Elevator part abrasion early warning method and system based on images

Abstract

The invention relates to the technical field of image processing, and discloses an image-based elevator part wear early warning method and system, and the method comprises the steps: carrying out the shooting of a plurality of directions of a to-be-detected elevator part, determining an image data set, determining a target part image based on a part image model and an initial part image, and carrying out the early warning of the wear of the to-be-detected elevator part. The method comprises the steps of establishing a wear mark for a to-be-detected elevator part based on all pixel points, determining a first wear value according to a wear pixel value of a wear pixel point, determining a wear detection area based on a part position, obtaining environment feature data corresponding to each environment obtaining point, determining a second wear value based on all environment feature data, and determining a wear detection area according to the second wear value. And the comprehensive wear value is compared with a historical data set, whether the comprehensive wear value is adjusted or not is judged according to a comparison result, and an early warning is given out to the to-be-detected elevator part according to the target wear value. According to the invention, the reliability of early warning is improved by processing the image data set.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to an image-based elevator component wear warning method and system. Background Art

[0002] With the development of urbanization, single-story buildings are gradually transitioning to high-rise buildings. Elevators have become an indispensable tool in high-rise buildings, and their safe operation is directly related to the safety of users. During long-term operation, elevator components inevitably wear out due to various factors such as mechanical stress, friction, and fatigue. Component wear not only affects the normal operation of the elevator, but also reduces the service life of the elevator, thereby causing safety accidents. Currently, the detection and early warning of elevator component wear mainly relies on manual inspections. However, manual inspections are susceptible to subjective judgment based on human experience, resulting in low reliability of detection and early warning. In addition, inspectors are limited by the space between elevators, resulting in low detection efficiency and long detection cycles, which further negatively impacts detection and early warning.

[0003] Therefore, it is necessary to design an image-based elevator component wear warning method and system to solve the problems existing in current technology. Summary of the Invention

[0004] In view of this, the present invention proposes an image-based elevator component wear warning method and system, aiming to solve the problem that manual inspections are easily subject to subjective judgment based on human experience, resulting in low reliability of detection and warning. In addition, inspection personnel are limited by the space of the elevator room, resulting in low detection efficiency and long detection cycle, which further have an adverse impact on detection and warning.

[0005] In one aspect, the present invention provides an image-based early warning method for elevator component wear, comprising:

[0006] Determine an elevator component to be inspected, photograph the elevator component in several orientations to determine an image dataset, process the image dataset to determine an initial part image, and determine a target part image based on a component image model and the initial part image;

[0007] Extracting all pixel points of the target part image, establishing a wear mark for the elevator component to be inspected based on all pixel points, extracting worn pixel points of the target part image based on the established wear mark, and determining a first wear value according to the wear pixel values ​​of the worn pixel points;

[0008] Determining a component position of an elevator component to be inspected, determining a wear detection area based on the component position, deploying a plurality of environmental acquisition points in the wear detection area, acquiring environmental characteristic data corresponding to each environmental acquisition point, and determining a second wear value based on all the environmental characteristic data;

[0009] Based on the first wear value and the second wear value, a comprehensive wear value of the elevator component to be inspected is determined, the comprehensive wear value is compared with a historical data set, and it is determined whether to adjust the comprehensive wear value based on the comparison result. When it is determined that the comprehensive wear value is to be adjusted, a target wear value is determined based on the historical data set, and an early warning is issued for the elevator component to be inspected based on the target wear value.

[0010] Furthermore, when the image data set is processed to determine the initial part image, the method includes:

[0011] Preprocessing the image data set, wherein the preprocessing includes image denoising and geometric correction;

[0012] Extract feature points from the preprocessed image dataset, match and register the extracted feature points, and merge the registered image datasets to determine a merged image;

[0013] The merged image is subjected to image processing to determine the initial part image, wherein the image processing includes adjusting image contrast and sharpening image edges.

[0014] Furthermore, when determining the target part image based on the component image model and the initial part image, the method includes:

[0015] Obtaining an image feature set, and dividing the image feature set into an image training set and an image test set according to a sampling ratio, preselecting a convolutional neural network model, training the convolutional neural network model based on the image training set, testing the trained convolutional neural network model based on the image test set, and determining the component image model based on the test results;

[0016] The initial part image is substituted into the component image model to output a verification value of the initial part image. If the verification value is greater than a verification threshold, the initial part image is determined as the target part image. If the verification value is less than or equal to the verification threshold, the image dataset of the elevator component to be inspected is reacquired.

[0017] Furthermore, when establishing wear marks for the elevator parts to be inspected based on all pixel points, the method includes:

[0018] Determine a target qualified part image corresponding to the target part image, extract all pixels of the target part image, and extract all qualified pixels from the target qualified part image, wherein each pixel corresponds to a qualified pixel;

[0019] Determining pixel values ​​corresponding to all pixel points, and determining qualified pixel values ​​corresponding to all qualified pixel points, and establishing a wear mark for the elevator component to be inspected based on the relationship between the pixel values ​​and the qualified pixel values;

[0020] The wear marks include qualified marks, wear marks and suspected wear marks.

[0021] Furthermore, when extracting the worn pixel points of the target part image based on the established wear mark and determining the first wear value according to the wear pixel values ​​of the worn pixel points, the method includes:

[0022] The worn pixel points include a first worn pixel point and a second worn pixel point;

[0023] If the wear mark established for the elevator component to be inspected is the suspected wear mark, the pixel point corresponding to the pixel value greater than the qualified pixel value in the target part image is recorded as the first wear pixel point, and the pixel point corresponding to the pixel value less than the qualified pixel value in the target part image is recorded as the second wear pixel point;

[0024] All first wear pixel points and all second wear pixel points in the target part image are extracted, and the first wear value is determined based on all first wear pixel points and all second wear pixel points.

[0025] Furthermore, when determining the wear detection area based on the component position, it includes:

[0026] The geometric center of the component position is extended in all directions to form a rectangular space with a length and width of s and a height of h. The wear detection area is determined by deleting the rectangular space based on the component position.

[0027] Furthermore, a plurality of environment acquisition points are deployed in the wear detection area, and environment characteristic data corresponding to each environment acquisition point is acquired. When the second wear value is determined based on all the environment characteristic data, the method includes:

[0028] Compare the environmental characteristic data of each environmental acquisition point with the standard environmental characteristic data; if the environmental characteristic data of the environmental acquisition point are all greater than the standard environmental characteristic data, record the environmental acquisition point as the first acquisition point; if the environmental characteristic data of the environmental acquisition point are all less than the standard environmental characteristic data, record the environmental acquisition point as the second acquisition point; if one or more environmental characteristic data of the environmental acquisition point are greater than the standard environmental characteristic data, and one or more environmental characteristic data are less than or equal to the standard environmental characteristic data, record the environmental acquisition point as a pending acquisition point;

[0029] A first number of the first acquisition points and a second number of the second acquisition points are counted, and the second wear value is determined according to the first number and the second number.

[0030] Furthermore, when determining a comprehensive wear value of the elevator component to be detected based on the first wear value and the second wear value, comparing the comprehensive wear value with a historical data set, and determining whether to adjust the comprehensive wear value according to the comparison result, the method includes:

[0031] The comprehensive wear value is the product of the first wear value and the second wear value;

[0032] The historical data set includes a historical comprehensive wear average, several historical comprehensive wear values ​​and several historical wear adjustment factors, and each historical comprehensive wear value corresponds to a historical wear adjustment factor. The comprehensive wear value is compared with the historical comprehensive wear average. If the comprehensive wear value is greater than or equal to the historical comprehensive wear average, it is determined that the comprehensive wear value will not be adjusted, and the comprehensive wear value is determined as the target wear value. If the comprehensive wear value is less than the historical comprehensive wear average, it is determined that the comprehensive wear value is adjusted.

[0033] Furthermore, when it is determined to adjust the comprehensive wear value, a target wear value is determined based on the historical data set, and an early warning is issued for the elevator component to be inspected according to the target wear value, including:

[0034] Comparing the comprehensive wear value with a historical data set, if a historical comprehensive wear value equal to the comprehensive wear value exists in the historical data set, adjusting the comprehensive wear value by a historical wear adjustment factor corresponding to the historical comprehensive wear value; if a historical comprehensive wear value equal to the comprehensive wear value does not exist in the historical data set, obtaining a historical comprehensive wear value with the greatest similarity to the comprehensive wear value, and adjusting the comprehensive wear value by the historical wear adjustment factor corresponding to the historical comprehensive wear value;

[0035] The target wear value is the product of the historical wear adjustment factor and the comprehensive wear value;

[0036] The target wear value is compared with the target wear threshold. If the target wear value is greater than or equal to the target wear threshold, it is determined that the elevator component to be detected is worn and an early warning is issued. If the target wear value is less than the target wear threshold, it is determined that the elevator component to be detected is not worn and no early warning is issued.

[0037] Compared with the prior art, the present invention has the following advantages: by constructing an image dataset through shooting from several directions, accurately processing the initial part image in combination with the component image model, establishing wear marks based on pixel-level analysis, accurately extracting wear pixels and calculating the first wear value, reflecting the degree of wear through the change in pixel value, effectively avoiding subjective errors and improving the reliability of early warning. Through the automated image acquisition and analysis process, early warning can be issued for the wear of the elevator parts to be inspected. At the same time, by deploying several environmental acquisition points in the wear detection area, the relevant environment of the elevator parts to be inspected can be fully covered, and environmental feature data can be acquired in real time and the second wear value can be calculated, thus realizing the monitoring of the operating environment of the elevator parts to be inspected. The comprehensive wear value is determined by comprehensively considering the image analysis and the operating environment, and the comprehensive wear value is dynamically adjusted according to the historical data set to determine the target wear value that fits the actual operating conditions. The data-driven dynamic early warning mechanism can track the wear of the elevator parts to be inspected in real time, thereby avoiding safety accidents caused by accumulated wear and providing reliable protection for the safe operation of the elevator.

[0038] On the other hand, the present application also provides an image-based elevator component wear warning system, which is used to apply the above-mentioned image-based elevator component wear warning method, including:

[0039] a data acquisition module configured to determine an elevator component to be inspected, photograph the elevator component to be inspected in a plurality of orientations to determine an image data set, process the image data set to determine an initial part image, and determine a target part image based on a component image model and the initial part image;

[0040] a first processing module configured to extract all pixels of the target part image, establish a wear mark for the elevator component to be inspected based on all pixels, extract worn pixels of the target part image based on the established wear mark, and determine a first wear value according to the wear pixel values ​​of the worn pixels;

[0041] a second processing module configured to determine a component position of an elevator component to be inspected, determine a wear detection area based on the component position, deploy a plurality of environment acquisition points in the wear detection area, acquire environmental characteristic data corresponding to each environment acquisition point, and determine a second wear value based on all the environmental characteristic data;

[0042] The comprehensive early warning module is configured to determine a comprehensive wear value of the elevator component to be detected based on the first wear value and the second wear value, compare the comprehensive wear value with a historical data set, determine whether to adjust the comprehensive wear value based on the comparison result, and when it is determined that the comprehensive wear value is to be adjusted, determine a target wear value based on the historical data set, and issue an early warning for the elevator component to be detected based on the target wear value.

[0043] It is understandable that the above-mentioned image-based elevator component wear warning method and system have the same beneficial effects and will not be described in detail here. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiment below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present invention. The same reference symbols are used throughout the drawings to represent the same components. In the drawings:

[0045] Figure 1 A flowchart of an image-based elevator component wear warning method provided by an embodiment of the present invention;

[0046] Figure 2 This is a functional block diagram of an image-based elevator component wear warning system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0047] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art. It should be noted that, unless there is a conflict, the embodiments of the present disclosure and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

[0048] In some embodiments of the present application, see Figure 1 As shown, an image-based early warning method for elevator component wear includes:

[0049] S100: Determine the elevator parts to be inspected, shoot the elevator parts to be inspected in several directions to determine an image data set, process the image data set to determine an initial part image, and determine a target part image based on the component image model and the initial part image.

[0050] S200: extract all pixel points of the target part image, establish wear marks for the elevator parts to be inspected based on all pixel points, extract wear pixel points of the target part image based on the established wear marks, and determine a first wear value according to the wear pixel values ​​of the wear pixel points.

[0051] S300: Determine the component position of the elevator component to be inspected, determine the wear detection area based on the component position, deploy several environmental acquisition points in the wear detection area, and obtain environmental feature data corresponding to each environmental acquisition point, and determine the second wear value based on all the environmental feature data.

[0052] S400: Determine the comprehensive wear value of the elevator component to be inspected based on the first wear value and the second wear value, compare the comprehensive wear value with the historical data set, and determine whether to adjust the comprehensive wear value based on the comparison result. When it is determined to adjust the comprehensive wear value, determine the target wear value based on the historical data set, and issue an early warning to the elevator component to be inspected based on the target wear value.

[0053] Specifically, image acquisition equipment such as machine vision and infrared cameras are used to capture images of the elevator parts to be inspected from multiple angles, including up, down, front, back, left, and right. This ensures that the image dataset fully captures the elevator parts to be inspected, preventing blind spots from a single angle that might cause parts to be missed. Since images are captured from different angles, the narrow elevator environment can interfere with the data collection process, resulting in some interference in the image dataset. Therefore, the image dataset is processed to determine the initial part image to eliminate interference from environmental noise and other factors. However, the initial part image after processing may be incomplete. Verification is performed based on the component image model to avoid image incompleteness affecting the final judgment result, laying the foundation for subsequent wear detection. All pixels in the target part image are extracted to establish a wear signature. Possible wear is identified based on changes in pixels. When a component wears, the surface morphology changes, which are reflected in the image as differences in pixel values. Through detailed pixel analysis, the worn pixels in the target part image can be accurately determined, thereby quantifying the wear of the elevator component to be inspected and determining a first wear value. The components to be inspected may be located in the car, traction device, and guide device. The actual environments these components are exposed to may not be completely consistent. For example, the car is a passenger or cargo carrying space, while the traction device is located in the elevator shaft. Therefore, the wear detection area is determined based on the component location, and a number of environmental acquisition points are deployed in the wear detection area. The number of environmental acquisition points is preferably 20, and the specific number of environmental acquisition points can be dynamically set according to the wear detection area. Humidity sensors, temperature sensors, and air pressure sensors are used to collect environmental characteristic data. These data include temperature, humidity, air pressure, and dust, which are key environmental factors critical to the stable operation of elevators. This data is used to quantify the impact of component wear and determine a secondary wear value, improving the comprehensiveness and reliability of wear warnings. The combined wear value is determined by combining the primary and secondary wear values ​​and then compared with historical data sets. Using historical data as a reference, comparative analysis ensures the stability of warnings.

[0054] It is understandable that image-based detection and early warning avoids errors caused by human subjective judgment and improves the reliability of detection and early warning. Moreover, the detection process is not restricted by the elevator space, thereby improving detection efficiency and shortening the detection cycle, providing strong guarantees for the safe operation of elevators and effectively reducing safety accidents caused by wear of components.

[0055] In some embodiments of the present application, when processing an image dataset to determine an initial part image, it includes: preprocessing the image dataset, the preprocessing includes image denoising and geometric correction, extracting feature points from the preprocessed image dataset, matching and registering the extracted feature points, merging the registered image datasets to determine a merged image, and performing image processing on the merged image to determine the initial part image, the image processing includes adjusting the image contrast and sharpening the image edges.

[0056] Specifically, image denoising uses filtering algorithms and other techniques to remove noise generated during the shooting process due to factors such as lighting and equipment, thereby improving the clarity of the image dataset and preventing noise from affecting the subsequent identification of elevator parts to be inspected. Geometric correction uses mathematical transformations to correct image deformation caused by shooting angle and lens distortion, ensuring the accuracy of the size and shape of the elevator parts to be inspected. Feature point extraction uses algorithms such as SIFT or SURF to find representative points (feature points) in the image dataset for subsequent image matching. Feature point matching and registration criteria correspond to feature points of images taken from different orientations to eliminate perspective differences. Feature point matching can be performed using the RANSAC algorithm, while registration can be performed using weighted mean and multi-band fusion techniques. The merged image is the process of fusing the registered image dataset into an image that fully presents the entire appearance of the elevator parts to be inspected. Image processing is performed on the merged image to determine the initial part image. Adjusting the image contrast enhances the surface details of the elevator parts to be inspected, and sharpening the image edges highlights the outline of the elevator parts to be inspected, laying the data foundation for subsequent detection.

[0057] In some embodiments of the present application, when determining a target part image based on a component image model and an initial part image, it includes: obtaining an image feature set, and dividing the image feature set into an image training set and an image test set according to a sampling ratio, pre-selecting a convolutional neural network model, training the convolutional neural network model according to the image training set, testing the trained convolutional neural network model according to the image test set, determining the component image model according to the test results, substituting the initial part image into the component image model to output a verification value of the initial part image, if the verification value is greater than a verification threshold, determining the initial part image as the target part image, and if the verification value is less than or equal to the verification threshold, re-acquiring the image data set of the elevator component to be detected.

[0058] Specifically, obtain the image feature set, which includes key data such as texture features (metallic gloss and processing lines, etc.), color features (color distribution), and size features (length, width, height, and spacing, etc.) of the elevator parts to be inspected. Divide the image feature set into an image training set and an image test set according to the sampling ratio. The sampling ratio is usually 7:3 to ensure that both the image training set and the image test set contain various data to improve the generalization ability of the model. Pre-select a convolutional neural network model. The convolutional neural network model contains multiple convolutional layers, pooling layers, and fully connected layers, designed to capture complex relationships in the data. The image training set is used to train the convolutional neural network model, and the image test set is used to test and evaluate the trained convolutional neural network model. The test indicators include accuracy, F1 score, and recall rate, which are used to measure the performance of the model.

[0059] It is understandable that during each training process, the model will try to learn the patterns and relationships in the data to improve its prediction or classification capabilities. If the test value of the currently trained convolutional neural network model is less than the test value of the previously trained convolutional neural network model, it means that the model performance has declined. At this time, it is necessary to reduce the amplitude of the model change in the gradient direction (i.e., the learning rate). Then, the learning rate is adjusted according to the cosine annealing method, and training is continued until the test value is greater than or equal to the test value of the previously trained convolutional neural network model, which helps the model to stably approach the global optimal solution. If the test value of the currently trained convolutional neural network model is greater than or equal to the test value of the previously trained convolutional neural network model, it means that the performance of the model has stabilized and increased. Then, the iterative training can be stopped, and the currently trained convolutional neural network model is determined as the component image model. The component image model can learn and distinguish the key features of the image. Since the component image model is obtained based on the convolutional neural network model, the convolutional neural network model can output the probability of image verification through the softmax function, i.e., the verification value of the initial part image. According to the verification value, it is dynamically determined whether to re-acquire the image dataset of the elevator parts to be inspected, thereby ensuring the stability and reliability of the target part image.

[0060] In some embodiments of the present application, when establishing a wear mark for an elevator component to be inspected based on all pixel points, it includes: determining a target qualified part image corresponding to the target part image, extracting all pixel points of the target part image, and extracting all qualified pixel points from the target qualified part image, and each pixel point corresponds to a qualified pixel point, determining the pixel values ​​corresponding to all pixel points, and determining the qualified pixel values ​​corresponding to all qualified pixel points, establishing a wear mark for the elevator component to be inspected based on the relationship between the pixel value and the qualified pixel value, and the wear mark includes a qualified mark, a wear mark and a suspected wear mark.

[0061] Specifically, the target qualified part image is obtained based on the qualified elevator parts to be inspected, and is specifically determined based on the unopened use or the provided certificate of qualification. Each pixel point corresponds to a qualified pixel point, ensuring the correspondence between the pixel value and the qualified pixel value. When establishing a wear mark for the elevator parts to be inspected based on the relationship between the pixel value and the qualified pixel value, if all the pixel values ​​are equal to the qualified pixel value, a qualified mark is established for the elevator parts to be inspected. The qualified mark indicates that the elevator parts to be inspected have not been worn and can continue to be used without issuing an early warning. If all the pixel values ​​are not equal to the qualified pixel value, a wear mark is established for the elevator parts to be inspected. The wear mark indicates that the elevator parts to be inspected have been worn and need to stop being used and directly issue an early warning. If there are one or more pixel values ​​that are not equal to the qualified pixel value, a suspected wear mark is established for the elevator parts to be inspected. The suspected wear mark indicates that the elevator parts to be inspected may have been worn and need to be analyzed, ensuring the adaptability and stability of the wear early warning.

[0062] In some embodiments of the present application, when extracting wear pixel points of a target part image based on an established wear mark and determining a first wear value according to the wear pixel value of the wear pixel point, it includes: the wear pixel point includes a first wear pixel point and a second wear pixel point. If the wear mark established for the elevator component to be inspected is a suspected wear mark, the pixel point corresponding to the pixel value greater than the qualified pixel value in the target part image is recorded as the first wear pixel point, and the pixel point corresponding to the pixel value less than the qualified pixel value in the target part image is recorded as the second wear pixel point. All the first wear pixel points and all the second wear pixel points in the target part image are extracted, and the first wear value is determined based on all the first wear pixel points and all the second wear pixel points.

[0063] Specifically, all first wear pixel points and all second wear pixel points are extracted, the first maximum wear pixel value and the first minimum wear pixel value among all first wear pixel points are determined, the second maximum wear pixel value and the second minimum wear pixel value among all second wear pixel points are determined, the difference between the first maximum wear pixel value and the first minimum wear pixel value is determined as the first difference, the difference between the second maximum wear pixel value and the second minimum wear pixel value is determined as the second difference, and the product value of the first difference and the second difference is determined as the first wear value.

[0064] It is understandable that when the elevator parts to be inspected may be worn, the surface morphology changes will be reflected as changes in pixel values ​​on the image. The qualified pixel value is used as the judgment basis to divide the pixel points into first wear pixel points and second wear pixel points. The first wear pixel points that are greater than the qualified pixel value correspond to surface protrusions and material accumulation on the elevator parts to be inspected, and the second wear pixel points that are less than the qualified pixel value correspond to surface depressions and material peeling on the elevator parts to be inspected. By extracting all two types of wear pixel points and determining their corresponding maximum and minimum wear pixel values, the first difference and the second difference are calculated, and the product of the first difference and the second difference is determined as the first wear value. The difference in pixel values ​​is used to quantify the degree of wear, and the range of pixel value changes and relative differences are comprehensively considered. It can more comprehensively and meticulously reflect the actual wear situation, thereby issuing a warning in a timely manner, thereby ensuring the safe operation of the elevator.

[0065] In some embodiments of the present application, when determining the wear detection area based on the component position, it includes: extending in all directions with the geometric center of the component position as the center point to form a rectangular space with a length and width of s and a height of h, and deleting the rectangular space based on the component position to determine the wear detection area.

[0066] Specifically, when deleting the rectangular space, the deletion is determined dynamically based on the position of the component. When the component is located in the car (possibly at the top, middle or bottom of the car), in the process of extending in all directions, the wear detection area finally determined is located inside the car, and does not exceed the car. For example: when the component is located at the top of the car, it is extended in all directions to form a rectangular space. When the extended height h touches the bottom of the car, the area containing the interior of the car is determined as the wear detection area, and the other areas are deleted. The same is true for the middle and bottom of the car. When the component is located outside the car (in the elevator shaft), in the process of extending in all directions, the area covering the interior of the elevator shaft is determined as the wear detection area, and the other areas are deleted. This ensures the adaptability and flexibility of dynamically determining the wear detection area for the component position, thereby dynamically detecting the environment in which the component position is located, and improving the comprehensiveness and stability of the early warning.

[0067] In some embodiments of the present application, several environmental acquisition points are deployed in the wear detection area, and environmental characteristic data corresponding to each environmental acquisition point is obtained. When the second wear value is determined based on all the environmental characteristic data, it includes: comparing the environmental characteristic data of each environmental acquisition point with the standard environmental characteristic data; if the environmental characteristic data of the environmental acquisition point are all greater than the standard environmental characteristic data, the environmental acquisition point is recorded as the first acquisition point; if the environmental characteristic data of the environmental acquisition point are all less than the standard environmental characteristic data, the environmental acquisition point is recorded as the second acquisition point; if there is one or more environmental characteristic data greater than the standard environmental characteristic data at the environmental acquisition point, and there is one or more environmental characteristic data less than or equal to the standard environmental characteristic data, the environmental acquisition point is recorded as a pending acquisition point, the first number of the first acquisition points and the second number of the second acquisition points are counted, and the second wear value is determined according to the first number and the second number.

[0068] Specifically, the number of environmental acquisition points is preferably 20, and the specific number of environmental acquisition points can be dynamically set according to the wear detection area. Environmental characteristic data is acquired using acquisition devices such as humidity sensors, temperature sensors, and air pressure sensors. Environmental characteristic data includes temperature, humidity, air pressure, and dust, which are environmental characteristic factors for stable elevator operation. Standard environmental characteristic data is determined based on the instructions for use of the elevator components to be tested. The product of the first and second quantities is determined as the second wear value. The larger the second wear value, the greater the degree to which the elevator components to be tested deviate from the standard environment and the greater the probability of wear. The second wear value is determined based on the first and second quantities, ensuring the comprehensiveness and reliability of early warning of elevator component detection.

[0069] In some embodiments of the present application, when determining the comprehensive wear value of the elevator component to be tested based on the first wear value and the second wear value, comparing the comprehensive wear value with the historical data set, and determining whether to adjust the comprehensive wear value based on the comparison result, it includes: the comprehensive wear value is the product of the first wear value and the second wear value, the historical data set includes a historical comprehensive wear average, several historical comprehensive wear values ​​and several historical wear adjustment factors, and each historical comprehensive wear value corresponds to a historical wear adjustment factor, the comprehensive wear value is compared with the historical comprehensive wear average, if the comprehensive wear value is greater than or equal to the historical comprehensive wear average, it is determined not to adjust the comprehensive wear value, and the comprehensive wear value is determined as the target wear value, if the comprehensive wear value is less than the historical comprehensive wear average, it is determined to adjust the comprehensive wear value.

[0070] Specifically, multiplying the first wear value (image analysis result) by the second wear value (environmental influence) is essentially a comprehensive analysis of the presence of certain wear and environmental adaptability. When both the first and second wear values ​​are high, the product amplifies the wear assessment of the elevator component under inspection. However, when either is low, the false alarm rate can be appropriately reduced. For example, if the first wear value is low but the second wear value is high (due to harsh environmental conditions), the product of the two will still indicate a high wear risk. The historical average comprehensive wear value represents the average wear level of similar components. Using it as a benchmark value can reflect the group characteristics of the elevator components under inspection. If the current comprehensive wear value is lower than the historical average comprehensive wear value, it may indicate that the wear characteristics are not obvious, there are individual differences between components, or the potential impact of environmental factors has not yet fully manifested, thus requiring adjustment. By introducing the historical average comprehensive wear value as a reference benchmark, the accuracy and automation of the comprehensive wear value adjustment are improved, the interference and error of human judgment are reduced, and the adaptability to different conditions and the comprehensiveness of the warning are enhanced.

[0071] In some embodiments of the present application, when determining to adjust the comprehensive wear value, a target wear value is determined based on a historical data set, and when an early warning is issued for the elevator component to be detected according to the target wear value, it includes: comparing the comprehensive wear value with the historical data set; if there is a historical comprehensive wear value equal to the comprehensive wear value in the historical data set, adjusting the comprehensive wear value by a historical wear adjustment factor corresponding to the historical comprehensive wear value; if there is no historical comprehensive wear value equal to the comprehensive wear value in the historical data set, obtaining a historical comprehensive wear value with the maximum similarity to the comprehensive wear value, and adjusting the comprehensive wear value by a historical wear adjustment factor corresponding to the historical comprehensive wear value; the target wear value is the product of the historical wear adjustment factor and the comprehensive wear value; comparing the target wear value with a target wear threshold; if the target wear value is greater than or equal to the target wear threshold, determining that the elevator component to be detected is worn and an early warning is issued; if the target wear value is less than the target wear threshold, determining that the elevator component to be detected is not worn and no early warning is issued.

[0072] Specifically, by determining the degree of match between the comprehensive wear value and the historical data set, when the same historical comprehensive wear value is found, the historical wear adjustment factor can be directly determined using this data, thereby ensuring the reliability and consistency of the adjustment. If there are multiple identical historical comprehensive wear values, the comprehensive wear value is adjusted by taking the average of the historical wear adjustment factors corresponding to each historical comprehensive wear value, and the target wear value is the product of the average and the comprehensive wear value. In the case where the comprehensive wear value does not completely match the historical comprehensive wear value, the corresponding historical wear adjustment factor is determined by determining the historical comprehensive wear value with the maximum similarity. The similarity can be determined by Euclidean distance or cosine similarity, etc. Determining the corresponding historical wear adjustment factor based on the historical comprehensive wear value with the maximum similarity can effectively respond to changes in adjustments. Through data-driven automated adjustments, reliance on human experience and intuition is reduced, and the uncertainty and detection risks brought about by human judgment are reduced, thereby improving the automation and accuracy of early warnings for elevator components to be inspected. By comprehensively utilizing a large amount of historical data, rich reference information is provided for the adjustment of the comprehensive wear value. The target wear threshold is used to distinguish whether the elevator parts to be inspected are worn. The target wear threshold can be set dynamically. By comparing the target wear value with the target wear threshold and integrating the image analysis results, environmental factors and historical data, the risks of low manual inspection efficiency and long inspection cycle are avoided, and the accuracy and reliability of wear warnings for elevator parts to be inspected are improved.

[0073] In summary, the beneficial effects of the present invention are as follows: by constructing an image dataset through shooting from several directions, accurately processing the initial part image in combination with the component image model, and establishing wear marks based on pixel-level analysis, thereby accurately extracting wear pixels and calculating the first wear value, reflecting the degree of wear through the change in pixel value, effectively avoiding subjective errors and improving the reliability of early warning. Through the automated image acquisition and analysis process, early warning can be issued for the wear of the elevator parts to be inspected. At the same time, by deploying several environmental acquisition points in the wear detection area, the relevant environment of the elevator parts to be inspected can be fully covered, and environmental feature data can be acquired in real time and the second wear value can be calculated, thus realizing the monitoring of the operating environment of the elevator parts to be inspected. The comprehensive wear value is determined by comprehensively considering the image analysis and the operating environment, and the comprehensive wear value is dynamically adjusted according to the historical data set to determine the target wear value that fits the actual operating conditions. The data-driven dynamic early warning mechanism can track the wear of the elevator parts to be inspected in real time, thereby avoiding safety accidents caused by accumulated wear and providing reliable protection for the safe operation of the elevator.

[0074] In another preferred embodiment based on the above embodiment, refer to Figure 2As shown, this embodiment provides an image-based elevator component wear warning system, which is used to apply the above-mentioned image-based elevator component wear warning method, including:

[0075] The data acquisition module is configured to determine the elevator parts to be inspected, and to shoot the elevator parts to be inspected in several orientations to determine an image data set, process the image data set to determine an initial part image, and determine a target part image based on the component image model and the initial part image.

[0076] The first processing module is configured to extract all pixel points of the target part image, establish wear marks for the elevator parts to be inspected based on all pixel points, extract wear pixel points of the target part image based on the established wear marks, and determine a first wear value according to the wear pixel values ​​of the wear pixel points.

[0077] The second processing module is configured to determine the component position of the elevator component to be inspected, determine the wear detection area based on the component position, deploy a number of environmental acquisition points in the wear detection area, and obtain environmental feature data corresponding to each environmental acquisition point, and determine the second wear value based on all the environmental feature data.

[0078] The comprehensive early warning module is configured to determine the comprehensive wear value of the elevator component to be inspected based on the first wear value and the second wear value, compare the comprehensive wear value with the historical data set, and determine whether to adjust the comprehensive wear value based on the comparison result. When it is determined that the comprehensive wear value should be adjusted, a target wear value is determined based on the historical data set, and an early warning is issued for the elevator component to be inspected based on the target wear value.

[0079] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or a combination of software and hardware embodiments. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0080] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0081] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0082] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0083] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the scope of protection of the claims of the present invention.

Claims

1. An image-based early warning method for elevator component wear, characterized in that: include: Determine an elevator component to be inspected, photograph the elevator component in several orientations to determine an image dataset, process the image dataset to determine an initial part image, and determine a target part image based on a component image model and the initial part image; Extracting all pixel points of the target part image, establishing a wear mark for the elevator component to be inspected based on all pixel points, extracting worn pixel points of the target part image based on the established wear mark, and determining a first wear value according to the wear pixel values ​​of the worn pixel points; Determining a component position of an elevator component to be inspected, determining a wear detection area based on the component position, deploying a plurality of environmental acquisition points in the wear detection area, acquiring environmental characteristic data corresponding to each environmental acquisition point, and determining a second wear value based on all the environmental characteristic data; Based on the first wear value and the second wear value, a comprehensive wear value of the elevator component to be inspected is determined, the comprehensive wear value is compared with a historical data set, and it is determined whether to adjust the comprehensive wear value based on the comparison result. When it is determined that the comprehensive wear value is to be adjusted, a target wear value is determined based on the historical data set, and an early warning is issued for the elevator component to be inspected based on the target wear value.

2. The image-based elevator component wear warning method according to claim 1, characterized in that: When the image data set is processed to determine the initial part image, the method includes: Preprocessing the image data set, wherein the preprocessing includes image denoising and geometric correction; Extract feature points from the preprocessed image dataset, match and register the extracted feature points, and merge the registered image datasets to determine a merged image; The merged image is subjected to image processing to determine the initial part image, wherein the image processing includes adjusting image contrast and sharpening image edges.

3. The image-based elevator component wear warning method according to claim 2, characterized in that: When determining a target part image based on the component image model and the initial part image, the method includes: Obtaining an image feature set, and dividing the image feature set into an image training set and an image test set according to a sampling ratio, preselecting a convolutional neural network model, training the convolutional neural network model based on the image training set, testing the trained convolutional neural network model based on the image test set, and determining the component image model based on the test results; The initial part image is substituted into the component image model to output a verification value of the initial part image. If the verification value is greater than a verification threshold, the initial part image is determined as the target part image. If the verification value is less than or equal to the verification threshold, the image dataset of the elevator component to be inspected is reacquired.

4. The image-based elevator component wear warning method according to claim 3, characterized in that: When establishing wear marks for the elevator parts to be inspected based on all pixel points, the method includes: Determine a target qualified part image corresponding to the target part image, extract all pixels of the target part image, and extract all qualified pixels from the target qualified part image, wherein each pixel corresponds to a qualified pixel; Determining pixel values ​​corresponding to all pixel points, and determining qualified pixel values ​​corresponding to all qualified pixel points, and establishing a wear mark for the elevator component to be inspected based on the relationship between the pixel values ​​and the qualified pixel values; The wear marks include qualified marks, wear marks and suspected wear marks.

5. The image-based elevator component wear warning method according to claim 4, characterized in that: When extracting worn pixels of the target part image based on the established wear mark and determining a first wear value according to the wear pixel values ​​of the worn pixels, the method includes: The worn pixel points include a first worn pixel point and a second worn pixel point; If the wear mark established for the elevator component to be inspected is the suspected wear mark, the pixel point corresponding to the pixel value greater than the qualified pixel value in the target part image is recorded as the first wear pixel point, and the pixel point corresponding to the pixel value less than the qualified pixel value in the target part image is recorded as the second wear pixel point; All first wear pixel points and all second wear pixel points in the target part image are extracted, and the first wear value is determined based on all first wear pixel points and all second wear pixel points.

6. The image-based elevator component wear warning method according to claim 5, characterized in that: When determining the wear detection area based on the component position, it includes: The geometric center of the component position is extended in all directions to form a rectangular space with a length and width of s and a height of h. The wear detection area is determined by deleting the rectangular space based on the component position.

7. The image-based elevator component wear warning method according to claim 6, characterized in that: Deploying a plurality of environment acquisition points in the wear detection area, acquiring environment characteristic data corresponding to each environment acquisition point, and determining the second wear value based on all the environment characteristic data includes: Compare the environmental characteristic data of each environmental acquisition point with the standard environmental characteristic data; if the environmental characteristic data of the environmental acquisition point are all greater than the standard environmental characteristic data, record the environmental acquisition point as the first acquisition point; if the environmental characteristic data of the environmental acquisition point are all less than the standard environmental characteristic data, record the environmental acquisition point as the second acquisition point; if one or more environmental characteristic data of the environmental acquisition point are greater than the standard environmental characteristic data, and one or more environmental characteristic data are less than or equal to the standard environmental characteristic data, record the environmental acquisition point as a pending acquisition point; A first number of the first acquisition points and a second number of the second acquisition points are counted, and the second wear value is determined according to the first number and the second number.

8. The image-based elevator component wear warning method according to claim 7, characterized in that: Determining a comprehensive wear value of the elevator component to be inspected based on the first wear value and the second wear value, comparing the comprehensive wear value with a historical data set, and determining whether to adjust the comprehensive wear value based on the comparison result, including: The comprehensive wear value is the product of the first wear value and the second wear value; The historical data set includes a historical comprehensive wear average, several historical comprehensive wear values ​​and several historical wear adjustment factors, and each historical comprehensive wear value corresponds to a historical wear adjustment factor. The comprehensive wear value is compared with the historical comprehensive wear average. If the comprehensive wear value is greater than or equal to the historical comprehensive wear average, it is determined that the comprehensive wear value will not be adjusted, and the comprehensive wear value is determined as the target wear value. If the comprehensive wear value is less than the historical comprehensive wear average, it is determined that the comprehensive wear value is adjusted.

9. The image-based elevator component wear warning method according to claim 8, characterized in that: When determining to adjust the comprehensive wear value, determining a target wear value based on the historical data set, and issuing an early warning for the elevator component to be inspected according to the target wear value, the method includes: Comparing the comprehensive wear value with a historical data set, if a historical comprehensive wear value equal to the comprehensive wear value exists in the historical data set, adjusting the comprehensive wear value by a historical wear adjustment factor corresponding to the historical comprehensive wear value; if a historical comprehensive wear value equal to the comprehensive wear value does not exist in the historical data set, obtaining a historical comprehensive wear value with the greatest similarity to the comprehensive wear value, and adjusting the comprehensive wear value by the historical wear adjustment factor corresponding to the historical comprehensive wear value; The target wear value is the product of the historical wear adjustment factor and the comprehensive wear value; The target wear value is compared with the target wear threshold. If the target wear value is greater than or equal to the target wear threshold, it is determined that the elevator component to be detected is worn and an early warning is issued. If the target wear value is less than the target wear threshold, it is determined that the elevator component to be detected is not worn and no early warning is issued.

10. An image-based elevator component wear warning system, used to apply the image-based elevator component wear warning method according to any one of claims 1 to 9, characterized in that: include: a data acquisition module configured to determine an elevator component to be inspected, photograph the elevator component to be inspected in a plurality of orientations to determine an image data set, process the image data set to determine an initial part image, and determine a target part image based on a component image model and the initial part image; a first processing module configured to extract all pixels of the target part image, establish a wear mark for the elevator component to be inspected based on all pixels, extract worn pixels of the target part image based on the established wear mark, and determine a first wear value according to the wear pixel values ​​of the worn pixels; a second processing module configured to determine a component position of an elevator component to be inspected, determine a wear detection area based on the component position, deploy a plurality of environment acquisition points in the wear detection area, acquire environmental characteristic data corresponding to each environment acquisition point, and determine a second wear value based on all the environmental characteristic data; The comprehensive early warning module is configured to determine a comprehensive wear value of the elevator component to be detected based on the first wear value and the second wear value, compare the comprehensive wear value with a historical data set, determine whether to adjust the comprehensive wear value based on the comparison result, and when it is determined that the comprehensive wear value is to be adjusted, determine a target wear value based on the historical data set, and issue an early warning for the elevator component to be detected based on the target wear value.

Images