Industrial equipment monitoring method and system based on industrial Internet

Abstract

The present invention relates to the field of industrial equipment monitoring technology, and specifically discloses an industrial equipment monitoring method and system based on the industrial Internet, the method comprising: acquiring monitoring video data of each industrial equipment in an operation workshop, and acquiring a target image set from the monitoring video data; performing preliminary recognition and analysis on the target image set, and acquiring damage information in the target image set; when the target component is abnormal, adjusting the direction of a camera within a preset distance range according to the damage information; acquiring a comprehensive monitoring video of the camera within the preset distance range, and determining a final damage grade of the target component according to a secondary recognition and analysis result and the damage information obtained by the preliminary recognition and analysis; generating an alarm prompt instruction according to the final damage grade; the present invention realizes multi-angle monitoring and recognition of damage, so that the monitoring and recognition results of the damage are more accurate, thereby improving the accuracy of monitoring and ensuring the safe operation of industrial equipment.

Description

Technical Field

[0001] The present invention relates to the field of industrial equipment monitoring technology, and specifically to an industrial equipment monitoring method and system based on industrial Internet. Background Art

[0002] Industrial Internet is a new type of infrastructure, application model and industrial ecology that deeply integrates the new generation of information and communication technology with the industrial economy. Through the comprehensive connection of people, machines, objects, systems, etc., a new manufacturing and service system covering the entire industrial chain and the entire value chain is built, providing a way to achieve the digitalization, networking and intelligent development of industry and even industries.

[0003] Industrial equipment monitoring is an important part of the industrial Internet. It mainly uses various sensors, data acquisition technologies, network communication technologies and other means to monitor, analyze and control the operating status, performance parameters and safety status of industrial equipment in real time to ensure the stable, reliable and safe operation of the equipment. Currently, cameras are installed in the operation workshop of industrial equipment to achieve remote monitoring of the external operation of industrial equipment. However, the monitoring angle of the camera in the operation workshop is usually fixed under normal circumstances, resulting in certain limitations in the detection results. Summary of the invention

[0004] The purpose of the present invention is to provide an industrial equipment monitoring method and system based on the Industrial Internet to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] An industrial equipment monitoring method based on the industrial Internet, the method comprising the following steps:

[0007] Acquire monitoring video data of each industrial equipment in the operation workshop, and acquire a target image set from the monitoring video data based on a target detection algorithm; wherein each industrial equipment in the operation workshop uses a plurality of cameras to monitor target components outside the equipment, and each camera is respectively provided with a main monitoring angle. When no abnormality is found, each camera maintains the main monitoring angle unchanged, and clarifies the position information and monitoring angle of each camera, and also clarifies the position information of each component in each industrial equipment;

[0008] Performing preliminary recognition and analysis on the target image set, obtaining damage information in the target image set, and judging whether the target component is abnormal based on the damage information, wherein the damage information includes damage type, damage level, and location information of the damage on the target component;

[0009] When the target component is abnormal, the direction of the camera within the preset distance range is adjusted according to the damage information so that the camera within the preset distance range is aimed at the damaged position of the target component;

[0010] Obtain comprehensive surveillance video from cameras within a preset distance range, perform secondary recognition analysis on the video to obtain damage information, and determine the final damage level of the target component based on the secondary recognition analysis results and the damage information obtained from the preliminary recognition analysis;

[0011] An alarm prompt instruction is generated according to the final damage level.

[0012] As a further technical solution of the present invention, the step of acquiring monitoring video data of each industrial equipment in the operation workshop and acquiring a target image set from the monitoring video data based on a target detection algorithm includes:

[0013] Obtain monitoring video data of various industrial equipment in the operation workshop;

[0014] Extracting sample pictures from the surveillance video data according to a preset time step to obtain a sample picture set;

[0015] The target detection algorithm is used to identify and analyze the sampled picture set, obtain the position information of the target parts in the sampled pictures, and intercept the target images where the target parts are located from the sampled pictures to obtain the target image set.

[0016] As a further technical solution of the present invention, the steps of performing preliminary recognition and analysis on the target image set, obtaining damage information in the target image set, and judging whether the target component is abnormal based on the damage information include:

[0017] Using a preset equipment external damage recognition model to extract damage information from the target image set, wherein the damage information includes damage type, damage level, and location information of the damage on the target component;

[0018] Obtaining preset component data conditions and comparing them with the damage information;

[0019] When the damage level in the damage information meets the preset component data condition, the target component is determined to be normal;

[0020] When the damage level in the damage information does not meet the preset component data conditions, the target component is determined to be abnormal.

[0021] As a further technical solution of the present invention, when the target component is abnormal, the step of adjusting the direction of the camera within the preset distance range according to the damage information so that the camera within the preset distance range is aimed at the damaged position of the target component includes:

[0022] When the target component is abnormal, obtaining the position information of the corresponding camera and the position information of the target component;

[0023] Generate absolute position information of the damage according to the position information of the target component and the position information of the damage on the target component;

[0024] Acquire the position information of a camera whose distance from the damaged absolute position information is within a preset range;

[0025] Generate camera adjustment angle information according to the absolute position information of the damage and the position information of the camera within a preset distance range;

[0026] The monitoring angle of each camera within the preset distance range is adjusted according to the camera adjustment angle information, so that the cameras within the preset distance range are aimed at the damaged position of the target component, thereby realizing high-precision verification and monitoring of industrial equipment.

[0027] As a further technical solution of the present invention, the step of obtaining the comprehensive monitoring video of the camera within the preset distance range, performing secondary recognition analysis on the video to obtain damage information, and determining the final damage level of the target component according to the secondary recognition analysis result and the damage information obtained by the preliminary recognition analysis includes:

[0028] Obtaining comprehensive monitoring videos from cameras within a preset distance range, performing secondary recognition analysis on the comprehensive monitoring videos, and obtaining damage information of target parts;

[0029] The damage information of the target parts obtained by the secondary identification analysis and the damage levels of the same damage type in the damage information obtained by the primary identification analysis are sorted from large to small to obtain a damage level sorting table;

[0030] The maximum value in the damage level ranking table is determined as the final damage level.

[0031] Another object of an embodiment of the present invention is to provide an industrial equipment monitoring system based on the industrial Internet, the system comprising:

[0032] A target image acquisition module is used to acquire monitoring video data of each industrial equipment in the operation workshop, and acquire a target image set from the monitoring video data based on a target detection algorithm; wherein each industrial equipment in the operation workshop uses a plurality of cameras to monitor the target components outside the equipment, and each camera is provided with a main monitoring angle;

[0033] a preliminary damage identification module, used to perform preliminary identification and analysis on the target image set, obtain damage information in the target image set, and determine whether the target component is abnormal based on the damage information, wherein the damage information includes damage type, damage level and location information of the damage on the target component;

[0034] A multi-angle monitoring module, used for adjusting the direction of the camera within the preset distance range according to the damage information when the target component is abnormal, so that the camera within the preset distance range is aimed at the damaged position of the target component;

[0035] A secondary damage recognition module is used to obtain the comprehensive monitoring video of the camera within a preset distance range, and perform secondary recognition analysis on it to obtain damage information, and determine the final damage level of the target component based on the secondary recognition analysis results and the damage information obtained by the preliminary recognition analysis;

[0036] An alarm prompt module is used to generate an alarm prompt instruction according to the final damage level.

[0037] As a further technical solution of the present invention, the damage preliminary identification module includes:

[0038] A damage information acquisition unit, used to extract damage information from the target image set using a preset equipment external damage recognition model, wherein the damage information includes damage type, damage level and location information of the damage on the target component;

[0039] A data comparison unit, used for obtaining preset component data conditions and comparing them with the damage information;

[0040] A part normality determination unit, configured to determine that the target part is normal when the damage level in the damage information meets a preset part data condition;

[0041] The part abnormality determination unit is used to determine that the target part is abnormal when the damage level in the damage information does not meet the preset part data conditions.

[0042] As a further technical solution of the present invention, the multi-angle monitoring module includes:

[0043] A position information acquisition unit, used to acquire position information of a corresponding camera and position information of a target component when the target component is abnormal;

[0044] A position information generating unit, used for generating absolute position information of the damage according to the position information of the target component and the position information of the damage on the target component;

[0045] A target information acquisition unit, used to acquire position information of a camera whose distance from the damaged absolute position information is within a preset range;

[0046] an adjustment information generating unit, configured to generate camera adjustment angle information according to the absolute position information of the damage and the position information of the camera within a preset distance range;

[0047] The monitoring angle adjustment unit is used to adjust the monitoring angle of each camera within a preset distance range according to the camera adjustment angle information, so that the cameras within the preset distance range are aimed at the damaged position of the target component, thereby realizing high-precision verification monitoring of industrial equipment.

[0048] As a further technical solution of the present invention, the damage secondary identification module includes:

[0049] A comprehensive data recognition unit, used to obtain comprehensive monitoring videos of cameras within a preset distance range, perform secondary recognition analysis on the comprehensive monitoring videos, and obtain damage information of target parts;

[0050] A damage information comparison unit is used to sort the damage information of the target parts obtained by the secondary identification analysis and the damage information of the same damage type obtained by the primary identification analysis from large to small, and obtain a damage level sorting table;

[0051] The final damage level determination unit is used to determine the maximum value in the damage level ranking table as the final damage level.

[0052] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention provides an industrial equipment monitoring method and system based on the industrial Internet, in which the external components of the industrial equipment are first monitored by each camera respectively, and real-time monitoring is performed on whether the components are damaged or abnormal, and the location of the damage is determined. When the component is initially determined to be abnormal, the cameras within a preset range of the damage can be accurately mobilized according to the preliminary identified damage information to simultaneously aim at the damage, thereby realizing multi-angle monitoring and identification of the damage, making the monitoring and identification results of the damage more accurate, improving the accuracy of monitoring, and ensuring the safe operation of industrial equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention.

[0054] Figure 1 This is a flowchart of the industrial equipment monitoring method based on the Industrial Internet.

[0055] Figure 2This is a flowchart of the steps of acquiring target images in the industrial equipment monitoring method based on the Industrial Internet.

[0056] Figure 3 This is a flowchart of the steps for initially determining damage anomalies in the industrial equipment monitoring method based on the Industrial Internet.

[0057] Figure 4 This is a flowchart of the multi-angle monitoring steps in the industrial equipment monitoring method based on the Industrial Internet.

[0058] Figure 5 The flowchart is a flow chart of the secondary damage determination step in the industrial equipment monitoring method based on the Industrial Internet.

[0059] Figure 6 This is the structural block diagram of the industrial equipment monitoring system based on the Industrial Internet. DETAILED DESCRIPTION

[0060] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0061] like Figure 1 As shown, an embodiment of the present invention provides an industrial equipment monitoring method based on the industrial Internet, and the method includes the following steps:

[0062] Step S100, obtaining monitoring video data of each industrial equipment in the operation workshop, and obtaining a target image set from the monitoring video data based on a target detection algorithm; wherein each industrial equipment in the operation workshop uses a plurality of cameras to monitor target components outside the equipment, and each camera is respectively provided with a main monitoring angle;

[0063] Among them, each camera monitors the target components it monitors in real time through the main monitoring angle. When no abnormality is found, each camera keeps the main monitoring angle unchanged and can obtain the position information and monitoring angle of each camera in real time. It can also obtain the position information of each component in each industrial equipment in the operation workshop and clarify the monitoring parameters of each camera;

[0064] Step S200, performing preliminary recognition and analysis on the target image set, obtaining damage information in the target image set, and judging whether the target component is abnormal based on the damage information, wherein the damage information includes damage type, damage level, and location information of the damage on the target component; wherein each damage type has a plurality of damage levels, and the location information of the damage on the target component may specifically refer to the location information of the center point of the damage contour on the target component;

[0065] Step S300, when the target component is abnormal, adjust the direction of the camera within the preset distance range according to the damage information, so that the camera within the preset distance range is aligned with the damaged position of the target component (wherein, the camera within the preset distance range is aligned with the damaged position of the target component can specifically refer to aligning the center point of the monitoring image of the camera within the preset distance range with the center point of the damaged contour of the target component, and the camera can also be aligned with the damage through other points);

[0066] Step S400, obtaining a comprehensive monitoring video of a camera within a preset distance range, performing secondary recognition analysis on the video to obtain damage information, and determining a final damage level of the target component based on the secondary recognition analysis result and the damage information obtained by the preliminary recognition analysis;

[0067] Step S500, generating an alarm prompt instruction according to the final damage level; the specific steps are: comparing the final damage level with the preset alarm damage level, when the final damage level is greater than the corresponding preset alarm damage level, determining that the target component is damaged, and generating an alarm prompt instruction, and also generating an instruction to rotate each camera back to the original main monitoring angle, and the alarm prompt instruction carries a comprehensive monitoring video.

[0068] In this embodiment, during use, each camera monitors the target component it monitors in real time through the main monitoring angle. When the camera finds that the target component is damaged, it can obtain damage information based on a preset equipment external damage recognition model. The damage information can adjust the direction of the camera whose distance from the damage is within a preset range, so that the camera within the preset distance range is aimed at the damaged position of the target component, thereby realizing multi-angle monitoring of the damage, determining the final damage level according to the results of multi-angle monitoring, and generating an alarm prompt instruction according to the final damage level, thereby improving the accuracy of monitoring and ensuring the safe operation of industrial equipment.

[0069] like Figure 2 As shown, as a preferred embodiment of the present invention, the step of acquiring monitoring video data of each industrial equipment in the operation workshop and acquiring a target image set from the monitoring video data based on a target detection algorithm includes:

[0070] Step S101, obtaining monitoring video data of each industrial equipment in the operation workshop;

[0071] Step S102, extracting sample pictures from the monitoring video data according to a preset time step to obtain a sample picture set;

[0072] The specific steps may be: determining a suitable preset time step, such as per second or per minute; segmenting the surveillance video according to the set time step to obtain a series of continuous frames; performing image processing and extraction on each segmented frame to obtain independent photos, thereby obtaining a sampled picture set.

[0073] Step S103, using a target detection algorithm to identify and analyze the sampled picture set, obtain the position information of the target parts in the sampled pictures, and intercept the target image where the target parts are located from the sampled pictures to obtain a target image set. Among them, the target detection algorithm can sample YOLO, Faster R-CNN, SSD, etc., and then use the training data set to train the target detection algorithm to generate a model suitable for the target parts, and apply the trained model to the sampled picture set to perform target parts detection, which will not be described in detail here.

[0074] like Figure 3 As shown, as a preferred embodiment of the present invention, the step of performing preliminary recognition and analysis on the target image set, obtaining damage information in the target image set, and judging whether the target component is abnormal based on the damage information includes:

[0075] Step S201, using a preset equipment external damage recognition model to extract damage information from the target image set, wherein the damage information includes damage type, damage level and location information of the damage on the target component, wherein the damage type includes crack, bend and fracture, etc., and the damage type includes a preset number of damage levels, for example, the damage level of crack includes primary crack, secondary crack and tertiary crack, etc., and the damage level of bend includes primary bend, secondary bend and tertiary bend, etc., and the higher the damage level, the more serious the damage;

[0076] The equipment external damage recognition model is based on a neural network model that is trained with a large amount of sample data. When the output result of the model reaches a preset accuracy rate, a trained equipment external damage recognition model is obtained, wherein the sample data includes equipment damage feature pictures and corresponding text labels. The text labels are normal and abnormal, and the abnormalities include damage type, damage level and damage location, etc. The specific equipment external damage recognition model training method is not described in detail here.

[0077] Step S202, obtaining preset component data conditions and comparing them with the damage information, wherein the preset component data conditions include a preset damage level within a normal range;

[0078] Step S203, when the damage level in the damage information meets the preset component data condition, the target component is determined to be normal, and if normal, there is no need to mobilize other cameras;

[0079] Step S204: when the damage level in the damage information does not meet the preset component data condition, the target component is determined to be abnormal.

[0080] like Figure 4 As shown, as a preferred embodiment of the present invention, when the target component is abnormal, the step of adjusting the direction of the camera within the preset distance range according to the damage information so that the camera within the preset distance range is aimed at the damaged position of the target component includes:

[0081] Step S301, when the target component is abnormal, obtaining the position information of the corresponding camera (the corresponding camera refers to the camera that discovers the abnormality) and the position information of the target component;

[0082] Step S302, generating the absolute position information of the damage according to the position information of the target component and the position information of the damage on the target component (the absolute position information of the damage here refers to the absolute position information of the damage in the operation workshop, and the position information of the damage on the target component is also the actual position information of the damage on the target component);

[0083] Step S303, obtaining the position information of a camera whose distance from the damaged absolute position information is within a preset range;

[0084] Step S304, generating camera adjustment angle information according to the absolute position information of the damage and the position information of the camera within a preset distance range;

[0085] Step S305, adjusting the monitoring angle of each camera within the preset distance range according to the camera adjustment angle information, so that the cameras within the preset distance range are aimed at the damaged position of the target component, thereby achieving high-precision verification monitoring of the industrial equipment.

[0086] like Figure 5 As shown, as a preferred embodiment of the present invention, the step of obtaining the comprehensive monitoring video of the camera within the preset distance range, performing secondary recognition analysis on the video to obtain damage information, and determining the final damage level of the target component according to the secondary recognition analysis result and the damage information obtained by the preliminary recognition analysis includes:

[0087] Step S401, obtaining a comprehensive monitoring video of a camera within a preset distance range, performing secondary recognition and analysis on the comprehensive monitoring video, and obtaining damage information of the target component; the method of obtaining the damage information here is the same as the method of obtaining the damage information by preliminary recognition mentioned above, and will not be repeated here;

[0088] Step S402, sorting the damage information of the target parts obtained by the secondary identification analysis and the damage levels of the same damage type in the damage information obtained by the primary identification analysis from large to small to obtain a damage level sorting table;

[0089] Step S403: determine the maximum value in the damage level ranking table as the final damage level.

[0090] In this embodiment, damage is monitored and identified by multiple cameras within a preset distance range, thereby achieving high-precision verification and monitoring of damage, making the final damage level obtained more accurate and avoiding the phenomenon of inadequate monitoring.

[0091] like Figure 6 As shown, another object of the embodiment of the present invention is to provide an industrial equipment monitoring system based on the industrial Internet, the system comprising:

[0092] The target image acquisition module 100 is used to acquire monitoring video data of each industrial equipment in the operation workshop, and acquire a target image set from the monitoring video data based on a target detection algorithm; wherein each industrial equipment in the operation workshop uses a plurality of cameras to monitor the target components outside the equipment, and each camera is respectively provided with a main monitoring angle;

[0093] A preliminary damage identification module 200 is used to perform preliminary identification and analysis on the target image set, obtain damage information in the target image set, and determine whether the target component is abnormal based on the damage information, wherein the damage information includes damage type, damage level and location information of the damage on the target component;

[0094] The multi-angle monitoring module 300 is used to adjust the direction of the camera within the preset distance range according to the damage information when the target component is abnormal, so that the camera within the preset distance range is aimed at the damaged position of the target component;

[0095] The damage secondary identification module 400 is used to obtain the comprehensive monitoring video of the camera within a preset distance range, and perform secondary identification analysis on it to obtain damage information, and determine the final damage level of the target component according to the secondary identification analysis result and the damage information obtained by the preliminary identification analysis;

[0096] The alarm prompt module 500 is used to generate an alarm prompt instruction according to the final damage level.

[0097] As a preferred embodiment of the present invention, the damage preliminary identification module 200 includes:

[0098] A damage information acquisition unit, used to extract damage information from the target image set using a preset equipment external damage recognition model, wherein the damage information includes damage type, damage level and location information of the damage on the target component;

[0099] A data comparison unit, used for obtaining preset component data conditions and comparing them with the damage information;

[0100] A part normality determination unit, configured to determine that the target part is normal when the damage level in the damage information meets a preset part data condition;

[0101] The part abnormality determination unit is used to determine that the target part is abnormal when the damage level in the damage information does not meet the preset part data conditions.

[0102] As a preferred embodiment of the present invention, the multi-angle monitoring module 300 includes:

[0103] A position information acquisition unit, used to acquire position information of a corresponding camera and position information of a target component when the target component is abnormal;

[0104] A position information generating unit, used for generating absolute position information of the damage according to the position information of the target component and the position information of the damage on the target component;

[0105] A target information acquisition unit, used to acquire position information of a camera whose distance from the damaged absolute position information is within a preset range;

[0106] an adjustment information generating unit, configured to generate camera adjustment angle information according to the absolute position information of the damage and the position information of the camera within a preset distance range;

[0107] The monitoring angle adjustment unit is used to adjust the monitoring angle of each camera within a preset distance range according to the camera adjustment angle information, so that the cameras within the preset distance range are aimed at the damaged position of the target component, thereby realizing high-precision verification monitoring of industrial equipment.

[0108] As a preferred embodiment of the present invention, the damage secondary identification module 400 includes:

[0109] A comprehensive data recognition unit, used to obtain comprehensive monitoring videos of cameras within a preset distance range, perform secondary recognition analysis on the comprehensive monitoring videos, and obtain damage information of target parts;

[0110] A damage information comparison unit is used to sort the damage information of the target parts obtained by the secondary identification analysis and the damage information of the same damage type obtained by the primary identification analysis from large to small, and obtain a damage level sorting table;

[0111] The final damage level determination unit is used to determine the maximum value in the damage level ranking table as the final damage level.

[0112] The functions that can be achieved by the above-mentioned industrial equipment monitoring method based on the industrial Internet are all completed by computer equipment. The computer equipment includes one or more processors and one or more memories. At least one program code is stored in the one or more memories. The program code is loaded and executed by the one or more processors to achieve the functions of the industrial equipment monitoring method based on the industrial Internet.

[0113] The processor takes out instructions from the memory one by one, analyzes the instructions, and then completes the corresponding operations according to the instruction requirements, generating a series of control commands, so that the various parts of the computer can automatically, continuously and coordinately move to become an organic whole, realize the input of programs, the input of data, and the calculation and output of results. The arithmetic operations or logical operations generated in this process are all completed by the operator; the memory includes a read-only memory (ROM), which is used to store computer programs, and a protection device is provided outside the memory.

[0114] Exemplarily, the computer program may be divided into one or more modules, one or more modules are stored in a memory and executed by a processor to implement the present invention. One or more modules may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program in a terminal device.

[0115] Those skilled in the art will understand that the description of the above service equipment is merely an example and does not constitute a limitation on the terminal equipment. It may include more or fewer components than described above, or a combination of certain components, or different components, for example, it may include input and output devices, network access devices, buses, etc.

[0116] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire user terminal.

[0117] The memory can be used to store computer programs and / or modules. The processor can realize various functions of the terminal device by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as an information collection template display function, a product information release function, etc.); the data storage area can store data created according to the use of the berth status display system (such as product information collection templates corresponding to different product types, product information that different product providers need to release, etc.). In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0118] If the module / unit integrated in the terminal device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the modules / units in the above-mentioned embodiment system, and can also be completed by instructing the relevant hardware through a computer program. The above-mentioned computer program can be stored in a computer-readable storage medium, and the computer program can realize the functions of the above-mentioned various system embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. Computer-readable media may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0119] It should be noted that, in this article, the term "comprises" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of more restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0120] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. An industrial equipment monitoring method based on the industrial Internet, characterized in that: The method comprises the following steps: Acquire monitoring video data of each industrial equipment in the operation workshop, and acquire a target image set from the monitoring video data based on a target detection algorithm; wherein each industrial equipment in the operation workshop uses a plurality of cameras to monitor target components outside the equipment, and each camera is respectively provided with a main monitoring angle; Performing preliminary recognition and analysis on the target image set, obtaining damage information in the target image set, and judging whether the target component is abnormal based on the damage information, wherein the damage information includes damage type, damage level, and location information of the damage on the target component; When the target component is abnormal, the direction of the camera within the preset distance range is adjusted according to the damage information so that the camera within the preset distance range is aimed at the damaged position of the target component; Obtain comprehensive surveillance video from cameras within a preset distance range, perform secondary recognition analysis on the video to obtain damage information, and determine the final damage level of the target component based on the secondary recognition analysis results and the damage information obtained from the preliminary recognition analysis; generating an alarm prompt instruction according to the final damage level; When the target component is abnormal, the step of adjusting the direction of the camera within the preset distance range according to the damage information so that the camera within the preset distance range is aimed at the damaged position of the target component comprises: When the target component is abnormal, obtaining the position information of the corresponding camera and the position information of the target component; Generate absolute position information of the damage according to the position information of the target component and the position information of the damage on the target component; Acquire the position information of a camera whose distance from the damaged absolute position information is within a preset range; Generate camera adjustment angle information according to the absolute position information of the damage and the position information of the camera within a preset distance range; According to the camera adjustment angle information, the monitoring angle of each camera within the preset distance range is adjusted so that the cameras within the preset distance range are aligned with the damaged position of the target component; Aligning the camera within a preset distance range with the damaged position of the target component, specifically aligning the center point of the monitoring image of the camera within the preset distance range with the center point of the damaged contour of the target component; The step of performing preliminary recognition and analysis on the target image set, obtaining damage information in the target image set, and judging whether the target component is abnormal based on the damage information comprises: Using a preset equipment external damage recognition model to extract damage information from the target image set, wherein the damage information includes damage type, damage level, and location information of the damage on the target component; Obtaining preset component data conditions and comparing them with the damage information; When the damage level in the damage information meets the preset component data condition, the target component is determined to be normal; When the damage level in the damage information does not meet the preset component data condition, the target component is determined to be abnormal; The equipment external damage recognition model is obtained by training a large amount of sample data based on a neural network model. When the output result of the model reaches a preset accuracy rate, a trained equipment external damage recognition model is obtained, wherein the sample data includes equipment damage feature pictures and corresponding text labels. The text labels are normal and abnormal, and the abnormalities include damage type, damage level and damage location.

2. According to claim 1, an industrial equipment monitoring method based on industrial Internet is characterized in that: The step of acquiring monitoring video data of each industrial equipment in the operation workshop and acquiring a target image set from the monitoring video data based on a target detection algorithm comprises: Obtain monitoring video data of various industrial equipment in the operation workshop; Extracting sample pictures from the surveillance video data according to a preset time step to obtain a sample picture set; The target detection algorithm is used to identify and analyze the sampled picture set, obtain the position information of the target parts in the sampled pictures, and intercept the target images where the target parts are located from the sampled pictures to obtain the target image set.

3. According to the industrial equipment monitoring method based on industrial Internet according to claim 1, it is characterized in that: The step of obtaining the comprehensive monitoring video of the camera within the preset distance range, performing secondary recognition analysis on the video to obtain damage information, and determining the final damage level of the target component according to the secondary recognition analysis result and the damage information obtained by the preliminary recognition analysis includes: Obtaining comprehensive monitoring videos from cameras within a preset distance range, performing secondary recognition analysis on the comprehensive monitoring videos, and obtaining damage information of target parts; The damage information of the target parts obtained by the secondary identification analysis and the damage levels of the same damage type in the damage information obtained by the primary identification analysis are sorted from large to small to obtain a damage level sorting table; The maximum value in the damage level ranking table is determined as the final damage level.

4. An industrial equipment monitoring system based on the industrial Internet, characterized in that: The system comprises: A target image acquisition module is used to acquire monitoring video data of each industrial equipment in the operation workshop, and acquire a target image set from the monitoring video data based on a target detection algorithm; wherein each industrial equipment in the operation workshop uses a plurality of cameras to monitor the target components outside the equipment, and each camera is provided with a main monitoring angle; a preliminary damage identification module, used to perform preliminary identification and analysis on the target image set, obtain damage information in the target image set, and determine whether the target component is abnormal based on the damage information, wherein the damage information includes damage type, damage level and location information of the damage on the target component; A multi-angle monitoring module, used for adjusting the direction of the camera within the preset distance range according to the damage information when the target component is abnormal, so that the camera within the preset distance range is aimed at the damaged position of the target component; A secondary damage recognition module is used to obtain the comprehensive monitoring video of the camera within a preset distance range, and perform secondary recognition analysis on it to obtain damage information, and determine the final damage level of the target component based on the secondary recognition analysis results and the damage information obtained by the preliminary recognition analysis; An alarm prompt module, used for generating an alarm prompt instruction according to the final damage level; The multi-angle monitoring module includes: A position information acquisition unit, used to acquire position information of a corresponding camera and position information of a target component when the target component is abnormal; A position information generating unit, used for generating absolute position information of the damage according to the position information of the target component and the position information of the damage on the target component; A target information acquisition unit, used to acquire position information of a camera whose distance from the damaged absolute position information is within a preset range; An adjustment information generating unit, configured to generate camera adjustment angle information according to the absolute position information of the damage and the position information of the camera within a preset distance range; A monitoring angle adjustment unit, used to adjust the monitoring angle of each camera within a preset distance range according to the camera adjustment angle information, so that the cameras within the preset distance range are aligned with the damaged position of the target component; Aligning the camera within a preset distance range with the damaged position of the target component, specifically aligning the center point of the monitoring image of the camera within the preset distance range with the center point of the damaged contour of the target component; The damage preliminary identification module includes: A damage information acquisition unit, used to extract damage information from the target image set using a preset equipment external damage recognition model, wherein the damage information includes damage type, damage level and location information of the damage on the target component; A data comparison unit, used for obtaining preset component data conditions and comparing them with the damage information; A part normality determination unit, configured to determine that the target part is normal when the damage level in the damage information meets a preset part data condition; A component abnormality determination unit, configured to determine that the target component is abnormal when the damage level in the damage information does not meet the preset component data condition; The equipment external damage recognition model is obtained by training a large amount of sample data based on a neural network model. When the output result of the model reaches a preset accuracy rate, a trained equipment external damage recognition model is obtained, wherein the sample data includes equipment damage feature pictures and corresponding text labels. The text labels are normal and abnormal, and the abnormalities include damage type, damage level and damage location.

5. According to claim 4, an industrial equipment monitoring system based on industrial Internet is characterized in that: The damage secondary identification module includes: A comprehensive data recognition unit, used to obtain comprehensive monitoring videos of cameras within a preset distance range, perform secondary recognition analysis on the comprehensive monitoring videos, and obtain damage information of target parts; A damage information comparison unit is used to sort the damage information of the target parts obtained by the secondary identification analysis and the damage information of the same damage type obtained by the primary identification analysis from large to small, and obtain a damage level sorting table; The final damage level determination unit is used to determine the maximum value in the damage level ranking table as the final damage level.

Images