Automatic monitoring method and system for metal plate laser cutting operation

Abstract

The invention discloses an automatic monitoring method and system for metal plate laser cutting operation, and relates to the technical field of laser cutting monitoring methods. The invention provides an automatic detection method for metal plate laser cutting operation. The automatic detection method comprises the following operation steps that the cutting length error rate and the laser fluctuation rate of a metal plate within a preset time period are obtained; evaluating an abnormal score according to the cutting length error rate and the laser fluctuation rate; if the abnormal score is greater than a preset threshold value, acquiring image information of the metal plate; evaluating a cutting quality score according to the image information; if the cutting quality score is greater than the target score, outputting an abnormal score misjudgment result, and tracing a misjudgment reason; and if the cutting quality score is smaller than the target score, obtaining a cutting defect type, and adjusting a cutting strategy.

Description

Technical Field

[0001] The present application relates to the technical field of laser cutting monitoring methods, and in particular to an automated monitoring method and system for metal sheet laser cutting operations. Background Art

[0002] In the metal processing industry, laser cutting technology is widely used due to its high precision, high efficiency and good cutting quality. However, in the actual production process, due to the influence of various factors, such as equipment aging, changes in material properties, laser power fluctuations, etc., laser cutting operations often have some unforeseen errors, which not only affect the dimensional accuracy of the cut parts, but also may cause quality defects on the cut surface. Traditionally, the inspection of these cutting qualities mainly relies on manual visual inspection or post-sampling inspection, which has low inspection efficiency and is greatly affected by human factors, making it difficult to achieve real-time and comprehensive quality control. Summary of the invention

[0003] The main purpose of this application is to provide an automated monitoring method and system for metal sheet laser cutting operations, aiming to solve the technical problems in the prior art that metal sheet laser cutting quality detection mainly relies on manual visual inspection or post-sampling inspection, has low inspection efficiency, and is greatly affected by human factors.

[0004] To achieve the above objectives, in a first aspect, the present application provides an automated detection method for metal sheet laser cutting operations, comprising the following steps:

[0005] Obtaining the cutting length error rate and laser fluctuation rate of the metal sheet within a preset time period;

[0006] evaluating an anomaly score based on the cutting length error rate and the laser fluctuation rate;

[0007] If the anomaly score is greater than a preset threshold, the image information of the metal sheet is obtained;

[0008] evaluating a cutting quality score according to the image information;

[0009] If the cutting quality score is greater than the target score, the abnormal score misjudgment result is output and the cause of the misjudgment is traced;

[0010] If the cutting quality score is less than the target score, the cutting defect type is obtained and the cutting strategy is adjusted.

[0011] Optionally, the step of obtaining the cutting length error rate and the laser fluctuation rate of the metal sheet within a preset time period includes:

[0012] According to the actual spatial coordinates of the laser cutting head and the reference spatial coordinates at the corresponding moment, the actual moving path and the reference moving path of the laser cutting head within a preset time period are obtained;

[0013] According to the actual moving path and the reference moving path, the cutting length error rate is obtained;

[0014] The calculation formula of cutting length error rate is as follows:

[0015]

[0016] Among them, d i represents the Euclidean distance between the actual space coordinate and the reference coordinate at the i-th moment, n is the total number of sampling points in the preset time period, L is the total length of the reference path in the preset time period, and w i is the weight factor.

[0017] Optionally, the step of obtaining the cutting length error rate and laser fluctuation rate of the metal sheet within a preset time period further includes:

[0018] According to a preset number of power output data collected within a preset time period, an average power and a standard deviation of the laser beam within the time period are obtained;

[0019] The laser fluctuation power is obtained according to the average power and the standard deviation.

[0020] Optionally, the step of evaluating the abnormality score according to the cutting length error rate and the laser fluctuation rate includes:

[0021] Configure weight coefficients for the cutting length error rate and the laser fluctuation rate respectively, and obtain an abnormality score through weighted calculation;

[0022] If the abnormality score is less than the preset threshold, the output cutting length error rate and laser fluctuation rate are within the error range;

[0023] If the anomaly score is greater than the target threshold and less than the preset threshold, the preset time is marked as a time period that requires special observation.

[0024] Optionally, the step of evaluating the cutting quality score according to the image information comprises:

[0025] According to the front image information and the back image information of the metal plate in the cutting area, the front image information and the back image information are preprocessed to obtain a grayscale image;

[0026] Extracting the features of the cutting area according to the grayscale image to obtain the type and degree of the cutting defect;

[0027] According to the cutting defect type, a weight coefficient of the defect degree is configured, and a weighted calculation is performed on all the obtained cutting defect types to obtain a cutting quality score.

[0028] Optionally, the step of extracting the features of the cutting area and obtaining the type and degree of the cutting defect according to the grayscale image includes:

[0029] The formula for obtaining the degree of defect is as follows:

[0030]

[0031] Among them, w j represents the weight of the jth feature, f j (·) represents the quantization function corresponding to the jth feature, and the eigenvalue ij is the j-th eigenvalue of defect type i.

[0032] Optionally, the step of configuring a weight coefficient of the defect degree according to the cutting defect type, performing weighted calculation on all acquired cutting defect types, and obtaining a cutting quality score includes:

[0033] The formula for the cut quality score is as follows:

[0034]

[0035] Among them, α i is the weight coefficient of the i-th defect type, D i is the defect degree of the ith defect type.

[0036] Optionally, if the cutting quality score is greater than the target score, the step of outputting an abnormal score misjudgment result and tracing the cause of the misjudgment includes:

[0037] If the cutting quality score is greater than the target score, an abnormal score misjudgment result is output;

[0038] According to the abnormal score misjudgment result, obtain whether there is a corresponding historical case record;

[0039] If so, then based on the historical case records, historical cutting information is obtained to trace the cause of the misjudgment;

[0040] If not, check the data acquisition equipment, cutting parameters and process in sequence to trace the cause of the misjudgment.

[0041] Optionally, if the cutting quality score is less than the target score, the step of obtaining the cutting defect type and adjusting the cutting strategy includes:

[0042] If the cutting quality score is less than the target score, the cutting defect type is obtained;

[0043] According to the cutting defect type, obtaining the cause of the defect;

[0044] According to the causes of the defects, the cutting parameters are adjusted and / or the cutting path is optimized.

[0045] In a second aspect, the present application provides an automated detection system for metal sheet laser cutting operations, comprising:

[0046] An error rate and fluctuation rate acquisition module, which is configured to acquire a cutting length error rate and a laser fluctuation rate of a metal sheet within a preset time period;

[0047] an abnormality score evaluation module, configured to evaluate an abnormality score according to the cutting length error rate and the laser fluctuation rate;

[0048] an image information acquisition module, configured to acquire image information of the metal sheet if the abnormality score is greater than a preset threshold;

[0049] a cutting quality score evaluation module, configured to evaluate a cutting quality score according to the image information;

[0050] A traceability module is configured to output an abnormal score misjudgment result if the cutting quality score is greater than the target score, and trace the cause of the misjudgment;

[0051] The cutting strategy adjustment module is configured to obtain the cutting defect type and adjust the cutting strategy if the cutting quality score is less than the target score.

[0052] Beneficial effects that this application can achieve:

[0053] The embodiment of the present application proposes an automated detection method and system for metal sheet laser cutting operations. By obtaining the cutting length error rate and laser fluctuation rate to evaluate the abnormality score, potential problems in the cutting process can be more accurately identified. When the abnormality score exceeds the preset threshold, the image information of the metal sheet is further obtained, and the cutting quality score is evaluated using image processing technology. This step not only improves the accuracy of the detection, but also realizes the intuitive evaluation of the cutting quality. If the cutting quality score is greater than the target score, the abnormal score misjudgment result is output, and the cause of the misjudgment is traced, which helps to optimize the evaluation model of the abnormality score, reduce the misjudgment rate, and improve the reliability of the detection system. If the cutting quality score is less than the target score, the cutting strategy is adjusted by identifying the type of cutting defects. This instant feedback and adjustment mechanism can significantly reduce the incidence of cutting defects and improve product qualification rate and production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 This is a schematic flow chart of an automated monitoring method for metal sheet laser cutting operations in this application.

[0055] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0056] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0057] It should be noted that all directional indications in the embodiments of the present invention (such as up, down, left, right, front, back, etc.) are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0058] In the present invention, unless otherwise clearly specified and limited, the terms "connection", "fixation", etc. should be understood in a broad sense. For example, "fixation" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0059] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present invention, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the meaning of "and / or" appearing in the full text includes three parallel schemes. Taking "A and / or B" as an example, it includes scheme A, or scheme B, or a scheme that satisfies both A and B. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the ability of ordinary technicians in the field to implement. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0060] Example 1

[0061] Reference Figure 1 The first embodiment of the present application provides an automated detection method for metal sheet laser cutting operations, comprising the following steps:

[0062] S10, obtaining a cutting length error rate and a laser fluctuation rate of the metal sheet within a preset time period.

[0063] Optionally, a high-precision positioning system (such as an optical positioner or a mechanical positioner) is used to monitor the spatial coordinate position of the metal sheet during the cutting process in real time, obtain the moving path within a preset time period, and compare it with the preset moving path to calculate the cutting length error rate. At the same time, a laser power monitor or a laser stability analyzer is used to monitor the output power fluctuation of the laser source in real time and calculate the laser fluctuation rate. The preset time period can be set according to actual needs, such as every minute, every five minutes, or after cutting a specific length.

[0064] S20. Evaluate an abnormality score according to the cutting length error rate and the laser fluctuation rate.

[0065] Optionally, the cutting length error rate refers to the deviation ratio between the actual cutting length and the preset cutting length, reflecting the accuracy and stability of the cutting operation. The cutting length error rate may be affected by many factors such as the accuracy of the cutting equipment, material properties (such as thickness, hardness), cutting speed, laser power, etc. A higher cutting length error rate means that the processed metal sheet may not meet the processing requirements, resulting in unqualified products or requiring additional processing to adjust the size. The laser fluctuation rate refers to the degree of fluctuation of the output power of the laser source during the cutting process, reflecting the stability and reliability of the laser cutting system. The laser fluctuation rate may be affected by factors such as aging of the laser source, unstable power supply, and poor cooling system. A higher laser fluctuation rate will lead to unstable cutting quality, and problems such as incomplete cutting, increased burrs, and expansion of the heat-affected zone may occur, affecting the appearance and performance of the cut parts. The abnormality score is evaluated to determine whether there are abnormal conditions in the cutting process.

[0066] S30: If the abnormality score is greater than a preset threshold, image information of the metal sheet is obtained.

[0067] Optionally, when the abnormality score is greater than the preset threshold, it indicates that there may be some faults, resulting in the quality of the processed metal sheet not meeting expectations. At this time, the cut metal sheet is photographed or recorded through image acquisition equipment such as a high-resolution industrial camera or infrared thermal imager to further determine whether the cutting quality meets expectations. Only when the abnormality score is greater than the preset threshold, the image information is obtained and analyzed, and resources are used rationally. Cutting defects can be more accurately identified through image information, thereby improving the accuracy of detection.

[0068] S40: Evaluate the cutting quality score according to the image information.

[0069] Optionally, an image processing algorithm is used to process and analyze the acquired image information to extract features such as the contour of the cutting edge and the texture of the cutting surface. According to the preset cutting quality evaluation standard, the extracted features are quantitatively scored to obtain the cutting quality score. The objective evaluation of cutting quality is achieved through image processing technology, reducing the influence of human factors. The cutting quality score provides an accurate basis for subsequent judgment and decision-making.

[0070] S50: If the cutting quality score is greater than the target score, the abnormal score misjudgment result is output and the cause of the misjudgment is traced.

[0071] Optionally, when the cutting quality score is higher than the target score, it indicates that the cutting quality of the metal sheet meets expectations and is judged as an abnormal score misjudgment. Review and analyze the measurement data of the cutting length error rate and laser fluctuation rate and the image processing results to find out the cause of the misjudgment. By tracing the cause of the misjudgment, the evaluation model and parameter settings can be optimized to improve the accuracy of the detection. Reduce the occurrence of misjudgments and improve production efficiency.

[0072] S60: If the cutting quality score is less than the target score, the cutting defect type is obtained and the cutting strategy is adjusted.

[0073] According to the image information and cutting quality evaluation standards, the specific cutting defect types (such as burrs, cracks, incomplete cutting, etc.) are identified, and the cutting parameters (such as laser power, cutting speed, focal length, etc.) or cutting path planning are adjusted according to the defect types. By identifying the cutting defect types and adjusting the cutting strategy, the cutting quality can be significantly improved. The product qualification rate and production efficiency are improved, and the production cost is reduced.

[0074] Example 2

[0075] Based on Example 1, this example provides an automated detection method for metal sheet laser cutting operations, including the following steps:

[0076] S10, obtaining a cutting length error rate and a laser fluctuation rate of the metal sheet within a preset time period.

[0077] Optionally, the step of obtaining the cutting length error rate and laser fluctuation rate of the metal sheet within a preset time period includes:

[0078] S101. Acquire an actual moving path and a reference moving path of the laser cutting head within a preset time period according to the actual space coordinates of the laser cutting head and the reference space coordinates at the corresponding moment.

[0079] Specifically, a high-precision positioning system (such as an optical locator or a mechanical locator) is used to record the actual spatial coordinates of the laser cutting head within a preset time period in real time. The preset time period can be set according to actual needs, such as every minute, every five minutes, or after cutting a specific length. According to the cutting operation plan or the preset cutting path, the reference space coordinates at the corresponding moment are obtained. The actual space coordinates and the reference space coordinates are synchronized in time to ensure that the two correspond at the same time point. Based on the coordinate data after time synchronization, the actual movement path and reference movement path of the laser cutting head are drawn. By recording the actual space coordinates of the laser cutting head in real time, the actual movement during the cutting process can be accurately reflected, and the introduction of the reference space coordinates provides a benchmark for the calculation of the cutting length error rate.

[0080] S102: Obtain a cutting length error rate according to the actual moving path and the reference moving path.

[0081] The calculation formula of cutting length error rate is as follows:

[0082]

[0083] Among them, d i represents the Euclidean distance between the actual space coordinate and the reference coordinate at the i-th moment, n is the total number of sampling points in the preset time period, L is the total length of the reference path in the preset time period, and w i is the weight factor. According to the importance or specific requirements of the cutting operation, a weight factor w is assigned to each sampling point. i .

[0084] Specifically, the spatial coordinates d at adjacent moments i The larger the deviation, the greater its contribution to the error rate. The larger the spatial coordinate deviation at adjacent moments, the greater the degree of laser cutting head vibration and the greater the error rate. It should be noted that this weighting method may make the error rate very sensitive to individual large deviations. Therefore, in practical applications, it is necessary to select an appropriate weight factor w according to the specific situation. i The 1 / L in the formula is to normalize the error rate to the length of the entire reference path. It represents the sum of weighted Euclidean distances of all sampling points, reflecting the overall deviation between the actual moving path and the reference moving path. It represents the sum of weight factors of all sampling points and is used to average the weighted Euclidean distance. By introducing weight factors, different parts of the cutting process can be given different degrees of attention according to actual needs, which improves the flexibility of evaluation. By obtaining the cutting length error rate, it provides a reliable data basis for subsequent anomaly detection, cutting quality evaluation and cutting strategy adjustment.

[0085] Calculate the Euclidean distance between the actual spatial coordinates and the reference coordinates of each sampling point within the preset time period. The Euclidean distance is expressed as follows:

[0086]

[0087] Among them, (x i ,y i , z i ) represents the actual spatial coordinates of the laser cutting head at the i-th moment, (x i ′ ,y i ′ , z i ′ ) represents the reference space coordinates of the laser cutting head at the i-th moment.

[0088] Optionally, the step of obtaining the cutting length error rate and laser fluctuation rate of the metal sheet within a preset time period further includes:

[0089] S103 . According to a preset number of power output data collected within a preset time period, obtain the average power and standard deviation of the laser beam within the time period.

[0090] Specifically, within a preset time period, a power monitor is used to collect power output data of the laser source at a certain sampling frequency. Ensure that the amount of power output data collected is sufficient to represent the laser power change within the time period. Calculate the average value of the collected power output data to obtain the average power of the laser beam. Calculate the deviation between the collected power output data and the average power, and calculate the average value of the sum of the squares of these deviations, and then take the square root to obtain the standard deviation.

[0091] S104. Obtain laser fluctuation power according to the average power and the standard deviation.

[0092] Specifically, the ratio of standard deviation to average power is used to indicate the relative fluctuation of laser power output. The laser fluctuation rate reflects the stability of laser power output. The larger the fluctuation rate, the greater the fluctuation of laser power output and the worse the stability. Laser fluctuation power provides an intuitive quantitative indicator for evaluating the stability of laser beam during laser cutting. By monitoring the changes in laser fluctuation power, abnormal fluctuations of the laser source can be discovered in time, providing a basis for subsequent abnormal detection and processing.

[0093] S20. Evaluate an abnormality score according to the cutting length error rate and the laser fluctuation rate.

[0094] Optionally, the step of evaluating the abnormality score according to the cutting length error rate and the laser fluctuation rate includes:

[0095] S201, respectively configuring weight coefficients for the cutting length error rate and the laser fluctuation rate, and obtaining an abnormality score through weighted calculation.

[0096] Specifically, according to the specific requirements and importance of the cutting operation, reasonable weight coefficients are configured for the cutting length error rate and the laser volatility. The size of the weight coefficient reflects the relative importance of the corresponding indicator in the calculation of the abnormality score. Use a weighted calculation formula, such as abnormality score = cutting length error rate × first weight coefficient + laser volatility × second weight coefficient, to calculate the abnormality score, and the sum of the first weight coefficient and the second weight coefficient is equal to one. Ensure that the configuration of the weight coefficient and the weighted calculation process meet actual needs and industry standards to ensure the accuracy and fairness of the evaluation. By configuring weight coefficients for the cutting length error rate and the laser volatility, and weightedly calculating the abnormality score, the impact of the two indicators on the quality of the cutting operation can be comprehensively considered to improve the comprehensiveness and accuracy of the evaluation. The adjustability of the weight coefficient makes the evaluation method more flexible and can adapt to changes in different cutting operation scenarios and needs.

[0097] S202: If the abnormality score is less than a preset threshold, the output cutting length error rate and laser fluctuation rate are within the error range.

[0098] Specifically, a reasonable preset threshold is set as a standard for judging whether the cutting length error rate and laser fluctuation rate are within an acceptable range. When the abnormality score is less than the preset threshold, the system automatically outputs information that the cutting length error rate and laser fluctuation rate are within the error range, indicating that the current cutting operation quality meets the predetermined requirements and cutting can continue without intervention.

[0099] S203: If the abnormality score is greater than the target threshold and less than the preset threshold, mark the preset time as a time period requiring key observation.

[0100] Specifically, a range between the preset threshold and the target threshold is set. This range is within the acceptable range, but can be used as a time period that requires intensive observation. The target threshold is usually lower than the preset threshold and is used to warn of possible abnormalities in advance. When the abnormality score falls within this range, the system automatically marks the current time period as a time period that requires intensive observation and issues a corresponding prompt or alarm. Based on the prompt or alarm, or when the cutting quality deteriorates in the future, the operator can conduct a more detailed review and analysis of the marked time period to promptly discover and resolve potential problems. It can detect and warn of abnormal situations that may occur in the cutting operation in advance, and improve the predictability and initiative of detection.

[0101] S30: If the abnormality score is greater than a preset threshold, image information of the metal sheet is obtained.

[0102] S40: Evaluate the cutting quality score according to the image information.

[0103] Optionally, the step of evaluating the cutting quality score according to the image information comprises:

[0104] S401, preprocessing the front image information and the back image information of the metal plate in the cutting area to obtain a grayscale image.

[0105] Specifically, the front and back images of the metal sheet are read from the image acquisition device or storage medium, and the color image is converted into a grayscale image. The weighted average method is usually used, such as the grayscale formula of the RGB image: Gray = 0.299*R+0.587*G+0.114*B. A filter (such as a Gaussian filter) is applied to remove noise in the image to improve the accuracy of subsequent feature extraction, and the grayscale value is normalized to the range of [0,1] or [0,255] to facilitate subsequent processing.

[0106] S402: Extract the features of the cutting area according to the grayscale image, and obtain the type and degree of the cutting defect.

[0107] Specifically, an edge detection algorithm (such as Canny edge detection) is used to identify the outline of the cutting area. The cutting area can be segmented from the background using methods such as threshold segmentation and region growing. The geometric features (such as length, width, shape, etc.) and texture features (such as grayscale co-occurrence matrix, wavelet transform, etc.) of the cutting area are extracted. Based on the extracted features, machine learning or deep learning models (such as SVM, CNN, etc.) are used to identify the type and degree of cutting defects (such as defect size, depth, etc.). Types of cutting defects include: incomplete cutting defects, the cutting does not completely penetrate the material, and the grayscale value in the back image is significantly higher than that in the front image; burr defects, there are small, sharp protrusions on the cutting edge; smoothness defects, the cutting surface is uneven, and there are obvious texture or edge mutations.

[0108] Some defect detection examples are shown in simplified Python code as follows:

[0109]

[0110]

[0111]

[0112] Optionally, the step of extracting the features of the cutting area according to the grayscale image and obtaining the type and degree of the cutting defect includes:

[0113] The formula for obtaining the degree of defect is as follows:

[0114]

[0115] Among them, w j represents the weight of the jth feature, reflecting the importance of this feature in assessing the degree of defect; f j (·) represents the quantization function corresponding to the jth feature, and the eigenvalue ij is the jth eigenvalue of defect type i, and m represents the number of features.

[0116] The specific form of the quantization function corresponding to the jth feature depends on the nature of the feature and its application in evaluating cutting quality. Specific feature examples are as follows:

[0117] Gray value features:

[0118]

[0119] The above formula is used to describe the overall brightness of the area, N represents the number of pixels in the area, and the gray value i,j,k It represents the gray value of the kth pixel under the jth feature (i.e., gray value feature) of the i-th defect type.

[0120] Gray value statistical characteristics:

[0121]

[0122] The above formula is used to describe the discrete degree of gray value in the region, μ i,j Represents the average gray value in the area.

[0123] Texture features:

[0124]

[0125] The above formula is used to describe the severity of local grayscale changes in an image, L is the grayscale level, P(l,k) represents the element value of the lth row and kth column in the grayscale co-occurrence matrix, and represents the probability of grayscale value l and grayscale value k appearing adjacently.

[0126] S403: According to the cutting defect type, a weight coefficient of the defect degree is configured, and weighted calculation is performed on all the obtained cutting defect types to obtain a cutting quality score.

[0127] Optionally, the step of configuring a weight coefficient of the defect degree according to the cutting defect type, performing weighted calculation on all acquired cutting defect types, and obtaining a cutting quality score includes:

[0128] The formula for the cut quality score is as follows:

[0129]

[0130] Among them, α i is the weight coefficient of the i-th defect type, D i is the defect severity of the ith defect type, and n is the number of defect types.

[0131] Configure a reasonable weight coefficient for each cutting defect type to reflect its impact on the overall cutting quality. Analyze historical data or expert experience to understand the importance of different defect types to cutting quality. Assign a weight coefficient α to each defect type based on the severity of the defect, the frequency of occurrence, and the impact on the performance of the final product. i , ensuring that the sum of the weight coefficients is 1, so that consistency is maintained in subsequent calculations. Based on the cutting quality score, the quality of the cutting operation can be objectively evaluated. Different score intervals can be set, corresponding to different quality levels (such as excellent, good, qualified, unqualified, etc.).

[0132] S50: If the cutting quality score is greater than the target score, the abnormal score misjudgment result is output and the cause of the misjudgment is traced.

[0133] Optionally, if the cutting quality score is greater than the target score, the step of outputting an abnormal score misjudgment result and tracing the cause of the misjudgment includes:

[0134] S501. If the cutting quality score is greater than the target score, an abnormal score misjudgment result is output.

[0135] Specifically, if the cutting quality score is greater than the target score, that is, the quality is within the expected range, and an error occurs in the calculation of the abnormal score, it is marked as an abnormal score misjudgment and the misjudgment result is output immediately.

[0136] S502: According to the abnormal score misjudgment result, whether there is a corresponding historical case record is obtained.

[0137] Specifically, the system queries the historical case record library corresponding to the abnormal score misjudgment result to check whether there are similar or identical misjudgment situations, including the type of misjudgment, cause and solution. Use historical experience to quickly locate the problem and reduce troubleshooting time. It helps to identify repetitive errors and promote continuous improvement and the formulation of preventive measures.

[0138] S503: If there is a corresponding historical case record, obtain historical cutting information according to the historical case record and trace the cause of the misjudgment.

[0139] Specifically, if there is a corresponding historical case, extract the historical cutting information in the case, such as cutting materials, process parameters, equipment status, etc. Compare the similarities and differences between the current cutting operation and the historical case, and analyze the cause of the misjudgment. Record and analyze the cause of the misjudgment to provide a basis for correcting the model or improving the process. Improve the accuracy and efficiency of problem solving through historical case learning. Promote knowledge accumulation and sharing, and reduce the risk of similar misjudgments in the future.

[0140] S504. If there is no corresponding historical case record, check the data acquisition equipment, cutting parameters and processes in sequence to trace the cause of the misjudgment.

[0141] Specifically, if there is no corresponding historical case, start with the data acquisition equipment to check whether the sensors, cameras, etc. are working properly and whether the data is accurate. Then check whether the cutting parameters, such as cutting speed, power, focal length, etc., are set within a reasonable range. Finally, check whether the cutting process, including cutting path planning, material handling, cooling method, etc., meets the specifications. Comprehensively and systematically check the possible causes to ensure that the problem is fundamentally solved.

[0142] S60: If the cutting quality score is less than the target score, the cutting defect type is obtained and the cutting strategy is adjusted.

[0143] If the cutting quality score is less than the target score, the step of obtaining the cutting defect type and adjusting the cutting strategy includes:

[0144] Optionally, if the cutting quality score is less than the target score, the cutting defect type is obtained;

[0145] S601, obtaining the cause of the defect according to the cutting defect type;

[0146] S602: Adjust cutting parameters and / or optimize cutting paths according to the causes of the defects.

[0147] Specifically, according to the types of cutting defects (such as cracks, burrs, incomplete cutting, etc.) pointed out in the cutting quality assessment report, the causes of these defects are further analyzed. The cause analysis may involve multiple aspects such as cutting material characteristics, cutting equipment status, cutting parameter settings, cutting path planning, operator skills, etc. According to the analysis results of the causes of defects, formulate corresponding improvement measures. If the defect is related to cutting parameters (such as cutting speed, power, focal length, etc.), adjust these parameters to a more appropriate range. If the defect is related to cutting path planning, optimize the cutting path, reduce unnecessary turns and overlaps, and improve cutting efficiency and quality. By carefully identifying the defect type and analyzing its cause, and then adjusting the cutting parameters and optimizing the cutting path in a targeted manner, the cutting quality can be significantly improved to meet higher standards of customer needs.

[0148] Example 3

[0149] Based on Example 1, this embodiment provides an automated detection system for metal sheet laser cutting operations, including:

[0150] An error rate and fluctuation rate acquisition module, which is configured to acquire a cutting length error rate and a laser fluctuation rate of a metal sheet within a preset time period;

[0151] an abnormality score evaluation module, configured to evaluate an abnormality score according to the cutting length error rate and the laser fluctuation rate;

[0152] an image information acquisition module, configured to acquire image information of the metal sheet if the abnormality score is greater than a preset threshold;

[0153] a cutting quality score evaluation module, configured to evaluate a cutting quality score according to the image information;

[0154] A traceability module is configured to output an abnormal score misjudgment result if the cutting quality score is greater than the target score, and trace the cause of the misjudgment;

[0155] The cutting strategy adjustment module is configured to obtain the cutting defect type and adjust the cutting strategy if the cutting quality score is less than the target score.

[0156] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. An automated detection method for metal sheet laser cutting operations, characterized in that: include: Obtaining the cutting length error rate and laser fluctuation rate of the metal sheet within a preset time period; evaluating an anomaly score based on the cutting length error rate and the laser fluctuation rate; If the anomaly score is greater than a preset threshold, the image information of the metal sheet is obtained; evaluating a cutting quality score according to the image information; If the cutting quality score is greater than the target score, the abnormal score misjudgment result is output and the cause of the misjudgment is traced; If the cutting quality score is less than the target score, the cutting defect type is obtained and the cutting strategy is adjusted.

2. The automated detection method for metal sheet laser cutting operation according to claim 1, characterized in that: The step of obtaining the cutting length error rate and laser fluctuation rate of the metal sheet within a preset time period includes: According to the actual spatial coordinates of the laser cutting head and the reference spatial coordinates at the corresponding moment, the actual moving path and the reference moving path of the laser cutting head within a preset time period are obtained; According to the actual moving path and the reference moving path, the cutting length error rate is obtained; The calculation formula of cutting length error rate is as follows: Among them, d i represents the Euclidean distance between the actual space coordinate and the reference coordinate at the i-th moment, n is the total number of sampling points in the preset time period, L is the total length of the reference path in the preset time period, and w i is the weight factor.

3. The automated detection method for metal sheet laser cutting operation according to claim 1, characterized in that: The step of obtaining the cutting length error rate and laser fluctuation rate of the metal sheet within a preset time period also includes: According to a preset number of power output data collected within a preset time period, an average power and a standard deviation of the laser beam within the time period are obtained; The laser fluctuation power is obtained according to the average power and the standard deviation.

4. The automated detection method for metal sheet laser cutting operation according to claim 1, characterized in that: The step of evaluating the abnormality score according to the cutting length error rate and the laser fluctuation rate comprises: Configure weight coefficients for the cutting length error rate and the laser fluctuation rate respectively, and obtain an abnormality score through weighted calculation; If the abnormality score is less than the preset threshold, the output cutting length error rate and laser fluctuation rate are within the error range; If the anomaly score is greater than the target threshold and less than the preset threshold, the preset time is marked as a time period that requires special observation.

5. The automated detection method for metal sheet laser cutting operation according to claim 1, characterized in that: The step of evaluating the cutting quality score according to the image information comprises: According to the front image information and the back image information of the metal plate in the cutting area, the front image information and the back image information are preprocessed to obtain a grayscale image; Extracting the features of the cutting area according to the grayscale image to obtain the type and degree of the cutting defect; According to the cutting defect type, a weight coefficient of the defect degree is configured, and a weighted calculation is performed on all the obtained cutting defect types to obtain a cutting quality score.

6. The automated detection method for metal sheet laser cutting operation as claimed in claim 5, characterized in that: The step of extracting the features of the cutting area and obtaining the type and degree of the cutting defect according to the grayscale image comprises: The formula for obtaining the degree of defect is as follows: Among them, w j represents the weight of the jth feature, f j (·) represents the quantization function corresponding to the jth feature, and the eigenvalue ij is the j-th eigenvalue of defect type i.

7. The automated detection method for metal sheet laser cutting operation as claimed in claim 5, characterized in that: The step of configuring a weight coefficient of the defect degree according to the cutting defect type, performing weighted calculation on all the obtained cutting defect types, and obtaining a cutting quality score comprises: The formula for the cut quality score is as follows: Among them, α i is the weight coefficient of the i-th defect type, D i is the defect degree of the ith defect type.

8. The automated detection method for metal sheet laser cutting operation according to claim 1, characterized in that: If the cutting quality score is greater than the target score, the steps of outputting an abnormal score misjudgment result and tracing the cause of the misjudgment include: If the cutting quality score is greater than the target score, an abnormal score misjudgment result is output; According to the abnormal score misjudgment result, obtain whether there is a corresponding historical case record; If so, then based on the historical case records, historical cutting information is obtained to trace the cause of the misjudgment; If not, check the data acquisition equipment, cutting parameters and process in sequence to trace the cause of the misjudgment.

9. The automated detection method for metal sheet laser cutting operation according to claim 1, characterized in that: If the cutting quality score is less than the target score, the step of obtaining the cutting defect type and adjusting the cutting strategy includes: If the cutting quality score is less than the target score, the cutting defect type is obtained; According to the cutting defect type, obtaining the cause of the defect; According to the causes of the defects, the cutting parameters are adjusted and / or the cutting path is optimized.

10. An automated detection system for metal sheet laser cutting operations, characterized in that: include: An error rate and fluctuation rate acquisition module, which is configured to acquire a cutting length error rate and a laser fluctuation rate of a metal sheet within a preset time period; an abnormality score evaluation module, configured to evaluate an abnormality score according to the cutting length error rate and the laser fluctuation rate; an image information acquisition module, configured to acquire image information of the metal sheet if the abnormality score is greater than a preset threshold; a cutting quality score evaluation module, configured to evaluate a cutting quality score according to the image information; A traceability module is configured to output an abnormal score misjudgment result if the cutting quality score is greater than the target score, and trace the cause of the misjudgment; The cutting strategy adjustment module is configured to obtain the cutting defect type and adjust the cutting strategy if the cutting quality score is less than the target score.

Images