining the adjustment of the cooling system; when it is detected... In this case, prioritize adjusting the air-cooling system by gradually increasing the air-cooling fan speed. To improve cooling capacity and meet cooling requirements. ( (This refers to the air-cooling coefficient), which reduces exhaust temperature by increasing air-cooling efficiency; if the air-cooled fan speed is increased to the rated speed... This means that even after the air-cooled system reaches its maximum cooling capacity, the compressor's exhaust temperature still meets the requirements. If necessary, immediately start the water cooling system and adjust the speed of the water cooling pump. Controlling cooling water flow ( (This refers to the water cooling coefficient), enabling the adjustment of cooling capacity. Through graded adjustment of air cooling and water cooling, the synergistic control of cooling parameters is achieved, until... This ensures a dynamic balance between compression heat and cooling energy consumption. .

[0055] Furthermore, after collecting multi-source operating data during the compressor unit's operation, energy consumption anomaly determination and cause localization are also carried out based on this multi-source operating data. First, based on the compressor's design parameters and historical operating data, combined with the load rate... Intake air temperature Constructing a theoretical energy consumption benchmark for compressors Then, the real-time collected multi-source operating data is converted into the actual energy consumption data of the compressor. Through the deviation formula Analyze the deviation between actual energy consumption and theoretical energy consumption benchmark; set a preset reasonable range for this deviation. When detected Furthermore, when the set duration is continuously observed, it is directly determined that the compressor has an abnormal energy consumption situation. Then, by combining the real-time changes of various parameters in the multi-source operating data, the operating parameters of each link such as intake, compression, cooling, and magnetic levitation bearing are checked one by one. Based on the abnormal characteristics of the parameters, the specific cause of the abnormal energy consumption is accurately located, providing a clear direction for subsequent fault handling.

[0056] This invention constructs a closed-loop control logic of "data acquisition - load prediction - parameter adjustment - collaborative control - fault early warning", and dynamically optimizes the compression system parameters by combining the 7 bar exhaust pressure characteristics. The specific steps are as follows: Furthermore, an intelligent control hardware system is constructed: the system consists of a sensor group, a PLC control unit, and a data storage module, realizing data acquisition and command issuance: Sensor group: Inlet end: temperature sensor, pressure sensor, flow sensor, filter differential pressure sensor; Compression stage: inlet and outlet temperatures and pressures of each stage; Cooling system: cooling water temperature, air volume, water pump power; Core components: magnetic levitation bearing displacement and vibration, motor current, voltage, speed, and temperature. PLC control unit: integrates a GPRS / 4G remote module, with built-in four modules: "load prediction, parameter adjustment, collaborative control, and fault early warning," and bidirectional communication with sensors, motor frequency converter, bearing controller, and cooling controller; Data storage module: stores historical operating data for nearly 3 months, load prediction model parameters, and a fault threshold database.

[0057] Further, load prediction model training and real-time prediction: A load prediction module is constructed using a Long Short-Term Memory (LSTM) neural network, with "average intake flow rate for the next hour" as the core prediction target. The steps are as follows: Feature extraction: Extract load-related features from historical data: Time features: hour, weekday / holiday, production shift (e.g., full load from 8 am to 8 pm); Operating condition features: intake temperature, intake pressure, intake flow rate, outlet pressure; Production features: number of production lines started and stopped remotely, production cycle time. Model training: Using the data from the previous two months as the training set, adjust the LSTM model parameters to ensure the prediction error is ≤5%; Real-time prediction: Call the model every 10 minutes, inputting "current time + real-time operating condition + production plan", outputting the predicted flow rate, and calculating the load rate.

[0058] Furthermore, dynamic adjustment of compression parameters based on load prediction: "Pressure ratio distribution, motor speed, and bearing electromagnetic force" are dynamically optimized according to the load rate to ensure stable and efficient operation at 7 bar pressure. Pressure ratio distribution optimization: The pressure ratio is dynamically distributed according to different load levels to reduce motor energy consumption. Speed ​​gradient adjustment: The speed change rate is ≤500 rpm / s to avoid increased vibration and energy consumption fluctuations. Bearing electromagnetic force optimization: Under low load, the electromagnetic force output can be appropriately reduced to decrease bearing energy consumption; under high load, the displacement correction frequency is increased to ensure effective displacement control.

[0059] Furthermore, the compressor and cooling system are controlled in tandem: based on the principle of "compression heat - cooling energy consumption" balance, cooling parameters are dynamically adjusted to avoid over-cooling or under-cooling: Cooling priority: based on the principle of "air cooling first, water cooling as an auxiliary", exhaust temperature thresholds are set for each stage; Air cooling adjustment: when the exhaust temperature of a certain stage exceeds the threshold, the cooling fan speed is increased first (for every 1°C increase, the speed increases by 5%) until the temperature reaches the standard; Water cooling coordination: when the fan speed is full and still exceeds the threshold, the water pump speed is adjusted according to the temperature difference between the inlet and outlet; Parameter linkage correction: when the cooling system is full load and still cannot cool down, the pressure ratio and speed of the corresponding compression stage are reduced to reduce the generation of compression heat and ensure that the compressor efficiency is ≥80%.

[0060] Furthermore, based on energy consumption anomalies, fault prediction and maintenance scheduling are implemented: anomalies are identified, faults are located, and maintenance is scheduled through the comparison of "energy consumption baseline and actual energy consumption": establishing an energy consumption baseline: constructing the correspondence between theoretical operating power and load rate and intake air temperature based on historical data; anomaly identification: real-time monitoring of actual power, when the deviation between actual power and theoretical operating power is ≥8% and lasts for 10 minutes, it is determined to be an energy consumption anomaly; fault location: locating the cause by combining other parameters; maintenance scheduling: pushing suggestions based on fault type and predicted load (e.g., if the filter is clogged and the load is ≤50% in the next 2 hours, it is recommended to shut down and replace it during the low load period; if the bearing parameters drift, they are automatically corrected, and if ineffective, remote debugging is performed).

[0061] Furthermore, closed-loop iterative optimization: every 5 minutes, analyze the deviations of "predicted load - actual load", "target pressure - actual pressure", and "theoretical energy consumption - actual energy consumption": if the load deviation is ≥10%, update the LSTM model parameters; if the pressure deviation exceeds ±0.1 bar, fine-tune the three-stage pressure ratio (±0.02); if the energy consumption deviation is ≥5%, optimize the energy consumption benchmark model to achieve continuous energy saving.

[0062] The embodiments of the present invention also have the following technical effects: significant energy saving effect: dynamic parameter adjustment and cooling synergy keep the variable efficiency stable under 7 bar operating conditions, and the energy consumption is reduced compared with the existing fixed control. The bearing electromagnetic force optimization is achieved under low load for additional energy saving; improved pressure stability: "load prediction + advance adjustment" makes the 7 bar exhaust pressure fluctuation ≤ ±0.1 bar, which meets the needs of high-precision industrial applications; reduced maintenance costs: potential fault prediction (such as the early signs of filter blockage) avoids equipment damage, extends the life of magnetic levitation bearings, and reduces the number of maintenance and maintenance costs.

[0063] Example 3 To achieve the above embodiments, such as Figure 3 As shown, this embodiment also provides an energy-saving collaborative control device 10 for a magnetic levitation air compressor based on load prediction, comprising: The multi-source data acquisition module 100 is used to collect multi-source operating data during the operation of the compressor unit. The load prediction and calculation module 200 is used to predict the load demand of the compressed air system in future periods based on the multi-source operating data and production plan information. The dynamic adjustment control module 300 is used to adjust the compression parameters of the compressor and the operating parameters of the magnetic levitation bearing according to the load requirements. The cooling parameter coordination adjustment module 400 is used to coordinately adjust the cooling parameters of the cooling system during the process of adjusting the compression parameters of the compressor, so as to balance the compression heat and cooling energy consumption.

[0064] Furthermore, the load prediction and calculation module 200 is also used for: Extract load-related time features, operating condition features, and production features from historical operating data, and train the prediction model based on these features; The multi-source operational data and production planning information are input into the trained prediction model to obtain prediction results for future loads.

[0065] Furthermore, the dynamic adjustment control module 300 is also used for: When the load demand is lower than the set threshold, reduce the compressor's compression ratio and / or speed, and reduce the electromagnetic force output of the magnetic levitation bearing; When the load demand exceeds the set threshold, increase the compressor's compression ratio and / or speed, and increase the displacement control frequency of the magnetic levitation bearing.

[0066] An energy-saving collaborative control device for a magnetic levitation air compressor based on load prediction according to an embodiment of the present invention can realize dynamic adaptation and adjustment of compression parameters and magnetic levitation bearings, effectively eliminate over-compression phenomenon under low load, improve variable efficiency and reduce energy consumption, while enhancing pressure stability and fault prediction capability, and significantly improve the operating energy efficiency of the magnetic levitation air compressor under 7 bar conditions.

[0067] Example 4 The present invention also provides an electronic device such as Figure 4 As shown, it includes a processor and a memory. The memory stores executable instructions. When the processor executes the instructions, it implements the above-mentioned energy-saving collaborative control method for magnetic levitation air compressors based on load prediction.

[0068] Example 5 The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-described energy-saving coordinated control method for a magnetic levitation air compressor based on load prediction.

[0069] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0070] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

Claims

1. A load-prediction-based energy-saving coordinated control method for a magnetic levitation air compressor, characterized in that, include: S1 collects multi-source operating data during the operation of the compressor unit; S2, based on the multi-source operating data and production plan information, predict the load demand of the compressed air system in the future period; S3, adjust the compression parameters of the compressor and the operating parameters of the magnetic levitation bearing according to the load requirements; S4. During the process of adjusting the compression parameters of the compressor, the cooling parameters of the cooling system are adjusted in coordination to balance the compression heat and cooling energy consumption.

2. The method according to claim 1, characterized in that, The predicted load demand of the compressed air system for future periods includes: Extract load-related time features, operating condition features, and production features from historical operating data, and train the prediction model based on these features; The multi-source operational data and production planning information are input into the trained prediction model to obtain prediction results for future loads.

3. The method according to claim 1, characterized in that, The step of dynamically adjusting the compressor's compression parameters and the magnetic levitation bearing's operating parameters according to the load demand includes: When the load demand is lower than the set threshold, reduce the compressor's compression ratio and / or speed, and reduce the electromagnetic force output of the magnetic levitation bearing; When the load demand exceeds the set threshold, increase the compressor's compression ratio and / or speed, and increase the displacement control frequency of the magnetic levitation bearing.

4. The method according to claim 1, characterized in that, The cooling parameters of the coordinated cooling system include: Monitor the compressor's exhaust temperature; When the exhaust temperature exceeds a preset threshold, the cooling capacity of the air-cooling system is increased first. If the exhaust temperature still exceeds the threshold after the cooling capacity of the air-cooled system reaches its upper limit, the cooling capacity of the water-cooled system will be activated and adjusted.

5. The method according to claim 1, characterized in that, The collection of multi-source operating data during the operation of the compressor unit also includes: Based on the multi-source operating data, the deviation between the actual energy consumption of the compressor and the theoretical energy consumption benchmark is analyzed. When the deviation exceeds the preset range, an energy consumption anomaly is determined, and the cause of the anomaly is located based on the multi-source operation data.

6. An energy-saving collaborative control device for a magnetic levitation air compressor based on load prediction, characterized in that, include: The multi-source data acquisition module is used to collect multi-source operating data during the operation of the compressor unit; The load prediction and calculation module is used to predict the load demand of the compressed air system in future periods based on the multi-source operating data and production plan information. The dynamic adjustment and control module is used to adjust the compression parameters of the compressor and the operating parameters of the magnetic levitation bearing according to the load requirements. The cooling parameter coordination adjustment module is used to coordinately adjust the cooling parameters of the cooling system during the adjustment of the compressor's compression parameters in order to balance compression heat and cooling energy consumption.

7. The apparatus as claimed in claim 6, characterized in that, The load prediction and calculation module is also used for: Extract load-related time features, operating condition features, and production features from historical operating data, and train the prediction model based on these features; The multi-source operational data and production planning information are input into the trained prediction model to obtain prediction results for future loads.

8. The apparatus as claimed in claim 6, characterized in that, The dynamic adjustment and control module is also used for: When the load demand is lower than the set threshold, reduce the compressor's compression ratio and / or speed, and reduce the electromagnetic force output of the magnetic levitation bearing; When the load demand exceeds the set threshold, increase the compressor's compression ratio and / or speed, and increase the displacement control frequency of the magnetic levitation bearing.

9. A computer device, characterized in that, Including processor and memory; The processor reads the executable program code stored in the memory to run a program corresponding to the executable program code, so as to implement the energy-saving collaborative control method for magnetic levitation air compressor based on load prediction as described in any one of claims 1-5.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements an energy-saving collaborative control method for a magnetic levitation air compressor based on load prediction as described in any one of claims 1-5.

Images