Predictive maintenance and energy-saving linkage method and device for industrial air conditioner, electronic equipment and computer readable storage medium

Abstract

The invention provides a predictive maintenance and energy-saving linkage method and device of an industrial air conditioner, electronic equipment and a computer readable storage medium, and is applied to the technical field of data processing. Core operation and environment parameters such as the start-stop frequency of the compressor are collected; monitoring the state of a key component by means of the Internet of Things and edge calculation, constructing an equipment degradation and environment association model, and generating a preliminary maintenance demand and energy consumption early warning; designing a hierarchical maintenance strategy by using a digital twinning and cost model, and outputting a target maintenance instruction and an energy-saving report; dynamically adjusting parameters to generate a linkage control scheme in combination with the thermal comfort and the peak-valley electricity price; further, a multi-device global collaboration strategy is expanded; and finally, generating the reliability level and the energy-saving benefit value of the equipment through multi-dimensional evaluation, forming a closed-loop technical system, and guaranteeing the safety and energy conservation of the equipment.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method, device, electronic device and computer-readable storage medium for predictive maintenance and energy saving linkage of an industrial air conditioner. Background Art

[0002] In the industrial sector, industrial air conditioners are key equipment for maintaining a stable production environment, and their stable operation and efficient energy conservation are crucial. Currently, conventional industrial air conditioner management relies heavily on traditional timing control and basic environmental feedback mechanisms. This makes it difficult to balance equipment maintenance with energy optimization under complex and changing operating conditions.

[0003] On the one hand, existing technologies have significant shortcomings in optimizing energy efficiency. Traditional systems are unable to accurately adjust air conditioning output based on real-time environmental changes, such as workshop traffic, equipment load, and external weather conditions. This leads to significant energy waste and fails to meet the current development needs of energy conservation and emission reduction. For example, when workshop equipment load changes, the air conditioner maintains fixed operating parameters, resulting in excessive cooling or heating.

[0004] Furthermore, there is a lack of fault prediction and preventive maintenance tools. Equipment failures are often only detected after they impact system operations. The lack of the ability to predict potential faults based on operational data increases maintenance costs and impacts long-term equipment efficiency and production safety. Sudden failures of core components like compressors can cause production halts and result in significant losses.

[0005] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute prior art known to ordinary technicians in the field. Summary of the Invention

[0006] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by practice of the invention.

[0007] According to one aspect of the present application, a predictive maintenance and energy-saving linkage method, device, electronic device and computer-readable storage medium for industrial air conditioners are provided, including: obtaining operating data and operating environment parameter information of each core component of the industrial air conditioner; processing the operating data and operating environment parameter information of the core components of the industrial air conditioner, monitoring the compressor lubricating oil level, heat exchanger scaling degree, motor winding insulation and filter clogging status in real time through the Internet of Things sensor network and edge computing nodes, building a component degradation trend and environmental load correlation model, generating preliminary maintenance requirements and energy consumption abnormality warning information; processing the preliminary maintenance requirements and energy consumption abnormality warning information, simulating the equipment operating status at different maintenance times through digital twin technology, designing a hierarchical maintenance strategy in combination with the full life cycle cost model, and applying partial The target maintenance execution instructions and energy-saving potential analysis report are generated based on the remaining life threshold constraint of the components and the objective function of the optimal configuration of maintenance resources; the target maintenance execution instructions and energy-saving potential analysis report are processed based on the corresponding adaptive algorithm, and the air-conditioning operation parameters are adjusted in real time in combination with the indoor thermal comfort requirements and the peak-valley electricity price mechanism of the power grid to generate a linkage control scheme that takes into account both maintenance effects and energy consumption optimization; the linkage control scheme that takes into account both maintenance effects and energy consumption optimization is processed to generate a global coordinated operation management strategy; the preliminary maintenance requirements and energy consumption abnormality warning information, target maintenance execution instructions, the linkage control scheme that takes into account both maintenance effects and energy consumption optimization, and the global coordinated operation management strategy are processed to generate comprehensive evaluation information on the operating status of industrial air conditioners, including equipment reliability level and quantitative value of energy-saving benefits.

[0008] Another aspect of the present application is a predictive maintenance and energy-saving linkage device for industrial air conditioners, including: an acquisition module for acquiring operating data and operating environment parameter information of core components of industrial air conditioners; a processing module for processing the operating data and operating environment parameter information of core components of industrial air conditioners, monitoring the compressor lubricating oil level, heat exchanger scaling degree, motor winding insulation and filter clogging status in real time through the Internet of Things sensor network and edge computing nodes, building a component degradation trend and environmental load correlation model, generating preliminary maintenance requirements and energy consumption abnormality warning information; processing the preliminary maintenance requirements and energy consumption abnormality warning information, simulating the equipment operating status at different maintenance times through digital twin technology, designing a hierarchical maintenance strategy in combination with the full life cycle cost model, and applying the remaining life of components. The target maintenance execution instruction and energy-saving potential analysis report are generated based on the life threshold constraint and the maintenance resource optimal configuration objective function; the target maintenance execution instruction and energy-saving potential analysis report are processed based on the corresponding adaptive algorithm, and the air-conditioning operation parameters are adjusted in real time in combination with the indoor thermal comfort requirements and the peak-valley electricity price mechanism of the power grid to generate a linkage control scheme that takes into account both maintenance effects and energy consumption optimization; the linkage control scheme that takes into account both maintenance effects and energy consumption optimization is processed to generate a global coordinated operation management strategy; the preliminary maintenance demand and energy consumption abnormality warning information, the target maintenance execution instruction, the linkage control scheme that takes into account both maintenance effects and energy consumption optimization, and the global coordinated operation management strategy are processed to generate comprehensive evaluation information on the operating status of industrial air-conditioning, including the equipment reliability level and the quantitative value of energy-saving benefits.

[0009] According to another aspect of the present application, an electronic device includes: a first processor; and a memory for storing executable instructions of the first processor; wherein the first processor is configured to execute the above-mentioned predictive maintenance and energy-saving linkage method for industrial air conditioning by executing the executable instructions.

[0010] According to another aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a second processor, the computer program implements the above-mentioned predictive maintenance and energy-saving linkage method for industrial air conditioning.

[0011] The present application provides a predictive maintenance and energy-saving linkage method, device, electronic device and computer-readable storage medium for industrial air conditioning. Through distributed sensing and edge computing, core data such as compressor start-stop frequency are collected; a component degradation and environmental load correlation model is then constructed to generate preliminary maintenance requirements and energy consumption warnings; then, target maintenance instructions and energy-saving reports are output using digital twins and a full life cycle cost model; then, parameters are dynamically adjusted to generate a linkage control solution based on thermal comfort and peak and valley electricity prices; and then expanded into a global collaborative strategy for multiple devices; finally, reliability levels and energy-saving benefit values ​​are generated through multi-dimensional evaluation, and pushed to multiple terminals in a visual manner, ensuring equipment safety, energy saving and efficient collaboration throughout the entire process. The technical logic is closed and feasible.

[0012] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 A flowchart illustrating a method for predictive maintenance and energy saving of an industrial air conditioner provided by an embodiment of the present application is shown;

[0014] Figure 2 A schematic structural diagram of a predictive maintenance and energy-saving linkage device for an industrial air conditioner provided in one embodiment of the present application is shown. DETAILED DESCRIPTION

[0015] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0016] The following combination Figure 1 The following describes a method for predictive maintenance and energy conservation for industrial air conditioners according to an exemplary embodiment of the present application. It should be noted that the following application scenarios are provided solely to facilitate understanding of the spirit and principles of the present application, and the embodiments of the present application are not limited in this respect. Rather, the embodiments of the present application are applicable to any applicable scenario.

[0017] In one embodiment, the present application also proposes a method, device, electronic device and computer-readable storage medium for predictive maintenance and energy saving linkage of industrial air conditioners. Figure 1 The present invention schematically shows a flow chart of a method for predictive maintenance and energy saving linkage of an industrial air conditioner according to an embodiment of the present application.

[0018] S101, obtaining the operating data and working environment parameter information of each core component of the industrial air conditioner.

[0019] In one implementation, a three-level architecture of "distributed sensor deployment + multi-protocol data transmission + edge node preprocessing" enables real-time and accurate collection of operating data and environmental parameters of core industrial air conditioning components. This covers three core data dimensions: equipment operating status, environmental factors, and energy consumption. This provides a complete data foundation for subsequent component degradation analysis and energy optimization. The data collection frequency is uniformly set to 1Hz (increased to 10Hz for special high-dynamic parameters such as refrigerant pressure) to ensure data timeliness and consistency. Compressor operating data acquisition focuses on "start-stop frequency." Current transformers and condition monitoring sensors are installed in the compressor control circuit to collect compressor operating current and start-stop signals in real time. Edge computing nodes are used to count the number of starts and stops per unit time to generate compressor start-stop frequency data. Auxiliary parameters such as compressor exhaust temperature and suction pressure are also collected to verify the validity of the start-stop frequency data. The data collection equipment is a Hall current sensor (model: ACS712) and a temperature sensor (model: PT100), which are deployed at the compressor terminal and exhaust duct. The sensor collects current and temperature signals once every 100ms. When the current jumps from "0A" to "above 80% of the rated current", it is judged as starting. When it drops from "above 80% of the rated current" to "0A", it is judged as stopping. The edge node counts the number of starts and stops every minute and generates a start-stop frequency (such as "5 times / hour"). If the start-stop frequency is still less than 1 time / hour when the exhaust temperature exceeds 120°C, the data is triggered and a data anomaly flag is simultaneously pushed to the operation and maintenance terminal.

[0020] The acquisition of heat exchanger operation data focuses on the "evaporator / condenser temperature". Distributed fiber optic temperature sensors are evenly distributed along the evaporator and condenser heat exchange tubes to collect the tube wall temperatures in different areas. The overall evaporator / condenser temperature is generated through the temperature average algorithm. At the same time, the refrigerant temperature and flow rate at the heat exchanger inlet and outlet are collected, and the heat exchange efficiency is calculated to assist in verifying the rationality of the temperature data. The data collection equipment is a distributed fiber optic temperature sensor (model: DTS-800) and a refrigerant flow sensor (model: FS400). Fiber optic sensors are deployed at 20 monitoring points every 50 cm along the evaporator heat exchange tubes. The fiber optic sensors collect the temperature of each monitoring point once every second. The edge node removes outliers from the temperature data of the 20 points (using the 3σ principle) and takes the average to generate the evaporator temperature (such as "7°C") and condenser temperature (such as "45°C"). At the same time, the refrigerant flow rate (such as "5m³ / h") is collected through the flow sensor. If the flow rate is lower than 60% of the rated value and the temperature deviation exceeds ±3°C, the temperature data is marked as "pending verification". The temperature data is compared with historical data for the same period. If the condenser temperature increases by more than 5°C compared with the same period, it is preliminarily determined that scaling may exist.

[0021] The acquisition of fan operation data is centered on "speed". A photoelectric encoder is installed at the shaft end of the fan motor to calculate the fan speed by counting photoelectric pulse signals. At the same time, the fan operating current and vibration acceleration are collected to evaluate the matching of speed data with the fan load, avoiding abnormal data such as "high speed at idling" and "high load but low speed". The data acquisition equipment consists of a photoelectric encoder (model: E6B2-CWZ6C) and a vibration sensor (model: ADXL345). The encoder is connected to the fan shaft end through a coupling, and the vibration sensor is attached to the fan casing. The encoder outputs a pulse signal every 10 ms. The edge node calculates the speed (e.g., 1450 r / min) using the formula "number of pulses / time × reduction ratio" and simultaneously acquires vibration acceleration (e.g., 0.5 g). If the speed displays 1450 r / min but the vibration acceleration exceeds 1.2 g, it is determined that "the speed data is normal but the equipment is abnormal," and the vibration data is marked separately. The encoder resolution is set to 1000 pulses / rev, and the speed calculation error is controlled within ±1 r / min, meeting the parameter accuracy requirements for fan speed control.

[0022] Refrigerant system data acquisition is centered on "pressure". High-pressure and low-pressure pressure sensors are installed at the evaporator inlet and condenser outlet of the refrigerant pipeline to collect refrigerant pressure in real time. At the same time, the refrigerant liquid level (liquid storage tank) and solenoid valve switch status are collected to ensure that the pressure data matches the system operation stage (such as "refrigeration mode" and "defrost mode"). The data collection equipment is a pressure sensor (model: MPX5700) and a liquid level sensor (model: YXC-100). The high-pressure sensor is deployed on the condenser outlet pipe (pressure range: 0-4MPa), and the low-pressure sensor is deployed on the evaporator inlet pipe (pressure range: 0-1.6MPa). The pressure sensor collects pressure values ​​once every 500ms. When the system is in "cooling mode", the normal low-pressure range is 0.4-0.6MPa, and the normal high-pressure range is 1.8-2.2MPa. If the low-pressure value is 0.2MPa, the solenoid valve switch status is checked simultaneously. If the solenoid valve is in the "closed" state, it is determined to be "normal shutdown pressure", otherwise it is marked as "leakage warning pressure". The pressure data is associated with the start-stop frequency of the compressor. If the low-pressure value does not rise to 0.4MPa within 30 seconds when the compressor starts, a preliminary warning of "insufficient refrigerant" is triggered.

[0023] Temperature and humidity parameter acquisition focuses on indoor and outdoor temperature and humidity. Integrated temperature and humidity sensors are used. Indoor sensors are evenly distributed throughout the industrial workshop at a density of 500 m² per sensor. Outdoor sensors are placed near air conditioner outdoor units (away from direct sunlight and in well-ventilated areas) to collect temperature and humidity data in real time. The heat dissipation power of production equipment within the workshop is also collected to analyze the correlation between ambient temperature and humidity and load. The data collection equipment is a temperature and humidity sensor (model: SHT30). Eight indoor sensors are deployed at different heights in the workshop (1.5m above the personnel area and 3m above the equipment top area). Outdoor sensors are deployed 1m to the side of the air conditioner outdoor unit. The sensors collect temperature and humidity data once a minute. The indoor sensors use the average of the eight points as the "average workshop temperature and humidity" (for example, "25°C, 60% RH"), while the outdoor sensors directly output the "ambient temperature and humidity" (for example, "32°C, 75% RH"). If the sensor in a certain area of ​​the workshop deviates from the average by more than ±2°C, the operating status of the production equipment in that area is checked. If the equipment is operating at full load, it is determined that "local load causes temperature and humidity anomalies" and the data for that area is separately marked. The indoor temperature and humidity are used for subsequent thermal comfort constraint determination, while the outdoor temperature and humidity are used to correct air conditioner operating parameters (for example, for every 5°C increase in outdoor temperature, the condenser fan speed is increased by 10%).

[0024] Load parameter acquisition is centered on the "load change curve." Through data interaction between the industrial air-conditioning main control system and the workshop production management system (MES), the operating status of production equipment in the workshop (such as the number of powered-on units and operating power) is acquired. Combined with the indoor temperature and humidity change rates, a load change curve is constructed. At the same time, an air volume sensor is installed on the air-conditioning main air inlet duct to collect the inlet air volume to assist in verifying the load data. The data collection equipment consists of an air volume sensor (model: FS700) and a data exchange gateway (supporting the OPCUA protocol). The gateway is deployed in the air conditioner's main control cabinet and establishes communication with the MES system. The gateway obtains production equipment operating data from the MES system every 5 minutes (for example, "10 machine tools are running, with a total power of 500 kW") and simultaneously collects the inlet air volume (for example, "10,000 m³ / h") through the air volume sensor. A load change curve is generated with time as the horizontal axis and "total equipment power + air volume" as the vertical axis (for example, "load 300 kW at 9:00, load 500 kW at 11:00, load 450 kW at 14:00"). If the load curve shows "500 kW" but the air volume is less than 8,000 m³ / h, it is determined that the "load data does not match the air conditioner air volume," triggering an air volume sensor calibration reminder.

[0025] The acquisition of energy consumption parameters is centered on "energy consumption metering data." Smart electricity meters are installed in the main power supply circuit of industrial air conditioners to collect total energy consumption data. At the same time, electricity meters are installed in sub-circuits of major energy-consuming components such as compressors, fans, and water pumps to collect sub-item energy consumption data. The difference between "total energy consumption - sub-item energy consumption" is counted through edge computing nodes to verify data integrity and avoid measurement omissions. The collection equipment is a smart energy meter (model: DTZY341). The total energy meter is deployed at the incoming line of the air conditioner distribution box, and the sub-item energy meters are deployed in the power supply circuits of the compressor, fan, and water pump. The energy meter collects energy consumption data (unit: kWh) once every 15 minutes. The total energy consumption data (for example, "total energy consumption for 15 minutes is 12 kWh") is summed and compared with the sub-item energy consumption data (compressor 8 kWh, fan 3 kWh, water pump 1 kWh). If the difference exceeds 0.5 kWh, it is determined that "sub-item measurement is abnormal" and the energy meter of the abnormal circuit is marked. In addition to the cumulative energy consumption, parameters such as voltage, current, and power factor (for example, "voltage 380 V, current 25 A, power factor 0.92") are simultaneously collected for subsequent energy consumption anomaly analysis. For example, if the power factor is lower than 0.85, it is determined that "excessive reactive power loss leads to abnormal energy consumption"

[0026] Sensors and edge computing nodes communicate using the LoRaWAN protocol (transmission distance ≤ 1km) or RS485 bus (transmission distance ≤ 100m). Edge computing nodes and cloud platforms transmit data via 5G / Industrial Ethernet to ensure a data transmission packet loss rate of less than 0.1%. Edge nodes process the collected data through "outlier removal (3σ principle), missing value filling (linear interpolation), and format standardization (unified to JSON format)". For example, if the refrigerant pressure data at a certain moment is missing, it is supplemented by linear interpolation of the previous 10 seconds and the next 10 seconds of data to avoid data gaps in subsequent modeling. The preprocessed data is stored in layers according to the "real-time library (storing data within 1 hour for real-time monitoring) + historical library (storing data for 1 year for trend analysis)". The real-time library update frequency is consistent with the collection frequency, and the historical library is compressed and stored according to the "hourly average".

[0027] S102 processes the operating data and operating environment parameter information of the core components of industrial air conditioners, and monitors the compressor lubricating oil level, heat exchanger scaling, motor winding insulation and filter blockage status in real time through the Internet of Things sensor network and edge computing nodes. It builds a correlation model between component degradation trends and environmental loads, and generates preliminary maintenance needs and energy consumption abnormality warning information.

[0028] In one implementation, the operating data of core components of industrial air conditioners and information about operating and environmental parameters are processed. A distributed monitoring system is constructed using an IoT sensor network and edge computing nodes. This data is then integrated and calculated using a dynamic weight distribution mechanism to provide real-time monitoring of compressor lubricant oil levels, heat exchanger scaling, motor winding insulation, and filter clogging. This distributed monitoring system utilizes a three-layer architecture: an IoT sensing layer, an edge computing layer, and a data fusion layer. The IoT sensing layer deploys multiple sensors (such as oil level, temperature, and pressure sensors) to collect real-time core component operating data and environmental parameters. The edge computing layer deploys localized edge nodes (such as the MG300 industrial gateway) to perform data preprocessing (such as initial outlier screening and format conversion) and low-latency computing. The data fusion layer uses a dynamic weight distribution mechanism to achieve cross-dimensional correlation between core component data and environmental parameters, ensuring that monitoring data accurately reflects the actual operating status of the equipment and keeping overall data transmission and processing latency within 500ms.

[0029] The system dynamically adjusts weights based on the priority of parameters' impact on equipment status. Core component operating data (such as compressor lubricant oil level and refrigerant pressure) has a base weight of 0.6, while environmental parameters (such as indoor temperature and humidity, and workshop load) have a base weight of 0.4. When the environmental load fluctuation coefficient (fluctuation coefficient = current load / rated load) exceeds 1.2 (i.e., the load exceeds the rated value by 20%), the environmental parameter weight is automatically increased to 0.5, while the core component data weight is decreased to 0.5. This prevents underestimation of the impact of environmental factors on equipment status under high-load conditions. For example, for an industrial air conditioner in a workshop, the input data includes a measured compressor lubricant oil level of 60% (normal range 50%-80%), an indoor temperature of 28°C (normal range 22-26°C), a workshop load of 120% (100% of rated load), and a condenser temperature of 48°C (normal range 40-50°C). First, the parameters are standardized. The standardized value = (measured value - minimum parameter value) / (maximum parameter value - minimum parameter value). For example, the standardized value of the compressor lubricating oil level = (60-50) / (80-50) ≈ 0.33. Since the indoor temperature exceeds the normal range, the standardized value is calculated based on the upper limit of 26°C = (28-22) / (26-22) = 1.5, and then corrected to 1.2 according to the rule of "taking the standardized value as 1.2 when exceeding the normal range"; the standardized value of the workshop load = (120-80) / (120-80) = 1.0 (normal load range 80%-120%); the standardized value of the condenser temperature = (48-40) / (50-40) = 0.8. Because the workshop load exceeded its rated value, the weight of environmental parameters was increased to 0.5, while the weight of core component data was decreased to 0.5. Using the weighted summation formula (fusion value = Σ(normalized parameter value × corresponding weight)), the final fusion value = (0.33 × 0.5) + (1.2 × 0.5) + (1.0 × 0.5) + (0.8 × 0.5) = 1.565. When the fusion value exceeds 1.5, the system triggers focused monitoring and subsequently increases the tracking frequency of compressor lubricant level and indoor temperature (from 1Hz to 2Hz).

[0030] A capacitive oil level sensor (model: CYW-100) is deployed on top of the compressor oil tank. Oil level data is converted based on the linear relationship between the sensor's output capacitance and the oil level, with a collection frequency of 1Hz. For example, when the sensor measures a capacitance value of 1800pF, the calibration curve, which states that a capacitance value of 1500pF corresponds to an oil level of 50% and a capacitance value of 2100pF corresponds to an oil level of 80%, yields an oil level of 60%. If the oil level drops from 60% to 58% for five consecutive minutes while the workshop load remains at 100%, the system identifies a "slowly decreasing oil level trend" and simultaneously correlates this with the compressor's operating current (1.1 times the rated current). This eliminates the possibility of current anomalies causing misdetection and preliminarily determines normal oil depletion.

[0031] Using an ultrasonic thickness sensor (model: UT3000), three monitoring points were evenly spaced along the heat exchanger tubes (at the inlet, middle, and outlet). The degree of scaling was estimated by measuring the rate of change in tube wall thickness. For every 0.2mm increase in thickness, the scaling level increased by one (mild, moderate, and severe). For example, if the initial tube wall thickness was 3mm, three months later, the thickness at the inlet monitoring point was 3.4mm, at the middle, 3.3mm, and at the outlet, 3.2mm. The average thickness change rate was calculated as (3.3-3) / 3×100%=10%, corresponding to the scaling level of "mild scaling." Simultaneously, the condenser temperature was measured and found to have increased by 3°C compared to before scaling (from 45°C to 48°C). Using a correlation model between temperature increase and scaling level, it was confirmed that scaling had affected heat exchange efficiency, providing a basis for determining subsequent maintenance needs.

[0032] An insulation resistance tester (model: MI2077) was integrated into the fan motor control circuit, collecting insulation resistance values ​​every five minutes. The normal range is ≥100MΩ. A value of 80MΩ was collected, below the threshold. The team first checked the workshop humidity (60% RH, normal range 40%-70%) to rule out any potential humidity abnormalities. The team then correlated the test with the fan's operating current (1.2 times the rated current) and found that the current was consistently high. The team determined that the insulation degradation was caused by aging of the motor windings, rather than external environmental factors, thus avoiding misjudging maintenance needs.

[0033] A differential pressure sensor (model: DPT100) is installed at the filter inlet and outlet ducts. The degree of blockage is determined by measuring the differential pressure. A normal differential pressure is ≤50Pa, a differential pressure of 51-80Pa indicates moderate blockage, and a differential pressure of >80Pa indicates severe blockage. For example, if a differential pressure of 80Pa is measured, the fan speed is first checked (1450r / min, normal range 1400-1500r / min) to rule out the possibility that the abnormal pressure differential is caused by excessive speed. The ventilation volume decay rate is then calculated. Based on the "pressure differential and ventilation volume correlation formula" (ventilation volume decay rate = (normal pressure differential - measured pressure differential) / normal pressure differential × 100%), a decay rate of 15% is determined, indicating "moderate blockage" and the filter cleaning and maintenance must be scheduled within one week.

[0034] Utilizing the component-environment dynamic correlation modeling framework, a three-level network structure consisting of multi-source data denoising and feature screening at the input layer, spatiotemporal correlation learning at the hidden layer, and demand and warning mapping at the output layer is used to construct a model for the correlation between component degradation trends and environmental loads. The hidden-layer spatiotemporal correlation learning introduces an LSTM network to capture the temporal correlation between component degradation and environmental loads, and combines it with an attention mechanism to strengthen the weights of key influencing factors. The model is constructed using a three-level network structure: "input-layer multi-source data denoising and feature screening - hidden-layer spatiotemporal correlation learning - output-layer demand and warning mapping." The input layer is responsible for eliminating data noise and screening key features, providing high-quality input for the model. The hidden layer uses an LSTM network and an attention mechanism to capture the temporal correlation between component degradation and environmental loads, as well as key influencing factors. The output layer converts the model's calculation results into directly applicable maintenance requirements and warning information, ensuring a prediction accuracy of ≥90%, meeting the precision requirements of predictive maintenance. A wavelet threshold noise reduction algorithm was used to process the collected data. For example, the original data from fan vibration acceleration data contained 5Hz high-frequency interference (caused by vibration transmission from other equipment in the workshop). By decomposing the data into five layers of wavelet coefficients and setting a noise reduction threshold of 0.05g for the high-frequency coefficients, the interference signal was removed and the data was reconstructed. The fluctuation amplitude of the vibration acceleration data was reduced from ±0.2g to ±0.08g, restoring the fan's true vibration state and preventing the model from misjudging equipment anomalies due to noise. The Pearson correlation coefficient was used to screen features strongly correlated with component degradation. For compressor degradation analysis, the initial input features included six items: compressor start / stop frequency, lubricating oil level, exhaust temperature, indoor temperature, outdoor temperature, and workshop load. The correlation coefficients between each feature and the compressor degradation level were calculated. The correlation coefficients of indoor temperature and outdoor temperature were 0.25 and 0.28, respectively, which were both below the screening threshold of 0.3 and were therefore eliminated. Four core features, namely compressor start / stop frequency (0.72), lubricating oil level (0.85), exhaust temperature (0.78), and workshop load (0.65), were retained to reduce the impact of irrelevant features on the model calculation efficiency.

[0035] A three-layer LSTM network (32 input layer neurons, 64 hidden layers, and 16 output layers) was constructed. It was fed nearly 72 hours of time-series data on compressor lubricant oil level, workshop load, and exhaust temperature. Using a gating mechanism consisting of input, forget, and output gates, the network learned how these parameters change over time. For example, given three consecutive days of time-series data, on day one, the compressor lubricant oil level was 65%, the workshop load was 80%, and the exhaust temperature was 85°C; on day two, the lubricant oil level was 62%, the load was 100%, and the exhaust temperature was 88°C; and on day three, the lubricant oil level was 60%, the load was 120%, and the exhaust temperature was 90°C. The LSTM network learned the temporal correlation that "for every 20% increase in workshop load, the compressor lubricant oil level decreases by 2% and the exhaust temperature increases by 3°C daily." Based on this trend, the network predicted that the lubricant oil level would drop to 52% (close to the lower limit of 50%) seven days later, providing data support for determining maintenance timing. An attention mechanism was introduced within the LSTM network to assign higher weight to key features that influence component degradation. Taking the heat exchanger fouling model as an example, the input features include condenser temperature, cooling water flow, workshop load, and ambient humidity. The weight of each feature is calculated through the attention mechanism. The results show that the weight of condenser temperature is 0.35, cooling water flow is 0.28, workshop load is 0.25, and ambient humidity is 0.12. Among them, the weight of condenser temperature is significantly higher than that of other features. The model automatically strengthens the impact of this feature on the fouling trend, reducing the fouling level prediction error from ±0.5 to ±0.2, thereby improving the prediction accuracy.

[0036] The model's output is validated for rationality based on the safe operating threshold constraints of core industrial air conditioning components. Abnormal data caused by sensor drift and data transmission interference are eliminated using the 3σ principle. Dynamic weighting of environmental factors is adjusted based on the environmental load fluctuation coefficient. This generates preliminary maintenance requirements and energy consumption anomaly warning information, including component maintenance priority, energy consumption anomaly type, and risk level. A dual mapping table is established: "component degradation level - maintenance requirement type" and "environmental load - warning level." Component degradation levels are categorized as Level 1 (mild degradation: performance degradation ≤10%), Level 2 (moderate degradation: performance degradation 10%-20%), and Level 3 (severe degradation: performance degradation >20%), corresponding to "routine maintenance requirements," "priority maintenance requirements," and "urgent maintenance requirements," respectively. Environmental load warning levels are categorized by the fluctuation coefficient: a "blue warning" is assigned for a coefficient of 1.0-1.2, a "yellow warning" for a coefficient of 1.2-1.5, and an "orange warning" for a coefficient >1.5. The model outputs a compressor degradation level of 2 (performance drop of 15%) and a workshop load fluctuation coefficient of 1.3 (yellow warning). The mapping table generates preliminary maintenance requirements and warning information: the maintenance requirement is "prioritize compressor maintenance, perform lubricating oil replenishment and winding insulation testing", and the warning information is "the workshop load is high (130% of the rated value), pay attention to the compressor exhaust temperature, and avoid long-term high-load operation to accelerate degradation." At the same time, the maintenance completion time limit is clearly stated as within 7 days, and the warning continuous monitoring frequency is increased to 2Hz.

[0037] Safe operating thresholds are set for each core component, such as a compressor lubricant oil level threshold of 50%-80%, a motor winding insulation resistance threshold of ≥100MΩ, and a refrigerant high-pressure pressure threshold of ≤2.5MPa. If the model outputs "compressor lubricant oil level 45%," and the thresholds are compared to find it's below the lower limit, a retrospective look at the data collection process reveals that the oil level sensor is drifting (oil obstruction causing low values). After cleaning the sensor, the actual oil level is 60%, and the model output is corrected to avoid misjudgments of maintenance needs due to sensor failure. For example, nearly 100 sets of indoor temperature data were collected, with a calculated mean of 24°C and a standard deviation of 1.2°C. Using the 3σ principle, the normal data range is determined to be 24°C - 3 × 1.2 = 20.4°C to 24°C + 3 × 1.2 = 27.6°C. The indoor temperature was recorded at 30°C, exceeding the 3σ range and thus identified as abnormal data. After verifying the sensor's location, it was discovered that the anomaly was caused by data transmission interference (the sensor was exposed to direct sunlight, an anomaly caused by environmental interference). This data was discarded and data collected by a backup sensor (located in the shade) was used instead (25°C), ensuring that the data input into the model was authentic and valid.

[0038] The model adjusts the weights of environmental factors based on the environmental load fluctuation coefficient. When the fluctuation coefficient is less than 0.8 (low load conditions), the environmental factor weight is reduced from a base value of 0.4 to 0.3, while the weight of core component data is increased to 0.7. This prevents environmental factors from excessively influencing model results under low load conditions. When the fluctuation coefficient is between 1.0 and 1.2 (normal load), the weight remains at the base value. When the fluctuation coefficient is greater than 1.2 (high load), the environmental factor weight is increased to 0.5. For example, due to a production plan adjustment, the load of a workshop suddenly increased from 90% (fluctuation coefficient of 0.9) to 130% (fluctuation coefficient of 1.3). The system automatically increased the weights of environmental factors (indoor temperature and load) from 0.4 to 0.5 and recalculated the model output. Before the adjustment, the model predicted an energy consumption anomaly rate of 5%. After the adjustment, the predicted energy consumption anomaly rate was revised to 8%, taking into account the impact of high load on energy consumption. This more closely reflects actual operating conditions and provides a more accurate basis for energy consumption anomaly warnings.

[0039] Component maintenance priority is determined using a scoring method based on "degradation level x component impact coefficient." Component impact coefficients are set based on equipment importance (compressor 1.2, heat exchanger 1.0, fan 0.8, filter 0.6). For example, in an air conditioning system, the compressor has a degradation level of 2 (score 2 x 1.2 = 2.4), the heat exchanger has a degradation level of 1 (1 x 1.0 = 1.0), the filter blockage level is 2 (2 x 0.6 = 1.2), and the fan has a degradation level of 1 (1 x 0.8 = 0.8). The maintenance priority, ranked from highest to lowest by score, is "compressor > filter > heat exchanger > fan." This generates a preliminary maintenance requirement: "Prioritize compressor maintenance (lubricant replenishment and insulation testing) within 7 days, followed by filter cleaning within 10 days. Heat exchangers and fans should be maintained according to the regular 30-day maintenance cycle."

[0040] Combining energy consumption data with model output results, the type of energy consumption anomaly is determined and the risk level is assigned. For example, during the peak period (10:00-12:00), the measured energy consumption is 80 kWh, 33% higher than the historical average of 60 kWh for the same period. Correlation with the model data reveals "mild scaling of the heat exchanger (an 8% decrease in heat exchange efficiency) combined with an excessively high indoor temperature setting (26°C to 28°C)." The energy consumption anomaly is determined to be "peak consumption excess due to decreased heat exchange efficiency and improper parameter settings." Based on the rule that "energy consumption excesses of 10%-20% are yellow risk, 20%-30% are orange risk, and >30% are red risk," the risk level is assigned to "red," and an energy consumption anomaly warning message is generated: "Peak energy consumption exceeds historical average by 33% (red risk). It is recommended to clean the heat exchanger (expected to increase heat exchange efficiency by 8%) and lower the indoor temperature to 26°C, which is expected to reduce peak energy consumption by 15%-20%. Optimization measures must be implemented within three days."

[0041] S103 processes preliminary maintenance requirements and abnormal energy consumption warning information, simulates the equipment operating status at different maintenance times through digital twin technology, designs a hierarchical maintenance strategy based on the full life cycle cost model, imposes component remaining life threshold constraints and maintenance resource optimal configuration objective functions, and generates target maintenance execution instructions and energy-saving potential analysis reports.

[0042] In one implementation, component degradation level data from preliminary maintenance requests is categorized and labeled, maintenance timelines are graded, and priority rankings are performed to generate basic component maintenance parameters. A three-level degradation standard is used to categorize and label component status: Level 1 (mild degradation) indicates a performance degradation of ≤10% with no risk of failure; Level 2 (moderate degradation) indicates a performance degradation of 10%-20% with a potential risk of failure; and Level 3 (severe degradation) indicates a performance degradation of >20% with the potential for failure in the near future. For example, for a compressor, preliminary monitoring data revealed a 12% overall performance degradation of 12% with a lubricant level of 60% (normal range 50%-80%) and a winding insulation resistance of 90 MΩ (normal range ≥100 MΩ), resulting in a 12% overall performance degradation, designated "Level 2 degradation." A heat exchanger with an 8% decrease in heat exchange efficiency due to fouling is designated "Level 1 degradation." A clogged filter results in a 15% decrease in ventilation volume, designated "Level 2 degradation."

[0043] Maintenance timelines are tiered based on the degradation level and component importance. Level 1 degradation components (low risk) have a maintenance timeline of 30 days, Level 2 degradation components (medium risk) have a timeline of 7-15 days, and Level 3 degradation components (high risk) have a timeline of 72 hours. For example, a compressor, a core component (with downtime losses of 500 yuan per hour), has a Level 2 degradation rate, but the timeline is shortened to 10 days. A heat exchanger, a non-core component with Level 2 degradation, has a timeline of 15 days. A filter, with Level 2 degradation but low replacement cost, has a timeline of 12 days.

[0044] Prioritize components using "degradation level x component importance coefficient" (importance coefficient: compressor 1.2, heat exchanger 1.0, fan 0.8, filter 0.6). Components are sorted from highest to lowest by score, and basic maintenance parameters (including degradation level, maintenance timeliness, priority score, and core maintenance details) are generated simultaneously. For example: Compressor score = 2 x 1.2 = 2.4, Heat exchanger score = 1 x 1.0 = 1.0, Filter score = 2 x 0.6 = 1.2, Fan score = 1 x 0.8 = 0.8. The resulting ranking is "Compressor > Filter > Heat Exchanger > Fan." The basic parameters are: Compressor (Level 2 degradation, maintenance within 10 days, priority 2.4, maintenance details: lubricant replenishment and insulation testing), Filter (Level 2 degradation, maintenance within 12 days, priority 1.2, maintenance details: filter cleaning / replacement), etc.

[0045] Energy consumption fluctuation data from abnormal energy consumption warning information is analyzed by identifying abnormality types, breaking down influencing factors, and calculating energy-saving potential. This generates energy consumption optimization analysis parameters, including characteristic matching model parameters for energy consumption anomalies, the impact coefficients of environmental loads / equipment conditions / operating parameters on energy consumption, and quantitative calculation rules for energy-saving potential under different abnormal scenarios. Energy consumption fluctuation data is extracted from abnormal energy consumption warning information. By "identifying abnormality types to locate the essence of the problem, breaking down influencing factors to identify key causes, and calculating energy-saving potential to quantify optimization potential," energy consumption optimization analysis parameters containing characteristic matching parameters, impact coefficients, and calculation rules are generated to provide a basis for subsequent energy-saving strategy formulation. Based on the comparison of energy consumption fluctuation characteristics (such as peak overconsumption, high no-load consumption, and sustained high consumption) with historical data, abnormality types are identified to locate the essence of the problem. For example, during the air conditioning peak period (10:00-12:00), a workshop's energy consumption was 80 kWh, 33% higher than the historical average of 60 kWh for the same period, and the fluctuation curve showed a "continuously rising" trend (not instantaneous fluctuations). Combined with the heat exchanger fouling data, this was identified as "peak consumption caused by decreased heat exchange efficiency." During the nighttime no-load period (23:00-7:00), energy consumption was 15 kWh, 87.5% higher than the normal no-load value of 8 kWh. Associated with the fan speed data (maintaining 1200 r / min when no-load, while the normal value should be 800 r / min), this was identified as "high no-load consumption caused by unreasonable operating parameter settings."

[0046] Fishbone diagram analysis was used to deconstruct influencing factors to identify key contributing factors. These factors were categorized into three categories: environmental load (e.g., workshop production load), equipment operating conditions (e.g., component degradation), and operating parameters (e.g., fan speed, set temperature). The impact coefficients of environmental load, equipment operating conditions, and operating parameters on energy consumption were calculated (the coefficient ranges from 0 to 1, with larger coefficients indicating a more significant impact). For example, for "peak excess energy consumption," the analysis yielded the following: environmental load (workshop load 120% of rated value, impact coefficient 0.3), equipment operating conditions (mild fouling on the heat exchanger, impact coefficient 0.4), and operating parameters (room temperature set at 28°C, normal 26°C, impact coefficient 0.3). The combined impact coefficient of these three factors was 1.0, covering all abnormal contributing factors. For "high no-load energy consumption," the analysis yielded the following: operating parameters (excessive fan speed, impact coefficient 0.8) and equipment operating conditions (mild wear on fan bearings, impact coefficient 0.2), clearly identifying fan speed as the primary contributing factor.

[0047] Based on influencing factors and energy consumption fluctuation data, energy-saving space is calculated to quantify optimization potential, and energy consumption optimization analysis parameters are simultaneously generated (including characteristic matching model parameters for energy consumption anomalies, the impact coefficients of environmental load / equipment operating conditions / operating parameters on energy consumption, and quantitative calculation rules for energy-saving potential under different abnormal scenarios). Example: For "peak overconsumption", the quantitative calculation rule for energy-saving potential under different abnormal scenarios is "Energy-saving potential = (measured energy consumption - baseline energy consumption) × Σ (influencing factor optimization rate × influence coefficient)", where the baseline energy consumption is 60kWh, the optimization rate after heat exchanger cleaning is 8% (influence coefficient 0.4), the optimization rate when the indoor temperature is lowered to 26°C is 10% (influence coefficient 0.3), and the optimization rate when the load is reduced to 100% is 5% (influence coefficient 0.3). The calculated energy-saving potential = (80-60) × (8% × 0.4 + 10 %×0.3+5%×0.3)=20×(0.032+0.03+0.015)=1.54kWh / peak segment; the energy consumption optimization analysis parameters finally generated include: characteristic matching model parameters for energy consumption anomalies (peak segment energy consumption excess >20% and heat exchange efficiency decrease >5%), the influence coefficients of environmental load / equipment operating conditions / operating parameters on energy consumption (environmental load 0.3, equipment operating conditions 0.4, operating parameters 0.3), and quantitative calculation rules for energy-saving potential under different abnormal scenarios (the above calculation formula).

[0048] Using digital twin technology, equipment operating status at different maintenance times is simulated. Maintenance timing decision parameters are generated through pre-, mid-, and post-maintenance equipment performance simulations, component life degradation simulations at different maintenance intervals, and dynamic measurement of the impact of maintenance interventions on energy consumption. A digital twin model of an industrial air conditioner (replicating the equipment structure, operating logic, and environmental interactions at a 1:1 ratio) is constructed. By simulating equipment operating status at different maintenance times (e.g., immediate maintenance, maintenance after 7 days, and maintenance after 15 days), the model outputs performance changes before, during, and after maintenance, life degradation trends, and energy consumption impact data. Maintenance timing decision parameters (including the optimal maintenance window, post-maintenance performance recovery rate, and energy consumption improvement rate) are generated. Equipment performance simulations before, during, and after maintenance are performed. Current equipment status parameters (e.g., compressor second-stage degradation, heat exchanger first-stage degradation) are input into the digital twin model to simulate key performance indicators at different maintenance stages. Example: For a compressor (level 2 degradation, current exhaust temperature 90°C, normal ≤85°C), the simulation of the "immediate maintenance" scenario: the exhaust temperature is 90°C before maintenance, and the machine is shut down for 2 hours during maintenance (lubricant replacement and insulation inspection). After maintenance, the exhaust temperature drops to 82°C, and the performance recovery rate is 95%; the simulation of the "maintenance after 7 days" scenario: the exhaust temperature rises to 93°C before maintenance (deterioration worsens), and drops to 83°C after maintenance, and the performance recovery rate is 93%; the simulation of the "maintenance after 15 days" scenario: the exhaust temperature rises to 98°C before maintenance (close to the failure threshold of 100°C), and drops to 85°C after maintenance, and the performance recovery rate is 90%, and some aging components need to be replaced.

[0049] Component life decay simulation under different maintenance intervals simulates the impact of different maintenance intervals (such as 30 days, 60 days, and 90 days) on the remaining life of the component, generating a life decay curve. For example, for a wind turbine (currently estimated to have a remaining life of 180 days), a simulation with a "30-day maintenance interval" shows that the lifespan recovers to 90% of its initial value after each maintenance, with a remaining lifespan of 120 days after 180 days. A simulation with a "60-day maintenance interval" shows that the lifespan decays faster, with a remaining lifespan of only 80 days after 180 days. A simulation with a "90-day maintenance interval" shows that a minor fault occurs within 180 days, reducing the remaining lifespan to 50 days. Through comparison, the optimal maintenance interval is determined to be 30 days, corresponding to a life decay coefficient (lifespan recovery rate after each maintenance) of 0.9.

[0050] Dynamically measure the impact of maintenance interventions on energy consumption, calculating the energy consumption improvement effect of maintenance interventions at different maintenance timings. For example, for a heat exchanger (Level 1 degradation, with current peak energy consumption increasing by 8% due to scaling), a simulation of "immediate maintenance" shows that peak energy consumption drops from 80kWh to 75kWh after maintenance, a 6.25% improvement. A simulation of "maintenance after 7 days" shows that, due to increased scaling, peak energy consumption drops to 76kWh after maintenance, a 5% improvement. A simulation of "maintenance after 15 days" shows that scaling progresses to Level 2, and peak energy consumption drops to 78kWh after maintenance, a 2.5% improvement. Combining performance and energy consumption data, maintenance timing decision parameters are generated: the optimal maintenance window is "immediate maintenance - within 7 days," with a performance recovery rate ≥93% and an energy consumption improvement rate ≥5%.

[0051] Combined with the full lifecycle cost model, the tiered maintenance strategy is analyzed for cost composition, benefit return calculations, and resource adaptation planning to generate maintenance strategy optimization parameters. The cost composition of different maintenance plans within the tiered maintenance strategy is analyzed, breaking down each cost and quantifying the amount. Example: For a compressor (level 2 degradation, priority 1), the cost of the "priority maintenance" strategy is analyzed as follows: maintenance cost (200 yuan for labor + 150 yuan for lubricant = 350 yuan), downtime loss (2 hours x 500 yuan / hour = 1000 yuan), and energy consumption cost (energy consumption decreases by 5% after maintenance, saving 120 yuan per month). The cost of the "routine maintenance" strategy (maintenance after 15 days) is analyzed as follows: maintenance cost (additional component replacement due to worsening degradation, adding 300 yuan, for a total of 650 yuan), downtime loss (2 hours x 500 yuan / hour = 1000 yuan), and energy consumption cost (approximately 80 yuan more electricity consumption over 15 days, reducing the monthly savings to 80 yuan). By comparison, the total cost of "priority maintenance" (1350 yuan - 120 yuan = 1230 yuan) is lower than that of "routine maintenance" (1650 yuan - 80 yuan = 1570 yuan).

[0052] Based on a life cycle cost model, a benefit-return calculation was conducted to calculate the ratio of benefits (including failure avoidance and energy savings) to costs (cost-benefit ratio) for different maintenance strategies. A strategy is considered feasible if the ratio is greater than 1. For example, the benefits of the "priority maintenance" strategy include: avoided compressor failure losses (single failure repair cost 5,000 yuan) and monthly energy savings of 120 yuan (annualized 1,440 yuan). The total benefit = 5,000 + 1,440 = 6,440 yuan; the cost-benefit ratio is 6,440 yuan / 1,230 yuan, which is 5.24 (greater than 1, feasible). The benefits of the "routine maintenance" strategy include: avoided failure losses of 5,000 yuan and monthly energy savings of 80 yuan (annualized 960 yuan). The total benefit = 5,960 yuan; the cost-benefit ratio is 5,960 yuan / 1,570 yuan, which is 3.79 (greater than 1, but lower than the priority maintenance strategy).

[0053] Based on the company's current maintenance resource availability (such as labor, spare parts, and funding), resource adaptation planning is performed for the tiered maintenance strategy. Resource allocation plans for different strategies are developed, and maintenance strategy optimization parameters are generated. For example, if the company currently has two maintenance personnel available and sufficient compressor lubricant spare parts, the "Priority Maintenance" strategy can immediately allocate one person and one set of spare parts, completing the work within three days. The resulting maintenance strategy optimization parameters include: optimal maintenance level (compressor priority maintenance, filter routine maintenance, heat exchanger routine maintenance), cost-benefit ratio (compressor priority maintenance 5.24, filter routine maintenance 3.12), and resource adaptation plan (1 maintenance personnel / time, 1 set of lubricant spare parts / time, downtime 2 hours / unit).

[0054] By applying component remaining life threshold constraints and a maintenance resource allocation objective function, these parameters are integrated and optimized. The feasibility of the maintenance plan is verified using the remaining life lower limit, and the maintenance task schedule is adjusted to maximize resource utilization. This generates target maintenance execution instructions and an energy-saving potential analysis report. Using the dual constraints of the component remaining life threshold constraint (e.g., remaining life of core components ≥ 100 days) and the maintenance resource allocation objective function (e.g., maximizing maintenance resource utilization, with a target value ≥ 90%), the system integrates and optimizes the basic maintenance parameters, energy consumption optimization analysis parameters, maintenance timing decision parameters, and maintenance strategy optimization parameters. The feasibility of the maintenance plan is verified, the task schedule is adjusted, and the target maintenance execution instructions (including specific maintenance tasks, time, and resources) and an energy-saving potential analysis report (including quantitative energy-saving targets and implementation paths) are generated. The current remaining life data of each component is input to verify whether the maintenance plan meets the "remaining life ≥ lower limit" (100 days for core components, 60 days for non-core components). For example, the compressor's current estimated remaining life is 150 days. If the "maintenance after 7 days" plan is used, the remaining life will be restored to 200 days after maintenance, meeting the ≥100-day constraint. The fan's current estimated remaining life is 180 days. If the "30-day maintenance interval" plan is used, the remaining life is always ≥120 days, meeting the constraint. If a component (such as an old filter) currently has a remaining life of only 50 days (lower than the lower limit of 60 days for non-core components), the maintenance plan is adjusted to "immediate maintenance" to avoid failures caused by insufficient life.

[0055] With the goal of maximizing maintenance resource utilization (target ≥90%), adjust maintenance task scheduling (e.g., staggering maintenance of multiple devices to avoid idle resources). For example, a company currently has two maintenance personnel, one set of compressor spare parts, and two sets of filter spare parts. The initial schedule is "Day 1 compressor maintenance (1 person), Day 3 filter maintenance (1 person)," resulting in only 50% resource utilization. After optimization, the schedule becomes "Day 1 morning compressor maintenance (1 person), afternoon filter maintenance for both devices (1 person)," achieving 100% personnel utilization, 100% spare parts utilization, and 100% resource utilization (exceeding the target value).

[0056] The target maintenance execution instructions are: "1. Compressor: Maintenance level priority, execution time Day 1 morning, maintenance content: replenishing lubricating oil (1 set of spare parts) + testing winding insulation, maintenance personnel 1, downtime 2 hours; 2. Filter: Maintenance level: Routine, execution time Day 1 afternoon, maintenance content: cleaning / replacement (2 sets of spare parts), maintenance personnel 1, downtime 1 hour / unit; 3. Heat exchanger: Maintenance level: Routine, execution time Day 7 morning, maintenance content: cleaning scale, maintenance personnel 1, downtime 1.5 hours";

[0057] The energy-saving potential analysis report is as follows: "1. Peak over-consumption optimization: Through compressor maintenance (energy consumption improvement rate of 5%) + heat exchanger maintenance (energy consumption improvement rate of 6.25%), peak energy consumption is reduced from 80kWh to 72kWh, and monthly energy savings are approximately 240kWh, equivalent to an electricity bill of 192 yuan (peak electricity price of 0.8 yuan / kWh); 2. No-load high-consumption optimization: Through fan speed parameter adjustment (influence coefficient of 0.8), no-load energy consumption is reduced from 15kWh to 9kWh, and monthly energy savings are approximately 180kWh, equivalent to an electricity bill of 54 yuan (off-peak electricity price of 0.3 yuan / kWh); 3. Total energy-saving target: Monthly energy saving of 420kWh, annual energy saving of 5040kWh, and energy-saving benefits of approximately 4032 yuan."

[0058] S104: Based on the corresponding adaptive algorithm, the target maintenance execution instructions and energy-saving potential analysis reports are processed. In combination with the indoor thermal comfort requirements and the peak-valley electricity price mechanism of the power grid, the air-conditioning operating parameters are adjusted in real time to generate a linkage control plan that takes into account both maintenance effects and energy consumption optimization.

[0059] In one implementation, adaptive feature matching and time-series correlation are performed on the maintenance period requirements, component protection parameters, and energy consumption anomaly data and energy saving target values ​​in the target maintenance execution instructions, along with the energy consumption anomaly data and energy saving target values ​​in the energy saving potential analysis report, to generate maintenance demand features and energy consumption optimization features. The target maintenance execution instructions extract maintenance period requirements (e.g., maintenance windows, downtime duration) and component protection parameters (e.g., allowable component operating temperature, pressure thresholds). Energy consumption anomaly data (e.g., peak overconsumption values, duration of high no-load consumption) and energy saving target values ​​(e.g., monthly kWh energy savings, percentage energy consumption reduction) from the energy saving potential analysis report. Through "adaptive feature matching + time-series correlation mapping," the unstructured instructions and report data are converted into standardized maintenance demand features (including time constraints and parameter constraints) and energy consumption optimization features (including anomaly features and target features).

[0060] The target maintenance execution instructions are clear: "The compressor maintenance period is Day 19:00-11:00 (shutdown for 2 hours), and the component protection parameters are the compressor exhaust temperature ≤90°C and the lubricating oil level ≥55% before and after maintenance; the filter maintenance period is Day 114:00-15:00 (shutdown for 1 hour), and the component protection parameters are the ventilation volume attenuation rate after maintenance ≤8%." Through adaptive feature matching, the "maintenance period 9:00-11:00" is matched with the "time constraint feature (T1: 9:00-11:00, shutdown for 2 hours)" and the "exhaust temperature ≤ 90°C, lubricating oil level ≥ 55%" is matched with the "parameter constraint feature (P1: exhaust temperature ≤ 90°C, P2: lubricating oil level ≥ 55%)"; similarly, the filter maintenance is matched with the "time constraint feature (T2: 14:00-15:00, shutdown for 1 hour)" and the "parameter constraint feature (P3: ventilation volume attenuation rate ≤ 8%)". The maintenance requirement feature is integrated to generate: {T1, T2, P1, P2, P3}.

[0061] The energy saving potential analysis report shows that "abnormal energy consumption during the peak period (10:00 AM - 12:00 PM) is 80 kWh (historical average: 60 kWh, 33% overconsumption), and abnormal energy consumption during the no-load period (11:00 PM - 7:00 AM) is 15 kWh (normal average: 8 kWh, 87.5% overconsumption); the monthly energy saving target is 240 kWh during peak period and 180 kWh during no-load period." Through adaptive feature matching, the "33% overconsumption during peak period and 87.5% overconsumption during no-load period" are matched to the "abnormal energy consumption feature (E1: peak period overconsumption > 20%, E2: no-load overconsumption > 50%)" and the "240 kWh monthly peak period energy saving and 180 kWh monthly no-load energy saving" are matched to the "energy saving target feature (G1: monthly peak period energy saving of 240 kWh, G2: monthly no-load energy saving of 180 kWh)." These features are then integrated to generate the energy consumption optimization feature: {E1, E2, G1, G2}.

[0062] Based on maintenance demand characteristics and energy consumption optimization characteristics, the adaptive algorithm generates dual-objective optimization weights, combining the temperature and humidity threshold ranges and perceived comfort weight coefficients in indoor thermal comfort requirements with the time period division standards and price fluctuation ratios in the power grid's peak and valley electricity pricing mechanism. The maintenance demand characteristics are linked to the energy consumption optimization characteristics along the time dimension to avoid conflicts between maintenance periods and periods of high energy consumption. For example, the compressor maintenance period T1 (9:00-11:00) partially overlaps with the peak period (10:00-12:00). After association, the adjusted feature is "T1': 9:00-10:00 (avoiding the core period of the peak period after 10:00), while strengthening P1 (exhaust temperature ≤ 88°C) to reduce the impact of peak energy consumption"; the filter maintenance period T2 (14:00-15:00) is a flat period (electricity price 0.5 yuan / kWh), there is no conflict, and the original feature remains unchanged; the final feature set after association is the maintenance demand feature {T1', T2, P1', P2, P3} and the energy consumption optimization feature {E1, E2, G1, G2}.

[0063] With the dual objectives of "achieving maintenance effectiveness" and "minimizing energy costs," this method combines the temperature and humidity thresholds (22-26°C, 40%-60%) and perceived comfort weight coefficient (weight of 1.0 at 24°C, decreasing by 0.1 for every 1°C deviation; weight of 1.0 at 50% RH, decreasing by 0.1 for every 5% deviation) specified in indoor thermal comfort requirements with the time period division criteria in the power grid's peak-valley electricity pricing mechanism (valley period: 23:00-7:00 AM, flat periods: 7:00-10:00 AM and 3:00 PM-23:00 PM, peak period: 10:00 AM-3:00 PM), and the price fluctuation ratio (peak period fluctuates 167% compared to valley period). Through "constraint quantification and dynamic weight allocation," the algorithm generates the dual-objective optimization weights (maintenance target weight W1, energy consumption target weight W2, with W1 + W2 = 1) for the adaptive algorithm. This ensures that the weight allocation meets both equipment maintenance needs and energy conservation and comfort requirements.

[0064] The current indoor temperature is 25°C (sensory weight 0.9), and the humidity is 55% (sensory weight 0.9). The comprehensive thermal comfort quantified value is (0.9 + 0.9) / 2 = 0.9. The current time period is the peak period (10:00-12:00), and the electricity price quantified value is 0.8 / 0.3 ≈ 2.67 (the multiple of the peak price relative to the off-peak price). The maintenance target base weight W10 is 0.5, and the energy consumption target base weight W20 is 0.5. The quantified values ​​are dynamically adjusted based on the constraints: when the comprehensive thermal comfort quantified value is ≥ 0.8, W10 remains unchanged; if it is < 0.8, W1 (maintenance weight) is decreased by 0.1, and W2 (energy consumption weight) is increased by 0.1 (prioritizing energy conservation to improve comfort). If the current quantized value is 0.9 ≥ 0.8, W1 remains unchanged. When the electricity price quantized value is ≥ 2.0 (peak period), W2 is increased by 0.1 and W1 is decreased by 0.1 (prioritizing energy conservation). When the electricity price quantized value is 1.0 < 2.0 (flat period), the weight remains unchanged. When the electricity price quantized value is ≤ 1.0 (valley period), W2 is decreased by 0.1 and W1 is increased by 0.1 (prioritizing maintenance). If the current quantized electricity price quantized value is 2.67 ≥ 2.0, W2 is increased by 0.1 and W1 is decreased by 0.1. The final dual-objective optimization weights of the adaptive algorithm are W1 = 0.5 - 0.1 = 0.4 (maintenance objective weight), and W2 = 0.5 + 0.1 = 0.6 (energy consumption objective weight).

[0065] Verify whether the weights meet the requirement of "maintenance needs are not ignored" and set the minimum threshold of W1 to 0.3. The current W1=0.4>0.3 meets the requirement. If the quantitative value of thermal comfort in a certain period is 0.7 (<0.8) and the quantitative value of electricity price is 2.5 (≥2.0), then W1=0.5-0.1-0.1=0.3 (reaching the minimum threshold), and W2=0.7, to avoid equipment damage caused by too low maintenance weight.

[0066] Input the initial parameters for iteration: compressor start / stop frequency 4 times / hour (maintenance allowable range 3-5 times / hour), fan speed 1400 rpm (maintenance allowable range 1200-1500 rpm), and indoor set temperature 25°C (thermal comfort range 22-26°C). The optimization objective function of the adaptive algorithm is: Min((1-W1)×maintenance parameter deviation+W2×energy consumption deviation), where maintenance parameter deviation = (measured component parameter - protection threshold) / protection threshold, and energy consumption deviation = (measured energy consumption - energy saving target value) / energy saving target value. The iterative process is as follows: 1st iteration: parameter combination (4 times / hour, 1400 rpm, 25°C), maintenance parameter deviation 0.05 (compressor exhaust temperature 88°C, protection threshold 90°C, deviation (88-90) / 90 ≈ -0.02, absolute value 0.02; lubricating oil level 58%, protection threshold 55%, deviation 0.05, comprehensive deviation (0.02 + 0.05) / 2 = 0.035), energy consumption deviation 0.1 (peak period measured energy consumption 78 kWh, energy saving target 72 kWh, deviation (78-72) / 72 ≈ 0.083); objective function value = (1-0.4) × 0.035 + 0.6 × 0. 083≈0.069; 50th iteration (convergence): parameter combination (3 times / hour, 1300 r / min, 26°C), maintenance parameter deviation 0.02 (exhaust temperature 87°C, deviation 0.033; lubricating oil level 60%, deviation 0.09, comprehensive deviation 0.0615 → 0.02 after correction, because some parameters are better than the threshold, the lower limit of the deviation is taken), energy consumption deviation 0.01 (peak period measured energy consumption 72.7 kWh, deviation (72.7-72) / 72≈0.0097≈0.01); objective function value = 0.6×0.02+0.6×0.01=0.018≤0.01 (convergence error), iteration ends.

[0067] Based on the dual-objective optimization weights and the parameter iteration output of the adaptive algorithm, the air conditioning operating parameters are adjusted in real time to generate a coordinated control scheme that balances maintenance effectiveness and energy consumption optimization. Based on the dual-objective optimization weights (maintenance target weight W1=0.4, energy consumption target weight W2=0.6) and the parameter iteration output of the adaptive algorithm (50th iteration convergence parameters: compressor start and stop frequency 3 times / hour, fan speed 1300r / min, indoor set temperature 26°C), the air conditioning operating parameters are adjusted in real time. Specifically, the compressor: start and stop frequency is reduced from 4 times / hour to 3 times / hour (reducing start and stop losses and meeting the maintenance parameter deviation requirement of 0.02), while avoiding the maintenance period T1' (9:00-10:00). , adjusted to start after 10:00 to avoid overlap of shutdown and peak period; fan: speed reduced from 1400r / min to 1300r / min (reduce energy consumption, peak energy consumption reduced from 78kWh to 72.7kWh, close to the energy-saving target value of 72kWh); indoor set temperature: increased from 25℃ to 26℃ (within the thermal comfort range, reducing cooling capacity consumption and helping to optimize energy consumption); at the same time, adjust the refrigerant pressure: high pressure pressure reduced from 2.0MPa to 1.9MPa (maintenance allowable range 1.8-2.2MPa) to reduce the load on the compressor.

[0068] The final linkage control scheme that takes into account both maintenance effect and energy consumption optimization includes the three-dimensional correlation content of "time period-parameter-target", realizing the dynamic coordination of maintenance and energy saving. Specifically, during the peak period (10:00-15:00): the compressor start-stop frequency is 3 times / hour, the fan speed is 1300r / min, the indoor set temperature is 26℃, and the refrigerant high pressure is 1.9MPa. The target is: maintenance parameter deviation ≤0.02, peak energy consumption ≤73kWh; maintenance period T1' (9:00-10:00): the compressor is shut down, The fan speed is reduced to 1200 r / min (maintaining basic ventilation), the indoor temperature is set at 24°C (to avoid excessive temperature fluctuations), and the targets are: compressor lubricant level ≥ 55%, and indoor temperature fluctuation ≤ 2°C during downtime. During the no-load period (23:00-7:00): the compressor is started and stopped twice per hour (off-peak electricity prices are low, so maintenance can be appropriately reduced), the fan speed is 1200 r / min, the indoor temperature is set at 23°C, and the target is: no-load energy consumption ≤ 9.5 kWh (close to the energy saving target of 9 kWh), with no abnormal component parameters. Through dynamic parameter adjustment and time-based target setting, while ensuring equipment maintenance requirements (such as component parameter compliance and life extension), precise energy consumption control is achieved (such as reduced peak energy consumption and reduced no-load losses), forming a closed-loop linkage between maintenance and energy conservation.

[0069] S105 , processing the linkage control scheme that takes into account both maintenance effect and energy consumption optimization, and generating a global coordinated operation management strategy.

[0070] In one implementation, global feature normalization and synergistic correlation extraction are performed on the single-device operating parameter adjustment rules, maintenance and energy-saving coordination thresholds, and load distribution requirements and energy supply constraints of multiple air conditioners in an industrial scenario, generating standardized synergistic features and global trend features. Taking the core parameters of three air conditioners (A, B, and C) in an industrial workshop as an example, the raw data to be normalized includes the single-device operating parameter adjustment rules: A air conditioner A's compressor start-stop frequency is 3-5 times / hour, B air conditioner 4-6 times / hour, and C air conditioner 2-4 times / hour; the maintenance and energy-saving coordination thresholds: A air conditioner A's maintenance period energy consumption limit is 73kWh, B air conditioner 75kWh, and C air conditioner 70kWh; the load distribution requirements: A air conditioner A's load area is 300kW, B air conditioner 400kW, and C air conditioner 300kW (total load 1000kW); and the energy supply constraint data: the maximum power supply power of the power grid during peak hours is 800kW, during flat hours is 1000kW, and during off-peak hours is 1200kW.

[0071] The global feature normalization process is performed using the "min-max normalization formula (normalized value = (original value - minimum value) / (maximum value - minimum value))": compressor start-stop frequency: A air conditioner (3-5) is normalized to (0-0.67), B air conditioner (4-6) is (0.33-1.0), C air conditioner (2-4) is (0-0.33); maintenance period energy consumption limit: A air conditioner 73kWh normalized value = (73-7 0) / (75-70)=0.6, air conditioner B with 75kWh is 1.0, and air conditioner C with 70kWh is 0.0; load distribution ratio (normalized load ratio): air conditioner A 30%, air conditioner B 40%, and air conditioner C 30%; energy supply limit: normalized value of 800kW in peak period = (800-800) / (1200-800)=0.0, 1000kW in flat period is 0.5, and 1200kW in valley period is 1.0.

[0072] By calculating the Pearson correlation coefficient between different parameters, synergistic correlation extraction and processing are performed to explore synergistic correlation relationships. The correlation between the operating parameters of a single device and load distribution is as follows: the correlation coefficient between the start and stop frequency of the air conditioner compressor A and the regional load is 0.82 (the higher the load, the higher the upper limit of the start and stop frequency), the air conditioner B is 0.85, and the air conditioner C is 0.78. The overall correlation average is 0.82, which is judged as "strong synergistic correlation"; the correlation between the maintenance and energy-saving synergistic threshold and energy supply: the correlation coefficient between the energy consumption upper limit during the maintenance period and the peak power supply power is -0.75 (the lower the peak power supply power, the stricter the energy consumption upper limit), which is judged as "strong negative synergistic correlation."

[0073] The standardized collaborative feature integrates normalized data and collaborative correlation to form {device number: [normalized range of start / stop frequency, normalized energy consumption upper limit, load share, and load correlation]}, such as air conditioner A: [0-0.67, 0.6, 30%, 0.82], air conditioner B: [0.33-1.0, 1.0, 40%, 0.85], and air conditioner C: [0-0.33, 0.0, 30%, 0.78]. The global trend feature is based on the collaborative correlation and energy supply data of the three air conditioners. It extracts trend features such as "When peak load is concentrated (loads of A+B+C exceed 80%), the upper limit of equipment start / stop frequency needs to be lowered by 10% to match energy supply constraints" and "Maintenance is prioritized during valley periods (sufficient energy supply, normalized value 1.0)" and quantified as "peak load-frequency adjustment coefficient 0.9" and "valley maintenance priority weight 1.2."

[0074] Based on standardized collaborative features and global trend characteristics, combined with the equipment cluster efficiency targets, total energy consumption limits, and workshop temperature and humidity zone linkage standards within the global management requirements of industrial scenarios, as well as pollutant emission control indicators, multi-dimensional adaptive weights are generated for the global collaborative algorithm. The equipment cluster efficiency target (e.g., total cooling capacity of three air conditioners ≥ 200kW) has a base weight of W10 = 0.3 (a core objective that impacts the production environment); the total energy consumption limit (e.g., daily energy consumption ≤ 1500kWh) has a base weight of W20 = 0.3 (critical for cost control); the workshop temperature and humidity zone linkage standard (e.g., temperature difference between zones ≤ 2°C, humidity 40%-60%) has a base weight of W30 = 0.25 (to ensure production processes and personnel comfort); and the pollutant emission control indicator (e.g., air conditioner refrigerant leakage rate ≤ 0.5% / year) has a base weight of W40 = 0.15 (a compliance requirement with less impact).

[0075] Weight adjustments were made based on standardized collaborative features and global trend features. The equipment efficiency weight was adjusted: the global trend feature indicated "large fluctuations in equipment efficiency during peak load concentrations." Since the current peak load ratio exceeds 80%, the equipment efficiency weight needed to be increased with a correction factor of 1.1, W1 = 0.3 × 1.1 = 0.33. The energy limit weight was adjusted: energy supply restriction data indicated "peak power supply shortages (normalized value 0.0)." Energy limit constraints were tightened with a correction factor of 1.2, W2 = 0.3 × 1.2 = 0.36. The temperature and humidity collaborative weight was adjusted: the standardized collaborative feature indicated that the temperature difference in the areas covered by the three air conditioners was currently 1.5°C (≤ 2°C, meeting the constraint), so no adjustment was required, W3 = 0.25 × 1.0 = 0.25. The emission control weight was adjusted: the current refrigerant leakage rate was 0.3% (≤ 0.5%, meeting the constraint), and there was no abnormal emission trend. The correction factor was 0.8, W4 = 0.15 × 0.8 = 0.12.

[0076] The total corrected weight = 0.33+0.36+0.25+0.12=1.06, which needs to be normalized (normalized weight = corrected weight / total): W1=0.33 / 1.06≈0.31 (equipment efficiency weight); W2=0.36 / 1.06≈0.34 (energy limit weight); W3=0.25 / 1.06≈0.24 (temperature and humidity coordination weight); W4=0.12 / 1.06≈0.11 (emission control weight); all weights are ≥0.1 (no target is ignored), and the energy limit weight is the highest (in line with the constraint of tight power supply during peak hours), followed by the equipment efficiency and temperature and humidity weights, and the emission weight is the lowest (in line with the current situation of compliance and no abnormalities). The multi-dimensional adaptation weight distribution of the global collaborative algorithm is reasonable. Key operating conditions during the forecast period: peak period (10:00-15:00, power supply 800kW), flat period (7:00-10:00, 15:00-23:00, power supply 1000kW), valley period (23:00-7:00, power supply 1200kW); 3 air conditioners require maintenance (A air conditioner compressor, B air conditioner filter, C air conditioner heat exchanger), and the total peak load is expected to be 900kW (exceeding the power supply limit).

[0077] Based on the iterative calculation results of multi-dimensional adaptation weights and global coordination algorithms, a globally coordinated operation and management strategy is generated, including a cross-device peak-shifting scheduling plan for maintenance tasks of multiple air-conditioning equipment, dynamic energy allocation rules during high-load periods, multi-device linkage control instructions when regional temperature and humidity are abnormal, and the optimal scheduling plan for maintenance resources among cluster devices. Iterative optimization objective function: Max (W1 × cluster efficiency + W3 × temperature and humidity compliance rate - W2 × energy excess rate - W4 × emission excess rate), where: cluster efficiency = actual total cooling capacity / rated total cooling capacity; energy excess rate = (actual energy consumption - limit) / limit (positive if exceeding the limit, otherwise 0); during peak periods: air conditioner A's start and stop frequency is 3 times / hour (from the original upper limit of 5 times / hour, reduced by 40%), air conditioner B's start and stop frequency is 4 times / hour (from the original upper limit of 6 times / hour, reduced by 33%), and air conditioner C's start and stop frequency is 2 times / hour (from the original upper limit of 4 times / hour, reduced by 50%). Total energy consumption is controlled at 780 kW (≤ 800 kW), and the cluster efficiency is 0.92. Maintenance of air conditioners A and C is scheduled between 2:00 PM and 4:00 AM, and between 4:00 AM and 6:00 AM. Maintenance of air conditioner B is scheduled during the off-peak period (4:00 PM to 5:00 PM, when the load is lower) to avoid temperature and humidity fluctuations caused by overlapping maintenance periods.

[0078] Multi-air conditioning equipment maintenance task cross-device staggered scheduling plan: A air conditioner (compressor maintenance) Day 12:00-4:00 (off-peak period, sufficient energy), B air conditioner (filter maintenance) Day 116:00-17:00 (normal period, load 300kW, accounting for 30%), C air conditioner (heat exchanger maintenance) Day 14:00-6:00 (off-peak period), maintenance interval ≥ 2 hours to avoid multiple equipment shutdowns in a single period causing temperature and humidity to exceed the standard; energy is used during high-load periods Dynamic allocation rule: During peak hours (10:00-15:00), energy is allocated based on "load share × efficiency weight": air conditioner A receives 30% × 0.31 ≈ 28% (224kW), air conditioner B receives 40% × 0.31 ≈ 38% (304kW), and air conditioner C receives 30% × 0.31 ≈ 34% (272kW), for a total allocation of 780kW (≤800kW). During flat / valley hours, energy is allocated based on "full load operation, with priority given to replenishing cooling capacity gaps caused by valley maintenance."

[0079] Multi-device linkage control instructions when regional temperature and humidity are abnormal: If the temperature in the area where air conditioner A is responsible rises to 28°C (exceeding the upper limit of 26°C), linkage control is triggered - air conditioner B increases the air volume by 10% (from 1300r / min to 1430r / min), air conditioner C reduces the set temperature by 0.5°C (from 25°C to 24.5°C), and the start and stop frequency of air conditioner A is temporarily increased to 4 times / hour (originally 3 times / hour) until the temperature in the area drops to 26°C; maintain the maximum balance of resources among cluster devices. Optimal scheduling plan: 2 maintenance personnel, 2 spare parts sets (1 set of compressor lubricating oil, 2 sets of filters, 1 set of heat exchanger cleaning agent), the scheduling plan is "Day12:00-4:00: 1 personnel + 1 set of lubricating oil spare parts to maintain air conditioner A; 4:00-6:00: the same personnel + 1 set of cleaning agent spare parts to maintain air conditioner C (saving personnel's round-trip time); 16:00-17:00: another personnel + 1 set of filter spare parts to maintain air conditioner B", the resource utilization rate is 100%, and there is no idleness.

[0080] S106, processing preliminary maintenance requirements and energy consumption abnormality warning information, target maintenance execution instructions, linkage control scheme that takes into account both maintenance effect and energy consumption optimization, and global coordinated operation management strategy, to generate comprehensive evaluation information on the operation status of industrial air conditioners including equipment reliability level and energy-saving benefit quantification value.

[0081] In one implementation, the component risk level and energy consumption anomaly type in preliminary maintenance requirements and energy consumption anomaly warning information are classified and quantified to generate basic assessment indicator data. Each component risk level is associated with a unique reliability coefficient, and each energy consumption anomaly type is associated with a target energy saving loss coefficient. A mapping rule is set for component risk level and reliability coefficient: mild risk (component performance degradation ≤ 10%) is associated with a unique reliability coefficient of 0.9, moderate risk (performance degradation 10%-20%) is associated with a unique reliability coefficient of 0.7, and severe risk (performance degradation > 20%) is associated with a unique reliability coefficient of 0.5. Based on preliminary maintenance requirements, the compressor's lubricating oil level was 60% (normal: 50%-80%) and insulation resistance was 90 MΩ (normal: ≥100 MΩ), resulting in a comprehensive assessment of medium risk, with a corresponding unique reliability coefficient of 0.7. Scaling on the heat exchanger resulted in an 8% decrease in heat transfer efficiency, resulting in a low risk assessment, with a corresponding unique reliability coefficient of 0.9. A clogged filter resulted in a 15% decrease in ventilation volume, resulting in a medium risk assessment, with a corresponding unique reliability coefficient of 0.7. The fan winding insulation was normal, resulting in a zero risk assessment, with a corresponding unique reliability coefficient of 1.0. Quantified component risk data was generated: compressor (0.7), heat exchanger (0.9), fan (1.0), and filter (0.7).

[0082] The mapping rules for energy consumption anomaly types and target energy-saving loss coefficients are set as follows: peak overconsumption (peak energy consumption exceeds 20% by more than 20%) corresponds to a target energy-saving loss coefficient of 1.2 (high loss); no-load high consumption (no-load energy consumption exceeds 50%) corresponds to a target energy-saving loss coefficient of 1.1; sustained high consumption (all-day energy consumption exceeds 10%) corresponds to 1.05; and no anomaly corresponds to 1.0 (no loss). Based on energy consumption anomaly warning information, peak energy consumption during the peak period (10:00-12:00) is 80 kWh (33% above the historical average), which is considered peak overconsumption and is assigned a coefficient of 1.2; energy consumption during the no-load period (23:00-7:00) is 15 kWh (87.5% above the normal average), which is considered no-load high consumption and is assigned a coefficient of 1.1; no sustained high consumption corresponds to a coefficient of 1.0. Quantified energy consumption anomaly data is generated: peak overconsumption (1.2), no-load high consumption (1.1), and sustained high consumption (1.0). Integrate quantitative data on component risks and energy consumption anomalies to form basic evaluation index data, including "component reliability coefficient set (compressor 0.7, heat exchanger 0.9, fan 1.0, filter 0.7)" and "energy consumption and energy saving loss coefficient set (peak 1.2, no-load 1.1, continuous 1.0)", and mark the data source (initial maintenance needs, energy consumption anomaly warning information) and evaluation cycle (monthly).

[0083] Basic evaluation indicator data, the maintenance completion rate and resource utilization rate in the target maintenance execution instructions, the parameter compliance rate in the linkage control scheme that balances maintenance effectiveness and energy consumption optimization, and the cluster coordination efficiency in the global coordinated operation management strategy are integrated and calculated to generate a multidimensional evaluation matrix encompassing equipment health, energy consumption, and coordination dimensions. The row vectors of the evaluation matrix represent the evaluation dimensions, and the column vectors represent the specific quantitative values. Based on the component reliability coefficients in the basic evaluation indicator data, the average value is calculated as the dimensional quantitative value, and the normalization formula is "health dimension value = (Σ component reliability coefficient) / total number of components." For example, (0.7 + 0.9 + 1.0 + 0.7) / 4 = 0.825, which is normalized to 0.83 (to two decimal places). The "maintenance completion rate" (e.g., planned maintenance of 3 items, actual completion of 3 items, 100% completion rate, normalized to 1.0) and "resource utilization rate" (2 maintenance personnel, actual use of 2 personnel, 100% utilization rate, normalized to 1.0) are also extracted from the target maintenance execution instructions.

[0084] Based on the energy-saving loss coefficients in the basic evaluation indicator data, a weighted average is calculated (peak energy consumption accounts for 40%, no-load accounts for 20%, and continuous accounts for 40%) using the formula "Energy consumption dimension value = Σ(energy-saving loss coefficient × time period ratio)." For example, 1.2 × 0.4 + 1.1 × 0.2 + 1.0 × 0.4 = 1.1, normalized to 1.1. The "parameter compliance rate" of the linkage control scheme that balances maintenance effectiveness and energy consumption optimization is extracted (for example, if all five parameters, such as compressor start / stop frequency and fan speed, meet the standards, the compliance rate is 100%, normalized to 1.0). The "cluster coordination efficiency" of the global coordinated operation management strategy is extracted (for example, if the overall load distribution balance rate of three air conditioners is 90% and the dynamic energy allocation compliance rate is 95%, the overall coordination efficiency = (90% + 95%) / 2 = 92.5%, normalized to 0.93). The "cross-device parameter coordination degree" of the linkage control scheme that balances maintenance effectiveness and energy consumption optimization is also correlated (for example, if the temperature and humidity regional difference is ≤ 2°C, the compliance rate is 100%, normalized to 1.0).

[0085] With the evaluation dimensions as row vectors and the specific quantitative values ​​as column vectors, a multi-dimensional evaluation matrix is ​​constructed as follows: Row 1 (equipment health dimension): health dimension value 0.83, maintenance completion rate 1.0, resource utilization rate 1.0; Row 2 (energy consumption dimension): energy consumption dimension value 1.1, parameter compliance rate 1.0; Row 3 (collaboration dimension): cluster collaboration efficiency 0.93, cross-device parameter collaboration 1.0; all quantitative values ​​in the matrix are in the range of 0-1.2 (the energy consumption dimension may slightly exceed 1.0 due to the loss coefficient), and the calculation basis of each parameter is marked (for example, the health dimension value comes from the average component reliability coefficient, and the cluster collaboration efficiency comes from the global strategy) to ensure traceability.

[0086] A multi-dimensional evaluation matrix was input into the industrial air conditioning operation status assessment model for weighted calculations, generating core assessment results including equipment reliability ratings and quantified energy-saving benefits. Based on the previously constructed multi-dimensional evaluation matrix (Row 1 (Equipment Health): Health value 0.83, Maintenance Completion Rate 1.0, Resource Utilization 1.0; Row 2 (Energy Consumption): Energy Consumption value 1.1, Parameter Compliance Rate 1.0; Row 3 (Collaboration): Cluster Collaboration Efficiency 0.93, Cross-Device Parameter Collaboration 1.0), this matrix was input into the industrial air conditioning operation status assessment model for calculations. Weights were assigned to each dimension in the model: 0.4 for Equipment Health (core, impacting equipment safety), 0.35 for Energy Consumption (critical, impacting costs), and 0.25 for Collaboration (auxiliary, impacting overall efficiency). Quantitative assessments were achieved through weighted calculations. The weighted calculation formula is: comprehensive evaluation value = (weighted sum of equipment health dimension) × 0.4 + (weighted sum of energy consumption dimension) × 0.35 + (weighted sum of synergy dimension) × 0.25, where the weighted sum of each dimension = Σ (parameter value within the dimension × parameter weight, parameter weight within the dimension is equally divided).

[0087] The calculation process is as follows: the weighted sum of the equipment health dimension = (0.83 × 1 / 3 + 1.0 × 1 / 3 + 1.0 × 1 / 3) ≈ 0.943; the weighted sum of the energy consumption dimension = (1.1 × 1 / 2 + 1.0 × 1 / 2) = 1.05; the weighted sum of the synergy dimension = (0.93 × 1 / 2 + 1.0 × 1 / 2) = 0.965; and the comprehensive assessment value = 0.943 × 0.4 + 1.05 × 0.35 + 0.965 × 0.25 ≈ 0.377 + 0.368 + 0.241 ≈ 0.986. Based on the comprehensive assessment value of 0.986 ≥ 0.9, the equipment reliability level is determined to be A, with the annotation "Overall equipment operation is safe, and core component risks are controllable."

[0088] Based on energy consumption data and grid electricity prices, the energy-saving benefit was calculated. The potential for optimizing peak overconsumption is to reduce peak energy consumption from 80 kWh to 72 kWh (target value). With a monthly peak duration of 60 hours and an electricity price of 0.8 yuan / kWh, the energy-saving benefit is calculated as (80 - 72) × 60 × 0.8 = 384 yuan. The potential for optimizing no-load high-consumption is to reduce no-load energy consumption from 15 kWh to 9 kWh (target value). With a monthly no-load duration of 480 hours and an electricity price of 0.3 yuan / kWh, the energy-saving benefit is calculated as (15 - 9) × 480 × 0.3 = 864 yuan. The total energy-saving benefit is calculated as 384 + 864 = 1,248 yuan / month. The core evaluation results were generated, specifically: an A equipment reliability rating (comprehensive evaluation value of 0.986) and a monthly energy-saving benefit of 1,248 yuan. A detailed weighting of each dimension and the energy-saving calculation process are provided to ensure the verifiability of the results.

[0089] The core assessment results trigger a visualization mechanism for assessment information, generating a visual assessment report. This report includes an equipment reliability trend curve, a bar chart comparing energy-saving benefits, and a radar chart showing the health status of each core component. Specifically, the equipment reliability trend curve extracts the comprehensive assessment values ​​for the past six months (January: 0.85, February: 0.88, March: 0.92, April: 0.95, May: 0.96, and June: 0.986). The curve is plotted with "month" on the horizontal axis and "comprehensive assessment value" on the vertical axis, with grade boundaries marked (0.9 for Grade A and 0.8 for Grade B). The curve shows a positive trend, with a gradual increase from Grade B in January to Grade A in June. The caption reads, "Equipment reliability continues to improve, primarily due to the effective reduction of component risks through predictive maintenance."

[0090] The energy-saving benefit comparison bar chart plots "Energy Consumption Type" (peak excess consumption, no-load high consumption, and total energy savings) on the horizontal axis and "Energy Savings Amount (CNY / month)" on the vertical axis. Peak excess consumption saves 384 CNY, no-load high consumption saves 864 CNY, and total energy savings is 1,248 CNY. The chart also shows a comparison of "Energy Consumption Before Optimization" and "Target Energy Consumption After Optimization" (e.g., peak excess consumption before optimization is 80 kWh, while peak excess consumption after optimization is 72 kWh). The caption states, "No-load high consumption accounts for the highest energy savings (69.2%), requiring continued optimization of fan speed parameters."

[0091] A radar chart of the health status of each core component uses "compressor, heat exchanger, fan, and filter" as the axes, with "reliability coefficient" as the radial dimension (ranging from 0 to 1.0). The chart shows a compressor of 0.7, a heat exchanger of 0.9, a fan of 1.0, and a filter of 0.7, with the caption "Compressor and filter reliability are low (0.7), requiring special attention to lubricant replenishment and filter cleaning." The report structure includes a cover page (assessment period, assessment target), a summary of core assessment results (Grade A, 1,248 yuan / month), detailed charts (trend curves, bar charts, radar charts), and optimization suggestions (such as "Prioritize compressor and filter maintenance in July"). Charts and tables are labeled with data sources and calculation methods to ensure professionalism and readability.

[0092] Based on the visual assessment report, comprehensive assessment information on the operating status of industrial air conditioners is distributed across multiple terminals, enabling simultaneous push of assessment information to the operation and maintenance management platform, energy monitoring center, and enterprise ERP system. The complete assessment process is recorded in the industrial air conditioner operation and maintenance log. The operation and maintenance management platform pushes a complete visual assessment report (including raw data and calculation details), allowing operation and maintenance personnel to view component risk details and energy-saving optimization paths, with "editable and exportable" permissions. The energy-saving benefit module (histogram, total energy savings) and energy consumption anomaly analysis are pushed to the energy monitoring center, allowing energy managers to track the achievement of energy-saving targets, with "viewable and statistical" permissions. Core assessment results (reliability rating, monthly energy savings) are pushed to the enterprise ERP system for cost accounting and budget planning, with "viewable and financial module-interconnectable" permissions. The distribution protocol uses MQTT (for IoT terminals) and HTTPS (for web platforms) to ensure data transmission security, with push latency controlled to within 1 minute.

[0093] The complete evaluation process is recorded in the industrial air-conditioning operation and maintenance log. The "evaluation cycle code (202406)" is used as the key to record the detailed evaluation process. The values ​​include input data: basic evaluation index data (component reliability coefficient, energy loss coefficient), multi-dimensional evaluation matrix; calculation process: evaluation model weight setting, comprehensive evaluation value calculation details, energy-saving benefit calculation formula; output results: core evaluation results (A level, 1,248 yuan), visual report link; abnormal description: no abnormal data is eliminated, and all parameters are verified by the 3σ principle; the log format uses JSON to facilitate subsequent queries and data analysis, and the retention period is set to 3 years.

[0094] In one embodiment, Figure 2 As shown, the present application also provides a predictive maintenance and energy-saving linkage device for industrial air conditioning, comprising:

[0095] Acquisition module 201 is used to obtain the operating data of each core component of the industrial air conditioner and the operating environment parameter information, including the compressor start and stop frequency, evaporator / condenser temperature, fan speed, refrigerant pressure, indoor and outdoor temperature and humidity, load change curve and energy consumption metering data;

[0096] The processing module 202 is used to process the operating data and working environment parameter information of the core components of the industrial air conditioner, monitor the compressor lubricating oil level, heat exchanger scaling degree, motor winding insulation and filter clogging status in real time through the Internet of Things sensor network and edge computing nodes, build a component degradation trend and environmental load correlation model, generate preliminary maintenance requirements and energy consumption abnormality warning information; process the preliminary maintenance requirements and energy consumption abnormality warning information, simulate the equipment operating status at different maintenance times through digital twin technology, design a hierarchical maintenance strategy in combination with the full life cycle cost model, impose component remaining life threshold constraints and maintenance resource optimal configuration objective function, generate target maintenance execution instructions and energy consumption abnormality warning information. Energy potential analysis report; based on the corresponding adaptive algorithm, the target maintenance execution instructions and energy-saving potential analysis report are processed, and the air-conditioning operation parameters are adjusted in real time in combination with the indoor thermal comfort requirements and the peak-valley electricity price mechanism of the power grid to generate a linkage control scheme that takes into account both maintenance effects and energy consumption optimization; the linkage control scheme that takes into account both maintenance effects and energy consumption optimization is processed to generate a global coordinated operation management strategy; the preliminary maintenance requirements and energy consumption abnormality warning information, target maintenance execution instructions, the linkage control scheme that takes into account both maintenance effects and energy consumption optimization, and the global coordinated operation management strategy are processed to generate comprehensive evaluation information on the operating status of industrial air conditioners including equipment reliability level and quantitative value of energy-saving benefits.

[0097] The computer-readable storage medium provided in the above-mentioned embodiments of the present application and the predictive maintenance and energy-saving linkage method for industrial air conditioners provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0098] Each embodiment of this application is described in a related manner. Similar portions between the various embodiments can be referenced to each other. Each embodiment focuses on the differences from other embodiments. In particular, the embodiments of the method for evaluating the linkage between predictive maintenance and energy conservation for industrial air conditioners, electronic devices, electronic devices, and readable storage media are generally similar to the aforementioned embodiments of the method for evaluating the linkage between predictive maintenance and energy conservation for industrial air conditioners. Therefore, the description is relatively simple. For related portions, reference can be made to the partial description of the aforementioned embodiments of the method for evaluating the linkage between predictive maintenance and energy conservation for industrial air conditioners.

Claims

1. A predictive maintenance and energy-saving linkage method for industrial air conditioning, characterized in that: include: Obtain operating data and operating environment parameter information of each core component of industrial air conditioners, including compressor start and stop frequency, evaporator / condenser temperature, fan speed, refrigerant pressure, indoor and outdoor temperature and humidity, load change curve and energy consumption metering data; The system processes the operating data and environmental parameters of core industrial air conditioning components, monitors compressor lubricating oil levels, heat exchanger scaling, motor winding insulation, and filter clogging status in real time through IoT sensor networks and edge computing nodes, builds a correlation model between component degradation trends and environmental loads, and generates preliminary maintenance requirements and abnormal energy consumption warnings. Process preliminary maintenance needs and energy consumption anomaly warning information, simulate equipment operating status at different maintenance opportunities through digital twin technology, design a hierarchical maintenance strategy based on the full life cycle cost model, apply component remaining life threshold constraints and maintenance resource optimal configuration objective functions, and generate target maintenance execution instructions and energy-saving potential analysis reports; Based on the corresponding adaptive algorithm, the target maintenance execution instructions and energy-saving potential analysis reports are processed. In combination with indoor thermal comfort requirements and the peak and valley electricity price mechanism of the power grid, the air conditioning operating parameters are adjusted in real time to generate a linkage control plan that takes into account both maintenance effects and energy consumption optimization. Process the linkage control scheme that takes into account both maintenance effect and energy consumption optimization to generate a global coordinated operation management strategy; The system processes preliminary maintenance needs and energy consumption abnormality warning information, target maintenance execution instructions, linkage control schemes that take into account both maintenance effects and energy consumption optimization, and global coordinated operation management strategies to generate comprehensive evaluation information on the operating status of industrial air conditioners, including equipment reliability levels and quantitative values ​​of energy-saving benefits.

2. The method according to claim 1, wherein The system processes the operating data and operating environment parameters of the core components of industrial air conditioners, and uses the IoT sensor network and edge computing nodes to monitor the compressor lubricating oil level, heat exchanger scaling, motor winding insulation, and filter clogging status in real time. It builds a correlation model between component degradation trends and environmental loads, and generates preliminary maintenance requirements and abnormal energy consumption warning information, including: The system processes the operating data of industrial air conditioner core components and operating environment parameter information, builds a distributed monitoring system through the Internet of Things sensor network and edge computing nodes, integrates the core component operating data and operating environment parameters with a dynamic weight distribution mechanism, and monitors the compressor lubricating oil level, heat exchanger scaling, motor winding insulation, and filter clogging status in real time. Utilizing a component-environment dynamic correlation modeling framework, a three-level network structure consisting of multi-source data denoising and feature screening at the input layer, spatiotemporal correlation learning at the hidden layer, and demand and warning mapping at the output layer is used to construct a model for correlating component degradation trends with environmental loads. The hidden-layer spatiotemporal correlation learning introduces an LSTM network to capture the temporal correlation between component degradation and environmental loads, and an attention mechanism is used to strengthen the weights of key influencing factors. The rationality of the model output results is verified in combination with the safe operation threshold constraints of the core components of industrial air conditioners. The abnormal data caused by sensor drift, data transmission interference, etc. are eliminated through the 3σ principle. At the same time, the dynamic weight of environmental factors is adjusted based on the environmental load fluctuation coefficient, and preliminary maintenance requirements and energy consumption abnormality warning information including component maintenance priority, energy consumption abnormality type and risk level are generated.

3. The method according to claim 1, wherein Process preliminary maintenance requirements and abnormal energy consumption warning information, simulate equipment operating status at different maintenance opportunities through digital twin technology, design a hierarchical maintenance strategy based on the full life cycle cost model, apply component remaining life threshold constraints and maintenance resource optimal configuration objective functions, and generate target maintenance execution instructions and energy-saving potential analysis reports, including: Classify and label component degradation level data in preliminary maintenance requirements, classify maintenance timeliness and prioritize them, and generate basic component maintenance parameters; The energy consumption fluctuation data in the energy consumption abnormality warning information is identified by abnormal type, influencing factors are broken down, and energy-saving space is calculated to generate energy consumption optimization analysis parameters, including characteristic matching model parameters of energy consumption abnormalities, the influence coefficients of environmental load / equipment working conditions / operating parameters on energy consumption, and quantitative calculation rules for energy-saving potential under different abnormal scenarios; Using digital twin technology, the operating status of equipment at different maintenance opportunities is simulated. Through equipment performance simulation before, during, and after maintenance, component life attenuation simulation at different maintenance intervals, and dynamic measurement of the impact of maintenance interventions on energy consumption, maintenance timing decision parameters are generated. Combined with the full life cycle cost model, the hierarchical maintenance strategy is analyzed for cost composition, benefit return calculation, and resource adaptation planning to generate maintenance strategy optimization parameters; By applying component remaining life threshold constraints and maintenance resource allocation objective functions, the above parameters are integrated and optimized. The feasibility of the maintenance plan is verified by the lower limit of the remaining life, and the maintenance task schedule is adjusted to maximize resource utilization. Target maintenance execution instructions and energy-saving potential analysis reports are generated.

4. The method according to claim 1, wherein Based on the corresponding adaptive algorithm, the target maintenance execution instructions and energy-saving potential analysis reports are processed. In combination with indoor thermal comfort requirements and the peak and valley electricity price mechanism of the power grid, the air conditioning operating parameters are adjusted in real time to generate a linkage control solution that takes into account both maintenance effects and energy consumption optimization, including: Adaptive feature matching and time-series correlation processing are performed on the maintenance period requirements in the target maintenance execution instructions, component protection parameters, energy consumption abnormality data in the energy-saving potential analysis report, and energy-saving target values ​​to generate maintenance demand features and energy consumption optimization features; Based on the maintenance demand characteristics and energy consumption optimization characteristics, combined with the temperature and humidity threshold ranges and perceived comfort weight coefficients in the indoor thermal comfort requirements, the time division standards and electricity price floating ratio in the peak and valley electricity pricing mechanism of the power grid, the dual-objective optimization weights of the adaptive algorithm are generated. Based on the parameter iteration output results of the dual-objective optimization weights and adaptive algorithm, the air conditioning operating parameters are adjusted in real time to generate a linkage control scheme that takes into account both maintenance effects and energy consumption optimization.

5. The method according to claim 4, wherein Process the linkage control scheme that takes into account both maintenance effect and energy consumption optimization to generate a global coordinated operation management strategy, including: Global feature normalization and collaborative correlation extraction are performed on the single-device operating parameter adjustment rules, maintenance and energy-saving coordination thresholds, load distribution requirements of multiple air-conditioning equipment in industrial scenarios, and energy supply limit data in the linkage control scheme that takes into account both maintenance effects and energy consumption optimization. This generates standardized collaborative features and global trend features. Based on standardized collaborative features and global trend characteristics, combined with the equipment cluster operation efficiency targets in the global management requirements of industrial scenarios, the total energy consumption limit and the workshop temperature and humidity regional linkage standards and pollutant emission control indicators in the environmental collaborative constraint mechanism, a multi-dimensional adaptation weight for the global collaborative algorithm is generated; Based on the iterative calculation results of multi-dimensional adaptation weights and global coordination algorithms, a globally coordinated operation and management strategy is generated, including a cross-device peak-shifting scheduling plan for maintenance tasks of multiple air-conditioning equipment, dynamic energy allocation rules during high-load periods, multi-device linkage control instructions when regional temperature and humidity are abnormal, and the optimal scheduling plan for maintenance resources among cluster devices.

6. The method according to claim 1, wherein The system processes preliminary maintenance requirements and energy consumption abnormality warning information, target maintenance execution instructions, linkage control solutions that balance maintenance effects and energy consumption optimization, and global coordinated operation management strategies to generate comprehensive evaluation information on the operating status of industrial air conditioners, including equipment reliability levels and quantified energy-saving benefits, including: Classify and quantify the component risk levels and energy consumption anomaly types in the preliminary maintenance requirements and energy consumption anomaly warning information to generate basic evaluation index data. Each component risk level corresponds to a unique reliability coefficient, and each energy consumption anomaly type corresponds to a target energy saving loss coefficient. The basic evaluation indicator data, the maintenance completion rate and resource utilization rate in the target maintenance execution instructions, the parameter compliance rate in the linkage control scheme that takes into account both maintenance effect and energy consumption optimization, and the cluster coordination efficiency in the global coordinated operation management strategy are integrated and calculated to generate a multi-dimensional evaluation matrix that includes equipment health dimensions, energy consumption dimensions, and coordination dimensions. The row vectors of the evaluation matrix are evaluation dimensions, and the column vectors are specific quantitative values. The multi-dimensional evaluation matrix is ​​input into the industrial air conditioning operation status evaluation model for weighted calculation processing to generate core evaluation results including equipment reliability level and energy-saving benefit quantitative value; The core assessment results trigger the assessment information visualization generation mechanism to generate a visual assessment report. The visual assessment report includes equipment reliability trend curves, energy-saving benefit comparison bar charts, and radar charts of the health status of each core component. Based on the visual assessment report, the comprehensive assessment information of the industrial air-conditioning operating status is distributed and processed on multiple terminals, and the assessment information is simultaneously pushed to the operation and maintenance management platform, energy monitoring center, and enterprise ERP system. The complete assessment process is recorded in the industrial air-conditioning operation and maintenance log.

7. A predictive maintenance and energy-saving linkage device for industrial air conditioning, characterized in that: The device comprises: Acquisition module, used to obtain the operating data of each core component of industrial air conditioner and working environment parameter information; The processing module is used to process the operating data and working environment parameter information of the core components of industrial air conditioners, monitor the compressor lubricating oil level, heat exchanger scaling degree, motor winding insulation and filter clogging status in real time through the Internet of Things sensor network and edge computing nodes, build a component degradation trend and environmental load correlation model, and generate preliminary maintenance requirements and energy consumption abnormality warning information; process the preliminary maintenance requirements and energy consumption abnormality warning information, simulate the equipment operating status at different maintenance times through digital twin technology, design a hierarchical maintenance strategy based on the full life cycle cost model, impose component remaining life threshold constraints and maintenance resource optimal configuration objective function, generate target maintenance execution instructions and energy saving Potential analysis report; based on the corresponding adaptive algorithm, the target maintenance execution instructions and energy-saving potential analysis report are processed, and the air-conditioning operating parameters are adjusted in real time in combination with the indoor thermal comfort requirements and the peak-valley electricity price mechanism of the power grid to generate a linkage control scheme that takes into account both maintenance effects and energy consumption optimization; the linkage control scheme that takes into account both maintenance effects and energy consumption optimization is processed to generate a global coordinated operation management strategy; the preliminary maintenance requirements and energy consumption abnormality warning information, target maintenance execution instructions, the linkage control scheme that takes into account both maintenance effects and energy consumption optimization, and the global coordinated operation management strategy are processed to generate comprehensive evaluation information on the operating status of industrial air-conditioning, including equipment reliability level and quantitative value of energy-saving benefits.

8. An electronic device, characterized in that: include: a first processor; and a memory for storing executable instructions of the first processor; Wherein, the first processor is configured to execute the predictive maintenance and energy-saving linkage method for industrial air conditioners according to any one of claims 1 to 6 by executing the executable instructions.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the second processor, the predictive maintenance and energy-saving linkage method for an industrial air conditioner according to any one of claims 1 to 6 is implemented.

Images