Refrigerating system fault intelligent diagnosis and processing method and system

Abstract

The invention discloses an intelligent fault diagnosis and processing method and system for a refrigerating system. The method comprises the steps that operating parameters of an internal auxiliary system and an external auxiliary system of the refrigerating system are collected; acquiring a current working condition reference parameter, and identifying as abnormal when the internal parameter deviates from the reference overlimit; causal analysis is carried out by combining external parameters, and fault roots and types are judged; if the monitoring data are invalid, calculating a virtual substitution value by using thermodynamic coupling parameters to maintain operation; if the security risk performance declines, actively adjusting the control parameters to compensate the performance loss; and if the fault is a safety risk fault, shutdown is executed. According to the method, false alarms are reduced through the working condition self-adaptive benchmark, fault sources are accurately distinguished through cross-system cooperation, a fault-tolerant mechanism is established to avoid unnecessary shutdown, and conversion from passive maintenance to active operation and maintenance is achieved.

Description

Technical Field

[0001] This invention relates to intelligent control of air conditioning systems, and more particularly to a method and system for intelligent diagnosis and handling of refrigeration system faults. Background Technology

[0002] High-temperature heat pumps and rotary dehumidifiers are widely used in industrial production, drying, and dehumidification. Currently, the control systems of these devices mostly focus on basic temperature and humidity PID regulation and safety protection after a fault occurs (such as high-voltage protection and overcurrent shutdown). This traditional control strategy mainly relies on "remedial measures," meaning that the system only issues an alarm after a fault has occurred or even caused a shutdown.

[0003] Although existing control technologies can maintain the basic operation of equipment, they still have many technical shortcomings in practical applications and cannot meet the needs of intelligent operation and maintenance. These shortcomings are manifested in the following aspects: First, it lacks adaptive capability and has a high false alarm rate. Existing fault diagnosis typically uses fixed alarm thresholds. However, the operating status of a refrigeration system is greatly affected by changes in ambient temperature, humidity, and load. Under different operating conditions (such as high humidity in summer or low temperature in winter), the normal operating parameter range of the system will drift. Fixed thresholds cannot adapt to these changing operating conditions, easily leading to false alarms under normal operating conditions or missed alarms under abnormal operating conditions, and lacking the ability to build a dynamic baseline based on the current operating conditions.

[0004] Second, diagnostics are isolated and lack cross-system collaborative analysis. Existing alarm systems are typically isolated, focusing only on components within the refrigeration system (such as compressors and heat exchangers). However, refrigeration systems often have thermodynamic coupling relationships with external auxiliary systems (such as cooling towers and chillers). When an external auxiliary system malfunctions (e.g., abnormal cooling tower fan speed leading to poor heat dissipation), it can cause an increase in the condensing pressure of the refrigeration system. Current technology struggles to distinguish whether the root cause of the fault lies within the refrigeration system or in the external auxiliary system, easily leading to misdiagnosis and increasing the difficulty of troubleshooting.

[0005] Third, the system lacks fault tolerance mechanisms and has weak anti-interference capabilities. In existing systems, once a critical sensor (such as a temperature or pressure sensor) malfunctions or its readings become abnormal, it typically triggers a system shutdown protection mechanism directly. This approach fails to consider the difference between sensor failure and actual equipment failure, and lacks a fault tolerance mechanism that uses other relevant parameters to calculate virtual substitute values ​​to maintain system operation, leading to unnecessary production interruptions and economic losses.

[0006] Fourth, there is a lack of proactive compensation and energy-saving optimization strategies. For performance degradation that occurs during equipment operation but is not a safety risk (such as minor filter clogging or slow scaling of heat exchangers), current technologies typically lack early warning and proactive intervention capabilities, leaving the equipment to operate with defects until the fault worsens to the shutdown threshold. During this period, the equipment often operates in a low-energy-efficiency state, resulting in significant energy waste.

[0007] In conclusion, there is an urgent need in this field for a better intelligent method for handling refrigeration system faults. Summary of the Invention

[0008] The purpose of this invention is to provide a method and system for intelligent diagnosis and handling of refrigeration system faults that can combine external operating parameters to perform causal correlation analysis, have adaptive operating conditions, and provide fault-tolerant operation and active compensation.

[0009] To achieve the above objectives, the present invention provides an intelligent diagnosis and handling method for refrigeration system faults, comprising: Real-time acquisition of internal operating parameters of the refrigeration system, and acquisition of external operating parameters of external auxiliary systems coupled with the refrigeration system; Obtain the baseline parameters under the current operating conditions. When the internal operating parameters deviate from the baseline parameters and exceed a preset threshold, the internal operating parameters are identified as abnormal parameters. In response to the abnormal parameters, a causal correlation analysis is performed in conjunction with the external operating parameters to determine the root cause of the fault leading to the abnormal parameters, and the fault type is determined accordingly. If the fault type is monitoring data failure, then the virtual substitution value is calculated using the relevant operating parameters of the monitoring object corresponding to the failed data that have a thermodynamic coupling relationship, and the virtual substitution value is used to maintain the operation of the refrigeration system. If the fault type is a performance degradation that is not a safety risk, then while keeping the refrigeration system running, the control parameters of the actuators of the refrigeration system or external auxiliary system are actively adjusted to compensate for the performance loss of the refrigeration system. If the fault type is a safety risk fault, then a shutdown protection mechanism will be implemented.

[0010] Preferably, the method for obtaining the reference parameters includes: A benchmark library is constructed based on the historical operating data of the refrigeration system. The benchmark library contains a variety of reference parameters that correspond to different typical operating conditions and are in a healthy state. Identify the current operating condition category of the refrigeration system and retrieve reference parameters matching the operating condition category from the benchmark library; The system aging state parameters of the refrigeration system are obtained, and the reference parameters are corrected using the system aging state parameters to generate the baseline parameters.

[0011] Preferably, the method for determining the fault type includes: The system invokes a preset expert rule base, which contains internal fault rules of the refrigeration system and associated fault rules that map the relationship between the internal and external auxiliary systems of the refrigeration system. The abnormal parameter is used to search the expert rule base to determine the candidate internal parameters and candidate external parameters associated with the abnormal parameter; Obtain the candidate extrinsic parameters that are synchronized with the abnormal parameters in time, and perform trend consistency analysis and cross-validation on the abnormal parameters and the candidate extrinsic parameters; If the verification result conforms to the logical relationship defined by the associated fault rule, then a cross-system causal chain is constructed to determine that the root cause of the fault is located in an external auxiliary system; If the verification result conforms to the logical relationship defined by the internal fault rules, then the root cause of the fault is determined to be inside the refrigeration system.

[0012] Preferably, based on the determination result of the root cause of the fault, the confidence score of the root cause of the fault is calculated and displayed.

[0013] Preferably, if the fault type is monitoring data failure, the method for calculating the virtual substitute value includes: Based on the heat and mass transfer equations of the refrigeration system, a mathematical calculation model is established between the monitoring object corresponding to the failure data and the relevant operating parameters. The relevant operating parameters collected in real time are input into the mathematical calculation model to calculate the virtual substitution value.

[0014] Preferably, if the fault type is a performance degradation that is not a safety risk, the method for actively adjusting the actuator control parameters of the refrigeration system or external auxiliary system includes: The optimal combination of control parameters is searched within a preset feasible region using an optimization algorithm. The objective function of the optimal combination of control parameters is to maximize the energy efficiency ratio of the refrigeration system under the current fault state. Adjusting the control parameters of the actuators of the refrigeration system or external auxiliary system includes: Adjust the fan speed or the opening of the electronic expansion valve in the refrigeration system; Alternatively, control commands can be sent through a cross-system communication interface to adjust the cooling tower fan speed or cooling water flow rate of the external auxiliary system.

[0015] Preferably, the internal operating parameters include thermodynamic parameters, electrical parameters, and mechanical parameters; the external operating parameters include cooling tower fan speed, cooling water inlet and outlet temperatures, and chiller unit energy efficiency ratio.

[0016] The present invention also provides an intelligent diagnosis and handling system for refrigeration system faults, which includes a controller, the controller controlling the operation of the refrigeration system based on the intelligent diagnosis and handling method for refrigeration system faults described above.

[0017] This invention also provides an intelligent fault diagnosis and handling system for refrigeration systems, comprising: One or more processors; Memory; and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the programs including instructions for performing the intelligent diagnosis and handling method for refrigeration system faults as described above.

[0018] The present invention also provides a computer-readable storage medium, characterized in that it includes a computer program, which can be executed by a processor to perform the intelligent diagnosis and handling method for refrigeration system faults as described above.

[0019] Compared with existing technologies, the intelligent fault diagnosis and handling method for refrigeration systems provided by the above-mentioned technical solution of this invention firstly identifies anomalies by acquiring baseline parameters under the current operating conditions, overcoming the shortcomings of traditional fixed threshold alarms that cannot adapt to drastic changes in ambient temperature, humidity, and load. This dynamic diagnostic logic based on operating condition adaptation ensures that the system maintains high-precision diagnostic capabilities under different operating conditions such as high humidity in summer and low temperature in winter, further reducing the false alarm rate. Secondly, based on cross-system collaborative diagnostic functions, it breaks down the information silos between the refrigeration system and external auxiliary systems, and can accurately distinguish between internal faults and external interference by combining external operating parameters, effectively solving the problem of misjudgment caused by external factors. At the same time, this invention establishes a sensor fault tolerance mechanism, using correlated parameters to calculate virtual values ​​to maintain system operation, avoiding production interruptions caused by unnecessary shutdowns. In addition, the proactive energy-saving compensation strategy based on fault classification enables the equipment to maintain efficient operation through parameter adjustments even under minor faults, realizing the transformation from passive maintenance to proactive operation and maintenance, taking into account both safety and economy. Attached Figure Description

[0020] Figure 1 This is a flowchart of a fault intelligent diagnosis and processing method in one embodiment of the present invention.

[0021] Figure 2 This is a flowchart illustrating the overall execution process of the intelligent diagnostic and processing method for faults in this embodiment of the invention. Detailed Implementation

[0022] To illustrate the technical content, structural features, objectives, and effects of the present invention in detail, the following description is provided in conjunction with the embodiments and accompanying drawings.

[0023] This embodiment provides an intelligent fault diagnosis and handling method for refrigeration systems, mainly applied to complex refrigeration and air handling systems such as high-temperature heat pumps and rotary dehumidifiers. The purpose of this embodiment is to solve the problems of fixed thresholds, isolated diagnosis, and lack of fault tolerance mechanisms in traditional control strategies through a data-driven closed-loop process of "perception-diagnosis-optimization-fault tolerance".

[0024] like Figure 1 As shown, the method mainly includes the following steps: S101: Real-time acquisition of internal operating parameters of the refrigeration system and acquisition of external operating parameters of external auxiliary systems coupled with the refrigeration system.

[0025] In this embodiment, the refrigeration system typically includes core components such as a compressor, condenser, expansion valve (or electronic expansion valve EXV), evaporator, and fan. External auxiliary systems refer to systems that have a thermodynamic relationship with the refrigeration system involving energy exchange or providing auxiliary support, such as cooling tower systems, chiller units, or connected terminal air conditioning units.

[0026] Data acquisition is accomplished through a multi-dimensional sensor network deployed on the device.

[0027] Internal operating parameters include, but are not limited to: Thermodynamic parameters: compressor suction temperature, compressor discharge temperature, evaporator inlet and outlet water (or air) temperature, condenser inlet and outlet water (or air) temperature, system high pressure (condensing pressure), system low pressure (evaporating pressure), subcooling, superheating, ambient temperature and humidity.

[0028] Electrical parameters: compressor operating current, voltage, frequency, fan operating current, and electronic expansion valve (EXV) opening feedback signal.

[0029] Mechanical parameters: compressor bearing vibration value, fan bearing vibration value, slight pressure difference across the filter, and external static pressure.

[0030] External operating parameters are obtained through cross-system communication modules (such as Modbus TCP / IP, OPC UA and other industrial communication protocols), mainly including: cooling tower fan speed, cooling water inlet and outlet temperature, cooling water flow rate, and real-time energy efficiency ratio (COP) of the chiller unit.

[0031] S102: Obtain the baseline parameters under the current operating conditions.

[0032] S103: Determine if the internal operating parameters are abnormal. If not, return to S102; if yes, proceed to S104.

[0033] When an internal operating parameter deviates from the baseline parameter and exceeds a preset threshold, the internal operating parameter is identified as an abnormal parameter.

[0034] Unlike traditional technologies that use fixed alarm thresholds (e.g., high voltage > 2.8 MPa alarm), this embodiment employs a dynamic benchmark. The system first identifies the current operating condition category. Then, it obtains the corresponding benchmark parameters based on that operating condition category.

[0035] The system calculates the deviation between the real-time acquired internal operating parameters and the baseline parameters. If the deviation exceeds a preset threshold, the internal operating parameter is determined to be abnormal. For example, if the current operating condition is summer and the measured condensing pressure is 1.8 MPa, while the upper limit of the healthy baseline for this condition is 1.6 MPa, then the condensing pressure is identified as an abnormal parameter.

[0036] S104: In response to abnormal parameters, perform causal correlation analysis in conjunction with external operating parameters to determine the root cause of the fault leading to the abnormal parameters and identify the fault type.

[0037] This step breaks down the diagnostic boundaries of a single system. When an anomaly in internal operating parameters is detected, an error is not immediately reported; instead, a collaborative diagnostic engine is activated.

[0038] Check external operating parameters that are physically or thermodynamically strongly correlated with the abnormal parameters. For example, when an abnormal parameter of high condensing pressure is found, the external cooling tower fan speed and cooling water temperature will be checked simultaneously.

[0039] The system uses logical rules to determine whether a fault originates from the refrigeration system itself (such as scaling on the condenser) or from an external system (such as a cooling tower fan failure).

[0040] Faults are classified into the following three types: Monitoring data failure: for example, sensor malfunction (open circuit, drift, jamming).

[0041] Performance degradation due to non-safety risks: Equipment performance deteriorates but does not reach the safety threshold (e.g., minor filter clogging, minor scale buildup in heat exchangers).

[0042] Safety risk failure: serious failures that may lead to equipment damage or safety accidents (such as compressor seizure, extreme overpressure, refrigerant leakage).

[0043] S105: Execute differentiated processing strategies based on the determined fault type. If the fault type is monitoring data failure, proceed to S106. If the fault type is performance degradation without safety risks, proceed to S107. If the fault type is a safety risk fault, proceed to S108.

[0044] S106 (Monitoring Data Failure): By utilizing the relevant operating parameters of the monitored object that have a thermodynamic coupling relationship with the failed data, a virtual substitute value is calculated and used to maintain the operation of the refrigeration system. For example, if the subcooling sensor fails, the subcooling can be estimated through pressure and temperature and used to replace the measured value in the control, thus avoiding shutdown.

[0045] S107 (Performance Degradation Due to Non-Safety Risks): While maintaining the operation of the refrigeration system, actively adjust the control parameters of the actuators of the refrigeration system or external auxiliary systems to compensate for the performance loss of the refrigeration system. For example, increase the fan speed to compensate for the decrease in heat exchange efficiency.

[0046] S108 (Safety Risk Fault): Immediately execute the shutdown protection procedure and disconnect the relevant power supply to prevent the accident from escalating.

[0047] The method in this embodiment achieves a shift from post-construction maintenance to pre-construction prediction and from single diagnosis to cross-system collaboration through the above steps.

[0048] Specifically, firstly, this embodiment obtains the operating parameters of the external auxiliary system coupled with the refrigeration system and performs causal correlation analysis in combination with the internal operating parameters, breaking down the information silos between the internal and external systems. This enables precise differentiation of whether the root cause of the fault is located in the refrigeration system itself or in the external environment or auxiliary equipment, thereby avoiding false alarms caused by external factors and significantly improving the accuracy of fault diagnosis.

[0049] Secondly, addressing the problem in existing technologies where sensor failure triggers shutdown protection and leads to production interruptions, this invention proposes a virtual substitution value calculation method based on thermodynamic coupling. When monitoring data fails, a virtual value is calculated using other related normal operating parameters to replace the failed data, maintaining the continued operation of the refrigeration system. This fault-tolerant control strategy effectively avoids unnecessary shutdowns caused by the failure of a single non-critical sensor, reducing economic losses and mechanical impacts on equipment caused by frequent start-ups and shutdowns.

[0050] Furthermore, for performance degradation not related to safety risks, performance loss is compensated in real time by actively adjusting the control parameters of the actuators in the refrigeration system or external auxiliary systems. This mechanism not only ensures that the system can still meet cooling requirements under minor faults, but also keeps the system within a relatively efficient operating range.

[0051] Furthermore, this embodiment implements differentiated processing strategies based on the type of fault. This tiered processing mechanism maximizes the system's operational potential and availability while ensuring absolute equipment safety (immediate shutdown upon encountering a safety risk), achieving an optimal balance between safety and economy.

[0052] In another embodiment, during the actual operation of the refrigeration system, the environment and load are dynamically changing, and the equipment itself undergoes aging. To ensure the accuracy of the diagnosis, methods for obtaining baseline parameters include: 1. Acquire and preprocess historical data.

[0053] Historical operating data is cleaned. Moving average filtering or Kalman filtering algorithms are used to remove sensor noise; obvious outliers and abnormal values ​​are eliminated; data consistency is checked to ensure that thermodynamic parameters meet basic energy conservation logic (e.g., exhaust temperature must be higher than condensation temperature).

[0054] 2. Working condition clustering and partitioning.

[0055] The cleaned historical data is processed using clustering algorithms (such as K-Means clustering or DBSCAN density clustering). Based on characteristic variables such as ambient temperature (Ta), ambient humidity (RHb), and system load rate, the operating conditions are automatically divided into several typical categories.

[0056] In this embodiment, the operating condition categories include, but are not limited to: High humidity conditions in summer: for example, Ta>30℃, RHb>70%.

[0057] Winter low temperature conditions: for example, Ta < 5℃.

[0058] During the transitional season, the normal temperature operating conditions are as follows: for example, 15℃≤Ta≤25℃.

[0059] And the corresponding low-load and high-load sub-conditions.

[0060] 3. Construct a dynamic health benchmark library for multiple operating conditions.

[0061] For each operating condition cluster, the distribution characteristics of its corresponding key parameters are statistically analyzed, and a dedicated health parameter baseline (i.e., reference parameters) is established to build a benchmark library.

[0062] For example, in high humidity conditions during summer, the healthy baseline range for filter pressure differential is determined to be 80 Pa. 120Pa; the healthy benchmark for condenser subcooling is 5K. 8K.

[0063] 4. Correction based on system aging status.

[0064] The longer the equipment operates, the more its performance will naturally decline (e.g., the heat transfer coefficient will decrease). To avoid false alarms caused by normal aging, system aging status parameters are introduced to correct the reference parameters.

[0065] Aging status parameters are generated by reading the device's cumulative runtime and maintenance records.

[0066] Finally, the reference parameters are corrected using the system aging state parameters, thus generating baseline parameters.

[0067] For example, the filter differential pressure alarm threshold of a new machine is 150Pa. After 5000 hours of operation, considering the irreversible dust accumulation on the filter, the alarm threshold is automatically corrected to 160Pa to avoid false alarms, until the limit value that must be replaced is reached.

[0068] Using the methods described above, this embodiment ensures that the diagnostic benchmark can be dynamically adjusted according to the season, operating conditions, and equipment lifespan, significantly reducing the false alarm rate.

[0069] In another embodiment, the method for determining the root cause of a fault includes: First, a multi-dimensional expert rule base is pre-built. This expert rule base not only includes the fault logic of a single system, but also the mapping relationships across systems.

[0070] For internal fault rules, for example, if (condensing pressure > threshold) AND (cooling water inlet temperature < threshold), then it is determined that there is scaling inside the condenser or excessive refrigerant charge.

[0071] For related fault rules, for example, if (condensing pressure > threshold) AND (cooling water inlet temperature > threshold) AND (cooling tower fan speed < set value), then it is determined that the cooling tower fan failure affects the refrigeration system.

[0072] Then, when abnormal parameters are detected (e.g., the refrigeration system COP drops from 5.2 to 4.3, and the condensing pressure rises to 1.8 MPa): Search the expert rule base for all possible causes of high condensation pressure.

[0073] Determine candidate internal parameters: filter pressure difference and evaporator subcooling.

[0074] Determine candidate external parameters: cooling tower fan speed and cooling water outlet temperature.

[0075] Next, trend consistency analysis and cross-validation are performed. That is, historical data synchronized with the time of the anomaly (e.g., a data window of the past 10 minutes) are retrieved and analyzed.

[0076] Specifically, if the condensing pressure of the refrigeration system continues to rise, the analysis is as follows: External data verification: Reading data from the cross-system communication module revealed that the cooling tower fan speed feedback value was fixed at 50% (the set value should be 100%), and the cooling water outlet temperature rose synchronously from 32℃ to 38℃.

[0077] Internal data verification: The pressure difference of the filter inside the refrigeration system is normal, and the subcooling of the evaporator is normal.

[0078] Therefore, it can be concluded that the increase in external cooling water temperature leads to an increase in condensation pressure, and the increase in water temperature is due to abnormal fan speed, which conforms to the associated fault rules.

[0079] Finally, based on the above verification, a cross-system causal chain is constructed: cooling tower fan malfunction -> cooling water temperature rise -> high refrigeration system condensing pressure -> COP decrease.

[0080] Therefore, the root cause of the fault lies in the external auxiliary system (cooling tower).

[0081] Furthermore, a confidence score, such as 95%, can be calculated based on the number of features matched by the rule.

[0082] In addition, warning messages and related confidence scores are displayed through the HMI (Human Machine Interface).

[0083] For example, the HMI (Human Machine Interface) displays: "Warning: The cooling tower fan speed is abnormal, causing the COP of the refrigeration system to drop by 17%. It is recommended to check the cooling tower fan motor and belt. Confidence level: 95%". This embodiment enables accurate differentiation between internal and external factors, avoiding erroneous maintenance.

[0084] In another embodiment, if the fault type is monitoring data failure, the virtual substitute value calculation method is explained below based on a specific example.

[0085] Assuming the regeneration outlet humidity sensor used to control the regeneration heating of the rotary dehumidifier malfunctions, and the reading is stuck at 90%, which is significantly inconsistent with the actual operating conditions (at which point the regeneration air temperature has reached 120℃, and the theoretical humidity should be extremely low), the troubleshooting procedure is as follows: First, fault identification was performed. The humidity reading remained unchanged for an extended period and showed a logical contradiction with related parameters (regeneration temperature, rotor speed) (it's impossible to maintain 90% humidity at high temperatures), indicating that the sensor was faulty.

[0086] Then, a pre-set mathematical calculation model based on the heat and mass transfer equation is invoked. For the rotary dehumidification process, the regeneration outlet humidity (Yout) is a function of the regeneration inlet temperature (Treg), the processing air volume (Vair), the rotary speed (ω), and the rotary adsorption performance coefficient (Kads). This mathematical calculation model can be a simplified empirical formula or a black-box model based on a neural network (trained in a self-learning layer).

[0087] Next, relevant normal operation parameters are collected in real time: Regeneration heating temperature Treg = 120℃; The calculated Vair is 5000 m³ / h based on the frequency feedback of the wind turbine. The rotational speed of the rotary motor is ω=15r / h.

[0088] Inputting the above parameters into the mathematical calculation model, the virtual regeneration outlet humidity Yvirtual = 10% (relative humidity) is calculated.

[0089] Therefore, the controller of the refrigeration system automatically shields the input signals from the physical sensors (90%) and uses the calculated virtual values ​​(10%) as feedback signals to input into the control loop.

[0090] If the controller determines that the humidity has reached the standard, it appropriately reduces the regenerative heating power, thus avoiding overheating and energy waste caused by the sensor falsely reporting high humidity, and also avoiding shutdown caused by sensor malfunction alarms.

[0091] Meanwhile, the HMI interface may display: "Humidity sensor malfunction, currently operating with virtual parameters for fault tolerance. Please calibrate or replace the sensor as soon as possible."

[0092] This embodiment uses soft measurement technology to give the system immunity to sensing layer faults, greatly improving the system's availability.

[0093] In another embodiment, if the fault type is a performance degradation that is not a safety risk, the method for actively adjusting the actuator control parameters of the refrigeration system or external auxiliary system includes: The optimal combination of control parameters is searched within a preset feasible region using an optimization algorithm. The objective function of the optimal combination of control parameters is to maximize the energy efficiency ratio of the refrigeration system under the current fault condition. Adjusting the control parameters of the actuators in the refrigeration system or external auxiliary system includes: Adjust the fan speed or the opening of the electronic expansion valve in the refrigeration system; Alternatively, control commands can be sent through a cross-system communication interface to adjust the cooling tower fan speed or cooling water flow rate of the external auxiliary system.

[0094] Specifically, the condenser subcooling was monitored to slowly decrease from a healthy 5K to 3K, while the COP decreased from 5.5 to 5.0.

[0095] Analysis ruled out sensor malfunction and external system malfunction, and determined that the problem was slight scaling on the condenser (increased thermal resistance).

[0096] This is a low-priority fault with no immediate safety risk (pressure not exceeded). Immediate shutdown and cleaning are not required, but performance compensation is necessary. The handling procedure is as follows: First, activate the energy-saving optimization module. Set the objective function to maximize the system's coefficient of performance (COP) under the current scaling condition (fault constraint).

[0097] Then, the optimal combination of control parameters is searched. The optimal solution is found within the feasible region using a particle swarm optimization (PSO) algorithm or an extreme value search algorithm.

[0098] In this embodiment, the adjustment objects include the refrigeration system fan speed, electronic expansion valve opening, external cooling tower fan speed, and cooling water flow rate.

[0099] For example, try increasing the cooling tower fan speed (from 60% to 75%), and at the same time try increasing the cooling water flow rate (from 80 m³ / h to 95 m³ / h).

[0100] By increasing the flow rate and air volume on the cooling water side, the inlet temperature of the cooling water is reduced, thereby increasing the heat transfer temperature difference to compensate for the decrease in the heat transfer coefficient caused by scaling. The ultimate goal is to lower the condensation temperature and restore the subcooling.

[0101] After adjustments, the condenser subcooling was monitored to have recovered to 4.5K, and the COP rose to 5.3 (energy saving rate increased by about 6%).

[0102] The HMI displays: "Alert: Scaling is occurring in the condenser. Energy-saving compensation optimization has been initiated. Chemical cleaning is recommended during the next planned shutdown." This embodiment achieves optimal control under non-safety risk failure operation, which ensures uninterrupted production while minimizing energy loss during failure.

[0103] In summary, this invention discloses an intelligent diagnosis and handling method for refrigeration system faults, such as... Figure 2 The overall execution process is as follows: S1: Local sensor network collects internal operating parameters of the refrigeration system, such as temperature, humidity, and pressure.

[0104] Meanwhile, external operating parameters (cooling tower status, chiller unit COP) of external auxiliary systems are collected based on the cross-system communication module.

[0105] S2: Calculate the dynamic thresholds of each internal operating parameter, i.e., the baseline parameters, based on the current operating conditions (e.g., "high humidity in summer").

[0106] S3: Determine if any internal operating parameter is normal. If it is, proceed to S4; otherwise, proceed to S5.

[0107] S4: The HMI displays a green light, indicating that the refrigeration system is operating based on a preset energy-saving strategy, executing the conventional optimal strategy (such as adjusting the fan frequency according to the load), and returning to the S2 cycle.

[0108] S5: Trigger an alarm and first determine the direction of the fault, that is, whether it is a sensor fault or a device fault. If it is a sensor fault, proceed to S6; if it is a device fault, proceed to S7.

[0109] S6: Calculate the virtual substitution value, maintain the operation of the refrigeration system, and return to the loop.

[0110] S7: Activate the cross-system collaborative diagnostic engine, call the expert rule base, and jointly retrieve local and external data. Perform trend analysis and cross-validation to locate the root cause of the fault (e.g., cooling tower failure).

[0111] S8: Prioritize fault and energy-saving operation judgment. If the fault is performance degradation and there is no safety risk, proceed to S9. If the fault poses a safety risk, proceed to S10.

[0112] S9: The HMI displays a yellow warning light and sends a maintenance reminder. Simultaneously, the cooling system initiates an energy-saving process, dynamically adjusting operating parameters (such as increasing speed compensation). Reset after maintenance is complete.

[0113] S10: The HMI displays a red alarm and immediately executes the safety shutdown procedure. After emergency maintenance is completed, the system is reset, the fault case is recorded, and the process returns.

[0114] In another preferred embodiment of the present invention, an intelligent diagnosis and handling system for refrigeration system faults is also disclosed, which includes a controller, wherein the controller controls the operation of the refrigeration system based on the intelligent diagnosis and handling method for refrigeration system faults in the above embodiment.

[0115] This invention also discloses another intelligent fault diagnosis and processing system, which includes one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors. The programs include instructions for performing the intelligent fault diagnosis and processing method described above. The processor may be a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, used to execute relevant programs to achieve the functions required by the modules in the intelligent fault diagnosis and processing system of this application embodiment, or to execute the intelligent fault diagnosis and processing method of this application method embodiment.

[0116] This invention also discloses a computer-readable storage medium comprising a computer program that can be executed by a processor to perform the intelligent fault diagnosis and processing method described above. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium can be read-only memory (ROM), random access memory (RAM), or magnetic media, such as floppy disks, hard disks, magnetic tapes, magnetic disks, or optical media, such as digital versatile discs (DVDs), or semiconductor media, such as solid-state disks (SSDs).

[0117] This application also discloses a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. The processor of an electronic device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the electronic device to perform the aforementioned intelligent fault diagnosis and processing method.

[0118] The above-disclosed embodiments are merely preferred embodiments of the present invention and should not be construed as limiting the scope of the present invention. Therefore, any equivalent variations made in accordance with the claims of the present invention are still within the scope of the present invention.

Claims

1. A method for intelligent diagnosis and handling of faults in a refrigeration system, characterized in that, include: Real-time acquisition of internal operating parameters of the refrigeration system, and acquisition of external operating parameters of external auxiliary systems coupled with the refrigeration system; Obtain the baseline parameters under the current operating conditions. When the internal operating parameters deviate from the baseline parameters and exceed a preset threshold, the internal operating parameters are identified as abnormal parameters. In response to the abnormal parameters, a causal correlation analysis is performed in conjunction with the external operating parameters to determine the root cause of the fault leading to the abnormal parameters, and the fault type is determined accordingly. If the fault type is monitoring data failure, then the virtual substitution value is calculated using the relevant operating parameters of the monitoring object corresponding to the failed data that have a thermodynamic coupling relationship, and the virtual substitution value is used to maintain the operation of the refrigeration system. If the fault type is a performance degradation that is not a safety risk, then while keeping the refrigeration system running, the control parameters of the actuators of the refrigeration system or external auxiliary system are actively adjusted to compensate for the performance loss of the refrigeration system. If the fault type is a safety risk fault, then a shutdown protection mechanism will be implemented.

2. The intelligent fault diagnosis and handling method for refrigeration systems according to claim 1, characterized in that, The method for obtaining the reference parameters includes: A benchmark library is constructed based on the historical operating data of the refrigeration system. The benchmark library contains a variety of reference parameters that correspond to different typical operating conditions and are in a healthy state. Identify the current operating condition category of the refrigeration system and retrieve reference parameters matching the operating condition category from the benchmark library; The system aging state parameters of the refrigeration system are obtained, and the reference parameters are corrected using the system aging state parameters to generate the baseline parameters.

3. The intelligent fault diagnosis and handling method for refrigeration systems according to claim 1, characterized in that, The methods for determining the fault type include: The system invokes a preset expert rule base, which contains internal fault rules of the refrigeration system and associated fault rules that map the relationship between the internal and external auxiliary systems of the refrigeration system. The abnormal parameter is used to search the expert rule base to determine the candidate internal parameters and candidate external parameters associated with the abnormal parameter; Obtain the candidate extrinsic parameters that are synchronized with the abnormal parameters in time, and perform trend consistency analysis and cross-validation on the abnormal parameters and the candidate extrinsic parameters; If the verification result conforms to the logical relationship defined by the associated fault rule, then a cross-system causal chain is constructed to determine that the root cause of the fault is located in an external auxiliary system; If the verification result conforms to the logical relationship defined by the internal fault rules, then the root cause of the fault is determined to be inside the refrigeration system.

4. The intelligent fault diagnosis and handling method for refrigeration systems according to claim 3, characterized in that, Based on the determination of the root cause of the fault, the confidence score of the root cause of the fault is calculated and displayed.

5. The intelligent fault diagnosis and handling method for a refrigeration system according to claim 1, characterized in that, If the fault type is monitoring data failure, the method for calculating the virtual substitute value includes: Based on the heat and mass transfer equations of the refrigeration system, a mathematical calculation model is established between the monitoring object corresponding to the failure data and the relevant operating parameters. The relevant operating parameters collected in real time are input into the mathematical calculation model to calculate the virtual substitution value.

6. The intelligent fault diagnosis and handling method for a refrigeration system according to claim 1, characterized in that, If the fault type is a performance degradation that is not a safety risk, the method for actively adjusting the control parameters of the actuators of the refrigeration system or external auxiliary system includes: The optimal combination of control parameters is searched within a preset feasible region using an optimization algorithm. The objective function of the optimal combination of control parameters is to maximize the energy efficiency ratio of the refrigeration system under the current fault state. Adjusting the control parameters of the actuators of the refrigeration system or external auxiliary system includes: Adjust the fan speed or the opening of the electronic expansion valve in the refrigeration system; Alternatively, control commands can be sent through a cross-system communication interface to adjust the cooling tower fan speed or cooling water flow rate of the external auxiliary system.

7. The intelligent fault diagnosis and handling method for refrigeration systems according to claim 1, characterized in that, The internal operating parameters include thermodynamic parameters, electrical parameters, and mechanical parameters; the external operating parameters include cooling tower fan speed, cooling water inlet and outlet temperatures, and chiller unit energy efficiency ratio.

8. A smart fault diagnosis and handling system for a refrigeration system, characterized in that, Includes a controller that controls the operation of the refrigeration system based on the intelligent diagnosis and handling method for refrigeration system faults as described in any one of claims 1 to 7.

9. A smart fault diagnosis and processing system for a refrigeration system, characterized in that, include: One or more processors; Memory; And one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the programs including instructions for performing the intelligent diagnosis and handling method for refrigeration system faults as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, It includes a computer program that can be executed by a processor to perform the intelligent diagnosis and handling method for refrigeration system faults as described in any one of claims 1 to 7.

Images