Metal surface damage detection method and system

Abstract

The invention discloses a metal surface damage detection method and system, and the method comprises the steps: collecting data in different types of sensors, introducing an order matrix, carrying out the processing of the data in different types of sensors, obtaining the key features of multiple types of data, and extracting the key features; a metal surface damage detection model is constructed, key features are fused, and a comprehensive damage evaluation index is established; according to the comprehensive damage evaluation index, outputting position information, damage depth and damage type of the metal surface damage; according to the method, data in different types of sensors are collected, the data in the different sensors are efficiently processed by using the order matrix, and key multi-class data features can be extracted; by constructing the metal surface damage detection model and combining with the comprehensive damage evaluation index, not only can the accurate position, depth and type information of the damage be provided, but also the comprehensiveness and accuracy of damage detection can be greatly improved, and a new innovative means is brought to the field of damage detection.

Description

Technical Field

[0001] The present invention relates to the field of analysis, processing and detection technology, and in particular to a metal surface damage detection method and system. Background Art

[0002] In the field of metal surface damage detection technology, the development of non-destructive testing (NDT) technology is crucial. This technology is used to evaluate the properties of materials or components without affecting their future availability, and is one of the key technologies to ensure structural integrity and operational safety. Although traditional detection technologies, such as ultrasonic testing, X-ray or magnetic particle testing, are quite mature in their respective application fields, they usually rely on a single type of sensor data, which limits the comprehensive understanding of complex damage situations. In recent years, with the progress of materials science, electronic technology and computer science, more advanced detection methods have been developed to improve the accuracy and efficiency of detection. In particular, the introduction of machine learning and image processing technology has provided new possibilities for the automatic identification and classification of tiny damage on metal surfaces.

[0003] However, despite the significant progress made in existing technologies, there are still some shortcomings. First, existing detection systems are often inefficient in processing multi-source data and it is difficult to achieve effective data fusion, which limits the application potential of the system in complex environments. Second, existing methods still face challenges in quantitative damage analysis, especially in accurately identifying damage location, depth and type. These shortcomings may lead to inaccurate damage assessment, thus affecting subsequent maintenance and repair decisions. Summary of the invention

[0004] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0005] In view of the above existing problems, the present invention is proposed. Therefore, the present invention provides a metal surface damage detection method to solve the problems raised in the background technology.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a method for detecting metal surface damage, comprising:

[0008] Collect data from different types of sensors, introduce an order matrix to process the data from the different types of sensors, obtain key features of multiple types of data, and extract the key features;

[0009] Construct a metal surface damage detection model, integrate the key features, and establish a comprehensive damage assessment index;

[0010] According to the comprehensive damage assessment index, the location information, damage depth and damage type of the metal surface damage are output.

[0011] As a preferred solution of the metal surface damage detection method of the present invention, the collecting of data from different types of sensors includes:

[0012] The different types of sensors include machine vision sensors, ultrasonic sensors, electromagnetic sensors, temperature and humidity integrated sensors, and stress and strain integrated sensors.

[0013] As a preferred solution of the metal surface damage detection method of the present invention, an order matrix is ​​introduced to process the data from the different types of sensors to obtain multiple types of key features of the data, including:

[0014] Assume that the initial data patterns in different types of sensors are D i (t);

[0015] The order matrix rank(A) is introduced to enhance the data patterns in different types of sensors, which can be expressed as:

[0016]

[0017] According to the transformed response function, a normalization function is designed;

[0018] Among them, R i (t) represents the response function of the i-th sensor data after data pattern enhancement; μ i and σ i They represent the data pattern center area and data distribution width in the i-th sensor respectively; t represents the time when the sensor acquires data at a certain moment.

[0019] As a preferred solution of the metal surface damage detection method of the present invention, the key features are extracted, including:

[0020] Set the sensor weights and use convolution operation to convert R i (t) and D i (t) is combined and the normalization function is introduced to obtain the key feature K of the extracted multi-category data.

[0021] As a preferred solution of the metal surface damage detection method of the present invention, a metal surface damage detection model is constructed, the key features are integrated, and a comprehensive damage assessment index is established, including:

[0022] The construction of the metal surface damage detection model is expressed as:

[0023]

[0024] Where M(D) is the metal surface damage detection model; b is the metal surface damage bias term; τ is the conversion function used to convert linear output into nonlinear output; v i It is expressed as the importance of the i-th key feature weight in damage detection; z(K i ) is represented as a nonlinear output conversion function, which is used to convert i key features.

[0025] As a preferred embodiment of the metal surface damage detection method of the present invention, it also includes:

[0026] Taking M(D) as the damage value of the comprehensive damage assessment index and combining it with the adjustment coefficient of key feature fusion, a comprehensive damage assessment index is established.

[0027] As a preferred solution of the metal surface damage detection method of the present invention, the location information, damage depth and damage type of the metal surface damage are output according to the comprehensive damage assessment index, including:

[0028] The comprehensive damage assessment index E(D) is expressed as follows:

[0029]

[0030] Among them, K represents the key features of the extracted multi-class data; θ represents the adjustment coefficient; D represents the data obtained from the sensor; T is the observation time window; S(t) is the time series signal obtained after processing by the order matrix; α is the attenuation coefficient; n is the total number of sensors; w i It is represented as the weight of the i-th sensor; F i is the characteristic intensity obtained from the i-th sensor; O i It is represented by the output of the ith sensor after being processed by the order matrix; ∈ is the zero-divided value of the log function, which is a minimum value and represents a positive number; M score (D) is the severity of the injury.

[0031] In a second aspect, the present invention provides a metal surface damage detection system, comprising:

[0032] The extraction module is used to collect data from different types of sensors, introduce the order matrix to process the data from different types of sensors, and obtain the key features of multiple types of data;

[0033] A model building and processing module is used to extract the key features, build a metal surface damage detection model, fuse the key features, and establish a comprehensive damage assessment index;

[0034] The output module is used to output the location information, damage depth and damage type of metal surface damage according to the comprehensive damage assessment index.

[0035] In a third aspect, the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, wherein: the processor implements any step of the above method when executing the computer program.

[0036] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: the computer program implements any step of the above method when executed by a processor.

[0037] Compared with the prior art, the beneficial effects of the invention are as follows: the present invention collects data from different types of sensors, introduces an order matrix to process the data from different types of sensors, obtains key features of multiple types of data, and extracts key features; constructs a metal surface damage detection model, fuses key features, and establishes a comprehensive damage assessment index; outputs the location information, damage depth, and damage type of metal surface damage based on the comprehensive damage assessment index; the present invention collects data from different types of sensors, and uses an order matrix to efficiently process the data from different sensors, and can extract key multi-category data features; by constructing a metal surface damage detection model and combining it with a comprehensive damage assessment index, it can not only provide accurate location, depth, and type information of damage, but also greatly improve the comprehensiveness and accuracy of damage detection, bringing new innovative means to the field of damage detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0039] Figure 1 This is an overall flow chart of a metal surface damage detection method according to an embodiment of the present invention;

[0040] Figure 2 This is a module composition diagram of a metal surface damage detection system according to an embodiment of the present invention;

[0041] Figure 3This is a graph comparing the scores of different sensors and a comprehensive model for metal surface damage detection in accordance with an embodiment of the present invention. DETAILED DESCRIPTION

[0042] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0043] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0044] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0045] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0046] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0047] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0048] Example 1

[0049] Reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides a metal surface damage detection method, comprising:

[0050] S1. Collect data from different types of sensors, introduce order matrix to process the data from different types of sensors, and obtain key features of multiple types of data;

[0051] Furthermore, the different types of sensors include machine vision sensors, ultrasonic sensors, electromagnetic sensors, temperature and humidity integrated sensors, and stress and strain integrated sensors;

[0052] Furthermore, machine vision sensors are responsible for collecting image data; ultrasonic sensors are responsible for collecting ultrasonic data; electromagnetic sensors are responsible for collecting electromagnetic data; temperature and humidity integrated sensors are responsible for collecting environmental data; stress and strain integrated sensors are responsible for collecting mechanical data;

[0053] Specifically, the image data includes: metal surface texture features: such as cracks, scratches, corrosion or dents; metal color changes: color differences caused by oxidation or other chemical changes on the metal surface; metal brightness and reflectivity: the reflective properties of the material caused by surface damage areas;

[0054] Specifically, ultrasonic data includes: echo intensity: the change in echo signal caused by internal structural changes (such as cracks or voids) when ultrasonic waves propagate inside metal; signal attenuation: the attenuation degree of ultrasonic signals caused by material damage; wave velocity change: the change in the propagation speed of ultrasonic waves in the material caused by metal surface damage;

[0055] Specifically, electromagnetic data include: resistance change: damage to the metal surface causes changes in the material's resistance; electromagnetic field distribution: the damage area affects the electromagnetic properties of the material, such as the distribution of induced current;

[0056] Specifically, environmental data include: Temperature: various types of damage (such as fatigue cracks) are affected by ambient temperature; Humidity: metal corrosion is accelerated, which affects the accuracy of damage detection and assessment;

[0057] Specifically, mechanical data include: stress distribution: judging the presence of damage inside the material by uneven stress distribution; strain response: revealing the behavior of the material under stress and identifying potential damage structures;

[0058] It should be noted that the structured representation of these data through an order matrix can improve the sensitivity of the subsequent construction of a metal surface damage detection model and help to fuse key features;

[0059] Furthermore, let the initial data patterns of different types of sensors be D i (t);

[0060] The order matrix rank(A) is introduced to enhance the data patterns in different types of sensors, which can be expressed as:

[0061]

[0062] Specifically, the order matrix rank(A) is used to capture the structure in the data pattern (the structure consists of multiple data points) and stretch it. Stretching means taking the longest data structure as a reference and representing data structures of different lengths as the same as the longest data structure.

[0063] It should be noted that the traditional method usually pre-processes the data to remove noise and outliers, but does not consider the data structure, which wastes time in extracting features. However, the present invention fully considers the data structure, improves the data structure by introducing the order matrix, eliminates the operations of denoising and removing outliers, and saves processing time for extracting key features.

[0064] Among them, R i (t) represents the response function of the i-th sensor data after data pattern enhancement, which is used for recognition and extraction operations; μ i and σ i They are respectively represented as the data pattern center area and data distribution width in the i-th sensor; t represents the time when the sensor acquires data at a certain moment; the data pattern center area refers to a value range in a continuous data set or signal, where the data points in this value range have frequency fluctuations, which is manifested as the peak area of ​​the data distribution; the data distribution width refers to the degree of dispersion or diffusion of data points around the central value (such as the mean or median);

[0065] Furthermore, a normalization function is designed according to the transformed response function;

[0066] Specifically, the normalization function is expressed as:

[0067]

[0068] It should be noted that the design of the normalization function is used to adjust the importance of the data within the observation time window T to ensure the balance of feature extraction; because the normalization function itself can increase the influence of the data over time and reflect the changes in data trends, it improves the accuracy of data processing and enhances the comprehensive ability of the metal surface damage detection model for different sensor data features;

[0069] S2. Extract key features, build a metal surface damage detection model, fuse key features, and establish a comprehensive damage assessment index;

[0070] Furthermore, we set the sensor weights and use the convolution operation to convert R i (t) and D i (t) Combine and bring in the normalization function to obtain the key feature K of the extracted multi-class data;

[0071] Specifically, the calculation formula of the key feature K of the extracted multi-class data is expressed as:

[0072]

[0073] Among them, * represents the convolution operation, which is used to enhance the extraction accuracy of key features;

[0074] Furthermore, the metal surface damage detection model is constructed as follows:

[0075]

[0076] Where M(D) is the metal surface damage detection model; b is the metal surface damage bias term, which is used to adjust the model deviation; τ is the conversion function, which is used to convert the linear output into the nonlinear output; v i It is expressed as the importance of the i-th key feature weight in damage detection; z(K i ) is represented as a nonlinear output conversion function, which is used to convert i key features;

[0077] Preferably, Rewrite as Using exponential functions to represent it can capture subtle damage characteristics;

[0078] Furthermore, M(D) is used as the damage value of the comprehensive damage assessment index, combined with the adjustment coefficient of key feature fusion, to establish a comprehensive damage assessment index;

[0079] It should be noted that the establishment of comprehensive damage assessment index is used to evaluate the accuracy of the output of the constructed metal surface damage detection model, rather than the output value of the model defined in the traditional way;

[0080] S3. Output the location information, damage depth and damage type of metal surface damage according to the comprehensive damage assessment index;

[0081] Specifically, the comprehensive damage assessment index is expressed as:

[0082]

[0083] Furthermore, M score(D) is expressed as:

[0084] M score (D) = M (D) × α + β × info (P os (D),D ept h(D),T ype (D)

[0085] Among them, K represents the key features of the extracted multi-category data; β represents the adjustment coefficient, which is used to adjust according to the key features, and the overall adjustment range is between [0.1 and 0.5]; D represents the data obtained from the sensor; T is the observation time window; S(t) is the time series signal obtained after processing by the order matrix; α is the attenuation coefficient; n is the total number of sensors; w i It is represented as the weight of the i-th sensor; F i is the characteristic intensity obtained from the i-th sensor; O i It is represented by the output of the ith sensor after being processed by the order matrix; ∈ is the zero-divided value of the log function, which is a minimum value and represents a positive number; M score (D) is the severity of the damage; info represents the comprehensive damage score of Pos(D), Depth(D) and Type(D); Pos(D) represents the location information of the metal surface damage; Depth(D) represents the damage depth of the metal surface damage; Type(D) represents the damage type of the metal surface damage;

[0086] It should be noted that by introducing key features, not only the comprehensiveness of the model for damage detection is improved, but also the accuracy of the model is improved. Compared with traditional methods, the iteration step is omitted, making the model more efficient.

[0087] Furthermore, this embodiment also provides a metal surface damage detection system, comprising:

[0088] The extraction module is used to collect data from different types of sensors, introduce the order matrix to process the data from different types of sensors, and obtain the key features of multiple types of data;

[0089] A model building and processing module is used to extract the key features, build a metal surface damage detection model, fuse the key features, and establish a comprehensive damage assessment index;

[0090] The output module is used to output the location information, damage depth and damage type of metal surface damage according to the comprehensive damage assessment index.

[0091] This embodiment also provides a computer device, which is applicable to the metal surface damage detection method, including:

[0092] Memory and processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the metal surface damage detection method proposed in the above embodiment.

[0093] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0094] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the metal surface damage detection method proposed in the above embodiment is implemented.

[0095] The storage medium proposed in this embodiment and the data storage method proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be found in the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0096] Example 2

[0097] Reference Figure 3 , which is the second embodiment of the present invention, and which provides a metal surface damage detection method, comprising: verifying the beneficial effects of the present invention by means of simulation experiments;

[0098] Five different types of sensors are set up: machine vision sensor, ultrasonic sensor, electromagnetic sensor, temperature and humidity integrated sensor, and stress and strain integrated sensor; these sensors are installed on a non-destructive testing platform (NDT), and the damage types are sampled respectively, and the data of the metal surface are collected simultaneously to obtain the accuracy of the detection results of various sensors used alone and the output of the comprehensive model, refer to Table 1;

[0099] Table 1

[0100]

[0101]

[0102] Through the table and Figure 3 It can be observed that the comprehensive damage assessment index is generally higher than the detection result of a single sensor, and the difference between the comprehensive damage assessment index and the accuracy of individual sensors is 1% to 3%. This is because for a single sensor, it usually evaluates the data that it is good at detecting. For example, a machine vision sensor is usually used to collect image data. If it is allowed to identify changes in the internal structure of a material, it is not as accurate as a stress and strain integrated sensor. However, the present invention improves the accuracy and comprehensiveness of damage detection by introducing an order matrix and fusing various sensors through key features and optimizing models, so that each type of sensor can maintain high accuracy and flexibility when identifying data that it is not good at.

[0103] Those skilled in the art will appreciate that the embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the application can adopt the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program codes. The scheme in the embodiments of the present application can be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.

[0104] 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 generate 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 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0105] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0106] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0107] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0108] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A metal surface damage detection method, characterized in that: include: Collect data from different types of sensors, introduce an order matrix to process the data from the different types of sensors, and obtain key features of multiple types of data; Extracting the key features, constructing a metal surface damage detection model, fusing the key features, and establishing a comprehensive damage assessment index; According to the comprehensive damage assessment index, the location information, damage depth and damage type of the metal surface damage are output.

2. The metal surface damage detection method according to claim 1, characterized in that: The collecting of data from different types of sensors includes: The different types of sensors include machine vision sensors, ultrasonic sensors, electromagnetic sensors, temperature and humidity integrated sensors, and stress and strain integrated sensors.

3. The metal surface damage detection method according to claim 2, characterized in that: The order matrix is ​​introduced to process the data from the different types of sensors to obtain multiple types of key features of the data, including: Assume that the initial data patterns in different types of sensors are D i (t); The order matrix rank(A) is introduced to enhance the data patterns in different types of sensors, which can be expressed as: According to the transformed response function, a normalization function is designed; Among them, R i (t) represents the response function of the i-th sensor data after data pattern enhancement; μ i and σ i They represent the data pattern center area and data distribution width in the i-th sensor respectively; t represents the time when the sensor acquires data at a certain moment.

4. The metal surface damage detection method according to claim 2 or 3, characterized in that: Extracting the key features includes: Set the sensor weights and use convolution operation to convert R i (t) and D i (t) is combined and the normalization function is introduced to obtain the key feature K of the extracted multi-category data.

5. The metal surface damage detection method according to claim 4, characterized in that: Construct a metal surface damage detection model, integrate the key features, and establish a comprehensive damage assessment index, including: The construction of the metal surface damage detection model is expressed as: Where M(D) is the metal surface damage detection model; b is the metal surface damage bias term; τ is the conversion function used to convert linear output into nonlinear output; v i It is expressed as the importance of the i-th key feature weight in damage detection; z(K i ) is represented as a nonlinear output conversion function, which is used to convert i key features.

6. The metal surface damage detection method according to claim 5, characterized in that: Also includes: Taking M(D) as the damage value of the comprehensive damage assessment index and combining it with the adjustment coefficient of key feature fusion, a comprehensive damage assessment index is established.

7. The metal surface damage detection method according to claim 6, characterized in that: According to the comprehensive damage assessment index, the location information, damage depth and damage type of the metal surface damage are output, including: The comprehensive damage assessment index E(D) is expressed as follows: Among them, K represents the key features of the extracted multi-class data; β represents the adjustment coefficient; D represents the data obtained from the sensor; T is the observation time window; S(t) is the time series signal obtained after processing by the order matrix; α is the attenuation coefficient; n is the total number of sensors; w i It is represented as the weight of the i-th sensor; F i is the characteristic intensity obtained from the i-th sensor; O i It is represented by the output of the ith sensor after being processed by the order matrix; ∈ is the zero-divided value of the log function, which is a minimum value and represents a positive number; M score (D) is the severity of the injury.

8. A metal surface damage detection system, based on the metal surface damage detection method according to any one of claims 1 to 7, characterized in that: include: The extraction module is used to collect data from different types of sensors, introduce the order matrix to process the data from different types of sensors, and obtain the key features of multiple types of data; A model building and processing module is used to extract the key features, build a metal surface damage detection model, fuse the key features, and establish a comprehensive damage assessment index; The output module is used to output the location information, damage depth and damage type of metal surface damage according to the comprehensive damage assessment index.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

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

Images