Intelligent detection method and system for variable frequency controller for air conditioner

Abstract

The invention discloses an intelligent detection method and system for a variable frequency controller for an air conditioner, and relates to the field of intelligent detection, and the method comprises the steps: dynamically generating a test case set through an association rule mining algorithm based on a parameter data set of the variable frequency controller in a historical fault database; generating a test instruction set based on the test case set, and generating a digital simulation signal data stream; inputting the data flow into a variable frequency controller of the tested air conditioner, and synchronously acquiring output data of the variable frequency controller to form a real-time response data set; calculating a dynamic matching degree between the real-time response data set and fault data in a historical fault database, judging a potential fault, and tracing a fault cause label; and the newly identified fault data and the tracing result are uploaded to the historical fault database, and the association rule base is updated. The method has the advantages that potential faults of the variable-frequency controller of the air conditioner are accurately diagnosed through dynamic test case generation, real-time data matching and historical fault library updating, and the fault detection accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent detection, and in particular to an intelligent detection method and system for a frequency conversion controller for an air conditioner. Background Art

[0002] With the development of variable frequency technology, variable frequency controllers have become a core component of air conditioners. They significantly improve energy efficiency and reduce energy waste by adjusting the compressor speed to suit varying load requirements. However, variable frequency controllers are subject to various factors during operation, such as voltage fluctuations, system failures, and environmental changes, which can lead to performance degradation or even failure.

[0003] Most current intelligent detection methods and systems for variable frequency controllers used in air conditioners rely on fixed test cases and preset detection standards. These methods lack flexibility and are unable to cope with the diverse performance of variable frequency controllers in different usage environments and operating conditions. This often results in these methods being unable to provide sufficient accuracy and comprehensiveness when detecting some new faults or complex operating conditions. Secondly, most existing methods lack dynamic adjustment capabilities and are unable to automatically optimize detection strategies based on real-time data or operating status, making their detection effectiveness easily limited by specific operating conditions and external factors. In addition, current detection methods generally lack intelligent data matching mechanisms, fail to fully exploit information in historical fault databases, and lack fault prediction capabilities based on big data analysis. Summary of the Invention

[0004] To improve existing methods and systems, an intelligent detection method and system for variable frequency controllers for air conditioners are provided. This method accurately diagnoses potential faults in the variable frequency controller of the air conditioner by generating dynamic test cases, combining digital twin simulation models, real-time data matching, and updating the historical fault library, thereby improving the accuracy of fault detection and system reliability.

[0005] In order to achieve the above objects, the technical solution adopted by the present invention is: An intelligent detection method for a frequency conversion controller for an air conditioner, comprising: Based on the parameter data set of the variable frequency controller in the historical fault database, a test case set is dynamically generated through an association rule mining algorithm. Each test case in the test case set contains a combination sequence of at least two of the four core operating conditions: voltage fluctuation, frequency jump, load mutation, and temperature gradient change. The test case set covers the combination sequence of all four core operating conditions. Generate a test instruction set based on the test case set, input the test instruction set into a pre-built digital twin model for simulation, and generate a digital simulation signal data stream containing voltage, current, frequency, and protection signals; The digital simulation signal data stream is input to the variable frequency controller of the air conditioner under test in real time, and the PWM drive signal waveform, communication bus data stream and protection circuit action status code output by it are synchronously collected to form a real-time response data set; Calculate the dynamic matching degree between the real-time response data set and the fault data in the historical fault database. When the matching degree exceeds the preset threshold, it is determined that there is a potential fault and the fault cause label in the association rule is traced back. Upload the newly identified fault data and tracing results to the historical fault database and update the association rule base.

[0006] Preferably, the parameter data set of the frequency converter in the historical fault database is used to dynamically generate a test case set through an association rule mining algorithm. Each test case in the test case set includes at least a combination sequence of two of the four core operating conditions: voltage fluctuation, frequency jump, load mutation, and temperature gradient change. The combination sequences of all four core operating conditions covered by the test case set specifically include: Obtain all parameter data related to the frequency converter in the historical fault database and define four core operating conditions based on the changes in each parameter in the historical fault data, including voltage fluctuation, frequency jump, load mutation, and temperature gradient change; The APRIORI association rule mining algorithm is used to iteratively search historical fault data layer by layer to obtain frequent association rules between various working conditions in the fault data; Obtain the most representative association rules based on the support and confidence of each association rule, and remove low-frequency redundant rules; Based on the acquired association rules, a test case template is constructed. Each test case contains a combination sequence of at least two core working conditions. The test cases are then optimized to remove duplicate cases and those with high similarity. Based on the processed test case templates, a test case set is obtained.

[0007] Preferably, generating a test instruction set based on a test case set, inputting the test instruction set into a pre-built digital twin model for simulation operation, and generating a digital simulation signal data stream including voltage, current, frequency, and protection signal specifically includes: Based on the acquired test case set, test instructions for the test targets under each of the four core working conditions are generated; Build a digital twin model based on real-time data from the actual variable frequency controller system and calibrate the model using historical data; Input the test instructions into the digital twin model for dynamic simulation to obtain the response parameter data of the frequency converter under different working conditions; The digital simulation signal data stream generated in real time by the digital twin model during the simulation operation is obtained, and the signal stream includes voltage, current, frequency and protection signal data.

[0008] Preferably, the real-time input of the digital simulation signal data stream into the variable frequency controller of the air conditioner under test, and the synchronous collection of the PWM drive signal waveform, communication bus data stream and protection circuit action status code outputted by the controller to form a real-time response data set specifically include: Based on the acquired digital simulation signal data stream, the data stream is input into the variable frequency controller of the air conditioner under test for detection; Use an oscilloscope to monitor and collect the PWM drive signal waveform output by the frequency conversion controller in real time; Real-time monitoring and recording of the communication bus data flow of the air conditioner's variable frequency controller through the communication protocol; Through external sensors, the protection circuit status code of the frequency converter is collected in real time; Perform data synchronization and timing alignment based on the collected data, add test condition labels to each data set, and generate a data set.

[0009] Preferably, the dynamic matching degree between the real-time response data set and the fault data in the historical fault database is calculated. When the matching degree exceeds a preset threshold, it is determined that a potential fault exists. The fault cause label in the tracing association rule specifically includes: Extract features based on real-time response data sets and fault data in historical fault databases, and generate several feature vectors in a unified format; The feature vectors of the real-time response dataset and the fault data in the historical fault database are traversally matched, and the matching degree between the feature vectors is calculated using cosine similarity; Based on the obtained matching calculation results, a matching threshold is set according to historical fault data, and if the matching degree is greater than the threshold, it is determined that there is a potential fault; Based on the existence of potential faults, the fault data set is backtracked through the APRIORI association rule mining algorithm and adding test condition labels to each data set; Based on the matched fault features, the fault cause labels associated with the faults in the historical fault database are obtained.

[0010] Preferably, uploading the newly identified fault data and tracing results to the historical fault database and updating the association rule base specifically includes: Collect the newly identified fault data and unify the data format; Upload the processed data to the historical fault database, including fault feature information and fault cause labels; Based on new fault data, the historical fault database is maintained by inserting new records and updating existing records, and data cleaning is performed regularly to remove outdated or redundant records.

[0011] Furthermore, an intelligent detection system for a variable frequency controller for an air conditioner is proposed, comprising: Historical fault database: The historical fault database is responsible for storing and managing the historical fault data and related parameters of the frequency converter, and provides fault data query and correlation analysis functions; Association rule mining module: The association rule mining module dynamically generates a test case set through an association rule mining algorithm and extracts frequent operating condition association rules from historical fault data for testing and analysis; Test case generation module: The test case generation module generates a test case set covering four core working conditions based on association rules, and optimizes and screens the test cases to ensure efficient testing; Digital twin model module: The digital twin model module is used to build a digital twin model that matches the variable frequency controller system, perform simulation operations, and generate digital simulation signal data streams to verify the controller's response under different operating conditions. Signal acquisition and synchronization module: The signal acquisition and synchronization module is used to collect the output signal of the frequency conversion controller of the air conditioner under test in real time and perform timing synchronization processing; Data matching module: The data matching module is used to calculate the dynamic matching degree between the real-time response data set and the historical fault data, and judge the potential fault based on the matching degree and trace the cause of the fault; Fault data backtracking module: The fault data backtracking module is used to upload newly identified fault data and tracing results to the historical fault database, update the association rule base, and ensure continuous learning and optimization of the system; Processor: The processor is used to process the calculation process of each formula and the construction calculation process of each model.

[0012] Compared with the prior art, the advantages of the present invention are: The test case set dynamically generated by the association rule mining algorithm can comprehensively cover four core operating conditions: voltage fluctuation, frequency jump, load mutation, and temperature gradient change. This allows for accurate and comprehensive testing of the variable frequency controller, ensuring efficient and accurate detection. Secondly, by combining simulation with the digital twin model, the controller's response under different operating conditions can be simulated in a virtual environment, generating reliable simulation signal data streams, which greatly reduces the potential risks and costs during actual testing. In addition, the dynamic matching calculation mechanism between the real-time response data set and historical fault data can promptly detect potential faults based on the similarity between historical data and real-time data, and trace the fault cause label through association rules, effectively improving the accuracy of fault diagnosis. Finally, the system can upload newly identified fault data and update the historical fault database and association rule library, ensuring the continuous optimization and self-learning ability of the detection method, thereby continuously improving the accuracy and robustness of detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 A schematic diagram of the method proposed in the present invention; Figure 2 This is a schematic diagram of generating a test case set proposed by the present invention; Figure 3 This is a schematic diagram of generating digital simulation signal data flow proposed by the present invention; Figure 4 This is a schematic diagram of generating a response data set proposed by the present invention; Figure 5 This is a schematic diagram for determining potential faults proposed by the present invention; Figure 6 This is a schematic diagram of uploading and updating data proposed by the present invention. DETAILED DESCRIPTION

[0014] The following description is intended to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are merely examples, and those skilled in the art may conceive of other obvious variations.

[0015] An intelligent detection system for a frequency conversion controller for an air conditioner, comprising: Historical fault database: The historical fault database is responsible for storing and managing the historical fault data and related parameters of the frequency converter, and provides fault data query and correlation analysis functions; Association rule mining module: The association rule mining module dynamically generates a test case set through an association rule mining algorithm and extracts frequent operating condition association rules from historical fault data for testing and analysis; Test case generation module: The test case generation module generates a test case set covering four core working conditions based on association rules, and optimizes and screens the test cases to ensure efficient testing; Digital twin model module: The digital twin model module is used to build a digital twin model that matches the variable frequency controller system, perform simulation operations, and generate digital simulation signal data streams to verify the controller's response under different operating conditions. Signal acquisition and synchronization module: The signal acquisition and synchronization module is used to collect the output signal of the frequency conversion controller of the air conditioner under test in real time and perform timing synchronization processing; Data matching module: The data matching module is used to calculate the dynamic matching degree between the real-time response data set and the historical fault data, and judge the potential fault based on the matching degree and trace the cause of the fault; Fault data backtracking module: The fault data backtracking module is used to upload newly identified fault data and tracing results to the historical fault database, update the association rule base, and ensure continuous learning and optimization of the system; Processor: The processor is used to process the calculation process of each formula and the construction calculation process of each model.

[0016] See Figure 1 As shown, an intelligent detection method for a variable frequency controller for an air conditioner includes: Step 1: Based on the parameter data set of the variable frequency controller in the historical fault database, a test case set is dynamically generated through an association rule mining algorithm. Each test case in the test case set contains at least a combination sequence of two of the four core operating conditions: voltage fluctuation, frequency jump, load mutation, and temperature gradient change. The test case set covers the combination sequences of all four core operating conditions. Step 2: Generate a test instruction set based on the test case set, input the test instruction set into the pre-built digital twin model for simulation operation, and generate a digital simulation signal data stream containing voltage, current, frequency and protection signals; Step 3: Input the digital simulation signal data stream into the variable frequency controller of the air conditioner under test in real time, and synchronously collect the output PWM drive signal waveform, communication bus data stream and protection circuit action status code to form a real-time response data set; Step 4: Calculate the dynamic matching degree between the real-time response dataset and the fault data in the historical fault database. When the matching degree exceeds the preset threshold, a potential fault is determined to exist and the fault cause label in the association rule is traced. Step 5: Upload the newly identified fault data and tracing results to the historical fault database and update the association rule base.

[0017] See Figure 2As shown, based on the parameter data set of the variable frequency controller in the historical fault database, a test case set is dynamically generated through an association rule mining algorithm. Each test case in the test case set contains at least a combination sequence of two of the four core operating conditions: voltage fluctuation, frequency jump, load mutation, and temperature gradient change. The test case set covers the combination sequences of all four core operating conditions, specifically including: Obtain all parameter data related to the frequency converter in the historical fault database and define four core operating conditions based on the changes in each parameter in the historical fault data, including voltage fluctuation, frequency jump, load mutation, and temperature gradient change; The APRIORI association rule mining algorithm is used to iteratively search historical fault data layer by layer to obtain frequent association rules between various working conditions in the fault data; Obtain the most representative association rules based on the support and confidence of each association rule, and remove low-frequency redundant rules; Based on the acquired association rules, a test case template is constructed. Each test case contains a combination sequence of at least two core working conditions. The test cases are then optimized to remove duplicate cases and those with high similarity. Based on the processed test case templates, a test case set is obtained.

[0018] Specifically, based on the changes in historical fault data, four core operating conditions are defined, including: Voltage fluctuation: voltage fluctuation beyond a certain threshold range; Frequency hopping: the frequency change rate exceeds a certain range; Load mutation: The load fluctuates greatly, exceeding the normal operating range of the equipment; Temperature gradient change: the rate of temperature change exceeds a certain threshold; The APRIORI algorithm mines frequent itemsets layer by layer through an iterative method and generates association rules based on these itemsets. It inputs a working condition labeling dataset, sets a minimum support threshold to represent the minimum frequency of the rule in the dataset, and sets a minimum confidence threshold to represent the credibility of the rule. Calculate the support of a single working condition (number of occurrences / total number of events), retain the working conditions with support greater than or equal to the minimum support threshold, generate frequent 1-item sets, merge the frequent 1-item sets to generate candidate 2-item sets, calculate their support, and filter out frequent 2-item sets; repeat the above steps, gradually expand the size of the item set until there are no new frequent item sets, and generate all possible association rules from the frequent item sets, which are in the form of: ,in 、 It is a set of operating condition items and calculates the confidence, for example: voltage fluctuation Frequency hopping (support 0.15, confidence 0.75); By setting the minimum support threshold and the minimum confidence threshold, we can filter out rules with high support (representing the universality of the rule) and high confidence (representing the reliability of the rule), remove low-frequency redundant rules (low support or low confidence), and merge rules with similar meanings; Generate test case templates based on association rules. Each test case contains a combined sequence of at least two core conditions. The sequence indicates the order in which the conditions occur, which may affect the fault behavior. The generation logic maps each association rule (such as X => Y) to a test case sequence: the sequence form is [X, Y], indicating that condition X occurs first and condition Y occurs later. If the rule involves multiple conditions (such as from frequent itemsets), a combined sequence is generated (for example, {VF, FJ} generates the sequence [VF, FJ] or [FJ, VF]). A test case set is obtained based on the generated test case template, and each test case contains specific working condition parameter values.

[0019] See Figure 3 As shown, a test instruction set is generated based on a test case set, and the test instruction set is input into a pre-built digital twin model for simulation operation to generate a digital simulation signal data stream containing voltage, current, frequency, and protection signals. Specifically, the following steps are included: Based on the acquired test case set, test instructions for the test targets under each of the four core working conditions are generated; Build a digital twin model based on real-time data from the actual variable frequency controller system and calibrate the model using historical data; Input the test instructions into the digital twin model for dynamic simulation to obtain the response parameter data of the frequency converter under different working conditions; The digital simulation signal data stream generated in real time by the digital twin model during the simulation operation is obtained, and the signal stream includes voltage, current, frequency and protection signal data.

[0020] Specifically, based on the four core operating conditions extracted from historical data, corresponding test instructions are generated for each operating condition. The voltage fluctuation test goal is to simulate the response of the frequency converter within a specific voltage fluctuation range. The voltage fluctuation function formula is: ; in, is the nominal value of the voltage, is the amplitude of voltage fluctuation, is the fluctuation frequency, For time; The frequency jump test goal is to simulate the response of the frequency converter controller when the frequency jumps. The formula is: ; in, are the final and initial frequencies, is the time constant, is time, exp() is the empirical function; The goal of the load mutation test is to simulate the impact of load changes on the performance of the variable frequency controller; The goal of the temperature gradient change test is to simulate the impact of temperature gradient changes on the performance of the variable frequency controller; Based on physical principles and control theory, a mathematical model of the frequency converter is constructed, and the generated test instructions are input into the digital twin model. During the simulation process, the digital twin model will generate the system response data in real time. The simulation will generate real-time signal data streams related to each operating condition change, including voltage, current, frequency and protection signals.

[0021] See Figure 4 As shown in the figure, the digital simulation signal data stream is input to the variable frequency controller of the air conditioner under test in real time, and the PWM drive signal waveform, communication bus data stream and protection circuit action status code output by it are synchronously collected to form a real-time response data set, which specifically includes: Based on the acquired digital simulation signal data stream, the data stream is input into the variable frequency controller of the air conditioner under test for detection; Use an oscilloscope to monitor and collect the PWM drive signal waveform output by the frequency conversion controller in real time; Real-time monitoring and recording of the communication bus data flow of the air conditioner's variable frequency controller through the communication protocol; Through external sensors, the protection circuit status code of the frequency converter is collected in real time; Perform data synchronization and timing alignment based on the collected data, add test condition labels to each data set, and generate a data set.

[0022] Specifically, the digital simulation signal data stream is passed as the input signal stream to the frequency converter, which drives the motor through the PWM signal. Changes in the PWM waveform reflect the performance of the frequency converter and its response to the input conditions. These waveforms are monitored in real time using an oscilloscope to observe changes in parameters such as voltage and frequency. A typical waveform is shown as follows: ; in, is the maximum voltage of the PWM signal, T is the PWM period, is a periodically expanded rectangular function; Analyze the collected PWM signal waveform through an oscilloscope to extract the PWM signal frequency and the PWM signal switching time ratio; The inverter controller of an air conditioner usually communicates with external systems through a communication bus. By using a communication protocol, the data exchange flow between the inverter controller and other devices is monitored and recorded in real time. The data packet usually includes control instructions, status codes, sensor data, etc. By parsing the communication data stream, the status information of the inverter controller can be extracted. The external sensor records the protection status of the frequency converter. Whenever the external sensor detects a change in the protection circuit status, the status value is recorded. By unifying the time base and taking the millisecond-level global clock of the air conditioner main control system as the benchmark, the timestamps of all sensor data are corrected, the data synchronization timing is aligned, and a corresponding operating condition label is added to each data set according to the input signal of each data set. The corresponding operating condition label is one of voltage fluctuation, frequency jump, load mutation, and temperature gradient change, which is consistent with the test operating condition of the digital simulation signal data stream input for each data set to generate the final data set.

[0023] See Figure 5 As shown in the figure, the dynamic matching degree between the real-time response data set and the fault data in the historical fault database is calculated. When the matching degree exceeds the preset threshold, it is determined that a potential fault exists. The fault cause labels in the tracing association rules specifically include: Extract features based on real-time response data sets and fault data in historical fault databases, and generate several feature vectors in a unified format; The feature vectors of the real-time response dataset and the fault data in the historical fault database are traversally matched, and the matching degree between the feature vectors is calculated using cosine similarity; Based on the obtained matching calculation results, a matching threshold is set according to historical fault data, and if the matching degree is greater than the threshold, it is determined that there is a potential fault; Based on the existence of potential faults, the fault data set is backtracked through the APRIORI association rule mining algorithm and adding test condition labels to each data set; Based on the matched fault features, the fault cause labels associated with the faults in the historical fault database are obtained.

[0024] Specifically, based on the experience of historical fault data, a matching threshold (e.g., 0.8) is set. When the cosine similarity between the real-time response data and the historical fault data is greater than the threshold, the fault mode is considered potential, indicating that a fault may exist. Once the potential failure mode is determined, the APRIORI algorithm is used to retrospectively analyze historical failure data to mine association rules between potential failures. Based on the potential failure data and association rules obtained from the retrospective analysis, the relevant failure cause labels are extracted based on the association rule results. Each association rule can correspond to a fault cause. For example, if "frequency jump" and "voltage fluctuation" often appear together in fault records, the association rule can be used to infer that these two may be the common cause of a certain type of fault.

[0025] See Figure 6 As shown, the newly identified fault data and tracing results are uploaded to the historical fault database, and the association rule base is updated, specifically including: Collect the newly identified fault data and unify the data format; Upload the processed data to the historical fault database, including fault feature information and fault cause labels; Based on new fault data, the historical fault database is maintained by inserting new records and updating existing records, and data cleaning is performed regularly to remove outdated or redundant records.

[0026] It should be noted that the order in which the embodiments of the present invention are described above is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0027] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0028] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. An intelligent detection method for a frequency conversion controller for an air conditioner, characterized in that: include: Based on the parameter data set of the variable frequency controller in the historical fault database, a test case set is dynamically generated through an association rule mining algorithm. Each test case in the test case set contains a combination sequence of at least two of the four core operating conditions: voltage fluctuation, frequency jump, load mutation, and temperature gradient change. The test case set covers the combination sequence of all four core operating conditions. Generate a test instruction set based on the test case set, input the test instruction set into a pre-built digital twin model for simulation, and generate a digital simulation signal data stream containing voltage, current, frequency, and protection signals; The digital simulation signal data stream is input to the variable frequency controller of the air conditioner under test in real time, and the PWM drive signal waveform, communication bus data stream and protection circuit action status code output by it are synchronously collected to form a real-time response data set; Calculate the dynamic matching degree between the real-time response data set and the fault data in the historical fault database. When the matching degree exceeds the preset threshold, it is determined that there is a potential fault and the fault cause label in the association rule is traced back. Upload the newly identified fault data and tracing results to the historical fault database and update the association rule base.

2. The intelligent detection method for a frequency conversion controller for an air conditioner according to claim 1, characterized in that: Based on the parameter data set of the variable frequency controller in the historical fault database, a test case set is dynamically generated through an association rule mining algorithm. Each test case in the test case set contains at least a combination sequence of two of the four core operating conditions: voltage fluctuation, frequency jump, load mutation, and temperature gradient change. The combination sequences of all four core operating conditions covered by the test case set specifically include: Obtain all parameter data related to the frequency converter in the historical fault database and define four core operating conditions based on the changes in each parameter in the historical fault data, including voltage fluctuation, frequency jump, load mutation, and temperature gradient change; The APRIORI association rule mining algorithm is used to iteratively search historical fault data layer by layer to obtain frequent association rules between various working conditions in the fault data; Obtain the most representative association rules based on the support and confidence of each association rule, and remove low-frequency redundant rules; Based on the acquired association rules, a test case template is constructed. Each test case contains a combination sequence of at least two core working conditions. The test cases are then optimized to remove duplicate cases and those with high similarity. Based on the processed test case templates, a test case set is obtained.

3. The intelligent detection method for a frequency conversion controller for an air conditioner according to claim 1, characterized in that: Generating a test instruction set based on a test case set, inputting the test instruction set into a pre-built digital twin model for simulation and running, and generating a digital simulation signal data stream containing voltage, current, frequency, and protection signals specifically includes: Based on the acquired test case set, test instructions for the test targets under each of the four core working conditions are generated; Build a digital twin model based on real-time data from the actual variable frequency controller system and calibrate the model using historical data; Input the test instructions into the digital twin model for dynamic simulation to obtain the response parameter data of the frequency converter under different working conditions; The digital simulation signal data stream generated in real time by the digital twin model during the simulation operation is obtained, and the signal stream includes voltage, current, frequency and protection signal data.

4. The intelligent detection method for a frequency conversion controller for an air conditioner according to claim 1, characterized in that: The real-time input of the digital simulation signal data stream into the variable frequency controller of the air conditioner under test and the synchronous collection of the PWM drive signal waveform, communication bus data stream and protection circuit action status code output by the controller to form a real-time response data set specifically include: Based on the acquired digital simulation signal data stream, the data stream is input into the variable frequency controller of the air conditioner under test for detection; Use an oscilloscope to monitor and collect the PWM drive signal waveform output by the frequency conversion controller in real time; Real-time monitoring and recording of the communication bus data flow of the air conditioner's variable frequency controller through the communication protocol; Through external sensors, the protection circuit status code of the frequency converter is collected in real time; Perform data synchronization and timing alignment based on the collected data, add test condition labels to each data set, and generate a data set.

5. The intelligent detection method for a frequency conversion controller for an air conditioner according to claim 1, characterized in that: The dynamic matching degree between the real-time response data set and the fault data in the historical fault database is calculated. When the matching degree exceeds a preset threshold, it is determined that a potential fault exists. The fault cause label in the tracing association rule specifically includes: Extract features based on real-time response data sets and fault data in historical fault databases, and generate several feature vectors in a unified format; The feature vectors of the real-time response dataset and the fault data in the historical fault database are traversally matched, and the matching degree between the feature vectors is calculated using cosine similarity; Based on the obtained matching calculation results, a matching threshold is set according to historical fault data, and if the matching degree is greater than the threshold, it is determined that there is a potential fault; Based on the existence of potential faults, the fault data set is backtracked through the APRIORI association rule mining algorithm and adding test condition labels to each data set; Based on the matched fault features, the fault cause labels associated with the faults in the historical fault database are obtained.

6. The intelligent detection method for a frequency conversion controller for an air conditioner according to claim 1, characterized in that: The uploading of the newly identified fault data and tracing results to the historical fault database and updating the association rule base specifically includes: Collect the newly identified fault data and unify the data format; Upload the processed data to the historical fault database, including fault feature information and fault cause labels; Based on new fault data, the historical fault database is maintained by inserting new records and updating existing records, and data cleaning is performed regularly to remove outdated or redundant records.

7. An intelligent detection system for a frequency conversion controller for an air conditioner, used to implement an intelligent detection method for a frequency conversion controller for an air conditioner according to any one of claims 1 to 6, characterized in that: include: Historical fault database: The historical fault database is responsible for storing and managing the historical fault data and related parameters of the frequency converter, and provides fault data query and correlation analysis functions; Association rule mining module: The association rule mining module dynamically generates a test case set through an association rule mining algorithm and extracts frequent operating condition association rules from historical fault data for testing and analysis; Test case generation module: The test case generation module generates a test case set covering four core working conditions based on association rules, and optimizes and screens the test cases to ensure efficient testing; Digital twin model module: The digital twin model module is used to build a digital twin model that matches the variable frequency controller system, perform simulation operations, and generate digital simulation signal data streams to verify the controller's response under different operating conditions. Signal acquisition and synchronization module: The signal acquisition and synchronization module is used to collect the output signal of the frequency conversion controller of the air conditioner under test in real time and perform timing synchronization processing; Data matching module: The data matching module is used to calculate the dynamic matching degree between the real-time response data set and the historical fault data, and judge the potential fault based on the matching degree and trace the cause of the fault; Fault data backtracking module: The fault data backtracking module is used to upload newly identified fault data and tracing results to the historical fault database, update the association rule base, and ensure continuous learning and optimization of the system; Processor: The processor is used to process the calculation process of each formula and the construction calculation process of each model.

Images