An intelligent evaluation method and system for particle attachment characteristics inside oil fume ducts

Abstract

The present invention relates to the technical field of particle attachment intelligent evaluation, and in particular to a method and system for intelligent evaluation of particle attachment characteristics inside a fume duct. The method comprises the following steps: installing a high-resolution particle monitor and a humidity sensor inside the fume duct and performing real-time monitoring of particle distribution images and duct humidity to obtain real-time image data of particle distribution inside the fume duct and real-time data of humidity inside the fume duct; performing image standardization processing and particle distribution area division on the real-time image data of particle distribution inside the fume duct, and performing particle attachment distribution density analysis and future attachment distribution prediction analysis, while performing particle attachment health evaluation calculation inside the fume duct, performing health intelligent early warning and cleaning suggestion analysis, generating a healthy cleaning suggestion plan for particle attachment inside the fume duct, and performing corresponding particle cleaning work inside the fume duct. The present invention can improve the particle attachment cleaning efficiency of the fume duct.

Description

Technical Field

[0001] The present invention relates to the technical field of particle attachment intelligent evaluation, and in particular to a method and system for intelligently evaluating particle attachment characteristics inside a fume duct. Background Art

[0002] In the kitchen fume exhaust system, the internal particle adhesion problem of the fume duct is a key factor affecting the efficiency and safety of the system. In long-term operation, the particles in the fume will be deposited on the inner wall of the duct, causing the duct to be blocked, the exhaust effect to be reduced, and the risk of fire to be increased. By installing a high-resolution camera or endoscope inside the fume duct and collecting image data inside the duct in real time, the image acquisition system can capture the detailed information of particle adhesion and provide intuitive data for subsequent analysis. In addition, by using computer vision and deep learning technology to process and analyze the collected images, the intelligent algorithm can identify and quantify the area, density and distribution of particle adhesion through image segmentation, feature extraction and pattern recognition. At the same time, by combining the image processing results with sensor data (such as airflow, temperature, humidity, etc.) for comprehensive analysis, it can provide a more comprehensive evaluation of particle adhesion characteristics, including adhesion layer thickness, particle type and deposition trend. Based on the evaluation results of particle adhesion characteristics, optimized maintenance and cleaning suggestions can be provided, including cleaning cycles, cleaning methods and pipeline adjustment plans to ensure the long-term stable operation of the fume duct. However, traditional particle adhesion evaluation methods inside oil fume ducts usually rely on manual inspection and regular cleaning, which is not only time-consuming and prone to missing particle adhesion inside the oil fume duct, but also has problems such as incomplete monitoring of particle adhesion characteristics and inaccurate data. Summary of the invention

[0003] Based on this, it is necessary for the present invention to provide a method and system for intelligently evaluating the particle adhesion characteristics inside a fume duct to solve at least one of the above-mentioned technical problems.

[0004] To achieve the above object, a method for intelligently evaluating particle adhesion characteristics inside a fume duct is provided, comprising the following steps:

[0005] Step S1: installing a high-resolution particle monitor and a humidity sensor inside the oil fume duct, and using the high-resolution particle monitor and the humidity sensor to perform real-time monitoring of the particle distribution image and the humidity of the duct inside the oil fume duct, thereby obtaining real-time image data of the particle distribution inside the oil fume duct and real-time data of the humidity inside the oil fume duct; performing image standardization processing on the real-time image data of the particle distribution inside the oil fume duct, thereby obtaining standard image data of the particle distribution inside the oil fume duct;

[0006] Step S2: dividing the particle distribution area of ​​the standard image data of the particle distribution inside the oil fume duct to obtain the particle attachment distribution area inside the oil fume duct and the particle suspension distribution area inside the oil fume duct; performing particle attachment distribution density analysis on the particle attachment distribution area inside the oil fume duct to obtain the particle attachment area distribution density inside the oil fume duct;

[0007] Step S3: performing time series synchronization processing on the suspended distribution area of ​​particles inside the oil fume duct and the real-time data of humidity inside the oil fume duct to obtain the suspended distribution change area of ​​particles inside the oil fume duct and the humidity change data inside the oil fume duct in the same time series dimension; based on the humidity change data inside the oil fume duct in the same time series dimension, performing future attachment distribution prediction analysis on the suspended particles inside the oil fume duct corresponding to the suspended distribution change area of ​​particles inside the oil fume duct, and obtaining the future attachment distribution position of the suspended particles inside the oil fume duct;

[0008] Step S4: Based on the distribution density of the particle attachment area inside the oil fume duct and the future attachment distribution position of the suspended particles inside the oil fume duct, a particle attachment health evaluation calculation is performed on the inside of the oil fume duct to obtain a particle attachment health status score value inside the oil fume duct; based on the particle attachment health status score value inside the oil fume duct, a health intelligent early warning and cleaning suggestion analysis is performed on the inside of the oil fume duct, and a healthy cleaning suggestion plan for particle attachment inside the oil fume duct is generated to perform corresponding particle cleaning work inside the oil fume duct.

[0009] Further, step S1 includes the following steps:

[0010] Step S11: installing a high-resolution particle monitor and a humidity sensor inside the oil fume duct, and using the high-resolution particle monitor to monitor the particle distribution image inside the oil fume duct in real time, thereby obtaining real-time image data of the particle distribution inside the oil fume duct;

[0011] Step S12: using a humidity sensor to monitor the humidity inside the oil fume duct in real time, and obtaining real-time humidity data inside the oil fume duct;

[0012] Step S13: performing image denoising processing on the real-time image data of the particle distribution inside the oil fume duct to obtain denoised image data of the particle distribution inside the oil fume duct;

[0013] Step S14: performing image contrast enhancement processing on the denoised image data of the particle distribution inside the oil fume duct to obtain contrast enhanced image data of the particle distribution inside the oil fume duct;

[0014] Step S15: performing image standardization processing on the image contrast enhancement data of the particle distribution inside the oil fume duct to obtain standard image data of the particle distribution inside the oil fume duct.

[0015] Further, step S2 includes the following steps:

[0016] Step S21: performing spatial position positioning processing on each particle in the standard image data of particle distribution inside the oil fume duct to obtain the spatial position distribution coordinates of each particle inside the oil fume duct;

[0017] Step S22: performing 3D corner point extraction processing on the inner wall of the oil fume duct on the standard image data of particle distribution inside the oil fume duct to obtain a set of spatially distributed corner points of the inner wall of the oil fume duct in a 3D state;

[0018] Step S23: performing three-dimensional spatial reconstruction processing on the standard image data of particle distribution inside the oil fume duct based on the spatial position distribution coordinates of each particle inside the oil fume duct and the spatial distribution corner point set of the inner wall of the oil fume duct in a 3D state, so as to generate a three-dimensional reconstructed spatial model of particle distribution inside the oil fume duct;

[0019] Step S24: dividing the particle distribution area of ​​the three-dimensional reconstructed spatial model of the particle distribution inside the oil fume duct based on the spatial position distribution coordinates of each particle inside the oil fume duct to obtain the particle attachment distribution area inside the oil fume duct and the particle suspension distribution area inside the oil fume duct;

[0020] Step S25: performing particle attachment distribution density analysis on the particle attachment distribution area inside the oil fume duct to obtain the particle attachment area distribution density inside the oil fume duct.

[0021] Further, step S24 includes the following steps:

[0022] Step S241: performing particle vertical point matching mapping on the inner wall of the oil fume duct in the three-dimensional reconstructed spatial model of particle distribution inside the oil fume duct based on the spatial position distribution coordinates of each particle inside the oil fume duct, so as to obtain the inner wall vertical matching point distribution coordinates corresponding to each particle inside the oil fume duct;

[0023] Step S242: performing quantitative calculation of the distance between each particle and the inner wall for the spatial position distribution coordinates of each particle inside the oil fume duct and the inner wall vertical matching point distribution coordinates corresponding to each particle inside the oil fume duct, so as to obtain the spatial distribution distance value between each particle inside the oil fume duct and the inner wall of the oil fume duct;

[0024] Step S243: comparing and judging the spatial distribution distance value between each particle inside the oil fume duct and the inner wall of the oil fume duct according to the preset oil fume duct internal particle attachment distance threshold, when the spatial distribution distance value is less than or equal to the preset oil fume duct internal particle attachment distance threshold, the corresponding particle in the three-dimensional reconstruction space model of the oil fume duct internal particle distribution is determined as the oil fume duct internal particle attachment particle point; when the spatial distribution distance value is greater than the preset oil fume duct internal particle attachment distance threshold, the corresponding particle in the three-dimensional reconstruction space model of the oil fume duct internal particle distribution is determined as the oil fume duct suspended particle point;

[0025] Step S244: connecting and dividing the attachment distribution area of ​​each particle corresponding to the three-dimensional reconstructed spatial model of particle distribution inside the oil fume duct based on the particle attachment point of the oil fume duct, so as to obtain the particle attachment distribution area inside the oil fume duct;

[0026] Step S245: based on the suspended particle points of the oil fume duct, the suspended distribution area of ​​each particle corresponding to the three-dimensional reconstructed spatial model of particle distribution inside the oil fume duct is connected and divided to obtain the suspended distribution area of ​​particles inside the oil fume duct.

[0027] Further, step S25 includes the following steps:

[0028] Step S251: performing a statistical analysis on the number of particles attached to the distribution area of ​​particles inside the oil fume duct to obtain the number of particles attached to the distribution area inside the oil fume duct;

[0029] Step S252: performing particle contour shape recognition analysis on the particle attachment distribution area inside the oil fume duct to obtain the particle attachment contour shape size in the distribution area inside the oil fume duct;

[0030] Step S253: based on the number of particles attached in the distribution area inside the oil fume duct and the size of the particle attachment contour in the distribution area inside the oil fume duct, the particle attachment area corresponding to each particle in the particle attachment distribution area inside the oil fume duct is calculated to obtain the total particle attachment area size in the area inside the oil fume duct;

[0031] Step S254: performing particle attachment distribution density analysis on the particle attachment distribution area inside the oil fume duct based on the total particle attachment area size inside the oil fume duct to obtain the particle attachment area distribution density inside the oil fume duct.

[0032] Further, step S3 includes the following steps:

[0033] Step S31: performing time series synchronization processing on the corresponding particle suspension distribution change in the particle suspension distribution area inside the oil fume duct and the real-time data of the humidity inside the oil fume duct, so as to obtain the particle suspension distribution change area inside the oil fume duct and the humidity change data inside the oil fume duct in the same time series dimension;

[0034] Step S32: performing a particle distribution change flow field simulation analysis on the particle suspension distribution change region inside the oil fume duct in the same time series dimension to obtain a particle suspension distribution change flow simulation field inside the oil fume duct;

[0035] Step S33: Based on the humidity change data inside the oil fume duct in the same time series dimension, a humidity change dynamic impact assessment analysis is performed on the particle suspended distribution change flow simulation field inside the oil fume duct to obtain the dynamic change impact relationship between the humidity change inside the oil fume duct and the particle suspended distribution flow;

[0036] Step S34: Based on the dynamic change influence relationship between the humidity change inside the oil fume duct and the particle suspended distribution flow, the future attachment distribution prediction analysis of the suspended particles inside the oil fume duct corresponding to the suspended distribution change area of ​​the particles inside the oil fume duct is performed to obtain the future attachment distribution position of the suspended particles inside the oil fume duct.

[0037] Further, step S33 includes the following steps:

[0038] The humidity change data inside the oil fume duct under the same time series dimension is subjected to dynamic time series change decomposition processing to obtain the dynamic change sub-data of the humidity inside the oil fume duct in different time series change segments;

[0039] Based on the dynamic change sub-data of humidity inside the oil fume duct at different time-series change segments, the dynamic coupling analysis of humidity change on the flow simulation field of particle suspension distribution change inside the oil fume duct is carried out to obtain the dynamic coupling distribution field between humidity change inside the oil fume duct and particle suspension flow;

[0040] The dynamic coupling distribution field between the humidity change inside the oil fume duct and the suspended particle flow is analyzed to determine the influence range of the spatial coupling effect between the humidity change inside the oil fume duct and the suspended particle flow.

[0041] According to the influence range of the spatial coupling effect between the humidity change inside the fume duct and the suspended flow of particles, the dynamic impact evaluation and analysis of the humidity change on the flow simulation field of the suspended distribution change of particles inside the fume duct is carried out to obtain the dynamic change influence relationship between the humidity change inside the fume duct and the suspended distribution flow of particles.

[0042] Further, step S4 includes the following steps:

[0043] Step S41: based on the particle attachment area distribution density inside the oil fume duct and the future attachment distribution position of the suspended particles inside the oil fume duct, a particle attachment health evaluation calculation formula is used to perform a particle attachment health evaluation calculation on the inside of the oil fume duct to obtain a particle attachment health status score value inside the oil fume duct;

[0044] Step S42: performing health intelligent early warning processing on the corresponding particle adhesion situation inside the oil fume duct based on the health status score value of particle adhesion inside the oil fume duct, and obtaining health early warning information data of particle adhesion inside the oil fume duct;

[0045] Step S43: performing particle attachment cleaning demand analysis on the health warning information data of particles attached inside the oil fume duct to obtain particle attachment cleaning demand data inside the oil fume duct;

[0046] Step S44: Based on the cleaning demand data of particles attached inside the oil fume duct, a cleaning suggestion analysis is performed on the corresponding particle attachment conditions inside the oil fume duct, and a healthy cleaning suggestion plan for particles attached inside the oil fume duct is generated to perform the corresponding particle cleaning work inside the oil fume duct.

[0047] Furthermore, the particle attachment health evaluation calculation formula in step S41 is specifically:

[0048] ;

[0049] ;

[0050] ;

[0051] In the formula, is the health status score of particles attached inside the oil fume duct, is the cross-sectional area inside the oil fume duct, is the length of the interior of the oil fume duct, is the distribution density of particle attachment area inside the oil fume duct, The future attachment distribution position of suspended particles inside the oil fume duct. is the particle flow velocity inside the oil fume duct, The particles inside the oil fume duct are located at The particle adhesion tendency coefficient at is the particle property constant inside the oil fume duct, The particles inside the oil fume duct are located at The fluid shear stress coefficient at is an exponential function, The particles inside the oil fume duct are located at The particle settling threshold velocity at is the standard deviation of particle settling velocity, is the particle settling velocity inside the oil fume duct, The particles inside the oil fume duct are located at The particle attachment activity coefficient at Actively adjust parameters for particle attachment, The particles inside the oil fume duct are located at The number of active particles attached at is the initial active number of particles inside the oil fume duct, It is the correction factor for the health status score of particles attached inside the oil fume duct.

[0052] Furthermore, the present invention also provides an intelligent evaluation system for particle adhesion characteristics inside a fume duct, which is used to execute the intelligent evaluation method for particle adhesion characteristics inside a fume duct as described above. The intelligent evaluation system for particle adhesion characteristics inside a fume duct comprises:

[0053] The real-time monitoring module for data inside the oil fume duct is used to install a high-resolution particle monitor and a humidity sensor inside the oil fume duct, and use the high-resolution particle monitor and the humidity sensor to monitor the particle distribution image and the humidity of the duct in real time, so as to obtain real-time image data of particle distribution inside the oil fume duct and real-time data of humidity inside the oil fume duct; perform image standardization processing on the real-time image data of particle distribution inside the oil fume duct, so as to obtain standard image data of particle distribution inside the oil fume duct;

[0054] The particle distribution area division and attachment density analysis module is used to divide the particle distribution area of ​​the standard image data of the particle distribution inside the oil fume duct to obtain the particle attachment distribution area inside the oil fume duct and the particle hanging distribution area inside the oil fume duct; perform particle attachment distribution density analysis on the particle attachment distribution area inside the oil fume duct to obtain the particle attachment area distribution density inside the oil fume duct;

[0055] The future attachment distribution prediction module of the particle hanging area is used to perform time-series synchronization processing on the real-time data of the particle hanging distribution area inside the oil fume duct and the humidity inside the oil fume duct, and obtain the particle hanging distribution change area inside the oil fume duct and the humidity change data inside the oil fume duct under the same time-series dimension; based on the humidity change data inside the oil fume duct under the same time-series dimension, the future attachment distribution prediction analysis is performed on the particles hanging inside the oil fume duct corresponding to the particle hanging distribution change area inside the oil fume duct, and the future attachment distribution position of the particles hanging inside the oil fume duct is obtained;

[0056] The particle attachment health evaluation and cleaning suggestion module is used to calculate the particle attachment health evaluation inside the oil fume duct based on the particle attachment area distribution density inside the oil fume duct and the future attachment distribution position of the suspended particles inside the oil fume duct, so as to obtain the particle attachment health status score value inside the oil fume duct; based on the particle attachment health status score value inside the oil fume duct, the health intelligent early warning and cleaning suggestion analysis of the inside of the oil fume duct is performed, and a healthy cleaning suggestion plan for the particle attachment inside the oil fume duct is generated to perform the corresponding particle cleaning work inside the oil fume duct.

[0057] Beneficial effects of the present invention:

[0058] 1. The intelligent evaluation method for particle attachment characteristics inside the oil fume duct proposed in the present invention, compared with the prior art, has the beneficial effect that by installing a high-resolution particle monitor and a humidity sensor inside the oil fume duct, the monitoring accuracy of the particulate matter and humidity inside the duct can be significantly improved, and by using a high-resolution particle monitor to monitor the particle distribution image inside the oil fume duct in real time, it can capture extremely small particles and provide detailed particle distribution image data, which is crucial for evaluating the cleanliness state, pollution degree and distribution characteristics of the oil fume duct, so as to help timely understand the distribution of oil fume particles inside the duct, and early discover blockage problems or abnormal pipe attachment. Such high-resolution data acquisition can more accurately guide maintenance and cleaning work, and reduce the performance degradation or failure risk of the oil fume duct system caused by blockage. The humidity level of the oil fume duct directly affects the condensation of oil fume, the attachment of particulate matter and the cleanliness of the duct. By monitoring the humidity inside the duct in real time, it is possible to effectively track humidity changes and evaluate their impact on the performance of the oil fume treatment system. For example, high humidity can cause condensation of oil smoke and form scale, which in turn increases the difficulty and frequency of cleaning the pipeline, while low humidity can cause the scattering of oil smoke particles, thus providing basic data guarantee for the subsequent processing process. At the same time, by performing image standardization on the real-time image data of particle distribution inside the oil smoke pipeline, the image data can be adjusted to a unified scale and format, eliminating changes caused by different shooting conditions or sensor settings. The standardized image data can be accurately compared at different time points or between different monitoring devices, making long-term monitoring and trend analysis possible. This processing can improve the comparability and consistency of data, support long-term monitoring and trend prediction of the state of the oil smoke pipeline, and thus better monitor the particle attachment in the oil smoke pipeline. Secondly, by dividing the particle distribution area of ​​the standard image data of particle distribution inside the oil smoke pipeline, the particles in the oil smoke pipeline can be divided into an attached area and a suspended area. The attached area refers to the area where the particles are deposited on the inner wall of the pipeline, while the suspended area refers to the area where the particles are suspended in the pipeline. This division helps to identify different particle distribution states in the pipeline and provides detailed information for subsequent maintenance and optimization. For example, analysis of the attachment area can help determine the scale accumulation in the pipeline and guide cleaning and maintenance plans; analysis of the suspended area helps understand the flow behavior of particles and predict future attachment distribution. Through regional division, managers can develop targeted treatment plans to optimize pipeline operating efficiency and reduce pollution risks.The particle attachment distribution density analysis is also performed on the particle attachment distribution area inside the oil fume duct. The core of the particle attachment distribution density analysis is to calculate the number of particles per unit area in the attachment area, thereby revealing the degree of particle deposition in these areas. Density analysis can not only help formulate targeted cleaning plans, but also evaluate the effectiveness of pipeline design. For example, if the attachment density in certain areas is too high, the design or operating parameters of the oil fume treatment system need to be adjusted to reduce the deposition and fouling of particles, help identify and predict potential maintenance needs, and prevent oil fume duct failures caused by excessive fouling. Then, by performing time-series synchronization processing on the corresponding particle suspension distribution changes in the particle suspension distribution area inside the oil fume duct and the real-time humidity data inside the oil fume duct, the particle distribution and humidity change data on a unified time scale are obtained. Through this synchronization processing, the relationship between particle distribution and humidity changes can be captured more accurately. The particulate matter in the oil fume duct is usually affected by the humidity factor, and the change of this influencing factor over time will cause changes in particle distribution. Therefore, by synchronously analyzing the particle suspension distribution and humidity data in the same time series dimension, the dynamic relationship between the two can be revealed, thereby providing accurate basic data for further simulation and analysis. This time series synchronization processing method helps to improve the accuracy of data analysis, avoid errors caused by data mismatch, and help to deeply understand the changing laws of the internal environment of the fume duct, and lay a solid foundation for subsequent flow simulation and dynamic evaluation. The future attachment distribution prediction analysis of the suspended particles in the fume duct corresponding to the particle suspension distribution change area in the fume duct is also carried out based on the internal humidity change data of the fume duct in the same time series dimension. The core value of this step is that it can predict the attachment and deposition trend of particulate matter in the fume duct in a forward-looking manner, thereby providing a scientific basis for the long-term maintenance and cleaning of the duct. Through in-depth analysis of the dynamic influence of humidity changes and particle flow, an accurate prediction model can be constructed to predict the attachment position and distribution of particles in a certain period of time in the future. This prediction capability helps to formulate targeted maintenance strategies, reduce the impact of particle accumulation on pipes, extend the service life of pipes, and improve the overall performance and reliability of oil fume pipes, thereby better improving the accuracy and comprehensiveness of monitoring particle attachment distribution characteristics, that is, being able to monitor in real time the particle distribution density in the attachment area and the future distribution position of particles in the suspended area and other particle attachment distribution characteristics.Finally, by calculating the particle attachment health evaluation inside the oil fume duct based on the particle attachment area distribution density inside the oil fume duct and the future attachment distribution position of the suspended particles inside the oil fume duct, the particle attachment health status inside the duct can be systematically evaluated. This process involves detailed monitoring and data analysis of the internal environment of the duct. Through calculation, the severity, distribution and potential health risks of particle attachment can be quantified. This detailed evaluation not only provides a quantitative health status score, but also reveals the impact of particle attachment on the overall performance and safety of the oil fume duct. This information is crucial for formulating subsequent cleaning and maintenance strategies, and can help to promptly discover potential hygiene problems and maintenance hazards, thereby improving the operating efficiency and safety of the oil fume duct. In addition, the health intelligent early warning and cleaning suggestion analysis of the oil fume duct is carried out based on the health status score of the particle attachment inside the oil fume duct. The score can be compared with the set health threshold, and the health early warning information data can be generated in real time. These early warning information can timely convey the status of particle attachment inside the pipeline to point out potential health risks, and conduct detailed cleaning suggestion analysis through the generated health early warning information. The generated cleaning suggestion plan provides a detailed and feasible cleaning plan based on the specific particle attachment situation. This process involves a comprehensive assessment of the cleaning needs inside the oil fume duct, including the selection of appropriate cleaning methods, equipment and materials, and the formulation of steps and schedules for cleaning operations. The cleaning suggestion plan not only takes into account the actual cleaning needs, but also combines industry best practices and technical standards to ensure the comprehensiveness and effectiveness of the cleaning work. Through systematic cleaning suggestions, managers can develop and implement efficient cleaning plans, effectively remove attached particles, restore the normal operation of the oil fume duct, and reduce the impact on equipment performance and operational safety, thereby improving the cleaning efficiency of particle attachment inside the oil fume duct.

[0059] 2. The intelligent evaluation system for particle attachment characteristics inside the oil fume duct proposed in the present invention is generally composed of a real-time monitoring module for oil fume duct internal data, a particle distribution area division and attachment density analysis module, a particle suspension area future attachment distribution prediction module, and a particle attachment health evaluation and cleaning suggestion module. It can implement the intelligent evaluation method for particle attachment characteristics inside any oil fume duct described in the present invention, and is used to combine the operations between computer programs running on each module to implement the intelligent evaluation method for particle attachment characteristics inside the oil fume duct. The internal structures of the system cooperate with each other, which can greatly reduce duplication of work and manpower investment, and can quickly and effectively provide a more accurate and efficient intelligent evaluation process for particle attachment characteristics inside the oil fume duct, thereby simplifying the operating procedures of the intelligent evaluation system for particle attachment characteristics inside the oil fume duct. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments thereof made with reference to the following drawings:

[0061] Figure 1 It is a schematic diagram of the steps of the intelligent evaluation method of particle attachment characteristics inside the oil fume duct of the present invention;

[0062] Figure 2 for Figure 1 Detailed step flow diagram of step S1;

[0063] Figure 3 for Figure 1 Detailed step flow chart of step S2 in FIG. DETAILED DESCRIPTION

[0064] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0065] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0066] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0067] To achieve this, please refer to Figures 1 to 3 The present invention provides an intelligent evaluation method for particle attachment characteristics inside a fume duct, the method comprising the following steps:

[0068] Step S1: installing a high-resolution particle monitor and a humidity sensor inside the oil fume duct, and using the high-resolution particle monitor and the humidity sensor to perform real-time monitoring of the particle distribution image and the humidity of the duct inside the oil fume duct, thereby obtaining real-time image data of the particle distribution inside the oil fume duct and real-time data of the humidity inside the oil fume duct; performing image standardization processing on the real-time image data of the particle distribution inside the oil fume duct, thereby obtaining standard image data of the particle distribution inside the oil fume duct;

[0069] Step S2: dividing the particle distribution area of ​​the standard image data of the particle distribution inside the oil fume duct to obtain the particle attachment distribution area inside the oil fume duct and the particle suspension distribution area inside the oil fume duct; performing particle attachment distribution density analysis on the particle attachment distribution area inside the oil fume duct to obtain the particle attachment area distribution density inside the oil fume duct;

[0070] Step S3: performing time series synchronization processing on the suspended distribution area of ​​particles inside the oil fume duct and the real-time data of humidity inside the oil fume duct to obtain the suspended distribution change area of ​​particles inside the oil fume duct and the humidity change data inside the oil fume duct in the same time series dimension; based on the humidity change data inside the oil fume duct in the same time series dimension, performing future attachment distribution prediction analysis on the suspended particles inside the oil fume duct corresponding to the suspended distribution change area of ​​particles inside the oil fume duct, and obtaining the future attachment distribution position of the suspended particles inside the oil fume duct;

[0071] Step S4: Based on the distribution density of the particle attachment area inside the oil fume duct and the future attachment distribution position of the suspended particles inside the oil fume duct, a particle attachment health evaluation calculation is performed on the inside of the oil fume duct to obtain a particle attachment health status score value inside the oil fume duct; based on the particle attachment health status score value inside the oil fume duct, a health intelligent early warning and cleaning suggestion analysis is performed on the inside of the oil fume duct, and a healthy cleaning suggestion plan for particle attachment inside the oil fume duct is generated to perform corresponding particle cleaning work inside the oil fume duct.

[0072] In the embodiment of the present invention, please refer to Figure 1 FIG. 1 is a schematic diagram of the steps of the intelligent evaluation method for particle attachment characteristics inside a fume duct according to the present invention. In this example, the intelligent evaluation method for particle attachment characteristics inside a fume duct includes the following steps:

[0073] Step S1: installing a high-resolution particle monitor and a humidity sensor inside the oil fume duct, and using the high-resolution particle monitor and the humidity sensor to perform real-time monitoring of the particle distribution image and the humidity of the duct inside the oil fume duct, thereby obtaining real-time image data of the particle distribution inside the oil fume duct and real-time data of the humidity inside the oil fume duct; performing image standardization processing on the real-time image data of the particle distribution inside the oil fume duct, thereby obtaining standard image data of the particle distribution inside the oil fume duct;

[0074] In the embodiment of the present invention, a corresponding high-resolution particle monitor and a humidity sensor are installed inside the oil fume duct, wherein the high-resolution particle monitor should be set at multiple key positions of the oil fume duct to ensure that the full range of particle distribution can be captured. The device has the function of detecting tiny particles and generating their distribution images, and the humidity sensor is installed inside the oil fume duct. The humidity sensor should have a high-precision humidity detection function and can collect humidity data in the duct in real time. At the same time, the previously installed high-resolution particle monitor is started to scan the inside of the oil fume duct through optical or laser technology to obtain the distribution image of oil fume particles in real time. Each image needs to be collected at a high resolution so as to accurately identify particles of different sizes and concentrations, thereby obtaining real-time image data of particle distribution inside the oil fume duct. The previously installed humidity sensor is used to measure the humidity changes inside the oil fume duct in real time through resistive or capacitive technology, and the detection results are transmitted to the data recording system in the form of digital signals. These data need to be displayed in real time and recorded in the data storage device, thereby obtaining real-time humidity data inside the oil fume duct. Then, the pre-processed real-time image data of the particle distribution inside the oil fume duct is standardized by using an image standardization algorithm to convert the image data into a unified standard format, which includes adjusting the image size, resolution and color depth to meet the preset standardization requirements. The processing process includes mapping the image data to a standard color space and adjusting the grayscale level to ensure the consistency and comparability of the image data. The standardized image data can be used for further analysis and comparison to finally obtain standard image data of the particle distribution inside the oil fume duct.

[0075] Step S2: dividing the particle distribution area of ​​the standard image data of the particle distribution inside the oil fume duct to obtain the particle attachment distribution area inside the oil fume duct and the particle suspension distribution area inside the oil fume duct; performing particle attachment distribution density analysis on the particle attachment distribution area inside the oil fume duct to obtain the particle attachment area distribution density inside the oil fume duct;

[0076] In an embodiment of the present invention, spatial positioning processing is performed on each particle in the standard image data of particle distribution inside the oil fume duct obtained through standardization previously, which involves analyzing the particles of the standard image data one by one, and using a deep learning model (such as YOLO or Mask R-CNN) to accurately locate the spatial position of each particle, so as to obtain its coordinates in the image, and detecting and extracting the corner points in the standard image data of particle distribution inside the oil fume duct obtained through standardization previously by using a computer vision algorithm (such as a feature point detection algorithm SIFT or SURF). These algorithms will identify the 3D corner point data of the inner wall of the oil fume duct in the image to ensure that all areas of the inner wall of the duct are covered. At the same time, by combining the spatial position distribution coordinates of each particle inside the oil fume duct determined by the previous analysis and the spatial distribution corner points of the inner wall of the oil fume duct in a 3D state, a spatial reconstruction algorithm (such as a three-dimensional reconstruction algorithm PoissonReconstruction) is used to perform three-dimensional spatial reconstruction processing on the corresponding standard image of particle distribution inside the oil fume duct, so as to convert these data into a three-dimensional model. The process includes creating an initial The three-dimensional grid model is initially obtained, and the spatial coordinates of the particles are mapped to the inner wall model of the pipe through iterative optimization. The corresponding three-dimensional reconstructed spatial model is connected and divided into particle distribution areas by combining the spatial position distribution coordinates of each particle inside the oil fume pipe determined previously, so as to calculate the distance between the particle and the inner wall of the pipe according to the spatial position distribution coordinates of each particle inside the oil fume pipe, and set a threshold value, and define the area with a distance less than or equal to the threshold value as the particle attachment area, and the area with a distance greater than the threshold value as the suspended area, and by applying a spatial division algorithm (such as Voronoi diagram or Delaunay triangulation), the three-dimensional reconstructed spatial model of particle distribution inside the oil fume pipe is divided into particle attachment area and suspended area, so as to connect and divide the particle attachment distribution area inside the oil fume pipe and the particle suspended distribution area inside the oil fume pipe. Then, the particle attachment distribution area inside the oil fume pipe is grid-divided by combining the previously divided particle attachment distribution area inside the oil fume pipe, so as to divide the particle attachment distribution area inside the oil fume pipe into multiple grid units, and quantify the total particle attachment area in each grid unit and the effective area of ​​the entire area. By using these data,

[0077] The density analysis method (such as dividing the total particle attachment area by the effective area of ​​the entire area) is applied to calculate the particle distribution density in each attachment distribution area, and finally the particle attachment area distribution density inside the fume duct is obtained.

[0078] Step S3: performing time series synchronization processing on the suspended distribution area of ​​particles inside the oil fume duct and the real-time data of humidity inside the oil fume duct to obtain the suspended distribution change area of ​​particles inside the oil fume duct and the humidity change data inside the oil fume duct in the same time series dimension; based on the humidity change data inside the oil fume duct in the same time series dimension, performing future attachment distribution prediction analysis on the suspended particles inside the oil fume duct corresponding to the suspended distribution change area of ​​particles inside the oil fume duct, and obtaining the future attachment distribution position of the suspended particles inside the oil fume duct;

[0079] In the embodiment of the present invention, by using a time series synchronization method, the corresponding particle suspension distribution changes in the particle suspension distribution area inside the oil fume duct and the real-time data of humidity inside the oil fume duct obtained by the previous analysis are synchronized in time series in the order of timestamps, so as to integrate these data into the same time series dimension, so as to obtain the particle distribution and humidity change data under the same time scale, and ensure that it can more accurately capture the relationship between particle distribution and humidity change, so as to obtain the particle suspension distribution change area inside the oil fume duct and the humidity change data inside the oil fume duct under the same time series dimension. At the same time, after obtaining the synchronized particle suspension distribution change area inside the oil fume duct, using fluid mechanics simulation software (such as ANSYS Fluent or OpenFOAM) is used to simulate and analyze the particle distribution flow field. The data of the particle suspension distribution position change after input synchronization is used as the initial condition. The fluid dynamics equations, boundary conditions and physical properties of the particles are set to analyze the flow field and distribution changes of the particles inside the oil fume duct at different time nodes. The simulation results will show the dynamic distribution pattern of the particles in the duct, including the flow simulation fields such as the aggregation, diffusion and flow trend of the particles during the flow process. The flow simulation field generated by the simulation is evaluated and analyzed by combining the humidity change data inside the oil fume duct obtained after time series synchronization to evaluate the dynamic impact of humidity changes and particle distribution flow. Then, by combining the dynamic change influence relationship between humidity change and particle distribution flow obtained by previous analysis, predictive modeling tools (such as machine learning algorithms, regression analysis, etc.) are used to predict the attachment distribution position of suspended particles inside the oil fume duct corresponding to the suspended distribution change area of ​​particles inside the oil fume duct. The humidity change trend and particle flow field simulation results are input to construct a future particle attachment distribution prediction model. Through learning from historical data, the model will predict the possible attachment position of particles inside the oil fume duct in a certain period of time in the future, thereby generating the attachment area distribution position of the prediction result, and finally obtaining the future attachment distribution position of suspended particles inside the oil fume duct.

[0080] Step S4: Based on the distribution density of the particle attachment area inside the oil fume duct and the future attachment distribution position of the suspended particles inside the oil fume duct, a particle attachment health evaluation calculation is performed on the inside of the oil fume duct to obtain a particle attachment health status score value inside the oil fume duct; based on the particle attachment health status score value inside the oil fume duct, a health intelligent early warning and cleaning suggestion analysis is performed on the inside of the oil fume duct, and a healthy cleaning suggestion plan for particle attachment inside the oil fume duct is generated to perform corresponding particle cleaning work inside the oil fume duct.

[0081] In an embodiment of the present invention, a suitable health evaluation calculation formula is formed by combining the distribution density of the particle attachment area inside the oil fume duct, the future attachment distribution position of the suspended particles inside the oil fume duct, and related parameters to perform a particle attachment health evaluation calculation on the inside of the oil fume duct, so as to quantitatively calculate a health status score value, which reflects the overall health status of the particle attachment inside the oil fume duct, thereby obtaining the particle attachment health status score value inside the oil fume duct. At the same time, the health status score values ​​previously obtained by quantitative calculation are compared by using a pre-set warning threshold, and the intelligent warning system is used to determine whether the current particle attachment state exceeds the health standard through the set warning threshold, so as to perform health intelligent warning processing on the corresponding particle attachment situation inside the oil fume duct according to the score value exceeding the corresponding warning threshold, and generate corresponding warning information by intelligent warning, which includes a detailed description of the particle attachment situation, the existing particle attachment health risks, and the warning level, and the health warning information data previously obtained through the warning is evaluated and analyzed by using a data analysis tool to evaluate the cleaning needs of the particle attachment area inside the oil fume duct. Specifically, the warning information data is input into the analysis system using the data analysis tool. The model calculates the required cleaning degree and priority according to the distribution density of particle attachment, health score and working conditions of the pipeline, and then analyzes the cleaning recommendations for particle attachment in the pipeline by combining the previously determined attachment cleaning requirement data with the corresponding particle attachment situation inside the oil fume duct, so as to input the cleaning requirement data into the cleaning recommendation generation system. The system formulates a cleaning plan based on the specific structure of the pipeline, the type and distribution of attached particles, including the selection of appropriate cleaning tools, such as high-pressure cleaning equipment or chemical cleaning agents, and their use methods, frequency and cleaning range, to ensure that normal operation is not affected during the cleaning process, and finally generates a corresponding healthy cleaning recommendation plan for particle attachment inside the oil fume duct, which is used to guide cleaning personnel to perform actual cleaning operations.

[0082] Further, step S1 includes the following steps:

[0083] Step S11: installing a high-resolution particle monitor and a humidity sensor inside the oil fume duct, and using the high-resolution particle monitor to monitor the particle distribution image inside the oil fume duct in real time, thereby obtaining real-time image data of the particle distribution inside the oil fume duct;

[0084] Step S12: using a humidity sensor to monitor the humidity inside the oil fume duct in real time, and obtaining real-time humidity data inside the oil fume duct;

[0085] Step S13: performing image denoising processing on the real-time image data of the particle distribution inside the oil fume duct to obtain denoised image data of the particle distribution inside the oil fume duct;

[0086] Step S14: performing image contrast enhancement processing on the denoised image data of the particle distribution inside the oil fume duct to obtain contrast enhanced image data of the particle distribution inside the oil fume duct;

[0087] Step S15: performing image standardization processing on the image contrast enhancement data of the particle distribution inside the oil fume duct to obtain standard image data of the particle distribution inside the oil fume duct.

[0088] As an embodiment of the present invention, refer to Figure 2 As shown, Figure 1 Detailed step flow diagram of step S1 in FIG. 1 , in this embodiment, step S1 includes the following steps:

[0089] Step S11: installing a high-resolution particle monitor and a humidity sensor inside the oil fume duct, and using the high-resolution particle monitor to monitor the particle distribution image inside the oil fume duct in real time, thereby obtaining real-time image data of the particle distribution inside the oil fume duct;

[0090] In an embodiment of the present invention, a corresponding high-resolution particle monitor and a humidity sensor are installed inside the oil fume duct, wherein the high-resolution particle monitor should be set at multiple key positions of the oil fume duct to ensure that the full range of particle distribution can be captured. The device has the function of detecting tiny particles and generating their distribution images, and the humidity sensor is installed inside the oil fume duct. The humidity sensor should have a high-precision humidity detection function and can collect humidity data in the duct in real time. At the same time, the previously installed high-resolution particle monitor is started to scan the inside of the oil fume duct through optical or laser technology to obtain the distribution image of the oil fume particles in real time. Each image needs to be collected at a high resolution in order to accurately identify particles of different sizes and concentrations, and finally obtain real-time image data of particle distribution inside the oil fume duct.

[0091] Step S12: using a humidity sensor to monitor the humidity inside the oil fume duct in real time, and obtaining real-time humidity data inside the oil fume duct;

[0092] In an embodiment of the present invention, a previously installed humidity sensor is used to measure the humidity changes inside the oil fume duct in real time through resistive or capacitive technology, and the detection results are transmitted to the data recording system in the form of digital signals. These data need to be displayed in real time and recorded in a data storage device to finally obtain real-time humidity data inside the oil fume duct.

[0093] Step S13: performing image denoising processing on the real-time image data of the particle distribution inside the oil fume duct to obtain denoised image data of the particle distribution inside the oil fume duct;

[0094] In an embodiment of the present invention, an image filtering algorithm, such as a median filter or a Gaussian filter, is used to perform image denoising on real-time image data of particle distribution inside the oil fume duct previously obtained through real-time monitoring to reduce random noise in the image. During the denoising process, each image pixel is smoothed using a set filter to reduce interference of background noise on particle identification. The processed image should show clear edges of particles and reduce false particle information, thereby finally obtaining denoised image data of particle distribution inside the oil fume duct.

[0095] Step S14: performing image contrast enhancement processing on the denoised image data of the particle distribution inside the oil fume duct to obtain contrast enhanced image data of the particle distribution inside the oil fume duct;

[0096] In an embodiment of the present invention, the particle distribution image data after denoising is contrast enhanced by applying a contrast enhancement algorithm such as histogram equalization. This step makes the visual features of the particles more prominent by adjusting the brightness and contrast of the image. The enhanced image needs to show obvious particle contours to improve the accuracy of subsequent processing, and finally obtain contrast enhanced data of the particle distribution image inside the fume duct.

[0097] Step S15: performing image standardization processing on the image contrast enhancement data of the particle distribution inside the oil fume duct to obtain standard image data of the particle distribution inside the oil fume duct.

[0098] In an embodiment of the present invention, the particle distribution image data that has previously undergone contrast enhancement is standardized by using an image standardization algorithm to convert the image data into a unified standard format, which includes adjusting the image size, resolution, and color depth to meet preset standardization requirements. The processing process includes mapping the image data to a standard color space and adjusting the grayscale level to ensure the consistency and comparability of the image data. The standardized image data can be used for further analysis and comparison to ultimately obtain standard image data of particle distribution inside the oil fume duct.

[0099] Further, step S2 includes the following steps:

[0100] Step S21: performing spatial position positioning processing on each particle in the standard image data of particle distribution inside the oil fume duct to obtain the spatial position distribution coordinates of each particle inside the oil fume duct;

[0101] Step S22: performing 3D corner point extraction processing on the inner wall of the oil fume duct on the standard image data of particle distribution inside the oil fume duct to obtain a set of spatially distributed corner points of the inner wall of the oil fume duct in a 3D state;

[0102] Step S23: performing three-dimensional spatial reconstruction processing on the standard image data of particle distribution inside the oil fume duct based on the spatial position distribution coordinates of each particle inside the oil fume duct and the spatial distribution corner point set of the inner wall of the oil fume duct in a 3D state, so as to generate a three-dimensional reconstructed spatial model of particle distribution inside the oil fume duct;

[0103] Step S24: dividing the particle distribution area of ​​the three-dimensional reconstructed spatial model of the particle distribution inside the oil fume duct based on the spatial position distribution coordinates of each particle inside the oil fume duct to obtain the particle attachment distribution area inside the oil fume duct and the particle suspension distribution area inside the oil fume duct;

[0104] Step S25: performing particle attachment distribution density analysis on the particle attachment distribution area inside the oil fume duct to obtain the particle attachment area distribution density inside the oil fume duct.

[0105] As an embodiment of the present invention, refer to Figure 3 As shown, Figure 1 Detailed step flow diagram of step S2 in FIG. 1 , in this embodiment, step S2 includes the following steps:

[0106] Step S21: performing spatial position positioning processing on each particle in the standard image data of particle distribution inside the oil fume duct to obtain the spatial position distribution coordinates of each particle inside the oil fume duct;

[0107] In an embodiment of the present invention, spatial positioning processing is performed on each particle in the standard image data of particle distribution inside the oil fume duct obtained through standardization. This involves analyzing the particles of the standard image data one by one, photographing the inside of the oil fume duct with a high-resolution camera, obtaining image data of particle distribution, and performing image segmentation by applying image processing software (such as OpenCV) to identify the boundary of each particle. At the same time, a deep learning model (such as YOLO or Mask R-CNN) is used to accurately locate the spatial position of each particle, thereby obtaining its coordinates in the image. The image coordinates are combined with known camera internal parameters and position correction data to convert them into three-dimensional spatial coordinates, and finally the spatial position distribution coordinates of each particle inside the oil fume duct are obtained.

[0108] Step S22: performing 3D corner point extraction processing on the inner wall of the oil fume duct on the standard image data of particle distribution inside the oil fume duct to obtain a set of spatially distributed corner points of the inner wall of the oil fume duct in a 3D state;

[0109] In an embodiment of the present invention, by using computer vision algorithms (such as feature point detection algorithms SIFT or SURF), the corner points in the previously standardized standard image data of the particle distribution inside the oil fume duct are detected and extracted. These algorithms will identify the obvious corner points in the image and calculate their positions in the 2D image. At the same time, by aligning these 2D corner point positions with the multi-view images, the 3D corner point data of the inner wall of the oil fume duct can be reconstructed to ensure that all areas of the inner wall of the duct are covered, and finally a set of spatially distributed corner points of the inner wall of the oil fume duct in a 3D state is obtained.

[0110] Step S23: performing three-dimensional spatial reconstruction processing on the standard image data of particle distribution inside the oil fume duct based on the spatial position distribution coordinates of each particle inside the oil fume duct and the spatial distribution corner point set of the inner wall of the oil fume duct in a 3D state, so as to generate a three-dimensional reconstructed spatial model of particle distribution inside the oil fume duct;

[0111] In an embodiment of the present invention, by combining the spatial position distribution coordinates of each particle inside the oil fume duct determined by the previous analysis and the set of spatial distribution corner points of the inner wall of the oil fume duct in a 3D state, a spatial reconstruction algorithm (such as a three-dimensional reconstruction algorithm Poisson Reconstruction) is used to perform three-dimensional spatial reconstruction processing on the corresponding standard image of the particle distribution inside the oil fume duct to convert these data into a three-dimensional model. The process includes creating an initial three-dimensional grid model, and through iterative optimization, mapping the spatial coordinates of the particles to the inner wall model of the pipe, and finally generating a three-dimensional reconstructed spatial model of the particle distribution inside the oil fume duct.

[0112] Step S24: dividing the particle distribution area of ​​the three-dimensional reconstructed spatial model of the particle distribution inside the oil fume duct based on the spatial position distribution coordinates of each particle inside the oil fume duct to obtain the particle attachment distribution area inside the oil fume duct and the particle suspension distribution area inside the oil fume duct;

[0113] In an embodiment of the present invention, the spatial position distribution coordinates of each particle inside the oil fume duct determined previously are combined to connect and divide the particle distribution areas of the corresponding three-dimensional reconstructed spatial model of the particle distribution inside the oil fume duct, so as to calculate the distance between the particle and the inner wall of the duct according to the spatial position distribution coordinates of each particle inside the oil fume duct, and set a threshold value, and define the area with a distance less than or equal to the threshold value as the particle attachment area, and the area with a distance greater than the threshold value as the suspended area, and by applying a space division algorithm (such as a Voronoi diagram or a Delaunay triangulation), the three-dimensional reconstructed spatial model of the particle distribution inside the oil fume duct is divided into a particle attachment area and a suspended area, and finally obtain the particle attachment distribution area inside the oil fume duct and the particle suspended distribution area inside the oil fume duct.

[0114] Step S25: performing particle attachment distribution density analysis on the particle attachment distribution area inside the oil fume duct to obtain the particle attachment area distribution density inside the oil fume duct.

[0115] In an embodiment of the present invention, grid division is performed by combining the previously divided particle attachment distribution area inside the oil fume duct to divide the particle attachment distribution area inside the oil fume duct into multiple grid units, and the total particle attachment area in each grid unit and the effective area of ​​the entire area are quantified and calculated. By utilizing these data, a density analysis method (such as dividing the total particle attachment area by the effective area of ​​the entire area) is applied to calculate the particle distribution density in each attachment distribution area, and finally the particle attachment area distribution density inside the oil fume duct is obtained.

[0116] Further, step S24 includes the following steps:

[0117] Step S241: performing particle vertical point matching mapping on the inner wall of the oil fume duct in the three-dimensional reconstructed spatial model of particle distribution inside the oil fume duct based on the spatial position distribution coordinates of each particle inside the oil fume duct, so as to obtain the inner wall vertical matching point distribution coordinates corresponding to each particle inside the oil fume duct;

[0118] In an embodiment of the present invention, in order to achieve the inner wall vertical point matching mapping of each particle in the three-dimensional reconstructed spatial model of particle distribution inside the fume duct, it is first necessary to obtain the three-dimensional model data of the inner wall of the fume duct, which can be achieved by scanning the fume duct with a high-precision laser scanner, thereby obtaining the three-dimensional coordinate point cloud of the inner wall of the fume duct, and then mapping the spatial position distribution coordinates of the particles inside the fume duct to the model of the inner wall of the fume duct. In the specific operation, an algorithm such as a nearest neighbor search or a distance minimization algorithm is used to determine the vertical point matching of each particle on the inner wall of the fume duct, so as to complete the particle vertical point matching by calculating the vertical distance from each particle to the inner wall of the fume duct and aligning the position of each particle with the nearest inner wall point, and determine the spatial distribution coordinates of its matching point, and finally map to obtain the inner wall vertical matching point distribution coordinates corresponding to each particle inside the fume duct.

[0119] Step S242: performing quantitative calculation of the distance between each particle and the inner wall for the spatial position distribution coordinates of each particle inside the oil fume duct and the inner wall vertical matching point distribution coordinates corresponding to each particle inside the oil fume duct, so as to obtain the spatial distribution distance value between each particle inside the oil fume duct and the inner wall of the oil fume duct;

[0120] In an embodiment of the present invention, the spatial distribution distance is quantitatively calculated by using the Euclidean distance formula for the spatial position distribution coordinates of each particle inside the oil fume duct previously determined and the inner wall vertical matching point distribution coordinates corresponding to each particle inside the oil fume duct, so as to quantitatively calculate the actual distance between the particle and the inner wall, that is, to quantify the spatial distribution distance value between the particle and the inner wall by using the distance formula between the three-dimensional coordinate points. This step is usually implemented through programming tools (such as the NumPy library in Python), and the actual distance between each particle and the vertical coordinate point of the inner wall of the oil fume duct is calculated, and finally the spatial distribution distance value between each particle inside the oil fume duct and the inner wall of the oil fume duct is obtained.

[0121] Step S243: comparing and judging the spatial distribution distance value between each particle inside the oil fume duct and the inner wall of the oil fume duct according to the preset oil fume duct internal particle attachment distance threshold, when the spatial distribution distance value is less than or equal to the preset oil fume duct internal particle attachment distance threshold, the corresponding particle in the three-dimensional reconstruction space model of the oil fume duct internal particle distribution is determined as the oil fume duct internal particle attachment particle point; when the spatial distribution distance value is greater than the preset oil fume duct internal particle attachment distance threshold, the corresponding particle in the three-dimensional reconstruction space model of the oil fume duct internal particle distribution is determined as the oil fume duct suspended particle point;

[0122] In an embodiment of the present invention, a spatial distribution distance value between each particle inside the oil fume duct and the inner wall of the oil fume duct obtained by previously quantitative calculation is compared and judged by using a preset oil fume duct internal particle attachment distance threshold. If the corresponding spatial distribution distance value is less than or equal to the preset oil fume duct internal particle attachment distance threshold, it means that the particle corresponding to the coordinate position is close to the inner wall of the oil fume duct, and the corresponding particle in the three-dimensional reconstructed spatial model of the particle distribution inside the oil fume duct is determined as the oil fume duct attached particle point; and if the corresponding spatial distribution distance value is greater than the preset oil fume duct internal particle attachment distance threshold, it means that there is a large spatial distance between the particle corresponding to the coordinate position and the inner wall of the oil fume duct, and the corresponding particle in the three-dimensional reconstructed spatial model of the particle distribution inside the oil fume duct is determined as the oil fume duct suspended particle point.

[0123] Step S244: connecting and dividing the attachment distribution area of ​​each particle corresponding to the three-dimensional reconstructed spatial model of particle distribution inside the oil fume duct based on the particle attachment point of the oil fume duct, so as to obtain the particle attachment distribution area inside the oil fume duct;

[0124] In an embodiment of the present invention, based on the oil fume duct attachment particle points determined in the previous step and realizing the connection division of the attachment distribution area for these attachment particle points, starting from the particle points that are initially marked as attached, a spatial clustering algorithm (such as DBSCAN or K-means) is used to aggregate and group these attachment particle points. The clustering algorithm will classify adjacent attachment particles into a regional collection point according to the spatial distance between the attachment particle points. This process is achieved by means of computer programming technology and algorithm tools (for example, using the Scikit-learn library in Python). After the division is completed, the corresponding attachment particle points in the regional collection point are connected to generate an attachment distribution area map of the particles inside the oil fume duct, and the particle distribution in the area is recorded, and finally the particle attachment distribution area inside the oil fume duct is obtained.

[0125] Step S245: based on the suspended particle points of the oil fume duct, the suspended distribution area of ​​each particle corresponding to the three-dimensional reconstructed spatial model of particle distribution inside the oil fume duct is connected and divided to obtain the suspended distribution area of ​​particles inside the oil fume duct.

[0126] In an embodiment of the present invention, similarly, by connecting and dividing the suspended particle points inside the oil fume duct into suspended distribution areas, the suspended particle points are taken as the basis, and the suspended particle points are aggregated and grouped using the same spatial clustering algorithm as the previous step, and the adjacent suspended particles are classified into a regional collection point according to the spatial distance between the suspended particle points. After the division is completed, the corresponding suspended particle points in the regional collection point are connected to generate a suspended distribution area map of the particles inside the oil fume duct, and finally the suspended distribution area of ​​the particles inside the oil fume duct is obtained.

[0127] Further, step S25 includes the following steps:

[0128] Step S251: performing a statistical analysis on the number of particles attached to the distribution area of ​​particles inside the oil fume duct to obtain the number of particles attached to the distribution area inside the oil fume duct;

[0129] In an embodiment of the present invention, an image analysis algorithm (such as edge detection and region segmentation) is applied to count the number of particles attached to the previously divided particle attachment distribution area inside the oil fume duct, so as to determine the specific position and number of particles in the attachment distribution area, and then the number of particles in each particle attachment area is statistically calculated to ensure that the particle distribution of the particle attachment area is accurately described, and finally the number of particles attached to the distribution area inside the oil fume duct is obtained.

[0130] Step S252: performing particle contour shape recognition analysis on the particle attachment distribution area inside the oil fume duct to obtain the particle attachment contour shape size in the distribution area inside the oil fume duct;

[0131] In an embodiment of the present invention, an image processing algorithm (such as a contour detection algorithm) is used to identify and extract the contour of each particle in the particle attachment distribution area inside the oil fume duct, so that by utilizing tools such as OpenCV and other image processing libraries, morphological operations can be performed on the image to separate and identify the contours of the particles. Thereafter, a shape analysis algorithm (such as Hu moment and Zernike moment) is used to calculate the specific shape characteristics and size of the particle contour, including indicators such as aspect ratio and roundness. These shape and size data will help further calculate the total area of ​​particle attachment, and ultimately obtain the shape and size of the particle attachment contour in the distribution area inside the oil fume duct.

[0132] Step S253: based on the number of particles attached in the distribution area inside the oil fume duct and the size of the particle attachment contour in the distribution area inside the oil fume duct, the particle attachment area corresponding to each particle in the particle attachment distribution area inside the oil fume duct is calculated to obtain the total particle attachment area size in the area inside the oil fume duct;

[0133] In an embodiment of the present invention, by combining the previously identified particle attachment contour shape size in the internal distribution area of ​​the fume duct, computer vision tools and geometric analysis methods (such as pixel-based area measurement or geometric shape-based area calculation) are used to accurately calculate the area of ​​the contour of each particle corresponding to the internal particle attachment distribution area of ​​the fume duct, so as to quantitatively calculate the contour area of ​​each particle, and summarize the area data of all particles according to the number of particles attached in the internal distribution area of ​​the fume duct, and finally obtain the total area size of the particles attached in the internal area of ​​the fume duct.

[0134] Step S254: performing particle attachment distribution density analysis on the particle attachment distribution area inside the oil fume duct based on the total particle attachment area size inside the oil fume duct to obtain the particle attachment area distribution density inside the oil fume duct.

[0135] In an embodiment of the present invention, the effective area of ​​the particle attachment distribution area inside the oil fume duct is quantitatively calculated, and the distribution density is calculated by combining the total area of ​​the particle attachment in the oil fume duct distribution area obtained by the previous quantitative calculation. The distribution density of the particle attachment area is quantitatively determined by dividing the total area of ​​the particle attachment in the oil fume duct distribution area by the area of ​​the effective area in the duct, and finally the distribution density of the particle attachment area inside the oil fume duct is obtained.

[0136] Further, step S3 includes the following steps:

[0137] Step S31: performing time series synchronization processing on the corresponding particle suspension distribution change in the particle suspension distribution area inside the oil fume duct and the real-time data of the humidity inside the oil fume duct, so as to obtain the particle suspension distribution change area inside the oil fume duct and the humidity change data inside the oil fume duct in the same time series dimension;

[0138] In an embodiment of the present invention, a time series synchronization method is used to synchronize the corresponding particle suspension distribution changes in the particle suspension distribution area inside the fume duct previously analyzed and the real-time data of humidity inside the fume duct in the order of timestamps, so as to integrate these data into the same time series dimension. By establishing a data model, the change area of ​​the particle suspension distribution is corresponded to the data of humidity change, so as to obtain the particle distribution and humidity change data under the same time scale, ensuring that it can more accurately capture the relationship between the particle distribution and humidity change, and finally obtain the particle suspension distribution change area inside the fume duct and the humidity change data inside the fume duct under the same time series dimension.

[0139] Step S32: performing a particle distribution change flow field simulation analysis on the particle suspension distribution change region inside the oil fume duct in the same time series dimension to obtain a particle suspension distribution change flow simulation field inside the oil fume duct;

[0140] In an embodiment of the present invention, after obtaining the synchronized area of ​​particle suspended distribution change inside the oil fume duct, a fluid dynamics simulation software (such as ANSYS Fluent or OpenFOAM) is used to simulate and analyze the particle distribution flow field, and the synchronized particle suspended distribution position change data is input as the initial condition, the fluid dynamics equations, boundary conditions and physical properties of the particles are set, and the flow field and distribution change of the particles inside the oil fume duct at different time nodes are obtained by calculating the fluid dynamics model. The simulation results will show the dynamic distribution pattern of the particles in the duct, including the aggregation, diffusion and flow trend of the particles during the flow process, and finally the flow simulation field of the particle suspended distribution change inside the oil fume duct is obtained.

[0141] Step S33: Based on the humidity change data inside the oil fume duct in the same time series dimension, a humidity change dynamic impact assessment analysis is performed on the particle suspended distribution change flow simulation field inside the oil fume duct to obtain the dynamic change impact relationship between the humidity change inside the oil fume duct and the particle suspended distribution flow;

[0142] In an embodiment of the present invention, an evaluation and analysis of the dynamic impact of the flow simulation field of the suspended distribution change of particles inside the oil fume duct is performed by combining the internal humidity change data of the oil fume duct obtained after time synchronization, so as to apply the influence relationship of humidity change on the suspended flow behavior of particles, and use the real-time humidity change data as input to evaluate the influence of humidity change on particle distribution and flow pattern, and by setting simulation scenes under different humidity conditions, calculate the attachment and distribution changes of particles in different humidity environments, and use statistical analysis methods to extract the specific impact of humidity change on the particle flow field, thereby forming a dynamic change influence relationship between humidity change and particle distribution flow, and finally obtaining a dynamic change influence relationship between humidity change inside the oil fume duct and particle suspended distribution flow.

[0143] Step S34: Based on the dynamic change influence relationship between the humidity change inside the oil fume duct and the particle suspended distribution flow, the future attachment distribution prediction analysis of the suspended particles inside the oil fume duct corresponding to the suspended distribution change area of ​​the particles inside the oil fume duct is performed to obtain the future attachment distribution position of the suspended particles inside the oil fume duct.

[0144] In an embodiment of the present invention, by combining the dynamic change influence relationship between the humidity change inside the oil fume duct and the particle suspended distribution flow obtained by previous analysis, a predictive modeling tool (such as machine learning algorithm, regression analysis, etc.) is used to predict the attachment distribution position of the suspended particles inside the oil fume duct corresponding to the suspended distribution change area of ​​the particles inside the oil fume duct, so as to input the humidity change trend and the particle flow field simulation results to construct a future particle attachment distribution prediction model, and through learning from historical data, the model will predict the possible attachment position of the particles inside the oil fume duct within a certain time period in the future, thereby generating the attachment area distribution position of the prediction result, and finally obtaining the future attachment distribution position of the suspended particles inside the oil fume duct.

[0145] Further, step S33 includes the following steps:

[0146] The humidity change data inside the oil fume duct under the same time series dimension is subjected to dynamic time series change decomposition processing to obtain the dynamic change sub-data of the humidity inside the oil fume duct in different time series change segments;

[0147] In an embodiment of the present invention, the time series change decomposition processing is performed on the humidity change data inside the oil fume duct in the same time series dimension obtained after time series synchronization by using wavelet transform technology, so as to select an appropriate wavelet basis function (such as Daubechies wavelet) and set the number of decomposition layers, and decompose the data into different time series change segments. Through this process, the long time series trend and short-term fluctuation of the humidity data can be separated, so as to obtain the humidity dynamic change sub-data of different time series change segments. For example, the humidity data of 24 hours a day is analyzed, and the data is decomposed into multiple time series segments such as daily cycle changes, hourly cycle changes and sudden changes, and the characteristic data of each segment is extracted for subsequent analysis, and finally the humidity dynamic change sub-data of the oil fume duct in different time series change segments are obtained.

[0148] Preferably, based on the sub-data of the dynamic change of humidity inside the oil fume duct of different time series change segments, the simulation field of the suspended distribution change flow of particles inside the oil fume duct is subjected to a dynamic coupling analysis of humidity change, so as to obtain a dynamic coupling distribution field between the humidity change inside the oil fume duct and the suspended flow of particles;

[0149] In an embodiment of the present invention, a dynamic coupling analysis of humidity changes is performed on the flow simulation field of the particle suspended distribution change inside the oil fume duct by combining the dynamic change sub-data of the humidity inside the oil fume duct with different time-series change segments obtained by previous analysis. This analysis process is simulated by using Finite Element Analysis (FEA) software, selecting a suitable coupling analysis model (such as a fluid-structure coupling model), inputting humidity change data and the initial conditions of the particle suspended flow, and obtaining the dynamic coupling distribution between humidity changes and the particle suspended flow through computer simulation to determine the specific effect of humidity on the particle suspended distribution inside the duct. For example, when the humidity increases from 60% to 80%, the simulation can show how the increase in humidity causes a change in the deposition rate of the particles and an adjustment in the flow pattern, and finally obtaining a dynamic coupling distribution field between the humidity change inside the oil fume duct and the particle suspended flow.

[0150] Preferably, the dynamic coupling distribution field between the humidity change inside the oil fume duct and the suspended particle flow is analyzed for the influence range of the humidity change coupling, so as to obtain the influence range of the spatial coupling effect between the humidity change inside the oil fume duct and the suspended particle flow;

[0151] In an embodiment of the present invention, a data visualization tool (such as the drawing function of MATLAB) and a spatial analysis method are used to perform a visualization analysis of the coupling influence range of the dynamic coupling distribution field between the humidity change inside the oil fume duct and the suspended particle flow obtained previously through the coupling analysis, so as to visualize the data of the coupling distribution field, draw a spatial distribution diagram of the influence of humidity change on the particle flow, and determine the specific influence range of the spatial coupling effect of humidity change on the suspended particle flow by quantitatively analyzing the influence range. For example, when the humidity increases by 20%, the influence range will expand to the 1-meter area in front and behind the oil fume duct, and finally the influence range of the spatial coupling effect between the humidity change inside the oil fume duct and the suspended particle flow.

[0152] Preferably, the dynamic impact evaluation and analysis of humidity changes on the flow simulation field of suspended particle distribution changes inside the oil fume duct is performed according to the influence range of the spatial coupling effect between the humidity changes inside the oil fume duct and the suspended particle flow, so as to obtain the dynamic change influence relationship between the humidity changes inside the oil fume duct and the suspended particle distribution flow.

[0153] In an embodiment of the present invention, an impact assessment analysis of humidity changes is performed on the corresponding simulation field of suspended particle distribution changes in the oil fume duct by combining the influence range of the spatial coupling effect between the humidity change in the oil fume duct and the suspended particle flow obtained by the previous analysis, so as to establish a dynamic impact assessment model, input the dynamic data of humidity changes into the model, perform dynamic impact assessment analysis, and evaluate the dynamic influence relationship of humidity changes on the suspended particle distribution flow by using a time series analysis method (such as a recursive neural network RNN). Through further processing and analysis of the simulation data, the specific influence degree and trend of humidity changes on the suspended particle distribution flow are obtained. For example, it is analyzed and revealed that an increase in humidity will lead to an increase in the amount of particle deposition in the duct and change the dynamic change influence relationship between the flow paths of the particles, and finally the dynamic change influence relationship between the humidity change in the oil fume duct and the suspended particle distribution flow is obtained.

[0154] Further, step S4 includes the following steps:

[0155] Step S41: based on the particle attachment area distribution density inside the oil fume duct and the future attachment distribution position of the suspended particles inside the oil fume duct, a particle attachment health evaluation calculation formula is used to perform a particle attachment health evaluation calculation on the inside of the oil fume duct to obtain a particle attachment health status score value inside the oil fume duct;

[0156] In an embodiment of the present invention, a suitable particle attachment health evaluation calculation formula is formed by combining the cross-sectional area inside the oil fume duct, the length inside the oil fume duct, the distribution density of the particle attachment area inside the oil fume duct, the future attachment distribution position of the suspended particles inside the oil fume duct, the particle flow rate inside the oil fume duct, the particle attachment tendency coefficient, the particle property constant inside the oil fume duct, the fluid shear stress coefficient, the exponential function, the particle sedimentation threshold velocity, the particle sedimentation velocity standard deviation, the particle sedimentation velocity inside the oil fume duct, the particle attachment activity coefficient, the particle attachment activity adjustment parameter, the particle attachment active number, the initial active number of particles inside the oil fume duct and related parameters to perform a particle attachment health evaluation calculation on the inside of the oil fume duct, so as to quantitatively calculate a health status score value, which reflects the overall health status of the particle attachment inside the oil fume duct, and finally obtains the particle attachment health status score value inside the oil fume duct.

[0157] Step S42: performing health intelligent early warning processing on the corresponding particle adhesion situation inside the oil fume duct based on the health status score value of particle adhesion inside the oil fume duct, and obtaining health early warning information data of particle adhesion inside the oil fume duct;

[0158] In an embodiment of the present invention, a pre-set warning threshold is used to compare the health status score value of particle attachment inside the oil fume duct obtained by previous quantitative calculation. The intelligent warning system determines whether the current particle attachment status exceeds the health standard through the set warning threshold, and performs health intelligent warning processing on the corresponding particle attachment situation inside the oil fume duct according to the score value exceeding the corresponding warning threshold. The corresponding warning information is generated by intelligent warning. The warning information includes a detailed description of the particle attachment situation, the existing health risks of particle attachment and the warning level. The information will be pushed to maintenance personnel through a visual interface or a notification system, and finally the health warning information data of particle attachment inside the oil fume duct is obtained.

[0159] Step S43: performing particle attachment cleaning demand analysis on the health warning information data of particles attached inside the oil fume duct to obtain particle attachment cleaning demand data inside the oil fume duct;

[0160] In an embodiment of the present invention, a data analysis tool is used to evaluate and analyze the particle attachment cleaning needs of the health warning information data of particle attachment inside the oil fume duct previously obtained through warning, so as to evaluate the cleaning needs of the attachment areas inside the oil fume duct. Specifically, the warning information data is input into the analysis model using the data analysis tool. The model calculates the required cleaning degree and priority based on the distribution density of particle attachment, the health score and the working conditions of the pipeline. The cleaning requirement levels of different areas inside the oil fume duct can be determined through the analysis results output by the model, and finally the particle attachment cleaning requirement data inside the oil fume duct can be obtained.

[0161] Step S44: Based on the cleaning demand data of particles attached inside the oil fume duct, a cleaning suggestion analysis is performed on the corresponding particle attachment conditions inside the oil fume duct, and a healthy cleaning suggestion plan for particles attached inside the oil fume duct is generated to perform the corresponding particle cleaning work inside the oil fume duct.

[0162] In an embodiment of the present invention, a cleaning recommendation analysis of particle attachment in the oil fume duct is performed on the corresponding particle attachment situation inside the oil fume duct in combination with the previously determined cleaning requirement data of particle attachment inside the oil fume duct, so as to input the cleaning requirement data into a cleaning recommendation generation system. The system formulates a cleaning plan based on the specific structure of the duct, the type and distribution of attached particles, which includes selecting appropriate cleaning tools, such as high-pressure cleaning equipment or chemical cleaning agents, and their usage methods, frequency and cleaning range. The recommendation plan will generate detailed operating steps and a schedule to ensure the effective removal of particles inside the oil fume duct. The plan will also take into account the actual operating conditions inside the oil fume duct to ensure that normal operation is not affected during the cleaning process. Finally, a corresponding healthy cleaning recommendation plan for particle attachment inside the oil fume duct is generated, which is used to guide cleaning personnel to perform actual cleaning operations.

[0163] Furthermore, the particle attachment health evaluation calculation formula in step S41 is specifically:

[0164] ;

[0165] ;

[0166] ;

[0167] In the formula, is the health status score of particles attached inside the oil fume duct, is the cross-sectional area inside the oil fume duct, is the length of the interior of the oil fume duct, is the distribution density of particle attachment area inside the oil fume duct, The future attachment distribution position of suspended particles inside the oil fume duct. is the particle flow velocity inside the oil fume duct, The particles inside the oil fume duct are located at The particle adhesion tendency coefficient at is the particle property constant inside the oil fume duct, The particles inside the oil fume duct are located at The fluid shear stress coefficient at is an exponential function, The particles inside the oil fume duct are located at The particle settling threshold velocity at is the standard deviation of particle settling velocity, is the particle settling velocity inside the oil fume duct, The particles inside the oil fume duct are located at The particle attachment activity coefficient at Actively adjust parameters for particle attachment, The particles inside the oil fume duct are located at The number of active particles attached at is the initial active number of particles inside the oil fume duct, It is the correction factor for the health status score of particles attached inside the oil fume duct.

[0168] The present invention obtains a particle attachment health evaluation calculation formula by using a specific mathematical model and after verification, which is used to perform particle attachment health evaluation calculation on the inside of the oil fume duct. The particle attachment health evaluation calculation formula can accurately evaluate the attachment health status of particles inside the oil fume duct by considering factors such as particle attachment area distribution density, flow rate, particle attachment tendency coefficient, particle sedimentation threshold velocity, etc. Through careful formula calculation, the particle attachment status at different positions can be deeply analyzed, thereby providing an accurate health score. Parameters in the formula such as flow rate and particle property constant enable the evaluation to reflect changes in actual conditions and provide dynamic health status feedback. Through the health status score value, the areas that need to be cleaned can be better identified, the cleaning work can be optimized, and the work efficiency can be improved. This formula provides a quantitative way to evaluate the particle attachment status inside the oil fume duct. By comprehensively considering factors such as the distribution density of the particle attachment area, the particle flow rate, the attachment tendency coefficient, and the fluid shear stress, the formula can accurately calculate the particle attachment health status score value inside the oil fume duct, which not only helps to monitor and evaluate the cleaning status of the pipeline in real time, but also provides a basis for subsequent health warnings and cleaning demand analysis, thereby realizing targeted cleaning suggestions, thereby improving the efficiency and effectiveness of pipeline maintenance. In summary, this formula fully considers the health status score of particles attached inside the oil fume duct. , the cross-sectional area inside the oil fume duct , the length of the interior of the oil fume duct , the distribution density of particle attachment area inside the oil fume duct , the future attachment distribution position of suspended particles inside the oil fume duct , particle flow rate inside the oil fume duct , the particles inside the oil fume duct are at the position Particle adhesion tendency coefficient at , the particle property constant inside the oil fume duct , the particles inside the oil fume duct are at the position The fluid shear stress coefficient at , exponential function , the particles inside the oil fume duct are at the position Threshold velocity of particle settling at , standard deviation of particle settling velocity , particle settling velocity inside the oil fume duct , the particles inside the oil fume duct are at the position Particle attachment activity coefficient at , particle attachment active adjustment parameters , the particles inside the oil fume duct are at the position The number of active particles attached at , the initial active number of particles inside the oil fume duct , Correction coefficient of health status score of particles attached inside fume duct , where the future attachment distribution position of suspended particles inside the oil fume duct is , particle flow rate inside the oil fume duct , the particle property constant inside the oil fume duct , the particles inside the oil fume duct are at the position The fluid shear stress coefficient at , exponential function , the particles inside the oil fume duct are at the position Threshold velocity of particle settling at and the standard deviation of particle settling velocity It constitutes a kind of oil fume duct internal particles in the position Particle adhesion tendency coefficient at Functional relationship In addition, the future attachment distribution position of suspended particles inside the oil fume duct is also , particle attachment active adjustment parameters , the particles inside the oil fume duct are at the position The number of active particles attached at And the initial active number of particles inside the oil fume duct It constitutes a kind of oil fume duct internal particles in the position Particle attachment activity coefficient at Functional relationship , according to the health status score of particles attached inside the oil fume duct The correlation between the above parameters constitutes a functional relationship This formula can realize the calculation process of the particle attachment health evaluation inside the oil fume duct. At the same time, the correction coefficient of the particle attachment health status score value inside the oil fume duct is The introduction of can be adjusted according to the errors occurring in the calculation process, thereby improving the accuracy and applicability of the particle attachment health evaluation calculation formula.

[0169] Furthermore, the present invention also provides an intelligent evaluation system for particle adhesion characteristics inside a fume duct, which is used to execute the intelligent evaluation method for particle adhesion characteristics inside a fume duct as described above. The intelligent evaluation system for particle adhesion characteristics inside a fume duct comprises:

[0170] The real-time monitoring module for data inside the oil fume duct is used to install a high-resolution particle monitor and a humidity sensor inside the oil fume duct, and use the high-resolution particle monitor and the humidity sensor to monitor the particle distribution image and the humidity of the duct in real time, so as to obtain real-time image data of particle distribution inside the oil fume duct and real-time data of humidity inside the oil fume duct; perform image standardization processing on the real-time image data of particle distribution inside the oil fume duct, so as to obtain standard image data of particle distribution inside the oil fume duct;

[0171] The particle distribution area division and attachment density analysis module is used to divide the particle distribution area of ​​the standard image data of the particle distribution inside the oil fume duct to obtain the particle attachment distribution area inside the oil fume duct and the particle hanging distribution area inside the oil fume duct; perform particle attachment distribution density analysis on the particle attachment distribution area inside the oil fume duct to obtain the particle attachment area distribution density inside the oil fume duct;

[0172] The future attachment distribution prediction module of the particle hanging area is used to perform time-series synchronization processing on the real-time data of the particle hanging distribution area inside the oil fume duct and the humidity inside the oil fume duct, and obtain the particle hanging distribution change area inside the oil fume duct and the humidity change data inside the oil fume duct under the same time-series dimension; based on the humidity change data inside the oil fume duct under the same time-series dimension, the future attachment distribution prediction analysis is performed on the particles hanging inside the oil fume duct corresponding to the particle hanging distribution change area inside the oil fume duct, and the future attachment distribution position of the particles hanging inside the oil fume duct is obtained;

[0173] The particle attachment health evaluation and cleaning suggestion module is used to calculate the particle attachment health evaluation inside the oil fume duct based on the particle attachment area distribution density inside the oil fume duct and the future attachment distribution position of the suspended particles inside the oil fume duct, so as to obtain the particle attachment health status score value inside the oil fume duct; based on the particle attachment health status score value inside the oil fume duct, the health intelligent early warning and cleaning suggestion analysis of the inside of the oil fume duct is performed, and a healthy cleaning suggestion plan for the particle attachment inside the oil fume duct is generated to perform the corresponding particle cleaning work inside the oil fume duct.

[0174] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0175] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. An intelligent evaluation method for particle adhesion characteristics inside a fume duct, characterized in that: The following steps are involved: Step S1: installing a high-resolution particle monitor and a humidity sensor inside the oil fume duct, and using the high-resolution particle monitor and the humidity sensor to perform real-time monitoring of the particle distribution image and the humidity of the duct inside the oil fume duct, thereby obtaining real-time image data of the particle distribution inside the oil fume duct and real-time data of the humidity inside the oil fume duct; performing image standardization processing on the real-time image data of the particle distribution inside the oil fume duct, thereby obtaining standard image data of the particle distribution inside the oil fume duct; Step S2: dividing the particle distribution area of ​​the standard image data of the particle distribution inside the oil fume duct to obtain the particle attachment distribution area inside the oil fume duct and the particle suspension distribution area inside the oil fume duct; performing particle attachment distribution density analysis on the particle attachment distribution area inside the oil fume duct to obtain the particle attachment area distribution density inside the oil fume duct; Step S3: performing time series synchronization processing on the suspended distribution area of ​​particles inside the oil fume duct and the real-time data of humidity inside the oil fume duct to obtain the suspended distribution change area of ​​particles inside the oil fume duct and the humidity change data inside the oil fume duct in the same time series dimension; based on the humidity change data inside the oil fume duct in the same time series dimension, performing future attachment distribution prediction analysis on the suspended particles inside the oil fume duct corresponding to the suspended distribution change area of ​​particles inside the oil fume duct to obtain the future attachment distribution position of the suspended particles inside the oil fume duct; wherein, step S3 includes the following steps: Step S31: performing time series synchronization processing on the corresponding particle suspension distribution change in the particle suspension distribution area inside the oil fume duct and the real-time data of the humidity inside the oil fume duct, so as to obtain the particle suspension distribution change area inside the oil fume duct and the humidity change data inside the oil fume duct in the same time series dimension; Step S32: performing a particle distribution change flow field simulation analysis on the particle suspension distribution change region inside the oil fume duct in the same time series dimension to obtain a particle suspension distribution change flow simulation field inside the oil fume duct; Step S33: Based on the internal humidity change data of the oil fume duct under the same time series dimension, the dynamic impact evaluation and analysis of the humidity change on the flow simulation field of the suspended distribution change of particles in the oil fume duct is performed to obtain the dynamic change influence relationship between the internal humidity change of the oil fume duct and the suspended distribution flow of particles; wherein step S33 includes the following steps: The humidity change data inside the oil fume duct under the same time series dimension is subjected to dynamic time series change decomposition processing to obtain the dynamic change sub-data of the humidity inside the oil fume duct in different time series change segments; Based on the dynamic change sub-data of humidity inside the oil fume duct at different time-series change segments, the dynamic coupling analysis of humidity change on the flow simulation field of particle suspension distribution change inside the oil fume duct is carried out to obtain the dynamic coupling distribution field between humidity change inside the oil fume duct and particle suspension flow; The dynamic coupling distribution field between the humidity change inside the oil fume duct and the suspended particle flow is analyzed to determine the influence range of the spatial coupling effect between the humidity change inside the oil fume duct and the suspended particle flow. According to the influence range of the spatial coupling effect between the humidity change inside the oil fume duct and the particle suspended flow, the dynamic impact evaluation and analysis of the humidity change on the flow simulation field of the particle suspended distribution change inside the oil fume duct is carried out to obtain the dynamic change influence relationship between the humidity change inside the oil fume duct and the particle suspended distribution flow; Step S34: based on the dynamic change influence relationship between the humidity change inside the oil fume duct and the particle suspended distribution flow, the future attachment distribution prediction analysis of the suspended particles inside the oil fume duct corresponding to the suspended distribution change area of ​​the particles inside the oil fume duct is performed to obtain the future attachment distribution position of the suspended particles inside the oil fume duct; Step S4: Based on the distribution density of the particle attachment area inside the oil fume duct and the future attachment distribution position of the suspended particles inside the oil fume duct, a particle attachment health evaluation calculation is performed on the inside of the oil fume duct to obtain a particle attachment health status score value inside the oil fume duct; based on the particle attachment health status score value inside the oil fume duct, a health intelligent early warning and cleaning suggestion analysis is performed on the inside of the oil fume duct, and a healthy cleaning suggestion plan for particle attachment inside the oil fume duct is generated to perform corresponding particle cleaning work inside the oil fume duct.

2. The intelligent evaluation method for particle adhesion characteristics inside the oil fume duct according to claim 1 is characterized in that: Step S1 includes the following steps: Step S11: installing a high-resolution particle monitor and a humidity sensor inside the oil fume duct, and using the high-resolution particle monitor to monitor the particle distribution image inside the oil fume duct in real time, thereby obtaining real-time image data of the particle distribution inside the oil fume duct; Step S12: using a humidity sensor to monitor the humidity inside the oil fume duct in real time, and obtaining real-time humidity data inside the oil fume duct; Step S13: performing image denoising processing on the real-time image data of the particle distribution inside the oil fume duct to obtain denoised image data of the particle distribution inside the oil fume duct; Step S14: performing image contrast enhancement processing on the denoised image data of the particle distribution inside the oil fume duct to obtain contrast enhanced image data of the particle distribution inside the oil fume duct; Step S15: performing image standardization processing on the image contrast enhancement data of the particle distribution inside the oil fume duct to obtain standard image data of the particle distribution inside the oil fume duct.

3. The intelligent evaluation method for particle adhesion characteristics inside a fume duct according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: performing spatial position positioning processing on each particle in the standard image data of particle distribution inside the oil fume duct to obtain the spatial position distribution coordinates of each particle inside the oil fume duct; Step S22: performing 3D corner point extraction processing on the inner wall of the oil fume duct on the standard image data of particle distribution inside the oil fume duct to obtain a set of spatially distributed corner points of the inner wall of the oil fume duct in a 3D state; Step S23: performing three-dimensional spatial reconstruction processing on the standard image data of particle distribution inside the oil fume duct based on the spatial position distribution coordinates of each particle inside the oil fume duct and the spatial distribution corner point set of the inner wall of the oil fume duct in a 3D state, so as to generate a three-dimensional reconstructed spatial model of particle distribution inside the oil fume duct; Step S24: dividing the particle distribution area of ​​the three-dimensional reconstructed spatial model of the particle distribution inside the oil fume duct based on the spatial position distribution coordinates of each particle inside the oil fume duct to obtain the particle attachment distribution area inside the oil fume duct and the particle suspension distribution area inside the oil fume duct; Step S25: performing particle attachment distribution density analysis on the particle attachment distribution area inside the oil fume duct to obtain the particle attachment area distribution density inside the oil fume duct.

4. The intelligent evaluation method for particle adhesion characteristics inside the oil fume duct according to claim 3 is characterized in that: Step S24 includes the following steps: Step S241: performing particle vertical point matching mapping on the inner wall of the oil fume duct in the three-dimensional reconstructed spatial model of particle distribution inside the oil fume duct based on the spatial position distribution coordinates of each particle inside the oil fume duct, so as to obtain the inner wall vertical matching point distribution coordinates corresponding to each particle inside the oil fume duct; Step S242: performing quantitative calculation of the distance between each particle and the inner wall for the spatial position distribution coordinates of each particle inside the oil fume duct and the inner wall vertical matching point distribution coordinates corresponding to each particle inside the oil fume duct, so as to obtain the spatial distribution distance value between each particle inside the oil fume duct and the inner wall of the oil fume duct; Step S243: comparing and judging the spatial distribution distance value between each particle inside the oil fume duct and the inner wall of the oil fume duct according to the preset oil fume duct internal particle attachment distance threshold, when the spatial distribution distance value is less than or equal to the preset oil fume duct internal particle attachment distance threshold, the corresponding particle in the three-dimensional reconstruction space model of the oil fume duct internal particle distribution is determined as the oil fume duct internal particle attachment particle point; when the spatial distribution distance value is greater than the preset oil fume duct internal particle attachment distance threshold, the corresponding particle in the three-dimensional reconstruction space model of the oil fume duct internal particle distribution is determined as the oil fume duct suspended particle point; Step S244: connecting and dividing the attachment distribution area of ​​each particle corresponding to the three-dimensional reconstructed spatial model of particle distribution inside the oil fume duct based on the particle attachment point of the oil fume duct, so as to obtain the particle attachment distribution area inside the oil fume duct; Step S245: based on the suspended particle points of the oil fume duct, the suspended distribution area of ​​each particle corresponding to the three-dimensional reconstructed spatial model of particle distribution inside the oil fume duct is connected and divided to obtain the suspended distribution area of ​​particles inside the oil fume duct.

5. The intelligent evaluation method for particle adhesion characteristics inside the oil fume duct according to claim 3 is characterized in that: Step S25 includes the following steps: Step S251: performing a statistical analysis on the number of particles attached to the distribution area of ​​particles inside the oil fume duct to obtain the number of particles attached to the distribution area inside the oil fume duct; Step S252: performing particle contour shape recognition analysis on the particle attachment distribution area inside the oil fume duct to obtain the particle attachment contour shape size in the distribution area inside the oil fume duct; Step S253: based on the number of particles attached in the distribution area inside the oil fume duct and the size of the particle attachment contour in the distribution area inside the oil fume duct, the particle attachment area corresponding to each particle in the particle attachment distribution area inside the oil fume duct is calculated to obtain the total particle attachment area size in the area inside the oil fume duct; Step S254: performing particle attachment distribution density analysis on the particle attachment distribution area inside the oil fume duct based on the total particle attachment area size inside the oil fume duct to obtain the particle attachment area distribution density inside the oil fume duct.

6. The intelligent evaluation method for particle adhesion characteristics inside a fume duct according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: based on the particle attachment area distribution density inside the oil fume duct and the future attachment distribution position of the suspended particles inside the oil fume duct, a particle attachment health evaluation calculation formula is used to perform a particle attachment health evaluation calculation on the inside of the oil fume duct to obtain a particle attachment health status score value inside the oil fume duct; Step S42: performing health intelligent early warning processing on the corresponding particle adhesion situation inside the oil fume duct based on the health status score value of particle adhesion inside the oil fume duct, and obtaining health early warning information data of particle adhesion inside the oil fume duct; Step S43: performing particle attachment cleaning demand analysis on the health warning information data of particles attached inside the oil fume duct to obtain particle attachment cleaning demand data inside the oil fume duct; Step S44: Based on the cleaning demand data of particles attached inside the oil fume duct, a cleaning suggestion analysis is performed on the corresponding particle attachment conditions inside the oil fume duct, and a healthy cleaning suggestion plan for particles attached inside the oil fume duct is generated to perform the corresponding particle cleaning work inside the oil fume duct.

7. The intelligent evaluation method for particle adhesion characteristics inside a fume duct according to claim 6, characterized in that: The particle attachment health evaluation calculation formula in step S41 is specifically: ； ； ； In the formula, is the health status score of particles attached inside the oil fume duct, is the cross-sectional area inside the oil fume duct, is the length of the interior of the oil fume duct, is the distribution density of particle attachment area inside the oil fume duct, The future attachment distribution position of suspended particles inside the oil fume duct. is the particle flow velocity inside the oil fume duct, The particles inside the oil fume duct are located at The particle adhesion tendency coefficient at is the particle property constant inside the oil fume duct, The particles inside the oil fume duct are located at The fluid shear stress coefficient at is an exponential function, The particles inside the oil fume duct are located at The particle settling threshold velocity at is the standard deviation of particle settling velocity, is the particle settling velocity inside the oil fume duct, The particles inside the oil fume duct are located at The particle attachment activity coefficient at Actively adjust parameters for particle attachment, The particles inside the oil fume duct are located at The number of active particles attached at is the initial active number of particles inside the oil fume duct, It is the correction factor for the health status score of particles attached inside the oil fume duct.

8. An intelligent evaluation system for particle adhesion characteristics inside a fume duct, characterized in that: The method for intelligently evaluating the particle adhesion characteristics inside the oil fume duct according to claim 1 is used to execute the method, wherein the particle adhesion characteristics intelligent evaluation system inside the oil fume duct comprises: The real-time monitoring module for data inside the oil fume duct is used to install a high-resolution particle monitor and a humidity sensor inside the oil fume duct, and use the high-resolution particle monitor and the humidity sensor to monitor the particle distribution image and the humidity of the duct in real time, so as to obtain real-time image data of particle distribution inside the oil fume duct and real-time data of humidity inside the oil fume duct; perform image standardization processing on the real-time image data of particle distribution inside the oil fume duct, so as to obtain standard image data of particle distribution inside the oil fume duct; The particle distribution area division and attachment density analysis module is used to divide the particle distribution area of ​​the standard image data of the particle distribution inside the oil fume duct to obtain the particle attachment distribution area inside the oil fume duct and the particle hanging distribution area inside the oil fume duct; perform particle attachment distribution density analysis on the particle attachment distribution area inside the oil fume duct to obtain the particle attachment area distribution density inside the oil fume duct; The future attachment distribution prediction module of the particle hanging area is used to perform time-series synchronization processing on the real-time data of the particle hanging distribution area inside the oil fume duct and the humidity inside the oil fume duct, and obtain the particle hanging distribution change area inside the oil fume duct and the humidity change data inside the oil fume duct under the same time-series dimension; based on the humidity change data inside the oil fume duct under the same time-series dimension, the future attachment distribution prediction analysis is performed on the particles hanging inside the oil fume duct corresponding to the particle hanging distribution change area inside the oil fume duct, and the future attachment distribution position of the particles hanging inside the oil fume duct is obtained; The particle attachment health evaluation and cleaning suggestion module is used to calculate the particle attachment health evaluation inside the oil fume duct based on the particle attachment area distribution density inside the oil fume duct and the future attachment distribution position of the suspended particles inside the oil fume duct, so as to obtain the particle attachment health status score value inside the oil fume duct; based on the particle attachment health status score value inside the oil fume duct, the health intelligent early warning and cleaning suggestion analysis of the inside of the oil fume duct is performed, and a healthy cleaning suggestion plan for the particle attachment inside the oil fume duct is generated to perform the corresponding particle cleaning work inside the oil fume duct.

Images