Automatic defect detection of wire ropes using image processing techniques

Abstract

Embodiments of automatic defect detection for flexible components using image processing are provided. The technique includes monitoring the flexible component via one or more sensors to obtain sensor data, converting the sensor data from the one or more sensors into image data, and receiving reference image data to compare with the image data. The technique also includes determining a defect based on the comparison and threshold setting information of the flexible component, and sending a notification based on the defect.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims the benefit of Indian Application No. 201811038485 filed on October 10, 2018, which is incorporated herein by reference in its entirety. Background Art

[0003] Embodiments described herein relate generally to health monitoring and, more particularly, to automated defect detection of steel ropes using image processing techniques.

[0004] The use of cables and wire ropes is found across all types of industries and applications. For example, cables are used in elevators, winches, cranes, etc. These applications include safety critical applications such as manned rescue missions. These cables need to be inspected regularly to determine if there are any defects. There are various types of defects that can occur such as wire rope breakage, rope breakage, etc. due to fatigue, heavy loads, or other events. Cable inspections may need to be performed consistently and efficiently. Summary of the invention

[0005] According to one embodiment, a system for automatic defect detection of a flexible member using image processing is provided, the system comprising: one or more sensors configured to monitor the flexible member; an image processor configured to convert sensor data from the one or more sensors into image data; and a processing module configured to receive reference image data. The processing module is further configured to compare the image data with the reference image data, determine a defect based on the comparison and threshold setting information of the flexible member, and send a notification based on the defect.

[0006] In addition to or as an alternative to one or more of the features described herein, further embodiments include a processing module configured to determine the defect, wherein determining the defect further includes classifying the defect into one or more categories based at least in part on the defect.

[0007] In addition to, or instead of, one or more of the features described herein, further embodiments include one or more sensors that are optical fibers.

[0008] In addition to or instead of one or more of the features described herein, further embodiments include a flexible member that is at least one of a rope, a wire, a belt, and a chain.

[0009] In addition to, or in lieu of, one or more of the features described herein, further embodiments include using flexible member based reference image data.

[0010] In addition to or in lieu of one or more of the features described herein, further embodiments include threshold setting information based on an application type of the flexible member.

[0011] In addition to or instead of one or more of the features described herein, further embodiments include a processing module configured to determine a location of a defect in the flexible member.

[0012] In addition to or in lieu of one or more of the features described herein, further embodiments include a notification that includes the location of the defect, the number of defects, the type of defect, or a recommendation to perform repairs associated with the flexible member.

[0013] According to another embodiment, a method for automatic defect detection of a flexible member using image processing is provided. The method includes monitoring the flexible member via one or more sensors to obtain sensor data, converting the sensor data from the one or more sensors into image data, and receiving reference image data to compare with the image data. The method also includes determining a defect based on the comparison and threshold setting information of the flexible member, and sending a notification based on the defect.

[0014] In addition to or as an alternative to one or more of the features described herein, further embodiments include determining the defect, wherein determining the defect further includes classifying the defect into one or more categories based at least in part on the defect.

[0015] In addition to, or instead of, one or more of the features described herein, further embodiments include one or more sensors that are optical fibers.

[0016] In addition to or instead of one or more of the features described herein, further embodiments include a flexible member that is at least one of a rope, a wire, a belt, and a chain.

[0017] In addition to or instead of one or more of the features described herein, further embodiments include reference image data based on the flexible member.

[0018] In addition to or instead of one or more of the features described herein, further embodiments include using threshold setting information based on an application type of the flexible member.

[0019] In addition to or instead of one or more of the features described herein, further embodiments include determining a location of a defect in a flexible member.

[0020] In addition to or in lieu of one or more of the features described herein, further embodiments include a notification that includes the location of the defect, the number of defects, the type of defect, or a recommendation to perform repairs associated with the flexible member.

[0021] Technical effects of embodiments of the present disclosure include using optical fibers, lenses, and image sensors and image processors to consistently and effectively monitor the health of cables and wire ropes.

[0022] Unless otherwise expressly indicated, the above features and elements may be combined in various combinations without being exclusive. These features and elements and their operation will become more apparent from the following description and accompanying drawings. However, it should be understood that the following description and accompanying drawings are intended to be illustrative and explanatory in nature, rather than limiting. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The following description should not be considered limiting in any way. Referring to the accompanying drawings, like elements are numbered the same:

[0024] Figure 1 Depicted is a system for automatic defect detection of steel wire ropes using image processing techniques according to one or more embodiments;

[0025] Figure 2 depicts arrangements of systems according to one or more embodiments;

[0026] Figure 3 depicts an arrangement of optical ports according to one or more embodiments;

[0027] Figure 4 Describes a process flow for automatic defect detection of steel wire rope using image processing according to one or more embodiments; and

[0028] Figure 5 A flow chart is depicted of a method for automatic defect detection of a steel rope using image processing techniques according to one or more embodiments. DETAILED DESCRIPTION

[0029] In today's environment, ropes, cables and cords (generally referred to as "ropes") are used in a variety of applications. The application in which the ropes are used may determine how often they will be inspected and the tolerance within which the ropes are allowed to be replaced / repaired. For safety-critical applications, frequent inspections may be required, such as every 100 cycles or every 10 hours of operation, while non-safety-critical applications may be inspected at longer intervals.

[0030] Ropes are flexible members and may be subjected to sudden loads and external disturbances where the load on the rope exceeds the rated load of the rope. Additionally, ropes may be subjected to repeated loads which may eventually lead to defects. These defects may include kinks, localized twisting (strand problems caused by metal-to-metal contact), dirt, corrosion, and many other factors. Ropes are inspected by trained technicians and the health of a rope may vary based on manual inspection by different maintenance technicians. The skill and experience of the maintenance technician may inform his assessment of the health of the rope, which may result in a range of subjectivity for the same rope and / or defects.

[0031] Additionally, rope inspections cannot be performed during operation. As a result, an installation including a rope and / or flexible member may be downtime due to the time it takes to remove the rope and send it for inspection. The length of the rope may vary depending on its application. For example, ropes used in elevators may vary in length, adding additional time to the inspection procedure. Furthermore, different types of ropes may exhibit different types of defects, and the service technician must be aware of each type of rope, their tolerances, and associated defects.

[0032] The technology described herein provides a non-invasive diagnostic method for monitoring the health of a rope by using image processing techniques. In addition, the technology provides a prognostic analysis of a rope or other flexible member. The technology described herein can use one or more sensors to collect data about the rope and monitor the health of the rope, wherein the sensor can include a fiber optic sensor.

[0033] The techniques described herein also provide for defect detection by using image processing and analysis methods. A variety of algorithms can be used to analyze the defects of the rope, and the algorithm that best suits the application can be selected. One or more techniques include a defect detection method that classifies the fault type and also ranks the severity of the operating gap based on the application of the rope. For example, a safety critical application such as a rescue mission may require a tighter threshold tolerance than a non-safety critical application.

[0034] The technology described herein also provides for consistent defect detection in ropes or other flexible members, which is the determination of the number of defects, the type of defects, the location of the defects in the rope, and other information related to the rope. In one or more embodiments, the system can be updated based on the collected field failure data to improve the overall detection efficiency and to correlate defects of different types of ropes with rope health.

[0035] exist Figure 1In the present invention, a system 100 for performing an automatic defect detection method for a rope using image processing according to one or more embodiments is provided.

[0036] The system 100 includes an image capture device 102 located within the control electronics of a wire rope handling device 130. The wire rope handling device 130 includes a mount 104 and is configured to monitor a flexible member 106, such as a rope, belt, wire, etc. The mount 104 can be positioned near the location where the flexible member 106 is dispensed from a device controlling it. In one or more embodiments, the image capture device 102 includes one or more sensors, such as optical fibers, configured to detect sensor data from the flexible member 106 by providing light on the surface of the flexible member 106 and analyzing the light reflected off the surface of the flexible member 106. The sensor is positioned to detect the entire surface of the flexible member 106. In this non-limiting example, there are three optical fibers (L1, L2, and L3) that are used to detect sensor data from the flexible member.

[0037] System 100 also includes an image conversion system 108 configured to receive sensor data from image capture device 102 and convert the sensor data into image data. In a non-limiting example, the sensor data is optical light data, and the light information is converted to form an image of flexible member 106. Figure 1 Also depicted is an image processor 110, which is configured to enhance image data from the conversion system 108 for further processing. The image processor 110 is configured to increase the sharpness of the image data, remove blur, remove distortion, crop the image to a region of interest, make the image monochrome, etc., to make the image suitable for further processing and analysis for defect detection.

[0038] The processing module 110 is configured to execute a variety of algorithms to process the image data received from the image processor 110. The processing module 110 is also configured to receive reference image data from a reference image data source 114 and threshold setting information from a threshold setting source 116. The reference image data and threshold setting information correspond to the type of flexible member 106 monitored by the system 100 and are used to compare the current flexible member 106 with a healthy or new flexible member. The reference image information may include information such as rope type, length, diameter, strand information, rope / strand pattern, etc. The threshold setting information may include information such as defect type, defect category mapped to rope remaining life or strength. It should be understood that other types of information may also be included in the reference image and threshold setting information, and the information may vary for each type of rope and application in which the rope is used. For example, the same rope used for two different applications may have different acceptable tolerances and operating thresholds.

[0039] In response to processing and analyzing the current image of flexible member 106 using the reference image and the threshold setting information, processing module 112 may send the results to display 118 .

[0040] In one or more embodiments, a display 118 may be included in the system 100 to display the results of the analysis. The display 118 may present graphical data, textual data, visual images of the rope, etc. The display 118 may also present notification information to the operator indicating information such as the health of the rope, including the severity of any defects that exist or recommendations on when the rope should be repaired / replaced.

[0041] In response to the results of the analysis, an alert may be sent to an operator or other user via the alert module 120. The alert may include information related to the defect type, rope defect severity, number of defects, repair and / or replacement recommendations, estimated repair time, visibility of the defect, etc. The results of the analysis performed by the system 100 may be stored in the storage device 122. Machine learning may optimize the type of defect and the remaining life of the rope as well as the recommendations provided for rope defects.

[0042] exist Figure 2 , a view of an arrangement 200 of a mount 104 for use in a system 100 according to one or more embodiments is shown. The device 102 includes a mount 104 configured to receive one or more sensors, such as optical fibers, for monitoring a flexible member 106. Each optical fiber includes optical fiber ports 202A, B, and C, such as Figure 3 Each optical fiber port 202 is configured to send and receive optical signals L1, L2 and L3 and has a field of view 204, such as Figure 2 shown.

[0043] In one or more embodiments, the optical fibers and ports 202 are spaced 120 degrees apart to cover the entire surface of the rope 106. In other embodiments, a different number of sensors, sensor types, spacing, etc., may be used to monitor the health of the rope. For example, where the system 100 is monitoring a belt, one or two sensor devices may be used to monitor the rope.

[0044] Reference now Figure 3 , shows an arrangement 300 of an internal view of an optical port 202. The optical port 202 is configured to attach to Figure 2 The housing / mount 104 is shown. The optical port 202 receives an optical cable 302 configured to exchange optical signal data to Figure 1The optical port 202 also includes one or more filters 304 and a lens 306. The optical port 202 includes a light source 308 configured to transmit light to the rope 106, and the optical port 202 is configured to receive reflected light data characterizing the surface of the rope 106 for further processing.

[0045] Reference now Figure 4 , a processing flow 400 for processing image data according to one or more embodiments is shown. As shown, at box 402, several inputs are received at the processing module 112 to use image processing techniques to automatically detect defects on the rope. In one or more embodiments, the input received at box 402 includes a data set 404, which includes captured image data, image file names, locations of rope segments, and reference image data. In one or more embodiments, the system 100 is configured to receive rope segment information from a winch, or a rope distribution system indicates the location of rope lengths that have been distributed. This information may include the size and number of turns of the drum used to distribute the rope. It should be understood that other techniques may be used. It should be understood that other data may be received and used for processing of image data. At box 406, the image data is converted into a black and white image for further processing.

[0046] The first marking technique 408A utilizes a Canny transform, which is used to compare the edges of the rope with a reference image. For example, the Canny transform process can be used to obtain loose strand information. The second marking technique 408B includes a differential filter for image gradient / image Laplacian magnitude, which is used to compare the current image with the reference image. Each frame can monitor a certain length of rope and divide the frame into smaller frames / windows for analysis against the reference frame. The third marking technique 408C includes using a block-based pixel color analysis for each segment of the rope. During processing, the image of the current rope can be provided in the form of a matrix and compared to the reference image, which is also provided in the form of a matrix. The two matrices can be further compared to each other and to the tolerance allowed by the threshold setting for this particular rope. At box 410, the defect images of various marking methods are voted. For example, the marking technique compares the reference image with the actual (defective) image. In addition, the voting process allows the use of threshold tolerances for various applications to determine whether the rope is suitable for operation or needs repair / replacement. It should be understood that the selection can be made according to configurable selections. The resulting defect image 412 may be provided to an operator in the form of a notification and / or provided for further analysis.

[0047] Reference now Figure 5, a flow chart of a method 500 for automatic defect detection of a flexible member using image processing techniques is provided. The method 500 begins at box 502 and proceeds to box 504, which provides monitoring the flexible member through one or more sensors to obtain sensor data. The method 500 continues to box 506 and is used to convert the sensor data from the one or more sensors into image data. Box 508 is used to receive reference image data and threshold setting information. At box 510, the method 500 is used to compare the image data with the reference image data. Box 512 is used to determine a defect based on the comparison and the threshold setting information. The method at box 514 is used to send a notification based on the defect. The method 500 ends at box 516.

[0048] Technical effects and benefits include real-time rope health monitoring that provides prognostic and diagnostic solutions. As a result, the reliability of the system is improved due to on-board diagnostics. Technical effects and benefits include reduced time for manual inspections and improved consistency in reporting rope health. Personnel safety is also improved when using wire ropes for both human and cargo applications. The system can be made more intelligent by using machine learning technology that is used to analyze field maintenance data to accurately identify defects and correlate defects with the remaining life of the rope.

[0049] A detailed description of one or more embodiments of the disclosed apparatus and methods is given herein by way of illustration and not limitation with reference to the accompanying figures.

[0050] The term "about" is intended to include the degree of error associated with the measurement of a particular quantity based on the equipment available at the time the application was filed.

[0051] The terms used herein are only used for the purpose of describing specific embodiments and are not intended to limit the present disclosure. As used herein, unless the context clearly indicates otherwise, the singular forms of "one", "a kind of" and "the / said" are also intended to include plural forms. It should also be understood that when used in this specification, the terms "include" and / or "comprise" specify the presence of the features, wholes, steps, operations, elements and / or parts, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, element parts and / or their groups.

[0052] Although the present disclosure has been described with reference to exemplary embodiments, it will be appreciated by those skilled in the art that various changes may be made and elements thereof may be substituted with equivalents without departing from the scope of the present disclosure. In addition, many modifications may be made to adapt specific circumstances or materials to the teachings of the present disclosure without departing from the essential scope of the present invention. Therefore, it is intended that the present disclosure is not limited to the specific embodiments disclosed as the best mode for implementing the present disclosure, but that the present disclosure will include all embodiments falling within the scope of the claims.

Claims

1. A system for automatic defect detection of a flexible component using image processing, the system comprising: a plurality of sensors configured to monitor a flexible member, wherein the plurality of sensors are three optical fibers, each optical fiber including a corresponding optical port, each of the plurality of sensors being configured to transmit a corresponding optical signal from the optical port toward the flexible member, and each of the plurality of sensors being configured to receive an optical signal reflected from a surface of the flexible member through a corresponding optical port, wherein the three optical fibers and their corresponding optical ports are spaced 120 degrees apart to cover the entire surface of the flexible member; an image processor configured to convert sensor data from the plurality of sensors into image data; as well as A processing module is configured to receive reference image data, compare the image data with the reference image data, determine a defect based on the comparison and threshold setting information for the flexible member, and send a notification based on the defect, wherein the threshold setting information is based on an application type of the flexible member, wherein the threshold setting information includes a defect category mapped to a remaining life of the flexible member based on the application type of the flexible member, and has different acceptable tolerances and operating thresholds for the flexible member for different applications, wherein the processing module is further configured to determine a location of the defect of the flexible member, classify the defect into one or more categories based at least in part on the defect, and associate the determined defect with the remaining life of the flexible member based on the mapping.

2. The system of claim 1, wherein the flexible member is at least one of a rope, a wire, a belt, and a chain.

3. The system of claim 1, wherein the reference image data is based on the flexible member.

4. The system of claim 1, wherein the notification includes a location of the defect, a number of defects, a type of defect, or a recommendation to perform maintenance associated with the flexible member.

5. A method for automatic defect detection of a flexible component using image processing, the method comprising: Monitoring the flexible member by a plurality of sensors to obtain sensor data, wherein the plurality of sensors are three optical fibers, each optical fiber including a corresponding optical port, wherein the three optical fibers and their corresponding optical ports are spaced 120 degrees apart to cover the entire surface of the flexible member, wherein monitoring comprises: sending a respective optical signal from each respective optical port toward the flexible member; and receiving an optical signal reflected from a surface of the flexible member via a corresponding optical port included in each sensor of the plurality of sensors; converting sensor data from the plurality of sensors into image data; receiving reference image data for comparison with the image data; determining a defect based on the comparison and threshold setting information for the flexible member, wherein the threshold setting information is based on an application type of the flexible member, wherein the threshold setting information includes a defect category mapped to a remaining life of the flexible member based on the application type of the flexible member and has different acceptable tolerances and operating thresholds for the flexible member used in different applications; determining a location of the defect in the flexible member; classifying the defects into one or more categories based at least in part on the defects; correlating the determined defect with a remaining life of the flexible member based on the mapping; and A notification is sent based on the defect.

6. The method of claim 5, wherein the flexible member is at least one of a rope, a wire, a belt, and a chain. The method of claim 5 , wherein the reference image data is based on the flexible member.

8. The method of claim 5, wherein the notification includes a location of the defect, a number of defects, a type of defect, or a recommendation to perform repairs associated with the flexible member.

Images