Refrigeration equipment energy-saving control system based on machine learning and energy-saving refrigeration equipment

Abstract

The invention relates to the technical field of machine learning, energy-saving refrigeration and the like, and provides a refrigeration equipment energy-saving control system based on machine learning and energy-saving refrigeration equipment.The refrigeration equipment energy-saving control system is provided with a filtering square pipe, an air inlet square pipe, a sensor module and a machine learning module, and two independent clean channels are formed in the filtering square pipe; a selection assembly is arranged in the air inlet square pipe, and the air inlet square pipe can be switched to any clean channel to form a filtering channel. The sensor module comprises air volume, pressure difference and dust concentration sensors, monitors data in real time and transmits the data to the machine learning module. The machine learning module predicts the optimal switching opportunity, the air filter screen inclination angle adjusting requirement, the filter screen cleaning requirement and the refrigeration load adjusting requirement according to the monitoring data, outputs corresponding control signals, completes filter channel switching, air filter screen angle adjusting, filter screen cleaning and refrigeration load adjusting, saves energy, reduces cost and prolongs the service life of equipment.

Description

Technical Field

[0001] The present invention relates to the technical fields of machine learning, energy-saving refrigeration, etc., and particularly relates to an energy-saving control system for a refrigeration device based on machine learning and an energy-saving refrigeration device. Background Art

[0002] Existing refrigeration devices generally rely on traditional filtration systems and constant load control strategies. In actual use, due to the fact that the empty filter screens in the filtration device are fixedly installed all year round and cannot be dynamically adjusted according to multi-dimensional factors such as actual air volume, dust concentration, pressure difference, etc., problems such as low filtration efficiency, serious energy consumption waste, high maintenance costs, and shortened filter screen life occur. For example, when the empty filter screen gradually accumulates dust, the air flow resistance increases and the air volume decreases accordingly. In order to maintain the refrigeration effect, it is usually necessary to increase the fan speed or increase the refrigeration load, resulting in a further increase in the overall energy consumption of the system. The traditional filtration structure is difficult to achieve online switching or adjustment of the inclination angle of the empty filter screen during use, and there is also no effective pressure difference and dust monitoring to determine the cleaning time, resulting in high equipment energy consumption and maintenance costs. In the absence of effective monitoring and prediction, the filter screen often either is not cleaned for a long time or can only be cleaned regularly based on manual experience. Excessive dust accumulation may cause the filter screen to deform or perforate, thus requiring replacement of the filter screen, resulting in continuous increase in maintenance costs. If the cleaning is not timely or not in place, it may also damage the normal operation of the system and shorten the overall service life of the equipment.

[0003] Therefore, how to reduce the energy consumption of refrigeration devices, improve the filtration efficiency, reduce the maintenance costs, and extend the service life of the equipment has become a technical problem to be solved urgently. Summary of the Invention

[0004] In view of the deficiencies of the above-mentioned existing technologies, the present invention provides an energy-saving control system for a refrigeration device based on machine learning and an energy-saving refrigeration device to adaptively control the switching of the filtration channel, the adjustment and cleaning of the inclination angle of the empty filter screen, and the adjustment of the refrigeration load, so as to achieve energy conservation and cost reduction and extend the service life of the equipment.

[0005] In a first aspect, the present invention provides an energy-saving control system for a refrigeration device based on machine learning, comprising:

[0006] A filtration square pipe, in which two symmetrically structured and mutually independent clean channels are arranged, and an adjustable inclined empty filter screen is installed in each clean channel;

[0007] An air inlet square pipe, which is connected to the air inlet end of the filtration square pipe, and a selection component for switching the connection between the air inlet square pipe and any one of the clean channels to form a filtration channel is arranged in the air inlet square pipe;

[0008] A sensor module, the sensor module includes an air volume sensor, a differential pressure sensor and a dust concentration sensor respectively installed in the intake square pipe and the clean channel, the air volume sensor is used to monitor air volume data in real time, the differential pressure sensor is used to monitor differential pressure data in real time, and the dust concentration sensor is used to monitor dust data in real time;

[0009] A machine learning module, connected and communicating with the sensor module, receiving the monitoring data monitored in real time by the air volume sensor, the differential pressure sensor, and the dust concentration sensor, predicting and switching the switching timing of forming the filter channel, the demand for adjusting the inclination angle of the empty filter screen, the demand for cleaning the empty filter screen, and the demand for adjusting the refrigeration load according to the monitoring data, so as to output corresponding control signals to control the selection component to switch the filter channel, and control the adjustment of the inclination angle of the empty filter screen, the cleaning of the empty filter screen, and the adjustment of the refrigeration load.

[0010] In a second aspect, the present invention provides an energy-saving refrigeration device, and the energy-saving refrigeration device uses an energy-saving refrigeration control system for refrigeration equipment based on machine learning for energy-saving refrigeration.

[0011] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0012] The present invention provides an energy-saving refrigeration control system for refrigeration equipment and an energy-saving refrigeration device based on machine learning. By setting a filter square pipe, an intake square pipe, a sensor module and a machine learning module, two structurally symmetric and independent clean channels are arranged in the filter square pipe, and an adjustable inclination angle empty filter screen is installed in each clean channel. The intake square pipe is connected to the air inlet end of the filter square pipe, and a selection component for switching the connection between the intake square pipe and any one of the clean channels to form a filter channel is arranged in the intake square pipe. The sensor module includes an air volume sensor, a differential pressure sensor and a dust concentration sensor respectively installed in the intake square pipe and the clean channel. The air volume sensor is used to monitor air volume data in real time, the differential pressure sensor is used to monitor differential pressure data in real time, and the dust concentration sensor is used to monitor dust data in real time. The machine learning module is connected and communicates with the sensor module, receives the monitoring data monitored in real time by the air volume sensor, the differential pressure sensor, and the dust concentration sensor, predicts and switches the switching timing of forming the filter channel, the demand for adjusting the inclination angle of the empty filter screen, the demand for cleaning the empty filter screen, and the demand for adjusting the refrigeration load according to the monitoring data, so as to output corresponding control signals to control the selection component to switch the filter channel, and control the adjustment of the inclination angle of the empty filter screen, the cleaning of the empty filter screen, and the adjustment of the refrigeration load, thereby realizing adaptive control of the filter channel switching, the inclination angle adjustment and cleaning of the empty filter screen, and the refrigeration load adjustment, achieving energy saving and cost reduction, and improving the equipment life. Description of the Drawings

[0013] The accompanying drawings described herein are used to provide a further understanding of the present invention and form a part of the present invention. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. Some specific embodiments of the present invention will be described in detail hereinafter with reference to the accompanying drawings in an exemplary rather than restrictive manner. The same reference numerals in the drawings denote the same or similar components or parts. Those skilled in the art should understand that these drawings are not necessarily drawn to scale. In the drawings:

[0014] Figure 1 is a schematic diagram of a system architecture of an energy-saving control system for a refrigeration device based on machine learning according to an embodiment of the present invention. Detailed implementation manners

[0015] In order to enable those skilled in the art of the present technology to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0016] See Figure 1 , an embodiment of the present invention provides an energy-saving control system for a refrigeration device based on machine learning, including:

[0017] A filtering square pipe, in which two structurally symmetric and independent clean channels are provided, and an adjustable tilt angle air filter is installed in each of the clean channels;

[0018] An intake air square pipe, the intake air square pipe is connected to the air inlet end of the filtering square pipe, and a selection component for switching the connection between the intake air square pipe and any one of the clean channels to form a filtering channel is provided in the intake air square pipe;

[0019] A sensor module, the sensor module includes an air volume sensor, a differential pressure sensor and a dust concentration sensor respectively installed in the intake air square pipe and the clean channel, the air volume sensor is used to monitor the air volume data in real time, the differential pressure sensor is used to monitor the differential pressure data in real time, and the dust concentration sensor is used to monitor the dust data in real time;

[0020] The machine learning module is connected and communicates with the sensor module, receives the monitoring data real-time monitored by the air volume sensor, the differential pressure sensor, and the dust concentration sensor, predicts and switches to form the switching timing of the filter channel, the air filter inclination adjustment requirement, the air filter cleaning requirement, and the refrigeration load adjustment requirement according to the monitoring data, so as to output corresponding control signals, control the selection component to switch the filter channel, and control the adjustment of the air filter inclination, the cleaning of the air filter, and the refrigeration load.

[0021] It should be noted that in order to improve the energy efficiency of the refrigeration equipment under different operating conditions, it is necessary to have a filter channel with dynamic adjustment and adaptive switching to meet various air volume and dust concentration conditions. In addition, it is difficult for the traditional refrigeration system to accurately predict the best adjustment timing of the filter screen based on the real-time monitoring data, resulting in excessive energy consumption or a decline in the filtering effect. In this embodiment, by configuring a selection component in the intake square pipe, it can be freely switched between two independent channels, reducing the operation waste caused by the blockage or insufficient efficiency of a single filter screen. The air volume sensor, differential pressure sensor, and dust concentration sensor of the sensor module can obtain key data in real time, providing accurate input for the machine learning module. The machine learning module dynamically predicts and outputs control signals according to the sensor information, coordinates the switching of the filter channel, the adjustment of the filter screen angle, the cleaning, and the matching of the refrigeration load, so as to achieve the comprehensive goals of adaptability, high efficiency, and energy saving, and effectively solve the problems in the traditional refrigeration equipment filtering system that it is difficult to balance high filtering efficiency and low energy consumption and it is difficult to achieve intelligent scheduling.

[0022] In some preferred embodiments, the selection component includes a rotatable assembly column installed in the intake square pipe and a gas guide groove provided on the assembly column; the assembly column changes the connection position between the gas guide groove and one of the two clean channels by rotation to form the filter channel, realizing the switching of the air flow path between the intake square pipe and the two clean channels. It should be noted that in this embodiment, a rotatable assembly column and a gas guide groove are provided in the intake square pipe, so as to change the connection position between the gas guide groove and the clean channel by rotating the assembly column, thereby completing the switching of the filter channel. When the filter screen is seriously dust-laden or the filtering efficiency declines, if the original channel is still forcibly maintained, it will lead to an increase in energy consumption and a deterioration of the refrigeration effect. By designing a rotatable assembly column in the intake square pipe, the system can quickly switch between two clean channels, avoiding performance degradation caused by using the same filtering path for a long time. At the same time, the structural design of the assembly column and the gas guide groove can be flexibly arranged in a limited space, making the channel switching simpler, the sealing better, and the air flow resistance smaller. This embodiment can not only improve the operation efficiency of the equipment, but also combine the prediction results of machine learning to automatically select a better channel to ensure the filtering effect and reduce the comprehensive energy consumption, thereby effectively solving the high energy consumption problem caused by the lack of an elastic switching mechanism in the traditional refrigeration system.

[0023] In some preferred embodiments, the machine learning module monitors the differential pressure before and after the air filter in the clean channel in real time according to the differential pressure sensor, the air dust concentration in real time according to the dust concentration sensor, and the air volume data in real time according to the air volume sensor. When it predicts that the filtration effect of the currently used clean channel decreases or the energy consumption increases significantly, it outputs a filtration channel switching control signal to control the rotation of the assembly column to switch the filtration channel. It should be noted that in this embodiment, the machine learning module uses the real-time data of the differential pressure sensor, the dust concentration sensor, and the air volume sensor to predict whether the filtration effect of the currently used channel decays. If the energy consumption increases significantly or the filtration effect decreases, it outputs a channel switching control signal. The traditional system mainly relies on fixed time or manual experience to judge whether the filter needs to be replaced or switched, and it is difficult to accurately identify when the filtration efficiency decreases significantly or the energy consumption increases significantly. With the help of multi-dimensional data of differential pressure, dust concentration, and air volume, machine learning can comprehensively judge the clogging trend of the filter and the load of the filter, so as to trigger channel switching at the best time. This can not only reduce the additional energy consumption caused by excessive filter clogging, but also effectively avoid resource waste caused by frequent switching, enable the system to operate under the best working conditions, greatly improve energy efficiency, and extend the service life of the filter.

[0024] In some preferred embodiments, the machine learning module predicts the improvement degree of the air filtration efficiency and the resulting air resistance change caused by increasing the inclination angle of the air filter according to the dust concentration data monitored by the dust concentration sensor in real time and the air volume data monitored by the air volume sensor in real time. When the comprehensive benefit of the improved filtration efficiency exceeds the influence of the air volume decrease caused by the increased air resistance, it outputs an angle inclination control signal to control the adjustment of the windward inclination angle of the air filter. It should be noted that in this embodiment, the machine learning module predicts whether increasing the inclination angle of the air filter helps to improve the filtration efficiency based on the dust concentration and air volume data, and outputs a control signal to adjust the inclination angle when the benefit brought by the improved filtration efficiency is greater than the loss of the air volume decrease caused by the increased air resistance. The inclination angle of the filter is an important factor affecting the air flow distribution and dust deposition. If the inclination angle is too small, although the resistance is small, the filtration efficiency may be insufficient. If the inclination angle is too large, although the filtration effect increases, the air resistance also increases. In the traditional design, the inclination angle of the filter is often fixed, which not only cannot adapt to environmental changes, but also causes energy waste or insufficient filtration. In this embodiment, by using machine learning to balance the benefits and losses with real-time dust and air volume data, it can ensure that the optimal inclination angle range is automatically found under different working conditions, reduce energy consumption, and maintain excellent filtration effects.

[0025] In some preferred embodiments, when the air volume sensor monitors that the real-time air volume is lower than the preset value and the dust concentration sensor monitors that the real-time dust concentration is lower than the set threshold, the machine learning module outputs a control signal to reduce the windward tilt angle of the air filter, and controls to reduce the windward tilt angle of the air filter. It should be noted that when the air volume monitoring value is lower than the preset value and the dust concentration is lower than the threshold, the machine learning module outputs a control signal to reduce the windward tilt angle of the air filter. If the environmental dust concentration is not high and the air volume has dropped below a certain critical level, maintaining a large-angle filter screen at this time will cause excessive wind resistance, resulting in a further decrease in air volume, leading to insufficient refrigeration efficiency or an increase in the load of the compressor and the fan. Based on this, in this embodiment, the system performs real-time analysis on the sensor data through machine learning. If it is found that the dust concentration is low and strong filtration is not required, the filter screen angle can be adjusted to be smaller to reduce resistance, thereby saving energy to the greatest extent and improving the overall efficiency of the equipment on the premise of ensuring the basic requirements of the filtration performance.

[0026] In some preferred embodiments, the machine learning module analyzes in real time the change trend of the pressure difference before and after the air filter monitored by the pressure difference sensor, the change trend of the air dust concentration monitored by the dust concentration sensor, and the change trend of the air volume monitored by the air volume sensor, predicts the clogging state of the air filter, and when the predicted clogging degree reaches the set value, outputs an air filter cleaning control signal to control the cleaning of the air filter. It should be noted that in this embodiment, by comprehensively analyzing the trends of the three types of sensor data of the pressure difference, the dust concentration, and the air volume, the clogging state of the air filter is predicted, and an air filter cleaning control signal is output when the clogging degree reaches the set value. It can be understood that simply relying on manual experience may result in the filter screen being cleaned only after excessive clogging, which not only keeps the energy consumption at a high level for a long time but also damages the equipment; if the cleaning is too frequent, the maintenance cost and downtime will increase. In this embodiment, by real-time monitoring the change trends of the three types of sensor data and using machine learning algorithms, the system can more accurately judge the clogging degree, avoid the two extreme situations of excessive clogging and frequent cleaning, and achieve a balance between energy saving and stable operation.

[0027] In some preferred embodiments, a filter screen cleaner is arranged in the clean channel, and the filter screen cleaner cleans the air filter according to the air filter cleaning control signal. It should be noted that a filter screen cleaner is arranged in the clean channel, and the filter screen cleaner cleans the air filter according to the air filter cleaning control signal, which can realize online cleaning or semi-automatic cleaning in combination with the cleaning signal of the machine learning module, saving time and effort, and ensuring the continuous and efficient operation of the equipment at the same time.

[0028] In some preferred embodiments, the machine learning module predicts the refrigeration load demand based on the monitoring data real-time monitored by the air volume sensor, differential pressure sensor, and dust concentration sensor, outputs a refrigeration load control signal, and controls and adjusts the compressor frequency and fan speed. It should be noted that the main sources of energy consumption in refrigeration equipment are the compressor and the fan. Traditional control mostly uses fixed frequency or simple PID algorithms, and it is difficult to track the changes in the external environment and the state of the filtration system in real time. If the filter resistance increases and the air volume suddenly decreases, the traditional strategy of still maintaining a fixed frequency may cause a reduction in refrigeration efficiency or excessive energy consumption. In this embodiment, by predicting and real-time regulating the load through machine learning algorithms, the system operation can be more in line with the current demand, reducing unnecessary energy losses and maintaining a stable refrigeration effect.

[0029] In some preferred embodiments, when the differential pressure abnormally monitored by the differential pressure sensor rises or the air volume abnormally monitored by the air volume sensor drops below a preset value, the machine learning module predicts that the equipment may have a failure risk and automatically outputs a failure response control message to control and reduce the compressor frequency or the fan operating speed. It should be noted that in refrigeration equipment, if the filter or related pipelines are severely blocked, it often leads to an extreme increase in differential pressure and a sudden drop in air volume, which in turn triggers failure risks such as abnormal equipment load, compressor or fan overload. If not dealt with in time, it will cause the equipment to shut down urgently or be further damaged. In this embodiment, by real-time monitoring and evaluating risks through machine learning, control instructions can be issued in time before the failure occurs to reduce the compressor frequency or the fan speed, so as to relieve the high-load risk and remind of maintenance to prevent more serious losses.

[0030] In some preferred embodiments, the machine learning module uses a deep neural network model, which is trained with the data of air volume, differential pressure, and dust concentration in historical operations to achieve prediction of filter channel switching, optimization of filter screen inclination, judgment of filter screen cleaning, and prediction of refrigeration load. It should be noted that traditional algorithms based on simple rules or linear models often cannot accurately capture the complex non-linear relationships between various sensor data, equipment energy consumption, and filtration efficiency; deep neural networks have stronger feature extraction capabilities and can learn more accurate decision-making rules through training with a large amount of historical data, so as to make more sensitive and reliable predictions and controls for the ever-changing states during operation, enhancing the self-learning and self-adaptive capabilities of the system.

[0031] In some preferred embodiments, the machine learning module performs online training and updates during real-time operation based on the latest data collected by air volume, pressure difference and dust concentration sensors, automatically adjusts model parameters, and realizes self-adaptation to real-time working conditions and environmental changes. It should be noted that the environment in which the refrigeration equipment is located (such as outdoor dust concentration, air temperature, and humidity) may fluctuate greatly over time. If only relying on offline trained models, the model accuracy may continue to decline as the equipment ages or the environment changes. The online training mechanism enables the machine learning model to continuously learn new sensor data, thereby dynamically correcting the control strategy, maintaining a high prediction accuracy and system efficiency, and avoiding control failure or mismatch problems caused by working condition deviations.

[0032] In some preferred embodiments, the input data of the machine learning module includes sliding window statistical features of air volume, pressure difference and dust concentration sensor data, and the random forest or XGBoost algorithm is used to predict and analyze the real-time operation trend of the refrigeration equipment. It should be noted that the change in the state of the refrigeration system is not only related to the data at a single moment, but also closely related to the data trend over the past period of time; the use of a sliding window method to extract data features can capture the laws of time series evolution and reduce the impact of noise on instantaneous values. Integrated learning algorithms such as random forests and XGBoost are relatively good at processing multi-dimensional sensor data and nonlinear relationships. They can mine more potential patterns in high-dimensional data and provide algorithmic support for the system to make more accurate energy consumption predictions and control decisions.

[0033] In some preferred embodiments, the machine learning module integrates a reinforcement learning algorithm, takes air volume, pressure difference and dust concentration data as real-time input, and optimizes system energy consumption by continuously optimizing the filter inclination angle, filter channel switching, filter cleaning timing and refrigeration load control strategy. It should be noted that reinforcement learning is suitable for dealing with control problems with trial and error mechanisms and long-term benefit optimization needs. The energy consumption of refrigeration equipment is not simply the best at a certain moment to be optimal in the long run, but also needs to comprehensively consider multiple factors such as filter state changes, cleaning frequency, equipment life, etc. Through reinforcement learning, the system can continuously accumulate experience during long-term operation and explore better behavior strategies, so as to achieve the goal of continuously optimizing energy consumption under different environmental and load conditions.

[0034] In some preferred embodiments, the machine learning module is deployed within a digital twin platform, a digital twin model is constructed within the digital twin platform, the machine learning module is deployed on the digital twin platform and is interconnected with the digital twin model; the digital twin model receives in real time the data from the air volume sensor, the differential pressure sensor, and the dust concentration sensor to simulate the operating state of the actual refrigeration equipment, the machine learning module optimizes the control strategy based on the operating data simulated by the digital twin model, and the optimized control strategy is sent to the actual refrigeration equipment after being verified by real-time simulation of the digital twin model. It should be noted that the operating environment of the real refrigeration equipment is complex and changeable. Directly performing frequent parameter adjustment or trial and error on the physical equipment is associated with high risks and high costs; while the digital twin model can receive sensor data in real time and perform high-precision simulation, providing a mirrored environment for the machine learning module to conduct strategy verification and optimization, thereby reducing the interference with the actual equipment and the cost of trial and error, and significantly shortening the optimization cycle.

[0035] In some preferred embodiments, the digital twin model receives in real time the data from the air volume sensor, the differential pressure sensor, and the dust concentration sensor and conducts dynamic simulation of the equipment operating state, the machine learning module predicts the possible fault risks of the actual refrigeration equipment according to the simulation results of the digital twin model, and automatically generates maintenance warning information and maintenance suggestions, which are output to the control terminal of the actual refrigeration equipment. It should be noted that when there are subtle fault symptoms in the refrigeration equipment, the sensor data and the digital twin model can capture the trend changes earlier, and the machine learning model can make a judgment based on this, avoiding the expansion of the fault and causing serious losses. In this embodiment, by simulating various extreme scenarios in advance in the digital twin model, it can help the machine learning algorithm identify the early fault characteristics. Once similar early fault characteristics are found, warning information and maintenance solutions can be output, thereby reducing the unplanned downtime, ensuring the stable operation of the equipment, and at the same time enhancing the foresight and accuracy of system maintenance.

Claims

1. A refrigeration equipment energy-saving control system based on machine learning, characterized in that: include: A filter square tube, wherein two clean channels with symmetrical structures and independent of each other are arranged in the filter square tube, and an air filter with adjustable inclination angle is installed in each of the clean channels; An air intake square tube, the air intake square tube is connected to the air intake end of the filtering square tube, and a selection component for switching the air intake square tube to be connected with any of the clean channels to form a filtering channel is provided in the air intake square tube; A sensor module, wherein the sensor module comprises an air volume sensor, a pressure difference sensor and a dust concentration sensor respectively installed in the air intake square tube and the clean channel, wherein the air volume sensor is used to monitor the air volume data in real time, the pressure difference sensor is used to monitor the pressure difference data in real time, and the dust concentration sensor is used to monitor the dust data in real time; The machine learning module is connected to the sensor module for communication, receives the monitoring data of the air volume sensor, the pressure difference sensor and the dust concentration sensor in real time, and predicts the switching timing of the filter channel, the air filter inclination adjustment requirement, the air filter cleaning requirement and the refrigeration load adjustment requirement according to the monitoring data, so as to output the corresponding control signal, control the selection component to switch the filter channel, and control the air filter inclination adjustment, air filter cleaning and refrigeration load adjustment.

2. The refrigeration equipment energy-saving control system based on machine learning according to claim 1 is characterized in that: The selection component includes an assembly column rotatably installed in the air intake square tube and an air guide groove arranged on the assembly column; the assembly column changes the connection position between the air guide groove and one of the two clean channels by rotation to form the filtering channel, thereby realizing the switching of the air flow path between the air intake square tube and the two clean channels.

3. The refrigeration equipment energy-saving control system based on machine learning according to claim 2 is characterized in that: The machine learning module predicts that when the filtering effect of the clean channel currently in use decreases or the energy consumption increases significantly, based on the pressure difference before and after the air filter in the clean channel monitored by the pressure difference sensor, the air dust concentration monitored by the dust concentration sensor, and the air volume data monitored by the air volume sensor, the machine learning module outputs a filter channel switching control signal to control the assembly column to rotate and switch the filter channel.

4. The refrigeration equipment energy-saving control system based on machine learning according to claim 1 is characterized in that: The machine learning module predicts the degree of improvement in air filtration efficiency and the resulting change in wind resistance by increasing the inclination angle of the air filter based on the dust concentration data monitored in real time by the dust concentration sensor and the wind volume data monitored in real time by the wind volume sensor. When the comprehensive benefits of the improved filtration efficiency exceed the impact of the decreased air volume caused by the increased wind resistance, the module outputs an angle tilt control signal to control the adjustment of the windward inclination angle of the air filter.

5. The refrigeration equipment energy-saving control system based on machine learning according to claim 4 is characterized in that: When the real-time air volume monitored by the air volume sensor is lower than the preset value and the real-time dust concentration monitored by the dust concentration sensor is lower than the set threshold, the machine learning module outputs a control signal to reduce the windward inclination angle of the air filter, thereby reducing the windward inclination angle of the air filter.

6. The refrigeration equipment energy-saving control system based on machine learning according to claim 1 is characterized in that: The machine learning module analyzes in real time the pressure difference change trend before and after the air filter monitored by the pressure difference sensor, the air dust concentration change trend monitored by the dust concentration sensor, and the air volume change trend monitored by the air volume sensor, predicts the blockage state of the air filter, and when the predicted blockage degree reaches the set value, outputs an air filter cleaning control signal to control the cleaning of the air filter.

7. The refrigeration equipment energy-saving control system based on machine learning according to claim 6 is characterized in that: A filter cleaner is arranged in the clean channel, and the filter cleaner cleans the air filter according to the air filter cleaning control signal.

8. The refrigeration equipment energy-saving control system based on machine learning according to claim 1 is characterized in that: The machine learning module predicts the refrigeration load demand based on the real-time monitoring data of the air volume sensor, the pressure difference sensor and the dust concentration sensor, outputs a refrigeration load control signal, and controls and adjusts the compressor frequency and the fan speed.

9. The refrigeration equipment energy-saving control system based on machine learning according to claim 8, characterized in that: When the pressure difference monitored by the differential pressure sensor increases abnormally or the air volume monitored by the air volume sensor decreases abnormally and exceeds the preset value, the machine learning module predicts the possible risk of equipment failure and automatically outputs fault response control information to control the reduction of compressor frequency or fan operating speed.

10. An energy-saving refrigeration device, characterized in that: The energy-saving refrigeration equipment uses the refrigeration equipment energy-saving control system based on machine learning as described in any one of claims 1-9 to perform energy-saving refrigeration.

Images