Oil product quality inspection method and system for finished oil discharge

Abstract

The invention relates to the technical field of product oil, and particularly discloses an oil product quality inspection method and system for product oil discharge, and the method comprises the steps: analyzing oil product data during product oil discharge in a historical period to obtain an impurity characterization value, marking a corresponding sub-region as an impurity region based on the impurity characterization value, and marking a corresponding sub-region as an impurity region based on the impurity region. The method comprises the steps of measuring impurity area heights, extracting impurity characterization values corresponding to all the impurity area heights, conducting linear fitting on the impurity characterization values of different impurity area heights, determining impurity distribution information in the oil tank, selecting different prediction models, obtaining a prediction approaching value through analysis based on the prediction models, and obtaining a truncation time point through analysis based on the prediction approaching value. According to the method, different prediction models are selected, the selected prediction model is verified, the accuracy of model prediction can be accurately judged, then the truncation time point of the impurity area of the refined oil product can be obtained, truncation separation is carried out on the refined oil product, and the purity of the refined oil product is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of refined oil products, and in particular to an oil quality inspection method and system for refined oil unloading. Background Art

[0002] Finished oil refers to gasoline, kerosene, diesel and other alternative fuels that meet national product quality standards and have the same uses, such as ethanol gasoline and biodiesel. Finished oil is produced in refineries through a series of complex refining processes such as crude oil distillation, catalytic cracking, and hydrotreating to meet different energy needs.

[0003] However, although the finished oil has undergone comprehensive analysis and inspection by the refinery before leaving the factory, there may be quality changes during long-distance transportation, which will increase the suspended matter in the finished oil tank. When receiving the transported finished oil, the recipient needs to conduct quality inspection on all suspended matter in the finished oil. If the suspended matter is not separated, the finished oil in the storage tank will be contaminated. If the finished oil in the tank is directly purified, it will consume a lot of testing time and finished oil purification time.

[0004] To this end, we propose an oil quality inspection method and system for finished oil unloading. Summary of the invention

[0005] The object of the present invention is to provide an oil quality inspection method and system for finished oil unloading, so as to solve the technical problems in the above background.

[0006] The purpose of the present invention can be achieved through the following technical solutions: In a first aspect, the present invention provides an oil quality inspection method for unloading finished oil, comprising: Step 1: In the historical period, the oil product data during the unloading of finished oil is analyzed to obtain the impurity characterization value, and based on the impurity characterization value, it is determined whether there are impurities in the finished oil sub-area in the oil tank. If there are impurities, the corresponding sub-area is marked as an impurity area; Among them, oil data include color intensity and transparency; Step 2: Based on the impurity area, measure the height of the impurity area, extract the impurity characterization values ​​corresponding to the height of all impurity areas, perform linear fitting on the impurity characterization values ​​of different impurity area heights, obtain the determination coefficient deviation value, determine the impurity distribution information in the fuel tank based on the determination coefficient deviation value, and judge the strength of the linear relationship between the impurity area height and the impurity characterization value; Step 3: Based on the strength of the linear relationship between the height of the impurity region and the impurity characterization value, different prediction models are selected; based on the prediction model, a predicted approach value is obtained through analysis; based on the predicted approach value, whether the impurity performance value of the first box of finished oil in the finished oil unloading process approaches the impurity performance value output by the prediction model is judged; an analysis signal is generated, wherein the analysis signal includes an approach signal and a non-approach signal; based on the approach signal, a cutoff time point is obtained through analysis; Step 4: Based on the non-approaching signal, analyze and obtain the approaching degree characterization value. Based on the approaching degree characterization value, determine whether to generate a control signal. If generated, adjust the impurity characterization threshold, and re-input the adjusted impurity characterization threshold into the value prediction model to obtain the remaining time again.

[0007] In a second aspect, the present invention provides an oil quality inspection system for unloading finished oil, comprising: Data processing module: In the historical period, the oil product data during the unloading of finished oil is analyzed to obtain the impurity characterization value. Based on the impurity characterization value, it is determined whether there are impurities in the finished oil sub-area in the oil tank. If there are impurities, the corresponding sub-area is marked as the impurity area; Among them, oil data include color intensity and transparency; Linear relationship judgment module: Based on the impurity area, measure the height of the impurity area, extract the impurity characterization values ​​corresponding to the height of all impurity areas, perform linear fitting on the impurity characterization values ​​of different impurity area heights, obtain the determination coefficient deviation value, determine the impurity distribution information in the fuel tank based on the determination coefficient deviation value, and judge the strength of the linear relationship between the impurity area height and the impurity characterization value; Model prediction module: based on the strength of the linear relationship between the height of the impurity region and the impurity characterization value, different prediction models are selected, based on the prediction model, a predicted approach value is obtained through analysis, based on the predicted approach value, it is determined whether the impurity performance value of the first box of finished oil in the finished oil unloading process approaches the impurity performance value output by the prediction model, and an analysis signal is generated, wherein the analysis signal includes an approach signal and a non-approach signal, and based on the approach signal, a cutoff time point is obtained through analysis; Control analysis module: Based on the non-approaching signal, the approach degree characterization value is analyzed and then judged whether to generate a control signal. If so, the impurity characterization threshold is adjusted and the adjusted impurity characterization threshold is re-input into the value prediction model to obtain the remaining time.

[0008] Beneficial effects of the present invention: (1) The present invention is based on analyzing the oil product data during the unloading of finished oil in the historical period to obtain the impurity characterization value, and judging whether there are impurities in the finished oil sub-region in the oil tank based on the impurity characterization value. If there are impurities, the corresponding sub-region is marked as the impurity region, wherein the oil product data includes color intensity and transparency. The present invention can timely discover and mark the impurity region in the oil tank through the analysis of the oil product data, thereby avoiding the influence of impurities on the quality of the entire oil product. By performing impurity analysis during the unloading process, potential impurity problems can be discovered in time, and corresponding measures can be taken to deal with them, which is helpful to optimize the unloading process and reduce oil pollution caused by impurities; (2) The present invention measures the height of the impurity region based on the impurity region, extracts the impurity characterization values ​​corresponding to the heights of all the impurity regions, performs linear fitting on the impurity characterization values ​​of different impurity region heights, obtains the determination coefficient deviation value, determines the impurity distribution information in the oil tank based on the determination coefficient deviation value, judges the strength of the linear relationship between the impurity region height and the impurity characterization value, selects different prediction models based on the strength of the linear relationship between the impurity region height and the impurity characterization value, analyzes and obtains the predicted approach value based on the prediction model, judges whether the impurity performance value of the first box of finished oil in the finished oil unloading process is close to the impurity performance value output by the prediction model based on the predicted approach value, and generates an analysis signal, wherein the analysis signal includes The invention includes approaching signals and non-approaching signals, and analyzes and obtains the cutoff time point based on the approaching signals, and obtains the approach degree characterization value based on the non-approaching signals, and determines whether to generate the control signal based on the approach degree characterization value. If generated, the impurity characterization threshold is adjusted, and the adjusted impurity characterization threshold is re-input into the prediction model to obtain the remaining time again. The invention analyzes the linear relationship between the height of the impurity area of ​​the finished oil in the fuel tank and the impurity characterization value, and then selects different prediction models, and verifies the selected prediction models, which is conducive to accurately judging the accuracy of the model prediction, and then the cutoff time point of the impurity area of ​​the finished oil can be obtained, the finished oil can be truncated and separated, and the purity of the finished oil can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The present invention will be further described below in conjunction with the accompanying drawings.

[0010] Figure 1 It is a flowchart of an oil quality inspection method for finished oil unloading according to an embodiment of the present invention; Figure 2 It is a system block diagram of an oil quality inspection system for finished oil unloading according to an embodiment of the present invention; Figure 3 It is a schematic diagram of the structure of an oil quality inspection system for finished oil unloading according to an embodiment of the present invention; Figure numbers: 3, computer device; 301, processor; 302, memory; 303, computer program. DETAILED DESCRIPTION

[0011] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0012] Example 1

[0013] Figure 1 The flowchart of the oil quality inspection method for finished oil unloading provided in the first embodiment of the present invention, the embodiment of the present invention can be applied to the suspended matter existing in the oil tank during the unloading process of finished oil, the oil quality inspection method for finished oil unloading can be executed by the oil quality inspection system for finished oil unloading, the oil quality inspection system for finished oil unloading can be implemented by software and / or hardware, and the oil quality inspection system for finished oil unloading can be configured in the oil quality inspection and analysis equipment for finished oil unloading. Optionally, the oil quality inspection equipment for finished oil unloading can be an electronic device, which can be a notebook, a desktop computer, a smart tablet, etc., and the embodiment of the present invention does not limit this.

[0014] like Figure 1 As shown, the oil quality inspection method for finished oil unloading according to the embodiment of the present invention specifically includes: Step 1: In the historical period, the oil product data during the unloading of finished oil is analyzed to obtain the impurity characterization value, and based on the impurity characterization value, it is determined whether there are impurities in the finished oil sub-area in the oil tank. If there are impurities, the corresponding sub-area is marked as an impurity area; Among them, oil data include color intensity and transparency; Divide the finished oil in the oil tank into a number of sub-areas of equal height according to the height of the oil tank; Preset the historical period, and obtain the oil product data of the sub-area when the finished oil is unloaded in the historical period through the edible oil color, transparency and impurity detection device; The color intensity and the color intensity standard value are subjected to difference processing, and the absolute value of the difference is taken to obtain the color intensity deviation value, and the color intensity deviation value is subjected to ratio processing with the color intensity standard value to obtain the color deviation degree ratio SC; The transparency is processed by difference with the transparency standard value, and the absolute value of the difference is taken to obtain the transparency deviation value, and the transparency deviation value is processed by ratio with the transparency standard value to obtain the transparency deviation degree ratio TC; It should be noted that the color intensity standard value and transparency deviation value are set by those skilled in the art based on historical experience; The color deviation ratio SC and transparency deviation ratio TC are processed by the formula: The impurity characterization value ZB is calculated, where a1 and a2 are both preset proportional coefficients, a1 is 1.036, and a2 is 1.881; Compare the Impurity Characterization Value to the Impurity Characterization Threshold: If the impurity characterization value is greater than the impurity characterization threshold, the corresponding sub-region is marked as an impurity region; If the impurity characterization value is less than or equal to the impurity characterization threshold, the corresponding sub-region is marked as a normal region; The technical solution of this embodiment is: within the historical period, the oil product data when the finished oil is unloaded is analyzed to obtain the impurity characterization value, and based on the impurity characterization value, it is determined whether there are impurities in the finished oil sub-region in the oil tank, and if so, the corresponding sub-region is marked as the impurity region, wherein the oil product data includes color intensity and transparency. The present invention can timely discover and mark the impurity region in the oil tank through the analysis of the oil product data, thereby avoiding the influence of impurities on the quality of the entire oil product. Impurity analysis is performed during the unloading process, so that potential impurity problems can be discovered in time, and corresponding measures can be taken to deal with them, which is helpful to optimize the unloading process and reduce oil pollution caused by impurities.

[0015] Example 2

[0016] like Figure 1 As shown, the oil quality inspection method for finished oil unloading provided by the embodiment of the present invention specifically includes: Step 2: Based on the impurity area, measure the height of the impurity area, extract the impurity characterization values ​​corresponding to the height of all impurity areas, perform linear fitting on the impurity characterization values ​​of different impurity area heights, obtain the determination coefficient deviation value, determine the impurity distribution information in the fuel tank based on the determination coefficient deviation value, and judge the strength of the linear relationship between the impurity area height and the impurity characterization value; Specifically, according to the location of the impurity area, the height of the impurity area is obtained by a rangefinder; Extract the impurity characterization values ​​corresponding to the heights of all impurity regions; Use statistical software (such as Excel, Python's matplotlib library) to construct a scatter plot based on the impurity characterization values ​​of different impurity region heights, perform linear regression on the scatter plot, and use the least squares method to fit the linear regression model; Wherein, the X-axis represents the impurity region, and the Y-axis represents the impurity characterization value; The equation for the linear regression model is: , where a is the regression coefficient and b is the intercept; The R² coefficient of determination is used to measure the degree of fit of the linear regression model to the number of historical test data, specifically: By formula: Calculate the R² coefficient of determination; Among them, SSE is the sum of squared errors, which represents the sum of squares of the differences between the model prediction value and the actual value; SST is the sum of squares, which represents the total variation of the dependent variable Y; The obtained determination coefficient is subtracted from 1, and the absolute value of the difference is taken to obtain the determination coefficient deviation value; comparing the coefficient of determination deviation value to the coefficient of determination deviation threshold; If the determination coefficient deviation value is greater than the determination coefficient deviation threshold, it means that the linear relationship between the impurity characterization value and the impurity region is weak; If the determination coefficient deviation value is less than or equal to the determination coefficient deviation threshold, it means that the linear relationship between the impurity characterization value and the impurity region is strong; Step 3: Based on the strength of the linear relationship between the height of the impurity region and the impurity characterization value, different prediction models are selected; based on the prediction model, a predicted approach value is obtained through analysis; based on the predicted approach value, whether the impurity performance value of the first box of finished oil in the finished oil unloading process approaches the impurity performance value output by the prediction model is judged; an analysis signal is generated, wherein the analysis signal includes an approach signal and a non-approach signal; based on the approach signal, a cutoff time point is obtained through analysis; Based on the judgment result of the linear relationship between the impurity characterization value and the impurity region, the impurity characterization values ​​corresponding to different impurity regions are integrated into a training data set. If the linear relationship between the impurity characterization value and the impurity region is strong, the linear regression model is selected as the prediction model. If the linear relationship between the impurity characterization value and the height of the impurity region is weak, the random forest model is selected as the prediction model. Based on the training data set, the prediction model is trained to obtain a trained prediction model. Inputting the impurity characterization threshold into the trained prediction model to obtain the predicted impurity region height; Obtain the flow rate of finished oil unloading, multiply the flow rate of finished oil unloading by the predicted impurity area height, obtain the time point when the impurity characterization threshold is reached during the finished oil unloading process, and mark it as the arrival time point, perform difference processing between the arrival time point and the current time point, obtain the remaining time to reach the impurity characterization threshold during the finished oil unloading process, and mark the time period corresponding to the remaining time as the predicted time period; Divide the prediction period into a number of time nodes with equal time intervals, obtain impurity characterization values ​​at different time nodes within the prediction period, and mark the impurity characterization values ​​at different time nodes within the prediction period as predicted impurity characterization values; Obtain the impurity characterization value of the first box of finished oil unloaded from the finished oil, and mark it as the actual impurity characterization value; Compare the predicted impurity characterization values ​​at different time points with the actual impurity characterization values, specifically: Based on any time point; If the predicted impurity characterization value corresponding to a time node is not equal to the actual impurity characterization value, the corresponding time node is marked as a non-identical time node; If the predicted impurity characterization value corresponding to a time node is equal to the actual impurity characterization value, the corresponding time nodes are marked as the same time nodes; Count the number of non-identical time nodes, and perform ratio processing on the number of non-identical time nodes and the total number of time nodes in the forecast period to obtain the forecast deviation number ratio YS; Obtain the predicted impurity characterization values ​​of non-identical time nodes, perform difference processing on the predicted impurity characterization values ​​of non-identical time nodes and the corresponding actual impurity characterization values, and take the absolute value of the difference to obtain the predicted deviation degree value, sum up and average the predicted deviation degree values ​​of all non-identical time nodes to obtain the predicted deviation degree mean, perform ratio processing on the predicted deviation degree mean and the predicted impurity characterization values ​​of non-identical time nodes to obtain the predicted deviation degree ratio YC; The forecast deviation quantity ratio YS and the forecast deviation degree ratio YC are processed by the formula: The predicted approach value YQ is calculated, where b1 and b2 are preset proportional coefficients, b1 is 1.203, and b2 is 1.341; Compare the predicted approach value to the predicted approach threshold: If the predicted approach value is greater than or equal to the predicted approach threshold, it means that the impurity performance value of the first box of finished oil in the finished oil unloading process does not approach the impurity performance value output by the prediction model, and a non-approach signal is generated; If the predicted approach value is less than the predicted approach threshold, it means that the impurity performance value of the first box of finished oil in the finished oil unloading process is approaching the impurity performance value output by the prediction model, and an approach signal is generated; Based on the approaching signal, when unloading of the second tank of refined oil begins, the second tank of refined oil is separated by taking the time point at which the predicted period arrives as the cutoff time point; Step 4: Based on the non-approaching signal, analyze and obtain the approaching degree characterization value, and based on the approaching degree characterization value, determine whether to generate a control signal. If generated, adjust the impurity characterization threshold, and re-input the adjusted impurity characterization threshold into the value prediction model to obtain the remaining time again; Based on the non-approaching signal, the predicted impurity characterization value of the non-same time node is subjected to difference processing with the corresponding actual impurity characterization value to obtain the impurity deviation value; If the impurity deviation value is greater than 0, the non-identical time nodes are marked as positive deviation nodes; If the impurity deviation value is less than 0, the non-identical time nodes are marked as negative deviation nodes; Count the number of positive deviation nodes and negative deviation nodes, and compare the number of positive deviation nodes with the number of negative deviation nodes, specifically: If the number of positive deviation nodes is greater than the number of negative deviation nodes, the positive deviation nodes are marked as target nodes; If the number of positive deviation nodes is less than the number of negative deviation nodes, the negative deviation nodes are marked as target nodes; If the number of positive deviation nodes is equal to the number of negative deviation nodes, the analysis is stopped, which means that the impurity characterization value of the oil product in the fuel tank is greater than the predicted impurity characterization value at half of the time nodes during the forecast period, and the impurity characterization value of the oil product in the fuel tank is less than the predicted impurity characterization value at half of the time nodes during the forecast period. The degree of change of the impurity characterization value of the oil product in the fuel tank during the forecast period is the same as that of the predicted impurity characterization value. Count the number of target nodes, and perform a ratio process on the number of target nodes and the total number of non-identical nodes to obtain the target node number ratio MS; The impurity deviation values ​​of all target nodes are combined into a deviation value data group, and the variance value PF of the deviation value data group is calculated; The target node number ratio MS, the variance value PF of the deviation value data group, and the predicted deviation number ratio YS corresponding to the non-approaching signal are processed by the formula: The approach degree characterization value QB is calculated, where c1, c2, and c3 are all preset proportional coefficients, c1 takes a value of 1.232, c2 takes a value of 1.031, and c3 takes a value of 1.102; Compare the proximity performance value to the proximity performance threshold: If the approaching degree performance value is greater than the approaching degree performance threshold, it means that the impurity performance value change of the first box of finished oil in the finished oil unloading process is approaching the impurity performance value change output by the prediction model, and a control signal is generated; If the approach degree performance value is less than or equal to the approach degree performance threshold, it means that the impurity performance value change of the first box of finished oil in the finished oil unloading process does not approach the impurity performance value change output by the prediction model, and no operation is performed; Based on the adjustment signal, the impurity deviation values ​​of all target nodes are obtained and summed to obtain the target impurity deviation mean. If the target impurity deviation mean is positive, the impurity characterization threshold and the target impurity deviation mean are subjected to difference processing to obtain the adjusted impurity characterization threshold, and the value prediction model is re-entered to obtain the remaining time. If the target impurity deviation mean is negative, the impurity characterization threshold and the absolute value of the target impurity deviation mean are summed to obtain the adjusted impurity characterization threshold, and the value prediction model is re-entered to obtain the remaining time. The remaining time obtained again is used at the start of unloading the second tank of finished oil, and the time period corresponding to the remaining time obtained again is used as the re-prediction time period, and the time point when the re-prediction time period arrives is used as the cutoff time point to separate the second tank of finished oil; The technical solution of this embodiment is: based on the impurity area, measure the height of the impurity area, extract the impurity characterization values ​​corresponding to the height of all impurity areas, perform linear fitting on the impurity characterization values ​​of different impurity area heights, obtain the determination coefficient deviation value, determine the impurity distribution information in the oil tank based on the determination coefficient deviation value, judge the strength of the linear relationship between the impurity area height and the impurity characterization value, select different prediction models based on the strength of the linear relationship between the impurity area height and the impurity characterization value, analyze and obtain the predicted approach value based on the prediction model, judge whether the impurity performance value of the first box of finished oil in the finished oil unloading process is close to the impurity performance value output by the prediction model based on the predicted approach value, and generate an analysis signal, wherein the analysis signal The signal includes an approach signal and a non-approach signal. Based on the approach signal, a cutoff time point is analyzed and based on the non-approach signal, an approach degree characterization value is analyzed. Based on the approach degree characterization value, it is determined whether a control signal is generated. If generated, the impurity characterization threshold is adjusted, and the adjusted impurity characterization threshold is re-input into the value prediction model to obtain the remaining time again. The present invention analyzes the linear relationship between the height of the impurity area of ​​the finished oil in the fuel tank and the impurity characterization value, and then selects different prediction models, and verifies the selected prediction models, which is conducive to accurately judging the accuracy of the model prediction, and then the cutoff time point of the impurity area of ​​the finished oil can be obtained, the finished oil can be truncated and separated, and the purity of the finished oil can be improved.

[0017] Example 3

[0018] Based on Example 1 and Example 2, please refer to Figure 1 , Figure 2 As shown, the oil quality inspection system for finished oil unloading according to the embodiment of the present invention includes: Data processing module: In the historical period, the oil product data during the unloading of finished oil is analyzed to obtain the impurity characterization value. Based on the impurity characterization value, it is determined whether there are impurities in the finished oil sub-area in the oil tank. If there are impurities, the corresponding sub-area is marked as the impurity area; Among them, oil data include color intensity and transparency; Linear relationship judgment module: Based on the impurity area, measure the height of the impurity area, extract the impurity characterization values ​​corresponding to the height of all impurity areas, perform linear fitting on the impurity characterization values ​​of different impurity area heights, obtain the determination coefficient deviation value, determine the impurity distribution information in the fuel tank based on the determination coefficient deviation value, and judge the strength of the linear relationship between the impurity area height and the impurity characterization value; Model prediction module: based on the strength of the linear relationship between the height of the impurity region and the impurity characterization value, different prediction models are selected, based on the prediction model, a predicted approach value is obtained through analysis, based on the predicted approach value, it is determined whether the impurity performance value of the first box of finished oil in the finished oil unloading process approaches the impurity performance value output by the prediction model, and an analysis signal is generated, wherein the analysis signal includes an approach signal and a non-approach signal, and based on the approach signal, a cutoff time point is obtained through analysis; Control analysis module: Based on the non-approaching signal, the approach degree characterization value is analyzed and then judged whether to generate a control signal. If so, the impurity characterization threshold is adjusted and the adjusted impurity characterization threshold is re-input into the value prediction model to obtain the remaining time.

[0019] Example 4

[0020] Reference Figure 3 The embodiment of the present invention further provides a computer device 3, comprising: a memory 302 and a processor 301 and a computer program 303 stored in the memory 302. When the computer program 303 is executed on the processor 301, the oil quality inspection method for finished oil unloading as described in any one of the above methods is implemented.

[0021] The computer device 3 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The computer device 3 may include, but is not limited to, a processor 301 and a memory 302. Those skilled in the art will appreciate that Figure 3 It is only an example of computer device 3 and does not constitute a limitation on computer device 3. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components, for example, it may also include input and output devices, network access devices, etc.

[0022] The processor 301 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0023] In some embodiments, the memory 302 may be an internal storage unit of the computer device 3, such as a hard disk or memory of the computer device 3. In other embodiments, the memory 302 may also be an external storage device of the computer device 3, such as a plug-in hard disk, a smart memory card (SmartMediaCard, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the computer device 3. Further, the memory 302 may also include both an internal storage unit of the computer device 3 and an external storage device. The memory 302 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program, etc. The memory 302 may also be used to temporarily store data that has been output or is to be output.

[0024] Example 5

[0025] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the oil quality inspection method for finished oil unloading as described in any one of the above methods is implemented.

[0026] In this embodiment, if the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, USB flash drive, mobile hard disk, disk or optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0027] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0028] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0029] In the embodiments disclosed in the present application, it should be understood that the disclosed apparatus / terminal equipment and method can be implemented in other ways. For example, the apparatus / terminal equipment embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. One point, the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, which may be electrical, mechanical or other forms.

[0030] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0031] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0032] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A method for inspecting the quality of finished oil during unloading, characterized in that: include: Step 1: In the historical period, the oil product data during the unloading of finished oil is analyzed to obtain the impurity characterization value, and based on the impurity characterization value, it is determined whether there are impurities in the finished oil sub-area in the oil tank. If there are impurities, the corresponding sub-area is marked as an impurity area; Among them, oil data include color intensity and transparency; Step 2: Based on the impurity area, measure the height of the impurity area, extract the impurity characterization values ​​corresponding to the height of all impurity areas, perform linear fitting on the impurity characterization values ​​of different impurity area heights, obtain the determination coefficient deviation value, determine the impurity distribution information in the fuel tank based on the determination coefficient deviation value, and judge the strength of the linear relationship between the impurity area height and the impurity characterization value; Step 3: Based on the strength of the linear relationship between the height of the impurity region and the impurity characterization value, different prediction models are selected; based on the prediction model, a predicted approach value is obtained through analysis; based on the predicted approach value, whether the impurity performance value of the first box of finished oil in the finished oil unloading process approaches the impurity performance value output by the prediction model is judged; an analysis signal is generated, wherein the analysis signal includes an approach signal and a non-approach signal; based on the approach signal, a cutoff time point is obtained through analysis; Step 4: Based on the non-approaching signal, analyze and obtain the approaching degree characterization value. Based on the approaching degree characterization value, determine whether to generate a control signal. If generated, adjust the impurity characterization threshold, and re-input the adjusted impurity characterization threshold into the value prediction model to obtain the remaining time again.

2. The oil quality inspection method for finished oil unloading according to claim 1, characterized in that: The impurity characterization value is obtained in the following manner: The color intensity and transparency of finished oil products during the historical period of unloading were analyzed to obtain the color deviation ratio SC and transparency deviation ratio TC; The color deviation ratio SC and transparency deviation ratio TC are processed by the formula: The impurity characterization value ZB is calculated, where a1 and a2 are both preset proportional coefficients.

3. The oil quality inspection method for finished oil unloading according to claim 2, characterized in that: The color deviation ratio SC and the transparency deviation ratio TC are obtained as follows: Divide the finished oil in the oil tank into a number of sub-areas of equal height according to the height of the oil tank; Preset the historical period, and obtain the oil product data of the sub-area when the finished oil is unloaded in the historical period through the edible oil color, transparency and impurity detection device; The color intensity and the color intensity standard value are subjected to difference processing, and the absolute value of the difference is taken to obtain the color intensity deviation value, and the color intensity deviation value is subjected to ratio processing with the color intensity standard value to obtain the color deviation degree ratio SC; The transparency is processed by performing difference processing on the transparency standard value, and the absolute value of the difference is taken to obtain the transparency deviation value, and the transparency deviation value is processed by performing ratio processing on the transparency standard value to obtain the transparency deviation degree ratio TC.

4. The oil quality inspection method for finished oil unloading according to claim 1, characterized in that: The determination coefficient deviation value is obtained as follows: According to the location of the impurity area, the height of the impurity area is obtained by using a rangefinder; Extract the impurity characterization values ​​corresponding to the heights of all impurity regions; The linear regression model is fitted using the least square method according to the impurity characterization values ​​of different impurity region heights; By formula: Calculate the R² coefficient of determination; Among them, SSE is the residual sum of squares, which represents the sum of squares of the differences between the model predicted values ​​and the actual values; SST is the total sum of squares, which represents the total variation of the dependent variable Y; The obtained determination coefficient is subtracted from 1, and the absolute value of the difference is taken to obtain the determination coefficient deviation value.

5. The oil quality inspection method for finished oil unloading according to claim 1, characterized in that: The method for obtaining the predicted approximate value is as follows: The judgment result of the strength of the linear relationship between the impurity characterization value and the height of the impurity area is analyzed to obtain a trained prediction model. Based on the trained prediction model, a prediction period in which the impurity characterization threshold is reached during the unloading process of the finished oil is determined. Based on the prediction period, a predicted impurity characterization value is determined. The predicted impurity characterization value of the prediction period is compared with the actual impurity characterization value of the first box of finished oil, and the prediction deviation quantity ratio YS and the prediction deviation degree ratio YC are obtained by analysis. The forecast deviation quantity ratio YS and the forecast deviation degree ratio YC are processed by the formula: The predicted approach value YQ is calculated, where b1 and b2 are both preset proportional coefficients; Based on the predicted approach value, it is compared with the predicted approach threshold to determine the approach signal. Based on the approach signal, when the unloading of the second tank of finished oil begins, the second tank of finished oil is separated with the arrival time point of the predicted time period as the cutoff time point.

6. The oil quality inspection method for finished oil unloading according to claim 5, characterized in that: The method for obtaining the prediction deviation quantity ratio YS and the prediction deviation degree ratio YC is as follows: Based on the judgment result of the linear relationship between the impurity characterization value and the impurity region, the impurity characterization values ​​corresponding to different impurity regions are integrated into a training data set, an applicable prediction model is selected, and the prediction model is trained based on the training data set to obtain a trained prediction model; Inputting the impurity characterization threshold into the trained prediction model to obtain the predicted impurity region height; Obtain the flow rate of finished oil unloading, multiply the flow rate of finished oil unloading by the predicted impurity area height, obtain the time point when the impurity characterization threshold is reached during the finished oil unloading process, and mark it as the arrival time point, perform difference processing between the arrival time point and the current time point, obtain the remaining time to reach the impurity characterization threshold during the finished oil unloading process, and mark the time period corresponding to the remaining time as the predicted time period; Divide the prediction period into a number of time nodes with equal time intervals, obtain impurity characterization values ​​at different time nodes within the prediction period, and mark the impurity characterization values ​​at different time nodes within the prediction period as predicted impurity characterization values; Obtain the impurity characterization value of the first box of finished oil unloaded from the finished oil, and mark it as the actual impurity characterization value; Compare the predicted impurity characterization values ​​at different time points with the actual impurity characterization values, specifically: Based on any time point; If the predicted impurity characterization value corresponding to a time node is not equal to the actual impurity characterization value, the corresponding time node is marked as a non-identical time node; Count the number of non-identical time nodes, and perform ratio processing on the number of non-identical time nodes and the total number of time nodes in the forecast period to obtain the forecast deviation number ratio YS; Obtain the predicted impurity characterization values ​​of non-identical time nodes, perform difference processing on the predicted impurity characterization values ​​of non-identical time nodes and the corresponding actual impurity characterization values, and take the absolute value of the difference to obtain the predicted deviation degree value, sum and average the predicted deviation degree values ​​of all non-identical time nodes to obtain the predicted deviation degree mean, perform ratio processing on the predicted deviation degree mean and the predicted impurity characterization values ​​of non-identical time nodes to obtain the predicted deviation degree ratio YC.

7. The oil quality inspection method for finished oil unloading according to claim 6, characterized in that: The approach degree characterization value QB is obtained in the following manner: Based on the non-approaching signal, the predicted impurity characterization values ​​of non-identical time nodes are compared and analyzed with the corresponding actual impurity characterization values ​​to obtain the target node quantity ratio MS and the variance value PF of the deviation value data group; The target node number ratio MS, the variance value PF of the deviation value data group, and the predicted deviation number ratio YS corresponding to the non-approaching signal are processed by the formula: The approach degree characterization value QB is calculated, where c1, c2, and c3 are all preset proportional coefficients.

8. The oil quality inspection method for finished oil unloading according to claim 7, characterized in that: The target node number ratio MS and the variance value PF of the deviation value data group are obtained as follows: Based on the non-approaching signal, the predicted impurity characterization value of the non-same time node is subjected to difference processing with the corresponding actual impurity characterization value to obtain the impurity deviation value; If the impurity deviation value is greater than 0, the non-identical time nodes are marked as positive deviation nodes; If the impurity deviation value is less than 0, the non-identical time nodes are marked as negative deviation nodes; Count the number of positive deviation nodes and negative deviation nodes, and compare the number of positive deviation nodes with the number of negative deviation nodes, specifically: If the number of positive deviation nodes is greater than the number of negative deviation nodes, the positive deviation nodes are marked as target nodes; If the number of positive deviation nodes is less than the number of negative deviation nodes, the negative deviation nodes are marked as target nodes; If the number of positive deviation nodes is equal to the number of negative deviation nodes, the analysis is stopped, which means that the impurity characterization value of the oil product in the fuel tank is greater than the predicted impurity characterization value at half of the time nodes during the forecast period, and the impurity characterization value of the oil product in the fuel tank is less than the predicted impurity characterization value at half of the time nodes during the forecast period. The degree of change of the impurity characterization value of the oil product in the fuel tank during the forecast period is the same as that of the predicted impurity characterization value. Count the number of target nodes, and perform a ratio process on the number of target nodes and the total number of non-identical nodes to obtain the target node number ratio MS; The impurity deviation values ​​of all target nodes are combined into a deviation value data group, and the variance value PF of the deviation value data group is calculated.

9. The oil quality inspection method for finished oil unloading according to claim 8, characterized in that: The specific process of adjusting the impurity characterization threshold is as follows: Based on the adjustment signal, the impurity deviation values ​​of all target nodes are obtained and summed to obtain the target impurity deviation mean. If the target impurity deviation mean is positive, the impurity characterization threshold and the target impurity deviation mean are subjected to difference processing to obtain the adjusted impurity characterization threshold, and the value prediction model is re-entered to obtain the remaining time. If the target impurity deviation mean is negative, the impurity characterization threshold and the absolute value of the target impurity deviation mean are summed to obtain the adjusted impurity characterization threshold, and the value prediction model is re-entered to obtain the remaining time. The remaining time obtained again is used as the start of unloading the second tank of finished oil. The time period corresponding to the remaining time obtained again is used as the re-prediction time period. The time point when the re-prediction time period is reached is used as the cutoff time point to separate the second tank of finished oil.

10. Oil quality inspection system for finished oil unloading, characterized in that: The system is used to execute the method described in any one of claims 1 to 9, and the system comprises: Data processing module: In the historical period, the oil product data during the unloading of finished oil is analyzed to obtain the impurity characterization value. Based on the impurity characterization value, it is determined whether there are impurities in the finished oil sub-area in the oil tank. If there are impurities, the corresponding sub-area is marked as the impurity area; Among them, oil data include color intensity and transparency; Linear relationship judgment module: Based on the impurity area, measure the height of the impurity area, extract the impurity characterization values ​​corresponding to the height of all impurity areas, perform linear fitting on the impurity characterization values ​​of different impurity area heights, obtain the determination coefficient deviation value, determine the impurity distribution information in the fuel tank based on the determination coefficient deviation value, and judge the strength of the linear relationship between the impurity area height and the impurity characterization value; Model prediction module: based on the strength of the linear relationship between the height of the impurity region and the impurity characterization value, different prediction models are selected, based on the prediction model, a predicted approach value is obtained through analysis, based on the predicted approach value, it is determined whether the impurity performance value of the first box of finished oil in the finished oil unloading process approaches the impurity performance value output by the prediction model, and an analysis signal is generated, wherein the analysis signal includes an approach signal and a non-approach signal, and based on the approach signal, a cutoff time point is obtained through analysis; Control analysis module: Based on the non-approaching signal, the approach degree characterization value is analyzed and then judged whether to generate a control signal. If so, the impurity characterization threshold is adjusted and the adjusted impurity characterization threshold is re-input into the value prediction model to obtain the remaining time.

Images