A laser cutting machine online monitoring and fault diagnosis method and system

Abstract

The present invention relates to the technical field of laser cutting machine fault diagnosis, and discloses a method and system for online monitoring and fault diagnosis of laser cutting machines, wherein the method comprises: collecting working status information of the laser cutting machine, constructing a working status feature vector, using a Stacking ensemble learning method to construct a laser cutting machine fault prediction model to predict the fault type and its occurrence probability, and generating a 3D model of the laser cutting machine for dynamic visualization fault warning; compared with the prior art, especially when facing multi-dimensional sensor data and various fault types, the technical problem of being unable to effectively process complex data combinations and having poor fault prediction accuracy, the present invention, by combining a machine learning model and a Stacking ensemble learning method, can efficiently classify and predict faults, and accurately determine whether the laser cutting machine has potential faults, thereby avoiding the problem of the traditional method being unable to perform accurate fault warnings in real time.

Description

Technical Field

[0001] The present invention belongs to the technical field of laser cutting machine fault diagnosis, and in particular relates to a laser cutting machine online monitoring and fault diagnosis method and system. Background Art

[0002] Laser cutting machines are currently widely used in the manufacturing industry, particularly in scenarios requiring high-precision and high-efficiency cutting. However, laser cutting machines inevitably encounter various problems during long-term operation, leading to equipment failure and downtime, which in turn impacts production efficiency and product quality. Existing fault diagnosis methods for laser cutting machines mostly rely on regular maintenance, manual inspections, or simple sensor monitoring. These methods suffer from several drawbacks: Fault warnings are delayed, with most existing technologies only providing alerts after a fault has occurred, failing to detect potential failure risks before they occur. For example, issues such as laser power fluctuations and manipulator overloads are often not detected until the equipment is severely damaged, resulting in low production efficiency and equipment damage. Data analysis accuracy is low, as existing monitoring methods typically rely on single-sensor data and are unable to effectively integrate data from multiple sensors for comprehensive analysis. For example, analyzing data solely from laser power or temperature sensors makes it difficult to accurately predict the overall health of the equipment, especially during high-load operation, when complex interactions exist between various components. Furthermore, traditional methods struggle to process multidimensional data, as they often struggle to handle the interactions between data from multiple sensors and equipment status, which compromises the accuracy of fault diagnosis. In practical applications, the operating status of laser cutting machines is affected by multiple factors, including laser power, cutting area temperature, robot vibration, conveyor belt load, etc.; traditional fault diagnosis methods are highly dependent on manual intervention, and operators are required to make decisions based on the results of manual inspections, which often lead to human errors. Therefore, there is an urgent need for an online monitoring and fault diagnosis method and system for laser cutting machines. This method can combine multi-dimensional sensor data and intelligent fault diagnosis methods to monitor the operating status of laser cutting machines in real time under complex working environments, and accurately predict faults through intelligent analysis before they occur, thereby improving production efficiency and equipment reliability. Summary of the Invention

[0003] In response to the above-mentioned technical deficiencies, the purpose of the present invention is to propose an online monitoring and fault diagnosis method for a laser cutting machine, aiming to solve the technical problems in the existing technology, especially when facing multi-dimensional sensor data and various fault types, such as the inability to effectively process complex data combinations and poor fault prediction accuracy.

[0004] In order to solve the above technical problems, the present invention adopts the following technical solutions: The present invention provides a method for online monitoring and fault diagnosis of a laser cutting machine.

[0005] The laser cutting machine online monitoring and fault diagnosis method includes:

[0006] Step S10: The working status information of the laser cutting machine is collected in real time by a sensor installed in the core part of the laser cutting machine, and the working status information is transmitted to a pre-built cloud database through the Ajax protocol;

[0007] Step S20: Obtaining working status information from the cloud database, constructing a normalization processing function, a Fourier transform function, and a sliding window average function to process the working status information to obtain a working status feature vector;

[0008] Step S30: constructing a first laser cutting machine fault prediction model using a support vector machine algorithm SVM, constructing a second laser cutting machine fault prediction model using a random forest algorithm RF, and using a stacking ensemble learning method to use the outputs of the SVM and RF as new features to construct a third laser cutting machine fault prediction model;

[0009] Step S40: training the third laser cutting machine fault prediction model, using the working state feature vector as the trained model input to obtain the fault type and its occurrence probability;

[0010] Step S50: Generate a 3D model of the laser cutting machine using PyThreeJS, and perform visual warning in the 3D model according to the fault type and its probability of occurrence.

[0011] Preferably, in step S30, the first laser cutting machine fault prediction model The formula is:

[0012]

[0013] in, is the working state feature vector, N is the number of samples in the preset model training, is the working state feature vector of sample i during the preset model training, is the fault label during the preset model training. For radial basis functions, To control the coefficient of each sample's influence on classification, is the preset bias term, is the activation function; model The output is the fault type, and the probability of the fault occurring is obtained through Platt scaling , ,in, and are parameters obtained through training.

[0014] Preferably, in step S30, the second laser cutting machine fault prediction model The formula is:

[0015]

[0016] in, is the prediction result of the working state feature vector of the preset j-th decision tree; model The output is the fault type, and the probability of the fault occurring is obtained through the probabilistic model ,in, It is the Sigmoid function, which is used to convert the output of the tree into a probability value.

[0017] Preferably, in step S30, the third laser cutting machine fault prediction model The formula is:

[0018]

[0019] in, and Fault prediction model for the third laser cutting machine The weights used to weight the SVM and RF outputs.

[0020] Preferably, in step S50, the fault types include abnormal laser power fluctuation, abnormal robot vibration, abnormal conveyor belt vibration and abnormal temperature fluctuation in the cutting area; the step of using PyThreeJS to generate a 3D model of the laser cutting machine specifically includes: installing and importing the PyThreeJS library, creating a scene and a renderer, generating the laser source, robot and conveyor belt data of the laser cutting machine, adding the laser source, robot and conveyor belt data of the laser cutting machine to the scene, using the renderer to render the 3D scene to the browser, and using the animation loop function in combination with the working status information in the cloud database in step S10 to update the 3D model in real time.

[0021] Preferably, in step S10, the working status information includes the output power of the laser source, the temperature of the cutting area, the vibration data of the robot, and the vibration data of the conveyor belt.

[0022] Preferably, in step S20, the working state characteristic vector includes the stability characteristic of the laser power, the vibration frequency characteristic of the robot, the vibration frequency characteristic of the conveyor belt, and the temperature fluctuation characteristic of the cutting area.

[0023] The present invention also provides a laser cutting machine online monitoring and fault diagnosis system comprising:

[0024] The data acquisition and transmission module is used to collect the working status information of the laser cutting machine in real time through sensors installed in the core part of the laser cutting machine, and transmit the working status information to a pre-built cloud database through the Ajax protocol;

[0025] The data processing and feature construction module is used to obtain working status information from the cloud database, construct a normalization processing function, a Fourier transform function, and a sliding window average function to process the working status information to obtain a working status feature vector;

[0026] A fault prediction model construction module is used to construct a first laser cutting machine fault prediction model using a support vector machine algorithm (SVM), a second laser cutting machine fault prediction model using a random forest algorithm (RF), and a third laser cutting machine fault prediction model using a stacking ensemble learning method with the outputs of the SVM and RF as new features;

[0027] The model training and fault diagnosis module is used to train the fault prediction model of the third laser cutting machine, and use the working state feature vector as the input of the trained model to obtain the fault type and its occurrence probability;

[0028] The 3D visualization and fault warning module is used to generate a 3D model of the laser cutting machine using PyThreeJS, and to provide visual warnings in the 3D model based on the fault type and its probability of occurrence.

[0029] The present invention also provides a computer program product, including a laser cutting machine online monitoring and fault diagnosis program, which implements the laser cutting machine online monitoring and fault diagnosis method when executed by a processor.

[0030] The beneficial effects of the present invention are as follows: compared with the technical problems of the prior art, especially when faced with multi-dimensional sensor data and diverse fault types, which are unable to effectively process complex data combinations and have poor fault prediction accuracy, the present invention, by combining a machine learning model, can accurately classify and predict multi-dimensional sensor data. Especially when there are diverse fault types, the machine learning model can effectively learn the characteristics of each fault type, thereby improving the accuracy of the prediction;

[0031] The stacking method of the present invention can make up for the shortcomings of a single model and improve the overall accuracy of fault prediction by combining multiple different machine learning models; BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. 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 any creative work.

[0033] Figure 1 This is a flow chart of a first embodiment of a method for online monitoring and fault diagnosis of a laser cutting machine according to the present invention.

[0034] Figure 2 This is a schematic diagram of equipment for an online monitoring and fault diagnosis method for a laser cutting machine according to the present invention. DETAILED DESCRIPTION

[0035] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0036] Example 1: Figure 1 FIG. 1 is a flow chart of a first embodiment of a method for online monitoring and fault diagnosis of a laser cutting machine according to the present invention, and provides a first embodiment of a method for online monitoring and fault diagnosis of a laser cutting machine according to the present invention.

[0037] In a first embodiment, the laser cutting machine online monitoring and fault diagnosis method includes:

[0038] Step S10: The working status information of the laser cutting machine is collected in real time by a sensor installed in the core part of the laser cutting machine, and the working status information is transmitted to a pre-built cloud database through the Ajax protocol;

[0039] It should be noted that in step S10, the operating status information includes the output power of the laser source, the temperature of the cutting area, the vibration data of the robot arm, and the vibration data of the conveyor belt. The Ajax protocol is an asynchronous data transmission method based on the HTTP protocol. It can realize real-time data exchange between the client and the cloud database, especially during the operation of the laser cutting machine, ensuring the timeliness and accuracy of the data.

[0040] It's understandable that the laser source's output power reflects the cutting capability and stability of the laser cutting machine. Excessive temperatures in the cutting zone can affect cutting quality. Excessive vibration can be a warning sign of a robot jam or overload. Abnormal conveyor belt vibration can lead to delayed waste collection or conveyor belt jams. The data collected in real time by these sensors is transmitted to a cloud database via the Ajax protocol for subsequent data analysis and fault diagnosis.

[0041] Step S20: Obtaining working status information from the cloud database, constructing a normalization processing function, a Fourier transform function, and a sliding window average function to process the working status information to obtain a working status feature vector;

[0042] It should be noted that, in step S20, the working state characteristic vector includes the stability characteristics of the laser power, the vibration frequency characteristics of the robot, the vibration frequency characteristics of the conveyor belt, and the temperature fluctuation characteristics of the cutting area.

[0043] It's understandable that the operating status feature vector is derived by processing and analyzing sensor data. This processed feature vector accurately reflects the operating status of the laser cutting machine. The operating status feature vector includes information from multiple dimensions, which can help accurately predict equipment failures, determine the type of failure, and determine the probability of failure.

[0044] It should be understood that the normalization function, Fourier transform function, and sliding window averaging function are used to extract meaningful features from the raw data, ensuring that the subsequent fault diagnosis model can obtain reliable input data. By applying these functions, noise interference can be effectively reduced and the accuracy of fault prediction can be improved.

[0045] For example, during the operation of a laser cutting machine, the laser power may fluctuate due to different cutting materials or aging of the laser source. At this time, the stability characteristics of the laser power can help detect whether there is power instability; the characteristics of the robot's vibration frequency extracted through Fourier transform can reveal whether the robot is stuck or overloaded; the vibration frequency characteristics of the conveyor belt can help identify whether there is a problem of jamming or abnormal wear of the conveyor belt; the temperature fluctuation characteristics of the cutting area can help detect whether there is a temperature anomaly, so as to determine whether it will affect the cutting quality or cause equipment damage.

[0046] Step S30: constructing a first laser cutting machine fault prediction model using a support vector machine algorithm SVM, constructing a second laser cutting machine fault prediction model using a random forest algorithm RF, and using a stacking ensemble learning method to use the outputs of the SVM and RF as new features to construct a third laser cutting machine fault prediction model;

[0047] It should be noted that in step S30, the first laser cutting machine fault prediction model The formula is:

[0048]

[0049] in, is the working state feature vector, N is the number of samples in the preset model training, is the working state feature vector of sample i during the preset model training, is the fault label during the preset model training. For radial basis functions, To control the coefficient of each sample's influence on classification, is the preset bias term, is the activation function; model The output is the fault type, and the probability of the fault occurring is obtained through Platt scaling , ,in, and are parameters obtained through training.

[0050] In step S30, the second laser cutting machine fault prediction model The formula is:

[0051]

[0052] in, is the prediction result of the working state feature vector of the preset j-th decision tree; model The output is the fault type, and the probability of the fault occurring is obtained through the probabilistic model ,in, It is the Sigmoid function, which is used to convert the output of the tree into a probability value.

[0053] In step S30, the third laser cutting machine fault prediction model The formula is:

[0054]

[0055] in, and Fault prediction model for the third laser cutting machine The weights used to weight the SVM and RF outputs.

[0056] It's easy to understand that by employing the stacking ensemble learning method, the outputs of the SVM and RF models (i.e., their fault state predictions) are fed into a meta-learning model (such as logistic regression or a neural network) as new features, further combining the strengths of both SVM and RF. The stacking method ensures the independence of each basic learner while leveraging their strengths. By combining multiple predictions, the accuracy of the final prediction is improved.

[0057] For example, suppose the operating state feature vector of a laser cutting machine includes features such as laser power fluctuations, robot vibration frequency, conveyor belt vibration frequency, and cutting area temperature. When using SVM, the model may determine whether a fault has occurred based on laser power fluctuations and robot vibration frequency; when using RF, the model may rely on conveyor belt vibration frequency and temperature fluctuations for prediction. Through the Stacking method, the outputs of SVM and RF (such as the predicted probability of failure) are input into the meta-learning model as new features, thereby obtaining more accurate fault prediction results. For example, if the SVM model predicts an 80% probability of laser power fluctuation failure and the RF model predicts a 75% probability of robot jamming failure, the Stacking model will combine these two predicted values ​​and derive the final fault probability prediction through weighted averaging or other methods.

[0058] Step S40: training the third laser cutting machine fault prediction model, using the working state feature vector as the trained model input to obtain the fault type and its occurrence probability;

[0059] As you can understand, the training process involves using historical datasets, including data from normal conditions and different fault types. This data is used to train the stacking model, which optimizes prediction accuracy by combining the outputs of the SVM and RF models. During training, cross-validation and other methods are used to ensure model stability and generalization, enabling the model to adapt to future fault diagnosis under different operating conditions.

[0060] It should be understood that the prediction results of fault type and probability are derived by the model's analysis and calculation of the input feature vector. The model output includes the fault type and the probability of the fault occurring, typically a value between 0 and 1, indicating the likelihood of the fault occurring.

[0061] For example, the working state characteristic vector obtained by step S20 includes the stability characteristic of the laser power , vibration frequency characteristics of the manipulator , Conveyor belt vibration frequency characteristics and temperature fluctuation characteristics of the cutting area These features are input into the Stacking ensemble learning model for training. The model learns the relationship between different fault modes (for example, laser power fluctuation and manipulator jamming) and these features based on historical data. The trained model can predict the fault type and its probability of occurrence in real time. For example, when the input new working state feature vector is: laser power fluctuation , robot vibration frequency 1.2. Conveyor belt vibration frequency , Temperature fluctuation in cutting area ,The model may predict the fault type of “laser power fluctuation” and output the ,probability of the fault occurring as 85%, prompting the operator that there may be ,problems with the laser power and needs to be checked.

[0062] Step S50: Generate a 3D model of the laser cutting machine using PyThreeJS, and perform visual warning in the 3D model according to the fault type and its probability of occurrence.

[0063] It's important to note that this step uses the PyThreeJS library to generate a 3D visualization model of the laser cutting machine. PyThreeJS allows you to create interactive 3D graphics in a web environment, displaying the various components of the laser cutting machine (such as the laser source, manipulator, and conveyor belt) within the model. The status of each component can be dynamically updated through color changes, animation effects, and other methods based on the type and probability of failure, providing intuitive early warning information to the operator.

[0064] It should be understood that the generated 3D model is not just a static display tool, but a dynamic interactive interface tightly integrated with the fault prediction system. The colors, animations, and labels within the 3D model change based on the predicted fault type, providing real-time feedback to help operators understand the cutting machine's operating status and potential problems. Specifically, laser power fluctuations, abnormal robot vibration, or conveyor belt load issues are all reflected in the 3D model.

[0065] For example, during the operation of a laser cutting machine, the laser power sensor detects laser power fluctuations, and according to the prediction of the machine learning model, the probability of failure is 85%. In the 3D model, the laser source part will automatically turn red to indicate the high failure risk of this component. Similarly, if the probability of failure of the robot vibration is 90%, the robot part will also turn red to remind the operator to check. If the probability of failure is low, the model component will continue to appear green or blue, indicating its normal operating status. In addition, the operator can interact with the 3D interface, rotate and zoom the view, view the status of each component, and troubleshoot according to the report content.

[0066] Embodiment 2: In addition, the present invention provides an online monitoring and fault diagnosis system for a laser cutting machine, which adopts the online monitoring and fault diagnosis method for a laser cutting machine in the above embodiment, and can solve the technical problem of online monitoring and fault diagnosis for a laser cutting machine. Compared with the existing technology, the beneficial effects of the online monitoring and fault diagnosis system for a laser cutting machine provided by the present invention are the same as the beneficial effects of the online monitoring and fault diagnosis method for a laser cutting machine provided by the above embodiment, and the other technical features of the online monitoring and fault diagnosis system for a laser cutting machine are the same as those disclosed in the above embodiment method, and are not further described here.

[0067] Example 3: The present invention provides an online monitoring and fault diagnosis device for a laser cutting machine, please refer to Figure 2A laser cutting machine online monitoring and fault diagnosis device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the laser cutting machine online monitoring and fault diagnosis method in the above-mentioned embodiment 1. The laser cutting machine online monitoring and fault diagnosis device in the embodiment of the present invention may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. The laser cutting machine online monitoring and fault diagnosis device is merely an example and should not impose any limitations on the functions and scope of use of the embodiments of the present invention. A laser cutting machine online monitoring and fault diagnosis device may include a processing device 1001 (e.g., a central processing unit, graphics processing unit, etc.), which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) 1002 or programs loaded from a storage device 1003 into a random access memory (RAM) 1004. RAM 1004 also stores various programs and data required for the operation of the laser cutting machine online monitoring and fault diagnosis device. Processing device 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, hard disk, etc.; and communication devices 1009. Communication devices 1009 can allow a laser cutting machine online monitoring and fault diagnosis device to communicate wirelessly or wired with other devices to exchange data. Although the figure shows a laser cutting machine online monitoring and fault diagnosis device with various systems, it should be understood that implementation or presence of all the illustrated systems is not required. More or fewer systems may alternatively be implemented or present.

[0068] Example 4: The present invention also provides a computer program product, comprising a computer program. When executed by a processor, the computer program implements the steps of the above-described method for online monitoring and fault diagnosis of a laser cutting machine. The computer program product provided by the present invention can solve the technical problem of online monitoring and fault diagnosis of a laser cutting machine. Compared with the prior art, the beneficial effects of the computer program product provided by the present invention are the same as those of the method for online monitoring and fault diagnosis of a laser cutting machine provided in the above-described embodiment, and are not further elaborated here.

[0069] In particular, according to the embodiments disclosed in the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present invention are performed.

[0070] It should be understood that the various parts disclosed in the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any appropriate manner in any one or more embodiments or examples.

[0071] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A method for online monitoring and fault diagnosis of a laser cutting machine, characterized in that: Methods include: Step S10: The working status information of the laser cutting machine is collected in real time by a sensor installed in the core part of the laser cutting machine, and the working status information is transmitted to a pre-built cloud database through the Ajax protocol; Step S20: Obtaining working status information from the cloud database, constructing a normalization processing function, a Fourier transform function, and a sliding window average function to process the working status information to obtain a working status feature vector; Step S30: constructing a first laser cutting machine fault prediction model using a support vector machine algorithm SVM, constructing a second laser cutting machine fault prediction model using a random forest algorithm RF, and using a stacking ensemble learning method to use the outputs of the SVM and RF as new features to construct a third laser cutting machine fault prediction model; Step S40: training the third laser cutting machine fault prediction model, using the working state feature vector as the trained model input to obtain the fault type and its occurrence probability; Among them, the third laser cutting machine fault prediction model The formula is: in, and Fault prediction model for the third laser cutting machine For weighted SVM and The weight of the output; is the Sigmoid function; is the preset bias item; represents the first laser cutting machine fault prediction model, Represents the working state feature vector; represents the fault prediction model of the second laser cutting machine; Step S50: Use PyThreeJS to generate a 3D model of the laser cutting machine, and perform visual warning in the 3D model according to the fault type and its probability of occurrence; wherein the fault type includes abnormal laser power fluctuation, abnormal robot vibration, abnormal conveyor belt vibration and abnormal temperature fluctuation in the cutting area; the steps of using PyThreeJS to generate a 3D model of the laser cutting machine specifically include: installing and importing the PyThreeJS library, creating a scene and a renderer, generating the laser source, robot and conveyor belt data of the laser cutting machine, adding the laser source, robot and conveyor belt data of the laser cutting machine to the scene, using the renderer to render the 3D scene to the browser, and using the animation loop function in combination with the working status information in the cloud database in step S10 to update the 3D model in real time.

2. A method for online monitoring and fault diagnosis of a laser cutting machine according to claim 1, characterized in that: In step S30, the first laser cutting machine fault prediction model The formula is: in, is the working state feature vector, N is the number of samples in the preset model training, is the working state feature vector of sample i during the preset model training, is the fault label during the preset model training. For radial basis functions, To control the coefficient of each sample's influence on classification, is the preset bias term, is the activation function; model The output is the fault type, and the probability of the fault occurring is obtained through Platt scaling , ,in, and are parameters obtained through training.

3. A method for online monitoring and fault diagnosis of a laser cutting machine according to claim 2, characterized in that: In step S30, the second laser cutting machine fault prediction model The formula is: in, is the prediction result of the working state feature vector of the preset j-th decision tree; model The output is the fault type, and the probability of the fault occurring is obtained through the probabilistic model ,in, It is the Sigmoid function, which is used to convert the output of the tree into a probability value.

4. The method for online monitoring and fault diagnosis of a laser cutting machine according to claim 1, wherein: In step S10, the working status information includes the output power of the laser source, the temperature of the cutting area, the vibration data of the robot, and the vibration data of the conveyor belt.

5. The method for online monitoring and fault diagnosis of a laser cutting machine according to claim 1, wherein: In step S20, the working state feature vector includes the stability feature of the laser power, the vibration frequency feature of the robot, the vibration frequency feature of the conveyor belt, and the temperature fluctuation feature of the cutting area.

6. A laser cutting machine online monitoring and fault diagnosis system, characterized in that: The laser cutting machine online monitoring and fault diagnosis system includes: The data acquisition and transmission module is used to collect the working status information of the laser cutting machine in real time through sensors installed in the core part of the laser cutting machine, and transmit the working status information to a pre-built cloud database through the Ajax protocol; The data processing and feature construction module is used to obtain working status information from the cloud database, construct a normalization processing function, a Fourier transform function, and a sliding window average function to process the working status information to obtain a working status feature vector; A fault prediction model construction module is used to construct a first laser cutting machine fault prediction model using a support vector machine algorithm (SVM), a second laser cutting machine fault prediction model using a random forest algorithm (RF), and a third laser cutting machine fault prediction model using a stacking ensemble learning method with the outputs of the SVM and RF as new features; The model training and fault diagnosis module is used to train the fault prediction model of the third laser cutting machine, and use the working state feature vector as the input of the trained model to obtain the fault type and its occurrence probability; Among them, the third laser cutting machine fault prediction model The formula is: in, and Fault prediction model for the third laser cutting machine For weighted SVM and The weight of the output; is the Sigmoid function; is the preset bias item; represents the first laser cutting machine fault prediction model, Represents the working state feature vector; represents the fault prediction model of the second laser cutting machine; The 3D visualization and fault warning module is used to generate a 3D model of a laser cutting machine using PyThreeJS, and to provide visual warnings in the 3D model based on the fault type and its probability of occurrence; wherein the fault types include abnormal laser power fluctuation, abnormal robot vibration, abnormal conveyor belt vibration, and abnormal temperature fluctuation in the cutting area; the steps of using PyThreeJS to generate a 3D model of a laser cutting machine specifically include: installing and importing the PyThreeJS library, creating a scene and a renderer, generating the laser source, robot, and conveyor belt data of the laser cutting machine, adding the laser source, robot, and conveyor belt data of the laser cutting machine to the scene, using the renderer to render the 3D scene to the browser, and using the animation loop function in combination with the working status information in the cloud database in step S10 to update the 3D model in real time.

7. A laser cutting machine online monitoring and fault diagnosis device, characterized in that: The laser cutting machine online monitoring and fault diagnosis device includes: a memory, a processor, and a laser cutting machine online monitoring and fault diagnosis program stored in the memory and runnable on the processor. When the laser cutting machine online monitoring and fault diagnosis program is executed by the processor, the laser cutting machine online monitoring and fault diagnosis method described in any one of claims 1 to 5 is implemented.

8. A computer program product, characterized in that The computer program product includes a laser cutting machine online monitoring and fault diagnosis program, which, when executed by a processor, implements the laser cutting machine online monitoring and fault diagnosis method according to any one of claims 1 to 5.

Images