An automated control method and system for a burner production line

Abstract

The application discloses an automatic control method and system for a burner production line, and relates to the technical field of production line control.The method comprises the following steps: acquiring function characteristic information and an identity of a burner part; identifying potential function abnormalities according to the function characteristic information; establishing a production process record according to the identity, the potential function abnormalities and workstation operation data; identifying a product performance fluctuation root cause according to the production process record; determining a production process parameter adjustment range according to the product performance fluctuation root cause, the function characteristic information and a production line running state; and adjusting a target production process parameter according to the production process parameter adjustment range.The application can adjust the production process parameter in combination with the potential function abnormalities and the product performance fluctuation root cause, so that the production line control is realized, and the accuracy and product quality are improved.

Description

Technical Field

[0001] This invention relates to the field of production line control technology, and in particular to an automated control method and system for a burner production line. Background Technology

[0002] In modern industrial production, for complex products like burners, the core of automated production lines lies in improving efficiency and quality consistency. Existing systems coordinate various workstations through a central control unit, executing steps such as component preparation, assembly, welding, and quality inspection for production line control. Each burner undergoes an ignition test, with an industrial camera capturing flame images and analyzing their shape, color, and stability to determine pass / fail status. However, actual production environments are complex and variable. For example, a change in raw materials from an upstream nozzle supplier can cause subtle differences in the internal flow channels of the nozzles, which are difficult to detect with conventional inspection tools. These nozzles are still used in production, and once inside the burner, the changes in their flow channels affect the mixing of gas and air, causing intermittent slight flame vibrations, resulting in blurred flame image analysis results and fluctuations in the pass rate. Faced with anomalies, existing systems perform self-diagnosis according to preset logic, potentially misjudging the problem as an assembly issue (such as a loose nozzle) and instructing the robotic arm to increase tightening force. However, the root cause is actually the physical characteristics of the nozzle, not the assembly process. Increasing force not only fails to stabilize the flame but may also damage the nozzle threads, affecting alignment with the housing, ultimately exacerbating production fluctuations, reducing control accuracy, and impacting product quality.

[0003] In summary, the technical problems existing in the relevant technologies need to be improved. Summary of the Invention

[0004] The main objective of this invention is to propose an automated control method and system for burner production lines, which can adjust production process parameters based on potential functional abnormalities and the root causes of product performance fluctuations to achieve production line control, thereby improving accuracy and product quality.

[0005] On one hand, embodiments of the present invention provide an automated control method for a burner production line, comprising the following steps: Obtain functional characteristic information and identification of burner components; Based on the aforementioned functional characteristic information, potential functional abnormalities can be identified; Based on the identity identifier, the potential functional abnormalities, and the workstation operation data, establish a production process record; Based on the production process records, identify the root causes of product performance fluctuations; Based on the root cause of the product performance fluctuation, the functional feature information, and the production line operating status, determine the adjustment range of the production process parameters; The target production process parameters are adjusted according to the adjustment range of the production process parameters.

[0006] On the other hand, embodiments of the present invention provide an automated control system for a burner production line, comprising: The information acquisition module is used to acquire functional characteristic information and identification information of burner components; A functional anomaly identification module is used to identify potential functional anomalies based on the functional feature information. The production process record creation module is used to create production process records based on the identity identifier, the potential functional abnormalities, and workstation operation data. The fluctuation source identification module is used to identify the root causes of product performance fluctuations based on the production process records. The adjustment range determination module is used to determine the adjustment range of production process parameters based on the root cause of the product performance fluctuation, the functional feature information, and the production line operating status. The parameter adjustment module is used to adjust the target production process parameters according to the production process parameter adjustment range.

[0007] The embodiments of this application include at least the following beneficial effects: First, the functional characteristic information and identification of burner components are obtained. Based on the functional characteristic information, potential functional abnormalities are identified. Then, based on the identification, potential functional abnormalities, and workstation operation data, a production process record is established. Based on the production process record, the root cause of product performance fluctuations is identified. Then, based on the root cause of product performance fluctuations, functional characteristic information, and production line operating status, the adjustment range of production process parameters is determined. Finally, based on the adjustment range of production process parameters, the target production process parameters are adjusted. This allows for the adjustment of production process parameters by combining potential functional abnormalities and the root cause of product performance fluctuations, thereby achieving production line control and improving accuracy and product quality.

[0008] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the description and the drawings. Attached Figure Description

[0009] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below.

[0010] Figure 1 This is a flowchart illustrating an automated control method for a burner production line according to an embodiment of the present invention; Figure 2 This is a schematic diagram of an automated control system for a burner production line according to an embodiment of the present invention. Detailed Implementation

[0011] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments.

[0012] In related technologies, achieving high efficiency and consistent product quality in automated production lines is crucial in modern industrial production, especially for products like burners that have stringent requirements for internal structure and function. Existing systems coordinate various workstations, from component preparation, assembly, and welding to final quality inspection. In the final step of production, each assembled burner undergoes an ignition test. Industrial cameras capture images of the flame, and analysis of its shape, color, and stability determines product quality. Data throughout the entire production process is collected in real-time and monitored and managed by a central control unit, aiming to achieve unmanned, efficient, and stable production.

[0013] However, the actual production environment is complex and variable. For example, in a continuous production run, the production line initially runs smoothly with a high product qualification rate. But later, the upstream nozzle supplier changed a batch of raw materials, resulting in a very subtle shape difference in the internal flow channels of the newly produced nozzles. This difference is so small that conventional inspection tools cannot detect it, and this batch of nozzles was used as qualified products. When these burners equipped with the new batch of nozzles entered the quality inspection station, the slight difference in the internal flow channels of the nozzles affected the mixing effect of the gas and air, causing the flame to exhibit a barely perceptible, intermittent, slight flickering after ignition. The analysis results of the flame image also became blurred, causing the overall qualification rate of the production line to decrease.

[0014] Faced with this anomaly, the existing system would diagnose and adjust according to preset logic, potentially mistakenly attributing the flame instability to a problem in the assembly process, such as a loose nozzle. The system would then instruct the robotic arm at the assembly station to increase the tightening force of the nozzles by 5%, hoping to solve the problem through a tighter connection. However, the root cause actually lies in the physical characteristics of the nozzle itself, not the assembly process. Increasing the tightening force not only failed to stabilize the flame but also caused minor damage to some nozzle threads due to excessive force, even affecting the alignment of the nozzle and the housing.

[0015] When these burners, after undergoing "error-optimization," returned to the testing station, some, due to damage to the nozzle threads, exhibited more severe flame fluctuations and were explicitly deemed unqualified by the system. Others, perhaps due to accidental changes in stress, showed a temporary improvement in flame performance. The data collected by the testing system became more chaotic, and the pass rate fluctuated more drastically. The system, faced with this complex data, made further erroneous judgments, potentially readjusting assembly force or adjusting welding station parameters such as current and time, believing that heat deformation during welding affected assembly accuracy. This created a vicious cycle on the production line: product quality issues were incorrectly attributed to upstream manufacturing processes. The control system continuously made inappropriate adjustments to previously correct process parameters, which not only failed to solve the initial problem but also introduced new, real process deviations, ultimately causing the entire production line to descend from stability into chaos, and product quality to continuously decline.

[0016] On an automated burner production line, when the quality inspection system detects critical fluctuations in product performance (such as flame stability), and these fluctuations may be caused by implicit batch differences in upstream components (such as nozzles) or subtle drifts in manufacturing process parameters such as assembly and welding, it is necessary to accurately identify and distinguish these complex and interactive root causes of the problem. This is to avoid making inappropriate adjustments to process parameters based on incorrect attributions, prevent the production process from falling into a chain reaction of instability, and ensure the continuous stability of product quality.

[0017] The embodiments of this application will be explained in detail below with reference to the accompanying drawings: Figure 1 This is an optional flowchart of an automated control method for a burner production line provided in an embodiment of this application. Figure 1 The method may include, but is not limited to, steps S101 to S106.

[0018] Step S101: Obtain the functional characteristic information and identification of burner components; Step S102: Identify potential functional abnormalities based on functional characteristic information; Step S103: Establish production process records based on identification, potential functional abnormalities, and workstation operation data; Step S104: Identify the root causes of product performance fluctuations based on production process records; Step S105: Determine the adjustment range of production process parameters based on the root cause of product performance fluctuations, functional characteristic information, and production line operating status; Step S106: Adjust the target production process parameters according to the adjustment range of the production process parameters.

[0019] Steps S101 to S106 as shown in the embodiments of this application can adjust the production process parameters in combination with the root causes of potential functional abnormalities and product performance fluctuations, so as to achieve production line control and improve accuracy and product quality.

[0020] In some embodiments, steps S101-S106 can first acquire the functional characteristic information and identification of burner components. Each component's batch number, supplier information, design parameters, etc., can be manually entered and recorded as identification. Simultaneously, conventional physical measuring tools, such as calipers and micrometers, can be used to measure the critical dimensions of the components, and the measurement results can be recorded as part of the functional characteristic information. Furthermore, visual inspection can be conducted by operators to check the appearance of the components and record any visible scratches, deformations, or other defects as preliminary functional characteristic information. It is understood that the functional characteristic information of burner components refers to the physical, chemical, or operational characteristics exhibited by each component of the burner (such as nozzles, mixing tubes, ignition electrodes, etc.) under operating conditions, such as the material's microstructure, surface roughness, internal flow channel geometry, coefficient of thermal expansion, thermal conductivity, and response characteristics under specific excitations. This information is the basis for evaluating component quality and potential defects. Identification refers to a unique identifier assigned to each burner component, such as a QR code, RFID tag, or serial number. By using identification tags, the entire lifecycle data of each component can be tracked from warehousing to final product assembly, achieving traceability of the production process.

[0021] Then, based on functional characteristic information, potential functional anomalies are identified. A threshold range can be set; if the dimensional measurement value of a component exceeds a preset tolerance range, it is marked as a potential functional anomaly. Alternatively, if visual inspection reveals obvious physical defects in a component, it can also be directly identified as a potential functional anomaly. These threshold ranges and rules can be set based on historical experience or design specifications. It is understood that potential functional anomalies refer to deviations in the functional characteristics of components that may lead to decreased product performance or failure. These anomalies may be very minor and difficult to detect through conventional inspection methods, but they may cause significant product performance problems under specific operating conditions.

[0022] Next, based on component identification, potential functional abnormalities, and workstation operation data, a production process record is established. This can be done by creating a spreadsheet or database, using the identification of each component as a unique key, and entering the corresponding functional characteristics, potential functional abnormality markers, and operation data (such as operator ID, operation time, and tool model used) for each workstation (e.g., assembly, welding). This data can be manually entered by operators or recorded by sensors (such as timers and counters). Workstation operation data refers to the operation records generated at each workstation on the production line during the production process, such as the torque value of the assembly robot arm, the current and voltage curves of the welding station, gas supply pressure, ambient temperature, and humidity. This data reflects the actual operation during the production process and is an important basis for analyzing the root causes of product performance fluctuations.

[0023] Identify the root causes of product performance fluctuations by analyzing production process records. For example, production records can be manually reviewed to check if any batches of components are frequently marked as having potential functional abnormalities, and if the final assembled products from these components fail quality inspections. In this way, it can be preliminarily inferred that potential functional abnormalities in components may be a root cause of product performance fluctuations.

[0024] Based on the root cause of product performance fluctuations, functional characteristic information, and production line operating status, determine the adjustment range of production process parameters. Empirical judgments can be made based on the identified root cause. For example, if the initial assessment is that the root cause of product performance fluctuations is the dimensional deviation of nozzles in a certain batch, and the functional characteristic information of that batch of nozzles indicates that their size is too small, then based on experience, the adjustment range of assembly force parameters related to nozzle size can be appropriately increased. The production line operating status can be displayed through simple indicator lights or an operation panel, such as showing whether the production line is currently operating normally, stopped, or in a fault state. This information can serve as a reference for determining the adjustment range.

[0025] Finally, the target production process parameters are adjusted according to the adjustment range of the production process parameters. Parameter adjustments can be made through the control system. For example, if it is determined that increased assembly force is needed, the system can adjust the parameter settings of the assembly robot arm to apply greater force. After adjustment, the performance of subsequently produced products can be observed to verify the adjustment effect.

[0026] Through the above technical solution, this embodiment systematically acquires the functional characteristic information and identification of burner components, and combines this with workstation operation data during the production process to establish a comprehensive production process record. Analysis of these records can identify potential functional anomalies and root causes of product performance fluctuations that are difficult to detect using traditional methods. For example, when a change in raw materials by an upstream nozzle supplier leads to minor differences in the internal flow channel of the nozzle, this embodiment can identify these minor potential functional anomalies by acquiring the functional characteristic information of the components (such as transient excitation sensitivity characteristics). This information is then combined with identification and workstation operation data to establish a detailed production process record. When the final product exhibits performance fluctuations such as flame flickering during quality inspection, this embodiment can trace back to the specific component batch and production workstation operation data. In-depth analysis of the production process records can identify the true root cause of product performance fluctuations, such as internal flow channel defects in a specific batch of nozzles, rather than insufficient assembly force. Then, based on this root cause, the functional characteristic information of the components, and the production line operating status, a precise range for adjusting production process parameters can be determined. For example, if the root cause is a defect in the nozzle's internal flow channel, the system will not incorrectly adjust the assembly force. Instead, it may suggest adjusting the gas supply pressure, mixing ratio, or even changing the supplier. This precise determination of the adjustment range avoids the problem of traditional control systems blindly adjusting parameters, leading to a vicious cycle in the production line. Ultimately, the system adjusts the target production process parameters according to the determined adjustment range. This parameter adjustment is based on a deep understanding of the root cause of the problem, thus more effectively solving product performance fluctuations and improving product quality and production efficiency.

[0027] In some embodiments, obtaining the functional characteristic information of the burner components in step S101 may include, but is not limited to, the following steps: Apply transient excitations simulating complex actual operating conditions to burner components; When a transient excitation is applied, transient response signals of the burner components are collected. These transient response signals include acoustic signals, non-visible light signals, or visible light spectral characteristics. Feature extraction is performed on the transient response signal to obtain transient excitation sensitivity features; The transient excitation sensitivity features are matched with the component feature library to identify functional feature information.

[0028] In some embodiments, transient excitation simulating actual complex operating conditions can be applied to the burner components. Short-duration, high-intensity energy input can be applied to the burner components using specific excitation devices, such as pulse generators, vibration tables, or thermal shock equipment. These transient excitations are designed to simulate extreme or rapidly changing operating conditions that the burner may encounter during actual operation, such as ignition shocks, flameout vibrations, sudden changes in gas pressure, or instantaneous increases / decreases in temperature. The aim is to stimulate potential defects or weaknesses within the components, making them manifest in the dynamic response, defects that may be difficult to detect through static inspection.

[0029] When transient excitation is applied, transient response signals of burner components are acquired. These transient response signals refer to the changes in the physical state or energy field of burner components within a short period after being subjected to transient excitation. Specifically, these signals can include: acoustic signals, such as sound waves generated by components under excited vibration or internal structural changes, acquired through a high-sensitivity microphone array; non-visible light signals, such as changes in non-visible light radiation caused by transient surface temperature distribution or internal structural defects in components, acquired through infrared thermal imagers or terahertz imaging devices; or visible light spectral characteristics, such as visible light spectral characteristics caused by stimulated light or microscopic changes on the material surface, acquired through a spectral analyzer. The acquisition of these signals aims to comprehensively capture the subtle changes in components under dynamic stress, providing a rich data foundation for subsequent defect identification.

[0030] Next, feature extraction is performed on the transient response signal to obtain transient excitation sensitivity characteristics. Signal processing and data analysis techniques can be used to identify and quantify key parameters closely related to the functional state and potential defects of components from the original transient response signal. For example, Fourier transform can be performed on acoustic signals to obtain frequency domain features, texture analysis can be performed on non-visible light signals to identify abnormal regions, or principal component analysis can be performed on visible light spectral features to extract key wavelength information. Transient excitation sensitivity characteristics refer to the degree and pattern of a component's response to a specific transient excitation. These characteristics can reflect the component's material uniformity, structural integrity, assembly quality, and the presence of potential problems such as microcracks, stress concentration, or material fatigue.

[0031] Finally, the transient excitation sensitivity features are matched with the component feature library to identify functional characteristic information. The component feature library is a pre-established database that stores a large number of known qualified or defective burner components' transient excitation sensitivity features and their corresponding functional characteristic information under the same transient excitation. By comparing and performing pattern recognition with the currently acquired and extracted transient excitation sensitivity features in the library, the functional status of the current burner component can be quickly and accurately determined. For example, if the matching result shows that the features of the current component are highly similar to the features of components known to have microcracks in the library, then the functional characteristic information of "potential structural integrity anomaly" in that component can be identified.

[0032] This embodiment applies transient excitation simulating complex actual operating conditions to burner components and collects their transient response signals. This allows for the capture of subtle changes in components under dynamic stress, changes that are often difficult to detect with static inspection. By extracting features from these transient response signals, transient excitation sensitivity features reflecting the true physical state and potential defects of the components can be obtained. Subsequently, these sensitivity features are matched with a pre-established component feature library to identify the functional characteristics of the components, including potential functional anomalies. This method enables a more comprehensive and in-depth assessment of component quality and reliability, overcoming the limitations of static inspection methods in detecting dynamic defects.

[0033] Through the above technical solution, this embodiment enables precise and dynamic acquisition of functional characteristic information of burner components. This embodiment can identify potential functional anomalies and structural defects in components under simulated complex operating conditions earlier and more accurately, such as microcracks, material fatigue, or assembly stress, which may be overlooked in conventional testing. Therefore, it can significantly improve the sensitivity and accuracy of component quality inspection, providing a more reliable and comprehensive data foundation for subsequent production process control and identification of the root causes of product performance fluctuations, thereby effectively improving the overall quality and reliability of burner products.

[0034] In some embodiments, step S104, identifying the root cause of product performance fluctuations based on production process records, may include, but is not limited to, the following steps: Identify potentially abnormal production process parameters based on production process records; Adjust the production process parameters for potential abnormalities based on the workstation operation data; After adjusting potentially abnormal production process parameters, obtain product status data; Based on the correlation between status and performance and product status data, assess the trend of product performance changes; Identify the root causes of product performance fluctuations based on product performance change trends.

[0035] In some embodiments, potentially abnormal production process parameters can be identified first based on production process records. In-depth analysis of the production process records, such as using statistical methods, data mining techniques, or machine learning algorithms, can detect process parameters that deviate significantly from the normal production process or preset benchmarks. These parameters may include, but are not limited to, temperature, pressure, flow rate, welding current, assembly torque, and gas supply pressure during burner production; abnormal fluctuations in these parameters may directly or indirectly lead to instability in burner product performance.

[0036] Then, based on the workstation operation data, adjustments are made to potentially abnormal production process parameters. After identifying potential abnormal parameters, these parameters can be fine-tuned or corrected in a targeted manner by combining the workstation operation data. The workstation operation data provides real-time intervention information on process parameters by operators or automated equipment in the actual production environment, which helps to understand the context of parameter anomalies and guides subsequent adjustment operations to verify or eliminate the possibility that they are the source of fluctuations.

[0037] After adjusting potentially abnormal production process parameters, product status data is acquired. Following adjustments to these parameters, real-time or delayed acquisition of various status data for the burner product is necessary. This data reflects whether the product's physical, chemical, or functional characteristics have changed during the adjusted process, such as combustion efficiency, emission composition, flame stability, and vibration frequency.

[0038] Then, based on the correlation between state and performance and product state data, the trend of product performance changes is assessed. A pre-established mapping model between product state and final performance, or an expert knowledge base, can be used, combined with adjusted product state data, to predict or evaluate the direction of product performance. This correlation can be a predictive model trained on historical data, or a simulation model based on physical principles, used to quantify the potential impact of process parameter adjustments on product performance.

[0039] Finally, based on the product performance change trend, the root cause of product performance fluctuations can be identified. By analyzing the product performance change trend, the specific cause of the performance fluctuation can be traced back. If adjusting a potentially abnormal process parameter improves the product performance trend or restores it to normal, then that parameter is likely one of the root causes of the fluctuation; otherwise, it is necessary to further investigate other potential abnormal parameters or factors.

[0040] This embodiment first identifies potential abnormal production process parameters that may cause fluctuations in product performance through detailed analysis of production process records. Then, by combining actual workstation operation data, these potential abnormal parameters are adjusted to simulate or verify their impact on product performance. After adjustment, by acquiring product status data and combining it with preset status-performance correlations, the trend of product performance changes can be evaluated. This iterative process of identification, adjustment, and evaluation allows the system to gradually focus on and ultimately identify the specific root causes of product performance fluctuations, thus providing a precise basis for subsequent process optimization.

[0041] Through the above technical solution, this embodiment can accurately identify the root causes of product performance fluctuations. This embodiment forms a closed-loop verification mechanism by introducing adjustments to potentially abnormal production process parameters and the acquisition and evaluation of adjusted product status data. This not only improves the accuracy of root cause identification and avoids misjudgments, but also more effectively locates the specific process steps or parameters causing performance fluctuations, providing more refined and reliable decision support for the automated control of the burner production line, thereby improving product quality stability and production efficiency.

[0042] In some embodiments, step S104, identifying the root cause of product performance fluctuations based on production process records, may include, but is not limited to, the following steps: Step S201: Obtain production line station information, environmental context data, and combustion behavior characteristics. Environmental context data includes assembly robot arm torque value, current and voltage curves of welding stations, gas supply pressure, ambient temperature, and ambient humidity. Step S202: Construct a digital image of the burner based on production line station information, environmental context data, and combustion behavior characteristics; Step S203: Identify potential abnormal production process parameters based on the production process records; Step S204: In the digital mirror of the burner, perform scenario simulation on potential abnormal production process parameters to obtain product performance data, which includes flame stability index, flame spectral characteristics and vibration frequency data. Step S205: Identify the root causes of product performance fluctuations based on product performance data and actual observation data.

[0043] In some embodiments, relying solely on historical data analysis may not fully capture the rapidly changing workstation states, environmental conditions, and real-time behavior of the burner itself during production. This limitation can lead to insufficient accuracy and efficiency in identifying the root causes of complex, multi-factor-driven product performance fluctuations, and may even prevent the timely detection of potential performance problems caused by minor process deviations or environmental disturbances. Failure to address these issues may result in haphazard adjustments to production process parameters, failing to fundamentally resolve product performance fluctuations and impacting product quality and production efficiency.

[0044] To this end, we can first acquire production line station information, environmental context data, and combustion behavior characteristics. Production line station information refers to detailed status data of each workstation during the burner production process, such as the specific operating steps at the assembly station and the test results at the testing station. Its purpose is to provide contextual information about the product at different production stages. Environmental context data refers to external environmental factors affecting burner production and performance, specifically including the torque value of the assembly robotic arm, the current and voltage curves at the welding station, gas supply pressure, ambient temperature, and ambient humidity. This data reflects subtle changes and external disturbances during the production process, aiming to capture environmental factors that may cause performance fluctuations. Combustion behavior characteristics refer to the burner's combustion performance under specific operating conditions, such as flame color, shape, and noise. These characteristics can be acquired in real time through sensors or obtained through visual analysis, aiming to directly reflect the burner's operating status and performance.

[0045] Then, based on production line station information, environmental context data, and combustion behavior characteristics, a digital image of the burner is constructed. A virtual model highly consistent with the physical entity can be established in digital space based on the physical burner's geometry, material properties, fluid dynamics model, and thermodynamic model. This digital image can receive and process various data in real time from production line station information, environmental context data, and combustion behavior characteristics, and can simulate the burner's operating status and performance under different operating conditions. Its purpose is to provide a platform for virtual testing and analysis.

[0046] Based on production process records, potential abnormal production process parameters are identified. These parameters are then simulated in a digital mirror of the burner to obtain product performance data. This product performance data refers to key indicators reflecting burner performance obtained through digital mirror simulation, including flame stability index, flame spectral characteristics, and flicker frequency data. This data comprehensively assesses the burner's combustion efficiency, emission characteristics, and operational stability. Specific production process parameters (such as minor deviations in the gas nozzle or geometric deformation of the mixing chamber) are adjusted in the digital mirror, and the impact of these parameter changes on burner performance is simulated. This simulation allows for prediction of potential product performance data under specific abnormal parameters, such as flame stability index, flame spectral characteristics, and flicker frequency data, aiming to quantify the specific impact of abnormal parameters on product performance.

[0047] Finally, based on product performance data and actual observation data, the root causes of product performance fluctuations are identified. Actual observation data refers to performance data collected from burner products on the actual production line, such as flame stability, spectrum, and vibration frequency data obtained through online sensors or laboratory tests. The purpose is to compare these data with the simulation results of the digital mirror to verify the accuracy of the simulation and identify actual performance fluctuations.

[0048] To illustrate this technical solution more clearly, a specific example is used below. Suppose a batch of burner products exhibits a low flame stability index during factory testing. To identify the root cause, the system first acquires production line station information for this batch of products during the production process, such as torque records of specific assembly robotic arms and current and voltage curves of welding stations. Simultaneously, environmental data during production is collected, including workshop ambient temperature, humidity, and gas supply pressure. Furthermore, the system acquires combustion behavior characteristics of this batch of burners during initial ignition testing, such as flame flicker frequency data. Based on this multi-source data, the system constructs a digital mirror image corresponding to this batch of burners. By analyzing the production process records, a potentially abnormal production process parameter is identified, such as the micro-geometric deformation of the gas nozzle potentially exceeding tolerance limits. Subsequently, in the burner digital mirror image, this micro-geometric deformation is simulated to simulate its impact on the gas-air mixing efficiency under actual operating conditions, thereby obtaining a series of product performance data, including simulated flame stability index, flame spectral characteristics, and flicker frequency data. Finally, the simulated product performance data is compared with actual observation data, such as a low flame stability index observed in real-world testing. If the simulation results closely match the actual observation data, it can be confirmed that the microscopic geometric deformation of the gas nozzle is the root cause of the low flame stability index. In this way, the specific root cause of product performance fluctuations can be identified efficiently and accurately without the need for actual production line adjustments or extensive physical testing.

[0049] Through the above technical solution, this embodiment enables a more accurate and comprehensive identification of the root causes of burner product performance fluctuations. By constructing a digital mirror of the burner and combining it with production line station information, environmental context data, and combustion behavior characteristics, virtual scenario simulations can be performed on potentially abnormal production process parameters. This allows for prediction of their impact on product performance without interfering with actual production. This method significantly improves the efficiency and accuracy of root cause identification, avoiding production losses that may result from trial and error. Furthermore, by comparing simulated data with actual observation data, the effectiveness of the simulation can be verified, and the root cause localization can be further refined. This provides a more reliable basis for subsequent adjustments to production process parameters, thereby effectively improving the quality stability of burner products and the level of automation control on the production line.

[0050] In some embodiments, step S204 involves scenario simulation of potentially abnormal production process parameters to obtain product performance data, which may include, but is not limited to, the following steps: Obtain the first sensitivity parameter of the burner components to transient thermal stress response in digital mapping; Based on potential abnormal production process parameters and primary sensitivity parameters, adjust the micro-geometric deformation and material stress distribution of the gas outlet region in the digital image of the burner; The first mixing efficiency of gas and air is calculated based on microscopic geometric deformation and material stress distribution. Based on the first mixing efficiency, product performance is evaluated to obtain product performance data.

[0051] In some embodiments, simulations based solely on macroscopic parameters may fail to adequately capture physical changes at the microscopic level, particularly the fine structure and stress distribution changes related to the thermal stress response of materials. This could lead to discrepancies between simulation results and actual product performance, thereby affecting the accuracy of identifying the root causes of product performance fluctuations.

[0052] To this end, a primary sensitivity parameter for the burner components' response to transient thermal stress in digital mapping can be obtained first. This parameter can be quantified using pre-established physical models, finite element analysis, or experimental data, to assess the sensitivity of burner components to transient thermal stresses (e.g., rapid temperature changes during ignition, flameout, or sudden changes in operating conditions), affecting their geometry, material properties, and internal stress states. This primary sensitivity parameter is a coefficient or function characterizing the material and structure's response to thermal shock, aiming to provide a precise physical basis for subsequent digital mapping adjustments.

[0053] Then, based on potential abnormal production process parameters and the primary sensitivity parameters, the microscopic geometric deformation and material stress distribution of the gas outlet region in the burner digital mirror are adjusted. Identified potential abnormal production process parameters (e.g., abnormal welding parameters leading to localized deformation, improper material heat treatment causing stress concentration, etc.) can be combined with the primary sensitivity parameters of burner components' response to transient thermal stress. This allows for precise simulation in the burner digital mirror of the effects of these abnormal parameters on the microscopic geometry (e.g., aperture, surface roughness, localized warpage, etc.) of the gas outlet region (e.g., nozzles, mixing chambers, etc.) and the internal stress distribution of the material (e.g., residual stress, thermal stress, etc.). The aim is to reproduce the physical defects that real production anomalies might cause in a virtual environment.

[0054] Then, based on the microscopic geometric deformation and material stress distribution, the first mixing efficiency of the gas and air is calculated. Using a computational fluid dynamics (CFD) model based on the adjusted microscopic geometric deformation and material stress distribution in a digital mirror, the mixing process of gas and air inside the burner can be simulated, and the mixing efficiency at this point can be calculated. The first mixing efficiency refers to the degree to which the gas and air achieve uniform mixing before entering the combustion zone, and is a key indicator affecting combustion stability and efficiency. Its purpose is to quantify the direct impact of physical defects on combustion performance.

[0055] Finally, based on the first mixing efficiency, product performance is evaluated to obtain product performance data. The calculated first mixing efficiency can be used as the core input, combined with other relevant digital mirror parameters, to evaluate the overall product performance of the burner. Product performance data may include flame stability index, flame spectral characteristics, and flicker frequency data, which can intuitively reflect the burner's operating status and performance. The aim is to predict and output product performance data affected by abnormal process parameters by quantifying changes in mixing efficiency.

[0056] To illustrate this technical solution more clearly, a specific example is used below. Suppose that on a burner production line, a slight deviation in the welding process parameters of a batch of burner components leads to micron-level localized deformation and residual stress at the nozzle edge in the gas outlet area. To identify the impact of this anomaly on product performance, the system first acquires the first sensitivity parameter of the transient thermal stress response of this type of burner component in a digital mapping. This parameter may be obtained through thermal shock experiments and finite element analysis on samples of the same batch or similar materials, for example, determining the changes in the material's coefficient of thermal expansion and yield strength under a specific temperature gradient. Next, this welding process deviation is used as a potential abnormal production process parameter. Combined with the first sensitivity parameter, the system accurately simulates the microscopic geometric deformation (e.g., from an ideal circle to a slight ellipse or localized bulge) and material stress distribution (e.g., localized stress concentration areas) of the nozzle edge in the burner digital mirror.

[0057] Subsequently, based on the updated microscopic geometric deformation and material stress distribution in the digital mirror, computational fluid dynamics (CFD) software (such as ANSYS Fluent or OpenFOAM) is used to simulate the flow and mixing process of gas and air inside the nozzle and in the outlet region, calculating the initial mixing efficiency of gas and air at this point. For example, it was found that due to nozzle deformation, the diffusion angle of the gas jet changed, leading to uneven mixing with air, and the initial mixing efficiency dropped from 95% to 90%. Finally, based on the calculated initial mixing efficiency (90%), combined with other parameters in the burner digital mirror, product performance was evaluated. The evaluation results might show a 5% decrease in the flame stability index, changes in the intensity of certain specific wavelengths in the flame spectral characteristics, and the appearance of new low-frequency components in the dithering frequency data. These product performance data are then used to compare with actual observation data to identify welding process deviations as the root cause of product performance fluctuations. In this way, even minor process anomalies can be accurately simulated and evaluated for their impact on the final product performance.

[0058] Through the above technical solution, this embodiment overcomes the limitation of scenario simulation in that it may not adequately consider microscopic physical details. By obtaining the first sensitivity parameter of the burner components to transient thermal stress response, and adjusting the microscopic geometric deformation and material stress distribution in the digital image accordingly, the scenario simulation of potentially abnormal production process parameters becomes more refined and physical. Therefore, the calculated first mixing efficiency of gas and air can more accurately reflect actual combustion performance, making product performance evaluation results closer to reality. This provides more reliable data support for identifying the root causes of product performance fluctuations and significantly improves the accuracy and effectiveness of automated control methods.

[0059] In some embodiments, step S204 involves scenario simulation of potentially abnormal production process parameters to obtain product performance data, which may include, but is not limited to, the following steps: Obtain the associated production process parameters that are linked to potentially abnormal production process parameters; Identify the physical correlation between potentially abnormal production process parameters and related production process parameters; Based on physical correlations, construct a parameter linkage adjustment strategy; Based on the parameter linkage adjustment strategy, potentially abnormal production process parameters and related production process parameters are adjusted in a coordinated virtual manner. Assess the comprehensive impact of collaborative virtual adjustments on the microstructure and hydrodynamic characteristics of burner components; Calculate the second mixing efficiency of gas and air based on the overall impact. Based on the second mixing efficiency, product performance is evaluated to obtain product performance data.

[0060] In some embodiments, due to the complex physical relationships between different production process parameters, adjusting a single parameter may trigger changes in other related parameters, thereby having a comprehensive impact on the microstructure and hydrodynamic characteristics of burner components. If only a single potentially abnormal production process parameter is simulated in isolation, it may not be able to fully and accurately reflect its true impact on product performance, resulting in an inaccurate identification of the root cause of product performance fluctuations.

[0061] To address this, we can first obtain the associated production process parameters that are relevant to the potential abnormal production process parameters. These parameters can be obtained through historical production data analysis, expert experience, or causal relationship deduction based on physical models. For example, when the potential abnormal production process parameter is the gas supply pressure, its associated parameters might include the geometry of the gas nozzle (such as orifice wear), the air premixing ratio, or the temperature distribution in the combustion chamber. Simultaneously, we need to identify the physical correlation between the potential abnormal production process parameter and the associated production process parameters. This physical correlation can manifest as interactions in thermodynamics, fluid mechanics, materials mechanics, or chemical reaction kinetics. For instance, changes in the gas supply pressure directly affect the gas velocity and injection momentum, thereby altering the gas-air mixing process, while nozzle orifice wear changes the microscopic flow field structure at the gas outlet. These physical correlations can be quantified by establishing multiphysics coupled simulation models or empirical models based on experimental data fitting.

[0062] Then, based on physical correlations, a parameter linkage adjustment strategy is constructed. This strategy defines how related production process parameters should coordinately change to maintain or alter a specific production state when potentially abnormal production process parameters change. For example, when the gas supply pressure drops, the linkage adjustment strategy might instruct the virtual wear level of the gas nozzle or airflow to be adjusted simultaneously in the virtual environment to simulate compensation or chain reactions that may occur in the actual production line. Based on the parameter linkage adjustment strategy, potentially abnormal production process parameters and related production process parameters are adjusted virtually in tandem. This means that in the burner digital mirror, these parameters do not change independently, but are adjusted synchronously or asynchronously according to a preset linkage relationship. For example, in the digital mirror, gas supply pressure, nozzle geometry, and airflow are adjusted simultaneously to simulate a complex changing scenario that more closely resembles real operating conditions.

[0063] Reassess the combined impact of collaborative virtual adjustments on the microstructure and hydrodynamic properties of burner components. This includes analyzing the flow field distribution, turbulence intensity, local temperature gradient, material stress distribution, and potential microstructural changes (such as thermal deformation and material fatigue) within the burner. These assessments can be performed using computational fluid dynamics (CFD) simulations, finite element analysis (FEA), or other multi-scale simulation methods.

[0064] Finally, based on the comprehensive influence, the second mixing efficiency of the gas and air is calculated. This second mixing efficiency comprehensively considers the changes in all linked parameters and their effects on microstructure and hydrodynamic characteristics, making it more accurate than the first mixing efficiency which only considers the influence of a single parameter. For example, the second mixing efficiency can be quantified by analyzing the uniformity of gas-air mixing in the combustion chamber and the equivalence ratio distribution in the reaction zone. Based on the second mixing efficiency, product performance is evaluated to obtain product performance data. This product performance data can include flame stability index, flame spectral characteristics, and flicker frequency data, which can more accurately reflect the actual performance of the burner under the influence of complex parameter linkages.

[0065] To illustrate this technical solution more clearly, a specific example is used below. Suppose that on a burner production line, a potential abnormal process parameter, "gas supply pressure fluctuation," is identified through production process records. First, related process parameters associated with the gas supply pressure can be obtained, such as "gas nozzle wear" and "air premixing valve opening." Through historical data and physical models, it is identified that a decrease in gas supply pressure may lead to accelerated nozzle wear, and simultaneously, to maintain combustion efficiency, the air premixing valve opening may be automatically or manually adjusted. Based on these physical correlations, a parameter linkage adjustment strategy is constructed. For example, when the gas supply pressure decreases by 5%, the virtual simulation shows an increase in nozzle wear of 0.1 mm, while the air premixing valve opening increases by 2%. In the burner's digital mirror, the gas supply pressure, nozzle geometry, and air premixing valve opening are adjusted collaboratively in a virtual manner. Subsequently, the combined impact of these collaborative changes on the internal flow field of the burner (such as turbulence intensity and local equivalence ratio) and material stress distribution is evaluated. For example, through CFD simulation analysis, it is found that the uniformity of gas-air mixing decreases significantly in a specific region, and a second mixing efficiency is calculated. Ultimately, based on this second mixing efficiency, product performance data such as a decrease in flame stability index, abnormal peaks in flame spectral characteristics, and an increase in vibration frequency were evaluated. This collaborative simulation allows for a more accurate identification of product performance fluctuations, showing that they are not only directly related to gas supply pressure but also closely linked to changes in nozzle wear and air premixing ratio, thus providing a more comprehensive insight for root cause analysis and process adjustments.

[0066] Through the above technical solution, this embodiment can significantly improve the accuracy and realism of scenario simulation in the burner digital mirror. By considering the complex interrelationships between production process parameters and their comprehensive impact on the internal characteristics of the burner, the obtained product performance data can more accurately reflect the actual fluctuations in product performance during production. This helps to more accurately identify the root causes of product performance fluctuations, avoid misjudgments due to incomplete information, and thus provide a more reliable basis for subsequent adjustments to production process parameters, improving the precision and effectiveness of automated control.

[0067] In some embodiments, step S204 involves scenario simulation of potentially abnormal production process parameters to obtain product performance data, which may include, but is not limited to, the following steps: Step S301: Obtain the material property degradation curves of the burner components; Step S302: Apply virtual loads under extreme operating conditions to the burner components; Step S303: Under virtual load, identify the material properties of the components based on the material property decay curve; Step S304: Calculate the stress distribution and deformation of the burner components based on the material properties of the components and potential abnormal production process parameters; Step S305: Based on the stress distribution and deformation of the burner components, conduct product performance evaluation to obtain product performance data.

[0068] In some embodiments, failure to adequately consider the material performance degradation of burner components under extreme operating conditions may lead to discrepancies between simulation results and the actual product's performance during long-term operation or in harsh environments, thereby affecting the accuracy of identifying the root causes of product performance fluctuations. If these issues are not addressed, the production line may fail to detect performance problems caused by material aging or fatigue in a timely manner, thus impacting product quality and service life.

[0069] To this end, the material property degradation curves of burner components can be obtained first. Through experimental testing, historical data analysis, or theoretical model prediction, the performance degradation law of a specific material under different environmental conditions (such as temperature, humidity, stress, corrosive media, etc.) and time can be obtained. This curve can characterize the changing trends of key mechanical or physical properties of the material, such as strength, toughness, hardness, and fatigue life, over time or under operating conditions. Its purpose is to provide an accurate material property benchmark for subsequent virtual load simulations.

[0070] Then, virtual loads under extreme operating conditions are applied to the burner components. In the digital mirror of the burner, mechanical loads, thermal loads, chemical loads, etc., under the most severe or critical conditions that the components might encounter in actual operation are simulated. For example, conditions such as high temperature and high pressure, severe vibration, corrosive gas erosion, or long-term continuous operation can be simulated. The purpose is to evaluate the performance of the components under extreme conditions and the potential failure risk.

[0071] Under virtual loads, the material properties of components are identified based on material property decay curves. By combining pre-acquired material property decay curves with the specific simulation time or conditions under which virtual loads are applied, the current material characteristics exhibited by burner components, such as their current elastic modulus, yield strength, and fatigue limit, can be determined. The aim is to ensure that the material parameters used in the simulation accurately reflect the actual performance of components under specific operating conditions and decay states.

[0072] Then, based on the material properties of the components and potential abnormal manufacturing process parameters, the stress distribution and deformation of the burner components are calculated. Finite element analysis (FEA) or other numerical simulation methods can be used, with the identified current material properties and potential abnormal manufacturing process parameters as input, to accurately calculate the internal stress field distribution and geometric deformation of the burner components under virtual loads. The purpose is to quantify the impact of abnormal process parameters on the structural integrity and geometric accuracy of the components.

[0073] Finally, based on the stress distribution and deformation of the burner components, product performance is evaluated to obtain product performance data. The calculated stress distribution and deformation results can be combined with preset product performance indicators (such as flame stability index, flame spectral characteristics, and vibration frequency data) to assess changes in the overall or local performance of the burner. For example, excessive deformation may alter the gas flow path, thus affecting combustion efficiency and stability; localized high stress may indicate the initiation of fatigue cracks. The aim is to map microscopic material and structural changes onto macroscopic product performance, thereby obtaining accurate product performance data.

[0074] To illustrate this technical solution more clearly, a specific example is used below. Suppose that after long-term high-temperature operation, the flame stability of a certain type of burner fluctuates. To identify the root cause of this fluctuation, scenario simulation can be performed. First, obtain the material property degradation curves of key burner components (e.g., flame tube, nozzle) under high-temperature, high-pressure gas scouring. These curves may show that the material's creep resistance or oxidation resistance decreases over time. Next, in a digital mirror of the burner, apply virtual loads simulating long-term high-temperature operation and gas scouring to these components under extreme conditions. Under the virtual load, based on the obtained material property degradation curves, identify the material properties of the components at the current simulation time point, such as their current elastic modulus and yield strength. Then, considering potential abnormal production process parameters (e.g., a batch of flame tubes welded at a lower temperature, resulting in localized grain coarsening), calculate the stress distribution and deformation of the components under the virtual load. For example, if it is found that the stress concentration in a certain area exceeds the yield limit of the currently decaying material, or that the deformation causes a significant change in the micro-geometry of the gas outlet, product performance can be evaluated accordingly. By analyzing the impact of these stress distributions and deformations on parameters such as gas-air mixing efficiency and flame propagation speed, product performance data such as flame stability index, flame spectral characteristics, and fluctuation frequency can be obtained. Finally, by comparing these simulated data with actually observed flame stability fluctuations, it can be identified that the fluctuations are caused by the combined effect of material performance degradation and abnormal process parameters in a specific batch of components.

[0075] Through the above technical solution, this embodiment can more comprehensively and accurately evaluate the performance of burner components under extreme operating conditions and long-term use. By introducing material performance degradation curves and virtual loads, this embodiment makes the scenario simulation results closer to reality, especially in predicting the long-term reliability and durability of products, demonstrating significant advantages. Therefore, it can more effectively identify the root causes of performance fluctuations caused by material fatigue, aging, or harsh environments, thus providing a more precise basis for adjusting production process parameters and significantly improving the quality stability, reliability, and service life of burner products.

[0076] In some embodiments, obtaining the material property degradation curve of the burner components in step S301 may include, but is not limited to, the following steps: Material composition analysis was performed on burner components to obtain material property characteristics; Determine the attenuation test parameters based on the material properties; Based on the attenuation test parameters, attenuation tests are conducted on the burner components to obtain the material performance attenuation curves.

[0077] In some embodiments, material composition analysis can be performed on burner components to obtain material characteristics. Physical or chemical methods, such as X-ray diffraction (XRD), scanning electron microscopy (SEM) combined with energy-dispersive X-ray spectroscopy (EDS), or Fourier transform infrared spectroscopy (FTIR), can be used to qualitatively or quantitatively analyze the constituent materials of burner components to identify their main chemical elements, crystal structure, phase composition, and microstructure, thereby obtaining material characteristics. These material characteristics form the basis for subsequently determining attenuation test parameters.

[0078] Then, based on the material's properties, the degradation test parameters are determined. A series of experimental conditions for evaluating material performance degradation can be set based on the identified material composition and microstructure, combined with materials science theory and engineering experience. For example, for high-temperature alloys, degradation test parameters might include specific temperature cycling ranges, applied stress levels, fatigue cycle counts, or corrosive media types. The determination of these parameters aims to simulate the various harsh operating conditions that burners may experience in actual operation, thereby accelerating the material performance degradation process.

[0079] Next, based on the attenuation test parameters, attenuation tests are conducted on the burner components to obtain material performance attenuation curves. Under preset test conditions, such as high temperature, high pressure, corrosive environments, or cyclic loading, the burner components undergo long-term or high-intensity operational simulations, and their key performance indicators, such as strength, hardness, toughness, fatigue life, or oxidation resistance, are periodically measured during this process. By recording the changes in these performance indicators over time or the number of cycles, material performance attenuation curves can be plotted. These curves intuitively reflect the performance degradation law of the material under specific operating conditions, providing data support for subsequent identification of component material properties.

[0080] This embodiment analyzes the material composition of burner components to accurately obtain their inherent material properties, providing a scientific basis for subsequent degradation testing. Based on these material properties, degradation test parameters can be specifically determined to ensure that the degradation test accurately reflects the performance degradation process of burner components under actual complex operating conditions. By conducting degradation tests under these parameters, a material performance degradation curve can be systematically obtained. This curve details the performance change trend of the material under different service conditions, enabling accurate identification of the material properties of components in subsequent virtual load scenario simulations. This, in turn, allows for precise calculation of stress distribution and deformation, ultimately improving the accuracy of product performance evaluation.

[0081] Through the above technical solution, this embodiment can systematically and accurately obtain the material performance degradation curves of burner components. This embodiment analyzes the material composition and customizes degradation test parameters based on its characteristics, making the obtained degradation curves more targeted and accurate. This not only improves the reliability of identifying component material properties in the burner's digital image but also provides a solid data foundation for subsequent calculations of the stress distribution and deformation of burner components. This significantly improves the accuracy and predictive ability of product performance evaluation, effectively avoiding potential product performance fluctuations caused by material performance degradation.

[0082] In some embodiments, step S205, identifying the root cause of product performance fluctuations based on product performance data and actual observation data, may include, but is not limited to, the following steps: Acquire auxiliary sensor data from the production line and a second sensitivity parameter of the burner component's response to environmental stimuli in a digital mapping; Compare product performance data with actual observation data to identify abnormal signals; Perform spectral analysis on abnormal signals to identify high-frequency transient fluctuations; Time series decomposition of abnormal signals is performed to identify non-periodic disturbance components; Correlation analysis is performed between abnormal signal components and auxiliary sensor data on the production line to identify transient environmental disturbances. Abnormal signal components include high-frequency transient fluctuations and non-periodic disturbance components. Based on the abnormal signals and the second sensitivity parameter, reverse deduction is performed to identify microscopic variations in the material; Identify the root causes of product performance fluctuations based on transient environmental disturbances and microscopic variations in materials.

[0083] In some embodiments, product performance fluctuations may be caused by a variety of complex factors, such as transient environmental disturbances or microscopic variations in materials, which may be difficult to accurately identify and distinguish using only simple performance data comparisons. Failure to address these issues may result in inaccurate judgment of the root cause of product performance fluctuations, thereby affecting the effectiveness of subsequent process parameter adjustments.

[0084] To this end, we can first obtain data from auxiliary sensors on the production line and the second sensitivity parameters of burner components in the digital mapping to environmental stimuli. Real-time data can be collected from various auxiliary sensors deployed on the production line (such as vibration sensors, temperature sensors, humidity sensors, pressure sensors, etc.), which can reflect instantaneous changes in the production environment. The second sensitivity parameter refers to the degree of response or sensitivity coefficient of burner components to specific environmental stimuli (such as temperature, humidity, pressure, vibration, etc.), which is determined in advance through simulation or experimentation in the burner digital mirror. Its purpose is to quantify the impact of environmental changes on component performance.

[0085] Then, the product performance data is compared with the actual observation data to identify abnormal signals. By comparing the product performance data obtained from digital mirror simulation (such as flame stability index, flame spectral characteristics, and vibration frequency data) with the actual observation data obtained from sensors or detection equipment on the actual production line, significant differences or deviations between the two can be identified, and these differences are considered abnormal signals.

[0086] Next, spectral analysis is performed on the abnormal signal to identify high-frequency transient fluctuations. Signal processing techniques such as Fourier transform can be used to convert the abnormal signal from the time domain to the frequency domain, analyze its frequency components, and thus identify those short-duration, high-frequency transient fluctuations. These fluctuations are often related to factors such as instantaneous impacts, vibrations, or electromagnetic interference. Time series decomposition is then performed on the abnormal signal to identify non-periodic disturbance components. Time series analysis methods (such as STL decomposition, seasonal decomposition, etc.) can be used to decompose the abnormal signal into trend terms, periodic terms, and residual terms. The residual terms typically represent non-periodic, random disturbance components, with the aim of separating irregular, sudden performance fluctuations.

[0087] Correlation analysis between anomalous signal components and auxiliary sensor data from the production line is performed to identify transient environmental disturbances. These anomalous signal components include high-frequency transient fluctuations and aperiodic disturbances. Statistical methods (such as correlation analysis and Granger causality tests) can be used to analyze the relationships between these high-frequency transient fluctuations and aperiodic disturbances and the auxiliary sensor data from the production line. This allows for the determination of which environmental factors (such as instantaneous temperature changes, air pressure fluctuations, and robotic arm vibration) are significantly associated with these anomalous signal components, thereby identifying specific transient environmental disturbances.

[0088] Based on anomalous signals and a second sensitivity parameter, reverse inference is performed to identify microscopic variations in materials. Using a pre-defined sensitivity model of burner components to environmental stimuli (i.e., the second sensitivity parameter), combined with the identified anomalous signals, reverse calculation or reasoning can be used to infer changes in the microstructure or properties of the internal materials of the components that cause these anomalous signals, such as material fatigue, microcracks, and component segregation. The aim is to reveal the underlying causes of performance fluctuations at the material level.

[0089] Finally, based on transient environmental disturbances and material micro-variations, the root causes of product performance fluctuations are identified. A comprehensive analysis of the identified transient environmental disturbances and material micro-variations can determine the specific and fundamental causes of product performance fluctuations. For example, this could be due to excessive instantaneous vibration at a certain workstation on the production line causing micro-cracks in components, or instantaneous fluctuations in gas supply pressure leading to unstable combustion.

[0090] To illustrate this technical solution more clearly, a specific example is used below. Suppose that during factory testing on a burner production line, a batch of burners exhibits slight but persistent fluctuations in flame stability index, and the flame spectral characteristics show an abnormal intensity distribution. First, auxiliary sensor data from the production line is acquired, such as the torque values ​​of the robotic arm recorded at the assembly station, the current and voltage curves at the welding station, and ambient temperature and humidity data. Simultaneously, a second sensitivity parameter for the burner components' response to environmental stimuli is acquired in the digital mapping. This parameter is pre-modeled based on the performance response of this type of burner component under different temperature, humidity, and vibration conditions. Next, the actually observed flame stability index and flame spectral characteristics are compared with the simulated normal product performance data obtained in the burner's digital mirror, identifying the flame fluctuations and spectral anomalies as abnormal signals.

[0091] Subsequently, spectral analysis of these abnormal signals revealed high-frequency transient fluctuations at specific frequencies. Time-series decomposition further identified non-periodic disturbance components. Further correlation analysis between these abnormal signal components and auxiliary sensor data from the production line revealed a strong correlation between the high-frequency transient fluctuations and the instantaneous torque peak of the assembly robot at a specific moment, thus identifying the transient environmental disturbance as an instantaneous mechanical impact during the assembly process. Simultaneously, based on the abnormal signals of flame flickering and spectral anomalies, as well as the second sensitivity parameter, reverse deduction was performed, inferring that there might be minute material fatigue or deformation in the burner nozzle area, i.e., identifying microscopic material variations. Ultimately, the root cause of the product performance fluctuations was determined to be: instantaneous mechanical impact at the assembly station caused microscopic fatigue in the nozzle material, which in turn affected the mixing efficiency of the gas and air, leading to decreased flame stability and spectral anomalies.

[0092] Through the above technical solution, this embodiment overcomes the limitations that may exist in identifying the root causes of product performance fluctuations, namely, the difficulty in accurately distinguishing and locating performance fluctuations caused by transient environmental disturbances or microscopic material variations. This embodiment introduces auxiliary sensor data from the production line and a second sensitivity parameter, combined with various advanced data processing and analysis methods such as spectrum analysis, time series decomposition, correlation analysis, and reverse inference, enabling a more in-depth and comprehensive analysis of abnormal signals. Therefore, it can not only identify the impact of transient environmental disturbances on product performance but also further reveal microscopic changes at the component material level, thus providing more accurate and comprehensive information on the root causes of product performance fluctuations. This refined identification capability significantly improves the accuracy of fault diagnosis, provides a more reliable basis for adjusting subsequent production process parameters, and thereby enhances the automation control level of the burner production line and the stability of product quality.

[0093] The beneficial effects of implementing the embodiments of the present invention include: First, the functional characteristic information and identification of burner components are obtained. Based on the functional characteristic information, potential functional abnormalities are identified. Then, based on the identification, potential functional abnormalities, and workstation operation data, a production process record is established. Based on the production process record, the root cause of product performance fluctuations is identified. Then, based on the root cause of product performance fluctuations, functional characteristic information, and production line operating status, the adjustment range of production process parameters is determined. Finally, based on the adjustment range of production process parameters, the target production process parameters are adjusted. This allows for the adjustment of production process parameters by combining potential functional abnormalities and the root cause of product performance fluctuations, thereby achieving production line control and improving accuracy and product quality.

[0094] like Figure 2 As shown, this embodiment of the invention also provides an automated control system for a burner production line, comprising: Information acquisition module 401 is used to acquire functional characteristic information and identification of burner components; The functional anomaly identification module 402 is used to identify potential functional anomalies based on functional characteristic information; The production process record creation module 403 is used to create production process records based on identity identification, potential functional abnormalities, and workstation operation data. The fluctuation source identification module 404 is used to identify the root cause of product performance fluctuations based on production process records; The adjustment range determination module 405 is used to determine the adjustment range of production process parameters based on the root cause of product performance fluctuations, functional characteristic information, and production line operating status. The parameter adjustment module 406 is used to adjust the target production process parameters according to the production process parameter adjustment range.

[0095] The content of the above method embodiments is applicable to this system embodiment. The specific functions implemented in this system embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0096] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

Claims

1. An automated control method for a burner production line, characterized in that, Includes the following steps: Obtain functional characteristic information and identification of burner components; Based on the aforementioned functional characteristic information, potential functional abnormalities can be identified; Based on the identity identifier, the potential functional abnormalities, and the workstation operation data, establish a production process record; Based on the production process records, identify the root causes of product performance fluctuations; Based on the root cause of the product performance fluctuation, the functional feature information, and the production line operating status, determine the adjustment range of the production process parameters; Adjust the target production process parameters according to the aforementioned production process parameter adjustment range; The step of identifying the root cause of product performance fluctuations based on the production process records includes: Acquire production line station information, environmental context data, and combustion behavior characteristics. The environmental context data includes the torque value of the assembly robot arm, the current and voltage curves of the welding station, the gas supply pressure, the ambient temperature, and the ambient humidity. A digital image of the burner is constructed based on the production line station information, the environmental context data, and the combustion behavior characteristics. Based on the production process records, identify potential abnormal production process parameters; In the digital mirror of the burner, scenario simulations are performed on the potential abnormal production process parameters to obtain product performance data, which includes flame stability index, flame spectral characteristics, and vibration frequency data. Identify the root causes of product performance fluctuations based on the product performance data and actual observation data; The step of identifying the root cause of product performance fluctuations based on the product performance data and actual observation data includes: Acquire production line auxiliary sensor data and a second sensitivity parameter of the burner components' response to environmental stimuli in a digital mapping; The product performance data is compared with actual observation data to identify abnormal signals; Spectral analysis was performed on the abnormal signal to identify high-frequency transient fluctuations; The abnormal signal is decomposed into a time series to identify non-periodic disturbance components; Correlation analysis is performed between abnormal signal components and data from the production line's auxiliary sensors to identify transient environmental disturbances. The abnormal signal components include the high-frequency transient fluctuations and the non-periodic disturbance components; Based on the abnormal signal and the second sensitivity parameter, reverse deduction is performed to identify microscopic variations in the material; The root causes of product performance fluctuations are identified based on the transient environmental disturbances and the microscopic variations in the materials.

2. The method according to claim 1, characterized in that, The acquisition of functional characteristic information of burner components includes: Transient excitation simulating actual complex operating conditions is applied to the burner components; When the transient excitation is applied, the transient response signal of the burner component is acquired, and the transient response signal includes acoustic signal, non-visible light signal or visible light spectral characteristics; Feature extraction is performed on the transient response signal to obtain transient excitation sensitivity features; The transient excitation sensitivity features are matched with the component feature library to identify the functional feature information.

3. The method according to claim 1, characterized in that, The step of identifying the root cause of product performance fluctuations based on the production process records includes: Based on the production process records, identify potential abnormal production process parameters; Based on the workstation operation data, the potentially abnormal production process parameters are adjusted; After adjusting the potentially abnormal production process parameters, product status data is obtained; Based on the correlation between status and performance and the product status data, assess the trend of product performance changes; Identify the root causes of product performance fluctuations based on the product performance change trends.

4. The method according to claim 1, characterized in that, The process of simulating the potential abnormal production process parameters to obtain product performance data includes: Obtain the first sensitivity parameter of the burner component to transient thermal stress response in digital mapping; Based on the potential abnormal production process parameters and the first sensitivity parameter, adjust the micro-geometric deformation and material stress distribution of the gas outlet region in the digital image of the burner; The first mixing efficiency of the gas and air is calculated based on the microscopic geometric deformation and the stress distribution of the material. Based on the first mixing efficiency, product performance is evaluated to obtain the product performance data.

5. The method according to claim 1, characterized in that, The process of simulating the potential abnormal production process parameters to obtain product performance data includes: Obtain the associated production process parameters that are related to the potentially abnormal production process parameters; Identify the physical correlation between the potential abnormal production process parameters and the associated production process parameters; Based on the aforementioned physical correlation, a parameter linkage adjustment strategy is constructed; Based on the parameter linkage adjustment strategy, the potential abnormal production process parameters and the associated production process parameters are adjusted in a coordinated virtual manner. Assess the comprehensive impact of collaborative virtual adjustments on the microstructure and hydrodynamic characteristics of the burner components; Calculate the second mixing efficiency of gas and air based on the overall impact level described above; Based on the second mixing efficiency, product performance is evaluated to obtain the product performance data.

6. The method according to claim 1, characterized in that, The process of simulating the potential abnormal production process parameters to obtain product performance data includes: Obtain the material property degradation curves of the burner components; Virtual loads under extreme operating conditions are applied to the burner components; Under virtual load, the material properties of the components are identified based on the material property decay curve. Based on the material properties of the components and the potential abnormal production process parameters, calculate the stress distribution and deformation of the burner components; Based on the stress distribution and deformation of the burner components, product performance is evaluated to obtain product performance data.

7. The method according to claim 6, characterized in that, The process of obtaining the material property degradation curves of the burner components includes: Material composition analysis was performed on the burner components to obtain material property characteristics; Based on the aforementioned material properties, determine the attenuation test parameters; Based on the attenuation test parameters, attenuation tests are performed on the burner components to obtain the material performance attenuation curves.

8. An automated control system for a burner production line, for performing the method as described in any one of claims 1 to 7, characterized in that, include: The information acquisition module is used to acquire functional characteristic information and identification information of burner components; A functional anomaly identification module is used to identify potential functional anomalies based on the functional feature information. The production process record creation module is used to create production process records based on the identity identifier, the potential functional abnormalities, and workstation operation data. The fluctuation source identification module is used to identify the root causes of product performance fluctuations based on the production process records. The adjustment range determination module is used to determine the adjustment range of production process parameters based on the root cause of the product performance fluctuation, the functional feature information, and the production line operating status. The parameter adjustment module is used to adjust the target production process parameters according to the production process parameter adjustment range.

Images