A method and system for gas path protection control of laser equipment
By collecting and analyzing pressure and flow data in real time in laser processing equipment, and using a time-series confidence coupling discriminant model to identify gas path faults, the problems of false alarms and batch scrapping in existing technologies are solved, and efficient and reliable gas path protection for laser processing is achieved.
Patent Information
- Application Number
- CN202611611273.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-10-19
- Publication Date
- 2026-11-17
AI Technical Summary
Existing gas path protection schemes for laser processing equipment cannot effectively identify hidden faults such as nozzle blockage, leading to frequent false alarms and unplanned shutdowns. Furthermore, when the gas path deteriorates, it cannot form a closed-loop constraint with the laser process parameters, resulting in batch scrapping.
By acquiring baseline values for laser processing technology type and gas medium type, real-time pressure and flow rate are collected, deviation coefficients and trend factors are calculated, and multi-channel information is fused using a time-series confidence coupling discrimination model to accurately identify fault types and implement graded fault-tolerant protection, thereby inversely constraining laser processing parameters.
It enables accurate identification of hidden faults such as nozzle blockage, reduces false alarm rate and unplanned downtime, establishes closed-loop constraints between gas path and process parameters, avoids batch scrap, and improves processing yield.
Smart Images

Figure CN123103172A_ABST
Abstract
Description
Technical Field
[0001] This application belongs to the field of laser processing gas path safety control technology, specifically relating to a laser equipment gas path protection control method and system. Background Technology
[0002] In laser processing technologies such as laser cutting, laser welding, laser cladding, laser cleaning, and laser engraving, auxiliary protective gas is a core process medium for ensuring processing quality, suppressing molten slag spatter, isolating oxidation, and protecting nozzles and optical lenses. All types of laser processing equipment are highly dependent on the stability of gas path pressure and flow rate. Existing laser equipment gas path protection solutions generally adopt a single pressure threshold alarm architecture, relying solely on pipeline pressure signals. When the pressure falls below a fixed threshold, an alarm is triggered and the machine shuts down. A few devices have added flow detection modules, but none use independent threshold judgments for pressure and flow rate, failing to establish a coupled logical relationship. This solution has significant shortcomings: Firstly, when nozzles are blocked or gas output is attenuated, the pipeline pressure is often normal, but the actual effective gas flow rate is significantly insufficient. Pressure detection cannot identify such hidden faults and struggles to distinguish between different fault types under different laser processes, leading to frequent false alarms and unplanned shutdowns. Secondly, the gas path is completely open-loop with the process; when the gas path deteriorates, it cannot reversely constrain laser processing parameters, causing the equipment to continue processing at high power, resulting in batch scrapping.
[0003] Therefore, there is an urgent need for a laser equipment gas path protection scheme that can achieve dual-parameter coupling discrimination of pressure and flow, accurately identify hidden faults such as nozzle blockage and reduce false alarm rate, and at the same time establish a closed-loop constraint mechanism between gas path deterioration and laser process parameters, and adaptively adjust processing parameters to avoid batch defects when the gas path is abnormal. Summary of the Invention
[0004] In a first aspect, embodiments of this application provide a method for gas path protection control of a laser device, comprising the following steps: S1. Obtain the current laser processing technology type and protective gas medium type, and retrieve the pressure reference value and flow reference value corresponding to the process type and gas medium type; S2. During laser processing, collect the real-time pressure and flow rate of the gas path in the laser equipment; S3. Calculate the pressure deviation coefficient and flow deviation coefficient based on real-time pressure, real-time flow, pressure reference value, and flow reference value. Calculate the pressure degradation trend factor and flow degradation trend factor based on the sampling data of a continuous preset number of frames. Use the pressure deviation coefficient, flow deviation coefficient, pressure degradation trend factor, and flow degradation trend factor as fault characteristic parameters. S4. Input the pressure deviation coefficient, flow deviation coefficient, pressure deterioration trend factor, and flow deterioration trend factor into the time-series confidence coupling discrimination model to calculate the global fault confidence, and determine the gas path state index based on the global fault confidence; the time-series confidence coupling discrimination model integrates three channels of information: instantaneous deviation, time-series trend, and duration of fault characteristic parameters; S5. Based on the global fault confidence level and the duration of the fault characteristic parameters, determine whether there is a gas path fault and the type of fault. S6. Implement graded fault-tolerant protection based on the fault type and global fault confidence level, and reverse-constrain the laser processing parameters based on the gas path state index.
[0005] Secondly, embodiments of this application also provide a gas path protection control system for laser equipment, comprising: The reference parameter acquisition module is used to acquire the current laser processing process type and protective gas medium type, and retrieve the pressure reference value and flow reference value corresponding to the process type and gas medium type. The signal acquisition module is used to acquire the real-time pressure and flow rate of the gas path in the laser equipment during laser processing. The feature calculation module is used to calculate the pressure deviation coefficient and flow deviation coefficient based on real-time pressure, real-time flow, pressure benchmark value, and flow benchmark value, and to calculate the pressure deterioration trend factor and flow deterioration trend factor based on the sampling data of a continuous preset number of frames, and to use the pressure deviation coefficient, flow deviation coefficient, pressure deterioration trend factor, and flow deterioration trend factor as fault feature parameters. The confidence calculation module is used to input the pressure deviation coefficient, flow deviation coefficient, pressure deterioration trend factor, and flow deterioration trend factor into the time-series confidence coupling discrimination model to calculate the global fault confidence, and determine the gas path state index based on the global fault confidence; the time-series confidence coupling discrimination model integrates three channels of information: instantaneous deviation, time-series trend, and duration of fault characteristic parameters; The fault determination module is used to determine whether there is a gas path fault and the type of fault based on the global fault confidence and the duration of the fault characteristic parameters. The protection and constraint module is used to perform graded fault-tolerant protection based on the fault type and global fault confidence, and to reverse-constrain the laser processing parameters based on the gas path state index.
[0006] As can be seen from the above technical solutions, this application has the following advantages: The laser equipment gas path protection control method and system provided in this application obtains the corresponding reference values by acquiring the process type and gas medium type, collects pressure and flow rate in real time, and calculates the deviation coefficient and degradation trend factor. It uses a time-series confidence coupling discrimination model to fuse information from three channels: instantaneous deviation, time-series trend, and duration to calculate the global fault confidence. Then, it combines the duration to determine the fault type and executes graded fault-tolerant protection and process reverse constraints. This achieves dual-parameter coupling discrimination of pressure and flow rate, which can accurately identify hidden faults such as nozzle blockage where the pressure is normal but the flow rate is insufficient, reducing false alarm rate and unplanned downtime. At the same time, it establishes a closed-loop constraint between gas path degradation and laser process parameters, and adaptively adjusts processing parameters when the gas path is abnormal, avoiding batch scrapping and improving the accuracy of laser equipment gas path protection and processing yield. Attached Figure Description
[0007] To more clearly illustrate the technical solution of this application, the accompanying drawings used in the description will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0008] Figure 1 This is a schematic flowchart of the laser equipment gas path protection control method of the present invention.
[0009] Figure 2 This is a schematic diagram of the gas path protection control system for the laser equipment of the present invention. Detailed Implementation
[0010] The various embodiments of this disclosure will be described more fully in the detailed steps of the gas path protection control method for laser equipment described below. This disclosure may have various embodiments, and adjustments and changes may be made therein. However, it should be understood that there is no intention to limit the various embodiments of this disclosure to the specific embodiments disclosed herein, but rather this disclosure should be understood to cover all adjustments, equivalents, and / or alternatives falling within the spirit and scope of the various embodiments of this disclosure.
[0011] This embodiment provides a gas path protection control method for laser equipment. By coupling pressure and flow as dual parameters, it can accurately identify hidden faults such as nozzle blockage and suppress false alarms caused by instantaneous disturbances. It also uses the gas path state index to inversely constrain laser power and speed, thus avoiding batch scrapping.
[0012] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0013] Please see Figure 1 The diagram shows a flowchart of a laser device gas path protection control method in a specific embodiment. The method includes the following steps: S1. Obtain the current laser processing technology type and protective gas medium type, and retrieve the pressure reference value and flow reference value corresponding to the process type and gas medium type; It should be noted that by obtaining the current laser processing technology type and protective gas medium type and retrieving the corresponding pressure and flow reference values, the fault diagnosis benchmark can be accurately matched with the specific process and gas medium, avoiding benchmark mismatch and misjudgment caused by process and gas differences. S2. During laser processing, collect the real-time pressure and flow rate of the gas path in the laser equipment; It should be noted that by collecting gas pressure and flow rate in real time during laser processing, a real-time data source is provided for feature calculation and fault identification, ensuring the timeliness of monitoring; S3. Calculate the pressure deviation coefficient and flow deviation coefficient based on real-time pressure, real-time flow, pressure reference value, and flow reference value. Calculate the pressure degradation trend factor and flow degradation trend factor based on the sampling data of a continuous preset number of frames. Use the pressure deviation coefficient, flow deviation coefficient, pressure degradation trend factor, and flow degradation trend factor as fault characteristic parameters. It should be noted that by calculating the pressure deviation coefficient and flow deviation coefficient and calculating the degradation trend factor based on the sampling data of a continuous preset number of frames, the instantaneous deviation degree is quantified and the degradation rate is characterized, providing a characteristic basis for distinguishing between sudden and slow failures. S4. Input the pressure deviation coefficient, flow deviation coefficient, pressure deterioration trend factor, and flow deterioration trend factor into the time-series confidence coupling discrimination model to calculate the global fault confidence, and determine the gas path state index based on the global fault confidence; the time-series confidence coupling discrimination model integrates three channels of information: instantaneous deviation, time-series trend, and duration of fault characteristic parameters; It should be noted that by inputting pressure and flow deviation coefficients and degradation trend factors into the time-series confidence coupling discrimination model that integrates instantaneous deviation, time-series trend and duration information, the global fault confidence is calculated. This unifies the multi-source and multi-time-scale criteria into a single confidence index, improving the robustness of fault discrimination and suppressing false alarms caused by a single signal. S5. Based on the global fault confidence level and the duration of the fault characteristic parameters, determine whether there is a gas path fault and the type of fault. It should be noted that by combining the global fault confidence and the duration of fault characteristics to determine whether there is a gas path fault and the type of fault, false anomalies caused by instantaneous airflow disturbances are eliminated, and accurate classification of fault root causes is achieved. S6. Implement graded fault-tolerant protection based on fault type and global fault confidence, and reverse-constrain laser processing parameters based on gas path state index; It should be noted that by implementing graded fault-tolerant protection based on fault type and global fault confidence, and by inversely constraining laser processing parameters based on gas path state index, a two-way closed loop between gas path degradation state and laser process parameters is achieved, which ensures equipment safety while avoiding mass scrapping.
[0014] This embodiment uses pressure and flow rate dual-parameter coupling discrimination and time series confidence fusion to identify hidden faults such as nozzle blockage where the pressure is normal but the flow is insufficient, effectively reducing false alarm rate and unplanned downtime; it establishes a closed-loop constraint between gas path deterioration and laser process parameters, and adaptively adjusts processing parameters when the gas path is abnormal, avoiding batch scrap and improving yield.
[0015] Furthermore, as a refinement and extension of the specific implementation of the above embodiments, in order to fully illustrate the specific implementation process in this embodiment, another method for gas path protection control of laser equipment is provided, which includes the following steps: S1. Obtain the current laser processing technology type and protective gas medium type, and retrieve the pressure reference value and flow reference value corresponding to the process type and gas medium type; The specific steps of step S1 are as follows: S11. Power on the device and initialize it, reading the laser processing process type and protective gas medium type currently locked by the device; S12. Retrieve pre-stored historical process reference parameters corresponding to the process type and protective gas medium type, wherein the historical process reference parameters include pressure reference value P0 and flow reference value Q0; S13. Determine whether the self-calibration trigger condition is met. The self-calibration trigger condition includes at least one of the following: equipment restart, process switching, gas medium switching, long-term standby restart, or sensor parameter drift exceeding the threshold. If the self-calibration trigger condition is met, proceed to step S14; If the self-calibration trigger condition is not met, proceed to step S15; S14. Lock the no-load steady-state operating condition, continuously collect N (e.g., 15-30) sets of pressure P and flow Q data, remove abnormal data through mean filtering, perform fitting calculations to generate the pressure reference value P0 and flow reference value Q0 for the current operating condition, and update the pre-stored historical process reference parameters. The self-calibration process in step S14 also includes sensor drift determination and compensation, specifically including: S141. After each self-calibration, calculate the relative offset between the current fitted benchmark and the historical benchmark:
[0016]
[0017] in, This is the pressure reference value obtained from this self-calibration. Based on historical pressure benchmarks, The reference flow rate value obtained from this self-calibration is... This is a historical traffic baseline value; S142. Preset pressure-side drift threshold =2.0%, flow-side drift threshold =3.0%; S143. When When the sensor is deemed to be in normal condition, the storage unit is updated directly with the new benchmark without triggering compensation. S144. When If a slight drift is detected, adaptive drift compensation is automatically initiated, and the sensor zero point and range compensation coefficient are corrected according to the offset. The sensor benchmark database is updated synchronously, and new benchmarks are enabled. S145. When If a serious drift or sensor failure is detected, the automatic benchmark update is paused, the original benchmark is retained, a sensor maintenance alarm is output, and manual verification is prompted. S15. Directly use the existing effective pressure reference value P0 and flow reference value Q0; S16. Output the final determined pressure reference value P0 and flow reference value Q0; S2. During laser processing, collect the real-time pressure and flow rate of the gas path in the laser equipment; The specific steps of step S2 are as follows: S21. The pressure of the main gas pipeline is collected in real time by a pressure sensor as the raw pressure signal. The pressure sensor is a diffused silicon pressure sensor and is installed downstream of the pressure regulating valve and upstream of the solenoid valve group. S22. The actual mass flow rate of the nozzle is collected in real time as the raw flow signal by a flow sensor. The flow sensor is a thermal mass flow sensor and is arranged close to the air inlet of the laser processing head. S23. Perform signal conditioning on the raw pressure signal and raw flow signal, and output standardized real-time pressure and flow data through hardware low-pass filtering and mean denoising algorithm; The specific processing steps of the signal conditioning module in step S23 include: S231. The sensor output signal is sequentially passed through an input buffer, a second-order active low-pass filter, isolation and gain amplification, and then sampled by an ADC with a sampling rate fs≥1kHz. S232. A second-order active low-pass filter with a cutoff frequency of fc=50Hz is used to filter out the solenoid valve switching impact, pipeline airflow pulsation and environmental electromagnetic interference. S233. Using a mean denoising algorithm (e.g., an extreme value removal moving average algorithm), for a continuous N-point original sampling sequence, first remove the two instantaneous peak samples (maximum and minimum values) within the window, and then average the remaining samples:
[0018] Where N is the length of the sliding window, and N=16 is taken; the Q channel is processed in the same way; S234. Continuously read the laser enable signal of the laser; If the laser is in standby mode, not emitting light, and has no processing load, only the background silent monitoring mode is enabled to continuously collect and store pressure and flow time-series data, without starting the fault judgment logic or triggering interlock protection actions. If the laser enable signal is detected to be valid and the equipment enters the formal processing state, the full-function timing confidence coupling monitoring and fault diagnosis mechanism will be activated immediately. S24. Use standardized real-time pressure data as the real-time pressure. Standardized real-time traffic data is used as real-time traffic data. ; S3. Calculate the pressure deviation coefficient and flow deviation coefficient based on real-time pressure, real-time flow, pressure reference value, and flow reference value. Calculate the pressure degradation trend factor and flow degradation trend factor based on the sampling data of a continuous preset number of frames. Use the pressure deviation coefficient, flow deviation coefficient, pressure degradation trend factor, and flow degradation trend factor as fault characteristic parameters. The specific steps of step S3 are as follows: S31. Based on real-time pressure Real-time traffic and pressure reference value Flow baseline value Calculate the instantaneous pressure deviation coefficient and instantaneous flow deviation coefficient :
[0019]
[0020] S32. Retrieve N consecutive frames of historical time-series sampling data and use least-squares linear fitting to calculate the pressure time-series slope. and flow time series slope Where N is the preset number of frames, which ranges from 15 to 30; S33. Pressure time series slope and flow time series slope Normalized to a relative rate of change, the pressure degradation trend factor is obtained. and traffic degradation trend factors :
[0021] ; The formula for calculating the least squares linear fit in step S32 is as follows:
[0022] in, The average value at each sampling time. Pressure mean; flow rate time-series slope Apply the same formula to the flow sequence ( , Solve this problem; Step S3 also includes using both slope ratio and goodness-of-fit criteria to distinguish between abrupt and gradual failures: Calculate the slope of the current fitting window slope of the previous window ratio and the coefficient of determination :
[0023] The judgment rule is as follows: like If the mutation slope ratio is greater than or equal to a preset threshold (e.g., 3) and R² is greater than or equal to a preset goodness-of-fit threshold (e.g., 0.90), it is determined to be a mutation-type fault. like Within a preset range of gradually changing slope ratios (e.g.) Inside, and The goodness-of-fit factor is greater than or equal to the preset goodness-of-fit threshold, while the pressure deterioration trend factor... The absolute value is less than the preset gradual trend threshold (e.g.) (% / s), and the duration of continuous same-direction offset exceeds the judgment time window. It was determined to be a slowly changing fault; If the slope alternates between positive and negative, and R² is less than the preset goodness-of-fit threshold (e.g., 0.90), it is determined to be a normal airflow disturbance. S4. Input the pressure deviation coefficient, flow deviation coefficient, pressure deterioration trend factor, and flow deterioration trend factor into the time-series confidence coupling discrimination model to calculate the global fault confidence, and determine the gas path state index based on the global fault confidence; the time-series confidence coupling discrimination model integrates three channels of information: instantaneous deviation, time-series trend, and duration of fault characteristic parameters; In step S4, the time-series confidence coupling discrimination model adopts a three-channel weighted fusion structure of instantaneous deviation, time-series trend, and duration of fault characteristic parameters. The global fault confidence... The calculation formula is:
[0024] in, , , It is a three-channel weight, and + + =1; Components for each channel are calculated as follows:
[0025]
[0026]
[0027] In the formula, The normalized threshold for pressure deviation, The normalized threshold for flow deviation; The normalized threshold for the pressure trend. The threshold for traffic trend normalization; Duration of the fault characteristic; To determine the time window; , The weights of pressure and flow rate within the instantaneous deviation channel. , The weights of pressure and flow within the trend channel; The three-channel weights are taken =0.45、 =0.35、 =0.20; the weight within the instantaneous deviation channel is taken as... =0.3、 =0.7; the weight within the trend channel is taken as... =0.4、 =0.6; the normalization threshold is taken as... =0.15、 =0.20、 =1.0% / s =2.0% / s; the determination time window Take 8-20ms; S5. Based on the global fault confidence level and the duration of the fault characteristic parameters, determine whether there is a gas path fault and the type of fault. The specific steps of step S5 are as follows: S51. Set the judgment time window When the duration of the fault characteristic parameter Exceeding the judgment time window At that time, it was confirmed as a valid fault; S52. Perform sensor logic verification and compare the consistency of pressure and flow parameter change logic; If the sensor change patterns are contradictory or the confidence level is low, the sensor is determined to be drifting, malfunctioning, or abnormal, and a sensor maintenance alarm is output, but the gas path fault protection action is not executed. S53. By using a preset multi-process fault coupling discrimination matrix, combined with the instantaneous pressure deviation coefficient... Instantaneous flow deviation coefficient Deviation magnitude and pressure deterioration trend factor and traffic degradation trend factors The trend change characteristics match the following fault types: Instantaneous pressure deviation coefficient Greater than zero and less than the normalized threshold for pressure deviation Instantaneous flow deviation coefficient Greater than or equal to the normalized threshold of flow deviation And traffic degradation trend factor The absolute value is greater than or equal to the traffic trend normalization threshold. When this occurs, it is determined to be a nozzle blockage fault; Instantaneous pressure deviation coefficient Greater than or equal to the normalized threshold of pressure deviation Instantaneous flow deviation coefficient Greater than or equal to the normalized threshold of flow deviation And the pressure deterioration trend factor and traffic degradation trend factors When all values are negative and their absolute values are greater than or equal to their respective trend normalization thresholds, it is determined that the upstream gas supply is insufficient or the main pipeline is leaking. Instantaneous pressure deviation coefficient Less than the normalized threshold of pressure deviation Instantaneous flow deviation coefficient Less than the normalized threshold of flow deviation And the pressure deterioration trend factor and traffic degradation trend factors When all values are negative, their absolute values are less than their respective trend normalization thresholds, and the duration of continuous unidirectional shift exceeds the judgment time window T0, it is determined to be a progressive blockage of the filter element or a micro-leakage fault in the pipeline. Instantaneous pressure deviation coefficient and instantaneous flow deviation coefficient A short-term fluctuation occurs, but the duration of the fluctuation is less than the judgment time window. And the pressure deterioration trend factor and traffic degradation trend factors If there is no continuous unidirectional offset, it is determined to be a momentary airflow disturbance in the process and is not considered a fault. Instantaneous pressure deviation coefficient Deviation coefficient with instantaneous flow rate The change direction is opposite, that is, the instantaneous pressure deviation coefficient. Increase the instantaneous flow deviation coefficient Reduce, or instantaneous pressure deviation coefficient Reduce instantaneous flow deviation coefficient When the global fault confidence level Conf increases and is lower than the preset sensor anomaly confidence level threshold, it is determined that the sensor is drifting or has failed, and a sensor self-test alarm is output. S6. Implement graded fault-tolerant protection based on fault type and global fault confidence, and reverse-constrain laser processing parameters based on gas path state index; Step S6 involves implementing tiered fault-tolerant protection, specifically including: S61. Define the gas path state index ; in For global fault confidence, ; S62. Based on the gas path state index The current protection level is determined by its relationship with the preset first, second, third, and fourth thresholds. When the gas path state index When the value is less than the first threshold, the protection level is 0, and only background records are made without triggering any protection action. When the gas path state index When the value is greater than or equal to the first threshold and less than the second threshold, the protection level is 1, an early warning is issued, the deterioration trend is recorded in the background, the cleaning or engraving processing speed is automatically reduced, and filter element maintenance is prompted without stopping the machine. When the gas path state index When the value is greater than or equal to the second threshold and less than the third threshold, the protection level is 2, and process intervention is performed to automatically limit the maximum output power of the laser to a first proportion below the rated value and reduce the processing speed to a second proportion below the rated value. When the gas path state index When the value is greater than or equal to the third threshold and less than the fourth threshold, the protection level is 3, and the pause protection is executed, which pauses the equipment's motion axis, shuts off the laser output, locks the processing status, and awaits manual inspection. When the gas path state index When the value is greater than or equal to the fourth threshold, the protection level is level 4, an emergency stop is executed, the laser enable output is immediately cut off, and the equipment interlock emergency stop is triggered. S63. The duration of the cumulative verification is applied when each protection level is triggered; Level 1 and Level 2 require the duration of fault characteristics Greater than or equal to the decision time window ; Level 3 requires duration Greater than or equal to twice the decision time window Since Level 3 pause protection will interrupt production, a more stringent duration condition is adopted to further reduce the probability of false pauses. Level 4 involves equipment and personal safety, and is relaxed to t≥T0 to respond as quickly as possible, ensuring no missed shutdowns even in the event of accidental shutdowns; S64. The threshold values for each protection level are adaptively adjusted based on process sensitivity: For cladding and precision engraving processes, the preset scores for all levels of thresholds will be lowered as a whole; For cutting and welding processes, the preset scores for all levels of thresholds will be increased. Step S6 involves inversely constraining the laser processing parameters based on the gas path state index, specifically including: S65. Based on the gas path state index Calculate the laser power constraint coefficient using the following mapping function. and processing speed constraint coefficient :
[0028]
[0029] in, This is the preset maximum power reduction percentage. The preset maximum rate of decrease. The preset constraint starting threshold, The preset constraint termination threshold, This is a limiting function; S66. Adjust the laser power constraint coefficient. and processing speed constraint coefficient Multiply by the rated power of the current process respectively and rated speed The output power after constraints is obtained. and output speed :
[0030]
[0031] This achieves reverse constraint on laser processing parameters based on the deterioration state of the gas path.
[0032] The following is an example of an application scenario involving early warning and process intervention for progressive filter clogging under laser cladding conditions.
[0033] The processing target is a stainless steel substrate surface laser-clad with nickel-based alloy powder. Argon is used as the protective gas, and a micro-flow, high-sensitivity, trend-priority thresholding method is employed. The system generates specific reference parameters for the current operating condition through a self-calibration process: pressure reference value. =0.35MPa, flow rate reference value =15L / min.
[0034] During the cladding process, pipeline pressure was collected. It remained basically stable at 0.34 MPa. ≈0.03, less than =0.15), the flow acquisition unit detected that the nozzle outlet flow rate Q slowly decreased to 13.5 L / min ( ≈0.10, less than =0.20). The temporal feature extraction module retrieves 25 consecutive frames of historical sampling data and obtains the traffic temporal slope through least squares fitting. When the value is negative, the normalized result is the flow degradation trend factor. ≈-0.3% / s (less than) =2.0% / s), pressure deterioration trend factor ≈-0.05% / s. The slope ratio R≈0.8 (in the gradually changing range of 0.3 to 3), R²≈0.95, is judged to be a gradually changing fault.
[0035] The time-series confidence coupled discriminant model calculates the following: ≈30, ≈25, =100×min(1,15 / 12)=100 (duration exceeds) The component is then saturated to 100%. =0.45×30+0.35×25+0.20×100≈13.5+8.75+20=42.25. This is confirmed as a valid fault. The fault coupling discrimination matrix matches the fault as either progressive filter blockage or micro-leakage in the pipeline.
[0036] Gas path condition index =42.25 / 100≈0.42, falling into the Level 1 (Warning) range (0.3≤S<0.5). The system executes Level 1 protection: the background records the degradation trend and automatically reduces the cladding scan speed. The value calculated using the mapping function is approximately 0.88. This prompts the operator to check the filter cartridge status without shutting down the machine. No porosity or oxidation defects were observed in the cladding layer, preventing mass scrapping.
[0037] In some embodiments, the following steps are also included: S7. Fault snapshot tracing, storage, and visualization prompts; specific steps are as follows: S71. Each time a protection action is triggered or a valid fault is identified, the system automatically retains the complete time-series curves of pressure and flow rate, real-time trend factor, fault confidence value, current laser processing technology type, laser output power, processing speed, protective gas type, and precise timestamp for 200ms before and after the fault occurs. S72. Save the above data permanently even after power failure, supporting subsequent fault playback and after-sales traceability analysis; S73. The human-machine interaction unit pops up a visual fault interface, outputting the textual root cause of the fault, the fault level, and corresponding operation and maintenance suggestions.
[0038] In some embodiments, the following steps are also included: S8. Fault Reset and Adaptive Cyclic Monitoring; Specific steps are as follows: S81. After manually troubleshooting and eliminating gas path faults and completing the equipment reset operation, the current fault status and protection lock command are automatically cleared, the reference judgment parameters are reinitialized, and the normal real-time monitoring cycle is returned to normal. S82. If it is a minor, gradual deterioration fault, no manual intervention is required. After the gas circuit conditions return to normal on their own and the fault confidence level falls back to the safe threshold range, the warning and process constraints will be automatically lifted, and the original processing parameters of the equipment will be restored. S83. Continuously execute gas path monitoring, discrimination and protection logic.
[0039] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
[0040] like Figure 2As shown, the following are embodiments of the laser equipment gas path protection control system provided in this disclosure. This system and the laser equipment gas path protection control method of the above embodiments belong to the same inventive concept. For details not described in detail in the embodiments of the laser equipment gas path protection control system, please refer to the embodiments of the laser equipment gas path protection control method described above.
[0041] The system includes: The reference parameter acquisition module is used to acquire the current laser processing process type and protective gas medium type, and retrieve the pressure reference value and flow reference value corresponding to the process type and gas medium type. The signal acquisition module is used to acquire the real-time pressure and flow rate of the gas path in the laser equipment during laser processing. The feature calculation module is used to calculate the pressure deviation coefficient and flow deviation coefficient based on real-time pressure, real-time flow, pressure benchmark value, and flow benchmark value, and to calculate the pressure deterioration trend factor and flow deterioration trend factor based on the sampling data of a continuous preset number of frames, and to use the pressure deviation coefficient, flow deviation coefficient, pressure deterioration trend factor, and flow deterioration trend factor as fault feature parameters. The confidence calculation module is used to input the pressure deviation coefficient, flow deviation coefficient, pressure deterioration trend factor, and flow deterioration trend factor into the time-series confidence coupling discrimination model to calculate the global fault confidence, and determine the gas path state index based on the global fault confidence; the time-series confidence coupling discrimination model integrates three channels of information: instantaneous deviation, time-series trend, and duration of fault characteristic parameters; The fault determination module is used to determine whether there is a gas path fault and the type of fault based on the global fault confidence and the duration of the fault characteristic parameters. The protection and constraint module is used to perform graded fault-tolerant protection based on the fault type and global fault confidence, and to reverse-constrain the laser processing parameters based on the gas path state index.
[0042] This embodiment achieves dual-parameter coupling discrimination of pressure and flow, accurate identification of latent faults, graded fault-tolerant protection, and bidirectional closed-loop constraint of gas path and process through the interactive collaboration of the reference parameter acquisition module, signal acquisition module, feature calculation module, confidence calculation module, fault judgment module, and protection and constraint module. This reduces the false alarm rate and the risk of batch scrapping, and improves the accuracy of gas path protection for laser equipment and the processing yield.
[0043] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A method for gas path protection and control of laser equipment, characterized in that, Includes the following steps: S1. Obtain the current laser processing technology type and protective gas medium type, and retrieve the pressure reference value and flow reference value corresponding to the process type and gas medium type; S2. During laser processing, collect the real-time pressure and flow rate of the gas path in the laser equipment; S3. Calculate the pressure deviation coefficient and flow deviation coefficient based on real-time pressure, real-time flow, pressure reference value, and flow reference value. Calculate the pressure degradation trend factor and flow degradation trend factor based on the sampling data of a continuous preset number of frames. Use the pressure deviation coefficient, flow deviation coefficient, pressure degradation trend factor, and flow degradation trend factor as fault characteristic parameters. S4. Input the pressure deviation coefficient, flow deviation coefficient, pressure deterioration trend factor and flow deterioration trend factor into the time series confidence coupled discrimination model to calculate the global fault confidence, and determine the gas path state index based on the global fault confidence. The time-series confidence coupling discriminant model integrates information from three channels: instantaneous deviation, time-series trend, and duration of fault characteristic parameters. S5. Based on the global fault confidence level and the duration of the fault characteristic parameters, determine whether there is a gas path fault and the type of fault. S6. Implement graded fault-tolerant protection based on the fault type and global fault confidence level, and reverse-constrain the laser processing parameters based on the gas path state index.
2. The laser equipment gas path protection control method according to claim 1, characterized in that, The specific steps of step S1 are as follows: S11. Power on the device and initialize it, reading the laser processing process type and protective gas medium type currently locked by the device; S12. Retrieve pre-stored historical process reference parameters corresponding to the process type and protective gas medium type, wherein the historical process reference parameters include pressure reference value P0 and flow reference value Q0; S13. Determine whether the self-calibration trigger condition is met. The self-calibration trigger condition includes at least one of the following: equipment restart, process switching, gas medium switching, long-term standby restart, or sensor parameter drift exceeding the threshold. If the self-calibration trigger condition is met, proceed to step S14; If the self-calibration trigger condition is not met, proceed to step S15; S14. Lock the no-load steady-state operating condition, continuously collect N sets of pressure P and flow Q data, remove abnormal data through mean filtering, perform fitting calculations to generate the pressure reference value P0 and flow reference value Q0 for the current operating condition, and update the pre-stored historical process reference parameters. S15. Directly use the existing effective pressure reference value P0 and flow reference value Q0; S16. Output the final determined pressure reference value P0 and flow reference value Q0.
3. The laser equipment gas path protection control method according to claim 2, characterized in that, The specific steps of step S2 are as follows: S21. The pressure of the main gas pipeline is collected in real time by a pressure sensor as the raw pressure signal; S22. The actual mass flow rate of the nozzle is collected in real time using a flow sensor as the raw flow signal; S23. Perform signal conditioning on the raw pressure signal and raw flow signal, and output standardized real-time pressure and flow data through hardware low-pass filtering and mean denoising algorithm; S24. Use standardized real-time pressure data as the real-time pressure. Standardized real-time traffic data is used as real-time traffic data. .
4. The laser equipment gas path protection control method according to claim 3, characterized in that, The specific steps of step S3 are as follows: S31. Based on real-time pressure Real-time traffic and pressure reference value Flow baseline value Calculate the instantaneous pressure deviation coefficient and instantaneous flow deviation coefficient : S32. Retrieve N consecutive frames of historical time-series sampling data and use least-squares linear fitting to calculate the pressure time-series slope. and flow time series slope Where N is the preset number of frames; S33. Pressure time series slope and flow time series slope Normalized to a relative rate of change, the pressure degradation trend factor is obtained. and traffic degradation trend factors : 。 5. The laser equipment gas path protection control method according to claim 4, characterized in that, The formula for calculating the least squares linear fit in step S32 is as follows: in, The average value at each sampling time. Pressure mean; flow rate time-series slope Apply the same formula to the flow sequence ( , Solve this problem; Step S3 also includes using both slope ratio and goodness-of-fit criteria to distinguish between abrupt and gradual failures: Calculate the slope of the current fitting window slope of the previous window ratio and the coefficient of determination : The judgment rule is as follows: like If the mutation slope ratio is greater than or equal to the preset threshold and R² is greater than or equal to the preset goodness-of-fit threshold, it is determined to be a mutation-type fault. like Within the preset range of gradually changing slope ratios, and The goodness-of-fit factor is greater than or equal to the preset goodness-of-fit threshold, while the pressure deterioration trend factor... The absolute value is less than the preset gradual trend threshold, and the duration of continuous same-direction offset exceeds the judgment time window. It was determined to be a slowly changing fault; If the slope alternates between positive and negative, and R² is less than the preset goodness-of-fit threshold, it is determined to be a normal airflow disturbance.
6. The laser equipment gas path protection control method according to claim 5, characterized in that, In step S4, the time-series confidence coupling discrimination model adopts a three-channel weighted fusion structure of instantaneous deviation, time-series trend, and duration of fault characteristic parameters. The global fault confidence... The calculation formula is: in, , , It is a three-channel weight, and + + =1; Components for each channel are calculated as follows: In the formula, The normalized threshold for pressure deviation, The normalized threshold for flow deviation; The normalized threshold for the pressure trend. The threshold for traffic trend normalization; Duration of the fault characteristic; To determine the time window; , The weights of pressure and flow rate within the instantaneous deviation channel. , The weights of pressure and flow within the trend channel.
7. The laser equipment gas path protection control method according to claim 6, characterized in that, The specific steps of step S5 are as follows: S51. Set the judgment time window When the duration of the fault characteristic parameter Exceeding the judgment time window At that time, it was confirmed as a valid fault; S52. Perform sensor logic verification and compare the consistency of pressure and flow parameter change logic; If the sensor change patterns are contradictory or the confidence level is low, the sensor is determined to be drifting, malfunctioning, or abnormal, and a sensor maintenance alarm is output, but the gas path fault protection action is not executed. S53. By using a preset multi-process fault coupling discrimination matrix, combined with the instantaneous pressure deviation coefficient... Instantaneous flow deviation coefficient Deviation magnitude and pressure deterioration trend factor and traffic degradation trend factors The trend change characteristics match the following fault types: Instantaneous pressure deviation coefficient Greater than zero and less than the normalized threshold for pressure deviation Instantaneous flow deviation coefficient Greater than or equal to the normalized threshold of flow deviation And traffic degradation trend factor The absolute value is greater than or equal to the traffic trend normalization threshold. When this occurs, it is determined to be a nozzle blockage fault; Instantaneous pressure deviation coefficient Greater than or equal to the normalized threshold of pressure deviation Instantaneous flow deviation coefficient Greater than or equal to the normalized threshold of flow deviation And the pressure deterioration trend factor and traffic degradation trend factors When all values are negative and their absolute values are greater than or equal to their respective trend normalization thresholds, it is determined that the upstream gas supply is insufficient or the main pipeline is leaking. Instantaneous pressure deviation coefficient Less than the normalized threshold of pressure deviation Instantaneous flow deviation coefficient Less than the normalized threshold of flow deviation And the pressure deterioration trend factor and traffic degradation trend factors All values are negative, their absolute values are less than their respective trend normalization thresholds, and the duration of continuous unidirectional shift exceeds the judgment time window. When this occurs, the problem is determined to be either gradual blockage of the filter element or a minor leak in the pipeline. Instantaneous pressure deviation coefficient and instantaneous flow deviation coefficient A short-term fluctuation occurs, but the duration of the fluctuation is less than the judgment time window. And the pressure deterioration trend factor and traffic degradation trend factors If there is no continuous unidirectional offset, it is determined to be a momentary airflow disturbance in the process and is not considered a fault. Instantaneous pressure deviation coefficient Deviation coefficient with instantaneous flow rate The change direction is opposite, that is, the instantaneous pressure deviation coefficient. Increase the instantaneous flow deviation coefficient Reduce, or instantaneous pressure deviation coefficient Reduce instantaneous flow deviation coefficient When the global fault confidence level Conf increases and is lower than the preset sensor abnormality confidence level threshold, it is determined that the sensor is drifting or has failed, and a sensor self-test alarm is output.
8. The laser equipment gas path protection control method according to claim 7, characterized in that, Step S6 involves implementing tiered fault-tolerant protection, specifically including: S61. Define the gas path state index ; in For global fault confidence, ; S62. Based on the gas path state index The current protection level is determined by its relationship with the preset first, second, third, and fourth thresholds. When the gas path state index When the value is less than the first threshold, the protection level is 0, and only background records are made without triggering any protection action. When the gas path state index When the value is greater than or equal to the first threshold and less than the second threshold, the protection level is 1, an early warning is issued, the deterioration trend is recorded in the background, the cleaning or engraving processing speed is automatically reduced, and filter element maintenance is prompted without stopping the machine. When the gas path state index When the value is greater than or equal to the second threshold and less than the third threshold, the protection level is 2, and process intervention is performed to automatically limit the maximum output power of the laser to a first proportion below the rated value and reduce the processing speed to a second proportion below the rated value. When the gas path state index When the value is greater than or equal to the third threshold and less than the fourth threshold, the protection level is 3, and the pause protection is executed, which pauses the equipment's motion axis, shuts off the laser output, locks the processing status, and awaits manual inspection. When the gas path state index When the value is greater than or equal to the fourth threshold, the protection level is level 4, an emergency stop is executed, the laser enable output is immediately cut off, and the equipment interlock emergency stop is triggered. S63. The duration of the cumulative verification is applied when each protection level is triggered; S64. The threshold values for each protection level are adaptively adjusted based on process sensitivity: For cladding and precision engraving processes, the preset scores for all levels of thresholds will be lowered as a whole; For cutting and welding processes, the preset scores for all levels of thresholds will be increased.
9. The laser equipment gas path protection control method according to claim 8, characterized in that, Step S6 involves inversely constraining the laser processing parameters based on the gas path state index, specifically including: S65. Based on the gas path state index Calculate the laser power constraint coefficient using the following mapping function. and processing speed constraint coefficient : in, This is the preset maximum power reduction percentage. The preset maximum rate of decrease. The preset constraint starting threshold, The preset constraint termination threshold, This is a limiting function; S66. Adjust the laser power constraint coefficient. and processing speed constraint coefficient Multiply by the rated power of the current process respectively and rated speed The output power after constraints is obtained. and output speed : This achieves reverse constraint on laser processing parameters based on the deterioration state of the gas path.
10. A gas path protection control system for laser equipment, characterized in that, include: The reference parameter acquisition module is used to acquire the current laser processing process type and protective gas medium type, and retrieve the pressure reference value and flow reference value corresponding to the process type and gas medium type. The signal acquisition module is used to acquire the real-time pressure and flow rate of the gas path in the laser equipment during laser processing. The feature calculation module is used to calculate the pressure deviation coefficient and flow deviation coefficient based on real-time pressure, real-time flow, pressure benchmark value, and flow benchmark value, and to calculate the pressure deterioration trend factor and flow deterioration trend factor based on the sampling data of a continuous preset number of frames, and to use the pressure deviation coefficient, flow deviation coefficient, pressure deterioration trend factor, and flow deterioration trend factor as fault feature parameters. The confidence calculation module is used to input the pressure deviation coefficient, flow deviation coefficient, pressure deterioration trend factor and flow deterioration trend factor into the time series confidence coupling discrimination model to calculate the global fault confidence, and determine the gas path state index based on the global fault confidence. The time-series confidence coupling discriminant model integrates information from three channels: instantaneous deviation, time-series trend, and duration of fault characteristic parameters. The fault determination module is used to determine whether there is a gas path fault and the type of fault based on the global fault confidence and the duration of the fault characteristic parameters. The protection and constraint module is used to perform graded fault-tolerant protection based on the fault type and global fault confidence, and to reverse-constrain the laser processing parameters based on the gas path state index.
