A low-carbon index intelligent scoring and weight configuration system for VOC auto repair enterprises

Abstract

This invention relates to the field of low-carbon technology for auto repair enterprises. Specifically, it relates to an intelligent scoring and weighting system for low-carbon VOC indicators in auto repair enterprises. The system includes a data acquisition module, a scoring video segmentation module, an operational deviation module, an energy consumption deviation module, and a low-carbon scoring module. The data acquisition module acquires video data from the paint booth of the auto repair enterprise, and simultaneously acquires real-time data on paint raw materials, exhaust emissions, and energy consumption. By constructing a collaborative operation system of five modules—data acquisition, scoring video segmentation, operational deviation, energy consumption deviation, and low-carbon scoring—the system achieves the fusion and acquisition of multi-source data for the painting process in auto repair enterprises, refined breakdown of single-vehicle operations, quantitative evaluation of process operations, scientific setting of low-carbon thresholds, and dynamic intelligent scoring and weighting. This system addresses the multi-dimensional deficiencies of existing technologies at the system level, significantly improving the accuracy of VOC emission reduction and low-carbon energy-saving management in the painting process.

Description

Technical Field

[0001] This invention relates to the field of campervan navigation technology, and more specifically, to a VOC vehicle repair enterprise low-carbon index intelligent scoring and weighting system. Background Technology

[0002] Against the backdrop of increasingly stringent green development and environmental regulations in the auto repair industry, VOC emission reduction and low-carbon energy-saving control technologies for the painting process play a core role in monitoring, evaluating, and controlling the environmental protection and energy consumption data of the painting process in auto repair enterprises. The aim is to standardize painting operations, reduce fugitive VOC emissions and production energy consumption, and ultimately achieve green and low-carbon operation of the painting process in auto repair enterprises.

[0003] Existing VOC and low-carbon control technologies for the painting process in the automotive repair industry are mostly applied to single-data monitoring at the enterprise level, post-event compliance verification at the regulatory level, and general low-carbon indicator evaluation at the industry level. However, they have many intractable shortcomings, as follows: Firstly, existing technologies mostly involve single-dimensional data collection and monitoring, which cannot achieve the integrated collection and coordinated analysis of multi-source data such as video footage, paint raw materials, exhaust emissions, and energy consumption. This lack of visualization and data support for the entire painting process results in a lack of objectivity and comprehensiveness in low-carbon assessments. Secondly, existing low-carbon evaluation methods mostly rely on manual statistics and static index scoring, which cannot be finely broken down and evaluated based on the actual working conditions of a single vehicle painting operation. They are easily affected by invalid work data such as paint booth idling and standby, and the evaluation results cannot accurately reflect the true low-carbon management level of a single vehicle painting operation. Third, existing technologies have not established a dynamic weight configuration mechanism adapted to the painting process nodes. The weight settings are rigid and lack incentives. They cannot be adaptively adjusted according to the compliance of the operation and the compliance of energy consumption and emissions. It is difficult to form a positive incentive for standardized, efficient, and low-carbon operations, and it is also impossible to accurately identify and mark the operation nodes that exceed the standards. To solve the above problems, a VOC automotive repair enterprise low-carbon index intelligent scoring and weight configuration system is proposed. Summary of the Invention

[0004] The purpose of this invention is to provide an intelligent scoring and weighting system for low-carbon indicators of VOC auto repair enterprises, so as to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, a smart scoring and weighting system for low-carbon indicators of VOC auto repair enterprises is provided, including a data acquisition module, a scoring video segmentation module, an operation deviation module, an energy consumption deviation module, and a low-carbon scoring module. The data acquisition module is used to acquire video data from the paint booth of the auto repair company, and at the same time acquire paint raw material data, exhaust emission data, and energy consumption data in real time. The scoring video segmentation module is used to segment the vehicle's entry and exit as the segmentation target. It captures the start frame of the vehicle entering the paint booth and the end frame of the vehicle leaving the paint booth through AI visual recognition, and segments the video data into multiple independent scoring videos. Based on the scoring videos, the paint area and paint process of the vehicle are analyzed to obtain the paint area and paint process of the vehicle corresponding to each scoring video. The operation deviation module is used to analyze the process nodes based on the painting process in the scoring video, and set the standard process for each process node in combination with the painting area. At the same time, it analyzes the operation deviation value between the standard process and the painting process of the corresponding process node to obtain the operation deviation value corresponding to each process node. The energy consumption deviation module is used to set standard low-carbon thresholds for each process node by combining the paint raw material data with the paint area and standard process. At the same time, it configures operation weights and energy consumption weights for scoring, and compares the exhaust gas emission data and energy consumption data corresponding to the process node with the standard low-carbon thresholds to obtain the energy consumption deviation value. The low-carbon scoring module is used to adjust the operation weights based on the energy consumption deviation value. When the energy consumption deviation value is negative, the operation weight of the corresponding process node is increased synchronously according to the operation deviation value. Then, based on the weighted fusion algorithm, the energy consumption deviation value, operation deviation value, dynamically adjusted operation weight and energy consumption weight of each process node are combined to carry out multi-dimensional scoring and total score calculation, so as to obtain the comprehensive low-carbon score of the entire painting process of a single vehicle in the scoring video, and complete the low-carbon evaluation report for auto repair companies.

[0006] As a further improvement to this technical solution, the data acquisition module deploys a full-coverage monitoring device in the paint booth of the auto repair enterprise to collect real-time video data in the paint booth, covering the entire process of vehicle entry, painting operation, drying and exit, with no blind spots. Simultaneously, it acquires real-time data on paint raw materials, exhaust emissions, and energy consumption.

[0007] As a further improvement to this technical solution, the scoring video segmentation module uses the vehicle's entry and exit as the segmentation target, employs an AI visual recognition algorithm to identify the vehicle's outline and entry and exit actions, takes the vehicle's entry as the starting point of the scoring video and the vehicle's exit as the ending point of the scoring video, and repeats the operation to segment multiple independent scoring videos from the video data, thereby eliminating video segments of paint booth idling, no operation standby, and invalid equipment debugging from the video data; Each segmented scoring video corresponds to only one complete painting cycle for a single vehicle; Then, based on the scoring video, the paint area and painting process of the vehicle are identified, and the paint area and painting process of the vehicle corresponding to each scoring video are obtained.

[0008] As a further improvement to this technical solution, the operation deviation module performs process node analysis based on the painting process of the scoring video, establishes a process database, identifies the painting process of the scoring video with the process database, obtains the process nodes of the process database corresponding to the painting process, and thus breaks down the complete painting process of the scoring video into independent and coherent operation nodes. Based on the painting area corresponding to the scoring video, and combined with the process database, a standardized process template adapted to single-vehicle operation is formed for the process nodes contained in the scoring video, that is, a standard process is set for each process node. Each process node corresponds to separate exhaust gas emission data, energy consumption data, painting process, and standard process.

[0009] As a further improvement to this technical solution, in the operation deviation module, for the process nodes of the same scoring video, the operation deviation value of the painting process and the standard process is calculated. The process sequence, operation time and operation actions of the painting process are compared with the standard process one by one, and the difference between the two is quantitatively calculated to obtain the operation deviation value corresponding to the process node. The more similar the painting process is to the standard process, the smaller the operational deviation value, which indicates that the operation is more standardized; Conversely, the more dissimilar the painting process is to the standard process, the greater the operational deviation value, indicating that the operation deviates more from the standard.

[0010] As a further improvement to this technical solution, the energy consumption deviation module combines the paint raw material data with the paint area and standard process to set a standard low-carbon threshold for each process node. Based on the environmental attributes of the paint raw material data, the paint area, and the standard process, the optimal energy consumption limit and VOC emission limit allowed for each process node are calculated, and the optimal energy consumption limit and VOC emission limit are summarized as the standard low-carbon threshold. Based on process importance and low-carbon management priority, operation weights and energy consumption weights are initially configured for each process node.

[0011] As a further improvement to this technical solution, the energy consumption deviation module compares the exhaust gas emission data and energy consumption data corresponding to each process node with the standard low-carbon threshold dimension by dimension to obtain the energy consumption deviation value and VOC emission deviation value of each node. Then, the node energy consumption deviation value and VOC emission deviation value are summarized as the energy consumption deviation value between the process node and the standard low-carbon threshold. When the energy consumption deviation value is negative, it means that the exhaust emission data and energy consumption data are lower than the standard low carbon threshold. When the energy consumption deviation value is positive, it means that the exhaust emission data and energy consumption data are higher than the standard low-carbon threshold.

[0012] As a further improvement to this technical solution, the low-carbon scoring module adaptively adjusts the operation weights according to the positive or negative amplitude of the energy consumption deviation value. When the energy consumption deviation value is negative, the operation is judged to be compliant and efficient, and the operation weight of the corresponding process node is increased synchronously according to the operation deviation value. When the energy consumption deviation value is positive, the corresponding weight is reduced and the abnormal node is marked. Based on the weighted fusion algorithm, the energy consumption deviation value, operation deviation value, and dynamically adjusted operation weight and energy consumption weight of each process node are combined to carry out multi-dimensional scoring and total score calculation, obtain the low carbon score of each process node, and then summarize the low carbon score of each process node according to the process node corresponding to the scoring video to obtain the low carbon score of each vehicle corresponding to the scoring video. Based on the low carbon score of each vehicle, the comprehensive low carbon score of the entire painting process of a single vehicle is obtained. By summarizing comprehensive low-carbon scores from multiple vehicle trips and cycles, a special low-carbon evaluation report on the painting process of auto repair enterprises is generated.

[0013] Compared with the prior art, the beneficial effects of the present invention are as follows: 1. This intelligent scoring and weighting system for low-carbon indicators in VOC automotive repair enterprises constructs a collaborative operation system of five modules: data acquisition, scoring video segmentation, operational deviation, energy consumption deviation, and low-carbon scoring. This system enables the fusion and collection of multi-source data for the painting process in automotive repair enterprises, the refined breakdown of single-vehicle operations, the quantitative evaluation of process operations, the scientific setting of low-carbon thresholds, and dynamic intelligent scoring and weighting. It solves the multi-dimensional defects of existing technologies at the system level and significantly improves the accuracy, intelligence, and effectiveness of VOC emission reduction and low-carbon energy-saving management in the painting process.

[0014] 2. This intelligent scoring and weighting system for low-carbon indicators in VOC auto repair enterprises utilizes a comprehensive monitoring device deployed in the paint booth. Combined with radio frequency identification, online monitoring sensors, and intelligent metering instruments, it achieves real-time, integrated collection of video data, paint raw material data, exhaust emission data, and energy consumption data throughout the entire process. Furthermore, it adds a unified timestamp to all data to achieve precise linkage. This not only provides comprehensive and reliable raw data support for low-carbon scoring but also enables visualized traceability of the entire painting process. It effectively compensates for the shortcomings of existing single-dimensional data collection technologies, making the low-carbon evaluation results more objective and comprehensive.

[0015] 3. This intelligent scoring and weighting system for low-carbon indicators in VOC auto repair enterprises relies on AI visual recognition algorithms to intelligently segment video data from paint booths. It accurately captures start and end frames based on vehicle entry and exit, automatically eliminating invalid video segments such as those showing idling or standby, ensuring that each scoring video corresponds only to a single vehicle's complete painting cycle. Simultaneously, it achieves precise acquisition of the painting area and process of a single vehicle through pixel analysis and process feature recognition. This represents a technological breakthrough from overall workshop evaluation to refined evaluation of individual vehicles, effectively avoiding interference from invalid data and allowing low-carbon scoring to accurately reflect the actual working conditions of a single vehicle's painting, significantly improving the precision of low-carbon evaluation. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the structure of a VOC automotive repair enterprise low-carbon index intelligent scoring and weight configuration system according to the present invention; Figure 2 This is a flowchart illustrating the data acquisition module of the present invention; Figure 3 This is a flowchart illustrating the scoring video segmentation module of the present invention; Figure 4 This is a flowchart illustrating the operation deviation module of the present invention; Figure 5 This is a flowchart illustrating the energy consumption deviation module of the present invention; Figure 6 This is a flowchart illustrating the low-carbon scoring module of the present invention. Detailed Implementation

[0017] 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.

[0018] Please see Figures 1-6 As shown, the purpose of this embodiment is to provide an intelligent scoring and weighting system for low-carbon indicators of VOC auto repair enterprises, including a data acquisition module, a scoring video segmentation module, an operation deviation module, an energy consumption deviation module, and a low-carbon scoring module. The data acquisition module is used to acquire video data from the paint booth of auto repair shops, and at the same time acquire real-time data on paint raw materials, exhaust emissions, and energy consumption; the data input terminal of the entire system is responsible for building a multi-source heterogeneous data acquisition system, providing original, complete, and reliable data support for all subsequent modules; In the data acquisition module, a full-coverage monitoring device is deployed in the paint booth of the auto repair company to collect real-time video data in the paint booth, covering the entire process of vehicle entry, painting operation, drying and exit, with no blind spots. Wide-angle surveillance cameras are installed at the four corners of the top of the spray booth and at high positions on the side walls. The angle and focus are adjusted to form full coverage without blind spots. All monitoring devices are connected to a unified network to achieve real-time uploading of video data, start continuous real-time acquisition, and fully capture the entire process of vehicle entry, spraying operation, drying operation and vehicle exit. A unique timestamp is added to the video data. Simultaneously, it acquires real-time data on paint raw materials, exhaust emissions, and energy consumption.

[0019] By connecting to the radio frequency identification or work order system, information such as paint type, actual paint consumption per vehicle, and environmental attributes of paint such as VOC content and solid content is obtained. The raw material data is then bound to the corresponding operating vehicle and a unified timestamp is attached. Online monitoring sensors are installed at the inlet and outlet of the waste gas treatment equipment to collect VOC concentration, non-methane total hydrocarbon concentration, waste gas emission flow rate and equipment operating status parameters in real time, and store them in time series with a unified timestamp attached. The total electricity consumption, gas heat consumption, and energy consumption of key equipment are collected by smart meters and gas meters. Energy consumption data is statistically analyzed according to the single vehicle operation cycle and linked with timestamps and vehicle information.

[0020] The scoring video segmentation module uses vehicle entry and exit as segmentation targets. It captures the start frame of a vehicle entering the paint booth and the end frame of a vehicle leaving the paint booth through AI visual recognition, segmenting the video data into multiple independent scoring videos. Based on the scoring videos, it analyzes the paint area and painting process of the vehicle to obtain the paint area and painting process corresponding to each scoring video. It achieves invalid data filtering and accurate segmentation of valid work segments, transforming continuous videos into independent samples that can be scored, and solving the problems of video data redundancy and sample confusion. In the video scoring module, the entry and exit of vehicles are used as the segmentation targets. AI visual recognition algorithms are used to identify the vehicle outline and the entry and exit actions. The entry of the vehicle is the starting point of the scoring video, and the exit of the vehicle is the ending point of the scoring video. The operation is repeated to segment multiple independent scoring videos from the video data, thereby eliminating video segments of paint booth idling, no operation standby, and invalid equipment debugging from the video data. The collected video data of the entire paint booth process is input into an AI visual recognition model. Using vehicle entry and exit from the paint booth as the core segmentation targets, the model identifies vehicle outline features through target detection algorithms and determines key action nodes for vehicle entry and exit using action recognition technology. The frame position of the vehicle entering the paint booth is marked as the starting point of the scoring video, and the frame position of the vehicle exiting the paint booth is marked as the ending point. This identification and marking operation is repeated to cut multiple independent scoring video segments from the continuous video data stream. During the cutting process, invalid video segments without vehicle operation, such as those showing the paint booth idling, idle, or undergoing equipment debugging, are automatically filtered out. This ensures that each segmented scoring video corresponds to only one vehicle's complete paint operation cycle from entry to exit. The formula is as follows: ; in, The confidence level for identifying vehicle entry / exit actions is set (a threshold of ≥95% is required for validity). The number of frames that match the vehicle motion features. The total number of frames within the window to be identified; Each segmented scoring video corresponds to only one complete painting cycle for a single vehicle; Then, based on the scoring video, the paint area and painting process of the vehicle are identified, and the paint area and painting process of the vehicle corresponding to each scoring video are obtained.

[0021] Based on the segmented scoring videos, a combination of pixel analysis and size calibration is used to extract contours, divide regions, and calculate areas for the painted parts of vehicles in the videos, accurately identifying the paint area of ​​a single vehicle. Simultaneously, a process feature recognition algorithm is used to analyze the painting operations, durations, and sequences in the videos, determining specific painting process types such as primer, intermediate coat, topcoat, leveling, and drying. Finally, the paint area and painting process parameters for each scored video are summarized and output, as shown in the following formula:

[0022] in, This represents the actual painted area of ​​the vehicle. The pixel area of ​​the painted area in the video. This is a conversion factor between pixels and actual size, in meters (m / pixel), derived from camera calibration. The operation deviation module is used to analyze the process nodes based on the painting process in the scoring video, and set the standard process for each process node in combination with the painting area. At the same time, it analyzes the operation deviation value between the standard process and the painting process of the corresponding process node to obtain the operation deviation value corresponding to each process node. Focusing on the standardization of painting operation, it transforms the qualitative process compliance into quantitative deviation value to achieve low-carbon control at the operation level. In the operation deviation module, the process nodes are analyzed based on the painting process in the scoring video, a process database is established, the painting process in the scoring video is matched with the process database for process identification, and the process nodes corresponding to the painting process in the process database are obtained, thereby breaking down the complete painting process in the scoring video into independent and coherent operation nodes. The system retrieves the painting process parameters corresponding to the scoring video, conducts in-depth analysis of the process nodes, and uses the system's built-in process database to match and identify the process. It accurately locates the corresponding node classification of the painting process in the database, breaks down the complete and coherent painting process into multiple independent and smoothly connected single operation nodes, and ensures that each process node can match the corresponding exclusive exhaust emission data, energy consumption data, and actual painting process parameters. Based on the painting area corresponding to the scoring video, and combined with the process database, a standardized process template adapted to single-vehicle operation is formed for the process nodes contained in the scoring video, that is, a standard process is set for each process node. By combining the paint area of ​​a single vehicle calculated from the scoring video, the standard parameters and benchmark processes in the process database are called up, and each process node is personalized and adapted to generate a standardized process template that is perfectly suited to the current single vehicle operation, thus completing the precise setting of the standard process for each node. Each process node corresponds to separate exhaust gas emission data, energy consumption data, painting process, and standard process.

[0023] In the operation deviation module, for process nodes with the same scoring video, the operation deviation value of the painting process is calculated by comparing it with the standard process. The process sequence, operation time, and operation actions of the painting process are compared with those of the standard process one by one, and the difference between the two is quantitatively calculated to obtain the operation deviation value corresponding to the process node. The formula is as follows: ; in, This represents the operational deviation value for a single process node. Weights are assigned to each comparison dimension (process sequence weight 0.4, operation time weight 0.3, operation action weight 0.3). These are the parameter values ​​for various dimensions of the actual process. These are the parameter values ​​for each dimension of the standard process; The more similar the painting process is to the standard process, the smaller the operational deviation value, which indicates that the operation is more standardized; Conversely, the more dissimilar the painting process is to the standard process, the greater the operational deviation value, indicating that the operation deviates more from the standard.

[0024] The energy consumption deviation module is used to set standard low-carbon thresholds for each process node by combining paint raw material data with paint area and standard process. At the same time, it configures operation weights and energy consumption weights for scoring. It compares the exhaust gas emission data and energy consumption data corresponding to the process node with the standard low-carbon thresholds to obtain the energy consumption deviation value. It is responsible for formulating scientific thresholds, configuring initial weights, and completing the comparison between actual energy consumption / emissions and standard values. It is the basis for dynamic weight adjustment. In the energy consumption deviation module, the paint raw material data is combined with the paint area and standard process to set standard low carbon thresholds for each process node. Based on the environmental attributes of the paint raw material data, the paint area, and the standard process, the optimal energy consumption limit and VOC emission limit allowed for each process node are calculated, and the optimal energy consumption limit and VOC emission limit are summarized as the standard low carbon threshold. First, retrieve the environmental attribute data such as VOC content, solid content, and paint type of the paint raw materials already collected by the system, as well as the painting area of ​​a single vehicle and the standard process parameters of each process node. Conduct detailed calculations for each process node, and determine the optimal energy consumption limit and VOC emission limit allowed for that node by combining industry low-carbon management standards and the actual production conditions of the enterprise. Integrate and summarize the two core limit values ​​as the standard low-carbon threshold exclusive to that process node, and ensure that each process node corresponds to a unique standard low-carbon threshold. Based on process importance and low-carbon management priority, operation weights and energy consumption weights are initially configured for each process node.

[0025] Subsequently, based on the importance of each process node in the entire painting process, the priority of low-carbon control, and the level of environmental risk, a differentiated initial weight configuration was carried out, and an operation weight and energy consumption weight were set separately for each process node to ensure that the weight configuration fits the actual control needs. In the energy consumption deviation module, the exhaust gas emission data and energy consumption data corresponding to each process node are compared with the standard low-carbon threshold dimension by dimension to obtain the energy consumption deviation value and VOC emission deviation value of each node. Then, the node energy consumption deviation value and VOC emission deviation value are summarized as the energy consumption deviation value between the process node and the standard low-carbon threshold. When the energy consumption deviation value is negative, it means that the exhaust emission data and energy consumption data are lower than the standard low carbon threshold. When the energy consumption deviation value is positive, it means that the exhaust emission data and energy consumption data are higher than the standard low-carbon threshold.

[0026] The low-carbon scoring module adjusts the operational weights based on energy consumption deviation values. When the energy consumption deviation value is negative, the operational weight of the corresponding process node is increased synchronously based on the operational deviation value. Then, based on a weighted fusion algorithm, combining the energy consumption deviation value, operational deviation value, dynamically adjusted operational weight, and energy consumption weight of each process node, multi-dimensional scoring and total score calculation are performed to obtain a comprehensive low-carbon score for the entire painting process of a single vehicle in the scoring video, thus generating a low-carbon evaluation report for auto repair companies. It achieves intelligent, fair, and incentivizing scoring by completing dynamic weight adjustment, weighted scoring, and report generation. In the low-carbon scoring module, the operation weights are adaptively adjusted based on the positive or negative magnitude of the energy consumption deviation value. When the energy consumption deviation value is negative, the operation is judged to be compliant and efficient, and the operation weight of the corresponding process node is increased synchronously according to the operation deviation value. When the energy consumption deviation value is positive, the corresponding weight is reduced and the abnormal node is marked. The total energy consumption deviation value of each process node is retrieved. First, the positive or negative attribute and magnitude of the deviation value are determined. Based on this, the initial operation weight is adaptively and dynamically fine-tuned. When the energy consumption deviation value is negative, the painting operation of that node is judged to be compliant and efficient. The operation weight of that process node is increased synchronously based on the magnitude of the corresponding operation deviation value. The smaller the operation deviation value, the greater the increase in weight, thus strengthening the positive contribution of standardized operation scoring. The formula is as follows: ; in, To dynamically adjust the weights of subsequent operations, As the initial operation weights, This is the weight adjustment coefficient (when the negative value meets the standard, λ>1, the weight is increased; when the positive value exceeds the standard, 0<λ<1, the weight is decreased). Based on the weighted fusion algorithm, the energy consumption deviation value, operation deviation value, and dynamically adjusted operation weight and energy consumption weight of each process node are combined to carry out multi-dimensional scoring and total score calculation, obtain the low carbon score of each process node, and then summarize the low carbon score of each process node according to the process node corresponding to the scoring video to obtain the low carbon score of each vehicle corresponding to the scoring video. Based on the low carbon score of each vehicle, the comprehensive low carbon score of the entire painting process of a single vehicle is obtained. By aggregating comprehensive low-carbon scores from multiple vehicle visits and periods, a specific low-carbon evaluation report for the painting process in auto repair shops is generated. This involves continuously collecting comprehensive low-carbon scores for individual vehicles across multiple periods (daily, weekly, and monthly), performing data statistics, averaging, and anomaly filtering, and ultimately generating a specific low-carbon evaluation report for the painting process in auto repair shops. This report includes the overall low-carbon score of the enterprise, a list of anomalies, analysis of reasons for deductions, and directions for rectification and optimization. The formula is as follows: ; in, The score for low carbon emissions at a single process node is based on a maximum score of 100. This represents the total energy consumption deviation value. Energy consumption weight (fixed initial value). This is the operational deviation value; ; in, The overall low-carbon score for a single bicycle, The score is the score for the i-th process node, and n is the total number of process nodes in the entire painting process for a single vehicle. ; in, A comprehensive low-carbon score for the enterprise's life cycle. Rate the j-th car individually. This is the total number of vehicles operating within the statistical period.

[0027] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely preferred examples and are not intended to limit the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of the present invention is defined by the appended claims and their equivalents.

Claims

1. A smart scoring and weighting system for low-carbon indicators in VOC-consuming auto repair enterprises, characterized in that: It includes a data acquisition module, a scoring video segmentation module, an operation deviation module, an energy consumption deviation module, and a low-carbon scoring module; The data acquisition module is used to acquire video data from the paint booth of the auto repair company, and at the same time acquire paint raw material data, exhaust emission data, and energy consumption data in real time. The scoring video segmentation module is used to segment the vehicle's entry and exit as the segmentation target. It captures the start frame of the vehicle entering the paint booth and the end frame of the vehicle leaving the paint booth through AI visual recognition, and segments the video data into multiple independent scoring videos. Based on the scoring videos, the paint area and paint process of the vehicle are analyzed to obtain the paint area and paint process of the vehicle corresponding to each scoring video. In the scoring video segmentation module, the entry and exit of vehicles are used as segmentation targets. AI visual recognition algorithms are used to identify the vehicle outline and entry and exit actions. The entry of the vehicle is the starting point of the scoring video, and the exit of the vehicle is the ending point of the scoring video. The operation is repeated to segment multiple independent scoring videos from the video data, thereby eliminating invalid video segments from the video data, such as those of the paint booth idling, not working, or undergoing equipment debugging. Each segmented scoring video corresponds to only one complete painting operation cycle for a single vehicle; Then, based on the scoring video, the paint area and painting process of the vehicle are identified, and the paint area and painting process of the vehicle corresponding to each scoring video are obtained. The operation deviation module is used to analyze the process nodes based on the painting process in the scoring video, and set the standard process for each process node in combination with the painting area. At the same time, it analyzes the operation deviation value between the standard process and the painting process of the corresponding process node to obtain the operation deviation value corresponding to each process node. The energy consumption deviation module is used to set standard low-carbon thresholds for each process node by combining the paint raw material data with the paint area and standard process. At the same time, it assigns operation weights and energy consumption weights to each process node and compares the exhaust gas emission data and energy consumption data corresponding to the process node with the standard low-carbon thresholds to obtain the energy consumption deviation value. The low-carbon scoring module is used to adjust the operation weights based on the energy consumption deviation value. When the energy consumption deviation value is negative, the operation weight of the corresponding process node is increased synchronously according to the operation deviation value. Then, based on the weighted fusion algorithm, the energy consumption deviation value, operation deviation value, dynamically adjusted operation weight and energy consumption weight of each process node are combined to carry out multi-dimensional scoring and total score calculation, so as to obtain the comprehensive low-carbon score of the entire painting process of a single vehicle in the scoring video, and complete the low-carbon evaluation report for auto repair companies.

2. The intelligent scoring and weighting system for low-carbon indicators of VOC auto repair enterprises according to claim 1, characterized in that: The data acquisition module deploys a full-coverage monitoring device in the paint booth of the auto repair shop to collect real-time video data in the paint booth, covering the entire process of vehicle entry, painting, drying and exit, with no blind spots. Simultaneously, it acquires real-time data on paint raw materials, exhaust emissions, and energy consumption.

3. The intelligent scoring and weighting system for low-carbon indicators of VOC auto repair enterprises according to claim 1, characterized in that: In the operation deviation module, the process nodes are analyzed based on the painting process of the scoring video, a process database is established, the painting process of the scoring video is matched with the process database for process identification, and the process nodes of the painting process corresponding to the process database are obtained, thereby breaking down the complete painting process of the scoring video into independent and coherent operation nodes. Based on the painting area corresponding to the scoring video, and combined with the process database, a standardized process template adapted to single-vehicle operation is formed for the process nodes contained in the scoring video, that is, a standard process is set for each process node. Each process node corresponds to separate exhaust gas emission data, energy consumption data, painting process, and standard process.

4. The intelligent scoring and weighting system for low-carbon indicators of VOC auto repair enterprises according to claim 1, characterized in that: In the operation deviation module, for the process nodes of the same scoring video, the operation deviation value of the painting process and the standard process is calculated. The process sequence, operation time and operation actions of the painting process are compared with the standard process one by one, and the difference between the two is quantitatively calculated to obtain the operation deviation value corresponding to the process node. The more similar the painting process is to the standard process, the smaller the operational deviation value, which indicates that the operation is more standardized; Conversely, the more dissimilar the painting process is to the standard process, the greater the operational deviation value, indicating that the operation deviates more from the standard.

5. The intelligent scoring and weighting system for low-carbon indicators of VOC auto repair enterprises according to claim 1, characterized in that: In the energy consumption deviation module, the paint raw material data is combined with the paint area and standard process to set standard low-carbon thresholds for each process node. Based on the environmental attributes of the paint raw material data, the paint area, and the standard process, the optimal energy consumption limit and VOC emission limit allowed for each process node are calculated, and the optimal energy consumption limit and VOC emission limit are summarized as the standard low-carbon threshold. Based on process importance and low-carbon management priority, operation weights and energy consumption weights are initially configured for each process node.

6. The intelligent scoring and weighting system for low-carbon indicators of VOC auto repair enterprises according to claim 1, characterized in that: In the energy consumption deviation module, the exhaust gas emission data and energy consumption data corresponding to each process node are compared with the standard low-carbon threshold dimension by dimension to obtain the energy consumption deviation value and VOC emission deviation value of each node. Then, the node energy consumption deviation value and VOC emission deviation value are summarized as the energy consumption deviation value between the process node and the standard low-carbon threshold. When the energy consumption deviation value is negative, it means that the exhaust emission data and energy consumption data are lower than the standard low carbon threshold. When the energy consumption deviation value is positive, it means that the exhaust emission data and energy consumption data are higher than the standard low-carbon threshold.

7. The intelligent scoring and weighting system for low-carbon indicators of VOC auto repair enterprises according to claim 1, characterized in that: In the low-carbon scoring module, the operation weight is adaptively adjusted according to the positive or negative magnitude of the energy consumption deviation value. When the energy consumption deviation value is negative, the operation is judged to be compliant and efficient, and the operation weight of the corresponding process node is increased synchronously according to the operation deviation value. When the energy consumption deviation value is positive, the corresponding weight is reduced and the abnormal node is marked. Based on the weighted fusion algorithm, the energy consumption deviation value, operation deviation value, and dynamically adjusted operation weight and energy consumption weight of each process node are combined to carry out multi-dimensional scoring and total score calculation, obtain the low carbon score of each process node, and then summarize the low carbon score of each process node according to the process node corresponding to the scoring video to obtain the low carbon score of each vehicle corresponding to the scoring video. Based on the low carbon score of each vehicle, the comprehensive low carbon score of the entire painting process of a single vehicle is obtained. By summarizing the comprehensive low-carbon scores from multiple vehicle trips and cycles, a special low-carbon evaluation report on the painting process of auto repair enterprises is generated.

Images