Gas combustion appliance detection method and device
By identifying the model of the gas-burning appliance, loading the testing process template, distributing standard parameters, and scheduling the test module, combined with the anomaly identification model, the problems of low efficiency and poor adaptability in existing testing methods are solved, and an efficient and intelligent testing process and diagnostic report generation are achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-15
- Publication Date
- 2026-04-14
AI Technical Summary
Existing gas combustion appliance testing methods lack intelligent anomaly identification and automated process adjustment, resulting in low testing efficiency and poor adaptability, and an inability to flexibly adjust the testing process in real time according to changes in equipment status.
By identifying the equipment model of the gas-burning appliance, the corresponding testing process template is loaded, standard test parameters are distributed to the testing module, and tests are performed according to the module scheduling order. Combined with a pre-trained anomaly recognition model, a fusion analysis is performed to generate a diagnostic report.
It enables rapid adaptation and accurate detection of different models of gas-fired appliances, improving the accuracy, automation and efficiency of detection, and can intelligently identify anomalies and generate operable diagnostic reports.
Smart Images
Figure CN121855764A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the technical field of gas appliance testing, and in particular to a method and apparatus for testing gas combustion appliances. Background Technology
[0002] Currently, the testing of gas combustion appliances mainly relies on single testing methods, such as airtightness testing, combustion analysis, and electrical safety testing. However, these methods are usually conducted independently, and the evaluation of test results often depends on manual judgment. These traditional testing methods have certain limitations. For example, they cannot flexibly adjust the testing process in real time according to changes in equipment status, and their adaptability is poor when encountering equipment failures or environmental changes. At the same time, single-module testing methods may lead to the omission of some problems and cannot achieve intelligent analysis and processing based on real-time data.
[0003] The existing technical solutions mentioned above have the following drawbacks: existing gas combustion appliance testing methods usually do not integrate multi-module testing processes, lack intelligent anomaly identification and automated process adjustment, resulting in low testing efficiency, and therefore there is room for improvement. Summary of the Invention
[0004] To improve testing efficiency, this application provides a method and apparatus for testing gas combustion appliances.
[0005] The above-mentioned objective of this application is achieved through the following technical solution: A method for testing gas-burning appliances, the method comprising: Identify the device model of the gas combustion appliance to be tested, and load the corresponding testing process template according to the device model. The testing process template includes standard test parameters, module scheduling order and warning threshold. The standard test parameters in the test process template are distributed to the test modules, which include an airtightness test module, a combustion analysis module, and an electrical safety test module. According to the module scheduling order in the testing process template, the corresponding test module is scheduled to test the gas combustion appliance, and the subsequent test mode is determined based on the test results of the gas combustion appliance under test. After the gas-burning appliance under test has been tested, the test results are fused and analyzed based on a pre-trained anomaly recognition model to generate a corresponding diagnostic report.
[0006] By adopting the above technical solutions, and by identifying the device model of the gas combustion appliance under test and loading the corresponding testing process template, rapid adaptation to different models of gas combustion appliances can be achieved, ensuring that each device can be accurately tested according to its specific testing process. By distributing standard test parameters to the test modules, it can be ensured that each module performs its test operation according to the accurate parameters, thereby improving the accuracy and consistency of the test. By scheduling the corresponding test modules according to the module scheduling order, the gas combustion appliances can be systematically tested according to the established process, thereby improving the automation and efficiency of the testing process. By fusing and analyzing the test results based on a pre-trained anomaly recognition model, intelligent anomaly classification and problem diagnosis can be performed after the test, thereby improving the accuracy of diagnosis and generating an operable diagnostic report.
[0007] In one example, this application can be further configured as follows: the identification of the device model of the gas combustion appliance to be tested, and loading the corresponding detection process template according to the device model, specifically includes: The model identification information of the gas combustion appliance under test is obtained by automatic identification means to obtain the equipment model of the gas combustion appliance under test. The automatic identification means include one or more of the following: QR code scanning, radio frequency identification, and image recognition. Retrieve a testing process template matching the device model from the local database. The testing process template includes a set of standard test parameters, module scheduling order, allowable error range, warning threshold, and process jump rules corresponding to the device model. When the device model fails to match in the local database, a preliminary template is derived based on the device structure dimensions, gas type, and electrical interface parameters of the gas combustion appliance to be tested, and the derived template is marked as pending confirmation.
[0008] By adopting the above technical solutions, the type of gas-burning appliance can be quickly and accurately determined by automatically identifying the appliance model and obtaining its model identification information, thereby reducing manual intervention and improving identification efficiency. By retrieving the corresponding testing process template from the local database, the standard test parameters, module scheduling sequence, and warning thresholds of the appliance can be accurately matched, ensuring the comprehensiveness and scientific nature of the testing process. By performing preliminary template deduction based on the appliance's structural dimensions, gas type, and electrical interface parameters, preliminary templates can be generated for mismatched appliances, ensuring adaptability to the testing of new or special appliances, thereby improving the comprehensiveness and flexibility of appliance testing.
[0009] In one example, this application can be further configured such that distributing the standard test parameters in the detection process template to the test module specifically includes: The standard test parameters contained in the test process template are analyzed. The parameters include the target pressure value and maximum allowable leakage rate of the air tightness test module, the standard value of flue gas concentration and the threshold for flame stability judgment of the combustion analysis module, and the withstand voltage, current standard and grounding resistance threshold of the electrical safety test module. The parsed standard test parameters are assigned to the corresponding test modules according to the module mapping relationship, so that each test module performs the predetermined detection operation according to the parsed standard test parameters.
[0010] By adopting the above technical solution, the standard test parameters in the testing process template can be parsed to clearly extract and understand the specific test standards required for each test module, thereby ensuring efficient execution and accurate judgment of the test. By assigning the parsed standard test parameters to the corresponding test modules, each test module can be guaranteed to perform its tasks according to the preset standards, thereby achieving precise parameterized control, avoiding manual intervention or parameter errors, and improving the standardization and accuracy of the test.
[0011] In one example, this application can be further configured as follows: according to the module scheduling order in the detection process template, the corresponding test module is scheduled to test the gas combustion appliance, and the subsequent test mode is determined based on the test result of the gas combustion appliance under test, specifically including: According to the module scheduling order set in the detection process template, one or more modules among the air tightness detection module, combustion analysis module and electrical safety detection module are started in sequence to perform detection operations; After each test module completes its test, the test results of the test module are evaluated in real time. If the test result of a certain test module exceeds the preset warning threshold or triggers the process jump rule, the subsequent test mode is dynamically adjusted according to the process jump rule. The dynamically adjusted subsequent test mode includes: when the leakage rate of the airtightness detection module exceeds the preset safety threshold, the test of the combustion analysis module and the electrical safety detection module is terminated. If the gas combustion appliance under test does not have an electrical connection interface, skip the electrical safety detection module test; If the test results from the combustion analysis module are close to the preset flame stability threshold, the combustion test time will be extended and additional combustion stability testing will be performed to ensure the accuracy of the test results.
[0012] By adopting the above technical solution, and scheduling test modules according to the module scheduling order in the testing process template, the automation and sequential execution of testing steps can be ensured, thereby improving the systematicness and efficiency of the entire testing process. By evaluating the test results of each test module in real time, abnormal or non-compliant test results can be identified in a timely manner, thereby reducing problems in subsequent tests and improving the real-time performance and responsiveness of the testing process. By dynamically adjusting subsequent test modes, different situations can be flexibly addressed during the testing process, ensuring the comprehensiveness and accuracy of the testing process, thereby improving the reliability and adaptability of the testing.
[0013] In one example, this application can be further configured such that the gas combustion appliance detection method further includes: Collect historical test data and corresponding equipment quality tags, and construct a training dataset based on the historical test data and corresponding equipment quality tags. The historical test data includes airtightness test results, combustion analysis data and electrical safety test data. An anomaly detection model is constructed using the random forest algorithm. The anomaly detection model is trained using the training dataset, and the model parameters are optimized using cross-validation during the training process to obtain the pre-trained anomaly detection model. After the model completes training, the pre-trained anomaly recognition model is dynamically updated through an online learning mechanism, and incremental training is performed in conjunction with real-time detection data to adapt to new equipment models and changes in operating conditions.
[0014] By adopting the above technical solutions, and by collecting historical detection data and equipment quality markers, rich historical information can be provided for the training dataset, thereby improving the quality and accuracy of model training. By using the random forest algorithm to build an anomaly recognition model and performing cross-validation optimization, the model can be ensured to have high accuracy and good generalization ability, thus making anomaly recognition more accurate and highly adaptable. Through the online learning mechanism to dynamically update the model, the model can be adjusted and optimized in real time according to new equipment models and changes in operating conditions, making the detection method highly flexible and adaptable, and able to cope with the continuous changes in future equipment.
[0015] In one example, this application can be further configured as follows: the detection results of the gas combustion appliance under test after the detection is completed based on the pre-trained anomaly recognition model are fused and analyzed to generate a corresponding diagnostic report, specifically including: The test results of the gas combustion appliance under test are input into the pre-trained anomaly recognition model for fusion analysis, and anomaly classification labels are output. Based on the anomaly classification labels, cause analysis is performed to obtain anomaly cause analysis results, and operation suggestions are generated based on the anomaly cause analysis results; A diagnostic report is generated based on the anomaly classification labels, the anomaly cause analysis results, and the operation suggestions.
[0016] By adopting the above technical solution, and inputting the test results of the gas combustion appliance under test into the anomaly identification model for fusion analysis, the test results can be quickly and accurately classified and identified, thereby improving the accuracy and intelligence of anomaly detection. By performing cause analysis based on anomaly classification tags, in-depth cause analysis can be provided for each anomaly, helping users accurately understand the root cause of the problem, thus providing a basis for subsequent operations. By generating operation suggestions, practical and feasible handling solutions can be provided to users after identifying the cause of the anomaly, thereby improving the practicality and guidance of the entire testing process and helping to quickly take effective repair or improvement measures.
[0017] In one example, this application can be further configured such that the gas combustion appliance detection method further includes: During the detection process, external environmental parameters are monitored in real time, and when the external environmental parameters change, an environmental change log is automatically recorded and generated. Adjust the standard test parameters in the testing process template according to the environmental change log to ensure the accuracy and adaptability of the test results.
[0018] By adopting the above technical solutions and monitoring external environmental parameters in real time, the testing process can be ensured to adapt to different environmental changes, thereby improving the adaptability and accuracy of the test. By automatically recording and generating environmental change logs, the impact of environmental parameter changes on the test results can be traced and analyzed, thereby providing data support for the testing process and ensuring the accuracy of the test. By adjusting the test parameters according to the environmental change logs, the testing process can be flexibly adjusted when environmental conditions are unstable, so as to maintain the stability and reliability of the test results.
[0019] The second objective of this invention is achieved through the following technical solution: A gas combustion appliance testing device, the gas combustion appliance testing device comprising: The device identification module is used to identify the device model of the gas combustion appliance to be tested, and load the corresponding detection process template according to the device model. The detection process template includes standard test parameters, module scheduling order and warning threshold. The parameter distribution module is used to distribute the standard test parameters in the test process template to the test modules, which include an airtightness test module, a combustion analysis module, and an electrical safety test module. The test scheduling module is used to schedule the corresponding test modules to test the gas combustion appliance according to the module scheduling order in the test process template, and determine the subsequent test mode based on the test results of the gas combustion appliance under test. The anomaly analysis module is used to perform a fusion analysis on the detection results of the gas combustion appliance after the detection is completed, based on a pre-trained anomaly recognition model, and generate a corresponding diagnostic report.
[0020] By adopting the above technical solutions, and by identifying the device model of the gas combustion appliance under test and loading the corresponding testing process template, rapid adaptation to different models of gas combustion appliances can be achieved, ensuring that each device can be accurately tested according to its specific testing process. By distributing standard test parameters to the test modules, it can be ensured that each module performs its test operation according to the accurate parameters, thereby improving the accuracy and consistency of the test. By scheduling the corresponding test modules according to the module scheduling order, the gas combustion appliances can be systematically tested according to the established process, thereby improving the automation and efficiency of the testing process. By fusing and analyzing the test results based on a pre-trained anomaly recognition model, intelligent anomaly classification and problem diagnosis can be performed after the test, thereby improving the accuracy of diagnosis and generating an operable diagnostic report.
[0021] In summary, this application includes the following beneficial technical effects: 1. By identifying the device model of the gas combustion appliance under test and loading the corresponding test process template, it is possible to quickly adapt to different models of gas combustion appliances, thereby ensuring that each device can be accurately tested according to its specific test process; by distributing standard test parameters to the test modules, it is possible to ensure that each module performs its test operation according to the accurate parameters, thereby improving the accuracy and consistency of the test. 2. By scheduling the corresponding test modules according to the module scheduling order, the gas combustion appliances can be systematically tested according to the established process, thereby improving the automation and efficiency of the testing process; by fusing and analyzing the test results based on the pre-trained anomaly recognition model, intelligent anomaly classification and problem diagnosis can be performed after the test, thereby improving the accuracy of diagnosis and generating an operable diagnostic report. Attached Figure Description
[0022] Figure 1 This is a flowchart of a gas combustion appliance testing method according to one embodiment of this application; Figure 2 This is a flowchart illustrating the implementation of step S10 in a gas combustion appliance detection method according to an embodiment of this application. Figure 3This is a flowchart illustrating the implementation of step S20 in a gas combustion appliance detection method according to an embodiment of this application. Figure 4 This is a flowchart illustrating the implementation of step S30 in a gas combustion appliance detection method according to an embodiment of this application. Figure 5 This is another implementation flowchart of step S40 in a gas combustion appliance detection method according to one embodiment of this application; Figure 6 This is a flowchart illustrating the implementation of step S40 in a gas combustion appliance detection method according to an embodiment of this application. Figure 7 This is another implementation flowchart of a gas combustion appliance detection method according to one embodiment of this application; Figure 8 This is a schematic block diagram of a gas combustion appliance detection device according to one embodiment of this application; Figure 9 This is a schematic diagram of the structure of a gas combustion appliance testing device in a gas combustion appliance testing method according to an embodiment of this application. Detailed Implementation
[0023] The present application will be further described in detail below with reference to the accompanying drawings.
[0024] In one embodiment, such as Figure 1 and Figure 9 As shown, this application discloses a method for testing gas-burning appliances, applied to a gas-burning appliance testing device. The method specifically includes the following steps: S10: Identify the device model of the gas combustion appliance to be tested, and load the corresponding test process template according to the device model. The test process template includes standard test parameters, module scheduling order and warning threshold.
[0025] Specifically, the device model of the gas combustion appliance under test is obtained through automatic identification methods, including QR code scanning, radio frequency identification, and image recognition. These methods automatically read the device identification information and match the device model with device information pre-stored in a local database to obtain the device model. Based on the identified device model, a corresponding testing process template is loaded. This template includes standard test parameters, module scheduling order, and warning thresholds for that device model. For example, if the device model under test is "ABC-123", then the standard test parameters related to "ABC-123" are retrieved from the database, such as the standard pressure value for air tightness testing and the standard value for flue gas concentration for combustion analysis, as well as the module scheduling order for testing, such as performing air tightness testing first, then combustion analysis testing, and finally electrical safety testing.
[0026] S20: Distribute the standard test parameters in the test process template to the test modules, which include an airtightness test module, a combustion analysis module, and an electrical safety test module.
[0027] Specifically, by parsing the loaded testing process template, standard test parameters are extracted, such as the target pressure value and maximum allowable leakage rate of the airtightness testing module, the standard value of flue gas concentration and the flame stability judgment threshold of the combustion analysis module, and the withstand voltage, current standard, and grounding resistance threshold of the electrical safety testing module. These extracted standard test parameters are then distributed to the corresponding testing modules so that each module can perform predetermined testing operations according to the specified standard parameters. For example, in the airtightness testing module, the extracted target pressure value is used to set the pressure measurement range of the testing equipment, and the maximum allowable leakage rate is used to determine whether the equipment meets the airtightness standard. In the combustion analysis module, the standard value of flue gas concentration is used to determine whether combustion is complete, while the flame stability judgment threshold is used to evaluate the stability of the flame, ensuring that the test results meet safety requirements.
[0028] S30: According to the module scheduling order in the testing process template, schedule the corresponding test module to test the gas combustion appliance, and determine the subsequent test mode based on the test results of the gas combustion appliance to be tested.
[0029] Specifically, according to the module scheduling order set in the testing process template, the corresponding test modules are started sequentially to test gas combustion appliances. For example, if the template specifies that air tightness testing is performed first, followed by combustion analysis testing, and finally electrical safety testing, then the system will start the air tightness testing module, combustion analysis module, and electrical safety testing module in that order. During each module's testing, the system collects test results in real time and dynamically determines whether to adjust subsequent test modes based on these results. If the test results of a certain module show abnormalities, the system will change the subsequent test steps according to preset process jump rules. For example, if the air tightness testing module detects a leakage rate exceeding a preset safety threshold, the subsequent combustion analysis and electrical safety testing will be immediately terminated to avoid unnecessary testing or potential safety risks.
[0030] S40: After the gas-burning appliance under test has been tested, the test results are fused and analyzed based on the pre-trained anomaly recognition model to generate a corresponding diagnostic report.
[0031] Specifically, after all testing modules are completed, all test results, including airtightness test results, combustion analysis results, and electrical safety test data, are input into a pre-trained anomaly identification model. This model will perform a fusion analysis of the test results for the gas combustion appliance under test by comparing historical test data with the equipment's standard behavior patterns to identify any anomalies. For example, if the airtightness test results show a significant leak, and the combustion analysis detects incomplete combustion, the model will label these anomalies and speculate on possible causes of equipment failure, such as poor sealing or burner damage. Finally, the system generates a detailed diagnostic report, which includes the test results of each testing module, anomaly classification labels (such as normal, abnormal, fault), anomaly cause analysis, and suggested remedial measures, such as replacing parts or repairing the equipment.
[0032] In one embodiment, such as Figure 2 As shown, in step S10, the device model of the gas combustion appliance to be tested is identified, and the corresponding testing process template is loaded according to the device model. Specifically, this includes: S11: Obtain the model identification information of the gas combustion appliance under test through automatic identification methods to obtain the equipment model of the gas combustion appliance under test. The automatic identification methods include one or more of the following: QR code scanning, radio frequency identification, and image recognition.
[0033] Specifically, the model number of the gas appliance under test is obtained through automatic identification methods, including QR code scanning, radio frequency identification (RFID), and image recognition. For example, QR code scanning technology allows a scanner to recognize and decode the QR code printed on the appliance to obtain the model number information; or RFID technology automatically reads and identifies the model number when the appliance under test is near the reader; or image recognition technology uses a camera to capture images of labels or printed information on the appliance and extracts and identifies the model number using image recognition algorithms. These automatic identification methods can efficiently extract the model number information from the gas appliance under test, avoiding human input errors and improving identification efficiency and accuracy.
[0034] S12: Retrieve a test process template that matches the device model from the local database. The test process template includes the standard test parameter set corresponding to the device model, the module scheduling order, the allowable error range, the warning threshold, and the process jump rules.
[0035] Specifically, based on the equipment model obtained through automatic identification, a search is performed in the local database to find a testing process template matching that model. This template includes a set of standard test parameters customized for that equipment model, such as standard pressure values for airtightness testing, flue gas concentration ranges and flame stability thresholds for combustion analysis, and standard withstand voltage values for electrical safety testing. In addition to test parameters, it also includes the module scheduling order, specifying the execution order of testing modules (e.g., airtightness testing module executed first, combustion analysis module followed, and electrical safety testing module executed last); allowable error ranges, such as the maximum tolerance for gas leakage rate; warning thresholds, which trigger an alarm if a test result exceeds these thresholds; and process jump rules, allowing automatic skipping of subsequent testing steps if a result in a certain stage fails. For example, if the equipment model is "XYZ123", the template returned from the database will ensure that subsequent tests are executed sequentially and meet the equipment characteristics.
[0036] S13: When the device model fails to match in the local database, a preliminary template is derived based on the device structure dimensions, gas type, and electrical interface parameters of the gas combustion appliance to be tested, and the derived template is marked as pending confirmation.
[0037] Specifically, if a testing process template that perfectly matches the equipment model cannot be found in the local database, a preliminary template deduction is performed based on the equipment's structural dimensions (such as size, shape, and weight), gas type (such as natural gas or liquefied petroleum gas), and electrical interface parameters (such as voltage, current, and interface type). Based on this information, a preliminary testing process template suitable for the equipment is automatically deduced, including preliminary test parameters and module scheduling sequence. This template is marked as "pending confirmation" and submitted to professionals for manual review or further adjustments to ensure its adaptability and accuracy. For example, if the equipment model is "XYZ200" and there is no directly corresponding template in the database, the system will deduce a basic testing process based on its structural dimensions, use of natural gas as fuel, and unique electrical interfaces, and submit it for manual review or further modification.
[0038] In one embodiment, such as Figure 3 As shown, in step S20, the standard test parameters in the detection process template are distributed to the test module, specifically including: S21: Analyze the standard test parameters contained in the test process template. The parameters include the target pressure value and maximum allowable leakage rate of the airtightness test module, the standard value of flue gas concentration and the threshold for flame stability judgment of the combustion analysis module, and the withstand voltage, current standard and grounding resistance threshold of the electrical safety test module.
[0039] Specifically, after loading the testing process template, the standard test parameters it contains are first parsed. The parsing process involves extracting each parameter from the testing process template according to its module category and assigning it to the corresponding test module. For the airtightness testing module, the target pressure value and maximum allowable leakage rate are extracted. For example, the target pressure value is set to 10 Pa, and the maximum allowable leakage rate is 0.5%. This value represents the standard range for airtightness testing during the testing process. If the airtightness test leakage rate exceeds this threshold, it is considered abnormal. In the combustion analysis module, the standard value of flue gas concentration and the flame stability judgment threshold are extracted. For example, the maximum tolerance value of flue gas concentration is 100 ppm, and the threshold for flame stability is 90%, meaning that an alarm will be triggered when the flame is unstable or the flue gas concentration exceeds the standard. In the electrical safety testing module, the withstand voltage, current standard, and grounding resistance threshold are extracted. For example, the withstand voltage is set to 220V, the current standard is 5A, and the grounding resistance threshold is 0.1Ω. After the standard parameters for each test module are parsed, these parameters will be used in subsequent testing operations.
[0040] S22: Assign the parsed standard test parameters to the corresponding test modules according to the module mapping relationship, so that each test module can perform the predetermined detection operation according to the parsed standard test parameters.
[0041] Specifically, based on the function and requirements of each module, standard test parameters are assigned to the corresponding test modules according to the module mapping relationship. Each test module needs to perform a test task matching its function, and the parsed parameters are passed to each module as input. For example, the airtightness test module needs to perform an airtightness test based on the parsed target pressure value and maximum allowable leakage rate. The equipment will be checked for sealing under this pressure, and the leakage rate will be monitored to see if it exceeds the preset maximum tolerance value. The combustion analysis module performs combustion analysis based on the parsed flue gas concentration standard value and flame stability judgment threshold, detecting the combustion efficiency and flue gas concentration of the equipment, and judging whether the flame is stable. The electrical safety test module performs an electrical safety check based on the parsed withstand voltage, current standard, and grounding resistance threshold, testing whether the equipment meets electrical safety standards. For example, if the withstand voltage test of the electrical part of the equipment exceeds 220V, or the grounding resistance exceeds 0.1Ω, it is judged as electrical safety unqualified. Through these assignments, it is ensured that each test module performs the corresponding operation according to the standard and can output the corresponding test results for comprehensive judgment.
[0042] In one embodiment, such as Figure 4 As shown, in step S30, the corresponding test module is scheduled to test the gas combustion appliance according to the module scheduling order in the test process template, and the subsequent test mode is determined based on the test results of the gas combustion appliance under test, specifically including: S31: Start one or more modules from the air tightness testing module, combustion analysis module and electrical safety testing module in sequence according to the module scheduling order set in the testing process template to perform testing operations.
[0043] Specifically, the module scheduling sequence set in the testing process template clearly defines the execution order of each test module. First, the airtightness testing module is activated to perform an airtightness test, followed by the combustion analysis module, and finally the electrical safety testing module. According to the testing process template, the system first activates the airtightness testing module to check the sealing of the gas combustion appliance, verifying the absence of leaks and ensuring safe gas use. Next, the combustion analysis module begins working, detecting the combustion efficiency and flue gas emissions of the gas combustion appliance to ensure it meets environmental protection requirements. Finally, the electrical safety testing module performs an electrical safety check to ensure that the electrical components of the equipment are free from wiring faults, overloads, or poor grounding. If the testing sequence specified in the testing process template changes, the module execution order will be adjusted accordingly to meet the needs of different equipment and specific testing scenarios.
[0044] S32: After each test module completes its test, the test results of the test module are evaluated in real time. If the test result of a certain test module exceeds the preset warning threshold or triggers the process jump rule, the subsequent test mode is dynamically adjusted according to the process jump rule.
[0045] Specifically, once a test module completes its testing operation, the system immediately evaluates the module's test results in real time. For example, if the leakage rate of the airtightness testing module exceeds the preset maximum allowable value (e.g., 0.5%), the module's test result is marked as abnormal, triggering a process jump rule. The system will then stop testing subsequent modules to avoid unnecessary testing operations and potential safety risks. Similarly, if the flue gas concentration of the combustion analysis module exceeds the preset safety range (e.g., exceeding 100 ppm), an early warning will be triggered, and an emergency response procedure will be initiated to make necessary process adjustments to ensure the smooth progress of subsequent testing stages. The process jump rule will dynamically adjust the subsequent test mode based on different early warning situations, such as skipping the electrical safety testing module or extending the combustion test time to further verify combustion stability.
[0046] The dynamically adjusted subsequent test modes include: terminating the testing of the combustion analysis module and the electrical safety detection module when the leakage rate of the airtightness detection module exceeds the preset safety threshold.
[0047] Specifically, when the airtightness testing module shows a leakage rate exceeding a preset safety threshold (e.g., 0.5%), the system will immediately terminate subsequent testing operations of the combustion analysis and electrical safety testing modules to prevent unnecessary combustion analysis and electrical safety testing from continuing. This measure avoids continuing non-compliant tests, saves time and resources, and prevents further equipment damage or unsafe test data. For example, if the airtightness test result is 1%, far exceeding the 0.5% safety threshold, the system will immediately terminate the execution of the combustion analysis and electrical safety testing modules to prevent combustion or electrical failure caused by excessive leakage.
[0048] If the gas-burning appliance under test does not have an electrical connection interface, skip the electrical safety testing module.
[0049] Specifically, if the gas appliance under test does not include an electrical connection interface in its design (e.g., the device is a purely mechanical combustion appliance without electrical components or interfaces), the system will automatically skip the electrical safety detection module test. This adjustment dynamically determines whether an electrical safety check is required by detecting the device's interface type, avoiding unnecessary testing steps and wasted time. For example, some older gas stoves without an electrical control system do not require an electrical safety check; the system will identify this type of device and skip the electrical safety test, proceeding directly to the next test step.
[0050] If the test results from the combustion analysis module are close to the preset flame stability threshold, the combustion test time will be extended and additional combustion stability testing will be performed to ensure the accuracy of the test results.
[0051] Specifically, if the combustion analysis module's test results show that the flame stability is close to the preset judgment threshold (e.g., a test result of 88%, close to the preset 90% stability threshold), the system will automatically extend the combustion test time and increase the number of combustion stability checks to ensure more accurate results. This dynamic adjustment mechanism ensures that, under critical conditions, the test can obtain sufficient data to make a final judgment. For example, if the flame stability result is close to but does not meet the standard, extending the test time and increasing stability checks can effectively eliminate occasional external interference factors, such as wind speed changes or unstable airflow, thereby ensuring the accuracy and reliability of the test results.
[0052] In one embodiment, such as Figure 5 As shown, the method for testing gas combustion appliances also includes: S401: Collect historical test data and corresponding equipment quality tags, and build a training dataset based on the historical test data and corresponding equipment quality tags. The historical test data includes airtightness test results, combustion analysis data and electrical safety test data.
[0053] Specifically, during the testing process, historical testing data is collected and stored in real time. This data includes equipment airtightness test results, such as leakage rate data; combustion analysis data, such as smoke concentration and flame stability; and electrical safety test data, such as voltage, current, and grounding resistance values. For each test result, it is combined with equipment quality labeling information, including the equipment's operating years, historical fault records, and maintenance status. By comparing the relationship between the test results and the quality labels, test results that do not meet the standards are marked as abnormal data, such as excessive leakage rate or insufficient flame stability, while test results that meet the standards are marked as normal data. These data are input into the model when building the training dataset to ensure that the model can identify which data is normal and which is abnormal. In this way, the model can better adapt to various equipment models and different operating conditions. For example, if the airtightness test result of a certain piece of equipment shows a large leak, but the historical quality label of the equipment is "long-term lack of maintenance," this information will be input as an anomaly label into the training dataset to help the model learn the relationship between equipment maintenance and test results.
[0054] S402: An anomaly detection model is constructed using the random forest algorithm. The anomaly detection model is trained based on the training dataset, and the model parameters are optimized using cross-validation during the training process to obtain a pre-trained anomaly detection model.
[0055] Specifically, the anomaly detection model is constructed using the collected training dataset and the Random Forest algorithm. The Random Forest algorithm classifies data using multiple decision trees and improves prediction accuracy through ensemble learning. During training, cross-validation is used to optimize model parameters. This means dividing the training dataset into several subsets, and the model is trained and validated sequentially on different subsets to ensure consistent performance across different datasets and avoid overfitting. Cross-validation helps identify optimal model parameters, such as the depth of the decision trees and feature selection strategies, thereby improving the model's generalization ability and accuracy. For example, if the training dataset contains detection data for multiple device models, the model learns the performance differences of different devices under the same operating conditions and classifies and evaluates the detection results of new devices accordingly.
[0056] S403: After the model completes training, the pre-trained anomaly recognition model is dynamically updated through an online learning mechanism, and incremental training is performed in combination with real-time detection data to adapt to new equipment models and changes in operating conditions.
[0057] Specifically, after the initially trained anomaly detection model is completed and deployed, it is dynamically updated through an online learning mechanism. Whenever new detection data is acquired, such as real-time airtightness test data or combustion analysis data, the model uses this real-time data as incremental data for training, gradually optimizing the model to adapt to new equipment models or changes in operating conditions. For example, when a new equipment model is put into testing, the model's parameters are fine-tuned based on real-time detection data, enabling the model to adapt to the characteristics of the new model. The online learning mechanism continuously absorbs new detection data, promptly adjusting the model's decision boundaries to prevent the model from becoming outdated or losing its adaptability to new equipment. Through this incremental training, the model not only continuously improves its accuracy but also maintains sensitivity to changes in equipment status under different operating conditions, ensuring the timeliness and reliability of the detection results.
[0058] In one embodiment, such as Figure 6 As shown, in step S40, the detection results of the gas combustion appliance under test are fused and analyzed based on the pre-trained anomaly recognition model after the test, and a corresponding diagnostic report is generated, which specifically includes: S41: Input the test results after the gas combustion appliance under test is completed into the pre-trained anomaly recognition model for fusion analysis and output anomaly classification labels.
[0059] Specifically, after all test modules of the gas combustion appliance under test have been completed, all test results are compiled and input into a pre-trained anomaly recognition model, including data such as airtightness leakage rate, combustion analysis flue gas concentration, flame stability, and electrical safety. The model then performs a fusion analysis based on historical data and features from the training set, combined with the test results, and outputs an anomaly classification label. This label categorizes the test results into multiple classes, such as "normal," "minor anomaly," and "serious anomaly," for further analysis and processing. For example, if the airtightness test shows a high leakage rate, and the combustion analysis also indicates an unstable flame, the model may output a "serious anomaly" label, indicating a significant risk to the equipment requiring immediate action.
[0060] S42: Perform cause analysis based on anomaly classification labels to obtain anomaly cause analysis results, and generate operation suggestions based on the anomaly cause analysis results.
[0061] Specifically, based on the output anomaly classification labels, further cause analysis is performed. The system analyzes possible causes of the anomaly based on the model's criteria for each anomaly classification label, combined with historical failure modes and failure data from similar equipment. For example, if the output anomaly classification label is "minor anomaly," and the equipment's airtightness leakage rate is at the upper limit of the acceptable range, the combustion analysis module may analyze that the root cause of the problem is that the equipment has not been maintained for a long time or its combustion efficiency has decreased. In this way, the specific cause of the equipment anomaly can be accurately identified. Based on the analysis results, the system generates operational suggestions, such as "It is recommended to perform regular maintenance on the equipment, clean the burner, and conduct an airtightness check," to help operators quickly take appropriate measures to avoid further damage to the equipment or operational instability.
[0062] S43: Generate a diagnostic report based on the anomaly classification label, anomaly cause analysis results, and operational suggestions.
[0063] Specifically, after completing the anomaly classification and cause analysis, the system integrates all test results, analysis conclusions, and operational suggestions to generate a complete diagnostic report. The report details all test parameters, anomaly classification labels, analysis results for each test, and corresponding operational suggestions. For example, if an airtightness issue is detected in the equipment and analysis indicates a leak may be caused by aging seals, the report will explain this in detail and recommend replacing the seals or performing repairs to ensure the long-term safe operation of the equipment. Furthermore, the diagnostic report includes the equipment's testing history, failure mode statistics, and maintenance recommendations to help technicians determine whether a comprehensive inspection or adjustment of the equipment is necessary. This diagnostic report not only helps to identify potential problems promptly but also provides data support for subsequent equipment management and maintenance.
[0064] In one embodiment, such as Figure 7 As shown, the method for testing gas combustion appliances also includes: S50: During the detection process, external environmental parameters are monitored in real time. When external environmental parameters change, environmental change logs are automatically recorded and generated.
[0065] Specifically, during the testing of gas-fired appliances, external environmental parameters such as temperature, humidity, and air pressure are monitored and recorded in real time. These environmental parameters can affect the accuracy and reliability of the test results, therefore they must be tracked promptly. During the testing process, sensors or external measuring devices continuously monitor these environmental changes and upload them to the testing platform in real time through a data acquisition system. Whenever a significant change occurs in an environmental parameter, such as a sudden drop in temperature or an increase in air pressure, the change is automatically recorded, generating an environmental change log. This log contains the specific numerical value of the change, the time of the change, and related test data. For example, when the temperature rises from 20°C to 25°C, this change is recorded along with the relevant test data at the time of the change. This helps in subsequent analysis to determine whether the deviation in the test results is due to environmental changes.
[0066] S60: Adjust the standard test parameters in the testing process template according to the environmental change log to ensure the accuracy and adaptability of the test results.
[0067] Specifically, based on real-time recorded environmental change logs, the testing platform dynamically adjusts the standard test parameters in the testing process template. For example, if the air pressure changes significantly during testing, such as dropping from the normal 1013 hPa to 1000 hPa, the system automatically adjusts relevant test parameters accordingly, such as the standard value of flue gas concentration in combustion analysis or the pressure setpoint in airtightness testing, to ensure that the test results still conform to actual environmental conditions. For instance, if the outside temperature suddenly rises, this may affect the flame stability parameters in the combustion analysis module. The system will adjust the temperature threshold for flame stability determination accordingly to avoid erroneous judgments caused by test parameters that are not adapted to environmental changes. In this way, the parameters during the testing process can be adjusted according to actual environmental changes, ensuring the accuracy and adaptability of the test results. For example, in seasons with drastic temperature changes, the system will pre-set temperature adjustment rules to ensure that the testing remains stable and accurate under large temperature differences.
[0068] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.
[0069] In one embodiment, a gas combustion appliance detection device is provided, which corresponds one-to-one with the gas combustion appliance detection method described in the above embodiments. For example... Figure 8 As shown, this gas combustion appliance detection device includes an equipment identification module, a parameter distribution module, a test scheduling module, and an anomaly analysis module. Detailed descriptions of each functional module are as follows: The device identification module is used to identify the device model of the gas combustion appliance to be tested, and load the corresponding test process template according to the device model. The test process template includes standard test parameters, module scheduling order and warning threshold. The parameter distribution module is used to distribute the standard test parameters in the test process template to the test modules, which include the airtightness test module, the combustion analysis module, and the electrical safety test module. The test scheduling module is used to schedule the corresponding test modules to test the gas combustion appliances according to the module scheduling order in the test process template, and determine the subsequent test mode based on the test results of the gas combustion appliances under test. The anomaly analysis module is used to perform fusion analysis on the test results of the gas-burning appliance after the test is completed, based on a pre-trained anomaly recognition model, and generate a corresponding diagnostic report.
[0070] Optionally, the device identification module includes: The automatic identification submodule is used to obtain the model identification information of the gas combustion appliance under test through automatic identification methods to obtain the equipment model of the gas combustion appliance under test. The automatic identification methods include one or more of the following: QR code scanning, radio frequency identification, and image recognition. The database retrieval submodule is used to retrieve the testing process template that matches the device model from the local database. The testing process template includes the standard test parameter set corresponding to the device model, the module scheduling order, the allowable error range, the warning threshold and the process jump rules. The template deduction submodule is used to perform preliminary template deduction based on the equipment structure dimensions, gas type and electrical interface parameters of the gas combustion appliance under test when the equipment model fails to match in the local database, and marks the deduced template as pending confirmation.
[0071] Optionally, the parameter distribution module includes: The parameter parsing submodule is used to parse the standard test parameters contained in the test process template. The parameter content includes the target pressure value and maximum allowable leakage rate of the air tightness test module, the standard value of flue gas concentration and the flame stability judgment threshold of the combustion analysis module, and the withstand voltage, current standard and grounding resistance threshold of the electrical safety test module. The parameter allocation submodule is used to allocate the parsed standard test parameters to the corresponding test modules according to the module mapping relationship, so that each test module can perform the predetermined detection operation according to the parsed standard test parameters.
[0072] Optionally, the test scheduling module includes: The module startup submodule is used to sequentially start one or more modules among the air tightness testing module, combustion analysis module, and electrical safety testing module to perform testing operations according to the module scheduling order set in the testing process template. The result evaluation submodule is used to evaluate the test results of each test module in real time after the test is completed. If the test result of a certain test module exceeds the preset warning threshold or triggers the process jump rule, the subsequent test mode will be dynamically adjusted according to the process jump rule.
[0073] Optionally, a gas combustion appliance detection device further includes: The historical data collection module is used to collect historical test data and corresponding equipment quality marks, and to build a training dataset based on the historical test data and corresponding equipment quality marks. The historical test data includes airtightness test results, combustion analysis data and electrical safety test data. The model training module is used to build an anomaly recognition model using the random forest algorithm. It trains the anomaly recognition model based on the training dataset and optimizes the model parameters using cross-validation during the training process to obtain a pre-trained anomaly recognition model. The incremental learning module is used to dynamically update the pre-trained anomaly recognition model through an online learning mechanism after the model has been trained. It combines real-time detection data for incremental training to adapt to new equipment models and changes in operating conditions.
[0074] Optional, the anomaly analysis module includes: The result input submodule is used to input the test results of the gas combustion appliance after the test is completed into the pre-trained anomaly recognition model for fusion analysis and output anomaly classification labels. The cause analysis submodule is used to perform cause analysis based on anomaly classification tags, obtain anomaly cause analysis results, and generate operation suggestions based on the anomaly cause analysis results; The report generation submodule is used to generate diagnostic reports based on anomaly classification tags, anomaly cause analysis results, and operational suggestions.
[0075] Optionally, a gas combustion appliance detection device further includes: The environmental monitoring module is used to monitor external environmental parameters in real time during the detection process, and automatically record and generate an environmental change log when the external environmental parameters change. The parameter adjustment module is used to adjust the standard test parameters in the testing process template according to the environmental change log to ensure the accuracy and adaptability of the test results.
[0076] For specific limitations regarding a gas-fired appliance testing device, please refer to the limitations regarding a gas-fired appliance testing method described above, which will not be repeated here. Each module in the aforementioned gas-fired appliance testing device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.
[0077] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.
[0078] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.
Claims
1. A method for testing gas-fired appliances, characterized in that, The method for detecting gas combustion appliances includes: Identify the device model of the gas combustion appliance to be tested, and load the corresponding testing process template according to the device model. The testing process template includes standard test parameters, module scheduling order and warning threshold. The standard test parameters in the test process template are distributed to the test modules, which include an airtightness test module, a combustion analysis module, and an electrical safety test module. According to the module scheduling order in the testing process template, the corresponding test module is scheduled to test the gas combustion appliance, and the subsequent test mode is determined based on the test results of the gas combustion appliance under test. After the gas-burning appliance under test has been tested, the test results are fused and analyzed based on a pre-trained anomaly recognition model to generate a corresponding diagnostic report.
2. The method for detecting gas combustion appliances according to claim 1, characterized in that, The process of identifying the device model of the gas-burning appliance under test and loading the corresponding detection process template based on the device model specifically includes: The model identification information of the gas combustion appliance under test is obtained by automatic identification means to obtain the equipment model of the gas combustion appliance under test. The automatic identification means include one or more of the following: QR code scanning, radio frequency identification, and image recognition. Retrieve a testing process template matching the device model from the local database. The testing process template includes a set of standard test parameters, module scheduling order, allowable error range, warning threshold, and process jump rules corresponding to the device model. When the device model fails to match in the local database, a preliminary template is derived based on the device structure dimensions, gas type, and electrical interface parameters of the gas combustion appliance to be tested, and the derived template is marked as pending confirmation.
3. The method for detecting gas combustion appliances according to claim 1, characterized in that, The step of distributing the standard test parameters in the detection process template to the test module specifically includes: The standard test parameters contained in the test process template are analyzed. The parameters include the target pressure value and maximum allowable leakage rate of the air tightness test module, the standard value of flue gas concentration and the threshold for flame stability judgment of the combustion analysis module, and the withstand voltage, current standard and grounding resistance threshold of the electrical safety test module. The parsed standard test parameters are assigned to the corresponding test modules according to the module mapping relationship, so that each test module performs the predetermined detection operation according to the parsed standard test parameters.
4. The method for detecting gas combustion appliances according to claim 1, characterized in that, The step of scheduling the corresponding test modules to test the gas combustion appliance according to the module scheduling order in the testing process template, and determining the subsequent test mode based on the test results of the gas combustion appliance under test, specifically includes: According to the module scheduling order set in the detection process template, one or more modules among the air tightness detection module, combustion analysis module and electrical safety detection module are started in sequence to perform detection operations; After each test module completes its test, the test results of the test module are evaluated in real time. If the test result of a certain test module exceeds the preset warning threshold or triggers the process jump rule, the subsequent test mode is dynamically adjusted according to the process jump rule. The dynamically adjusted subsequent test mode includes: when the leakage rate of the airtightness detection module exceeds the preset safety threshold, the test of the combustion analysis module and the electrical safety detection module is terminated. If the gas combustion appliance under test does not have an electrical connection interface, skip the electrical safety detection module test; If the test results from the combustion analysis module are close to the preset flame stability threshold, the combustion test time will be extended and additional combustion stability testing will be performed to ensure the accuracy of the test results.
5. The method for testing gas combustion appliances according to claim 1, characterized in that, The method for detecting gas combustion appliances also includes: Collect historical test data and corresponding equipment quality tags, and construct a training dataset based on the historical test data and corresponding equipment quality tags. The historical test data includes airtightness test results, combustion analysis data and electrical safety test data. An anomaly detection model is constructed using the random forest algorithm. The anomaly detection model is trained using the training dataset, and the model parameters are optimized using cross-validation during the training process to obtain the pre-trained anomaly detection model. After the model completes training, the pre-trained anomaly recognition model is dynamically updated through an online learning mechanism, and incremental training is performed in conjunction with real-time detection data to adapt to new equipment models and changes in operating conditions.
6. The method for detecting gas combustion appliances according to claim 1, characterized in that, The process involves fusing and analyzing the detection results of the gas combustion appliance after the test, based on a pre-trained anomaly recognition model, to generate a corresponding diagnostic report. This includes: The test results of the gas combustion appliance under test are input into the pre-trained anomaly recognition model for fusion analysis, and anomaly classification labels are output. Based on the anomaly classification labels, cause analysis is performed to obtain anomaly cause analysis results, and operation suggestions are generated based on the anomaly cause analysis results; A diagnostic report is generated based on the anomaly classification labels, the anomaly cause analysis results, and the operation suggestions.
7. The method for testing gas combustion appliances according to claim 1, characterized in that, The method for detecting gas combustion appliances also includes: During the detection process, external environmental parameters are monitored in real time, and when the external environmental parameters change, an environmental change log is automatically recorded and generated. Adjust the standard test parameters in the testing process template according to the environmental change log to ensure the accuracy and adaptability of the test results.
8. A gas combustion appliance detection device, characterized in that, The gas combustion appliance detection device includes: The device identification module is used to identify the device model of the gas combustion appliance to be tested, and load the corresponding detection process template according to the device model. The detection process template includes standard test parameters, module scheduling order and warning threshold. The parameter distribution module is used to distribute the standard test parameters in the test process template to the test modules, which include an airtightness test module, a combustion analysis module, and an electrical safety test module. The test scheduling module is used to schedule the corresponding test modules to test the gas combustion appliance according to the module scheduling order in the test process template, and determine the subsequent test mode based on the test results of the gas combustion appliance under test. The anomaly analysis module is used to perform a fusion analysis on the detection results of the gas combustion appliance after the detection is completed, based on a pre-trained anomaly recognition model, and generate a corresponding diagnostic report.