Intelligent cutting system for steel plate shearing based on artificial intelligence

Abstract

The invention discloses an intelligent cutting system for steel plate shearing processing based on artificial intelligence, which belongs to the technical field of steel plate processing and comprises an equipment analysis module, a processing analysis module and a shearing module; the equipment analysis module is used for performing performance analysis on steel plate shearing equipment and establishing a processing feature library; the processing analysis module is used for analyzing target drawings and obtaining various shearing sections; and setting representative processing parameters corresponding to various shearing sections; setting corresponding shearing paths according to representative processing parameters corresponding to various shearing sections; generating shearing schemes according to various shearing sections, representative processing parameters and shearing paths; the shearing module is used for shearing steel plates, conveying steel plates to processing locations of steel plate shearing equipment, and positioning and adjusting steel plates; obtaining shearing schemes, and shearing steel plates according to the shearing schemes; and realizing intelligent analysis and intelligent shearing of steel plates through the mutual cooperation among the equipment analysis module, the processing analysis module, the shearing module and the monitoring module, thereby improving work efficiency.

Description

Technical Field

[0001] The present invention belongs to the technical field of steel plate processing, and in particular is an intelligent cutting system for steel plate shearing processing based on artificial intelligence. Background Art

[0002] With the rapid development of the manufacturing industry, steel plate shearing, as an important process, has increasingly higher requirements for production efficiency, product quality and cost control. The traditional steel plate shearing method mainly relies on manual operation and simple mechanical equipment, which has many problems and shortcomings.

[0003] First, in the traditional steel plate shearing process, operators need to manually adjust equipment parameters according to drawings and process requirements to position and cut the steel plates. This method is not only inefficient, but also easily affected by workers' skill level and experience, making it difficult to ensure cutting accuracy and consistency.

[0004] Secondly, existing steel plate shearing equipment often lacks intelligent and automated functions, and is unable to collect and analyze production data in real time, making it difficult to optimize and regulate the production process. This leads to low production efficiency, serious waste of resources, and difficulty in meeting the market's demand for personalized and customized products.

[0005] In addition, with the fluctuation of raw material prices and the intensification of market competition in the steel industry, steel plate shearing processing companies are facing huge cost pressure. Traditional processing methods often make it difficult to reduce costs while ensuring product quality and production efficiency, limiting the competitiveness of companies.

[0006] Therefore, developing an intelligent cutting system for steel plate shearing based on artificial intelligence to realize the automation, intelligence and efficiency of steel plate shearing has become an urgent problem to be solved in the current field of steel plate shearing. Summary of the invention

[0007] In order to solve the problems existing in the above-mentioned solutions, the present invention provides an intelligent cutting system for steel plate shearing based on artificial intelligence.

[0008] The purpose of the present invention can be achieved through the following technical solutions:

[0009] Intelligent steel plate shearing processing system based on artificial intelligence, including equipment analysis module, processing analysis module and shearing module;

[0010] The equipment analysis module is used to perform performance analysis on the steel plate shearing equipment, obtain historical processing data, analyze the historical processing data, determine various shearing features, and the shearing features include shape features, steel plate information and processing parameters; summarize the various shearing features to establish a corresponding shearing feature library;

[0011] Establish corresponding feature recognition models according to each shear feature library;

[0012] Matching corresponding shearing features from a shearing feature library according to the steel plate shearing equipment, and setting corresponding steel plate restriction conditions for each matched shearing feature;

[0013] According to the steel plate shearing equipment, the matching shearing features are simulated to determine whether the processing parameters meet the processing requirements; according to the determination results, the processing parameters are adjusted to obtain new shearing features;

[0014] A processing feature library is established according to each shearing feature and the corresponding steel plate restriction conditions.

[0015] Furthermore, the method for analyzing the historical processing data includes:

[0016] Identify each processing drawing in the historical processing data, and identify the shape features corresponding to each shearing position according to the processing drawings; determine the processing parameters corresponding to each shape feature under the corresponding steel plate information; and integrate each shape feature, steel plate information and processing parameters into a shearing feature.

[0017] Furthermore, the method for determining whether the processing parameters meet the processing requirements includes:

[0018] Establish an effect judgment model, the expression of the effect judgment model is Where: s is the input data;

[0019] The judgment is made through the effect judgment model.

[0020] The processing analysis module is used to analyze the target drawings uploaded by the user, identify the shape features corresponding to each cutting position in the target drawing through the feature recognition model; identify the corresponding steel plate information according to the target drawing; match the corresponding cutting features from the processing feature library according to the shape features and the steel plate information; identify the corresponding processing parameters in the cutting features; merge the cutting positions according to the processing parameters to obtain the cutting segments; and set the representative processing parameters corresponding to the cutting segments;

[0021] A corresponding cutting path is set according to representative processing parameters corresponding to each cutting segment; and a cutting plan is generated according to each cutting segment, representative processing parameters and cutting path.

[0022] Furthermore, the method of merging the shearing positions according to the processing parameters includes:

[0023] Step SA1: Setting a reference point; marking a shearing position adjacent to the reference point as an evaluation point;

[0024] Step SA2: marking the processing parameters corresponding to the reference points as reference parameters, and marking the processing parameters corresponding to the evaluation points as evaluation parameters; performing a difference evaluation on the reference parameters and the evaluation parameters to obtain corresponding processing difference values;

[0025] Step SA3: Mark the cut position adjacent to the merged segment as an evaluation point, and perform a merge evaluation on the merged segment and the evaluation point. When the evaluation meets the merge requirement, the merged segment and the evaluation point are merged; when the evaluation does not meet the merge requirement, the merged segment and the corresponding evaluation point are not merged.

[0026] Step SA4: looping step SA3 until there is no evaluation point that can be merged in the merged segment, marking the merged segment as a cut segment;

[0027] Step SA5: Return to step SA1 until there is no reference point.

[0028] Furthermore, the method for performing differential evaluation on the benchmark parameter and the evaluation parameter includes:

[0029] Identify various shearing features in the processing feature library, classify each shearing feature according to the steel plate information, and obtain feature classification data corresponding to each steel plate information; identify the processing parameters corresponding to each shearing feature in the feature classification data; establish a difference analysis model based on each processing parameter and shape feature;

[0030] Analyze the reference parameters, evaluation parameters and corresponding shape features through the difference analysis model to obtain corresponding initial difference values;

[0031] Collect environmental data according to each preset environmental factor to obtain environmental analysis data, analyze the environmental analysis data to obtain the corresponding environmental correction coefficient;

[0032] The initial difference value is marked as CL; the environmental correction factor is marked as η;

[0033] The corresponding processing difference value is calculated according to the formula PK=η×CL; wherein: PK is the processing difference value.

[0034] Furthermore, the method for setting the representative processing parameters of each shearing segment includes:

[0035] Identify the processing parameters corresponding to each shearing position in the shearing section, and determine the positioning coordinate set of each shearing position;

[0036] Generate a positioning curve corresponding to each shearing position according to the positioning coordinate set of each shearing position; fit the positioning curve to obtain a corresponding curve function, and mark the curve function as Q(z);

[0037] According to the formula Calculate the shear value corresponding to each shear position;

[0038] Where: PU is the shear value;

[0039] The processing parameter corresponding to the shearing position with the smallest shearing value is marked as the representative processing parameter.

[0040] The shearing module is used to shear the steel plate, transport the steel plate to the processing location of the steel plate shearing equipment, and perform positioning adjustment on the steel plate; obtain a shearing plan, and shear the steel plate according to the obtained shearing plan.

[0041] Furthermore, it also includes a monitoring module, which is used to monitor when the steel plate is sheared; obtain corresponding monitoring data in real time; obtain an effect judgment model, analyze the monitoring data through effect judgment, and judge whether the monitoring is abnormal;

[0042] When the monitoring is judged to be normal, no corresponding operation is performed;

[0043] When monitoring abnormalities are detected, early warning processing is performed according to the preset early warning method.

[0044] Compared with the prior art, the present invention has the following beneficial effects:

[0045] Through the cooperation between the equipment analysis module, processing analysis module, shearing module and monitoring module, intelligent analysis and intelligent shearing of steel plates can be realized; work efficiency can be improved; by setting up the equipment analysis module, a full analysis of the steel plate shearing equipment can be achieved, a feature recognition model and a processing feature library can be established, and the corresponding processing plan can be quickly determined according to the processing drawings uploaded by the user, so as to achieve rapid shearing of steel plates. By setting up the processing analysis module, the corresponding shearing plan can be intelligently generated according to the target drawings uploaded by the user, and intelligent processing can be realized; it is convenient to reduce the burden on employees. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0047] Figure 1 This is a principle block diagram of the present invention;

[0048] Figure 2 This is an example diagram of this shape feature. DETAILED DESCRIPTION

[0049] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. 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.

[0050] like Figure 1 to Figure 2 As shown, the intelligent cutting system for steel plate shearing processing based on artificial intelligence includes equipment analysis module, processing analysis module, shearing module and monitoring module;

[0051] The equipment analysis module is used to perform performance analysis on the steel plate shearing equipment. This module is mainly used by the equipment manufacturer to perform usage analysis, making full use of the numerous test data of the equipment manufacturer to fully analyze the shearing performance of the steel plate shearing equipment, so as to facilitate the subsequent intelligent generation of shearing plans according to the shape to be sheared and the material, size and other information of the steel plate, and realize intelligent processing; the specific process is as follows:

[0052] Obtain historical processing data during the steel plate shearing operation, the historical processing data includes various related data such as processing drawings, steel plate information, processing parameters, etc.; analyze the historical processing data, count the various shearing features, summarize the obtained shearing features, and establish a corresponding shearing feature library; the shearing feature library is set at the equipment side; the equipment manufacturer determines the various shearing features that can be achieved by the steel plate processing equipment and the steel plate restriction conditions corresponding to each shearing feature based on its performance requirements for the steel plate processing equipment, because even the same shearing feature may not be processed on steel plates of certain types, thicknesses, etc. due to the performance differences of the steel plate shearing equipment; therefore, it is necessary to set the corresponding steel plate restriction conditions according to the actual design performance of the steel plate shearing equipment;

[0053] The steel plate shearing equipment is used to simulate and adjust each selected shearing feature, that is, the steel plate with the corresponding steel plate information is sheared by the steel plate shearing equipment of this type at the equipment manufacturer, and the processing parameters corresponding to each shape feature are used for processing. It is judged whether the requirements are met based on the processing results, and the processing parameters are adjusted based on the judgment results to form new shearing features. Exemplarily, a corresponding effect judgment model is established based on the possible processing effects to judge whether the processing effects meet the processing requirements; the processing requirements are set by the equipment manufacturer; the expression is Where: s is the input data, that is, the processing effect of applying the processing parameters, which is generally judged by image acquisition and image recognition technology; and judged by the effect judgment model.

[0054] A processing feature library is established by combining the shearing features and steel plate restriction conditions of each setting; the processing feature library is set in the steel plate shearing equipment.

[0055] Among them, the methods for analyzing historical processing data include:

[0056] Identify each processing drawing in the historical processing data, and obtain the processing parameters corresponding to each cutting position in the processing drawing; identify the shape features corresponding to each cutting position according to the processing drawing, such as the front and rear adjacent straight line cutting, the front point arc and the rear point straight line, and other shape features set according to the shape of the graphic; for example, Figure 2 As shown, segment AB is a straight line segment, and the shape features are the same when point A is not included. Point A is an inflection point, which is different from both B and C. Each shape feature is mainly set according to the processing shape of its drawing, and the specific description and representation form can be adjusted as needed. According to the definition of shape features, each processing drawing is compared manually to form a corresponding training set, which includes input data and output data. The input data is the drawing information at each cutting position, and the output data is the shape feature of the cutting position. A corresponding feature recognition model is established based on a neural network such as a CNN network or a DNN network, and training is performed using the established training set. The feature recognition model after successful training is used for subsequent use, mainly for subsequent recognition and analysis of drawings uploaded by users.

[0057] Determine the processing parameters under different steel plate information according to the processing parameters corresponding to each shape feature. Multiple processing drawings will have multiple processing parameters. Select the processing parameters with the best processing effect as the processing parameters determined under the processing parameters and steel plate information.

[0058] The various shape features, steel plate information and processing parameters are integrated into shear features.

[0059] By setting up the equipment analysis module, we can fully analyze the steel plate shearing equipment, establish a feature recognition model and a processing feature library, and quickly determine the corresponding processing plan based on the processing drawings uploaded by the user to achieve rapid shearing of the steel plate.

[0060] The processing analysis module is used to analyze the processing drawings uploaded by the user, mark the processing drawings uploaded by the user as target drawings in order to distinguish them from previous processing drawings; identify the shape features corresponding to each cutting position in the target drawing through the feature recognition model; identify the corresponding steel plate information according to the target drawing, such as the type, specification, size and other related information of the steel plate; match the corresponding cutting features from the processing feature library according to the shape features and the steel plate information; identify the corresponding processing parameters in the cutting features; merge the cutting positions according to the processing parameters to obtain the cutting segments; and set the representative processing parameters corresponding to the cutting segments;

[0061] The corresponding cutting path is set according to the representative processing parameters corresponding to each cutting segment; after the processing parameters of each position are determined, the specific cutting path can be determined according to the existing technology; and a cutting plan is generated according to each cutting segment, the representative processing parameters and the cutting path.

[0062] Methods for merging the shearing positions according to the processing parameters include:

[0063] Step SA1: Setting a reference point, selecting one or more cutting positions as reference points in an optional manner, or setting the reference points in other preset manners; marking the cutting positions adjacent to the reference points as evaluation points;

[0064] Step SA2: Mark the processing parameters corresponding to the reference points as reference parameters, and mark the processing parameters corresponding to the evaluation points as evaluation parameters; perform difference evaluation on the reference parameters and the evaluation parameters to obtain corresponding processing difference values; merge the reference points and the evaluation points whose processing difference values ​​are less than the threshold value X1 to obtain a merged segment; if there are no evaluation points that can be merged, they are independently used as cut segments;

[0065] Methods for differential evaluation of baseline parameters and evaluation parameters include:

[0066] Identify various shear features in the processing feature library, classify each shear feature according to the steel plate information, and obtain the feature classification data corresponding to each steel plate information; identify the processing parameters corresponding to each shear feature in the feature classification data; simulate the simulation records of the matching shear features by the steel plate shearing equipment in the equipment analysis module, and obtain the processing effect change data of each processing parameter under each shape feature; set the corresponding initial difference value according to the processing effect change data, and the value range of the initial difference value is [0, 10], 0 represents no effect difference, 10 represents the initial difference value corresponding to the maximum effect difference that may occur, and then determine the effect change critical state corresponding to the initial difference value. The initial difference value sets the corresponding threshold value X1, indicating that the degree of change of the effect makes it impossible to apply the processing parameters to process the shape feature; a corresponding training set is established in the above manner, and the training set includes input data and output data, the input data is two shape features and two processing parameters; the output data is the largest initial difference value; because the initial difference values ​​that may be obtained are different based on any one of the two shape features, therefore, the largest initial difference value is selected for output 2; a corresponding difference analysis model is established based on a CNN network or a DNN network, and training is performed through the established training set, and analysis is performed through the difference analysis model after successful training.

[0067] Acquire environmental factors that have an impact on the shearing process, collect environmental data according to each environmental factor, obtain environmental analysis data, analyze the environmental analysis data, and obtain corresponding environmental correction coefficients for correcting the initial difference value; specifically, set the degree of impact of different environments on the shearing process, and the value range is [0.8, 1.3]; exemplarily, establish a corresponding environmental analysis model based on a CNN network or a DNN network, and manually establish a corresponding training set for training, the training set includes input data and output data, the input data is the environmental analysis data, and the output data is the environmental correction coefficient; analyze the environmental analysis model after successful training to obtain the corresponding environmental correction coefficient.

[0068] The obtained initial difference value is marked as CL; the environmental correction factor is marked as η;

[0069] The corresponding processing difference value is calculated according to the formula PK=η×CL; wherein: PK is the processing difference value.

[0070] Step SA3: Mark the cut position adjacent to the merged segment as an evaluation point, and perform a merge evaluation on the merged segment and the evaluation point. When the evaluation meets the merge requirement, the merged segment and the evaluation point are merged; when the evaluation does not meet the merge requirement, the merged segment and the corresponding evaluation point are not merged.

[0071] The method for merging and evaluating the merged segment and the evaluation point is:

[0072] The processing difference values ​​between the evaluation point and the processing parameters corresponding to each position in the merged segment are calculated one by one, and the maximum processing difference value is compared with the threshold value X1 to obtain the corresponding evaluation result.

[0073] Step SA4: looping step SA3 until there is no evaluation point that can be merged in the merged segment, marking the merged segment as a cut segment;

[0074] Step SA5: Return to step SA1 until there is no reference point.

[0075] The method for setting the representative processing parameters of each shearing segment includes:

[0076] Identify the processing parameters corresponding to each shearing position in the shearing section, and determine the positioning coordinate set of each shearing position; the positioning coordinate set is composed of the positioning coordinates corresponding to the shearing position and other shearing positions, the horizontal axis of the positioning coordinates represents the serial numbers of other shearing positions, which are sorted according to the shearing order, and the serial number of a shearing position for comparative analysis is deducted; the vertical axis represents the corresponding processing difference value;

[0077] Generate a positioning curve corresponding to each shearing position according to the positioning coordinate set of each shearing position; fit the positioning curve to obtain a corresponding curve function, and mark the curve function as Q(z);

[0078] According to the formula Calculate the shear value corresponding to each shear position; where PU is the shear value; mark the processing parameter corresponding to the shear position with the smallest shear value as the representative processing parameter.

[0079] By setting up a processing analysis module, it is possible to intelligently generate corresponding cutting plans based on the target drawings uploaded by the user, thus achieving intelligent processing and facilitating the reduction of employee burden.

[0080] The shearing module is used to shear the steel plate, transport the steel plate to the processing location of the steel plate shearing equipment, and perform positioning adjustment on the steel plate; obtain a shearing plan, and shear the steel plate according to the obtained shearing plan.

[0081] In one embodiment, due to the influence of various factors, when an abnormal situation occurs, it may not be discovered in time because of intelligent shearing, which easily leads to waste of resources; therefore, in this embodiment, on the basis of the above shearing, the shearing process of the steel plate is monitored in real time; the specific process is as follows:

[0082] Setting a monitoring module, which is used to monitor the steel plate when it is sheared, and obtain corresponding monitoring data, generally using image monitoring; obtaining an effect judgment model, analyzing the monitoring data through effect judgment, and judging whether the monitoring is abnormal, that is, failure to meet the processing requirements is regarded as a monitoring abnormality;

[0083] When the monitoring is judged to be normal, no corresponding operation is performed;

[0084] When monitoring abnormalities are detected, early warning processing is performed according to the preset early warning method.

[0085] In other embodiments, corresponding intelligent technologies may be combined to perform intelligent analysis on abnormal situations, and the shearing process may be adjusted accordingly.

[0086] The above formulas are all calculated by removing dimensions and taking numerical values. The formula is a formula that is closest to the actual situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained by simulating a large amount of data.

[0087] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. Intelligent cutting system for steel plate shearing based on artificial intelligence, characterized by: It includes equipment analysis module, processing analysis module and shearing module; The equipment analysis module is used to perform performance analysis on the steel plate shearing equipment, obtain historical processing data, analyze the historical processing data, determine various shearing features, and the shearing features include shape features, steel plate information and processing parameters; summarize the various shearing features to establish a corresponding shearing feature library; Establish corresponding feature recognition models according to each shear feature library; Matching corresponding shearing features from a shearing feature library according to the steel plate shearing equipment, and setting corresponding steel plate restriction conditions for each matched shearing feature; According to the steel plate shearing equipment, the matching shearing features are simulated to determine whether the processing parameters meet the processing requirements; according to the determination results, the processing parameters are adjusted to obtain new shearing features; Establish a processing feature library according to each shearing feature and the corresponding steel plate restriction conditions; The processing analysis module is used to analyze the target drawings uploaded by the user, identify the shape features corresponding to each cutting position in the target drawing through the feature recognition model; identify the corresponding steel plate information according to the target drawing; match the corresponding cutting features from the processing feature library according to the shape features and the steel plate information; identify the corresponding processing parameters in the cutting features; merge the cutting positions according to the processing parameters to obtain the cutting segments; and set the representative processing parameters corresponding to the cutting segments; Set a corresponding cutting path according to the representative processing parameters corresponding to each cutting segment; generate a cutting plan according to each cutting segment, the representative processing parameters and the cutting path; The shearing module is used to shear the steel plate, transport the steel plate to the processing location of the steel plate shearing equipment, and perform positioning adjustment on the steel plate; obtain a shearing plan, and shear the steel plate according to the obtained shearing plan.

2. The intelligent cutting system for steel plate shearing based on artificial intelligence according to claim 1 is characterized in that: Methods for analyzing historical processing data include: Identify each processing drawing in the historical processing data, and identify the shape features corresponding to each shearing position according to the processing drawings; determine the processing parameters corresponding to each shape feature under the corresponding steel plate information; and integrate each shape feature, steel plate information and processing parameters into a shearing feature.

3. The intelligent cutting system for steel plate shearing based on artificial intelligence according to claim 1 is characterized in that: Methods for judging whether processing parameters meet processing requirements include: Establish an effect judgment model, the expression of the effect judgment model is ;Where: s is the input data; The judgment is made through the effect judgment model.

4. The intelligent cutting system for steel plate shearing based on artificial intelligence according to claim 1 is characterized in that: Methods for merging the shearing positions according to the processing parameters include: Step SA1: Setting a reference point; marking a shearing position adjacent to the reference point as an evaluation point; Step SA2: marking the processing parameters corresponding to the reference points as reference parameters, and marking the processing parameters corresponding to the evaluation points as evaluation parameters; performing a difference evaluation on the reference parameters and the evaluation parameters to obtain corresponding processing difference values; Step SA3: marking the cut position adjacent to the merged segment as an evaluation point, and merging the merged segment and the evaluation point for evaluation; When the evaluation meets the merging requirements, the merged segment is merged with the evaluation point; When the assessment does not meet the merging requirements, the merging between the merged segment and the corresponding assessment point is not performed; Step SA4: looping step SA3 until there is no evaluation point that can be merged in the merged segment, marking the merged segment as a cut segment; Step SA5: Return to step SA1 until there is no reference point.

5. The intelligent cutting system for steel plate shearing based on artificial intelligence according to claim 4 is characterized in that: Methods for differential evaluation of baseline parameters and evaluation parameters include: Identify various shearing features in the processing feature library, classify each shearing feature according to the steel plate information, and obtain feature classification data corresponding to each steel plate information; identify the processing parameters corresponding to each shearing feature in the feature classification data; establish a difference analysis model based on each processing parameter and shape feature; Analyze the reference parameters, evaluation parameters and corresponding shape features through the difference analysis model to obtain corresponding initial difference values; Collect environmental data according to each preset environmental factor to obtain environmental analysis data, analyze the environmental analysis data to obtain the corresponding environmental correction coefficient; The initial difference value is marked as CL; the environmental correction factor is marked as η; The corresponding processing difference value is calculated according to the formula PK=η×CL; wherein: PK is the processing difference value.

6. The intelligent cutting system for steel plate shearing based on artificial intelligence according to claim 1 is characterized in that: The method for setting the representative processing parameters of each shearing segment includes: Identify the processing parameters corresponding to each shearing position in the shearing section, and determine the positioning coordinate set of each shearing position; Generate a positioning curve corresponding to each shearing position according to the positioning coordinate set of each shearing position; fit the positioning curve to obtain a corresponding curve function, and mark the curve function as Q(z); According to the formula Calculate the shear value corresponding to each shear position; Where: PU is the shear value; z is the shear position number, t is the time; The processing parameter corresponding to the shearing position with the smallest shearing value is marked as the representative processing parameter.

7. The intelligent cutting system for steel plate shearing based on artificial intelligence according to claim 1 is characterized in that: It also includes a monitoring module, which is used to monitor the steel plate when it is sheared; obtain corresponding monitoring data in real time; obtain an effect judgment model, analyze the monitoring data through effect judgment, and judge whether the monitoring is abnormal; When the monitoring is judged to be normal, no corresponding operation is performed; When monitoring abnormalities are detected, early warning processing is performed according to the preset early warning method.

Images