Waste engine oil treatment monitoring method and system based on machine vision

Abstract

The invention is applicable to the technical field of waste engine oil treatment, and provides a waste engine oil treatment monitoring method and system based on machine vision, and the method comprises the following steps: when a treatment container receives waste engine oil, determining a target viscosity characteristic of the waste engine oil, obtaining initial heat treatment parameters set for the target viscosity characteristic, and meanwhile, obtaining a historical treatment record of the treatment container, and determining a predetermined cleaning cycle of the processing container. The influence of gradual increase of the pollution degree of the inner wall of the treatment container in the cleaning cycle progress on the adhesiveness of the waste engine oil and the influence of the pollution degree change of the waste engine oil on the heat treatment process are fully considered. The system dynamically adjusts treatment parameters by monitoring and analyzing the pollution condition of the inner wall of the treatment container and the pollution degree of the waste engine oil in real time, and it is ensured that the waste engine oil treatment process can adapt to the changes.

Description

Technical Field

[0001] The present invention belongs to the technical field of waste oil treatment, and particularly relates to a waste oil treatment monitoring method and system based on machine vision. Background Art

[0002] In the existing waste oil treatment technologies, the treatment of waste oil usually relies on static setting of treatment parameters. These treatment parameters such as temperature, pressure, and time are usually fixed and cannot be adjusted in real time according to the actual characteristics of the waste oil or the degree of contamination of the treatment container. Traditional methods usually adopt unified treatment parameters, and regardless of the degree of contamination of the waste oil, the treatment process often proceeds under preset conditions. Although this "unified treatment" method can ensure the treatment of waste oil to a certain extent, it often ignores the changes in the degree of contamination of the waste oil and the inner wall of the treatment container, resulting in insufficiently refined and efficient treatment effects.

[0003] Especially during the waste oil treatment process, the contamination of the inner wall of the treatment container gradually increases with the passage of the cleaning cycle, and the adhesiveness of the waste oil also increases accordingly. However, the existing technologies have not been able to effectively respond to this change, and the heat treatment parameters during the treatment process remain unchanged all the time, unable to make corresponding adjustments to the change in the adhesiveness of the waste oil. The increasing inner wall contamination not only affects the treatment efficiency of the waste oil, but may also lead to incomplete treatment of the waste oil and even damage the equipment performance. At the same time, the change in the degree of contamination of the waste oil has an important impact on the treatment effect. The existing methods cannot dynamically adjust the treatment parameters according to the specific contamination situation of the waste oil, resulting in energy waste and unstable treatment quality.

[0004] Therefore, the traditional waste oil treatment technologies have problems such as low treatment efficiency, high energy consumption, serious equipment wear, and unstable treatment effects. They fail to fully consider the changes in the adhesiveness and degree of contamination of the waste oil, resulting in an inflexible treatment process and inability to optimize according to different treatment conditions. These problems have accumulated technical defects in the waste oil treatment process, and there is an urgent need for a new waste oil treatment method that can monitor in real time and dynamically adjust treatment parameters to adapt to the changes in the degree of contamination of the waste oil and the inner wall of the treatment container, thereby improving the treatment efficiency and quality of the waste oil and extending the service life of the equipment. Summary of the Invention

[0005] The purpose of the present invention is to provide a waste oil treatment monitoring method and system based on machine vision, aiming to solve the problems proposed in the background art.

[0006] The present invention is implemented as follows. A waste oil treatment monitoring method based on machine vision, the method includes:

[0007] When the processing container receives waste engine oil, determine the target viscosity characteristics of the waste engine oil, and obtain the initial heat treatment parameters set for it. At the same time, obtain the historical processing records of the processing container and determine the predetermined cleaning cycle of the processing container;

[0008] Intelligently analyze the historical processing records, screen out the sub-processing records consistent with the target viscosity characteristics of the waste engine oil, and determine the target cleaning cycle containing the most such sub-processing records;

[0009] Based on machine vision technology, analyze the adhesion degree values of the waste engine oil on the inner wall of the processing container in each sub-processing record within the target cleaning cycle, and generate an adhesion degree curve that changes with time progress according to these adhesion degree values of the waste engine oil. Calculate the average slope of the adhesion degree curve and use it as the first optimization coefficient;

[0010] Based on machine vision technology, evaluate the current pollution degree value of the waste engine oil, determine the standard pollution degree threshold corresponding to the waste engine oil with target viscosity characteristics, and use the deviation value between it and the current pollution degree value as the second optimization coefficient;

[0011] Based on the first optimization coefficient and the second optimization coefficient, dynamically adjust the initial heat treatment parameters.

[0012] As a further limitation of the technical solution of the embodiment of the present invention, the target cleaning cycle should only include the relevant processing records of processing waste engine oil that meets the target viscosity characteristics.

[0013] As a further limitation of the technical solution of the embodiment of the present invention, the step of, based on machine vision technology, analyzing the adhesion degree values of the waste engine oil on the inner wall of the processing container in each sub-processing record within the target cleaning cycle, and generating an adhesion degree curve that changes with time progress according to these adhesion degree values of the waste engine oil, calculating the average slope of the adhesion degree curve, and using it as the first optimization coefficient includes:

[0014] According to the historical processing records, obtain the inner wall images of the processing container corresponding to each sub-processing record within the target cleaning cycle, and use machine vision technology to intelligently analyze each inner wall image to determine the adhesion degree value of the waste engine oil in the corresponding sub-processing record;

[0015] According to the time stamp of each inner wall image, combine the corresponding adhesion degree value of the waste engine oil to generate an adhesion degree curve that changes with time;

[0016] Calculate the average slope of the adhesion degree curve and use it as the first optimization coefficient.

[0017] As a further limitation of the technical solution of the embodiment of the present invention, the steps of evaluating the current pollution degree value of waste oil based on machine vision technology, determining the standard pollution degree threshold corresponding to the waste oil with the target viscosity characteristic, and using the deviation value between it and the current pollution degree value as the second optimization coefficient include:

[0018] Evaluating the current pollution degree of waste oil using machine vision technology;

[0019] Retrieving a preset reference model, extracting the standard pollution degree threshold corresponding to the target viscosity characteristic, calculating the deviation value between the current pollution degree value and the standard pollution degree threshold, and using this deviation value as the second optimization coefficient;

[0020] The reference model refers to a preset standard pollution degree evaluation model established based on historical data and processing experience of different waste oil viscosity characteristics and pollution degrees. This reference model includes the pollution degree thresholds that waste oil with different viscosity characteristics can be effectively received by the processing container.

[0021] As a further limitation of the technical solution of the embodiment of the present invention, the steps of dynamically adjusting the initial heat treatment parameters based on the first optimization coefficient and the second optimization coefficient include:

[0022] Retrieving a preset parameter optimization formula, and dynamically adjusting the initial heat treatment parameters in combination with the first optimization coefficient and the second optimization coefficient to obtain optimized heat treatment parameters;

[0023] Applying the optimized heat treatment parameters to the process of the processing container for treating the current waste oil.

[0024] As a further limitation of the technical solution of the embodiment of the present invention, the parameter optimization formula is: , where T optimized refers to the initial heat treatment parameter, T initial refers to the optimized heat treatment parameter, S refers to the average slope of the adhesion degree curve, that is, the first optimization coefficient, W1 refers to the corresponding adjustment weight of the first optimization coefficient, refers to the deviation value between the current pollution degree value and the standard pollution degree threshold, that is, the second optimization coefficient, W2 refers to the corresponding adjustment weight of the second optimization coefficient.

[0025] A waste oil treatment monitoring system based on machine vision, the system includes: a data acquisition module, a target cleaning cycle determination module, a first optimization coefficient generation module, a second optimization coefficient generation module, and a heat treatment parameter optimization module, where:

[0026] A data acquisition module, which is used to determine the target viscosity characteristics of waste oil when a processing container receives waste oil, obtain the set initial heat treatment parameters for it, and at the same time, obtain the historical processing records of the processing container and determine the predetermined cleaning cycle of the processing container;

[0027] A target cleaning cycle determination module, which is used to intelligently analyze the historical processing records, screen out the sub-processing records consistent with the target viscosity characteristics of the waste oil, and determine the target cleaning cycle containing the most such sub-processing records. Only the relevant processing records of processing waste oil meeting the target viscosity characteristics should be included in the target cleaning cycle;

[0028] A first optimization coefficient generation module, which is used to analyze the waste oil adhesion degree values on the inner wall of the processing container in each sub-processing record within the target cleaning cycle based on machine vision technology, and generate an adhesion degree curve that changes with time according to these waste oil adhesion degree values, calculate the average slope of the adhesion degree curve, and use it as the first optimization coefficient;

[0029] A second optimization coefficient generation module, which is used to evaluate the current pollution degree value of the waste oil based on machine vision technology, determine the standard pollution degree threshold corresponding to the waste oil with target viscosity characteristics, and use the deviation value between it and the current pollution degree value as the second optimization coefficient;

[0030] A heat treatment parameter optimization module, which is used to dynamically adjust the initial heat treatment parameters based on the first optimization coefficient and the second optimization coefficient.

[0031] As a further limitation of the technical solution of the embodiment of the present invention, the steps of the first optimization coefficient generation module specifically include:

[0032] An adhesion degree value determination unit, which is used to obtain the inner wall image of the processing container corresponding to each sub-processing record within the target cleaning cycle according to the historical processing records, and use machine vision technology to intelligently analyze each inner wall image to determine the waste oil adhesion degree value in the corresponding sub-processing record;

[0033] An adhesion degree curve generation unit, which is used to generate an adhesion degree curve that changes with time according to the time stamp of each inner wall image and the corresponding waste oil adhesion degree value;

[0034] An average slope calculation unit, which is used to calculate the average slope of the adhesion degree curve and use it as the first optimization coefficient.

[0035] As a further limitation of the technical solution of the embodiment of the present invention, the steps of the second optimization coefficient generation module specifically include:

[0036] A current pollution degree evaluation unit, which is used to evaluate the current pollution degree of the waste oil by using machine vision technology;

[0037] A deviation value calculation unit is configured to retrieve a preset reference model, extract a standard pollution degree threshold corresponding to the target viscosity characteristic, calculate the deviation value between the current pollution degree value and the standard pollution degree threshold, and use this deviation value as the second optimization coefficient;

[0038] The reference model refers to a preset standard pollution degree evaluation model established based on historical data and processing experience of different waste engine oil viscosity characteristics and pollution degrees. This reference model includes the pollution degree thresholds that waste engine oil with different viscosity characteristics can be effectively accepted by the processing container.

[0039] As a further limitation of the technical solution of the embodiment of the present invention, the heat treatment parameter optimization module specifically includes:

[0040] A heat treatment parameter optimization unit is configured to retrieve a preset parameter optimization formula and dynamically adjust the initial heat treatment parameters in combination with the first optimization coefficient and the second optimization coefficient to obtain optimized heat treatment parameters;

[0041] An optimized parameter application unit is configured to apply the optimized heat treatment parameters to the process of the processing container for treating the current waste engine oil;

[0042] The parameter optimization formula is: , where T optimized refers to the initial heat treatment parameter, T initial refers to the optimized heat treatment parameter, S refers to the average slope of the adhesion degree curve, that is, the first optimization coefficient, W1 refers to the corresponding adjustment weight of the first optimization coefficient, refers to the deviation value between the current pollution degree value and the standard pollution degree threshold, that is, the second optimization coefficient, W2 refers to the corresponding adjustment weight of the second optimization coefficient.

[0043] Compared with the prior art, the present invention has the following beneficial effects:

[0044] The present invention fully considers the influence of the gradually increasing pollution degree of the inner wall of the processing container on the adhesion of waste engine oil during the cleaning cycle progress, and the influence of the change in the pollution degree of waste engine oil on the heat treatment process. The system dynamically adjusts the processing parameters by real-time monitoring and analyzing the pollution condition of the inner wall of the processing container and the pollution degree of waste engine oil to ensure that the waste engine oil treatment process can adapt to these changes. Specifically, as the inner wall pollution gradually increases, the adhesion of waste engine oil increases, and the system automatically optimizes the heat treatment parameters to prevent the excessive influence of inner wall pollution on the waste engine oil treatment efficiency. At the same time, the system also adjusts the processing parameters according to the pollution degree of waste engine oil to ensure that the treatment process is always in the best state.

[0045] This dynamic adjustment mechanism solves the deficiency in traditional methods that fails to fully consider the changes in inner wall contamination and waste oil contamination, avoids a one-size-fits-all approach, and improves the processing efficiency and quality. Through this mechanism, the waste oil treatment process can be continuously optimized, not only reducing energy consumption but also extending the service life of the equipment. In addition, the synergy between the treatment container and the waste oil is fully utilized, and the treatment effect is more precise and efficient, providing an important technical guarantee for the efficient and environmentally friendly treatment of waste oil. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 is a flowchart of the method provided by an embodiment of the present invention;

[0047] Figure 2 is a flowchart of generating a first optimization coefficient in the method provided by an embodiment of the present invention;

[0048] Figure 3 is a flowchart of generating a second optimization coefficient in the method provided by an embodiment of the present invention;

[0049] Figure 4 is a flowchart of optimizing and adjusting the initial heat treatment parameters in the method provided by an embodiment of the present invention;

[0050] Figure 5 is an application architecture diagram of the system provided by an embodiment of the present invention;

[0051] Figure 6 is a structural block diagram of a first optimization coefficient generation module in the system provided by an embodiment of the present invention;

[0052] Figure 7 is a structural block diagram of a second optimization coefficient generation module in the system provided by an embodiment of the present invention;

[0053] Figure 8 is a structural block diagram of a heat treatment parameter optimization module in the system provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0054] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0055] Figure 1 shows a flowchart of the method provided by an embodiment of the present invention.

[0056] Specifically, a method for monitoring the treatment of waste oil based on machine vision, the method specifically includes the following steps:

[0057] Step S100, when the processing container receives waste oil, determine the target viscosity characteristics of the waste oil, obtain the initial heat treatment parameters set for it, and at the same time, obtain the historical processing records of the processing container and determine the predetermined cleaning cycle of the processing container.

[0058] In the embodiments of the present invention, the processing container refers to a device specifically used for waste oil treatment in the present invention, and generally includes various industrial devices capable of heating, filtering, and decomposing waste oil. The design goal of these containers is to efficiently and safely treat waste oil so that it meets the standards before being recycled or further processed. The structure of the processing container usually includes an inner wall, a heating system, a discharge system, etc., to ensure that the waste oil can be evenly heated and processed during the heat treatment process.

[0059] The target viscosity characteristics of waste oil can be determined by various methods. Common technical means include viscosity measurement and rheological analysis. By measuring the fluidity of waste oil, its viscosity characteristics can be obtained, and then the processing process can be adjusted according to the specific viscosity requirements of the waste oil. For example, common devices such as rotational viscometers and capillary viscometers can help obtain the viscosity data of waste oil. In addition, the viscosity characteristics of waste oil can also be comprehensively judged in combination with its component analysis, such as the type of oil product, impurity content, etc.

[0060] The initial heat treatment parameters refer to a set of starting treatment conditions set during the waste oil treatment process. These conditions are crucial for the subsequent treatment process. The initial heat treatment parameters include heating temperature, heating time, heating rate, etc., which affect the thermal decomposition effect of waste oil and the pollutant removal efficiency. Common prior art means may involve setting these parameters based on the preliminary analysis results of waste oil, and may be achieved through empirical data or through computational models for automated setting.

[0061] The historical processing records of the processing container include multiple aspects, mainly detailed records of the previous waste oil treatment process. These records can include the starting characteristics of the waste oil (such as viscosity, degree of pollution), specific operations during the heat treatment process (such as temperature changes, treatment time, heating rate, etc.), the treatment effect of the waste oil after treatment (such as viscosity changes, pollutant removal conditions, etc.), and the history of cleaning and maintenance (such as container cleaning cycle, cleaning method, cleaning effect, etc.). These data help to optimize the waste oil treatment process based on historical experience and data analysis.

[0062] The predetermined cleaning cycle refers to the regular cleaning operation cycle that the processing container needs to perform after a certain period of time or number of processing times. This is usually set by the equipment manufacturer or the user according to the equipment operation conditions and cleaning effects. In the prior art, the predetermined cleaning cycle is applied in many industrial equipment, especially those that require regular maintenance. The cleaning cycle is usually set based on the equipment usage frequency, pollutant accumulation, and equipment operation efficiency.

[0063] Furthermore, the machine vision-based waste oil treatment monitoring method further includes the following steps:

[0064] Step S200, intelligently analyze the historical processing records, screen out the sub-processing records that are consistent with the target viscosity characteristics of the waste oil, and determine the target cleaning cycle that contains the most such sub-processing records. Only the relevant processing records of treating waste oil that meets the target viscosity characteristics should be included within the target cleaning cycle.

[0065] In the embodiment of the present invention, the purpose of screening out the cleaning cycle that contains the most such sub-processing records as the target cleaning cycle is to find the cycle that is most stable and effective when treating similar waste oil (i.e., having the same or similar viscosity characteristics) through historical data. The selection of the cleaning cycle is based on the analysis of data in the historical records to find the time period with the best treatment effect in the past processing. This can improve the consistency and efficiency of the processing and ensure that each treatment within the cleaning cycle can achieve the optimal effect.

[0066] The significance of "only the relevant processing records of treating waste oil that meets the target viscosity characteristics should be included within the target cleaning cycle" is that the viscosity characteristics of the waste oil have an important impact on its treatment effect. Different viscosity characteristics of waste oil may require different treatment parameters or technologies to achieve the ideal cleaning effect. Therefore, limiting the treatment of waste oil that meets the target viscosity characteristics within the target cleaning cycle can avoid data errors caused by mixing the processing records of other different viscosity waste oils, thereby ensuring that the parameter adjustment is consistent with the waste oil type and improving the accuracy and efficiency of the final processing process.

[0067] Furthermore, the machine vision-based waste oil treatment monitoring method further includes the following steps:

[0068] Step S300, based on machine vision technology, analyze the waste oil adhesion degree values on the inner wall of the processing container in each sub-processing record within the target cleaning cycle, and generate an adhesion degree curve that changes with time progress based on these waste oil adhesion degree values. Calculate the average slope of the adhesion degree curve and use it as the first optimization coefficient.

[0069] Specifically, Figure 2 The flowchart showing the generation of the first optimization coefficient is shown.

[0070] Among them, based on machine vision technology, analyze the adhesion degree value of waste engine oil on the inner wall of the processing container in each sub - processing record within the target cleaning cycle, and based on these adhesion degree values of waste engine oil, generate an adhesion degree curve that changes with the progress of time, calculate the average slope of the adhesion degree curve, and use it as the first optimization coefficient, which specifically includes the following steps:

[0071] Step S301: According to the historical processing records, obtain the images of the inner wall of the processing container corresponding to each sub - processing record within the target cleaning cycle, and use machine vision technology to perform intelligent analysis on each inner wall image to determine the adhesion degree value of waste engine oil in the corresponding sub - processing record;

[0072] Step S302: According to the time stamp of each inner wall image, combined with the corresponding adhesion degree value of waste engine oil, generate an adhesion degree curve that changes with time;

[0073] Step S303: Calculate the average slope of the adhesion degree curve and use it as the first optimization coefficient.

[0074] In the embodiment of the present invention, machine vision technology is used to perform intelligent analysis on each inner wall image to determine the adhesion degree value of waste engine oil in the corresponding sub - processing record. The specific implementation method is to analyze the image of the inner wall of the processing container through image recognition and image processing technologies. In the prior art, image segmentation and edge detection algorithms are usually used to identify the residual situation of waste engine oil in the image. For example, using deep learning models such as convolutional neural networks (CNNs) to train and classify images can accurately identify the adhesion layer of waste engine oil. By extracting and analyzing the pixel values of the waste engine oil area in the inner wall image, combined with the clarity of the image, lighting conditions, and the material of the inner wall of the processing container, machine vision technology can evaluate the adhesion degree of waste engine oil on the inner wall of the container in real time. The key to this method is to identify the adhesion degree through the intelligent processing of image data, so as to provide accurate input data for the subsequent optimization of heat treatment parameters.

[0075] The generation of the adhesion degree curve is of great significance. It reflects the change of the adhesion of waste engine oil on the inner wall of the processing container. As the processing progresses, the adhesion degree of waste engine oil will change. Through continuous images and adhesion degree data on the time axis, a curve reflecting this change trend can be generated. The adhesion degree curve helps to evaluate the interaction between waste engine oil and the inner wall of the container, as well as the removal effect of waste engine oil during the heat treatment process. By analyzing this curve, it is possible to provide an intuitive data basis for optimizing heat treatment parameters and ensure that the heat treatment process is more efficient and accurate.

[0076] The significance of taking the average slope of the adhesion degree curve as the first optimization coefficient is that the average slope can objectively reflect the change rate of the adhesion degree of waste engine oil. The larger the slope, the more rapid the change in the adhesion of waste engine oil on the inner wall of the container, and more efficient treatment means may be required. By calculating the average slope of the adhesion degree curve, the change trend of the waste engine oil removal effect can be quantified, providing a data basis for the dynamic adjustment of the heat treatment parameters. As an optimization coefficient, the first optimization coefficient dynamically adjusts the parameters in the heat treatment process through the change of this value, so as to achieve more precise treatment of waste engine oil and improve the equipment efficiency and treatment quality.

[0077] Further, the machine vision-based waste engine oil treatment monitoring method further includes the following steps:

[0078] Step S400, evaluate the current pollution degree value of the waste engine oil based on machine vision technology, determine the standard pollution degree threshold corresponding to the waste engine oil with the target viscosity characteristic, and take the deviation value between it and the current pollution degree value as the second optimization coefficient.

[0079] Specifically, Figure 3 The flowchart for generating the second optimization coefficient is shown.

[0080] Among them, evaluating the current pollution degree value of the waste engine oil based on machine vision technology, determining the standard pollution degree threshold corresponding to the waste engine oil with the target viscosity characteristic, and taking the deviation value between it and the current pollution degree value as the second optimization coefficient specifically includes the following steps:

[0081] Step S401, evaluate the current pollution degree of the waste engine oil using machine vision technology;

[0082] Step S402, retrieve the preset reference model, extract the standard pollution degree threshold corresponding to the target viscosity characteristic, calculate the deviation value between the current pollution degree value and the standard pollution degree threshold, and take this deviation value as the second optimization coefficient.

[0083] The reference model refers to a standard pollution degree evaluation model established in advance based on historical data and treatment experience of different waste engine oil viscosity characteristics and pollution degrees. This reference model contains the pollution degree thresholds that waste engine oil with different viscosity characteristics can be effectively accepted by the treatment container.

[0084] In the embodiment of the present invention, the step of "using machine vision technology to evaluate the current contamination level of waste oil" is usually implemented by combining image analysis and sensor data. Specifically, machine vision technology can collect image data of waste oil in real time through camera equipment, and use image processing algorithms (such as edge detection, color segmentation, texture analysis, etc.) to evaluate the status of waste oil. These images can show the distribution of impurities, sediments, and pollutants in the waste oil, and determine its contamination level through intelligent algorithms.

[0085] In the existing technology, image features are usually compared with known pollution standards. For example, the presence of pollutants can be detected by color differences, or the degree of pollution can be determined by the size and distribution pattern of particles in the image. In addition, the concentration of suspended matter in waste oil can be evaluated by combining spectral analysis and laser scanning with machine vision technology to further quantify the degree of pollution. The combination of these technical means enables machine vision to effectively evaluate the pollution status of waste oil and determine its current degree of pollution.

[0086] The degree of contamination is selected as the secondary direction because the degree of contamination directly affects the treatment efficiency and quality of waste oil, especially when the waste oil contains more impurities, which may lead to increased adhesion to the inner wall during the treatment process, thereby affecting the working state of the treatment container. The degree of adhesion to the inner wall is closely related to the degree of contamination. Waste oil with heavier contamination tends to accumulate more easily on the inner wall of the container, increasing the difficulty of cleaning. Therefore, evaluating the degree of contamination of waste oil is a key step in evaluating the effectiveness of the entire treatment process. It can provide a more comprehensive feedback, help dynamically adjust the treatment parameters, and optimize the entire treatment process.

[0087] The reference model in the present invention refers to a standard contamination level assessment model, which is established based on a large amount of historical data and processing experience, and is used to quantify the contamination level threshold under different waste oil viscosity characteristics. By analyzing the treatment effects of waste oils with different viscosity characteristics, the reference model determines the contamination level threshold at which various types of waste oil can be effectively accepted in the processing container. The core of this model is that it can provide a standardized contamination level limit to help determine whether the waste oil is within the treatable range or needs further adjustment.

[0088] Taking the deviation value as the second optimization coefficient is of great significance. The deviation value represents the difference between the current pollution degree of waste engine oil and the standard pollution degree threshold. By calculating this deviation value, the degree of excess or deficiency of the pollution degree of waste engine oil relative to the standard threshold can be quantified, which provides a reference basis for subsequent adjustment of heat treatment parameters. If the deviation value is large, it indicates a high pollution degree of waste engine oil, and stronger heat treatment parameters may be required; if the deviation value is small, it means a low pollution degree, and the heat treatment intensity can be correspondingly reduced, thus saving energy and avoiding over-treatment. Therefore, the second optimization coefficient (i.e., the deviation value) can help adjust the heat treatment parameters more precisely to adapt to waste engine oil with different pollution degrees, improving the treatment effect and treatment efficiency.

[0089] Further, the waste engine oil treatment monitoring method based on machine vision further includes the following steps:

[0090] Step S500, dynamically adjust the initial heat treatment parameters based on the first optimization coefficient and the second optimization coefficient.

[0091] Specifically, Figure 4 The flowchart showing the optimized adjustment of the initial heat treatment parameters is shown.

[0092] Among them, dynamically adjusting the initial heat treatment parameters based on the first optimization coefficient and the second optimization coefficient specifically includes the following steps:

[0093] Step S501, retrieve the preset parameter optimization formula, and dynamically adjust the initial heat treatment parameters in combination with the first optimization coefficient and the second optimization coefficient to obtain the optimized heat treatment parameters;

[0094] Step S502, apply the optimized heat treatment parameters to the process of treating the current waste engine oil in the treatment container.

[0095] The parameter optimization formula is: , where T optimized refers to the initial heat treatment parameter, T initial refers to the optimized heat treatment parameter, S refers to the average slope of the adhesion degree curve, that is, the first optimization coefficient, W1 refers to the corresponding adjustment weight of the first optimization coefficient, refers to the deviation value between the current pollution degree value and the standard pollution degree threshold, that is, the second optimization coefficient, W2 refers to the corresponding adjustment weight of the second optimization coefficient.

[0096] In the embodiments of the present invention, the significance of dynamically adjusting the initial heat treatment parameters by combining the first optimization coefficient and the second optimization coefficient lies in that they can comprehensively evaluate multiple key factors in the waste oil treatment process starting from different characteristics of the waste oil, thereby achieving precise adjustment of heat treatment parameters. In the prior art, the waste oil treatment process usually relies on fixed treatment parameters and is difficult to cope with the complexity of different types of waste oil, resulting in unstable treatment effects. Especially when the characteristics such as the pollution degree and viscosity of the waste oil change greatly, the influence on the treatment parameters is often not fully considered.

[0097] In the present invention, the first optimization coefficient reflects how the waste oil interacts with the inner wall of the treatment container during the treatment process by analyzing the adhesion degree of the waste oil on the inner wall of the treatment container. The change in the adhesion degree directly affects the treatment efficiency. Therefore, the first optimization coefficient helps to optimize the heat treatment parameters, especially in the adjustment of temperature and treatment time, by calculating the average slope of the adhesion degree curve. If the adhesion degree is high, it may be necessary to increase the temperature or extend the treatment time to reduce the adhesion of the oil product to the inner wall.

[0098] The second optimization coefficient is adjusted based on the deviation between the pollution degree of the waste oil and the standard pollution degree, which reflects the actual difference in the pollution degree of the waste oil. When the pollution degree of the waste oil is low, the deviation from the standard pollution degree threshold is negative, indicating that the oil product is cleaner and may have a lower adhesion degree to the inner wall of the container. Thus, the initial heat treatment parameters can be appropriately weakened (such as reducing the temperature or shortening the treatment time). On the contrary, when the pollution degree is high, the deviation value is positive, meaning that the oil product is relatively dirty and it may be necessary to increase the heat treatment intensity to improve the treatment effect.

[0099] By combining the first optimization coefficient and the second optimization coefficient, the system can comprehensively evaluate the treatment requirements of the waste oil from two dimensions: on the one hand, considering the adhesion degree of the waste oil to the inner wall of the treatment container, and on the other hand, considering its pollution degree. This correlation makes the adjustment of heat treatment parameters more refined, can be automatically adapted during the treatment process of different types of waste oil, and thus achieves a more efficient and energy-saving treatment effect.

[0100] In summary, the present invention takes into account the influence of the gradual increase in the pollution degree of the inner wall of the treatment container on the adhesion of the waste oil as the cleaning cycle progresses, and also considers the influence of the change in the pollution degree of the waste oil on the heat treatment process. By dynamically adjusting the treatment parameters, the system can optimize the treatment process according to the changes in the inner wall pollution and the pollution degree of the waste oil. This dynamic adjustment mechanism can ensure that the waste oil treatment process always remains in the optimal state, thus avoiding the problems in the traditional treatment method that fail to effectively cope with the changes in the inner wall pollution and the pollution degree of the waste oil, improving the waste oil treatment efficiency and treatment quality, and ensuring that the synergistic effect of the treatment container and the waste oil is fully exerted.

[0101] Furthermore, Figure 5 The application architecture diagram of the system provided by the embodiment of the present invention is shown.

[0102] Among them, in another preferred embodiment provided by the present invention, a waste oil treatment monitoring system based on machine vision includes:

[0103] A data acquisition module 100, configured to determine the target viscosity characteristics of waste oil when a processing container receives waste oil, obtain the set initial heat treatment parameters for it, and at the same time, obtain the historical processing records of the processing container and determine the predetermined cleaning cycle of the processing container.

[0104] In the embodiment of the present invention, the processing container refers to a device specifically used for waste oil treatment in the present invention, and generally includes various industrial devices capable of heating, filtering, and decomposing waste oil. The design goal of these containers is to efficiently and safely process waste oil so that it meets the standards before being recycled or further processed. The structure of the processing container usually includes an inner wall, a heating system, a discharge system, etc., to ensure that the waste oil can be evenly heated and processed during the heat treatment process.

[0105] The target viscosity characteristics of waste oil can be determined by various methods. Common technical means include viscosity measurement and rheological analysis. By measuring the fluidity of waste oil, its viscosity characteristics can be obtained, and then the processing process can be adjusted according to the specific viscosity requirements of waste oil. For example, common devices such as rotational viscometers and capillary viscometers can help obtain the viscosity data of waste oil. In addition, the viscosity characteristics of waste oil can also be comprehensively judged in combination with its component analysis, such as the type of oil product, impurity content, etc.

[0106] The initial heat treatment parameters refer to a set of starting treatment conditions set during the waste oil treatment process, and these conditions are crucial for the subsequent treatment process. The initial heat treatment parameters include heating temperature, heating time, heating rate, etc., which affect the thermal decomposition effect of waste oil and the pollutant removal efficiency. Common existing technical means may involve setting these parameters based on the preliminary analysis results of waste oil, and may be achieved through empirical data or through calculation models for automatic setting.

[0107] The historical processing records of the processing container include multiple aspects, mainly the detailed records of the previous waste oil treatment process. These records can include the initial characteristics of waste oil (such as viscosity, pollution degree), specific operations during the heat treatment process (such as temperature change, processing time, heating rate, etc.), the treatment effect of the waste oil after treatment (such as viscosity change, pollutant removal situation, etc.), and the history of cleaning and maintenance (such as container cleaning cycle, cleaning method, cleaning effect, etc.). These data help to optimize the waste oil treatment process based on historical experience and data analysis.

[0108] The predetermined cleaning cycle refers to the regular cleaning operation cycle that the processing container needs to perform after a certain period of time or number of processing times. This is usually set by the equipment manufacturer or the user according to the equipment operation conditions and cleaning effects. In the prior art, the predetermined cleaning cycle is applied in many industrial equipment, especially those that require regular maintenance. The cleaning cycle is usually set based on the equipment usage frequency, pollutant accumulation, and equipment operation efficiency.

[0109] Furthermore, the machine vision-based waste oil treatment monitoring system further includes:

[0110] A target cleaning cycle determination module 200, configured to intelligently analyze historical processing records, screen out sub-processing records that are consistent with the target viscosity characteristics of the waste oil, and determine the target cleaning cycle that contains the most such sub-processing records. Only the relevant processing records of treating waste oil that meets the target viscosity characteristics should be included within the target cleaning cycle.

[0111] In the embodiment of the present invention, the purpose of screening out the cleaning cycle that contains the most such sub-processing records as the target cleaning cycle is to find the cycle that is most stable and effective when treating similar waste oil (i.e., having the same or similar viscosity characteristics) through historical data. The selection of the cleaning cycle is based on the analysis of data in historical records to find the time period with the best treatment effect in past processing. This can improve the consistency and efficiency of processing and ensure that each treatment within the cleaning cycle can achieve the optimal effect.

[0112] The significance of "only the relevant processing records of treating waste oil that meets the target viscosity characteristics should be included within the target cleaning cycle" is that the viscosity characteristics of waste oil have an important impact on its treatment effect. Waste oil with different viscosity characteristics may require different treatment parameters or technologies to achieve the ideal cleaning effect. Therefore, limiting the treatment of waste oil that meets the target viscosity characteristics within the target cleaning cycle can avoid data errors caused by mixing the processing records of other different viscosity waste oils, thereby ensuring that the parameter adjustment is consistent with the waste oil type and improving the accuracy and efficiency of the final processing process.

[0113] Furthermore, the machine vision-based waste oil treatment monitoring system further includes:

[0114] A first optimization coefficient generation module 300, configured to analyze the waste oil adhesion degree values on the inner wall of the processing container in each sub-processing record within the target cleaning cycle based on machine vision technology, generate an adhesion degree curve that changes with time progress according to these waste oil adhesion degree values, calculate the average slope of the adhesion degree curve, and use it as the first optimization coefficient.

[0115] Specifically, Figure 6The block diagram of the first optimization coefficient generation module 300 in the system provided by the embodiments of the present invention is shown.

[0116] Among them, in the preferred embodiment provided by the present invention, the first optimization coefficient generation module 300 specifically includes:

[0117] The adhesion degree value determination unit 301 is configured to obtain the inner wall image of the processing container corresponding to each sub-processing record within the target cleaning period according to the historical processing records, and use machine vision technology to perform intelligent analysis on each inner wall image to determine the waste oil adhesion degree value in the corresponding sub-processing record;

[0118] The adhesion degree curve generation unit 302 is configured to generate an adhesion degree curve that changes with time according to the time stamp of each inner wall image and in combination with the corresponding waste oil adhesion degree value;

[0119] The average slope calculation unit 303 is configured to calculate the average slope of the adhesion degree curve and use it as the first optimization coefficient.

[0120] In the embodiments of the present invention, machine vision technology is used to perform intelligent analysis on each inner wall image to determine the waste oil adhesion degree value in the corresponding sub-processing record. The specific implementation method is to analyze the image of the inner wall of the processing container through image recognition and image processing technologies. In the prior art, image segmentation and edge detection algorithms are usually used to identify the waste oil residue situation in the image. For example, by using deep learning models such as convolutional neural networks (CNNs) to train and classify images, the adhesion layer of waste oil can be accurately identified. By extracting and analyzing the pixel values of the waste oil area in the inner wall image and combining the clarity of the image, the lighting conditions and the material of the inner wall of the processing container, machine vision technology can real-time evaluate the adhesion degree of waste oil on the inner wall of the container. The key to this method is to identify the adhesion degree through the intelligent processing of image data, so as to provide accurate input data for the subsequent optimization of heat treatment parameters.

[0121] The generation of the adhesion degree curve is of great significance. It reflects the change of the adhesion of waste oil on the inner wall of the processing container. As the processing progresses, the adhesion degree of waste oil will change. Through the continuous images and adhesion degree data on the time axis, a curve reflecting this change trend can be generated. The adhesion degree curve helps to evaluate the interaction between waste oil and the inner wall of the container, as well as the removal effect of waste oil during the heat treatment process. By analyzing this curve, intuitive data basis can be provided for optimizing heat treatment parameters to ensure that the heat treatment process is more efficient and accurate.

[0122] The significance of taking the average slope of the adhesion degree curve as the first optimization coefficient is that the average slope can objectively reflect the change rate of the adhesion degree of waste engine oil. The larger the slope, the more rapid the change in the adhesion of waste engine oil to the inner wall of the container, and more efficient treatment means may be required. By calculating the average slope of the adhesion degree curve, the change trend of the removal effect of waste engine oil can be quantified, providing a data basis for the dynamic adjustment of heat treatment parameters. As an optimization coefficient, the first optimization coefficient dynamically adjusts the parameters in the heat treatment process through the change of this value, so as to achieve more precise treatment of waste engine oil and improve the equipment efficiency and treatment quality.

[0123] Furthermore, the waste engine oil treatment monitoring system based on machine vision further includes:

[0124] A second optimization coefficient generation module 400, configured to evaluate the current pollution degree value of waste engine oil based on machine vision technology, determine the standard pollution degree threshold corresponding to the waste engine oil with the target viscosity characteristic, and use the deviation value between it and the current pollution degree value as the second optimization coefficient.

[0125] Specifically, Figure 7 The structure block diagram of the second optimization coefficient generation module 400 in the system provided by the embodiment of the present invention is shown.

[0126] Among them, in the preferred embodiment provided by the present invention, the second optimization coefficient generation module 400 specifically includes:

[0127] A current pollution degree evaluation unit 401, configured to evaluate the current pollution degree of waste engine oil by using machine vision technology;

[0128] A deviation value calculation unit 402, configured to retrieve a preset reference model, extract the standard pollution degree threshold corresponding to the target viscosity characteristic, calculate the deviation value between the current pollution degree value and the standard pollution degree threshold, and use this deviation value as the second optimization coefficient.

[0129] The reference model refers to a standard pollution degree evaluation model established in advance based on historical data and processing experience of different waste engine oil viscosity characteristics and pollution degrees. This reference model includes the pollution degree thresholds that waste engine oil with different viscosity characteristics can be effectively accepted by the treatment container.

[0130] In the embodiment of the present invention, the step of "using machine vision technology to evaluate the current contamination level of waste oil" is usually implemented by combining image analysis and sensor data. Specifically, machine vision technology can collect image data of waste oil in real time through camera equipment, and use image processing algorithms (such as edge detection, color segmentation, texture analysis, etc.) to evaluate the status of waste oil. These images can show the distribution of impurities, sediments, and pollutants in the waste oil, and determine its contamination level through intelligent algorithms.

[0131] In the existing technology, image features are usually compared with known pollution standards. For example, the presence of pollutants can be detected by color differences, or the degree of pollution can be determined by the size and distribution pattern of particles in the image. In addition, the concentration of suspended matter in waste oil can be evaluated by combining spectral analysis and laser scanning with machine vision technology to further quantify the degree of pollution. The combination of these technical means enables machine vision to effectively evaluate the pollution status of waste oil and determine its current degree of pollution.

[0132] The degree of contamination is selected as the secondary direction because the degree of contamination directly affects the treatment efficiency and quality of waste oil, especially when the waste oil contains more impurities, which may lead to increased adhesion to the inner wall during the treatment process, thereby affecting the working state of the treatment container. The degree of adhesion to the inner wall is closely related to the degree of contamination. Waste oil with heavier contamination tends to accumulate more easily on the inner wall of the container, increasing the difficulty of cleaning. Therefore, evaluating the degree of contamination of waste oil is a key step in evaluating the effectiveness of the entire treatment process. It can provide a more comprehensive feedback, help dynamically adjust the treatment parameters, and optimize the entire treatment process.

[0133] The reference model in the present invention refers to a standard contamination level assessment model, which is established based on a large amount of historical data and processing experience, and is used to quantify the contamination level threshold under different waste oil viscosity characteristics. By analyzing the treatment effects of waste oils with different viscosity characteristics, the reference model determines the contamination level threshold at which various types of waste oil can be effectively accepted in the processing container. The core of this model is that it can provide a standardized contamination level limit to help determine whether the waste oil is within the treatable range or needs further adjustment.

[0134] Taking the deviation value as the second optimization coefficient is of great significance. The deviation value represents the difference between the current pollution degree of waste oil and the standard pollution degree threshold. By calculating this deviation value, the degree of excess or deficiency of the pollution degree of waste oil relative to the standard threshold can be quantified, which provides a reference basis for subsequent adjustment of heat treatment parameters. If the deviation value is large, it indicates that the pollution degree of waste oil is high, and stronger heat treatment parameters may be required; if the deviation value is small, it means that the pollution degree is low, and the heat treatment intensity can be correspondingly reduced, thus saving energy and avoiding over-treatment. Therefore, the second optimization coefficient (i.e., the deviation value) can help adjust the heat treatment parameters more precisely to adapt to waste oil with different pollution degrees, improving the treatment effect and treatment efficiency.

[0135] Furthermore, the waste oil treatment monitoring system based on machine vision further includes:

[0136] A heat treatment parameter optimization module 500, configured to dynamically adjust the initial heat treatment parameters based on the first optimization coefficient and the second optimization coefficient.

[0137] Specifically, Figure 8 FIG. shows the structural block diagram of the heat treatment parameter optimization module 500 in the system provided by the embodiment of the present invention.

[0138] Among them, in the preferred embodiment provided by the present invention, the heat treatment parameter optimization module 500 specifically includes:

[0139] A heat treatment parameter optimization unit 501, configured to retrieve a preset parameter optimization formula and dynamically adjust the initial heat treatment parameters in combination with the first optimization coefficient and the second optimization coefficient to obtain optimized heat treatment parameters;

[0140] An optimized parameter application unit 502, configured to apply the optimized heat treatment parameters to the process of treating the current waste oil in the treatment container.

[0141] The parameter optimization formula is: , where T optimized refers to the initial heat treatment parameter, T initial refers to the optimized heat treatment parameter, S refers to the average slope of the adhesion degree curve, that is, the first optimization coefficient, W1 refers to the corresponding adjustment weight of the first optimization coefficient, refers to the deviation value between the current pollution degree value and the standard pollution degree threshold, that is, the second optimization coefficient, and W2 refers to the corresponding adjustment weight of the second optimization coefficient.

[0142] In the embodiments of the present invention, the significance of dynamically adjusting the initial heat treatment parameters by combining the first optimization coefficient and the second optimization coefficient lies in that they can comprehensively evaluate multiple key factors in the waste oil treatment process starting from different characteristics of the waste oil, thereby achieving precise adjustment of heat treatment parameters. In the prior art, the waste oil treatment process usually relies on fixed treatment parameters and is difficult to cope with the complexity of different types of waste oil, resulting in unstable treatment effects. Especially when the characteristics of waste oil such as pollution degree and viscosity change greatly, the impact on treatment parameters is often not fully considered.

[0143] In the present invention, the first optimization coefficient reflects how the waste oil interacts with the inner wall of the treatment container during the treatment process by analyzing the adhesion degree of the waste oil on the inner wall of the treatment container. The change in the adhesion degree directly affects the treatment efficiency. Therefore, the first optimization coefficient helps to optimize the heat treatment parameters, especially in the adjustment of temperature and treatment time, by calculating the average slope of the adhesion degree curve. If the adhesion degree is high, it may be necessary to increase the temperature or extend the treatment time to reduce the adhesion of the oil product to the inner wall.

[0144] The second optimization coefficient is adjusted based on the deviation between the pollution degree of the waste oil and the standard pollution degree, which reflects the actual difference in the pollution degree of the waste oil. When the pollution degree of the waste oil is low, the deviation from the standard pollution degree threshold is negative, indicating that the oil product is "cleaner" and the adhesion degree to the inner wall of the container may be lower, and thus the initial heat treatment parameters can be appropriately weakened (such as reducing the temperature or shortening the treatment time). On the contrary, when the pollution degree is high, the deviation value is positive, meaning that the oil product is relatively dirty and it may be necessary to increase the heat treatment intensity to improve the treatment effect.

[0145] By combining the first optimization coefficient and the second optimization coefficient, the system can comprehensively evaluate the treatment requirements of the waste oil from two dimensions: on the one hand, considering the adhesion degree of the waste oil to the inner wall of the treatment container, and on the other hand, considering its pollution degree. This correlation makes the adjustment of heat treatment parameters more refined, can be automatically adapted during the treatment process of different types of waste oil, and thus achieves a more efficient and energy-saving treatment effect.

[0146] In summary, the present invention takes into account the impact of the gradual increase in the pollution degree of the inner wall of the treatment container on the adhesion of waste oil as the cleaning cycle progresses, and also considers the impact of the change in the pollution degree of the waste oil on the heat treatment process. By dynamically adjusting the treatment parameters, the system can optimize the treatment process according to the changes in the inner wall pollution and the pollution degree of the waste oil. This dynamic adjustment mechanism can ensure that the waste oil treatment process always remains in the optimal state, thereby avoiding the problems in the traditional treatment method that fail to effectively cope with the changes in the inner wall pollution and the pollution degree of the waste oil, improving the waste oil treatment efficiency and treatment quality, and ensuring that the synergistic effect of the treatment container and the waste oil is fully exerted.

[0147] It should be understood that although the steps in the flowcharts of the embodiments of the present invention are shown sequentially as indicated by the arrows, these steps are not necessarily executed sequentially in the order indicated by the arrows. Unless there is a clear indication in this article, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in each embodiment may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0148] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or an external cache. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0149] The technical features of the above-described embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the various technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0150] The above-described embodiments merely represent several implementation manners of the present invention. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the patent for the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all fall within the protection scope of the present invention. Therefore, the protection scope of the patent for the present invention shall be subject to the appended claims.

[0151] The foregoing is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A waste oil treatment monitoring method based on machine vision, characterized in that, The method includes: When the processing container receives waste engine oil, determine the target viscosity characteristics of the waste engine oil, and obtain the initial heat treatment parameters set for it. At the same time, obtain the historical processing records of the processing container and determine the predetermined cleaning cycle of the processing container; Intelligently analyze the historical processing records, screen out the sub-processing records consistent with the target viscosity characteristics of the waste engine oil, and determine the target cleaning cycle containing the most such sub-processing records; Based on machine vision technology, analyze the waste engine oil adhesion degree values on the inner wall of the processing container in each sub-processing record within the target cleaning cycle, and generate an adhesion degree curve that changes with time progress based on these waste engine oil adhesion degree values. Calculate the average slope of the adhesion degree curve and use it as the first optimization coefficient; Evaluate the current pollution degree value of the waste engine oil based on machine vision technology, determine the standard pollution degree threshold corresponding to the waste engine oil with target viscosity characteristics, and use the deviation value between it and the current pollution degree value as the second optimization coefficient; Dynamically adjust the initial heat treatment parameters based on the first optimization coefficient and the second optimization coefficient.

2. The machine vision-based waste oil treatment monitoring method according to claim 1, wherein The target cleaning cycle should only include the relevant processing records of processing waste engine oil that meets the target viscosity characteristics.

3. The machine vision-based waste oil treatment monitoring method according to claim 1, characterized in that, The step of, based on machine vision technology, analyzing the waste engine oil adhesion degree values on the inner wall of the processing container in each sub-processing record within the target cleaning cycle, and generating an adhesion degree curve that changes with time progress based on these waste engine oil adhesion degree values, calculating the average slope of the adhesion degree curve and using it as the first optimization coefficient includes: According to the historical processing records, obtain the inner wall images of the processing container corresponding to each sub-processing record within the target cleaning cycle, and use machine vision technology to intelligently analyze each inner wall image to determine the waste engine oil adhesion degree value in the corresponding sub-processing record; Generate an adhesion degree curve that changes with time based on the time stamp of each inner wall image and the corresponding waste engine oil adhesion degree value; Calculate the average slope of the adhesion degree curve and use it as the first optimization coefficient.

4. The machine vision-based waste oil treatment monitoring method according to claim 1, characterized in that, The step of, based on machine vision technology, evaluating the current pollution degree value of the waste engine oil, determining the standard pollution degree threshold corresponding to the waste engine oil with target viscosity characteristics, and using the deviation value between it and the current pollution degree value as the second optimization coefficient includes: Evaluate the current pollution degree of the waste engine oil using machine vision technology; Retrieve the preset reference model, extract the standard pollution degree threshold corresponding to the target viscosity characteristics, calculate the deviation value between the current pollution degree value and the standard pollution degree threshold, and use this deviation value as the second optimization coefficient; The reference model refers to a preset standard pollution degree evaluation model established based on historical data and processing experience of different waste engine oil viscosity characteristics and pollution degrees. This reference model contains the pollution degree thresholds that waste engine oil with different viscosity characteristics can be effectively received by the processing container.

5. The machine vision-based waste oil treatment monitoring method according to claim 1, characterized in that, The step of dynamically adjusting the initial heat treatment parameters based on the first optimization coefficient and the second optimization coefficient includes: Retrieve the preset parameter optimization formula, and dynamically adjust the initial heat treatment parameters in combination with the first optimization coefficient and the second optimization coefficient to obtain the optimized heat treatment parameters; Apply the optimized heat treatment parameters to the process of the processing container for processing the current waste engine oil.

6. The machine vision-based waste oil treatment monitoring method according to claim 5, wherein The parameter optimization formula is as follows: , where T optimized refers to the initial heat treatment parameter, and T initial refers to the optimized heat treatment parameter. S refers to the average slope of the adhesion degree curve, i.e., the first optimization coefficient, and W1 refers to the corresponding adjustment weight of the first optimization coefficient. refers to the deviation value between the current pollution degree value and the standard pollution degree threshold, i.e., the second optimization coefficient, and W2 refers to the corresponding adjustment weight of the second optimization coefficient.

7. A waste engine oil treatment monitoring system based on machine vision, characterized in that, The system includes: a data acquisition module, a target cleaning cycle determination module, a first optimization coefficient generation module, a second optimization coefficient generation module, and a heat treatment parameter optimization module, where: The data acquisition module is used to determine the target viscosity characteristics of waste oil when the processing container receives waste oil, obtain the initial heat treatment parameters set for it, and at the same time, obtain the historical processing records of the processing container and determine the predetermined cleaning cycle of the processing container; The target cleaning cycle determination module is used to intelligently analyze the historical processing records, filter out the sub-processing records consistent with the target viscosity characteristics of waste oil, and determine the target cleaning cycle containing the most such sub-processing records. Only the relevant processing records of processing waste oil meeting the target viscosity characteristics should be included within the target cleaning cycle; The first optimization coefficient generation module is used to analyze the waste oil adhesion degree values on the inner wall of the processing container in each sub-processing record within the target cleaning cycle based on machine vision technology, generate an adhesion degree curve that changes with time according to these waste oil adhesion degree values, calculate the average slope of the adhesion degree curve, and use it as the first optimization coefficient; The second optimization coefficient generation module is used to evaluate the current pollution degree value of waste oil based on machine vision technology, determine the standard pollution degree threshold corresponding to waste oil with target viscosity characteristics, and use the deviation value between it and the current pollution degree value as the second optimization coefficient; The heat treatment parameter optimization module is used to dynamically adjust the initial heat treatment parameters based on the first optimization coefficient and the second optimization coefficient.

8. The machine vision-based waste oil treatment monitoring system according to claim 7, characterized in that, The steps of the first optimization coefficient generation module specifically include: The adhesion degree value determination unit is used to obtain the inner wall image of the processing container corresponding to each sub-processing record within the target cleaning cycle according to the historical processing records, and use machine vision technology to intelligently analyze each inner wall image to determine the waste oil adhesion degree value in the corresponding sub-processing record; The adhesion degree curve generation unit is used to generate an adhesion degree curve that changes with time according to the time stamp of each inner wall image and the corresponding waste oil adhesion degree value; The average slope calculation unit is used to calculate the average slope of the adhesion degree curve and use it as the first optimization coefficient.

9. The machine vision-based waste oil treatment monitoring system according to claim 8, characterized in that, The steps of the second optimization coefficient generation module specifically include: The current pollution degree evaluation unit is used to evaluate the current pollution degree of waste oil based on machine vision technology; The deviation value calculation unit is used to retrieve the preset reference model, extract the standard pollution degree threshold corresponding to the target viscosity characteristics, calculate the deviation value between the current pollution degree value and the standard pollution degree threshold, and use this deviation value as the second optimization coefficient; The reference model refers to a preset standard pollution degree evaluation model established based on historical data and processing experience of different waste oil viscosity characteristics and pollution degrees. This reference model includes the pollution degree thresholds that waste oil with different viscosity characteristics can be effectively received by the processing container.

10. The machine vision-based waste oil treatment monitoring system according to claim 9, wherein, The heat treatment parameter optimization module specifically includes: The heat treatment parameter optimization unit is used to retrieve the preset parameter optimization formula and dynamically adjust the initial heat treatment parameters in combination with the first optimization coefficient and the second optimization coefficient to obtain the optimized heat treatment parameters; Optimized parameter application unit, which is used to apply the optimized heat treatment parameters to the process of treating the current waste engine oil in the treatment container; The parameter optimization formula is as follows: , where T optimized refers to the initial heat treatment parameter, and T initial refers to the optimized heat treatment parameter. S refers to the average slope of the adhesion degree curve, i.e., the first optimization coefficient. W1 refers to the corresponding adjustment weight of the first optimization coefficient. refers to the deviation value between the current pollution degree value and the standard pollution degree threshold, i.e., the second optimization coefficient. W2 refers to the corresponding adjustment weight of the second optimization coefficient.

Images