Fault monitoring method of bending machine for processing anti-blocking block

Abstract

The invention provides a fault monitoring method of a bending machine for processing an anti-blocking block, and belongs to the technical field of fault monitoring, and the method comprises the following steps: determining an anti-blocking block quality monitoring result based on anti-blocking block quality monitoring data; monitoring operation data of the bending machine based on a first time interval in response to the fact that the resistance block quality monitoring result meets a first condition, and the first condition is that defect information does not exist; monitoring operation data of the bending machine based on a second time interval in response to the fact that the anti-blocking block quality monitoring result meets a second condition, and the second condition is that defect information exists; the first time interval is greater than the second time interval; and analyzing and determining a fault diagnosis result of the bending machine based on the operation data of the bending machine. According to the fault monitoring method of the bending machine for processing the obstruction block, the fault monitoring efficiency of the bending machine can be improved.

Description

Technical Field

[0001] The present disclosure belongs to the technical field of fault monitoring, and more specifically, relates to a method for monitoring faults of a bending machine used for processing anti-collision blocks. Background Art

[0002] Anti-collision blocks are indispensable components in highway traffic safety facilities. When processing anti-collision blocks, a bending machine is a key device. Therefore, the operating condition of the bending machine is crucial for the processing quality of anti-collision blocks. When the bending machine malfunctions, it not only affects the processing quality of anti-collision blocks but also causes damage to the bending machine and production stagnation. However, when the bending machine is operating, multiple components work together, and any abnormality in a component may trigger a fault, thus affecting the processing quality of anti-collision blocks. Therefore, there is an urgent need for an efficient and reliable method for monitoring faults of a bending machine. Summary of the Invention

[0003] The purpose of the present disclosure is to provide a method for monitoring faults of a bending machine used for processing anti-collision blocks to improve the efficiency of fault monitoring of the bending machine.

[0004] In the first aspect of an embodiment of the present disclosure, a method for monitoring faults of a bending machine used for processing anti-collision blocks is provided, including: Determining a monitoring result of the quality of the anti-collision block based on the quality monitoring data of the anti-collision block; In response to the monitoring result of the quality of the anti-collision block satisfying a first condition, monitoring the operating data of the bending machine based on a first time interval, where the first condition is that there is no defect information; In response to the monitoring result of the quality of the anti-collision block satisfying a second condition, monitoring the operating data of the bending machine based on a second time interval, where the second condition is that there is defect information; the first time interval is greater than the second time interval; Analyzing the operating data of the bending machine to determine a fault diagnosis result of the bending machine.

[0005] In the second aspect of an embodiment of the present disclosure, a device for monitoring faults of a bending machine used for processing anti-collision blocks is provided, including: An anti-collision block monitoring module for determining a monitoring result of the quality of the anti-collision block based on the quality monitoring data of the anti-collision block; A first monitoring module for, in response to the monitoring result of the quality of the anti-collision block satisfying a first condition, monitoring the operating data of the bending machine based on a first time interval, where the first condition is that there is no defect information; A second monitoring module for, in response to the monitoring result of the quality of the anti-collision block satisfying a second condition, monitoring the operating data of the bending machine based on a second time interval, where the second condition is that there is defect information; the first time interval is greater than the second time interval; A fault diagnosis module, configured to analyze the operation data of the bending machine to determine the fault diagnosis result of the bending machine.

[0006] In a third aspect of the embodiments of the present disclosure, there is provided an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of the above-mentioned fault monitoring method for a bending machine used in anti-block processing are implemented.

[0007] In a fourth aspect of the embodiments of the present disclosure, there is provided a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned fault monitoring method for a bending machine used in anti-block processing are implemented.

[0008] The beneficial effects of the fault monitoring method for a bending machine used in anti-block processing provided by the embodiments of the present disclosure are as follows: By establishing a linkage mechanism between production quality monitoring and equipment diagnosis, the present disclosure uses defect information to trigger the switching of the monitoring mode. During normal production, a larger monitoring interval is adopted to reduce data redundancy, and during abnormal states, the sampling period is shortened, which not only reduces the monitoring load but also ensures the capture of fault characteristics. After that, the present disclosure analyzes the faults of the bending machine through operation data and can accurately determine the diagnosis result of the bending machine. Therefore, the present disclosure can improve the efficiency of fault monitoring for the bending machine. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present disclosure. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0010] Figure 1 It is a schematic flowchart of a fault monitoring method for a bending machine used in anti-block processing provided by an embodiment of the present disclosure; Figure 2 It is a structural block diagram of a fault monitoring device for a bending machine used in anti-block processing provided by an embodiment of the present disclosure; Figure 3 It is a schematic block diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0011] In the following description, specific details such as specific system architectures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present disclosure. However, those skilled in the art should clearly understand that the present disclosure can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present disclosure.

[0012] To make the objectives, technical solutions, and advantages of the present disclosure clearer, the following will be described through specific embodiments in conjunction with the accompanying drawings.

[0013] Please refer to Figure 1 , Figure 1 which is a schematic flowchart of a method for monitoring faults of a bending machine for processing anti-blocking blocks provided in an embodiment of the present disclosure. The method includes: S101: Determine the anti-blocking block quality monitoring result based on the anti-blocking block quality monitoring data.

[0014] In this embodiment, the anti-blocking block quality monitoring data may be relevant information collected from each quality monitoring link during the production process of the anti-blocking block. The anti-blocking block quality monitoring data may include dimension data and surface quality. Among them, the dimension data may be the length, width, thickness, or bending angle of the anti-blocking block, etc., and the surface quality may be the presence or absence of scratches, indentations, cracks, or deformations, etc.

[0015] The anti-blocking block quality monitoring result can be a judgment conclusion on the quality status of the anti-blocking block after comprehensively analyzing the anti-blocking block quality monitoring data, and can be divided into the situation of no defect information or no defect information.

[0016] Specifically, the anti-blocking block quality monitoring data includes anti-blocking block dimension data and anti-blocking block image data; Determining the anti-blocking block quality monitoring result based on the anti-blocking block quality monitoring data includes: Comparing the anti-blocking block dimension data with the standard anti-blocking block dimension data to determine the first quality monitoring result; Performing image recognition on the anti-blocking block image data and determining the second quality monitoring result based on the image recognition result; Taking the first quality monitoring result and the second quality monitoring result as the anti-blocking block quality monitoring result.

[0017] In this embodiment, the size data of the anti-block can be measured by a laser rangefinder, which is used to reflect the geometric size characteristics of the anti-block. The standard size data of the anti-block is the size value specified according to the design requirements and quality standards of the anti-block, and can be used as a reference benchmark for judging whether the size data of the actually produced anti-block is qualified. The first quality monitoring result is the judgment result on whether the size of the anti-block meets the standard after comparing the size data of the anti-block with the standard anti-block data, which can be that the size is qualified or there is a size deviation and it is unqualified.

[0018] The image data of the anti-block can contain the surface appearance information of the anti-block, such as whether there are defects on the surface, such as scratches, cracks, depressions, deformations, etc. Image recognition is to use computer technology to analyze and process the image data of the anti-block, and identify the characteristic information contained in the image, such as the type, position, size, etc. of the defect, so as to judge the surface quality status of the anti-block. The second quality monitoring result is the result of the anti-block image recognition, and the judgment result on whether the surface quality of the anti-block is qualified, which can be that the surface quality is qualified or there are surface defects and it is unqualified.

[0019] The anti-block quality monitoring result combines the first quality monitoring result (in terms of size) and the second quality monitoring result (in terms of surface quality), and gives the final judgment conclusion on the overall quality status of the anti-block, which is divided into qualified (that is, both the size and the surface quality are qualified) or unqualified (that is, there is at least one unqualified item in the size or the surface quality). Therefore, according to the anti-block quality monitoring result, the monitoring time period of the operation data of the bending machine can be determined subsequently.

[0020] S102: In response to the anti-block quality monitoring result satisfying the first condition, monitor the operation data of the bending machine based on the first time interval, and the first condition is that there is no defect information.

[0021] In this embodiment, the first condition is that the anti-block quality monitoring result shows that there is no defect information, that is, the anti-block meets the quality standards in both the size and the surface quality aspects.

[0022] The first time interval is the time period set for monitoring the operation data of the bending machine when the quality monitoring result satisfies the first condition. This time interval will be relatively long because when the anti-block quality is qualified, the probability of the bending machine malfunctioning is relatively low, and there is no need to frequently monitor the operation data of the bending machine.

[0023] The operation data of the bending machine includes various parameters during the working process of the bending machine, such as hydraulic parameters, electrical parameters, mechanical rotation parameters, etc., and the above parameters can all reflect the operation state of the bending machine.

[0024] In this embodiment, the quality monitoring result of the anti-block can be determined through step S101, and based on this, it is judged whether the first condition is met. If the quality monitoring result of the anti-block meets the first condition, the first time interval is used as the monitoring period for the operation data of the bending machine. For example, the first time interval is set to monitor once every 12 hours. Then, at the set first time interval node, devices such as sensors and data acquisition systems are used to collect the operation data of the bending machine at the current moment, such as hydraulic parameters, electrical parameters, mechanical rotation parameters, etc.

[0025] Specifically, in this embodiment, the monitoring frequency of the operation data of the bending machine is determined based on the quality status of the anti-block. When the quality of the anti-block is qualified (meeting the first condition), it is considered that the bending machine is in a relatively stable operation state, so a longer first time interval is used for monitoring. The principle is that the quality of the anti-block is an external manifestation of the operation effect of the bending machine. If the produced anti-block is of qualified quality, it indicates that the bending machine is probably working normally and does not require high-frequency monitoring; by regularly (the first time interval) collecting the operation data of the bending machine, its operation status can be continuously tracked so as to detect potential fault signs in a timely manner.

[0026] S103: In response to the quality monitoring result of the anti-block meeting the second condition, the operation data of the bending machine is monitored based on the second time interval, where the second condition is the existence of defect information; the first time interval is greater than the second time interval.

[0027] In this embodiment, the second condition is that the quality monitoring result shows the existence of defect information, that is, the anti-block fails to meet the quality standard in terms of size or surface quality.

[0028] The second time interval is the time period set for monitoring the operation parameters of the bending machine when the quality monitoring result of the anti-block meets the second condition. Compared with the first time interval, the second time interval is shorter because the occurrence of defects in the anti-block indicates that the bending machine may have a fault and more frequent monitoring is required to determine the fault status of the bending machine.

[0029] In this embodiment, the quality monitoring result of the anti-block can be determined through step S101, and based on this, it is judged whether the second condition is met. If the quality monitoring result of the anti-block meets the second condition, the second time interval is used as the monitoring period for the operation data of the bending machine. Suppose the second time interval is set to monitor once every 2 hours. Then, according to the second time interval, with the help of sensors, data acquisition devices, etc., the operation data of the bending machine is collected at each interval time point.

[0030] Specifically, in this embodiment, the monitoring frequency of the operating data of the bending machine is dynamically adjusted based on the quality status of the anti-block. Once a quality defect occurs in the anti-block (meeting the second condition), it indicates that there are likely operating problems with the bending machine. Therefore, the monitoring time interval is shortened (adopting the second time interval) to more timely capture the faults existing in the bending machine. The principle is that the quality of the anti-block is closely related to the operating condition of the bending machine, and quality defects are often the external manifestations of the faults of the bending machine. Increasing the monitoring frequency helps to quickly locate and solve the faults of the bending machine and avoid producing more unqualified products.

[0031] Considering the determination of the second time interval, after the monitoring result of the anti-block quality meets the second condition, a method for monitoring the faults of a bending machine for processing anti-blocks further includes: Determining the classified defect characteristics of the anti-block based on the defect information of the anti-block; Determining the first component based on the classified defect characteristics, where the first component is a component of the bending machine; Adjusting the first time interval corresponding to monitoring the first component to obtain the second time interval.

[0032] In this embodiment, the defect information of the anti-block may include dimensional accuracy problems, such as bending angle deviation, length dimension deviation, etc.; surface quality problems, such as scratches, indentations, surface deformation or cracks, etc. The classified defect characteristics of the anti-block are representative characteristics extracted from the defect information and can be used to subsequently determine which component has failed.

[0033] Determining the classified defect characteristics of the anti-block based on the defect information of the anti-block includes: If the defect information of the anti-block is a scratch or an indentation, the classified defect characteristics of the anti-block are mechanical defect characteristics; the mechanical defect characteristics are defects caused by the mechanical components of the bending machine; If the defect information of the anti-block is length dimension deviation or surface deformation, the classified defect characteristics of the anti-block are electrical defect characteristics; the electrical defect characteristics are defects caused by the electrical components of the bending machine; If the defect information of the anti-block is bending angle deviation or crack, the classified defect characteristics of the anti-block are hydraulic defect characteristics; the hydraulic defect characteristics are defects caused by the hydraulic components of the bending machine.

[0034] Therefore, determining the first component based on the classified defect characteristics includes: If the classified defect characteristics are mechanical defect characteristics, the first component is a mechanical component; If the classified defect characteristics are electrical defect characteristics, the first component is an electrical component; If the classified defect characteristics are hydraulic defect characteristics, the first component is a hydraulic component.

[0035] In this embodiment, the classification defect features of the anti-blocking block are used to analyze the possible causes of defects, and the causes of the anti-blocking block defects are associated with the failures of the operating components of the bending machine. The first component is inferred based on the defect classification features of the anti-blocking block, that is, a certain component of the bending machine that is directly related to the generation of the defects of the anti-blocking block, such as abrasive wear, inaccurate sensors, or certain valves in the hydraulic system.

[0036] The first time interval is the time period set for monitoring the operating data of the bending machine when there are no defects in the anti-blocking block, and this time interval can be set according to experience.

[0037] The second time interval is the new monitoring time period obtained after adjusting the monitoring time interval corresponding to the first component (i.e., the first time interval) according to the defect features of the anti-blocking block. It is shorter than the first time interval to more closely monitor the operation of this component.

[0038] Therefore, the calculation formula for the second time interval is:

[0039] where is the first time interval, is the second time interval, is the total number of defects in the anti-blocking block, is the average repair time for the failure of the first component.

[0040] The total number of defects in the anti-blocking block is the sum of the data on the defects of the anti-blocking block in the monitoring batches; the average repair time M for the failure of the first component is obtained by collecting the past multiple failure repair records of this component and calculating the ratio of the total repair time to the number of repairs. The more the number of defects, the greater the impact of the bending machine on the quality of the anti-blocking block, and more frequent monitoring and processing are required.

[0041] S104: Analyze based on the operating data of the bending machine to determine the fault diagnosis result of the bending machine.

[0042] In this embodiment, the operating data of the bending machine can be various types of parameters such as the pressure monitoring data and positioning monitoring data of sensors, the rotational speed data of the motor, the hydraulic oil flow and pressure of the hydraulic system, the position and speed of the slider, and the number of bending times.

[0043] The fault diagnosis result is to judge whether there is a fault in the bending machine by analyzing the operating data. If there is a fault, information such as the type of the fault is determined.

[0044] Specifically, first, collect the operation data of the bending machine, and then perform operations such as data preprocessing and feature extraction to determine the processed operation data; after that, establish a fault diagnosis model, which can be a signal analysis model or a machine learning model, etc., and train the fault diagnosis model in combination with historical operation data and corresponding fault types to determine the trained fault diagnosis model; then, input the processed operation data into the trained fault diagnosis model to obtain the fault diagnosis result of the bending machine; finally, present the fault diagnosis result to the operator in an intuitive way, such as displaying the fault type through a display screen.

[0045] As can be seen from the above, the present disclosure establishes a linkage mechanism for production quality monitoring and equipment diagnosis, uses defect information to trigger the monitoring mode switch, adopts a larger monitoring interval during normal production to reduce data redundancy, and shortens the sampling period under abnormal conditions, which not only reduces the monitoring load but also ensures the capture of fault characteristics; after that, the present disclosure analyzes the faults of the bending machine through operation data and can accurately determine the diagnosis result of the bending machine. Therefore, the present disclosure can improve the efficiency of fault monitoring for the bending machine.

[0046] In an embodiment of the present disclosure, before performing image recognition on the anti-blocking block image data, it further includes: Calculate the gray variance of the original anti-blocking block image data to obtain the original image variance value; In response to the original image variance value being greater than or equal to the first threshold, use the original anti-blocking block image data as the anti-blocking block image data; In response to the original image variance value being less than the first threshold, perform local feature enhancement on the original anti-blocking block image data to obtain the anti-blocking block image data.

[0047] In this embodiment, the original anti-blocking block image data is a visual image of the anti-blocking block obtained through an image acquisition device such as a camera, which records the appearance information of the anti-blocking block.

[0048] The gray variance is a statistic used to measure the degree of dispersion of pixel gray values in an image. The larger the variance, the greater the difference in pixel gray values in the image, and the higher the contrast of the image.

[0049] The first threshold is a preset reference value used to determine whether the gray variance of the anti-blocking block image is within the range that requires further processing. After comparing the gray variance with this threshold, it is decided whether to perform local feature enhancement on the original anti-blocking block image data.

[0050] Local feature enhancement is to perform strengthening processing on the features of specific regions in the image, such as highlighting edges and enhancing textures, etc., so that the key detail information in the image is more obvious, which is helpful for subsequent image recognition.

[0051] Specifically, the steps of this embodiment are: First, calculate the gray variance of the original anti-collision block image data: Traverse each pixel point in the original anti-collision block image data to obtain its gray value. According to the calculation formula of gray variance (such as first calculating the average value of all pixel gray values, then calculating the sum of the squares of the differences between each pixel gray value and the average value, and finally dividing by the total number of pixels), calculate the gray variance of the entire image, that is, obtain the original image variance value. The gray variance can reflect the contrast and richness of details in the image. If the variance is small, it means that the overall image is relatively blurred and the pixel gray values do not differ much; if the variance is large, the light and dark contrast of the image is obvious and the detail information is more abundant.

[0052] Second, determine the relationship between the original image variance value and the first threshold: Compare the calculated original image variance value with the pre-set first threshold. If the original image variance value is less than the first threshold, it means that local feature enhancement is required; if the original image variance value is greater than or equal to the first threshold, it means that the contrast and detail level of the image already meet the basic requirements for subsequent recognition and no additional local feature enhancement processing is needed.

[0053] Third, perform local feature enhancement on the original anti-collision block image data: Highlight local features such as textures and edges, facilitating subsequent image recognition algorithms to more accurately extract and identify these features.

[0054] It can be concluded from the above that in this embodiment, by dynamically evaluating the image quality and performing adaptive enhancement, the recognition robustness is improved. The variance threshold mechanism effectively filters high-quality images and avoids redundant calculations; local enhancement optimizes the problem areas, enabling subsequent recognition algorithms to still maintain high accuracy in complex lighting or noise environments.

[0055] In an embodiment of the present disclosure, performing local feature enhancement on the original anti-collision block image data to obtain anti-collision block image data includes: Determine the neighborhood window corresponding to each first pixel point in the original anti-collision block image data; Based on the pixel values within the neighborhood window corresponding to each first pixel point, calculate the local mean and local variance corresponding to each first pixel point; Perform normalization processing on each first pixel point based on the local mean and local variance to obtain normalized pixel values; Perform contrast enhancement on the normalized pixel values to obtain anti-collision block image data.

[0056] In this embodiment, the first pixel point is any pixel point in the original anti-collision block image data, which is the basic unit constituting the image, and each pixel point has a corresponding gray value or color value. The neighborhood window is an area centered on a certain first pixel point and delimits a region containing several surrounding pixel points for analyzing the local features around the pixel point.

[0057] The local mean is the average of the pixel values of all pixel points within the neighborhood window, reflecting the average gray level or color level of the local area. The local variance is the degree of dispersion of the pixel values relative to the local mean within the neighborhood window, reflecting the variation of the pixel values in the local area. The larger the variance, the greater the difference in pixel values.

[0058] Normalization is to map the pixel values to a specific range according to certain rules, making the pixel values in different regions comparable and eliminating the influence of numerical differences on subsequent processing. The normalized pixel value is the pixel value obtained after the first pixel point undergoes normalization processing.

[0059] Contrast enhancement is to increase the difference between different pixel values in the image through a suitable contrast enhancement algorithm (such as linear transformation, histogram equalization, etc.), making the bright parts of the image brighter and the dark parts darker, thereby highlighting the details and features of the image.

[0060] Determine the neighborhood window corresponding to each first pixel point in the original anti-blocking block image data, including: Determine the initial neighborhood window; Calculate the gradient magnitude of the anti-blocking block image based on the Sobel operator; If the gradient magnitude of the original anti-blocking block image data is less than or equal to the first magnitude threshold, control the initial neighborhood window to increase by the first range step size; If the gradient magnitude of the original anti-blocking block image data is greater than the first magnitude threshold, control the initial neighborhood window to decrease by the second range step size.

[0061] Among them, the initial neighborhood window is a preset initial value or default value; the first magnitude threshold, the first range step size, and the second range step size are all set according to experience.

[0062] It can be concluded from the above that in this embodiment, the defect monitoring performance is significantly improved through adaptive contrast optimization. The normalization processing based on neighborhood statistics effectively suppresses light interference, making the features in different regions comparable; subsequent contrast enhancement specifically amplifies local details, providing a reliable image preprocessing guarantee for the quality monitoring of anti-blocking blocks.

[0063] In an embodiment of the present disclosure, analyzing the operation data of a bending machine to determine the fault diagnosis result of the bending machine includes: If the first component is a first type of component, analyze the operation data of the bending machine based on the fast Fourier transform algorithm to obtain the fault diagnosis result of the bending machine; the first type of component is a mechanical component of the bending machine; If the first component is a second type of component, analyze the operation data of the bending machine based on the first neural network model to obtain the fault diagnosis result of the bending machine; the second type of component is an electrical component of the bending machine; If the first component is a third - type component, analyze the operation data of the bending machine based on the second neural network model to obtain the fault diagnosis result of the bending machine; the third - type component is the hydraulic component of the bending machine; Among them, the input parameters of the first neural network model and the second neural network model are different.

[0064] In this embodiment, the first - type components are the mechanical components of the bending machine, such as molds, transmission gears, lead screw nuts, etc. These components mainly achieve the functions of the bending machine through mechanical motion. The second - type components are the electrical components of the bending machine, including motors, relays, sensors, etc., which are mainly responsible for providing power and controlling the operation of the bending machine. The third - type components are the hydraulic components of the bending machine, such as hydraulic pumps, hydraulic cylinders, hydraulic valves, etc., which use the pressure of hydraulic oil to drive the work of the bending machine.

[0065] The fast Fourier transform algorithm can convert time - domain signals into frequency - domain signals and can be used to analyze the frequency components of signals. In the fault diagnosis of bending machines, the frequency characteristics in the operation data of mechanical components can be analyzed through the fast Fourier transform algorithm to find abnormal frequencies and determine whether there are faults.

[0066] The first neural network model is a neural network model designed for the fault diagnosis of the electrical components of the bending machine. It is trained with a large amount of fault and normal operation data of electrical components to learn the mapping relationship between the operation data of electrical components and the fault types. The second neural network model is a neural network model used for the fault diagnosis of the hydraulic components of the bending machine. It is also trained with a large amount of relevant data of hydraulic components to achieve accurate diagnosis of hydraulic component faults. The first neural network model and the second neural network model have different required input parameters because the components they diagnose are different.

[0067] Specifically, if it is for the first - type components (mechanical components), use the fast Fourier transform algorithm to analyze the operation data of the bending machine. Mechanical components generate vibration signals during operation, and these signals contain rich fault information. The time - domain vibration signals are converted into frequency - domain signals through the fast Fourier transform algorithm, and different faults correspond to different characteristic frequencies.

[0068] If it is for the second - type components (electrical components), input the operation data of the bending machine into the first neural network model for analysis. The first neural network model has learned the characteristics of the operation data of electrical components in normal and faulty states. After inputting the data, the model calculates according to its internal weights and biases and outputs the fault diagnosis result.

[0069] If it is the third type of component (hydraulic component), the operating data is input into the second neural network model. The second neural network model is trained with hydraulic component data and can identify the fault patterns of hydraulic components. According to the input parameters such as the pressure and flow rate of the hydraulic system, the model outputs the fault diagnosis results of the hydraulic components, such as determining whether the hydraulic pump is leaking or whether the hydraulic cylinder is stuck, etc.

[0070] It can be concluded from the above that in this embodiment, the fast Fourier transform algorithm is used for mechanical components to capture vibration characteristics and accurately identify mechanical faults; different neural networks are used for electrical / hydraulic components to automatically learn complex fault patterns. This embodiment combines timeliness and accuracy, can adapt to the multi-physical domain characteristics of the equipment, provides an intelligent solution for the health monitoring of the entire bending machine system, effectively extends the equipment life and reduces the risk of unplanned downtime.

[0071] In an embodiment of the present disclosure, the fault diagnosis result of the bending machine includes the fault type; A fault monitoring method for a bending machine used for manufacturing anti-blocking blocks further includes: Calculating the similarity between the fault type and the standard fault type, and determining the target maintenance strategy corresponding to the fault type based on the similarity; each standard fault type corresponds to a maintenance strategy.

[0072] In this embodiment, the fault type is a classification definition of the faults occurring in the bending machine, such as die wear, hydraulic system leakage, sensor instability, etc., which is used to clarify the current fault state of the equipment.

[0073] The standard fault type is a set of preset, sorted and classified common fault types, and each standard fault type corresponds to a maintenance strategy, which is an important reference basis for fault diagnosis and maintenance.

[0074] The similarity is a quantitative index for measuring the similarity degree between the fault type obtained by fault diagnosis and the standard fault type. The target maintenance strategy is to determine the specific maintenance measures to be taken for the current fault type according to the similarity between the fault type and the standard fault type, including repair steps, replacement part list, repair tool preparation, etc.

[0075] Calculate the similarity between the fault type and the standard fault type based on the first formula, and the first formula is:

[0076] Where, is the similarity between the fault type and the standard fault type, is the feature vector of the fault type, is the feature vector of the standard fault type, is the weight vector corresponding to each feature vector, , The closer the similarity value is to 0, the more similar the two fault types are.

[0077] Sort the calculated similarity values to find the standard fault type with the highest similarity to the current fault type. Since each standard fault type is pre-corresponded with a maintenance strategy, directly retrieve the maintenance strategy corresponding to the standard fault type with the highest similarity and determine it as the target maintenance strategy for the current fault type.

[0078] As can be seen from the above, in this embodiment, the target maintenance strategy is efficiently determined by introducing a similarity matching mechanism. The standardized fault library pre-defines typical fault characteristics and corresponding maintenance strategies. In this embodiment, the similarity between the diagnostic result and the standard fault is calculated, and the optimal maintenance plan is automatically matched, improving the equipment maintenance efficiency and the accuracy of the whole life cycle management.

[0079] Corresponding to the above-mentioned embodiment, a fault monitoring method for a bending machine used for processing anti-blocking blocks Figure 2 is a structural block diagram of a fault monitoring device for a bending machine used for processing anti-blocking blocks provided by an embodiment of the present disclosure. For the sake of illustration, only the parts related to the embodiments of the present disclosure are shown. Refer to Figure 2 This fault monitoring device 20 for a bending machine used for processing anti-blocking blocks includes: an anti-blocking block monitoring module 21, a first monitoring module 22, a second monitoring module 23, and a fault diagnosis module 24.

[0080] Among them, the anti-blocking block monitoring module 21 is used to determine the anti-blocking block quality monitoring result based on the anti-blocking block quality monitoring data; The first monitoring module 22 is used to monitor the operation data of the bending machine based on the first time interval in response to the anti-blocking block quality monitoring result satisfying the first condition, and the first condition is that there is no defect information; The second monitoring module 23 is used to monitor the operation data of the bending machine based on the second time interval in response to the anti-blocking block quality monitoring result satisfying the second condition, and the second condition is that there is defect information; the first time interval is greater than the second time interval; The fault diagnosis module 24 is used to analyze and determine the fault diagnosis result of the bending machine based on the operation data of the bending machine.

[0081] In an embodiment of the present disclosure, a fault monitoring device 20 for a bending machine used for processing anti-blocking blocks further includes: a second time interval determination module, which is used to determine the classified defect characteristics of the anti-blocking block based on the defect information of the anti-blocking block; Determine the first component based on the classified defect characteristics, and the first component is a component of the bending machine; Adjust the monitored first time interval corresponding to the first component to obtain the second time interval.

[0082] In one embodiment of the present disclosure, the anti-block mass monitoring data includes anti-block size data and anti-block image data; The anti-block monitoring module 21 is specifically configured to compare the anti-block size data with the standard anti-block size data to determine the first quality monitoring result; Perform image recognition on the anti-block image data and determine the second quality monitoring result based on the image recognition result; Use the first quality monitoring result and the second quality monitoring result as the anti-block quality monitoring result.

[0083] In one embodiment of the present disclosure, a fault monitoring device 20 for a bending machine used in anti-block processing further includes: a local feature enhancement module, configured to calculate the gray variance of the original anti-block image data to obtain the original image variance value; In response to the original image variance value being greater than or equal to the first threshold, use the original anti-block image data as the anti-block image data; In response to the original image variance value being less than the first threshold, perform local feature enhancement on the original anti-block image data to obtain the anti-block image data.

[0084] In one embodiment of the present disclosure, the local feature enhancement module is specifically configured to determine the neighborhood window corresponding to each first pixel point in the original anti-block image data; Based on the pixel values within the neighborhood window corresponding to each first pixel point, calculate the local mean and local variance corresponding to each first pixel point; Perform normalization processing on each first pixel point based on the local mean and local variance to obtain the normalized pixel value; Perform contrast enhancement on the normalized pixel value to obtain the anti-block image data.

[0085] In one embodiment of the present disclosure, the fault diagnosis module 24 is specifically configured to, if the first component is a first type of component, analyze the operation data of the bending machine based on the fast Fourier transform algorithm to obtain the fault diagnosis result of the bending machine; the first type of component is a mechanical component of the bending machine; If the first component is a second type of component, analyze the operation data of the bending machine based on the first neural network model to obtain the fault diagnosis result of the bending machine; the second type of component is an electrical component of the bending machine; If the first component is a third type of component, analyze the operation data of the bending machine based on the second neural network model to obtain the fault diagnosis result of the bending machine; the third type of component is a hydraulic component of the bending machine; Wherein, the input parameters of the first neural network model and the second neural network model are different.

[0086] In one embodiment of the present disclosure, the fault diagnosis result of the bending machine includes the fault type; A fault monitoring device 20 for a bending machine used in anti-block processing further includes: a maintenance strategy determination module, configured to calculate the similarity between the fault type and the standard fault type, and determine the target maintenance strategy corresponding to the fault type based on the similarity; each standard fault type corresponds to a maintenance strategy.

[0087] See Figure 3 , Figure 3 is a schematic block diagram of an electronic device provided by an embodiment of the present disclosure. As Figure 3 shown, the electronic device 300 in this embodiment may include: one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The above-mentioned processors 301, input devices 302, output devices 303, and memories 304 communicate with each other through a communication bus 305. The memory 304 is used to store computer programs, and the computer programs include program instructions. The processor 301 is configured to execute the program instructions stored in the memory 304. Among them, the processor 301 is configured to call the program instructions to execute the functions of each module / unit in the above-mentioned device embodiments, such as Figure 2 the functions of the modules 21 to 24 shown.

[0088] It should be understood that in the embodiments of the present disclosure, the so-called processor 301 may be a central processing unit (Central Processing Unit, CPU), and this processor may also be other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application-specific integrated circuits (Application Specific Integrated Circuit, ASIC), field-programmable gate arrays (Field-Programmable Gate Array, FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or this processor may also be any conventional processor, etc.

[0089] The input device 302 may include a touchpad, a fingerprint acquisition sensor (for acquiring the fingerprint information and the direction information of the fingerprint of the user), a microphone, etc., and the output device 303 may include a display (such as an LCD), a speaker, etc.

[0090] The memory 304 may include a read-only memory and a random access memory, and provide instructions and data to the processor 301. A part of the memory 304 may also include a non-volatile random access memory. For example, the memory 304 may also store information about the device type.

[0091] In a specific implementation, the processor 301, the input device 302, and the output device 303 described in the embodiments of the present disclosure may execute the implementation manners described in the first and second embodiments of a method for monitoring faults of a bending machine for processing anti-blocking blocks provided by the embodiments of the present disclosure, and may also execute the implementation manner of the electronic device described in the embodiments of the present disclosure, which will not be elaborated herein.

[0092] In another embodiment of the present disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, and the computer program includes program instructions. When the program instructions are executed by a processor, all or part of the processes in the method of the above embodiments are implemented. It can also be completed by instructing relevant hardware through the computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0093] The computer-readable storage medium may be an internal storage unit of the electronic device in any of the foregoing embodiments, such as the hard disk or memory of the electronic device. The computer-readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device. Further, the computer-readable storage medium may also include both the internal storage unit and the external storage device of the electronic device. The computer-readable storage medium is used to store the computer program and other programs and data required by the electronic device. The computer-readable storage medium may also be used to temporarily store the data that has been output or will be output.

[0094] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this disclosure.

[0095] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the above-described electronic devices and units can refer to the corresponding processes in the foregoing method embodiments, and will not be described herein again.

[0096] In several embodiments provided in this application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed couplings or direct couplings or communication connections to each other can be indirect couplings or communication connections through some interfaces or units, and can also be electrical, mechanical, or other forms of connection.

[0097] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place, or can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiments of this disclosure.

[0098] In addition, the functional units in various embodiments of this disclosure can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0099] The above is only the specific implementation manner of this disclosure, but the protection scope of this disclosure is not limited thereto. Any person skilled in the art can easily think of various equivalent modifications or replacements within the technical scope disclosed by this disclosure, and these modifications or replacements should be covered within the protection scope of this disclosure. Therefore, the protection scope of this disclosure should be subject to the protection scope of the claims.

Claims

1. A method for monitoring faults of a bending machine for processing an anti-block block, characterized in that: include: Determine the quality monitoring result of the anti-blocking block based on the quality monitoring data of the anti-blocking block; In response to the quality monitoring result of the anti-blocking block satisfying a first condition, monitoring the operation data of the bending machine based on a first time interval, wherein the first condition is that there is no defect information; In response to the quality monitoring result of the anti-blocking block satisfying a second condition, monitoring the operation data of the bending machine based on a second time interval, wherein the second condition is the presence of defect information; The first time interval is greater than the second time interval; The fault diagnosis result of the bending machine is determined by analyzing the operation data of the bending machine.

2. A method for monitoring faults of a bending machine for processing an anti-block block according to claim 1, characterized in that: After the response to the anti-blocking block quality monitoring result satisfying the second condition, the method further includes: Determining the classification defect characteristics of the anti-blocking block based on the defect information of the anti-blocking block; determining a first component based on the classified defect feature, the first component being a component of the bending machine; The first time interval corresponding to monitoring the first component is adjusted to obtain the second time interval.

3. A method for monitoring faults of a bending machine for processing an anti-block block as claimed in claim 2, characterized in that: The analyzing and determining the fault diagnosis result of the bending machine based on the operation data of the bending machine includes: If the first component is a first-category component, the operating data of the bending machine is analyzed based on a fast Fourier transform algorithm to obtain a fault diagnosis result of the bending machine; the first-category component is a mechanical component of the bending machine; If the first component is a second-category component, the operating data of the bending machine is analyzed based on the first neural network model to obtain a fault diagnosis result of the bending machine; the second-category component is an electrical component of the bending machine; If the first component is a third-category component, the operating data of the bending machine is analyzed based on the second neural network model to obtain a fault diagnosis result of the bending machine; the third-category component is a hydraulic component of the bending machine; Among them, the input parameters of the first neural network model and the second neural network model are different.

4. A method for monitoring faults of a bending machine for processing an anti-block block as claimed in claim 3, characterized in that: The fault diagnosis result of the bending machine includes the fault type; The method for monitoring faults of a bending machine for processing an anti-block block further comprises: Calculating the similarity between the fault type and a standard fault type, and determining a target maintenance strategy corresponding to the fault type based on the similarity; Each standard failure type corresponds to a maintenance strategy.

5. A method for monitoring faults of a bending machine for processing an anti-block block according to claim 1, characterized in that: The anti-blocking block quality monitoring data includes anti-blocking block size data and anti-blocking block image data; The method of determining the anti-blocking block quality monitoring result based on the anti-blocking block quality monitoring data includes: Comparing the anti-blocking block size data with the standard anti-blocking block size data to determine a first quality monitoring result; Performing image recognition on the anti-blocking block image data, and determining a second quality monitoring result based on the image recognition result; The first quality monitoring result and the second quality monitoring result are used as the quality monitoring result of the anti-blocking block.

6. A method for monitoring faults of a bending machine for processing an anti-block block as claimed in claim 5, characterized in that: Before performing image recognition on the anti-blocking block image data, the method further includes: Calculate the grayscale variance of the original anti-blocking block image data to obtain the variance value of the original image; In response to the original image variance value being greater than or equal to a first threshold, using the original anti-blocking block image data as the anti-blocking block image data; In response to the original image variance value being less than a first threshold, local feature enhancement is performed on the original anti-blocking block image data to obtain anti-blocking block image data.

7. A method for monitoring faults of a bending machine for processing an anti-block block as claimed in claim 6, characterized in that: The step of performing local feature enhancement on the original anti-blocking block image data to obtain the anti-blocking block image data includes: Determine a neighborhood window corresponding to each first pixel point in the original anti-blocking block image data; Based on the pixel values ​​in the neighborhood window corresponding to each first pixel point, a local mean and a local variance corresponding to each first pixel point are calculated; Performing normalization processing on each first pixel point based on the local mean and the local variance to obtain a normalized pixel value; The normalized pixel values ​​are contrast enhanced to obtain anti-blocking block image data.

8. A fault monitoring device for a bending machine used for processing an anti-block block, characterized in that: include: The anti-blocking block monitoring module is used to determine the anti-blocking block quality monitoring result based on the anti-blocking block quality monitoring data; A first monitoring module, configured to monitor the operation data of the bending machine based on a first time interval in response to the quality monitoring result of the anti-blocking block satisfying a first condition, wherein the first condition is that there is no defect information; A second monitoring module is used to monitor the operation data of the bending machine based on a second time interval in response to the quality monitoring result of the anti-blocking block meeting a second condition, wherein the second condition is the presence of defect information; The first time interval is greater than the second time interval; A fault diagnosis module is used to analyze and determine a fault diagnosis result of the bending machine based on the operating data of the bending machine.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images