Energy supply chain management system based on machine vision perception and energy production and sales relationship combination

Abstract

The application provides an energy supply chain management system based on machine vision perception and energy production and sales relationship combination, relates to the technical field of energy internet, and comprises a perception layer, data acquired by the perception layer is uploaded to a platform layer through a network layer, and the platform layer analyzes and then issues analysis results to an application layer. Through construction of an energy management system integrating real-time monitoring of device states, self-evaluation of data quality, deep fusion of multi-source information and intelligent prediction of production capacity, the application realizes cooperation of front-end optical self-checking and back-end intelligent processing, and improves monitoring precision of energy production equipment, system maintenance efficiency and scientificity of production and sales decision.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of energy internet, and particularly relates to an energy supply chain management system based on machine vision perception and energy production and sales relationship. BACKGROUND

[0002] When the machine vision is applied in the energy supply chain management system, the equipment state, environmental safety and operation efficiency of energy production, transportation and consumption can be monitored and intelligently diagnosed in real time through image recognition and analysis technology, so that fine management and optimization of the energy production and sales process can be realized, for example, equipment abnormal state is recognized to prevent fault shutdown, the surrounding environment of energy facilities is analyzed to eliminate safety hazards, and energy flow and equipment operation parameters are monitored to optimize production scheduling, so as to finally improve the reliability, safety and economy of the energy supply chain.

[0003] However, in the prior art, the existing energy supply chain management system widely uses cameras for visual monitoring, but the cameras installed outdoors are easily affected by weather factors such as strong wind and heavy rain, and are prone to shaking and displacement, resulting in distorted pictures and reduced data reliability. The software algorithm for post-image stabilization cannot evaluate data quality from the source, and the effect is limited under high-precision requirements, and there is room for improvement. SUMMARY

[0004] The purpose of the present application is to solve the problems in the prior art by constructing an energy management system integrating real-time monitoring of equipment state, self-evaluation of data quality, deep fusion of multi-source information and intelligent prediction of production capacity, and combining the cooperation of front-end optical self-checking and back-end intelligent processing to improve the monitoring accuracy of energy production equipment, system maintenance efficiency and the scientific nature of production and sales decision-making.

[0005] In order to achieve the above purpose, the technical scheme adopted by the present application is as follows: an energy supply chain management system based on machine vision perception and energy production and sales relationship, comprising a perception layer, data obtained by the perception layer is uploaded to a platform layer through a network layer, the platform layer analyzes and then issues the analysis results to an application layer;

[0006] The perception layer comprises a visual perception unit for monitoring energy production equipment, a visual unit self-checking module for monitoring the visual perception unit and an Internet of Things sensing unit for energy production data;

[0007] The network layer is used to transmit image data collected by the perception layer, data of the visual unit self-checking module and energy production data to the platform layer;

[0008] The platform layer comprises a data pool for storing data, a machine vision analysis module for analyzing image data, a pre-screening module for judging image quality, and a collaborative analysis module for comprehensive analysis of perception layer data.

[0009] As a preferred embodiment, the visual unit self-checking module comprises a laser emitter mounted on the camera and a cylindrical laser receiver mounted on the camera mounting structure, the cylindrical laser receiver comprises a bottom laser receiver array, the side of the bottom laser receiver array is provided with a side laser receiver array, the axis of the bottom laser receiver array overlaps with the axis of the side laser receiver array, the bottom laser receiver is provided with a laser reflection surface on the side surface close to the side laser receiver array, the infrared laser emitted by the laser emitter is refracted and reflected by the laser reflection surface, part of the laser reflected by the laser reflection surface is directed to the side laser receiver array, and part of the laser refracted by the laser reflection surface is directed to the bottom laser receiver array.

[0010] As a preferred embodiment, after the pre-screening module obtains the image data of the visual perception unit and the infrared perception data of the visual unit self-checking module, the pre-screening module calculates the laser path according to the point position data of the side laser receiver array and the point position data of the bottom laser receiver array in the visual unit self-checking module, calculates the change of the orientation angle of the laser emitter, calculates the specific offset data of the image data according to the change data of the orientation angle of the laser emitter, and performs three-level marking on the image data according to the preset offset threshold value: the first level is the image data with an offset degree less than or equal to 3%, the second level is the image data with an offset degree greater than 3% and less than or equal to 5%, and the third level is the image data with an offset degree greater than 5%.

[0011] As a preferred embodiment, the specific logic of the offset data calculation of the pre-screening module is as follows:

[0012] Firstly, the pre-screening module reads the spot coordinates of the side laser receiver array and the bottom laser receiver array, then the pre-screening module calculates the horizontal deflection angle according to the spot coordinate data of the side laser receiver array, the pre-screening module calculates the pitch angle according to the spot coordinate data of the bottom laser receiver array, the calculation result of the horizontal deflection angle is used as the horizontal resolution calculation parameter of the image, the calculation result of the pitch angle is used as the vertical resolution calculation parameter of the image, the expected offset pixel value of the image center point in the horizontal and vertical directions is calculated respectively, and the modulus of the overall offset degree is calculated to obtain the percentage of the offset vector relative to the diagonal line size of the entire image.

[0013] As a preferred embodiment, the machine vision analysis module receives image data screened by the pre-screening module, performs regular image preprocessing on the first-level marked image according to the offset mark of the pre-screening module on the image data, performs image correction and angle correction preprocessing on the second-level marked image according to the offset data, performs time axis marking on the third-level marked image and sends the image to the data pool for processing, then selects the corresponding contrast image according to the camera number corresponding to the image data, compares the image data with the contrast image, and outputs the result to the data pool and the collaborative analysis module.

[0014] As a preferred embodiment, the collaborative analysis module receives the image data analyzed by the machine vision analysis module and the sensing data of the Internet of Things sensing unit, then performs data cleaning and space-time alignment on the analyzed image data and the sensing data, performs association, matching and feature extraction on the analyzed image data and the sensing data according to the preset logic, then performs collaborative reasoning and predictive analysis based on the preset rules, generates a prediction report based on the result of the predictive analysis, and sends the prediction report to the application layer.

[0015] As a preferred embodiment, the cameras of the visual sensing unit of the sensing unit and the bottom laser receiver array and the side laser receiver array of the visual unit self-checking module are grouped and numbered when the system is constructed, and each group of the visual sensing unit and the visual unit self-checking module is assigned a number.

[0016] As a preferred embodiment, the visual sensing unit and the visual unit self-checking module perform contrast image acquisition when the installation is completed, and upload the acquired contrast image to the data pool for storage.

[0017] As a preferred embodiment, the application layer provides an interactive interface for users.

[0018] Compared with the prior art, the application has the advantages and positive effects that:

[0019] 1. The application constructs an energy management system integrating real-time monitoring of device status, self-evaluation of data quality, deep fusion of multi-source information and intelligent prediction of production capacity, and improves the monitoring accuracy of energy production equipment, the system maintenance efficiency and the scientificity of production and sales decision-making through the cooperation of front-end optical self-checking and back-end intelligent processing.

[0020] 2. The application constructs a complete mathematical conversion chain from physical spot displacement to image pixel offset, realizes high-precision digital representation of the offset amount of the camera through deep fusion of optical measurement and geometric calculation, not only provides accurate correction parameters for subsequent image processing, but also optimizes the allocation of analysis resources through a hierarchical mechanism, and fundamentally improves the reliability of visual monitoring data and the overall efficiency of the system. Attached Figure Description

[0021] Fig. 1 The present invention proposes a module diagram for an energy supply chain management system based on the combination of machine vision perception and energy production and sales relationships.

[0022] Fig. 2 This invention proposes an operation flowchart for an energy supply chain management system based on the combination of machine vision perception and energy production and sales relationships.

[0023] Fig. 3 This invention presents an infrared light path diagram of the self-inspection module of the vision unit in an energy supply chain management system that combines machine vision perception with energy production and sales relationships. Detailed Implementation

[0024] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0025] Example 1

[0026] like Figs. 1-3 As shown, this invention provides a technical solution: an energy supply chain management system based on machine vision perception and the integration of energy production and sales relationships. The system includes a perception layer, where data acquired by the perception layer is uploaded to a platform layer via a network layer. The platform layer analyzes the data and then distributes the analysis results to the application layer. Specifically, the perception layer collects visual information from energy production equipment, camera status data, and physical energy data in real time. The network layer acts as a transmission channel, reliably uploading this heterogeneous data to the platform layer. The platform layer, acting as an intelligent hub, utilizes the storage capacity of a data pool, the image quality assessment and grading capabilities of a pre-screening module, the image recognition and processing capabilities of a machine vision analysis module, and the multi-source data fusion and predictive analysis capabilities of a collaborative analysis module to perform in-depth data processing. Finally, the analysis results and prediction reports are communicated to the user through an interactive interface via the application layer.

[0027] The perception layer includes a visual perception unit for monitoring the energy production equipment, a visual unit self-checking module for monitoring the visual perception unit, and an Internet of Things sensing unit for energy production data, the camera of the visual perception unit of the visual perception unit and the bottom laser receiver array and the side laser receiver array of the visual unit self-checking module are grouped and numbered when the system is constructed, each group of the visual perception unit and the visual unit self-checking module is applicable to one number, the visual perception unit and the visual unit self-checking module are compared and image data is collected after installation is completed, and the collected contrast image is uploaded to a data pool for storage, specifically, through the cooperative deployment of the visual perception unit, the visual unit self-checking module and the Internet of Things sensing unit in the perception layer, a three-dimensional data perception system integrating device monitoring, self-monitoring and energy data collection is constructed, and the camera of the visual perception unit and the bottom laser receiver array and the side laser receiver array of the visual unit self-checking module are bound as the same numbered group when the system is implemented, so as to ensure that the image data and the corresponding self-checking state data in the subsequent data stream have unique correlation, so that accurate tracing can be realized when the platform layer is processed, and the contrast image collected and uploaded to the data pool for storage immediately after installation is completed can provide a standard reference system for the machine vision analysis module, the continuous monitoring of the self-checking module and the real-time data supplement of the Internet of Things sensing unit are realized by using laser spot coordinate calculation camera offset, not only the visual monitoring of the running state of the energy production equipment is realized, but also through the device grouping relationship and the reference image fixed in the early stage, the platform layer can efficiently and accurately process each frame of image and each piece of sensing data when judging image quality, offset correction, multi-source data fusion and analysis in the subsequent stage, greatly improving the data consistency and decision reliability of the entire energy supply chain management system.

[0028] The network layer is used for transmitting the image data collected by the perception layer, the data of the visual unit self-checking module and the energy production data to the platform layer, specifically, the network layer as the core data transmission channel connecting the perception layer and the platform layer can use a high-bandwidth, low-delay communication protocol such as industrial Ethernet or 5G technology to transmit the multi-source heterogeneous data collected by the perception layer, including the high-resolution image stream generated by the visual perception unit, the laser spot coordinate and device state data generated by the visual unit self-checking module, and the real-time energy production data collected by the Internet of Things sensing unit, the network layer can implement compression coding on the image type large flow data to reduce bandwidth occupation through the built-in data preprocessing and priority scheduling mechanism, and high-priority real-time transmission queues are used for the self-checking state data and the energy sensing data to ensure their timeliness and integrity, and time stamp synchronization technology can be used to ensure the spatiotemporal consistency of all data in the transmission process.

[0029] The platform layer comprises a data pool for storing data, a machine vision analysis module for analyzing image data, a pre-screening module for judging image quality, and a collaborative analysis module for comprehensive analysis of perception layer data, the pre-screening module performs three-level marking on image data according to the offset condition of the image, specifically, through the collaborative operation of the data pool, the machine vision analysis module, the pre-screening module and the collaborative analysis module, a multi-level processing flow from data storage, quality judgment to intelligent analysis is constructed, the pre-screening module receives the image data of the visual perception unit uploaded by the network layer and the laser perception data of the visual unit self-checking module, can calculate the horizontal deflection angle and the pitch angle of the laser emitter according to the spot coordinate data, and then deduce the pixel offset value of the image center point in the horizontal and vertical directions, and obtain the accurate overall offset degree percentage by calculating the ratio of the modulus of the offset vector to the size of the image diagonal, then automatically mark the image data according to the preset offset threshold.

[0030] The application layer provides an interactive interface for users, specifically, the application layer can realize the function of receiving and intuitively presenting various analysis results issued by the platform layer through the interactive interface integrating data visualization, real-time monitoring, early warning notification and decision support functions, the application layer can build a customizable dashboard using a high-interactive front-end framework based on Web, and dynamically render the visual chart of the energy equipment running state, real-time video stream and early warning information panel through the real-time docking of the API gateway with the data pool and analysis module of the platform layer, so that the user can trigger the re-analysis request or model optimization instruction of the platform layer through interface interaction.

[0031] Further, the machine vision analysis module receives the image data screened by the pre-screening module, according to the offset mark of the image data by the pre-screening module, performs regular image preprocessing on the first-level marked image, performs image correction and angle correction preprocessing according to the offset data on the second-level marked image, performs time axis marking on the third-level marked image and sends it to the data pool for processing, then selects the corresponding contrast image according to the camera number corresponding to the image data, compares and analyzes the image data and the contrast image, and outputs the result to the data pool and the collaborative analysis module. Specifically, the machine vision analysis module receives the image data marked by the pre-screening module, first implements a differentiated processing flow according to different marking levels: for the first-level marked image, directly perform regular image preprocessing, including noise filtering, contrast enhancement and edge sharpening basic operations, for the second-level marked image, first according to the horizontal deflection angle and pitch angle data calculated by the pre-screening module, through affine transformation algorithm or perspective transformation algorithm, geometric correction and angle correction are performed to eliminate the distortion caused by the change of camera pose, and then regular preprocessing is performed, while for the third-level marked image, the analysis process is suspended, accurate timestamp is automatically added and directly archived to the data pool as the original data of device state abnormality or later traceability, then the machine vision analysis module calls the corresponding number of reference contrast image collected during system initialization from the data pool according to the camera number associated with the image data, compares and analyzes through feature point matching and deep learning model, identifies the abnormal state, operating parameter or environmental change of the energy production equipment, finally synchronously outputs the analysis result to the data pool for persistent storage, and pushes it to the collaborative analysis module in real time for multi-source data fusion.

[0032] Further, the collaborative analysis module receives the image data analyzed by the machine vision analysis module and the perception data of the IoT sensing unit, then performs data cleaning and spatio-temporal alignment on the analyzed image data and the perception data, and then performs association, matching and feature extraction on the analyzed image data and the perception data according to a preset logic, and then performs collaborative reasoning and predictive analysis based on a preset rule, and generates a prediction report of the predictive analysis and sends it to the application layer. Specifically, the collaborative analysis module serves as the data fusion and intelligent decision-making hub of the platform layer. By receiving the image data processed by the machine vision analysis module and the real-time perception data of the IoT sensing unit, the collaborative analysis module first performs data cleaning of removing abnormal values and filling missing values on the heterogeneous data, and performs spatio-temporal alignment by mapping the unified time stamp and spatial coordinates, to ensure the consistency of the vision data and the sensing data in the time and spatial dimensions. Then, based on the preset association rule, the image features and the sensing parameters are matched and fused, and the deep association features in the multi-source data are mined by using the feature extraction algorithm. Finally, based on the preset rule base or machine learning model, collaborative reasoning and predictive analysis are performed, and the analysis result is generated into a structured prediction report, which is issued to the application layer through the API interface.

[0033] In the embodiment, the perception layer constructs a multi-source data acquisition basis, in which the visual perception unit monitors the equipment operation state, the visual unit self-checking module monitors the camera pose change in real time through the designed optical monitoring mechanism, the IoT sensing unit collects energy production parameters, and the data traceability basis is established through the device grouping number and the reference image acquisition and storage during system initialization; the platform layer constitutes an intelligent processing core, the data pool centrally stores the original data and the processed data, the pre-screening module deduces the pixel-level offset according to the laser spot coordinates of the self-checking module and classifies it according to the threshold value, the machine vision analysis module processes it differently according to the difference, and the collaborative analysis module fuses the vision analysis result and the sensing data, and generates a prediction report by using multi-source feature fusion and prediction algorithm after data cleaning and spatio-temporal alignment; the application layer presents the analysis result.

[0034] Embodiment 2

[0035] As Figs. 1-3As shown, the visual unit self-checking module includes a laser emitter mounted on the camera and a cylindrical laser receiver mounted on the camera mounting structure, the cylindrical laser receiver includes a bottom laser receiver array, the side of the bottom laser receiver array is provided with a side laser receiver array, the axis of the bottom laser receiver array overlaps the axis of the side laser receiver array, the bottom laser receiver is provided with a laser reflection surface on one side close to the side laser receiver array, the infrared laser emitted by the laser emitter is refracted and reflected by the laser reflection surface, part of the laser reflected by the laser reflection surface is directed to the side laser receiver array, and part of the laser refracted by the laser reflection surface is directed to the bottom laser receiver array. Specifically, the visual unit self-checking module realizes accurate self-monitoring of the camera posture through optical structure design. The space geometric measurement system composed of the laser emitter mounted on the camera and the cylindrical laser receiver fixed on the mounting structure: the infrared laser beam emitted by the laser emitter is directed to the laser reflection surface on the bottom laser receiver array, which can be made of a semi-transparent and semi-reflective optical coating, the laser reflection surface simultaneously reflects and refracts, the reflected part of the laser is directed to the side laser receiver array at a specific angle, and the refracted part of the laser is directly transmitted to the bottom laser receiver array. The axes of the bottom laser receiver array and the side laser receiver array coincide to ensure the uniformity of the measurement reference. When the camera changes its position, the laser emitter moves with the camera, causing the incident light path to change, thereby causing the spot coordinates on the bottom array and the side array to shift. By analyzing the spot displacement data on the two perpendicular laser receiver arrays, the angular displacement in the three-dimensional space of the camera can be calculated, providing a quantitative basis for the image quality classification of the subsequent pre-screening module.

[0036] Further, after the pre-screening module obtains the image data of the visual perception unit and the infrared perception data of the visual unit self-checking module, the point position data of the side laser receiver array and the point position data of the bottom laser receiver array in the visual unit self-checking module are used to calculate the laser path, thereby calculating the change in the orientation angle of the laser emitter. According to the orientation angle change data of the laser emitter, the specific offset data of the image data is calculated. According to the preset offset threshold, the image data is marked in three levels: level one is image data with an offset degree less than or equal to 3%, level two is image data with an offset degree greater than 3% and less than or equal to 5%, and level three is image data with an offset degree greater than 5%. Specifically, the pre-screening module constructs an efficient data filtering mechanism according to the influence of the camera position change on the image quality, quantifies the influence of the camera position change on the image quality, not only provides clear classification processing basis for the subsequent machine vision analysis module, but also significantly reduces the processing overhead of invalid data through front-end quality evaluation, and improves the resource utilization rate and analysis reliability of the entire system.

[0037] The offset data calculation specific logic of the pre-screening module is as follows:

[0038] First, the pre-screening module reads the spot coordinates of the side laser receiver array and the bottom laser receiver array, then the pre-screening module calculates the horizontal deflection angle according to the spot coordinate data of the side laser receiver array, the pre-screening module calculates the pitch angle according to the spot coordinate data of the bottom laser receiver array, the calculation result of the horizontal deflection angle is used as the horizontal resolution calculation parameter of the image, the calculation result of the pitch angle is used as the vertical resolution calculation parameter of the image, the expected pixel value of the image center point in the horizontal and vertical directions is calculated respectively, then the modulus of the overall offset is calculated, and the percentage of the offset vector relative to the diagonal line of the entire image is obtained, which is specifically as follows:

[0039] According to the spot horizontal displacement Δx of the side laser receiver array and the system focal length parameter f, the horizontal deflection angle θ is calculated:

[0040] θ = arctan (Δx / f);

[0041] According to the spot vertical displacement Δy of the bottom array and the focal length f, the pitch angle φ is calculated:

[0042] φ = arctan (Δy / f);

[0043] Convert the angle to pixel offset:

[0044] Calculate the horizontal pixel offset ΔP x :

[0045] ΔP x =k x ×tanθ×R, wherein k x is the horizontal proportionality coefficient, and R is the image resolution;

[0046] Calculate the vertical pixel offset ΔP y :

[0047] ΔP y =k y ×tanφ×R, wherein k y is the vertical proportionality coefficient;

[0048] Calculate the overall offset modulus |ΔP|:

[0049] |ΔP| = √(ΔP x ²+ΔP y ²);

[0050] Compare with the diagonal pixel length L diag of the image to obtain the percentage offset δ:

[0051] δ = (|ΔP| / Ldiag ) x 100 %;

[0052] Offset degree classification: first level is delta <= 3%; second level is 3% < delta <= 5%; third level is delta > 5%.

[0053] In the embodiment, the precise quantitative monitoring of the camera pose is realized by the designed optical-geometric measurement system, wherein the vision unit self-checking module utilizes the laser transmitter installed on the camera and the cylindrical laser receiver fixed to the mounting structure to form a spatial measurement basis: the infrared laser emitted by the laser transmitter is irradiated to the semi-transparent and semi-reflective optical coating reflecting surface on the bottom laser receiver array, the reflecting surface simultaneously generates reflecting and refracting optical phenomena, the reflecting light beam is projected to the side laser receiver array, and the refracting light beam directly reaches the bottom laser receiver array; when the camera pose changes, the moving laser transmitter causes the incident light path to change, thereby forming spot displacement on the two side arrays; the pre-screening module calculates the horizontal deflection angle and the pitch angle by analyzing the spot coordinate data and combining the system focal length parameters, and then converts the image pixel offset amount through the projection geometry model, finally calculates the overall offset degree module length and compares it with the image diagonal pixel length to obtain the percentage offset degree, and marks the three levels according to the delta value.

[0054] Working principle:

[0055] As shown in Figs. 1-3 , before the construction, the associated logic and rules of the perception layer data are first formulated, then the vision perception unit is installed at the preset position, the laser transmitter of the vision unit self-checking module is installed on the camera of the vision perception unit, the bottom laser receiver array and the side laser receiver array are installed on the mounting structure where the camera bracket is located, and after the picture calibration, the image data captured by the camera is collected as the comparative image data analyzed by the machine vision analysis module.

[0056] When the application is in operation, the monitoring image data of the energy production equipment are acquired by the vision perception unit, the operation data and environment data of the energy production equipment are acquired by the Internet of Things sensing unit, then the image data and the infrared data of the vision unit self-checking module are uploaded to the pre-screening module for image offset analysis and grading marking, the image data after grading marking are uploaded to the machine vision analysis module for analysis, the analyzed data of the machine vision analysis module and the data acquired by the Internet of Things sensing unit are uploaded to the collaborative analysis module for collaborative analysis, and finally the results analyzed by the collaborative analysis module are issued to the application layer for user use.

[0057] The above merely describes preferred embodiments of the present application, but is not intended to limit the present application to other forms, any person skilled in the art can make changes or modifications to the above disclosed technical contents into equivalent embodiments with equivalent changes, and apply to other fields, but any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present application without departing from the technical solution content of the present application still belongs to the protection scope of the present application technical solution.

Claims

1. An energy supply chain management system based on the combination of machine vision perception and energy production and consumption relationship, characterized in that: The sensing layer obtains data which is uploaded to the platform layer through the network layer, and the platform layer analyzes and sends the analysis result to the application layer; The sensing layer includes a visual sensing unit for monitoring energy production equipment, a visual unit self-checking module for monitoring the visual sensing unit, and an Internet of Things sensing unit for energy production data; The network layer is used to transmit image data collected by the sensing layer, data of the visual unit self-checking module, and energy production data to the platform layer; The platform layer includes a data pool for storing data, a machine vision analysis module for analyzing image data, a pre-screening module for judging image quality, and a collaborative analysis module for comprehensive analysis of sensing layer data; After the pre-screening module obtains image data of the visual sensing unit and infrared sensing data of the visual unit self-checking module, it calculates the laser path according to the point data of the side laser receiver array and the point data of the bottom laser receiver array in the visual unit self-checking module, calculates the orientation angle change of the laser emitter, calculates the specific offset data of the image data according to the orientation angle change data of the laser emitter, and performs three-level marking on the image data according to the preset offset threshold: first-level for image data with an offset degree less than or equal to 3%, second-level for image data with an offset degree greater than 3% but less than or equal to 5%, and third-level for image data with an offset degree greater than 5%; The specific logic of the offset data calculation of the pre-screening module is as follows: First, the pre-screening module reads the spot coordinates of the side laser receiver array and the bottom laser receiver array, then the pre-screening module calculates the horizontal deflection angle according to the spot coordinate data of the side laser receiver array, and calculates the pitch angle according to the spot coordinate data of the bottom laser receiver array, takes the calculation result of the horizontal deflection angle as the horizontal resolution calculation parameter of the image, takes the calculation result of the pitch angle as the vertical resolution calculation parameter of the image, respectively calculates the expected offset pixel value of the image center point in the horizontal and vertical directions, and then calculates the modulus of the overall offset degree to obtain the percentage of the offset vector relative to the diagonal line size of the entire image; The machine vision analysis module receives image data screened by the pre-screening module, according to the offset marking of the pre-screening module on the image data, performs regular image preprocessing on the first-level marked image, performs image correction and angle correction preprocessing according to the offset data on the second-level marked image, and performs time axis marking on the third-level marked image and sends it to the data pool for processing, then selects the corresponding comparison image according to the camera number corresponding to the image data, compares the image data with the comparison image, and outputs the result to the data pool and the collaborative analysis module; The cooperative analysis module receives the image data analyzed by the machine vision analysis module and the sensing data of the Internet of Things sensing unit, then performs data cleaning and space-time alignment on the analyzed image data and the sensing data, and then performs association, matching and feature extraction on the analyzed image data and the sensing data according to a preset logic, and then performs cooperative reasoning and predictive analysis based on a preset rule, and generates a prediction report of the predictive analysis and sends the prediction report to the application layer.

2. The energy supply chain management system based on the combination of machine vision perception and energy production and sales relationship according to claim 1, characterized in that: The visual unit self-checking module includes a laser emitter installed on the camera and a cylindrical laser receiver installed on the camera mounting structure, the cylindrical laser receiver includes a bottom laser receiver array, the side of the bottom laser receiver array is provided with a side laser receiver array, the axis of the bottom laser receiver array overlaps with the axis of the side laser receiver array, the side of the bottom laser receiver array close to the side laser receiver array is provided with a laser reflection surface, the infrared laser emitted by the laser emitter is refracted and reflected by the laser reflection surface, part of the laser reflected by the laser reflection surface is shot to the side laser receiver array, and part of the laser refracted by the laser reflection surface is shot to the bottom laser receiver array. 3.The energy supply chain management system based on machine vision perception and energy production and sales relationship combination of claim 1, wherein: The camera of the visual sensing unit of the sensing unit and the bottom laser receiver array and the side laser receiver array of the visual unit self-checking module are grouped and numbered when the system is constructed, each group of the visual sensing unit and the visual unit self-checking module is provided with a number. 4.The energy supply chain management system based on machine vision perception and energy production and sales relationship combination of claim 1, wherein: When the visual sensing unit and the visual unit self-checking module are installed, comparative image acquisition is performed, and the acquired comparative images are uploaded to a data pool for storage. 5.The energy supply chain management system based on machine vision perception and energy production and sales relationship combination of claim 1, wherein: The application layer provides an interactive interface for users.

Images