Metal wire rope quality detection method and system based on Internet of Things technology

Abstract

The invention relates to a metal wire rope quality detection method and system based on the Internet of Things technology, in particular to the field of Internet of Things quality inspection. A strain sensor is installed to obtain real-time data of strain and vibration of a metal wire rope, and a high-resolution camera is installed to obtain surface image data of the metal wire rope; the method comprises the following steps: extracting time domain features of real-time data of strain and vibration, extracting shape features, color features, texture features and angular point features through edge detection, color histogram, wavelet transform and angular point detection, carrying out surface defect monitoring on the metal wire rope, and analyzing a rated load of the metal wire rope through the real-time data of strain and vibration. And judging whether the stress condition of the metal wire rope is within a safety quality range or not, through the rated load safety quality range and prediction of the service life and toughness quality of the metal wire rope, creating a visual chart to display real-time data of dynamic strain and vibration in real time, and creating a visual interface to mark specific features and surface defects of a visual module.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of Internet of Things quality inspection, and more particularly, to a metal wire rope quality detection method and system based on Internet of Things technology. BACKGROUND

[0002] The current metal wire rope quality detection includes visual inspection and non-destructive testing, but has certain limitations and cannot comprehensively and accurately evaluate the quality of the metal wire rope.

[0003] The visual inspection can only detect surface defects and cannot detect internal defects, the non-destructive testing can detect internal defects and requires a higher operating personnel, and the metal wire rope quality detection can only provide average values and sampling data and cannot comprehensively evaluate each metal wire rope, resulting in uncertainty of the metal wire rope quality detection result, production line stagnation and delay, and increased production cost and time cost. SUMMARY

[0004] The present application provides a metal wire rope quality detection method and system based on Internet of Things technology to solve the problems in the background technology.

[0005] The technical scheme for solving the above technical problems is as follows: a metal wire rope quality detection method based on Internet of Things technology, comprising the following steps:

[0006] S101. Installing a strain sensor to obtain real-time data of strain and vibration of the metal wire rope, installing a high-resolution camera to obtain surface image data of the metal wire rope, and using minimum-maximum normalization to reduce the real-time data of strain and vibration and the surface image data to a specified range;

[0007] S102. Extracting time domain features of the real-time data of strain and vibration, and extracting shape features, color features, texture features and corner point features through edge detection, color histogram, wavelet transform and corner point detection;

[0008] S103. Monitoring surface defects of the metal wire rope through contour boundary, texture features and corner point features, analyzing rated load of the metal wire rope through the real-time data of strain and vibration, and judging whether the stress condition of the metal wire rope is within a safe quality range, and predicting the service life and toughness quality of the metal wire rope through the rated load safe quality range;

[0009] S104. Creating a visual chart to real-time display dynamic strain and vibration real-time data, and marking the judgment result of quality detection, and creating a visual interface to mark specific features and surface defects of the visual module;

[0010] In a preferred embodiment, in S101, the strain sensor is installed on each wire rope to monitor the dynamic state of the wire rope and form a sensor node, which is used to obtain the real-time data of strain and vibration of the wire rope, and the sensor node is used to build a wireless sensor network to upload the real-time data of strain and vibration to the cloud for temporary storage.

[0011] Further, a high-resolution camera is installed on the production line of each wire rope to obtain surface image data of the wire rope, which is connected to the sensor node interface and uploaded to the cloud for temporary storage through the wireless sensor network.

[0012] Further, the real-time data of strain and vibration and the surface image data are reduced to a specified range and mapped to the same scale by using the min-max normalization formula:

[0013]

[0014] wherein Q represents the value of the normalized real-time data of strain and vibration and surface image data, P represents the value of the current real-time data of strain and vibration and surface image data, P min represents the minimum value of the real-time data of strain and vibration and surface image data, P max represents the maximum value of the real-time data of strain and vibration and surface image data.

[0015] In a preferred embodiment, in S102, the time domain features of the real-time data of strain and vibration are extracted, wherein the skewness is used to describe the skewness of the distribution of the real-time data of strain and vibration, and the specific formula is:

[0016]

[0017] wherein Sc represents the skewness of the real-time data of strain and vibration, n represents the number of the real-time data of strain and vibration, x i represents the i-th real-time data of strain and vibration, represents the average value of the real-time data of strain and vibration, positive skewness indicates that the right tail is longer, and negative skewness indicates that the left tail is longer.

[0018] Further, the shape feature is extracted by edge detection, the color feature is extracted by color histogram, and the texture feature is extracted by wavelet transform. The wavelet transform is continuous wavelet transform, and the surface image data is continuously transformed by using different scale and translation parameters to generate continuous scale images, providing texture transform information of the surface image data at different frequencies and times. The corner point feature of the surface image data is extracted by corner point detection.

[0019] In a preferred embodiment, in S103, the real-time strain and vibration data and the surface image data are divided into a training set, a validation set and a test set. 70% of the real-time strain and vibration data and the surface image data are used as the training set, 20% of the real-time strain and vibration data and the surface image data are used as the validation set, and 10% of the real-time strain and vibration data and the surface image data are used as the test set.

[0020] Further, the surface image data is set with 10 input nodes as the input layer of the neural network and input into the training set. The hidden layer is connected by using a weight matrix, and the neurons in the hidden layer are selected and transmitted by the weight matrix. The output layer of the neural network is set with 10 output nodes, and the surface defect monitoring of the wire rope is performed by using the contour boundary, the texture feature and the corner point feature.

[0021] Further, the rated load of the wire rope is analyzed by using the real-time strain and vibration data, which is used to determine whether the stress condition of the wire rope is within the safe quality range. The real-time strain and vibration data is set with 10 input nodes as the input layer of the neural network and input into the training set. The hidden layer is connected by using a weight matrix, and the neurons in the hidden layer are selected and transmitted by the weight matrix. The output layer of the neural network is set with 10 output nodes, and the life and toughness quality of the wire rope are predicted by using the rated load safe quality range.

[0022] Further, the surface defect monitoring is associated with the life and toughness quality prediction of the wire rope as a validation test node, and the validation set and the test set are input. When the stress condition of the wire rope is within the safe quality range, it is determined that the wire rope meets the quality detection, including the tensile strength, fatigue life and stability of the wire rope. When the stress condition of the wire rope is not within the safe quality range, it is determined that the wire rope does not meet the quality detection, and the production is selected to return and iterate the detection step.

[0023] In a preferred embodiment, the S104 of creating a visualization chart includes a column chart and a line chart, wherein the visualization chart has a time axis at the bottom, and is used to display real-time data of dynamic strain and vibration in real time, and a current time point and a rated load of a force point of the wire rope are marked by a visualization label, and a judgment result of quality detection is marked.

[0024] Further, a visualization interface is created, the surface image of the wire rope is divided into three visualization modules of contour boundary, texture transformation and corner point information, specific features and surface defects of the visualization modules are marked by a visualization label, and the visualization modules are used for internal dynamic quality detection of the wire rope in combination with expert experience.

[0025] Further, a quality detection report is generated according to the visualization chart and the visualization interface, including data source and time, data detection method and quality detection judgment result, the visualization chart and the visualization interface are regularly updated, and the quality detection report is shared to the cloud, the specific regular time is 15 days, and the quality detection report is obtained by connecting the cloud through a production department.

[0026] In a preferred embodiment, the system includes a data acquisition and processing module, a data feature extraction module, a neural network prediction module and a quality detection visualization module.

[0027] The data acquisition and processing module: installs a strain sensor to obtain real-time data of strain and vibration of the wire rope, and installs a high-resolution camera to obtain surface image data of the wire rope.

[0028] The data feature extraction module: extracts time domain features of the real-time data of strain and vibration, and extracts shape features, color features, texture features and corner point features through edge detection, color histogram, wavelet transformation and corner point detection.

[0029] The neural network prediction module: sets input nodes and uses neuron transmission to monitor surface defects of the wire rope, and sets input nodes and uses neuron transmission to predict the life and toughness quality of the wire rope.

[0030] The quality detection visualization module: creates a visualization chart to display real-time data of dynamic strain and vibration in real time, and marks a judgment result of quality detection, and creates a visualization interface to mark specific features and surface defects of the visualization modules.

[0031] The beneficial effects of the present application are: by minimum-maximum normalization, the values of different data ranges are mapped to the same scale, which helps to compare and analyze the relationship between different data, and provides more accurate data reference, by extracting the shape, color, texture and corner features of the time domain features and surface image data, the state and performance of the wire rope are comprehensively understood, which helps to find potential problems in time and take corresponding measures, improves the safety and reliability of the wire rope, by the neural network model, the surface defect detection and life and toughness quality prediction of the wire rope are realized, which helps to judge whether the stress condition of the wire rope is within the safe quality range, avoids the safety hidden danger caused by overload, improves the product quality and safety, by the visual chart and visual interface, the real-time data of dynamic strain and vibration and the surface defects of the wire rope are displayed in real time, which helps the production department to monitor the quality state of the wire rope in real time and take corresponding measures in time. BRIEF DESCRIPTION OF DRAWINGS

[0032] Figure 1 The method flowchart of the present application is shown in the figure.

[0033] Figure 2 The system structure block diagram of the present application is shown in the figure. DETAILED DESCRIPTION

[0034] The technical solutions in the embodiments of the present application will be described clearly and completely in combination with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the present application.

[0035] In the description of the present application, the terms "first", "second" are only used for description purpose, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Therefore, the features limited by "first", "second" can explicitly or implicitly include one or more of the features. In the description of the present application, the meaning of "multiple" is two or more, unless otherwise specifically limited.

[0036] In the description of the present application, the term "for example" is used to indicate "serving as an example, instance, or illustration." Any embodiment described as "for example" in this application is not necessarily to be construed as preferred or advantageous over other embodiments. The following description is presented to enable any person skilled in the art to make and use the application. In the following description, for the purposes of explanation, specific details are set forth in order to provide a thorough understanding of the application. It will be apparent to one ordinarily skilled in the art that the application can be practiced without the use of these specific details. In other instances, well-known structures and processes are not elaborated upon in order to avoid obscuring the description of the application. Thus, the present application is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features presented herein.

[0037] Embodiment 1

[0038] The present embodiment provides a metal wire rope quality detection method based on Internet of Things technology as shown in Figure 1 The present embodiment provides a metal wire rope quality detection method based on Internet of Things technology as shown in

[0039] S101. Install strain sensors to obtain real-time data of strain and vibration of the metal wire rope, install high-resolution cameras to obtain surface image data of the metal wire rope, and use minimum-maximum normalization to reduce the real-time data of strain and vibration and the surface image data to a specified range;

[0040] Further, install strain sensors on each metal wire rope for dynamic monitoring of the metal wire rope and form sensor nodes for obtaining real-time data of strain and vibration of the metal wire rope, and build a wireless sensor network through the sensor nodes to upload the real-time data of strain and vibration to the cloud for temporary storage.

[0041] Further, install high-resolution cameras on the production line of each metal wire rope for obtaining surface image data of the metal wire rope, and connect the sensor node interface to upload the surface image data to the cloud for temporary storage through the wireless sensor network.

[0042] Further, use minimum-maximum normalization to reduce the real-time data of strain and vibration and the surface image data to a specified range and map them to the same scale, and the minimum-maximum normalization formula is:

[0043]

[0044] where Q represents the value of the normalized real-time data of strain and vibration and surface image data, P represents the current value of the real-time data of strain and vibration and surface image data, P min represents the minimum value of the real-time data of strain and vibration and surface image data, P maxThe maximum value of the real-time data of strain, vibration and surface image data.

[0045] S102. Extracting the time domain features of the real-time data of strain, vibration, extracting shape features, color features, texture features and corner features through edge detection, color histogram, wavelet transform and corner detection;

[0046] Further, the time domain features of the real-time data of strain, vibration are extracted, wherein the skewness is used to describe the skewness of the distribution of the real-time data of strain, vibration, and the specific formula is:

[0047]

[0048] Wherein Sc represents the skewness of the real-time data of strain, vibration, n represents the number of the real-time data of strain, vibration, x i represents the i-th real-time data of strain, vibration, represents the average value of the real-time data of strain, vibration, positive skewness indicates that the right tail is longer, and negative skewness indicates that the left tail is longer.

[0049] Further, the shape features are extracted through edge detection, including the feature information of the contour boundary in the surface image data, the color features are extracted through color histogram, including the feature information of the color distribution in the surface image data, the texture features are extracted through wavelet transform, including the feature information of the texture in the surface image data, and the wavelet transform is continuous wavelet transform, which uses different scales and translation parameters to continuously transform the surface image data to generate continuous scale images, providing texture transformation information of the surface image data at different frequencies and times, and the corner point features of the surface image data are extracted through corner detection.

[0050] S103. Surface defect monitoring of the wire rope through the contour boundary, texture features and corner point features, analyzing the rated load of the wire rope through the real-time data of strain, vibration, and judging whether the stress condition of the wire rope is within the safe quality range, predicting the life and toughness quality of the wire rope through the rated load safe quality range;

[0051] Further, the real-time data of strain, vibration and surface image data are divided into training set, validation set and test set, wherein 70% of the real-time data of strain, vibration and surface image data are used as training set, 20% of the real-time data of strain, vibration and surface image data are used as validation set, and 10% of the real-time data of strain, vibration and surface image data are used as test set.

[0052] Further, the surface image data is set with 10 input nodes as the input layer of the neural network, and the training set is input, the hidden layer is connected by the weight matrix, the neurons in the hidden layer are selected and transmitted by the weight matrix, and 10 output nodes are set as the output layer of the neural network. The surface defect monitoring of the wire rope is carried out through the contour boundary, texture feature and corner point feature.

[0053] Further, the rated load of the wire rope is analyzed through the real-time data of strain and vibration to determine whether the stress condition of the wire rope is within the safe quality range. The real-time data of strain and vibration are set with 10 input nodes as the input layer of the neural network, and the training set is input, the hidden layer is connected by the weight matrix, the neurons in the hidden layer are selected and transmitted by the weight matrix, and 10 output nodes are set as the output layer of the neural network. The safe quality range of the rated load is used to predict the service life and toughness quality of the wire rope.

[0054] Further, the surface defect monitoring is associated with the prediction of the service life and toughness quality of the wire rope as a verification test node. The validation set and test set are input, and when the stress condition of the wire rope is within the safe quality range, it is determined that the wire rope meets the quality detection, including the tensile strength, fatigue life and stability of the wire rope. When the stress condition of the wire rope is not within the safe quality range, it is determined that the wire rope does not meet the quality detection, and the production is selected to return and iterate the detection step.

[0055] S104. Create a visualization chart to display the real-time data of dynamic strain and vibration in real time, and mark the judgment result of quality detection. Create a visualization interface to mark the specific features of the visualization module and surface defects;

[0056] Further, the visualization chart includes column chart and line chart, and the bottom of the visualization chart is time axis, which is used to display the real-time data of dynamic strain and vibration in real time. The current time point and the rated load of the stress point of the wire rope are marked by the visualization label, and the judgment result of quality detection is marked.

[0057] Further, the visualization interface is created, and the surface image of the wire rope is divided into three visualization modules of contour boundary, texture transformation and corner point information. The specific features of the visualization module and the surface defects are marked by the visualization label, and the internal dynamic quality detection of the wire rope is carried out by combining the expert experience with the visualization module.

[0058] Further, the quality detection report is generated according to the visualization chart and the visualization interface, including data source and time, data detection method and quality detection judgment result. The visualization chart and the visualization interface are updated regularly, and the quality detection report is shared to the cloud. The specific regular time is 15 days, and the quality detection report is obtained by connecting the cloud through the production department.

[0059] Example 2

[0060] This embodiment provides, for example Figure 2 The present invention discloses a metal wire rope quality inspection system based on Internet of Things (IoT) technology, which specifically includes: a data acquisition and processing module, a data feature extraction module, a neural network prediction module, and a quality inspection visualization module.

[0061] Data acquisition and processing module: Install strain sensors to acquire real-time data on strain and vibration of the metal wire rope, and install high-resolution cameras to acquire surface image data of the metal wire rope;

[0062] Data feature extraction module: Extracts the temporal features of real-time strain and vibration data, and extracts shape features, color features, texture features and corner features through edge detection, color histogram, wavelet transform and corner detection;

[0063] Neural network prediction module: Set input nodes and use neuron transmission to monitor surface defects of metal wire ropes; set input nodes and use neuron transmission to predict the lifespan and toughness quality of metal wire ropes.

[0064] Quality Inspection Visualization Module: Creates visual charts to display real-time data on dynamic strain and vibration, and marks the judgment results of quality inspection. Creates a visual interface to mark specific features of the visualization module and surface defects.

[0065] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0066] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0067] The present application is described in reference to the flowchart illustrations and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams.

[0068] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams.

[0069] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams.

[0070] While the preferred embodiments of the application have been described, additional variations and modifications can be made to the embodiments by those of skill in the art once they have the benefit of the present disclosure without departing from the spirit and scope of the application. Accordingly, the attached claims are intended to embrace all such variations and modifications as fall within the scope of the present application.

[0071] Obviously, numerous modifications and variations of the present application are possible in light of the above teachings. It is therefore to be understood that within the scope of the appended claims and their equivalents, the application can be practiced otherwise than as specifically described.

Claims

1. A metal wire rope quality detection method based on Internet of Things technology, characterized in that, Specifically comprising the following steps: S101. Installing a strain sensor to obtain real-time data of strain and vibration of the wire rope, installing a high-resolution camera to obtain surface image data of the wire rope, and using minimum-maximum normalization to reduce the real-time data of strain and vibration and the surface image data to a specified range; S102. Extracting time domain features of the real-time data of strain and vibration, and extracting shape features, color features, texture features and corner point features through edge detection, color histogram, wavelet transform and corner point detection; S103. Monitoring surface defects of the wire rope through contour boundary, texture features and corner point features, analyzing the rated load of the wire rope through the real-time data of strain and vibration, and judging whether the stress condition of the wire rope is within the safe quality range, and predicting the service life and toughness quality of the wire rope through the rated load safe quality range; S104. Creating a visual chart to display dynamic real-time data of strain and vibration in real time, and marking the judgment results of quality detection, and creating a visual interface to mark specific features of the visualization module and surface defects. 2.The metal wire rope quality detection method based on the Internet of Things technology according to claim 1, characterized in that: In the S101, the strain sensor is installed on each wire rope to perform dynamic monitoring of the wire rope and form a sensor node to obtain real-time data of strain and vibration of the wire rope, and a wireless sensor network is constructed through the sensor node to upload the real-time data of strain and vibration to the cloud for temporary storage. A high-resolution camera is installed on the production line of each wire rope to obtain surface image data of the wire rope, and the sensor node interface is connected to upload the surface image data to the cloud for temporary storage through the wireless sensor network. The real-time data of strain and vibration and the surface image data are reduced to a specified range using minimum-maximum normalization and mapped to the same scale. 3.The metal wire rope quality detection method based on the Internet of Things technology according to claim 2, characterized in that: The minimum-maximum normalization formula is: wherein Q represents a value of the normalized strain, real-time data of the vibration, and surface image data, P represents a value of the current strain, real-time data of the vibration, and surface image data, P min represents a minimum value of the strain, real-time data of the vibration, and surface image data, P max represents a maximum value of the strain, real-time data of the vibration, and surface image data.

4. The metal wire rope quality detection method based on the Internet of Things technology according to claim 1, characterized in that: In the S102, the time domain features of the real-time data of strain and vibration are extracted, wherein the skewness is used to describe the skewness of the distribution of the real-time data of strain and vibration, the shape features are extracted through edge detection, including feature information of the contour boundary in the surface image data, the color features are extracted through color histogram, including feature information of the color distribution in the surface image data, the texture features are extracted through wavelet transform, including feature information of the texture in the surface image data, providing texture transformation information of the surface image data at different frequencies and times, and the corner point features of the surface image data are extracted through corner point detection.

5. The metal wire rope quality detection method based on the Internet of Things technology according to claim 4, characterized in that: The specific formula of skewness is: wherein Sc represents skewness of the real-time data of strain, vibration, n represents the number of real-time data of strain, vibration, x i represents the i-th real-time data of strain, vibration, represents the average value of the real-time data of strain, vibration, positive skewness represents a longer right tail, and negative skewness represents a longer left tail. 6.The metal wire rope quality detection method based on the Internet of Things technology according to claim 1, characterized in that: In S103, the real-time data of strain and vibration and the surface image data are divided into training set, validation set and test set, the surface image data is set 10 input nodes as the input layer of neural network, and is input into the training set, the weight matrix is used to connect the hidden layer, the neurons in the hidden layer are selected and transmitted through the weight matrix, 10 output nodes are set as the output layer of neural network, the surface defect monitoring of the wire rope is performed through the contour boundary, texture feature and corner point feature, the rated load of the wire rope is analyzed through the real-time data of strain and vibration, whether the stress of the wire rope is within the safe quality range is judged, 10 input nodes of the real-time data of strain and vibration are set as the input layer of neural network, and are input into the training set, the weight matrix is used to connect the hidden layer, the neurons in the hidden layer are selected and transmitted through the weight matrix, 10 output nodes are set as the output layer of neural network, the life and toughness quality of the wire rope are predicted through the rated load safe quality range, and the surface defect monitoring is associated with the life and toughness quality prediction of the wire rope as the validation test node, and the validation set and test set are input. 7.The metal wire rope quality detection method based on the Internet of Things technology of claim 1, characterized in that: In S104, a visualization chart including column chart and line chart is created, the visualization chart has a time axis at the bottom, and is used to display the real-time data of dynamic strain and vibration in real time, the current time point and the rated load of the stress point of the wire rope are marked by a visualization label, and the judgment result of quality detection is marked, a visualization interface is created, the surface image of the wire rope is divided into three visualization modules of contour boundary, texture transformation and corner point information, the specific features of the visualization modules and the surface defects are marked by the visualization label, and the internal dynamic quality detection of the wire rope is performed by the visualization modules combined with expert experience. 8.The metal wire rope quality detection method based on the Internet of Things technology of claim 7, characterized in that: A quality detection report is generated according to the visualization chart and the visualization interface, including data source and time, data detection method and quality detection judgment result, the visualization chart and the visualization interface are regularly updated, and the quality detection report is shared to the cloud, the regular update time is 15 days, and the quality detection report is obtained from the cloud by the production department.

9. The metal wire rope quality detection system based on Internet of Things technology is applied to the metal wire rope quality detection method based on Internet of Things technology according to any one of claims 1-8, characterized in that: The data acquisition and processing module, the data feature extraction module, the neural network prediction module and the quality detection visualization module are included. The data acquisition and processing module: a strain sensor is installed to obtain the real-time data of strain and vibration of the wire rope, and a high-resolution camera is installed to obtain the surface image data of the wire rope. The data feature extraction module: the time domain features of the real-time data of strain and vibration are extracted, the shape features, color features, texture features and corner point features are extracted through edge detection, color histogram, wavelet transformation and corner point detection. The neural network prediction module: input nodes are set and neurons are used for transmission to perform surface defect monitoring of the wire rope, input nodes are set and neurons are used for transmission to perform life and toughness quality prediction of the wire rope. The quality detection visualization module: a visualization chart is created to display the real-time data of dynamic strain and vibration in real time, and the judgment result of quality detection is marked, and a visualization interface is created to mark the specific features of the visualization modules and the surface defects.

Images