Automatic control maintenance method and system of intelligent clean air conditioner

Abstract

The invention discloses a self-control maintenance method and system for an intelligent clean air conditioner, and belongs to the technical field of clean air conditioners. According to the method, a multi-source heterogeneous data sensing layer is constructed to collect fan bearing vibration data, filter monitoring data and surface air cooler monitoring data; and constructing a fault prediction model according to the fan bearing vibration data, adopting a machine to learn vibration spectrum time-varying characteristics, predicting the residual life of the fan bearing, and performing self-control maintenance. A filter blockage dynamic model is further constructed according to filter monitoring data, maintenance and air volume compensation are carried out according to the blockage condition and the service life of a bearing, meanwhile, the frosting condition of a surface air cooler is monitored, hot gas bypass defrosting is carried out in time, the clean air conditioner can find and process potential faults in time, and the stability of the system is improved; the intelligent self-control maintenance greatly reduces the frequency and cost of manual maintenance, and improves the management efficiency of the equipment at the same time.

Description

Technical Field

[0001] The present invention belongs to the technical field of clean air conditioning, and in particular relates to an automatic control maintenance method and system for an intelligent clean air conditioning. Background Art

[0002] Cleanroom air conditioning systems are core equipment for clean environments such as biomedicine, electronic chips, and sterile operating rooms. They must continuously meet stringent requirements for constant temperature and humidity, positive pressure control, and air cleanliness (e.g., ISO Class 5). Traditional maintenance relies on regular manual inspections and post-fault repairs, which can lead to delayed response, high maintenance costs, and extensive energy consumption control. Existing intelligent solutions primarily analyze the overall operating performance of cleanroom air conditioners. For example, patent number CN118623453A discloses a cleanroom air conditioner performance prediction method and system using a hybrid physical and data-driven technology. However, these solutions lack the ability to collaboratively analyze and predict hidden degradation parameters such as fan vibration, filter pressure differential, and surface cooler scaling. Without corresponding intelligent automatic maintenance methods, it is difficult to implement preventive maintenance to ensure the system maintains stable operation over the long term. Summary of the Invention

[0003] In order to solve the above problems existing in the prior art, the present invention provides an automatic control maintenance method and system for an intelligent clean air conditioner. The purpose of the present invention can be achieved through the following technical solutions: The first aspect of the present invention provides an automatic control maintenance method for an intelligent clean air conditioner, characterized in that it includes the following steps: S1: Collect fan bearing vibration data, filter monitoring data, and surface cooler monitoring data; S2: Build a fault prediction model based on the analysis of fan bearing vibration data and predict the remaining life of the fan bearing for automatic maintenance; S3: Based on the filter monitoring data, a dynamic model of filter blockage is constructed to evaluate the filter status and perform compensation control; S4: frost detection and defrosting of the surface cooler based on the surface cooler monitoring data; As stated.

[0004] Specifically, the filter monitoring data includes: filter pressure difference data, filter particulate matter concentration data, and air volume data; the surface cooler data includes: surface cooler temperature data and temperature distribution area data.

[0005] Specifically, the specific steps of the fan bearing automatic control maintenance include: S21: Real-time monitoring of the fan's lubrication failure spectrum characteristics to determine whether the fan's lubricant has failed. If failure is detected, the bearing maintenance and adjustment module is automatically triggered to add lubricant to the fan's bearings. S22: Build a fault prediction model based on machine learning to predict the life of wind turbine bearings based on the degree of outer ring fault and current corrosion; S23: Perform automatic maintenance on the fan bearings according to the degree of fault on the outer ring of the fan bearings and the degree of current corrosion; Specifically, the step S22 is as follows: Vibration data of fan bearings were collected; time-frequency features including outer ring fault frequency, high-frequency discrete spectral line density and noise floor were extracted from the vibration data; the outer ring fault development speed was determined based on the growth rate of the outer ring fault frequency; the degree of current corrosion was predicted based on the high-frequency discrete spectral line density and the degree of noise floor elevation; the bearing life was predicted based on the outer ring fault development speed and current corrosion degree according to the time-frequency features of the vibration spectrum using machine learning combined with historical data, and the bearing life was divided into cycles.

[0006] Specifically, the bearing life cycle is divided into three stages: a normal stage, a degradation stage, and a critical failure stage.

[0007] Specifically, the filter status assessment and compensation control further includes the following steps: S31: Collecting pressure difference data, particle concentration data and air volume data of each filter level; S32: Determine whether it is a false blockage by combining the pressure difference data, particulate matter concentration and air volume data; S33: Determine the blockage level based on the pressure difference data and the characteristic value range of the particulate matter concentration; S34: Perform corresponding automatic maintenance compensation according to the congestion level; Specifically, the false blockage identification logic is: if a pressure difference increase is detected, and at the same time, the particulate matter concentration increases synchronously and the air volume is stable, it is determined to be a real blockage; if the pressure difference increases but the particulate matter concentration does not increase synchronously, it is determined to be interference.

[0008] Specifically, the automatic maintenance compensation includes speed compensation, which is specifically: increasing the monitoring frequency of the fan bearings when performing speed compensation; adopting different degrees of periodic speed compensation strategies based on the life cycle of the current fan bearings; limiting the time of a single continuous operation of the fan speed increase; and ensuring that the air volume is maintained within a safe range.

[0009] Specifically, the surface cooler is defrosted by hot gas bypass.

[0010] As a preferred technical solution of the present invention.

[0011] A second aspect of the present invention provides an automatic maintenance system for an intelligent clean air conditioner, which applies the automatic maintenance method for an intelligent clean air conditioner described above, specifically comprising: a data acquisition module, a bearing automatic maintenance module, a filter automatic maintenance module, and a surface cooler automatic maintenance module; The data acquisition module includes a vibration sensor, a laser particle counter, a differential pressure detector, an air volume sensor, and an infrared thermal imager. The vibration sensor is used to collect fan bearing vibration data; the laser particle counter is used to collect gas particle concentration data after filtration by the primary, secondary, and high-pressure filters; the differential pressure detector is used to collect gas pressure differential data before and after filtration by the primary, secondary, and high-pressure filters; the air volume sensor is used to detect the current clean air volume data of the air conditioner; and the infrared thermal imager is used to collect surface temperature data of the surface cooler and the corresponding temperature area data. The bearing automatic maintenance module specifically includes a fan bearing life prediction module and a bearing maintenance adjustment module. The fan bearing prediction module detects whether the fan lubricant has failed based on bearing vibration data and predicts the fan bearing life to determine the specific bearing life cycle. The bearing maintenance adjustment module is used to add lubricant to the fan bearing and perform further frequency reduction maintenance and early warning reminders based on the current bearing life cycle. The filter automatic maintenance module specifically includes a filter monitoring module and a filter maintenance adjustment module; the filter monitoring module is used to identify the filter blockage and determine the blockage level based on the pressure difference data, particulate matter concentration data and air volume data; the filter maintenance adjustment module is used to perform corresponding automatic maintenance compensation operations based on the filter blockage level; The automatic control and maintenance module for the cooler includes a cooler detection module and a hot gas bypass module; the cooler detection module is used to determine whether the cooler is frosted based on the temperature and area data collected by the infrared thermal imager; the hot gas bypass module is used to perform the hot gas defrost operation of the cooler; The beneficial effects of the present invention are: The present invention constructs a fan bearing fault prediction model, uses machine learning to learn the time-varying characteristics of the vibration spectrum, predicts the remaining life of the fan bearing and performs automatic maintenance, which can effectively extend the service life of the bearing, keep the bearing in a stable and controllable working state, and reduce the frequency of bearing failures.

[0012] The present invention constructs a dynamic model of filter blockage to evaluate the status of the clean air conditioner; and performs speed compensation based on the bearing life, effectively compensating for the impact of filter blockage on the air volume of the clean air conditioner, so that the clean air conditioner system can always maintain a safe and stable operating state.

[0013] The present invention defrosts the surface cooler by adopting a hot gas bypass method, which is simple, convenient and efficient and can further improve the stability of the system.

[0014] The present invention monitors and issues fault warnings for the fan bearings, filters, and surface coolers accordingly, thereby enabling timely detection of potential faults and performing automatic maintenance. This significantly reduces the efficiency reduction of the clean air-conditioning system due to hidden degradation problems, enables the clean air-conditioning system to operate in a stable state for a long time, reduces the frequency and cost of manual maintenance, and improves the management efficiency of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] To facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0016] Figure 1 A flowchart of an automatic control maintenance method for an intelligent clean air conditioner provided by an embodiment of the present invention; Figure 2 A schematic diagram of the process of predicting the life of a wind turbine bearing and automatically controlling maintenance according to an embodiment of the present invention; Figure 3 A schematic diagram of the process of filter status assessment and automatic maintenance provided by an embodiment of the present invention; Figure 4 A schematic structural diagram of an automatic control and maintenance system for an intelligent clean air conditioner provided by an embodiment of the present invention; DETAILED DESCRIPTION The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0017] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative position relationship, movement status, etc. between the various components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0018] In addition, the descriptions of "first", "second", etc. in the present invention are for descriptive purposes only and should not be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" or "second" may explicitly or implicitly include at least one of such features. In addition, the technical solutions between the various embodiments can be combined with each other, but this must be based on the fact that they can be implemented by ordinary technicians in this field. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0019] A clean air conditioning system refers to the use of physical methods to perform various air treatments (such as heating, humidification, drying, cooling, cleaning, etc.), and is usually composed of a cold (heat) source, an air handling unit, and a ventilation system.

[0020] After a clean air conditioning system has been running for a certain period of time, moving parts will experience wear and failure, and stationary parts and pipes will also become loose, scaled, and clogged. This can cause changes in the equipment's operating performance and the system's working conditions, and even cause accidents, affecting the system's normal operation and effectiveness. The effectiveness of a clean air conditioning system is primarily affected by the air handling unit, which is a prone area for failures. In particular, hidden degradation issues such as fan vibration, filter pressure differential changes, and surface cooler scaling can be discovered and preventive or restorative repair measures implemented promptly. This can effectively improve the stability and operational level of the entire system, reduce maintenance costs, and extend the system's service life.

[0021] Specifically, the automatic control maintenance method and system of an intelligent clean air conditioner of the present invention are described in detail through the following content: Example 1 See Figure 1 This embodiment provides a method for automatic maintenance of an intelligent clean air conditioner; the specific steps include: S1: Collect fan bearing vibration data, filter monitoring data, and surface cooler monitoring data; Specific filter monitoring data include: filter pressure difference data, filter particulate matter concentration data and air volume data; Surface cooler data includes: surface cooler temperature data and temperature distribution area data; S2: Build a fault prediction model based on the analysis of fan bearing vibration data and predict the remaining life of the fan bearing for automatic maintenance; In clean air-conditioning systems, fan bearings are core components that ensure constant temperature and humidity, positive pressure control, and air cleanliness. Their failures will directly affect the reliability of the system.

[0022] The main types of failure of wind turbine bearings include lubrication failure, outer ring peeling, and current corrosion; Lubricating oil is essential for fan bearings in clean air conditioners. It plays four key roles: friction reduction, heat dissipation, corrosion protection, and sealing. Lubrication failure is the primary cause of most fan bearing failures. This failure is caused by grease drying up due to long-term operation or increased filter resistance leading to increased bearing load and rupture of the lubricating film. Its spectral characteristics include a wide-band noise floor rise and random, non-periodic pulses in the time domain signal. The main cause of fan bearing outer ring peeling is: long-term high-speed operation of the fan leads to accumulated contact fatigue, which causes microcracks on the subsurface and further expands to outer ring peeling; when the fan bearing outer ring peels off, a corresponding core characteristic frequency will be generated, namely the outer ring failure frequency (BPFO). Different fan bearings have specific outer ring failure frequencies. When the fan is working, when the outer ring failure frequency and its harmonics are detected in the spectrum, it can be clearly determined that the outer ring is damaged. The higher the harmonic order, the more serious the damage. The growth rate of the outer ring failure frequency can reflect the speed of fault development, thereby predicting the life of the fan bearing.

[0023] Current corrosion refers to the pitting caused by high-frequency leakage current from a frequency converter (VFD) passing through fan bearings. Cleanroom air conditioning fans generally use variable frequency drive (VFD), and the carrier frequency of the VFD affects the extent of fan bearing corrosion. Its spectral characteristics are characterized by high-frequency discrete spectral lines associated with the bearing frequency and a gradually rising broadband white noise floor. As the extent of current corrosion in the fan increases, the density of the high-frequency discrete spectral lines gradually increases, and the rise in the white noise floor also intensifies. Different carrier frequencies affect the extent of fan bearing corrosion. The life of fan bearings can be predicted based on the operating carrier frequency, combined with the density of the high-frequency discrete spectral lines and the white noise floor.

[0024] Based on the above characteristics, a fault prediction model is constructed and the remaining life of the fan bearing is predicted based on machine learning. The fan bearing is then automatically maintained according to different situations. See Figure 2 The specific steps include: S21: Monitor the lubrication failure spectrum characteristics of the fan in real time to determine whether the fan lubricant has failed. If failure is detected, the bearing maintenance adjustment module is automatically triggered to add lubricant to the fan bearing.

[0025] The above steps complete the automatic maintenance of the fan bearing lubrication, so that the fan bearing is maintained in a relatively stable working state, thereby predicting the life of the fan bearing.

[0026] S22: Build a fault prediction model based on machine learning to predict the life of the fan bearing according to the degree of outer ring fault and current corrosion.

[0027] Specifically, vibration data of fan bearings are collected; time-frequency features are extracted from the vibration data, including outer ring fault frequency, high-frequency discrete spectral line density and noise floor; the outer ring fault development speed is determined based on the growth rate of the outer ring fault frequency; the degree of current corrosion is predicted based on the high-frequency discrete spectral line density and the degree of noise floor elevation; the bearing life is predicted based on the outer ring fault development speed and current corrosion degree using machine learning vibration spectrum time-frequency features combined with historical data; and the bearing life cycle is divided into three stages: normal stage, degradation stage and critical failure stage.

[0028] S23: Perform automatic maintenance on the fan bearings according to the degree of fault on the outer ring of the fan bearings and the degree of current corrosion.

[0029] Automatic maintenance includes: when the bearing life cycle is in the degradation stage, active early warning and increased monitoring frequency; when the bearing life cycle reaches the critical failure stage, measures are taken to reduce the fan frequency and trigger an alarm to prompt the user to replace it.

[0030] S3: Based on the filter monitoring data, a dynamic model of filter blockage is constructed to evaluate the filter status and perform compensation control; In clean air conditioning systems, filters are the core components for maintaining air cleanliness. Their failure will directly affect system performance and environmental compliance. Filter configuration is generally divided into multiple layers, depending on the required cleanliness level. It is generally configured as three parts, namely primary filter, medium filter and high efficiency filter.

[0031] The primary filter is located at the front end of the air conditioner and is used to filter larger particles in the air, such as dust, hair, insects, fibers, etc. It protects the subsequent medium-efficiency and high-efficiency filters from being blocked too quickly by large particles, thus extending their service life. The medium efficiency filter is located after the primary filter and before the high efficiency filter. It is usually located inside the air conditioning box. It is used to filter medium-sized particles, further improving air cleanliness, taking on the main filtering load and extending the life of the terminal high efficiency filter. High-efficiency filters are usually installed at the end of the air conditioning system and are the last barrier to ensure that the air delivered to the clean room meets the final cleanliness requirements. They are used to filter out most of the tiny particles in the air, including bacteria and virus carriers, and are the core guarantee for achieving high cleanliness levels. After the air conditioning system is installed and put into use, as time goes by, the stains and dust inside the entire air conditioning system will gradually accumulate, causing the filters to become clogged to varying degrees. If left untreated, the clean air conditioning system will have a reduced air supply volume, insufficient wind speed and ventilation frequency, and will not be able to operate normally. Specifically, a pressure difference monitor is used to monitor the pressure difference of the primary, medium and high efficiency filters respectively, and a laser particle counter is used to monitor the concentration of particles of different particle sizes in the air filtered by the primary, medium and high efficiency filters respectively.

[0032] For further information, see Figure 3 Based on the pressure difference-particle data and combined with the air volume change, a dynamic filter blockage model is constructed; the filter status is evaluated and compensation control is performed. The specific steps include: S31: Collecting pressure difference data, particle concentration data and air volume data of each filter level; S32: Determine whether it is a false blockage by combining the pressure difference data, particulate matter concentration and air volume data; When the fan speed is unstable or changes suddenly, the temperature and humidity fluctuate (when switching between hot and cold modes), the air valve is misadjusted or opened and closed abnormally, the pressure difference will change and be mistaken for blockage. Therefore, a single pressure difference data is prone to misjudgment. When the filter is clogged, the pressure difference and particle concentration will change synchronously, and the air volume fluctuations are stable. Therefore, based on the pressure difference and combined with the changes in particle concentration and air volume fluctuations, it is possible to comprehensively and accurately identify whether the filter is clogged.

[0033] Specifically, the blockage identification logic is as follows: if the system detects a rise in pressure differential, a simultaneous rise in particulate matter concentration, and a stable air volume, it is considered a true blockage; if the pressure differential rises but the particulate matter concentration does not increase synchronously, it is considered an interference; S33: Determine the blockage level based on the pressure difference data and the characteristic value range of the particulate matter concentration; The size of the pressure difference and the concentration of particulate matter reflect the degree of filter blockage; the greater the pressure difference, the higher the corresponding particulate matter concentration will be, and the corresponding air supply volume will gradually decrease as the degree of blockage deepens.

[0034] Specifically, the pressure difference characteristic of the primary filter is a linear increase, and it mainly monitors particles larger than 5um; the pressure difference characteristic of the intermediate filter is an S-shaped curve increase; it mainly monitors particles around 3um; the pressure difference characteristic of the advanced filter is an exponential increase (especially in the later stage); it mainly monitors particles of 0.3um.

[0035] The blockage level is classified as normal, mild, moderate, and severe based on the differential pressure ratio and the monitored particle concentration. The differential pressure ratio is the actual pressure difference between the filter and the baseline pressure difference when the filter is initially clean. For example, a primary filter with a differential pressure ratio (sum of differential pressures) less than 1.5 and a 5µm particle concentration of 20 particles / m³ is considered normal; a differential pressure ratio of 1.5-2.0 and a 5µm particle concentration of 20-50 particles / m³ is considered mild; a differential pressure ratio of 2.0-2.5 and a 5µm particle concentration of 50-100 particles / m³ is considered moderate; and a differential pressure ratio greater than 2.5 and a 5µm particle concentration greater than 100 particles / m³ is considered severe. S34: Perform corresponding automatic maintenance compensation according to the congestion level; When the filter is detected to be slightly clogged, a preliminary warning will be issued and the clogging trend will be recorded; When any of the primary, secondary and high filters is detected to be moderately clogged, speed compensation is started. The degree of compensation is determined by the level of the clogged filter and the degree of clogged filter. The air volume drop caused by the clog is compensated to maintain a stable air volume. When any of the filters is detected to be severely clogged, speed compensation is stopped and spare parts are forced to be replaced or the machine is shut down with an alarm.

[0036] Specifically, when speed compensation increases the fan frequency, it needs to be combined with the life cycle of the above-mentioned fan bearings, specifically: increase the monitoring frequency of the fan bearings when performing speed compensation; adopt different degrees of periodic speed compensation strategies based on the current life cycle of the fan bearings; limit the time of a single continuous operation of the fan speed increase; ensure that the air volume is maintained in a safe range; example: when it is monitored that the intermediate filter has reached moderate blockage, the current bearing life cycle is collected. If the bearing life cycle is in the normal stage, speed compensation is performed to increase the fan operating frequency until the air volume reaches 100% of the normal value. If the bearing cycle is in the degradation stage, speed compensation is performed to increase the fan operating frequency until the air volume reaches 95% of the normal value. If the bearing cycle is in the critical failure stage, a further early warning is issued to indicate that the filter is clogged and the bearing has reached the critical failure stage.

[0037] The above steps can ensure the stable operation of the filter and extend its service life. However, when the fan frequency is reduced or the filter is clogged, the probability of frost on the surface cooler will increase to a certain extent. Therefore, the surface cooler needs to be monitored and defrosted. S4: frost detection and defrosting of the surface cooler based on the surface cooler monitoring data; The surface cooler is the core device for heat and humidity treatment in cleanroom air conditioning systems. It controls the temperature, humidity, and cleanliness of the cleanroom environment through cooling and dehumidification. It is usually placed between the primary filter and the secondary filter. Frosting of the surface cooler can easily lead to a decrease in heat exchange efficiency, causing temperature and humidity to lose control. It can also aggravate airflow turbulence, increase particle concentration, and affect the monitoring effect of the filter. Therefore, frost detection and defrosting of the surface cooler are necessary. Furthermore, an infrared thermometer is used to collect data from the cooler to monitor frost formation. This data includes cooler temperature and temperature distribution area. The temperature distribution area refers to the area ratio of the cooler surface to the corresponding temperature range. When frost is detected, hot gas bypass is used to remove the frost.

[0038] Example: The infrared thermal imager scans the surface temperature field of the cooler at a frequency of 10Hz. When it detects that >15% of the area is ≤-2℃ for three consecutive frames, the defrost command is triggered. The system closes the chilled water electric valve of the cooler and reduces the fan speed to maintain the basic airflow. The hot air bypass circuit is activated and the hot air is used to melt the frost layer. , and resume normal operation after removing the frost layer.

[0039] Example 2 See Figure 4 This embodiment also provides an automatic maintenance system for an intelligent clean air conditioner, which specifically includes a data acquisition module, a bearing automatic maintenance module, a filter automatic maintenance module, and a surface cooler automatic maintenance module; The data acquisition module includes a vibration sensor, a laser particle counter, a differential pressure detector, an air volume sensor, and an infrared thermal imager. The vibration sensor is used to collect fan bearing vibration data; the laser particle counter is used to collect gas particle concentration data after filtration by the primary, secondary, and high-pressure filters; the differential pressure detector is used to collect gas pressure differential data before and after filtration by the primary, secondary, and high-pressure filters; the air volume sensor is used to detect the current clean air volume data of the air conditioner; and the infrared thermal imager is used to collect surface temperature data of the surface cooler and the corresponding temperature area data. The bearing automatic maintenance module specifically includes a fan bearing life prediction module and a bearing maintenance adjustment module. The fan bearing prediction module detects whether the fan lubricant has failed based on bearing vibration data and predicts the fan bearing life to determine the specific bearing life cycle. The bearing maintenance adjustment module is used to add lubricant to the fan bearing and perform further frequency reduction maintenance and early warning reminders based on the current bearing life cycle. The filter automatic maintenance module specifically includes a filter monitoring module and a filter maintenance adjustment module; the filter monitoring module is used to identify the filter blockage and determine the blockage level based on the pressure difference data, particulate matter concentration data and air volume data; the filter maintenance adjustment module is used to perform corresponding automatic maintenance compensation operations based on the filter blockage level; The automatic control maintenance module of the cooler includes a cooler detection module and a hot gas bypass module; the cooler detection module is used to judge whether the cooler is frosted based on the temperature and area data collected by the infrared thermal imager; the hot gas bypass module is used to perform the hot gas defrost operation of the cooler.

[0040] The above description is merely a preferred embodiment of the present invention and does not constitute any form of limitation to the present invention. Although the present invention has been disclosed as above in terms of a preferred embodiment, it is not intended to limit the present invention. Any person skilled in the art can, without departing from the scope of the technical solution of the present invention, make some changes or modifications to equivalent embodiments using the technical contents disclosed above. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. A method for automatic maintenance of an intelligent clean air conditioner, characterized by: Including steps: S1: Collect fan bearing vibration data, filter monitoring data and surface cooler monitoring data; S2: Build a fault prediction model based on the analysis of fan bearing vibration data and predict the remaining life of the fan bearing for automatic maintenance; S3: Based on the filter monitoring data, a dynamic model of filter blockage is constructed to evaluate the filter status and perform compensation control; S4: frost detection and defrosting of the surface cooler are performed based on the surface cooler monitoring data.

2. The automatic control maintenance method of an intelligent clean air conditioner according to claim 1, characterized in that: The filter monitoring data includes: filter pressure difference data, filter particulate matter concentration data and air volume data; the surface cooler data includes: surface cooler temperature data and temperature distribution area data.

3. The automatic control maintenance method of an intelligent clean air conditioner according to claim 1, characterized in that: The specific steps of the fan bearing automatic control maintenance include: S21: Real-time monitoring of the fan's lubrication failure spectrum characteristics to determine whether the fan's lubricant has failed. If failure is detected, the bearing maintenance and adjustment module is automatically triggered to add lubricant to the fan's bearings. S22: Build a fault prediction model based on machine learning to predict the life of wind turbine bearings based on the degree of outer ring fault and current corrosion; S23: Perform automatic maintenance on the fan bearings according to the degree of fault on the outer ring of the fan bearings and the degree of current corrosion.

4. The automatic control maintenance method of an intelligent clean air conditioner according to claim 3, characterized in that: The step S22 specifically includes: Vibration data of fan bearings were collected; time-frequency features including outer ring fault frequency, high-frequency discrete spectral line density and noise floor were extracted from the vibration data; the outer ring fault development speed was determined based on the growth rate of the outer ring fault frequency; the degree of current corrosion was predicted based on the high-frequency discrete spectral line density and the degree of noise floor elevation; the bearing life was predicted based on the outer ring fault development speed and current corrosion degree according to the time-frequency features of the vibration spectrum using machine learning combined with historical data, and the bearing life was divided into cycles.

5. The automatic control maintenance method of an intelligent clean air conditioner according to claim 4, characterized in that: The bearing life cycle is divided into three stages: a normal stage, a degradation stage and a critical failure stage.

6. The automatic control maintenance method of an intelligent clean air conditioner according to claim 1, characterized in that: The filter performs state evaluation and compensation control, including the following steps: S31: Collecting pressure difference data, particle concentration data and air volume data of each filter level; S32: Determine whether it is a false blockage by combining the pressure difference data, particulate matter concentration and air volume data; S33: Determine the blockage level based on the pressure difference data and the characteristic value range of the particulate matter concentration; S34: Perform corresponding automatic maintenance compensation according to the congestion level.

7. The automatic control maintenance method of an intelligent clean air conditioner according to claim 6, characterized in that: The false blockage identification logic is as follows: if a pressure differential increase is detected, and the particulate matter concentration increases synchronously while the air volume is stable, it is determined to be a real blockage; if the pressure differential increases but the particulate matter concentration does not increase synchronously, it is determined to be interference.

8. The automatic control maintenance method of an intelligent clean air conditioner according to claim 6, characterized in that: The automatic maintenance compensation includes speed compensation, which specifically includes: increasing the monitoring frequency of the fan bearings when performing speed compensation; adopting different degrees of periodic speed compensation strategies based on the current life cycle of the fan bearings; limiting the time of a single continuous operation of the fan speed increase; and ensuring that the air volume is maintained within a safe range.

9. The automatic control maintenance method of an intelligent clean air conditioner according to claim 1, characterized in that: The surface cooler is defrosted by hot gas bypass.

10. An automatic control maintenance system for an intelligent clean air conditioner, using the automatic control maintenance method for an intelligent clean air conditioner according to any one of claims 1 to 9, characterized in that: Including data acquisition module, bearing automatic control and maintenance module, filter automatic control and maintenance module and surface cooler automatic control and maintenance module; The data acquisition module includes a vibration sensor, a laser particle counter, a differential pressure detector, an air volume sensor, and an infrared thermal imager; the vibration sensor is used to collect fan bearing vibration data; the laser particle counter is used to collect gas particle concentration data after filtration by the primary, secondary, and high-pressure filters; the differential pressure detector is used to collect gas pressure differential data before and after filtration by the primary, secondary, and high-pressure filters; the air volume sensor is used to detect the current clean air volume data of the air conditioner; the infrared thermal imager is used to collect surface temperature data of the surface cooler and the corresponding temperature area data; The bearing automatic maintenance module includes a fan bearing life prediction module and a bearing maintenance adjustment module. The fan bearing prediction module detects whether the fan lubricant has failed based on bearing vibration data and predicts the fan bearing life to determine the specific bearing life cycle. The bearing maintenance adjustment module is used to add lubricant to the fan bearing and perform further frequency reduction maintenance and early warning reminders based on the current bearing life cycle. The filter automatic maintenance module includes a filter monitoring module and a filter maintenance adjustment module; the filter monitoring module is used to identify the filter blockage and determine the blockage level based on the pressure difference data, particulate matter concentration data and air volume data; the filter maintenance adjustment module is used to perform corresponding automatic maintenance compensation operations based on the filter blockage level; The automatic control maintenance module of the cooler includes a cooler detection module and a hot gas bypass module; the cooler detection module is used to judge whether the cooler is frosted based on the temperature and area data collected by the infrared thermal imager; the hot gas bypass module is used to perform the hot gas defrost operation of the cooler.

Images