Sensor-based lubricating oil sampling quality evaluation method and system

Abstract

This application relates to a sensor-based method and system for evaluating the quality of lubricating oil samples. The method includes: acquiring intermediate product quality characteristic information from multiple key processing stages in the production of recycled lubricating oil, wherein the key processing stages include at least a deep dehydration stage, a vacuum distillation stage, a combined refining stage, and a final blending stage; importing the quality characteristic information into preset judgment and processing rules for analysis, and evaluating the quality status of the intermediate products at each of the key processing stages based on the analysis results, wherein the judgment and processing rules define the acceptable range, warning range, and unacceptable range of the quality characteristics; when the analysis results indicate that the quality status of the intermediate product deviates from the acceptable range, generating warning information and generating suggestions for adjusting process parameters. This invention achieves real-time feedback on the quality of multiple key processing stages of recycled lubricating oil, ultimately achieving stable quality of recycled lubricating oil products.

Description

Technical Field

[0001] This application relates to the field of lubricating oil production quality control technology, and in particular to a sensor-based lubricating oil sampling quality assessment method and system. Background Technology

[0002] The production process of lubricating oil, especially recycled lubricating oil, is a sophisticated and complex chemical process. This process involves multiple key chemical conversion and purification steps, and the effectiveness of each step directly determines the quality grade and performance of the final product. A typical production process for recycled lubricating oil begins with the pretreatment of waste oil feedstock, followed by core processing units such as deep dehydration, vacuum distillation, combined refining, and final blending. The core function of each unit is to gradually remove moisture from the feedstock, separate different fractions, and deeply purify the oil, thereby ensuring the stability of the recycled base oil's composition, purity, and final performance. Therefore, effectively evaluating the quality formation process throughout the entire production process, especially the core refining stage, is crucial to ensuring the quality of recycled lubricating oil products.

[0003] However, the current quality inspection methods used in the production of recycled lubricating oil have significant flaws. Quality assessment heavily relies on offline laboratory testing after all final products have been manufactured, making the entire production process a "black box." Specifically, existing quality monitoring models cannot provide real-time, online quantitative evaluation of the effectiveness of core chemical conversion and purification processes such as deep dehydration and combined refining. This makes it difficult for production managers to promptly grasp the immediate quality indicators of intermediate products at the exit points of each key process.

[0004] The aforementioned "black box" quality monitoring model has brought about many negative impacts: on the one hand, there is a significant lag in quality feedback, and when laboratory tests find that the final product quality does not meet the standards, it is impossible to quickly locate the specific process and root cause of the problem; on the other hand, the adjustment of process parameters lacks real-time data support, and it is difficult to optimize process parameters in a timely manner based on the quality changes of intermediate products during the production process, which leads to low production efficiency and insufficient product quality stability, seriously restricting the process upgrading and quality improvement of the recycled lubricating oil production industry.

[0005] In summary, there is an urgent need for a method in the current production process of recycled lubricating oil that can effectively and in real time evaluate the quality of the entire production process, especially the core refining stage, in order to solve the technical pain points of the existing quality monitoring model, such as feedback lag, difficulty in tracing the root cause, and lack of basis for parameter adjustment, and improve production efficiency and product quality stability. Summary of the Invention

[0006] This application provides a sensor-based method and system for evaluating the quality of lubricating oil sampling, which at least solves the problems of lagging quality monitoring, lack of real-time basis for process parameter adjustment, and difficulty in tracing the root cause of problems in the production process of recycled lubricating oil in related technologies.

[0007] In a first aspect, this application provides a sensor-based method for evaluating the quality of lubricating oil samples, comprising the following steps: The intermediate product quality characteristics information of multiple key processing steps in the production of recycled lubricating oil is obtained, wherein the key processing steps include at least a deep dehydration step, a vacuum distillation step, a combined refining step, and a final blending step; The quality characteristic information is imported into a preset judgment and processing rule for analysis. The intermediate product quality status of each key processing step is evaluated based on the analysis results. The judgment and processing rule defines the qualified range, warning range and unqualified range of the quality characteristics. When the analysis results indicate that the quality status of the intermediate product deviates from the acceptable range, a warning message is generated, and suggestions for adjusting process parameters are generated.

[0008] Optionally, when the analysis results indicate that the quality status of the intermediate product deviates from the acceptable range, a warning message is generated, and suggestions for adjusting process parameters are generated, including: Establish a process influence correlation map, wherein the process influence correlation map describes the influence relationship between key process parameters and intermediate product quality indicators in subsequent processes; When the quality characteristic information of a downstream process deviates from the center value of the normal operating range to the warning range, the quality characteristic information of the downstream process is marked as a potential quality deviation. Initiate a reverse tracing mechanism to deduce the upstream process parameters or steps that caused the potential quality deviation based on the potential quality deviation. Retrieve and analyze real-time or recent historical data of upstream process parameters to find the root cause of abnormal fluctuations that match the potential quality deviations. Based on the abnormal fluctuations in the root cause, a root cause diagnosis report is generated, which indicates the abnormal fluctuations in the root cause and their impact on downstream quality deviations, and provides targeted corrective action recommendations.

[0009] Optionally, the step of generating a warning message and generating suggestions for adjusting process parameters when the analysis results indicate that the quality status of the intermediate product deviates from the acceptable range further includes: Obtain the current operating constraints information of the production line; When multiple quality indicators are identified to deviate from the acceptable range simultaneously, adjustment suggestions that may cause conflicts are sorted according to preset process optimization priority rules. Evaluate the impact of the proposed adjustments after sorting on the operational constraints; Based on the preset process parameter linkage rules, a set of conflict-free comprehensive adjustment suggestions is generated. Calculate the expected effect and potential impact on the operational constraints for each comprehensive adjustment suggestion in the comprehensive adjustment suggestion set; Select the comprehensive adjustment recommendation that yields the best expected results and does not violate the operational constraints, and use it as the final adjustment instruction.

[0010] Optionally, marking the quality characteristic information of the downstream process as a potential quality deviation when it deviates from the center value of the normal operating range to a warning range includes: Obtain quality characteristic information from multiple downstream processes; Calculate the degree of deviation between the quality characteristic information of multiple downstream processes and the center value of their respective normal operating ranges; Based on preset process influence correlation rules, identify the process correlation between the quality feature information; Calculate the combined deviation index of multiple quality characteristics that are process-related; When the combined deviation index exceeds the preset combined warning threshold, the quality characteristic information of the associated downstream process is collaboratively marked as a potential quality deviation.

[0011] Optionally, the step of marking the quality characteristic information of the downstream process as a potential quality deviation when the quality characteristic information of the downstream process deviates from the center value of the normal operating range to the warning range further includes: The quality characteristic information is obtained as a change feature within a continuous time window, the change feature including the rate of change, fluctuation amplitude and duration; Based on the aforementioned change characteristics, deviation patterns of the quality characteristic information are identified, wherein the deviation patterns include cumulative deviation patterns, periodic deviation patterns, and sudden deviation patterns; When the deviation mode is a cumulative deviation mode, the warning threshold is dynamically lowered and the deviation duration requirement is extended. When the deviation lasts for more than a certain period of time, the quality characteristic information is marked as a potential quality deviation. When the deviation pattern is a periodic deviation pattern, a larger deviation amplitude is allowed at the peak or trough of the periodic fluctuation. When the amplitude and frequency of the fluctuation exceed the range of normal periodic fluctuation, the quality characteristic information is marked as a potential quality deviation. When the deviation mode is a sudden deviation mode, an early warning is immediately triggered and the deviation duration requirement is shortened. When the deviation amplitude reaches a preset value, the quality characteristic information is marked as a potential quality deviation.

[0012] Optionally, the step of marking the quality characteristic information of the downstream process as a potential quality deviation when the deviation of the quality characteristic information of the downstream process from the center value of the normal operating range reaches the warning level further includes: Obtain multiple key attribute information of the current batch of waste oil raw materials, wherein the key attribute information includes raw material source, initial pollutant content and pretreatment parameters; Based on the key attribute information, retrieve historical batch data that matches the attributes of the current batch of waste oil from the preset raw material batch feature library; Based on the historical batch data, calculate the center value of the normal operating range corresponding to the quality characteristic information of the current batch of waste oil raw materials in each downstream process; Continuously monitor the quality characteristic information of each downstream process and compare it with the calculated center value; When the quality characteristic information deviates from the calculated center value to the level of a warning, the quality characteristic information is marked as a potential quality deviation.

[0013] Optionally, marking the quality feature information as a potential quality deviation when the deviation from the calculated center value reaches a warning level includes: Obtain the current operating status information of the production line, wherein the operating status information includes equipment operating time, ambient temperature, and operator shifts; Based on the operating condition information, retrieve historical operating data that matches the current operating condition from a preset operating condition feature library; Based on the historical operating data, calculate the quality warning threshold corresponding to the quality characteristic information of each downstream process under the current operating conditions; The quality characteristic information of each downstream process is continuously monitored and compared with the calculated center value. When the quality characteristic information deviates from the calculated center value to the quality warning threshold, the quality characteristic information is marked as a potential quality deviation.

[0014] Optionally, the step of generating a warning message and generating suggestions for adjusting process parameters when the analysis results indicate that the quality status of the intermediate product deviates from the acceptable range further includes: Obtain the dependencies and order requirements among the multiple process parameter adjustment suggestions; Based on the dependencies and the order requirements, construct and adjust the suggested execution path; Assess the impact of each adjustment step in the proposed adjustment path on the quality characteristic information of subsequent processes; When the evaluation results indicate that there are adjustment steps in the proposed adjustment path that cause negative impacts, the proposed adjustment path is optimized to eliminate the negative impacts, and the optimized proposed adjustment sequence is used as the final adjustment instruction.

[0015] Secondly, this application provides a sensor-based lubricating oil sampling quality assessment system, the system comprising: The information acquisition module is used to acquire intermediate product quality characteristic information of multiple key processing steps in the production process of recycled lubricating oil, wherein the key processing steps include at least a deep dehydration step, a vacuum distillation step, a combined refining step, and a final blending step. The information transmission module is used to import the quality characteristic information into a preset judgment and processing rule for analysis, and to evaluate the intermediate product quality status of each key processing step based on the analysis results. The judgment and processing rule defines the qualified range, warning range and unqualified range of the quality characteristic. The quality assessment module is used to generate warning information and suggestions for adjusting process parameters when the analysis results indicate that the quality status of the intermediate product deviates from the qualified range.

[0016] Thirdly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method provided in the first aspect.

[0017] Compared with related technologies, the sensor-based lubricating oil sampling quality assessment method and system provided in this application have at least the following technical advantages: By acquiring intermediate product quality characteristic information from multiple key processing stages in the production of recycled lubricating oil, and analyzing this information according to preset judgment and processing rules, the system assesses the quality status of intermediate products at each stage based on the analysis results. The judgment and processing rules clearly define the acceptable, warning, and unacceptable ranges for quality characteristics. When the analysis results indicate that the quality status deviates from the acceptable range, the system promptly generates warning information and, based on the analysis results, generates suggestions for adjusting process parameters. Through this technical solution, the real-time acquisition and analysis of intermediate product quality characteristic information enables online and dynamic monitoring of the production process, allowing production managers to promptly grasp the immediate quality indicators of each key process. When the quality status deviates from the preset acceptable range, a warning is quickly issued, and specific process parameter adjustment suggestions are provided, thus breaking the "black box" state, achieving immediate quality feedback, precise adjustment of process parameters, and convenient traceability of the root cause of problems, ultimately improving the production efficiency and stabilizing the quality of recycled lubricating oil.

[0018] Details of one or more embodiments of this application are set forth in the following drawings and description to make other features, objects and advantages of this application more readily apparent. Attached Figure Description

[0019] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 This is a flowchart illustrating a sensor-based lubricating oil sampling quality assessment method according to an exemplary embodiment.

[0020] Figure 2 This is a flowchart illustrating step S3 according to an exemplary embodiment.

[0021] Figure 3 This is a flowchart illustrating step S3 according to another exemplary embodiment.

[0022] Figure 4 This is a flowchart illustrating step S3A2 according to an exemplary embodiment.

[0023] Figure 5 This is a flowchart illustrating step S3A2 according to another exemplary embodiment.

[0024] Figure 6 This is a block diagram illustrating a sensor-based lubricating oil sampling quality assessment system according to an exemplary embodiment. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of this application clearer, the application is described and illustrated below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application. All other embodiments obtained by those skilled in the art based on the embodiments provided in this application without inventive effort are within the scope of protection of this application.

[0026] Obviously, the accompanying drawings described below are merely some examples or embodiments of this application. Those skilled in the art can apply this application to other similar scenarios based on these drawings without any creative effort. Furthermore, it is understood that although the efforts made in this development process may be complex and lengthy, for those skilled in the art related to the content disclosed in this application, any changes to design, manufacturing, or production based on the technical content disclosed in this application are merely conventional technical means and should not be construed as insufficient disclosure of the content of this application.

[0027] In this application, the reference to "embodiment" means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0028] This invention provides a sensor-based method and system for evaluating the quality of lubricating oil sampling, which will be described in detail below with reference to specific embodiments and accompanying drawings.

[0029] Example 1 This invention provides a sensor-based method for evaluating the quality of lubricating oil samples. Figure 1 This is a flowchart illustrating a sensor-based lubricating oil sampling quality assessment method according to an exemplary embodiment. Figure 1 As shown, the method includes the following steps: S1. Obtain intermediate product quality characteristic information of multiple key processing steps in the production process of recycled lubricating oil, wherein the key processing steps include at least a deep dehydration step, a vacuum distillation step, a combined refining step, and a final blending step; In this embodiment, the recycled lubricating oil production process involves treating waste lubricating oil through a series of physical and chemical processes to restore or approximate the performance of new lubricating oil. This typically includes pretreatment, deep dehydration, vacuum distillation, combined refining, and final blending. Intermediate product quality characteristic information refers to the various physicochemical indicators obtained from testing semi-finished oil products during these key processing stages, such as moisture content, acid value, kinematic viscosity, flash point, color, and contaminant content. This intermediate product quality characteristic information is crucial for evaluating the processing effectiveness and product quality status at each stage. Various methods can be used to obtain this information. For example, one approach is to install online sensors and analyzers on the production line to monitor the intermediate products flowing through each key processing stage in real time, automatically collecting quality characteristic data such as moisture content, acid value, viscosity, density, and contaminant concentration. These sensors can be infrared spectrometers, viscometers, densitometers, moisture sensors, etc. Another approach is to set up sampling points at each key processing stage, where operators manually collect intermediate product samples periodically or irregularly, send them to a laboratory for rapid testing, and record the results into the system. For example, after the deep dehydration stage, samples can be taken to test the water content; after the vacuum distillation stage, samples can be taken to test the viscosity and flash point of different fractions; after the combined refining stage, samples can be taken to test the color, acid value, and contaminant content of the oil.

[0030] S2. The quality characteristic information is imported into a preset judgment and processing rule for analysis. The intermediate product quality status of each key processing step is evaluated based on the analysis results. The judgment and processing rule defines the qualified range, warning range and unqualified range of the quality characteristic. In this embodiment, the preset judgment and processing rules define the acceptable range, warning range, and unacceptable range of quality characteristic information. For example, for moisture content, the acceptable range may be set to less than 50 ppm, the warning range to 50-100 ppm, and the unacceptable range to greater than 100 ppm. After the quality characteristic information is imported into the preset judgment and processing rules, it will be compared with these preset ranges in the judgment and processing rules. For example, if the moisture content of an intermediate product in a certain stage is 80 ppm, it is determined to be within the warning range. It is understood that the preset judgment and processing rules are a logical system based on historical production data, process expert experience, and industry standards, used to define the acceptable, warning, and unacceptable ranges of quality characteristics.

[0031] S3. When the analysis results indicate that the quality status of the intermediate product deviates from the qualified range, a warning message is generated, and suggestions for adjusting the process parameters are generated. In this embodiment, for example, if the quality of intermediate products in a certain stage is determined to be within the warning or non-conforming range, the system will immediately generate a warning message and notify operators and managers through audible and visual alarms, SMS, email, or pop-up windows on the control interface. Simultaneously, based on the specific deviation and in conjunction with preset process parameter adjustment strategies, the system will generate corresponding adjustment suggestions. For another example, if the moisture content in the deep dehydration stage is too high, the system may suggest increasing the dehydration temperature, extending the dehydration time, or increasing the amount of dehydrating agent. These suggestions can be based on preset rule base matching results or optimization schemes generated based on historical data and machine learning models.

[0032] The core of the technical solution described above lies in the real-time and intelligent evaluation and feedback of intermediate product quality characteristics at multiple key processing stages in the production of recycled lubricating oil. By acquiring and analyzing the intermediate product quality characteristics at multiple key processing stages in real time during production, online and real-time monitoring of the production process is achieved. When the quality status deviates from the acceptable range, the system can immediately generate warning information and provide targeted process parameter adjustment suggestions, thereby transforming quality control from "post-event remediation" to "pre-event prevention" and "in-event intervention." For example, in the deep dehydration stage of recycled lubricating oil, if the online sensor detects that the moisture content of the intermediate product is consistently high and enters the warning range, the processing unit will immediately issue an alarm. At the same time, the system will suggest that operators appropriately increase the dehydration temperature or extend the dehydration time according to the preset process adjustment strategy. In this way, production managers can promptly identify and correct quality problems in the production process. This real-time feedback and intelligent decision support mechanism greatly shortens the problem response time, improves the accuracy and efficiency of process adjustments, effectively avoids the generation of unqualified products, and improves the production efficiency and product quality stability of recycled lubricating oil.

[0033] In one possible design, Figure 2 This is a flowchart illustrating step S3 according to an exemplary embodiment. (Refer to...) Figure 2 Step S3 includes the following steps: S3A1. Establish a process influence correlation map, wherein the process influence correlation map describes the influence relationship between key process parameters and intermediate product quality indicators in subsequent processes. In this embodiment, establishing a process influence correlation map refers to constructing a data model or knowledge base that records in detail the interaction relationships and degree of influence between various key process parameters (such as temperature, pressure, flow rate, catalyst dosage, etc.) in the production of recycled lubricating oil and the quality indicators of intermediate products in each subsequent process (such as viscosity, acid value, flash point, impurity content, etc.). This process influence correlation map can be constructed and continuously optimized through historical production data analysis, expert experience, physicochemical models, etc.

[0034] S3A2. When the quality characteristic information of a downstream process deviates from the center value of the normal operating range to the warning range, the quality characteristic information of the downstream process is marked as a potential quality deviation. In this embodiment, the system monitors in real time. Once it detects that the value of a certain quality indicator or a group of quality indicators exceeds its normal fluctuation range and reaches a preset warning threshold, it identifies it as a signal that there may be a quality problem. The center value of the normal operating range usually refers to the average value or target value of the quality characteristic under stable production conditions.

[0035] S3A3: Initiate the reverse tracing mechanism to deduce the upstream process parameters or links that caused the potential quality deviation based on the potential quality deviation. In this embodiment, after identifying potential quality deviations, the system utilizes a pre-established process influence correlation map to trace back along the process flow, starting from the downstream process where the deviation occurred, and gradually investigate upstream process parameters or production links that may have caused the deviation. For example, if the viscosity of the final product is unqualified, the traceability mechanism will analyze which upstream parameter changes may affect the viscosity based on the map, thereby narrowing down the scope of investigation.

[0036] S3A4. Retrieve and analyze real-time or recent historical data of upstream process parameters to find the root cause of abnormal fluctuations that match the potential quality deviations. In this embodiment, data comparison and pattern recognition are used to accurately pinpoint the specific parameter anomalies causing the quality problem. For example, if the tracing points to the temperature parameter of a certain reactor, the system will retrieve the temperature data of that reactor before and after the quality deviation occurred, and analyze whether there are abnormal increases or decreases, or whether there are unstable fluctuations.

[0037] S3A5. Based on the abnormal fluctuations in the root cause, generate a root cause diagnosis report, wherein the root cause diagnosis report indicates the abnormal fluctuations in the root cause and their impact on downstream quality deviations, and provides targeted corrective measures recommendations. In this embodiment, after identifying the specific source of the anomaly, the system automatically generates a detailed report. This report not only clearly indicates which process parameter or step has a problem, but also explains how the problem affects the quality indicators of downstream processes, and provides specific and actionable adjustment suggestions, such as "reduce the reaction temperature by 2°C" or "check the flow stability of a certain pump".

[0038] In the technical solution of the above embodiments, by introducing process influence correlation maps and reverse tracing mechanisms, the specific process parameters or links leading to quality deviations are clearly identified, making process adjustments more targeted and effective, avoiding blind trial and error and unnecessary production interruptions. When potential quality deviations occur in downstream processes, this solution no longer merely focuses on surface phenomena, but uses pre-set correlation maps to deduce the causes from the results, systematically investigating upstream process parameters and links. Through in-depth analysis of real-time or historical data of upstream parameters, abnormal fluctuations or trend changes consistent with quality deviations can be accurately identified, thereby pinpointing the true source of the anomaly. This mechanism deepens the diagnosis of quality problems from "discovering problems" to "locating the root cause," not only improving the efficiency of problem solving and reducing production costs, but also helping to improve the stability and consistency of product quality, providing a more intelligent quality management method for the production process of recycled lubricating oil.

[0039] In one example, suppose that during the refining stage of recycled lubricant production, the acid value (a key quality indicator) of the final product remains consistently high, exceeding the center value of the normal operating range and reaching a warning level. In this case, the system will mark the acid value information from the refining stage as a potential quality deviation.

[0040] Subsequently, a reverse tracing mechanism was activated. Based on a pre-established process impact correlation map, which showed that the acid value of the refining stage might be affected by parameters such as the reaction temperature, catalyst dosage, and initial acid value of the feedstock in the upstream deacidification stage, the system would deduce these upstream parameters and stages as potential sources of anomalies.

[0041] Next, the system retrieved real-time and recent historical data on parameters such as reaction temperature and catalyst dosage in the deacidification process before and after the occurrence of high acid value. Analysis revealed that before the acid value became high, the reaction temperature in the deacidification process showed a continuous, slight decreasing trend, while the catalyst dosage remained constant. This abnormal temperature fluctuation closely matched the high acid value.

[0042] Ultimately, the system generates a root cause diagnosis report. The report identifies the source of the high acid value in the refining process as an excessively low reaction temperature in the upstream deacidification stage. It explains how the temperature drop led to incomplete deacidification, thus affecting the acid value of the subsequent refined product. The report also provides targeted corrective action recommendations, such as "increasing the reaction temperature in the deacidification stage by 2°C and monitoring acid value changes." In this way, production personnel can quickly pinpoint the problem and take precise adjustments, effectively resolving quality deviations.

[0043] In one possible design, Figure 3 This is a flowchart illustrating step S3 according to another exemplary embodiment. (Refer to...) Figure 3 Step S3 further includes the following steps: S3B1: Obtain the current production line's operational constraint information; In this embodiment, operational constraint information refers to the various restrictions that the current production line must comply with during operation, such as the maximum processing capacity of the equipment, temperature and pressure ranges, raw material supply, product quality standards, safe operating procedures, and energy consumption limits. Obtaining operational constraint information aims to provide boundary conditions for subsequent adjustment suggestions.

[0044] S3B2. When multiple quality indicators are identified to deviate from the qualified range at the same time, the adjustment suggestions that may cause conflict are sorted according to the preset process optimization priority rules. In this embodiment, when multiple quality indicators are identified as deviating from preset ranges simultaneously—for example, the viscosity, acid value, and moisture content of lubricating oil all exceeding normal ranges—the system will prioritize potentially conflicting adjustment suggestions according to preset process optimization priority rules. These priority rules can be set based on factors such as the severity of the impact on production, adjustment costs, adjustment difficulty, or historical experience, to ensure that optimization of key indicators takes precedence over secondary indicators, or to avoid adjustments that have a greater negative impact on production.

[0045] S3B3. Evaluate the impact of the sorted adjustment suggestions on the operational constraints; In this embodiment, each potential adjustment suggestion is simulated or analyzed to determine whether it would cause the production line to exceed preset operating constraints. For example, an adjustment suggestion might require increasing the reaction temperature, but if the current equipment's maximum tolerance temperature is lower than the suggested value, the suggestion is considered a violation of operating constraints.

[0046] S3B4. Based on the preset process parameter linkage rules, integrate and generate a set of conflict-free comprehensive adjustment suggestions; In this embodiment, the linkage rules describe the interrelationships between different process parameters. For example, increasing the temperature of a reactor may affect the load of the subsequent cooling unit. By considering these linkages, the system can integrate multiple independent adjustment suggestions into a coordinated and consistent comprehensive solution, avoiding new problems caused by adjusting a single parameter.

[0047] S3B5. Calculate the expected effect and potential impact on the operational constraints of each comprehensive adjustment suggestion in the comprehensive adjustment suggestion set; In this embodiment, this step aims to quantify the advantages and disadvantages of each integrated solution. Expected effects include the degree of improvement in quality indicators, increased production efficiency, or reduced energy consumption; potential impacts include negative effects on equipment lifespan, safety risks, or other non-target quality indicators.

[0048] S3B6. Select the comprehensive adjustment suggestion that yields the best expected results and does not violate the operational constraints, and use it as the final adjustment instruction; In this embodiment, the solution selected through the above steps not only effectively solves the quality problem, but is also feasible and optimal under the current production conditions.

[0049] The technical solution described in the above embodiments improves the accuracy of process parameter adjustments during the production of recycled lubricating oil by introducing the acquisition of production line operation constraint information, prioritizing adjustment suggestions when multiple indicators deviate, evaluating the adjustment suggestions and operation constraints, and generating a conflict-free comprehensive set of adjustment suggestions based on process parameter linkage rules. Specifically, when multiple quality indicators simultaneously become abnormal, the system no longer processes each indicator in isolation, but intelligently prioritizes potential adjustment suggestions through priority rules to ensure that critical issues are addressed first. Simultaneously, by evaluating operation constraints, adjustment schemes that may lead to production line instability or safety issues are filtered out. More importantly, through process parameter linkage rules, the system can generate a holistic and coordinated comprehensive adjustment suggestion, avoiding the global negative impact that local optimization may bring, thereby ensuring the feasibility and overall optimality of adjustment instructions, effectively improving product quality stability, reducing production costs, and increasing production efficiency.

[0050] In one example, suppose that during the refining process of recycled lubricating oil, the product is found to have low viscosity, high acid value, and substandard color. Traditional methods might suggest increasing the reaction temperature, increasing the amount of deacidifying agent, and extending the adsorption time, respectively. However, increasing the reaction temperature may further deepen the color, increasing the amount of deacidifying agent may affect the viscosity, and extending the adsorption time may exceed the limitations of the current production cycle.

[0051] According to the scheme of this application, firstly, the current operating constraints of the production line are obtained, such as the maximum temperature of the reactor, the maximum amount of deacidifying agent added, and the maximum processing time of the adsorption tower. Next, when it is identified that the three quality indicators—viscosity, acid value, and color—simultaneously deviate from the preset range, the adjustment suggestions that may cause conflict are prioritized according to preset process optimization priority rules (e.g., viscosity has the highest priority, followed by acid value, and finally color). For example, for low viscosity, it may be suggested to increase the reaction temperature; for high acid value, it may be suggested to increase the amount of deacidifying agent; for substandard color, it may be suggested to extend the adsorption time or replace the adsorbent.

[0052] The system then evaluates the impact of these ranked adjustment suggestions on operational constraints. For example, if a suggestion to increase the reaction temperature exceeds the reactor's maximum tolerance temperature, the suggestion will be marked as infeasible. Simultaneously, based on preset process parameter linkage rules, the system generates a conflict-free comprehensive set of adjustment suggestions. For instance, the system might discover that by fine-tuning the dosage of a certain catalyst, the acid value can be reduced and the color improved without significantly affecting viscosity, or that by optimizing the combination of reaction time and temperature, viscosity requirements can be met while also considering acid value and color.

[0053] Finally, the expected effects (e.g., the extent of improvement in viscosity, acid value, and color parameters) and potential impacts on operational constraints (e.g., increased energy consumption, equipment wear) of each comprehensive adjustment suggestion in the set are calculated. By comparison, the system selects the comprehensive adjustment suggestion with the best expected effect that does not violate any operational constraints; for example, suggesting a fine-tuning of the reaction temperature to a specific value while simultaneously adjusting the dosage of catalyst A, as the final adjustment instruction. In this way, production operators obtain a comprehensive, coordinated, and executable optimization plan.

[0054] In one possible design, Figure 4 This is a flowchart illustrating step S3A2 according to an exemplary embodiment. (Refer to...) Figure 4 Step S3A2 includes the following steps: S3A2A1: Obtain quality characteristic information from multiple downstream processes; In this embodiment, during the continuous or batch processing of recycled lubricating oil production, the system collects intermediate product quality data from multiple closely linked subsequent processes in real time or periodically. These quality characteristics may include, but are not limited to, viscosity, acid value, flash point, color, and impurity content.

[0055] S3A2A2, Calculate the degree of deviation between the quality characteristic information of multiple downstream processes and their respective normal operating range center values; In this embodiment, for each collected quality feature information, the difference between it and the ideal target value or average value of the feature under normal production conditions is quantified by mathematical methods (such as absolute difference, percentage deviation or standardized deviation).

[0056] S3A2A3: Identify the process correlation between the quality feature information according to the preset process influence correlation rules; In this embodiment, a pre-established knowledge base or data model is used to analyze whether there are causal relationships, synergistic changes, or common influences from a certain upstream process parameter among different quality characteristic information. For example, if a temperature anomaly in an upstream processing stage may simultaneously affect the viscosity and color indicators of the downstream refining process, then there is a process correlation between viscosity and color.

[0057] S3A2A4. Calculate the combined deviation index of multiple quality characteristic information that are related to the process; In this embodiment, the deviations of the identified interrelated quality characteristics are weighted or unweighted to form a single value that comprehensively reflects the overall deviation of these related indicators. This combined deviation index can be calculated using multivariate statistical methods (such as principal component analysis or discriminant analysis) or weighted summation based on expert experience, thereby integrating scattered quality fluctuation information into a more indicative comprehensive indicator.

[0058] S3A2A5. When the combined deviation index exceeds the preset combined early warning threshold, the quality characteristic information of the associated downstream process is collaboratively marked as a potential quality deviation. In this embodiment, when the combined performance of multiple related quality indicators exceeds the acceptable fluctuation range, the system immediately marks these related quality characteristics as a whole, indicating the existence of potential quality problems that require attention. This ultimately achieves early, coordinated warnings of complex quality risks, avoiding missed intervention opportunities due to the insignificant fluctuations of a single indicator.

[0059] In the technical solution of the above embodiments, by acquiring and comprehensively analyzing the quality characteristic information of multiple downstream processes, and further identifying the process correlation between these information, a combined deviation index is calculated. This allows for a more comprehensive capture of potential quality problems caused by complex upstream factors that may be missed by traditional single-index monitoring methods, thus improving the early identification capability of potential quality deviations in the production of recycled lubricating oil. Specifically, by comprehensively considering the quality characteristic information and process correlation of multiple downstream processes and calculating the combined deviation index, this application can more sensitively capture quality risks that are not obvious in a single index, caused by subtle changes in upstream process parameters or the synergistic effect of multiple factors. This not only helps to discover and intervene in potential quality problems earlier, preventing them from worsening, but also reduces the occurrence of false alarms and missed alarms, thereby improving the accuracy and reliability of quality assessment. In addition, the collaborative labeling mechanism makes the identification of potential quality deviations more comprehensive and systematic, providing more accurate guidance for subsequent root cause diagnosis and process optimization.

[0060] In one example, assume that after the refining stage of the recycled lubricating oil, there are decolorization and filtration processes. The intermediate product quality characteristics of the decolorization process include color index and transmittance, while those of the filtration process include impurity particle size. According to pre-defined process influence correlation rules, there is a close process correlation between color index, transmittance, and impurity particle size. For example, insufficient upstream decolorizing agent addition may simultaneously lead to a high color index, low transmittance, and increased impurity particle size after filtration.

[0061] In this application, the color index and transmittance of the decolorization process and the particle size of the impurities in the filtration process are first obtained. Then, the deviation of these three quality characteristics from their respective normal operating range center values ​​is calculated. For example, the color index deviates from the center value by +5%, the transmittance by -8%, and the particle size by +10%.

[0062] Subsequently, based on the preset process influence correlation rules, the correlation between these three indicators is confirmed. The system calculates a combined deviation index, which comprehensively considers the deviations of color index, transmittance, and impurity particle size, as well as their mutual influences. For example, using a weighted average model, the combined deviation index is calculated to be 7.5.

[0063] When the combined deviation index exceeds the preset combined warning threshold (e.g., set to 6.0) by 7.5, the system will immediately mark the color index and transmittance of the decolorization process and the impurity particle size of the filtration process as potential quality deviations. At this time, even if the deviation of a single indicator may not have reached its own independent warning threshold, the system can still issue a timely warning because the combined deviation has exceeded the safe range, indicating that there may be a potential quality problem affecting multiple downstream processes, thereby triggering the subsequent reverse tracing and process parameter adjustment suggestion generation process.

[0064] In one possible design, Figure 5 This is a flowchart illustrating step S3A2 according to another exemplary embodiment. (Refer to...) Figure 5 Step S3A2 further includes the following steps: S3A2B1. Obtain the change characteristics of the quality characteristic information within a continuous time window, wherein the change characteristics include the rate of change, fluctuation amplitude, and duration. In this embodiment, the rate of change of quality characteristic information refers to the amount of numerical change of the information per unit time, reflecting the speed at which the quality status deteriorates. The fluctuation amplitude refers to the difference between the maximum and minimum values ​​of the quality characteristic information within a certain time range, reflecting the instability of the quality status. The duration refers to the length of time during which the quality characteristic information deviates from the normal or warning range.

[0065] S3A2B2. Based on the aforementioned change characteristics, identify the deviation patterns of the quality characteristic information, wherein the deviation patterns include cumulative deviation patterns, periodic deviation patterns, and sudden deviation patterns. In this embodiment, the identification of deviation patterns is based on a comprehensive analysis of the aforementioned quality characteristic information. Cumulative deviation patterns typically manifest as a slow but continuous drift of quality characteristic information in an undesirable direction, with a small rate of change but a long duration. Periodic deviation patterns typically manifest as regular fluctuations in quality characteristic information. Sudden deviation patterns typically manifest as a drastic and significant deviation of quality characteristic information within a short period.

[0066] S3A2B2-1. When the deviation mode is a cumulative deviation mode, the warning threshold is dynamically lowered and the deviation duration requirement is extended. When the deviation lasts for more than a certain duration, the quality characteristic information is marked as a potential quality deviation. In this embodiment, the cumulative deviation pattern typically manifests as a slow but continuous drift of quality characteristic information in an undesirable direction, with a small rate of change but a long duration. For this type of pattern, by dynamically lowering the warning threshold and extending the required deviation duration, potential quality problems can be detected earlier, avoiding delays in warnings due to excessively high thresholds.

[0067] S3A2B2-2. When the deviation mode is a periodic deviation mode, a larger deviation amplitude is allowed at the peak or trough of the periodic fluctuation. When the amplitude and frequency of the fluctuation exceed the range of normal periodic fluctuation, the quality characteristic information is marked as a potential quality deviation. In this embodiment, the periodic deviation pattern typically manifests as regular fluctuations in quality characteristic information, influenced by factors such as equipment maintenance cycles, raw material batch changes, or changes in ambient temperature. In this type of pattern, a larger deviation is allowed at the peaks or troughs of the periodic fluctuations to avoid false alarms about normal fluctuations. However, when the amplitude and frequency of the fluctuations exceed the range of normal periodic fluctuations, it indicates an anomaly, and should be marked as a potential quality deviation.

[0068] S3A2B2-3. When the deviation mode is a sudden deviation mode, an early warning is immediately triggered and the deviation duration requirement is shortened. When the deviation amplitude reaches a preset value, the quality characteristic information is marked as a potential quality deviation. In this embodiment, the sudden deviation mode typically manifests as a drastic and significant deviation of quality characteristic information within a short period of time, usually caused by emergencies such as equipment failure, operational errors, or sudden changes in raw materials. For this type of mode, an early warning needs to be triggered immediately, and the deviation duration requirement needs to be shortened to ensure a rapid response. When the deviation reaches a preset value, it should be quickly marked as a potential quality deviation.

[0069] In the technical solution of the above embodiments, by acquiring the rate of change, fluctuation amplitude, and duration of quality characteristic information within a continuous time window, and identifying different deviation patterns such as cumulative, periodic, and sudden deviations based on these dynamic parameters, and adopting differentiated early warning strategies for different types of deviation patterns, false alarms or missed alarms caused by single threshold judgments can be effectively avoided. For example, for slowly accumulating quality problems, early warnings can be achieved, buying valuable time for process adjustments; for anomalies in periodic fluctuations, the true anomalies can be accurately identified, reducing unnecessary intervention; and for sudden quality accidents, rapid response can be achieved, minimizing losses. This enables the quality assessment system to cope more intelligently and robustly with complex production environments.

[0070] In one example, suppose the acid value of the product is continuously monitored during the refining process of recycled lubricating oil. When the acid value rises slowly over several hours but has not yet reached the traditional warning threshold, the system identifies it as a cumulative deviation pattern by analyzing its rate of change and duration. In this case, the system dynamically lowers the warning threshold and extends the required duration of the deviation. For example, if the acid value deviates from the center value by more than 0.05 mg KOH / g for more than 4 hours, it is marked as a potential quality deviation, thus issuing an alert before the acid value reaches the traditional warning line, prompting operators to check catalyst activity or reaction temperature. When the acid value exhibits periodic fluctuations with a slight increase at the end of each shift, but its amplitude and frequency are within the normal range, the system allows for such fluctuations.

[0071] However, if the peak value of a fluctuation exceeds 10% of the normal periodic fluctuation range, or if the periodic frequency changes significantly, the system will identify it as an abnormal periodic deviation pattern and mark it as a potential quality deviation, indicating that there may be equipment wear or operational issues.

[0072] When the acid value suddenly and drastically increases from the normal range within a few minutes, for example, momentarily deviating from the central value by 0.5 mg KOH / g, the system will immediately identify it as a sudden deviation. At this time, the system will immediately trigger an early warning and shorten the deviation duration requirement. For example, as long as the deviation reaches a preset value (such as 0.3 mg KOH / g) and lasts for 1 minute, it will be marked as a potential quality deviation, thus quickly indicating that raw material contamination or sudden equipment failure may have occurred, requiring emergency handling.

[0073] In one possible design, step S3A2 further includes the following steps: S3A2C1. Obtain multiple key attribute information of the current batch of waste oil raw materials, wherein the key attribute information includes raw material source, initial pollutant content and pretreatment parameters; In this embodiment, key attribute information refers to the inherent characteristics and preliminary treatment of waste oil raw materials before they enter the recycling production line. For example, the source of raw materials refers to the recycling channel of waste oil, the initial pollutant content refers to the initial concentration of impurities such as water, acid value, and metal elements in waste oil, and the pretreatment parameters refer to the set values ​​of pretreatment processes such as dehydration and filtration that waste oil undergoes before entering the main production line.

[0074] S3A2C2. Based on the key attribute information, retrieve historical batch data that matches the attributes of the current batch of waste oil from the preset raw material batch feature library; In this embodiment, the raw material batch feature library is a pre-established database that stores a large amount of key attribute information of historical batches of waste oil raw materials and their corresponding intermediate product quality characteristics and normal operation data in different downstream processes. By matching the key attribute information of the current batch of waste oil raw materials with the historical data in this feature library, the historical batch data most similar to the characteristics of the current batch of raw materials can be found.

[0075] S3A2C3. Based on the historical batch data, calculate the center value of the normal operating range corresponding to the quality characteristic information of the current batch of waste oil raw materials in each downstream process; In this embodiment, the central value of the normal operating range is calculated using statistical methods, such as calculating the average or median of historical batch data across quality characteristics in each downstream process, as the expected normal value for the current batch of raw materials in a specific process. This central value is dynamically generated and reflects the expected impact of the current batch's raw material characteristics on its quality characteristics.

[0076] S3A2C4. Continuously monitor the quality characteristic information of each downstream process and compare it with the calculated center value; In this embodiment, intermediate product quality data at each key processing stage on the production line are collected in real-time or near real-time. Subsequently, this real-time monitored quality characteristic information is compared with the dynamic center value calculated for the current batch of raw materials to determine if any deviation exists.

[0077] S3A2C5. When the quality characteristic information deviates from the calculated center value to the level of a warning, the quality characteristic information is marked as a potential quality deviation. In this embodiment, when the deviation reaches a preset warning threshold, it is considered that the quality feature information indicates a potential quality deviation, and the quality feature information is marked.

[0078] In the technical solution of the above embodiments, by incorporating consideration of key attribute information of waste oil raw materials and dynamically calculating the center value of the normal operating range in conjunction with historical batch data, the accuracy of identifying potential quality deviations in the lubricating oil regeneration production process is improved. Specifically, when different batches of waste oil raw materials enter the production line, their inherent attribute differences will lead to different "normal" quality states of intermediate products in each downstream process. By acquiring key attribute information such as the source of the current batch of waste oil raw materials, the initial contaminant content, and pretreatment parameters, and matching it with historical batch data in the raw material batch feature library, the expected quality characteristics of the current batch of raw materials in each downstream process can be accurately predicted. Thus, the calculated center value can accurately reflect the expected normal quality level of the current batch of raw materials. When the actual monitored quality characteristic information deviates from the dynamically adjusted center value and reaches the warning level, the marked potential quality deviations will be more targeted and accurate, thereby avoiding false alarms or omissions caused by differences in raw material batches.

[0079] In one example, suppose a recycled lubricating oil production line receives two batches of waste oil feedstock: Batch A is industrial waste oil with a high initial contaminant content, and the pretreatment parameters are set to high-intensity dehydration; Batch B is automotive waste oil with a relatively low initial contaminant content, and the pretreatment parameters are set to conventional dehydration. In traditional methods, a fixed center value might be used to evaluate the quality of intermediate products across all batches. For example, for the colorimetric index after the decolorization process, a fixed center value might be set to 50.

[0080] According to the scheme of this application, the key attribute information of batch A (industrial waste oil, high pollutant content, high-intensity dehydration) is first obtained, and historical batch data matching this is retrieved from the raw material batch feature database. After analyzing this historical data, it is calculated that the normal operating center value of the color index of batch A after the decolorization process should be 60 (because the initial pollutant content is high, even with normal treatment, the color may be slightly higher). At the same time, the key attribute information of batch B (automobile waste oil, low pollutant content, conventional dehydration) is obtained, and matching historical data is retrieved. It is calculated that the normal operating center value of the color index of batch B after the decolorization process should be 45. During the production process, if the color monitoring value of batch A after decolorization is 65, traditional methods may consider it to be far from the fixed center value of 50, triggering an alarm. However, according to the scheme of this application, the deviation of 65 from the dynamic center value of 60 of batch A is small, and it may still be within the normal fluctuation range, thus avoiding false alarms. Conversely, if the color monitoring value of batch B after decolorization is 55, traditional methods may consider it to be close to the fixed center value of 50, and no alarm is triggered. However, according to the scheme of this application, the deviation between 55 and the dynamic center value of 45 of batch B is relatively large, which may have reached the warning level, thus enabling timely identification of potential quality deviations. In this way, this application can dynamically adjust the quality assessment benchmark according to the characteristics of different raw material batches, making the identification of potential quality deviations more accurate.

[0081] In one possible design, step S3A2C5 includes the following steps: S3A2C51. Obtain the current operating status information of the production line, wherein the operating status information includes equipment operating time, ambient temperature, and operator shifts; In this embodiment, the system collects multi-dimensional data related to the production line's operating status in real time or periodically. Among these data, equipment uptime reflects the degree of equipment wear or operational stability, ambient temperature may affect the physicochemical properties of materials or reaction rates, and operator shifts may be related to differences in operating habits or experience. These operational conditions collectively constitute the current operating context of the production line.

[0082] S3A2C52. Based on the operating condition information, retrieve historical operating data that matches the current operating condition from the preset operating condition feature library; In this embodiment, the operating condition feature library is a database that stores a large amount of historical production data and its corresponding operating conditions. Upon obtaining the current operating condition information, the system intelligently searches the feature library for historical operating data that is similar to or matches the current operating condition. This historical operating data includes the actual fluctuations in the quality characteristics of each downstream process under similar operating conditions and the corresponding early warning triggering situations.

[0083] S3A2C53. Based on the historical operating data, calculate the quality warning threshold corresponding to the quality characteristic information of each downstream process under the current operating conditions; In this embodiment, the warning threshold is dynamically adjusted according to the current specific operating conditions. For example, under certain specific operating conditions, the normal fluctuation range of quality characteristic information may be slightly wider, and the warning threshold will be appropriately relaxed; while under other quality-sensitive operating conditions, even a small deviation may indicate a problem, and the warning threshold will be tightened.

[0084] S3A2C54. Continuously monitor the quality characteristic information of each downstream process and compare it with the calculated center value. When the quality characteristic information deviates from the calculated center value and reaches the quality warning threshold, the quality characteristic information is marked as a potential quality deviation. In the technical solution of the above embodiments, by acquiring operating condition information such as equipment running time, ambient temperature, and operator shifts, and combining it with historical data to dynamically calculate the early warning threshold, the early warning mechanism becomes more aligned with actual production conditions. For example, when prolonged equipment operation leads to a slight decrease in performance, the system appropriately relaxes the early warning threshold to avoid unnecessary alarms; conversely, under abnormal ambient temperature conditions or during critical operating shifts, the system tightens the threshold to increase sensitivity to potential problems. This enables quality control personnel to more accurately identify and respond to genuine quality deviations, avoiding resource waste caused by unnecessary alarms and reducing production losses due to failure to detect problems in a timely manner.

[0085] In one possible design, step S3 further includes the following steps: S3C1. Obtain the dependencies and order requirements among multiple process parameter adjustment suggestions; In this embodiment, after generating multiple process parameter adjustment suggestions, the system analyzes whether there is a logical order or mutual constraint relationship between these suggestions. For example, adjusting one parameter may require adjusting another parameter first, or the adjustment of two parameters cannot be performed simultaneously. These dependencies and order requirements can be obtained through a preset knowledge base, expert experience rules, or models built based on historical data analysis.

[0086] S3C2. Based on the dependencies and the order requirements, construct the proposed execution path. In this embodiment, after clarifying the dependencies and sequence requirements of each adjustment suggestion, the system plans one or more possible adjustment step sequences based on this information, forming one or more adjustment suggestion execution paths.

[0087] S3C3. Evaluate the impact of each adjustment step in the proposed adjustment path on the quality characteristic information of subsequent processes; In this embodiment, for each constructed adjustment suggestion execution path, the system simulates or predicts the potential impact of each adjustment step in the path on the intermediate product quality characteristics of subsequent production processes. The simulation or prediction is performed using physical models, data-driven models, or expert systems to identify potential positive or negative effects.

[0088] S3C4. When the evaluation result indicates that there are adjustment steps in the adjustment suggestion execution path that cause negative impacts, optimize the adjustment suggestion execution path to eliminate the negative impacts, and use the optimized adjustment suggestion execution sequence as the final adjustment instruction. In this embodiment, if the evaluation finds that an adjustment step may lead to quality deterioration in subsequent processes or other adverse consequences, the system will modify the current adjustment suggestion execution path. Modifications may include reordering adjustment steps, replacing an adjustment suggestion, or introducing new compensatory adjustment measures to ensure the positive effect of the entire adjustment sequence. Therefore, after the above evaluation and adjustment process, the system will output an optimized, conflict-free process parameter adjustment sequence that effectively improves quality. This sequence will serve as the final instruction guiding production line operators in parameter adjustments, ensuring the effectiveness and safety of the adjustments.

[0089] In the technical solution of the above embodiments, by introducing the dependency relationships, sequence requirements, and impact assessment mechanisms on subsequent processes for process parameter adjustment suggestions, the execution path of adjustment suggestions can be systematically planned and optimized, ensuring the feasibility of adjustment instructions and improving the success rate of process parameter adjustments. Specifically, firstly, the dependencies and sequence between adjustment suggestions are obtained to ensure the logicality of the adjustment; secondly, the execution path is constructed and the impact of each step is assessed to identify and avoid potential risks in advance; finally, the negative impact is eliminated by adjusting the execution path, generating an optimized, conflict-free adjustment sequence.

[0090] In summary, the sensor-based lubricating oil sampling quality assessment method provided in this invention acquires intermediate product quality characteristic information from multiple key processing stages in the recycled lubricating oil production process. Based on preset judgment and processing rules, it analyzes this quality characteristic information and assesses the quality status of intermediate products at each stage based on the analysis results. The judgment and processing rules clearly define the acceptable range, warning range, and unacceptable range for the quality characteristics. When the analysis results indicate that the quality status deviates from the acceptable range, the system promptly generates warning information and, based on the analysis results, generates suggestions to guide the adjustment of process parameters.

[0091] Example 2 Embodiment 2 of the present invention provides a sensor-based lubricating oil sampling quality assessment system. Figure 6This is a block diagram illustrating a sensor-based lubricating oil sampling quality assessment system according to an exemplary embodiment. Figure 6 As shown, the system includes: Information acquisition module 01 is used to acquire intermediate product quality characteristic information of multiple key processing links in the production process of recycled lubricating oil, wherein the key processing links include at least a deep dehydration link, a vacuum distillation link, a combined refining link and a final blending link; The information transmission module 02 is used to import the quality characteristic information into a preset judgment and processing rule for analysis, and to evaluate the intermediate product quality status of each key processing step based on the analysis results. The judgment and processing rule defines the qualified range, warning range and unqualified range of the quality characteristic. The quality assessment module 03 is used to generate warning information and suggestions for adjusting process parameters when the analysis results indicate that the quality status of the intermediate product deviates from the qualified range.

[0092] The IoT-based machine tool control system provided in Embodiment 2 of this invention acquires intermediate product quality characteristic information from multiple key processing stages in the production of recycled lubricating oil. Based on preset judgment and processing rules, it analyzes this quality characteristic information and evaluates the quality status of intermediate products at each stage based on the analysis results. The judgment and processing rules clearly define the acceptable, warning, and unacceptable ranges for the quality characteristics. When the analysis results indicate that the quality status deviates from the acceptable range, the system promptly generates warning information and, based on the analysis results, generates suggestions for adjusting process parameters. Through the above technical solution, this application achieves real-time acquisition and analysis of intermediate product quality characteristic information, realizing online and dynamic monitoring of the production process. This allows production managers to promptly grasp the real-time quality indicators of each key process. When the quality status deviates from the preset acceptable range, a warning is quickly issued, and specific process parameter adjustment suggestions are provided. This breaks the "black box" state, achieving immediate quality feedback, precise adjustment of process parameters, and convenient tracing of the root cause of problems, ultimately improving the production efficiency and stabilizing the quality of recycled lubricating oil.

[0093] Example 3 Embodiment 3 of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method provided in Embodiment 1.

[0094] In a possible implementation, the present invention can also be implemented as a program product comprising program code, which, when the program product is run on a terminal device, causes the terminal device to perform the steps of implementing the sensor-based lubricating oil sampling quality assessment method in Embodiment 1.

[0095] The program code for executing the present invention can be written in any combination of one or more programming languages. The program code can be executed entirely on the user device, partially on the user device, as a standalone software package, partially on the user device and partially on a remote device, or entirely on a remote device.

[0096] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0097] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for evaluating the quality of lubricating oil sampling, characterized in that, Includes the following steps: The intermediate product quality characteristics information of multiple key processing steps in the production of recycled lubricating oil is obtained, wherein the key processing steps include at least a deep dehydration step, a vacuum distillation step, a combined refining step, and a final blending step; The quality characteristic information is imported into a preset judgment and processing rule for analysis. The intermediate product quality status of each key processing step is evaluated based on the analysis results. The judgment and processing rule defines the qualified range, warning range and unqualified range of the quality characteristics. When the analysis results indicate that the quality status of the intermediate product deviates from the acceptable range, a warning message is generated, and suggestions for adjusting process parameters are generated.

2. The evaluation method according to claim 1, characterized in that, When the analysis results indicate that the quality status of the intermediate product deviates from the acceptable range, a warning message is generated, and suggestions for adjusting process parameters are generated, including: Establish a process influence correlation map, wherein the process influence correlation map describes the influence relationship between key process parameters and intermediate product quality indicators in subsequent processes; When the quality characteristic information of a downstream process deviates from the center value of the normal operating range to the warning range, the quality characteristic information of the downstream process is marked as a potential quality deviation. Initiate a reverse tracing mechanism to deduce the upstream process parameters or steps that caused the potential quality deviation based on the potential quality deviation. Retrieve and analyze real-time or recent historical data of upstream process parameters to find the root cause of abnormal fluctuations that match the potential quality deviations. Based on the abnormal fluctuations in the root cause, a root cause diagnosis report is generated, which indicates the abnormal fluctuations in the root cause and their impact on downstream quality deviations, and provides targeted corrective action recommendations.

3. The evaluation method according to claim 1, characterized in that, The method of generating a warning message and generating suggestions for adjusting process parameters when the analysis results indicate that the quality status of the intermediate product deviates from the acceptable range also includes: Obtain the current operating constraints information of the production line; When multiple quality indicators are identified to deviate from the acceptable range simultaneously, adjustment suggestions that may cause conflicts are sorted according to preset process optimization priority rules. Evaluate the impact of the proposed adjustments after sorting on the operational constraints; Based on the preset process parameter linkage rules, a set of conflict-free comprehensive adjustment suggestions is generated. Calculate the expected effect and potential impact on the operational constraints for each comprehensive adjustment suggestion in the comprehensive adjustment suggestion set; Select the comprehensive adjustment recommendation that yields the best expected results and does not violate the operational constraints, and use it as the final adjustment instruction.

4. The evaluation method according to claim 2, characterized in that, When the quality characteristic information of a downstream process deviates from the center value of the normal operating range to the warning range, the quality characteristic information of the downstream process is marked as a potential quality deviation, including: Obtain quality characteristic information from multiple downstream processes; Calculate the degree of deviation between the quality characteristic information of multiple downstream processes and the center value of their respective normal operating ranges; Based on preset process influence correlation rules, identify the process correlation between the quality feature information; Calculate the combined deviation index of multiple quality characteristics that are process-related; When the combined deviation index exceeds the preset combined warning threshold, the quality characteristic information of the associated downstream process is collaboratively marked as a potential quality deviation.

5. The evaluation method according to claim 4, characterized in that, The step of marking the quality characteristic information of a downstream process as a potential quality deviation when it deviates from the center value of the normal operating range to the warning range also includes: The quality characteristic information is obtained as a change feature within a continuous time window, the change feature including the rate of change, fluctuation amplitude and duration; Based on the aforementioned change characteristics, deviation patterns of the quality characteristic information are identified, wherein the deviation patterns include cumulative deviation patterns, periodic deviation patterns, and sudden deviation patterns; When the deviation mode is a cumulative deviation mode, the warning threshold is dynamically lowered and the deviation duration requirement is extended. When the deviation lasts for more than a certain period of time, the quality characteristic information is marked as a potential quality deviation. When the deviation pattern is a periodic deviation pattern, a larger deviation amplitude is allowed at the peak or trough of the periodic fluctuation. When the amplitude and frequency of the fluctuation exceed the range of normal periodic fluctuation, the quality characteristic information is marked as a potential quality deviation. When the deviation mode is a sudden deviation mode, an early warning is immediately triggered and the deviation duration requirement is shortened. When the deviation amplitude reaches a preset value, the quality characteristic information is marked as a potential quality deviation.

6. The evaluation method according to claim 4, characterized in that, The step of marking the quality characteristic information of the downstream process as a potential quality deviation when the deviation from the center value of the normal operating range reaches the warning level further includes: Obtain multiple key attribute information of the current batch of waste oil raw materials, wherein the key attribute information includes raw material source, initial pollutant content and pretreatment parameters; Based on the key attribute information, retrieve historical batch data that matches the attributes of the current batch of waste oil from the preset raw material batch feature library; Based on the historical batch data, calculate the center value of the normal operating range corresponding to the quality characteristic information of the current batch of waste oil raw materials in each downstream process; Continuously monitor the quality characteristic information of each downstream process and compare it with the calculated center value; When the quality characteristic information deviates from the calculated center value to the level of a warning, the quality characteristic information is marked as a potential quality deviation.

7. The evaluation method according to claim 6, characterized in that, When the quality characteristic information deviates from the calculated center value to a warning level, the quality characteristic information is marked as a potential quality deviation, including: Obtain the current operating status information of the production line, wherein the operating status information includes equipment operating time, ambient temperature, and operator shifts; Based on the operating condition information, retrieve historical operating data that matches the current operating condition from a preset operating condition feature library; Based on the historical operating data, calculate the quality warning threshold corresponding to the quality characteristic information of each downstream process under the current operating conditions; The quality characteristic information of each downstream process is continuously monitored and compared with the calculated center value. When the quality characteristic information deviates from the calculated center value to the quality warning threshold, the quality characteristic information is marked as a potential quality deviation.

8. The evaluation method according to claim 1, characterized in that, The method of generating a warning message and generating suggestions for adjusting process parameters when the analysis results indicate that the quality status of the intermediate product deviates from the acceptable range also includes: Obtain the dependencies and order requirements among the multiple process parameter adjustment suggestions; Based on the dependencies and the order requirements, construct and adjust the suggested execution path; Assess the impact of each adjustment step in the proposed adjustment path on the quality characteristic information of subsequent processes; When the evaluation results indicate that there are adjustment steps in the proposed adjustment path that cause negative impacts, the proposed adjustment path is optimized to eliminate the negative impacts, and the optimized proposed adjustment sequence is used as the final adjustment instruction.

9. A sensor-based lubricating oil sampling quality assessment system, characterized in that, The system includes: The information acquisition module is used to acquire intermediate product quality characteristic information of multiple key processing steps in the production process of recycled lubricating oil, wherein the key processing steps include at least a deep dehydration step, a vacuum distillation step, a combined refining step, and a final blending step. The information transmission module is used to import the quality characteristic information into a preset judgment and processing rule for analysis, and to evaluate the intermediate product quality status of each key processing step based on the analysis results. The judgment and processing rule defines the qualified range, warning range and unqualified range of the quality characteristic. The quality assessment module is used to generate warning information and suggestions for adjusting process parameters when the analysis results indicate that the quality status of the intermediate product deviates from the qualified range.

10. A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method according to any one of claims 1-8.

Images