A smart early warning method and system based on laser-controlled industrial data

Abstract

This invention discloses an intelligent early warning method and system based on laser control industrial data, belonging to the field of laser safety early warning technology. The system includes an equipment control module, a data acquisition module, an analysis database, a model management module, a monitoring and judgment module, and an alarm module. The equipment control module controls the laser to cut industrial products; the data acquisition module collects cutting data and parameter data generated during the cutting process; the analysis database stores historical data of cutting data and parameter data; the model management module establishes a deviation analysis model to analyze the impact of different influencing parameters on the cutting deviation of industrial products; the monitoring and judgment module determines whether there are any abnormalities in the current cutting of industrial products; and the alarm module issues alarms for abnormalities. This method considers the impact of different influencing parameters on the cutting deviation of industrial products, improving the accuracy of system data analysis.

Description

Technical Field

[0001] This invention relates to the field of laser safety early warning technology, specifically to an intelligent early warning method and system based on laser control industrial data. Background Technology

[0002] With the rapid development of intelligent manufacturing, lasers, as core equipment in modern industrial manufacturing, have been widely used in the processing and manufacturing of high-precision equipment such as cutting and welding. Against this backdrop, the analysis of industrial data for laser control is gradually evolving from simple operation monitoring to multi-level intelligent decision-making. Through data analysis, process parameters such as temperature and cutting depth generated by laser operation can be monitored in real time, thereby predicting component life, identifying abnormal operations and providing early warnings, effectively extending equipment life and reducing the risk of safety failures.

[0003] When using laser industrial control data to issue early warnings for equipment safety faults, this is often achieved by setting early warning thresholds. When the analyzed laser industrial control data exceeds the early warning threshold, a safety warning is issued. However, the operating environment of lasers is complex and variable. A single early warning threshold judgment does not take into account the impact of changes in other factors on the laser's operating results, which can easily lead to system misjudgments. Existing technologies are unable to quickly and accurately assess equipment safety anomalies under different laser operating modes, thereby increasing the management costs throughout the equipment's life cycle. Summary of the Invention

[0004] In view of the shortcomings of the existing technology, the purpose of this invention is to provide an intelligent early warning method and system based on laser-controlled industrial data to solve the problems mentioned in the background.

[0005] To achieve the above objectives, the present invention provides the following technical solution: an intelligent early warning method based on laser-controlled industrial data, comprising:

[0006] Based on the production batch, the laser is controlled to cut industrial products, and cutting data and parameter data generated during the cutting process are collected. The cutting data includes the preset cutting depth and the actual cutting depth of the industrial products. The parameter data represents the monitored parameters that affect the cutting deviation of the industrial products.

[0007] Establish an analysis database to store historical data on cutting data and parameter data; based on the stored historical cutting data and historical parameter data, establish a deviation analysis model to analyze the impact of different influencing parameters on the cutting deviation of industrial products;

[0008] The system monitors the collected cutting data and parameter data in real time, calculates the cutting deviation for the current production batch, and determines whether there are any abnormalities in the cutting of the current industrial products based on the established deviation analysis model and F-detection. If the cutting is normal, monitoring continues; if there are any cutting abnormalities, an alarm is triggered and the alarm signal is sent to the management personnel.

[0009] An intelligent early warning system based on laser-controlled industrial data includes an equipment control module, a data acquisition module, an analysis database, a model management module, a monitoring and judgment module, and an alarm module.

[0010] The equipment control module is used to control the laser to cut industrial products according to the production batch;

[0011] The data acquisition module is used to collect cutting data and parameter data generated during the cutting process of industrial products; the cutting data includes the preset cutting depth and the actual cutting depth of the industrial products; the parameter data represents the monitoring parameters that affect the cutting deviation of the industrial products; and the collected cutting data and parameter data are sent to the analysis database and the monitoring and judgment module.

[0012] The analysis database is used to store historical data of cutting data and parameter data;

[0013] The model management module is used to establish a deviation analysis model based on stored historical cutting data and historical parameter data, and to analyze the influence of different influencing parameters on the cutting deviation of industrial products.

[0014] The monitoring and judgment module is used to monitor the collected cutting data and parameter data in real time, calculate the cutting deviation under the current production batch, and determine whether there is an abnormality in the cutting of the current industrial product based on the established deviation analysis model and F detection. If the cutting is normal, monitoring continues; if there is a cutting abnormality, an abnormal signal is sent to the alarm module.

[0015] The alarm module is used to generate abnormal alarms and send alarm signals to management personnel.

[0016] Compared with existing technologies, the beneficial effects achieved by this invention are as follows: By establishing a deviation analysis model, the influence of different influencing parameters on the cutting deviation of industrial products is analyzed, which improves the accuracy of subsequent laser safety anomaly analysis and reduces the misjudgment that may be caused by a single threshold in the system; by using F-detection, the current cutting of industrial products is identified as abnormal, and the influence of different influencing parameters on the cutting deviation of industrial products is considered, avoiding interference from other influencing factors on the judgment of abnormal cutting of industrial products, thereby improving the accuracy of system data analysis; and warnings are given for abnormal cutting of industrial products, enabling managers to perform maintenance in a timely manner and reducing the operation and maintenance management costs of equipment. Attached Figure Description

[0017] The disclosure of this invention is illustrated with reference to the accompanying drawings. It should be understood that the drawings are for illustrative purposes only and are not intended to limit the scope of protection of this invention. Wherein:

[0018] Figure 1 This is a schematic diagram of the structure of an intelligent early warning system based on laser-controlled industrial data according to the present invention. Detailed Implementation

[0019] 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 of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0020] The present invention provides the following technical solution:

[0021] In this first embodiment, an intelligent early warning method based on laser-controlled industrial data is provided, including:

[0022] Based on the production batch, the laser is controlled to cut industrial products, and cutting data and parameter data generated during the cutting process are collected. The cutting data includes the preset cutting depth and the actual cutting depth of the industrial products. The parameter data represents the monitored parameters that affect the cutting deviation of the industrial products.

[0023] It should be noted that laser control industrial data refers to the general term for various data generated during the laser cutting process, including the laser's operating status and the industrial product processing process. In this embodiment, laser control industrial data includes collected cutting data and parameter data. The parameter data includes the average temperature of the industrial product at the cut point when the laser cutting ends and the average input power after the laser cutting ends.

[0024] Furthermore, before cutting industrial products, the quantity of industrial products in the current production batch is determined. Based on the preset cutting depth, the laser is controlled to cut the industrial products. After cutting, the actual cutting depth of each industrial product in the current production batch is determined. Among them, the preset cutting depth of industrial products cut in the same production batch is the same.

[0025] In this embodiment, the industrial product is a semiconductor wafer. During the industrial product cutting process, the input power of each industrial product after cutting is collected in real time by a high-precision laser power device, and the average input power of each industrial product after cutting is obtained by summing the data. The temperature of the industrial product at the cutting point at the end of cutting is collected by a non-contact infrared thermal imager, and the average temperature of the industrial product at the cutting point at the end of cutting is obtained by summing the data. The initial temperature of each industrial product before cutting is kept the same by a temperature control system.

[0026] Establish an analysis database to store historical data on cutting data and parameters; based on the stored historical cutting data and historical parameter data, establish a deviation analysis model to analyze the impact of different influencing parameters on the cutting deviation of industrial products.

[0027] Furthermore, the method and steps for establishing a deviation analysis model and analyzing the influence of different parameters on the cutting deviation of industrial products are as follows:

[0028] S1. Retrieve historical cutting data and historical parameter data from the analysis database for analysis; based on the historical cutting data, obtain the quantity of industrial products cut under different production batches. and preset cutting depth And obtain the set of actual cutting depths for different industrial products in each production batch. ;in, ; This represents the set of actual cutting depths for different industrial products in the j-th production batch; Let represent the actual cutting depth of different industrial products in the j-th production batch; m represents the number of production batches in the analyzed historical cutting data; based on the historical parameter data, the influence parameter values ​​during the cutting of different industrial products in each production batch are obtained, and the average input power after laser cutting in the j-th production batch is denoted as . , will the The average temperature of the industrial product at the cut point at the end of each production batch is recorded as follows: ;

[0029] S2. Calculate the cutting deviation for different production batches based on the actual cutting depth of different industrial products in each production batch. According to the calculation formula:

[0030] ;

[0031] in, This represents the cutting deviation in the j-th production batch; This represents the actual cutting depth of the i-th industrial product in the j-th production batch; This represents the number of industrial products cut in the j-th production and processing batch; This represents the average actual cutting depth of different industrial products in the j-th production batch;

[0032] S3. Establish a deviation analysis model, using the influencing parameters in the industrial product cutting process as independent variables and the cutting deviation under different production batches as dependent variables, and fit the relationship curves of the influence of different influencing parameters on the cutting deviation of industrial products:

[0033] ;

[0034] in, Indicates cutting deviation; This represents the average input power after the laser cutting process is completed; This indicates the average temperature of the industrial product at the cut point when the laser cutting is completed. This indicates the weight of the influence of input power on the cutting deviation; Indicates the weight of the effect of temperature on cutting deviation; This indicates the effect of changes in input power on the temperature of industrial products and thus on cutting deviation.

[0035] It should be noted that as the average input power increases, the cutting deviation first decreases and then increases. Furthermore, as the temperature of the industrial product increases, the cutting deviation continues to increase. By establishing a deviation analysis model, the... As The training parameters; As The training parameters, As The training parameters are substituted into the aforementioned relationship curves, and the least squares method is used for fitting to determine the results. and The value of the threshold is used to consider the effects of input power and temperature on cutting deviation, thereby improving the accuracy of subsequent laser safety anomaly analysis and reducing the misjudgment that may be caused by a single threshold in the system.

[0036] The system monitors the collected cutting data and parameter data in real time, calculates the cutting deviation for the current production batch, and determines whether there are any abnormalities in the cutting of the current industrial products based on the established deviation analysis model and F-detection. If the cutting is normal, monitoring continues; if there are any cutting abnormalities, an alarm is triggered and the alarm signal is sent to the management personnel.

[0037] Specifically, based on the established deviation analysis model and F-detection, the steps for determining whether there are any abnormalities in the cutting of current industrial products are as follows:

[0038] S10. Monitor the collected cutting data and parameter data in real time. Based on the cutting data, determine the quantity n of industrial products to be cut in the current production batch and the preset cutting depth h, and determine the actual cutting depth of different industrial products in the current production batch. Based on the parameter data, determine the influencing parameter values ​​for cutting different industrial products in the current production batch, and obtain the average input power after laser cutting in the current production batch. The average temperature of the industrial product at the cut point at the end of laser cutting ;

[0039] S20. Calculate the cutting deviation for the current production batch according to the calculation formula in step S2. Based on the established deviation analysis model, the impact of different influencing parameters on the cutting deviation of industrial products is determined. :

[0040] ;

[0041] S30, will The cutting deviations were compared with those of different production batches analyzed in the database. Perform pairwise comparisons and calculate F-statistic with different cutting deviations:

[0042] ;

[0043] in, express The F-statistic between the cutting deviation and the cutting deviation in the j-th production batch;

[0044] S40. Based on the significance level, Using the numerator and denominator degrees of freedom, determine the critical value of the corresponding F-distribution. ; Determine if there are any abnormalities in the current cutting of industrial products; When When both conditions are met, the cutting of the current industrial product is normal; when there is... At that time, the cutting of industrial products was abnormal.

[0045] In this embodiment, the molecular degrees of freedom The denominator degrees of freedom Through significance level and molecular degrees of freedom Degrees of freedom of the denominator Determine the critical value corresponding to the F distribution. The method involves determining whether there is a significant difference between the cutting deviation of the current production batch and the cutting deviation of different production batches analyzed in the database. Specifically, based on historical cutting data and historical parameter data stored in the database, management sets the significance level of the cutting deviation and determines the critical value of the F-distribution for different cutting deviations according to the degrees of freedom in the cutting deviation. The method is as follows: using the F-statistic as the independent variable based on the numerator and denominator degrees of freedom, the probability density function of the F-distribution is obtained; based on the determined significance level, the critical value of the F-distribution is determined; where the critical value of the F-distribution makes the area on the right side of the probability density function curve equal to the determined significance level.

[0046] It should be noted that the critical value of the F-distribution depends on the significance level set by the management and the degrees of freedom in the cutting deviation. The significance level represents the risk that the management can accept in erroneously rejecting the null hypothesis. Given the significance level and degrees of freedom, the F-statistic calculated using the critical value of the F-distribution is sufficiently extreme to determine whether to reject the null hypothesis. When the calculated F-statistic is greater than the critical value of the F-distribution, the null hypothesis is rejected, indicating that the current industrial product cutting is abnormal. When the calculated F-statistic is less than or equal to the critical value of the F-distribution, the null hypothesis is not rejected, indicating that there is insufficient evidence to suggest that the current industrial product cutting is abnormal, and that the current industrial product cutting is normal. Through F-detection, the cutting deviation of the current production batch is compared with the cutting deviation of different production batches in the analysis database. Historical data in the analysis database is used as a comparison parameter to identify whether the current industrial product cutting is abnormal. Simultaneously, based on the deviation analysis model, the influence of different influencing parameters on the industrial product cutting deviation is considered, avoiding interference from other influencing factors in the judgment of industrial product cutting anomalies, thereby improving the accuracy of system data analysis. Warnings are issued for abnormal cutting of industrial products, enabling management to perform timely maintenance and reducing equipment operation and maintenance costs.

[0047] Please see Figure 1 In this second embodiment, an intelligent early warning system based on laser-controlled industrial data is provided. The system includes an equipment control module, a data acquisition module, an analysis database, a model management module, a monitoring and judgment module, and an alarm module.

[0048] The equipment control module is used to control the laser to cut industrial products according to the production batch;

[0049] The data acquisition module is used to collect cutting data and parameter data generated during the cutting process of industrial products; the cutting data includes the preset cutting depth and the actual cutting depth of the industrial products; the parameter data represents the monitoring parameters that affect the cutting deviation of the industrial products; and the collected cutting data and parameter data are sent to the analysis database and the monitoring and judgment module.

[0050] The analysis database is used to store historical data of cutting data and parameter data;

[0051] The model management module is used to establish a deviation analysis model based on stored historical cutting data and historical parameter data, and to analyze the influence of different influencing parameters on the cutting deviation of industrial products.

[0052] The monitoring and judgment module is used to monitor the collected cutting data and parameter data in real time, calculate the cutting deviation under the current production batch, and determine whether there is an abnormality in the cutting of the current industrial product based on the established deviation analysis model and F detection. If the cutting is normal, monitoring continues; if there is a cutting abnormality, an abnormal signal is sent to the alarm module.

[0053] The alarm module is used to generate abnormal alarms and send alarm signals to management personnel.

[0054] Furthermore, the model management module includes a historical data analysis unit, a cutting deviation calculation unit, and a model analysis unit;

[0055] The historical data analysis unit is used to retrieve historical cutting data and historical parameter data from the analysis database for analysis. Based on the historical cutting data, it obtains the number of industrial products cut and the preset cutting depth under different production batches, and obtains the set of actual cutting depths for different industrial products under each production batch. Based on the historical parameter data, it obtains the influence parameter values ​​for cutting different industrial products under each production batch.

[0056] The cutting deviation calculation unit is used to calculate the cutting deviation for different production batches based on the actual cutting depth of different industrial products in each production batch.

[0057] The model analysis unit is used to establish a deviation analysis model, taking the influencing parameters in the industrial product cutting process as independent variables and the cutting deviation under different production batches as dependent variables, and fitting the relationship curve of the influence of different influencing parameters on the cutting deviation of industrial products.

[0058] Furthermore, the monitoring and judgment module includes a real-time data analysis unit, an intelligent computing unit, and an intelligent judgment unit;

[0059] The real-time data analysis unit is used to monitor the collected cutting data and parameter data in real time. Based on the cutting data, it determines the number of industrial products to be cut and the preset cutting depth in the current production batch, and determines the actual cutting depth of different industrial products in the current production batch. Based on the parameter data, it determines the influencing parameter values ​​when cutting different industrial products in the current production batch.

[0060] The intelligent computing unit is used to calculate the cutting deviation under the current production batch; determine the impact of different influencing parameters on the cutting deviation of industrial products; and calculate the F-statistic between the cutting deviation under the current production batch and different cutting deviations in the analysis database.

[0061] The intelligent judgment unit is used to determine whether there is any abnormality in the current cutting of industrial products.

[0062] Furthermore, a human-computer interaction platform is provided, through which managers can view and analyze historical cutting data and historical parameter data in the database, view cutting deviations under different production batches, and set the significance level of cutting deviations.

[0063] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. An intelligent early warning method based on laser-controlled industrial data, characterized in that: include: Based on the production batch, the laser is controlled to cut industrial products, and cutting data and parameter data generated during the cutting process are collected. The cutting data includes the preset cutting depth and the actual cutting depth of the industrial products. The parameter data represents the monitored parameters that affect the cutting deviation of the industrial products. Establish an analysis database to store historical data on cutting data and parameter data; based on the stored historical cutting data and historical parameter data, establish a deviation analysis model, taking the influencing parameters in the industrial product cutting process as independent variables and the cutting deviation under different production batches as dependent variables, fit the relationship curve of the influence of different influencing parameters on the cutting deviation of industrial products, and analyze the influence of different influencing parameters on the cutting deviation of industrial products. The collected cutting data and parameter data are monitored in real time. Based on the number of industrial products cut in the current production batch, the preset cutting depth, and the actual cutting depth of different industrial products in the current production batch, the cutting deviation in the current production batch is calculated. Based on the established deviation analysis model and F-detection, the influence of different influencing parameters on the cutting deviation of industrial products is determined, and it is judged whether there is any abnormality in the cutting of industrial products. If the cutting is normal, continue monitoring; if there is an abnormality in the cutting, issue an alarm and send the alarm signal to the management personnel. Based on the established deviation analysis model and F-detection, the method and steps for determining whether there are abnormalities in the cutting of current industrial products are as follows: S10. Monitor the collected cutting data and parameter data in real time. Based on the cutting data, determine the quantity n of industrial products to be cut in the current production batch and the preset cutting depth h, and determine the actual cutting depth of different industrial products in the current production batch. Based on the parameter data, determine the influencing parameter values ​​for cutting different industrial products in the current production batch, and obtain the average input power after laser cutting in the current production batch. The average temperature of the industrial product at the cut point at the end of laser cutting ; S20. According to the calculation formula Calculate the cutting deviation under the current production batch. Based on the established deviation analysis model, the impact of different influencing parameters on the cutting deviation of industrial products is determined. : ； in, This indicates the weight of the influence of input power on the cutting deviation; Indicates the weight of the effect of temperature on cutting deviation; This indicates the effect of input power variations on the temperature of industrial products on cutting deviations. Indicates the error term; This represents the cutting deviation in the j-th production batch; This represents the actual cutting depth of the i-th industrial product in the j-th production batch; This represents the number of industrial products cut in the j-th production and processing batch; This represents the average actual cutting depth of different industrial products in the j-th production batch; S30, will The cutting deviations were compared with those of different production batches analyzed in the database. Perform pairwise comparisons and calculate F-statistic with different cutting deviations: ； in, express The F-statistic between the cutting deviation and the cutting deviation in the j-th production batch; S40. Based on the significance level, Using the numerator and denominator degrees of freedom, determine the critical value of the corresponding F-distribution. ; Determine if there are any abnormalities in the current cutting of industrial products; When When both conditions are met, the cutting of the current industrial product is normal; when there is... At that time, the cutting of industrial products was abnormal.

2. The intelligent early warning method based on laser-controlled industrial data according to claim 1, characterized in that: Before cutting industrial products, the quantity of industrial products in the current production batch is determined. Based on the preset cutting depth, the laser is controlled to cut the industrial products. After cutting, the actual cutting depth of each industrial product in the current production batch is determined. Among them, the preset cutting depth of industrial products cut in the same production batch is the same.

3. The intelligent early warning method based on laser-controlled industrial data according to claim 1, characterized in that: During the industrial product cutting process, a high-precision laser power unit collects the input power of each industrial product after the cutting is completed in real time, and the sum is used to obtain the average input power of each industrial product after the cutting is completed. A non-contact infrared thermal imager collects the temperature of the industrial product at the cutting point at the end of the cutting of each industrial product, and the sum is used to obtain the average temperature of the industrial product at the cutting point at the end of the cutting of each industrial product. The initial temperature of each industrial product before cutting is kept the same by a temperature control system.

4. The intelligent early warning method based on laser-controlled industrial data according to claim 1, characterized in that: The steps for establishing a deviation analysis model and analyzing the influence of different parameters on the cutting deviation of industrial products are as follows: S1. Retrieve historical cutting data and historical parameter data from the analysis database for analysis; based on the historical cutting data, obtain the quantity of industrial products cut under different production batches. and preset cutting depth And obtain the set of actual cutting depths for different industrial products in each production batch. ;in, ; This represents the set of actual cutting depths for different industrial products in the j-th production batch; , representing the actual cutting depth of different industrial products in the j-th production batch; m represents the number of production batches in the analyzed historical cutting data; based on the historical parameter data, the influence parameter values ​​for cutting different industrial products in each production batch are obtained; S2. Calculate the cutting deviation for different production batches based on the actual cutting depth of different industrial products in each production batch. According to the calculation formula: ； in, This represents the cutting deviation in the j-th production batch; This represents the actual cutting depth of the i-th industrial product in the j-th production batch; This represents the number of industrial products cut in the j-th production and processing batch; This represents the average actual cutting depth of different industrial products in the j-th production batch; S3. Establish a deviation analysis model, taking the influencing parameters in the industrial product cutting process as independent variables and the cutting deviation under different production batches as dependent variables, and fit the relationship curve of the influence of different influencing parameters on the cutting deviation of industrial products.

5. An intelligent early warning system based on laser-controlled industrial data, employing the intelligent early warning method based on laser-controlled industrial data as described in any one of claims 1-4, characterized in that: The system includes an equipment control module, a data acquisition module, an analysis database, a model management module, a monitoring and judgment module, and an alarm module; The equipment control module is used to control the laser to cut industrial products according to the production batch; The data acquisition module is used to collect cutting data and parameter data generated during the cutting process of industrial products; the cutting data includes the preset cutting depth and the actual cutting depth of the industrial products; the parameter data represents the monitoring parameters that affect the cutting deviation of the industrial products; and the collected cutting data and parameter data are sent to the analysis database and the monitoring and judgment module. The analysis database is used to store historical data of cutting data and parameter data; The model management module is used to establish a deviation analysis model based on stored historical cutting data and historical parameter data. It takes the influencing parameters in the industrial product cutting process as independent variables and the cutting deviation under different production batches as dependent variables. It fits the relationship curve of the influence of different influencing parameters on the cutting deviation of industrial products and analyzes the influence of different influencing parameters on the cutting deviation of industrial products. The monitoring and judgment module is used to monitor the collected cutting data and parameter data in real time. Based on the number of industrial products cut in the current production batch, the preset cutting depth, and the actual cutting depth of different industrial products in the current production batch, it calculates the cutting deviation in the current production batch. Based on the established deviation analysis model and F-detection, it determines whether there is an abnormality in the cutting of the current industrial products. If the cutting is normal, monitoring continues; if there is a cutting abnormality, an abnormal signal is sent to the alarm module. The monitoring and judgment module includes a real-time data analysis unit, an intelligent computing unit, and an intelligent judgment unit. The real-time data analysis unit is used to monitor the collected cutting data and parameter data in real time. Based on the cutting data, it determines the number of industrial products to be cut and the preset cutting depth in the current production batch, and determines the actual cutting depth of different industrial products in the current production batch. Based on the parameter data, it determines the influencing parameter values ​​when cutting different industrial products in the current production batch. The intelligent computing unit is used to calculate the cutting deviation under the current production batch; determine the impact of different influencing parameters on the cutting deviation of industrial products; and calculate the F-statistic between the cutting deviation under the current production batch and different cutting deviations in the analysis database. The intelligent judgment unit is used to determine whether there is any abnormality in the current cutting of industrial products; The alarm module is used to generate abnormal alarms and send alarm signals to management personnel.

6. The intelligent early warning system based on laser-controlled industrial data according to claim 5, characterized in that: The model management module includes a historical data analysis unit, a cutting deviation calculation unit, and a model analysis unit; The historical data analysis unit is used to retrieve historical cutting data and historical parameter data from the analysis database for analysis. Based on the historical cutting data, it obtains the number of industrial products cut and the preset cutting depth under different production batches, and obtains the set of actual cutting depths for different industrial products under each production batch. Based on the historical parameter data, it obtains the influence parameter values ​​for cutting different industrial products under each production batch. The cutting deviation calculation unit is used to calculate the cutting deviation for different production batches based on the actual cutting depth of different industrial products in each production batch. The model analysis unit is used to establish a deviation analysis model, taking the influencing parameters in the industrial product cutting process as independent variables and the cutting deviation under different production batches as dependent variables, and fitting the relationship curve of the influence of different influencing parameters on the cutting deviation of industrial products.

7. The intelligent early warning system based on laser-controlled industrial data according to claim 6, characterized in that: A human-computer interaction platform is provided, through which managers can view and analyze historical cutting data and historical parameter data in the database, view cutting deviations under different production batches, and set the significance level of cutting deviations.

Images