Rapid detection method and system for diesel oil and aviation kerosene mixing based on near infrared spectrum

Abstract

The invention relates to the technical field of petrochemical engineering detection, in particular to a method and a system for rapidly detecting mixing of diesel oil and aviation kerosene based on a near infrared spectrum. The method comprises the following steps: collecting aviation kerosene and diesel oil standard samples covering different producing areas and batches, and collecting spectral data by adopting a near-infrared spectrometer in a constant-temperature environment; a partial least square method is combined with a data weighting optimization strategy, and a quantitative analysis model covering the full mixing proportion is constructed; collecting 1-5mL of an oil sample to be detected, directly putting the sample into a portable near-infrared detection instrument, scanning in an environment of-10 DEG C to 50 DEG C to obtain a spectral signal, and inputting the signal into the optimized quantitative model for data analysis; outputting the diesel fuel and aviation fuel mixing proportion of the to-be-tested sample by the model; the system comprises a spectrum acquisition module, a model construction module, a signal analysis module and a mixing proportion judgment and result output module. The aim of quickly, accurately and nondestructively detecting the aviation kerosene on a transportation site is fulfilled.

Description

Technical Field

[0001] This invention relates to the field of petrochemical testing technology, and in particular to a rapid detection method and system for diesel fuel and aviation kerosene blending based on near-infrared spectroscopy. Background Technology

[0002] As a core strategic resource of the air transport system, aviation kerosene's quality stability and transport safety are directly related to the reliability of flight takeoffs and landings and the safety of air passengers. However, during long-distance transfers and multi-segment circulation, it faces serious risks of fuel theft and contamination. Driven by the significant price difference between aviation kerosene and diesel, some tanker truck drivers take advantage of service area stops, temporary nighttime parking, or blind spots in remote road sections to illegally extract aviation kerosene from the tanks by privately modifying unloading valves and installing concealed extraction pipes. To compensate for the difference in fuel level, they often mix in low-grade diesel, waste engine oil, or illegally added antifreeze, directly contaminating the remaining aviation kerosene. This leads to huge direct economic losses for companies and poses multiple safety hazards: aviation kerosene and diesel have fundamentally different physical and chemical properties, and mixing them can cause severe wear on the tanker truck engine or even cause combustion and explosion accidents. If contaminated aviation kerosene flows into aircraft, it may lead to poor fuel nozzle atomization and icing blockage of fuel lines at high altitudes, posing fatal flight safety risks.

[0003] Currently, the industry primarily relies on offline laboratory testing technologies such as gas chromatography and gas chromatography-mass spectrometry (GC-MS) for detecting the blending of jet fuel and diesel. While these methods can achieve a certain level of accuracy in detecting the blending ratio, they have significant limitations: the testing cycle is lengthy, with a single test taking 4 to 24 hours, making it unsuitable for the dynamic monitoring needs of transport vehicles; the operational technical threshold is high, requiring specialized personnel to operate in specific laboratory environments, making it difficult to adapt to the complex working conditions at transport sites; the testing cost is high, and it is a destructive test, resulting in waste of jet fuel and chemical reagents. Traditional manual inspections can only observe surface features such as fuel level gauges and the integrity of seals, with a detection rate of less than 10% for concealed fuel theft methods, leading to a predicament of "difficult to detect, difficult to investigate, and weak deterrence" in jet fuel transportation supervision.

[0004] In conclusion, it is essential to propose a rapid detection method and system for diesel-jet fuel blending based on near-infrared spectroscopy, which enables fast, accurate, and non-destructive testing of aviation kerosene at the transportation site. Summary of the Invention

[0005] The purpose of this invention is to provide a rapid detection method and system for diesel fuel and aviation kerosene based on near-infrared spectroscopy, which enables rapid, accurate and non-destructive testing of aviation kerosene at the transportation site.

[0006] To achieve the above objectives, the present invention employs a rapid detection method for diesel fuel and aviation kerosene blending based on near-infrared spectroscopy, comprising the following steps: Standard samples of jet fuel and diesel fuel from different origins and batches were collected, and parallel samples were prepared with a blending ratio of 0% to 100%. Spectral data were collected using a near-infrared spectrometer under constant temperature conditions. Based on the preprocessed spectral data, combined with the absorption differences between diesel and jet fuel at characteristic wavelengths, a quantitative analysis model covering the full blending ratio was constructed using partial least squares method combined with data weighted optimization strategy. The model was then cross-validated using leave-one-out method. Collect 1-5 mL of the oil sample to be tested and place it directly into a portable near-infrared detector. Scan the spectral signal at an environment of -10℃ to 50℃ and input the signal into the optimized quantitative model for data analysis. The model outputs the diesel-jet fuel blending ratio of the sample to be tested, and a blending ratio of ≥5% is considered unqualified.

[0007] Among the steps, in collecting standard samples of jet fuel and diesel fuel covering different origins and batches, preparing parallel samples with a blending ratio of 0% to 100%, and collecting spectral data using a near-infrared spectrometer under constant temperature conditions: Aviation kerosene and diesel fuel from different origins and multiple production batches that meet the corresponding national standards were selected as basic standard samples. The gradient was designed with a mixing ratio of 0% to 100%, with a low ratio range of 1% to 5% where the ratio was set more densely. Parallel samples containing blank controls were prepared for each ratio. Under constant temperature conditions, near-infrared spectrometers with a specified wavelength range were used to collect spectral data of each standard sample according to preset parameters. The wavelength range of the near-infrared spectrometer was 780~2526nm.

[0008] The step of collecting spectral data of each standard sample under a constant temperature environment using a near-infrared spectrometer with a specified wavelength range and according to preset parameters is as follows: A four-step purification method, consisting of baseline correction, smoothing and denoising, multivariate scattering correction, and standard normal variable transformation, was used to preprocess the acquired raw spectral data to eliminate interference factors.

[0009] Among these steps, based on preprocessed spectral data and considering the absorption differences between diesel and jet fuel at characteristic wavelengths, a quantitative analysis model covering the entire blending ratio is constructed using partial least squares combined with a data weighted optimization strategy. The model is then validated using the leave-one-out method. Extract the absorption peak information of diesel and jet fuel at characteristic wavelengths from the preprocessed spectral data to determine the spectral differences between the two. A preliminary quantitative correlation model for the full mixing ratio was constructed by using partial least squares method combined with an optimization strategy that weights data from low-proportion mixed samples. The model was repeatedly tested using leave-one-out cross-validation, and the model parameters were continuously adjusted to enhance the contribution of the characteristic wavelengths.

[0010] After repeatedly testing the model using leave-one-out cross-validation, continuously adjusting the model parameters, and strengthening the contribution of feature wavelengths: Validate model performance, correlation coefficient (R²) 2 With a detection error of ≤2% and a result ≥0.98, the final optimized quantitative analysis model is formed.

[0011] In the step of collecting 1-5 mL of the oil sample to be tested, directly placing it into a portable near-infrared detector, scanning to acquire the spectral signal in an environment of -10℃ to 50℃, and inputting the signal into an optimized quantitative model for data analysis: Collect 1-5 mL of sample from the designated location of the oil sample to be tested and use it directly. No pretreatment is required for the sample. Place the spare sample into the detection pool of the portable near-infrared detector, where the instrument is in an operating environment of -10℃ to 50℃; The instrument is started to perform a spectral scan on the sample, quickly acquiring the spectral signal of the sample to be tested, and then converting the spectral signal into data.

[0012] The process includes the steps of starting the instrument to perform a spectral scan on the sample, quickly acquiring the spectral signal of the sample to be tested, and then converting the spectral signal into data: The converted spectral signal is input into the optimized quantitative analysis model, which then automatically performs data comparison and analysis.

[0013] In the step where the model outputs the diesel-jet fuel blending ratio of the sample to be tested, and the sample is deemed unqualified when the blending ratio is ≥5%: Receive the specific numerical value of the diesel-jet fuel blending ratio of the sample to be tested, output by the quantitative analysis model; According to the preset judgment criteria, determine whether the mixing ratio reaches or exceeds the threshold of 5%; Generate a test result report, clearly indicating the mixing ratio and the judgment conclusion.

[0014] In the step of determining whether the mixing ratio reaches or exceeds the 5% threshold by comparing it with preset judgment criteria: If the blending ratio is ≥5%, the oil sample to be tested is deemed unqualified; if it is less than 5%, it is deemed qualified.

[0015] This invention also provides a rapid detection system for diesel fuel and aviation kerosene blending based on near-infrared spectroscopy, comprising a spectral acquisition module, a model construction module, a signal analysis module, and a blending ratio determination and result output module; wherein: The spectral acquisition module is used to collect standard samples of jet fuel and diesel fuel covering different origins and batches, prepare parallel samples with a mixing ratio of 0% to 100%, and collect spectral data using a near-infrared spectrometer under constant temperature conditions. The model building module is used to construct a quantitative analysis model covering the full blending ratio based on preprocessed spectral data, combined with the absorption difference between diesel and jet fuel at characteristic wavelengths, using partial least squares method combined with data weighting optimization strategy, and cross-validating the model through leave-one-out method. The signal analysis module is used to perform near-infrared detection on oil samples, scan and acquire spectral signals in an environment of -10℃ to 50℃, and input the signals into an optimized quantitative model for data analysis. The blending ratio determination and result output module is used to output the diesel-jet fuel blending ratio of the sample to be tested. When the blending ratio is ≥5%, it is determined to be unqualified.

[0016] This invention discloses a rapid detection method and system for diesel and aviation kerosene blending based on near-infrared spectroscopy. The method comprises the following steps: collecting standard samples of aviation kerosene and diesel fuel from different origins and batches, preparing parallel samples with blending ratios ranging from 0% to 100%, and acquiring spectral data using a near-infrared spectrometer under constant temperature conditions; based on the preprocessed spectral data and considering the absorption differences between diesel and aviation kerosene at characteristic wavelengths, constructing a quantitative analysis model covering all blending ratios using partial least squares and a data weighted optimization strategy, and cross-validating the model using leave-one-out cross-validation; collecting 1-5 mL samples of the fuel to be tested and directly placing them into a portable near-infrared detector, scanning to acquire spectral signals at -10℃ to 50℃, and inputting the signals into the optimized quantitative model for data analysis; the model outputs the diesel and aviation kerosene blending ratio of the sample, wherein a blending ratio ≥ 5% is considered unqualified. This method achieves the goal of rapid, accurate, and non-destructive testing of aviation kerosene at the transportation site. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart of the steps of the rapid detection method for diesel fuel and aviation kerosene based on near-infrared spectroscopy of the present invention.

[0019] Figure 2 This is a flowchart of steps S100 of the present invention.

[0020] Figure 3 This is a flowchart of steps S200 of the present invention.

[0021] Figure 4 This is a flowchart of steps S300 of the present invention.

[0022] Figure 5 This is a flowchart of steps S400 of the present invention.

[0023] Figure 6 This is a schematic diagram of the principle of the rapid detection system for diesel fuel and aviation kerosene based on near-infrared spectroscopy of the present invention.

[0024] Figure 7 This is a schematic diagram of the electronic device of the present invention.

[0025] 501 - Spectrum acquisition module, 502 - Model construction module, 503 - Signal analysis module, 504 - Mixing ratio determination and result output module. Detailed Implementation

[0026] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application.

[0027] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0028] It should be understood that although the terms first, second, third, etc., may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0029] Please see Figures 1-5 This invention provides a rapid detection method for diesel fuel and jet fuel blending based on near-infrared spectroscopy, comprising the following steps: S100: Collect standard samples of jet fuel and diesel fuel covering different origins and batches, prepare parallel samples with a blending ratio of 0% to 100%, and collect spectral data using a near-infrared spectrometer under constant temperature conditions.

[0030] In this embodiment, standard samples of jet fuel and diesel fuel from different origins and batches were collected, and parallel samples were prepared at a blending ratio of 0% to 100%. Spectral data were collected using a near-infrared spectrometer under constant temperature conditions. The specific process is as follows: S101: Select aviation kerosene and diesel fuel from different origins and multiple production batches that meet the corresponding national standards as basic standard samples; S102: The gradient is designed according to the mixing ratio of 0% to 100%, with the low ratio range of 1% to 5% being densely set, and parallel samples containing blank control are prepared for each ratio. S103: Under constant temperature conditions, use a near-infrared spectrometer with a specified wavelength range to collect spectral data of each standard sample according to preset parameters, wherein the wavelength range of the near-infrared spectrometer is 780~2526nm. S104: A four-step purification method, consisting of baseline correction, smoothing and denoising, multivariate scattering correction, and standard normal variable transformation, is used to preprocess the acquired raw spectral data to eliminate interference factors.

[0031] In the above process, firstly, jet fuel and diesel fuel from different origins and multiple production batches that meet the corresponding national standards are selected as basic standard samples; then, a gradient is designed according to the blending ratio of 0% to 100%, with the low ratio range of 1% to 5% being more densely set, and parallel samples containing blank controls are prepared for each ratio; under constant temperature environment, spectral data of each standard sample are collected using a near-infrared spectrometer with a specified wavelength range of 780 to 2526 nm according to preset parameters; then, a four-step purification method of baseline correction, smoothing and denoising, multivariate scattering correction and standard normal variable transformation is used to preprocess the collected raw spectral data to eliminate interference factors.

[0032] S200: Based on the preprocessed spectral data and combined with the absorption differences between diesel and jet fuel at characteristic wavelengths, a quantitative analysis model covering the full blending ratio is constructed using partial least squares method combined with data weighted optimization strategy, and the model is cross-validated using leave-one-out method.

[0033] In this embodiment, based on the preprocessed spectral data and the absorption differences between diesel and jet fuel at characteristic wavelengths, a quantitative analysis model covering the full blending ratio is constructed using partial least squares method combined with a data weighted optimization strategy. The model is then validated using leave-one-out cross-validation. The specific process is as follows: S201: Extract the absorption peak information of diesel and jet fuel at characteristic wavelengths from the preprocessed spectral data to determine the spectral differences between the two. S202: Using partial least squares method combined with a weighted optimization strategy of low proportion mixed sample data, a preliminary quantitative correlation model of the full mixing ratio is constructed. S203: The model is repeatedly tested using leave-one-out cross-validation to continuously adjust the model parameters and enhance the contribution of the characteristic wavelengths; S204: Validate model performance, correlation coefficient (R²) 2 With a detection error of ≤2% and a result ≥0.98, the final optimized quantitative analysis model is formed.

[0034] In the above process, firstly, the absorption peak information of diesel and jet fuel at characteristic wavelengths is extracted from the preprocessed spectral data to determine the spectral differences between the two. Then, partial least squares method is used, combined with a weighted optimization strategy of low-proportion blended sample data, to initially construct a quantitative correlation model for the full blending ratio. Next, the model is repeatedly tested using leave-one-out cross-validation to continuously adjust the model parameters and strengthen the contribution of characteristic wavelengths. Finally, the model performance is verified, and the correlation coefficient (R²) is measured. 2 With a detection error of ≤2% and a result ≥0.98, the final optimized quantitative analysis model is formed.

[0035] S300: Collect 1~5mL of the oil sample to be tested, place it directly into a portable near-infrared detector, scan to obtain the spectral signal in an environment of -10℃~50℃, and input the signal into the optimized quantitative model for data analysis.

[0036] In this embodiment, 1-5 mL of the oil sample to be tested is collected and directly placed into a portable near-infrared spectral analyzer. The spectral signal is acquired by scanning at an environment of -10℃ to 50℃. The signal is then input into an optimized quantitative model for data analysis. The specific process is as follows: S301: Collect 1-5 mL of sample from the designated location of the oil sample to be tested, and use it directly. No pretreatment is required for the sample. S302: Place the spare sample into the detection cell of the portable near-infrared detector, where the instrument is in an operating environment of -10℃ to 50℃; S303: Start the instrument to perform a spectral scan on the sample, quickly acquire the spectral signal of the sample to be tested, and convert the spectral signal into data; S304: Input the converted spectral signal into the optimized quantitative analysis model, and the model will automatically perform data comparison and analysis.

[0037] In the above process, firstly, 1-5 mL of sample is collected from a designated location of the oil sample to be tested and set aside directly without any pretreatment. Then, the prepared sample is placed in the detection cell of a portable near-infrared detector, which operates in an environment of -10℃ to 50℃. Next, the instrument is started to perform a spectral scan on the sample, quickly acquiring the spectral signal of the sample to be tested, and converting the spectral signal into data. Then, the converted spectral signal is input into an optimized quantitative analysis model, which automatically performs data comparison and analysis.

[0038] S400: The model outputs the diesel-jet fuel blending ratio of the sample to be tested. When the blending ratio is ≥5%, it is judged as unqualified.

[0039] In this embodiment, the model outputs the diesel-jet fuel blending ratio of the sample to be tested. A blending ratio ≥ 5% is considered unqualified. The specific process is as follows: S401: Receives the specific numerical value of the diesel-jet fuel blending ratio of the sample to be tested, output by the quantitative analysis model; S402: Determine whether the mixing ratio reaches or exceeds the 5% threshold by comparing with the preset judgment criteria; S403: Generate a test result report, clearly indicating the mixing ratio and judgment conclusion.

[0040] In the above process, the specific value of the blending ratio of diesel and aviation kerosene in the sample to be tested is first received from the quantitative analysis model; the blending ratio is compared with the preset judgment standard to determine whether it reaches or exceeds the threshold of 5%. If the blending ratio is ≥5%, the sample to be tested is judged to be unqualified, and if it is less than 5%, it is judged to be qualified; then the test result report is generated, clearly indicating the blending ratio and the judgment conclusion.

[0041] Please see Figure 6 This invention provides a rapid detection system for diesel fuel and aviation kerosene blending based on near-infrared spectroscopy, comprising a spectral acquisition module 501, a model construction module 502, a signal analysis module 503, and a blending ratio determination and result output module 504; wherein: The spectral acquisition module 501 is used to collect standard samples of jet fuel and diesel fuel covering different origins and batches, prepare parallel samples with a mixing ratio of 0% to 100%, and collect spectral data using a near-infrared spectrometer under constant temperature environment. The model building module 502 is used to construct a quantitative analysis model covering the full blending ratio based on the preprocessed spectral data, combined with the absorption difference between diesel and jet fuel at characteristic wavelengths, using partial least squares method combined with data weighting optimization strategy, and cross-validating the model through leave-one-out method. The signal analysis module 503 is used to perform near-infrared detection on oil samples, scan and acquire spectral signals in an environment of -10℃ to 50℃, and input the signals into an optimized quantitative model for data analysis. The blending ratio determination and result output module 504 is used to output the diesel-jet fuel blending ratio of the sample to be tested.

[0042] In this embodiment, the spectral acquisition module 501 collects standard samples of aviation kerosene and diesel fuel from different origins and batches, preparing parallel samples with blending ratios ranging from 0% to 100%. Spectral data is acquired using a near-infrared spectrometer under constant temperature conditions. The model construction module 502, based on the preprocessed spectral data and considering the absorption differences between diesel fuel and aviation kerosene at characteristic wavelengths, employs partial least squares combined with a data weighted optimization strategy to construct a quantitative analysis model covering all blending ratios. The model is then cross-validated using the leave-one-out method. The signal analysis module 503 performs near-infrared detection on the fuel samples, scanning and acquiring spectral signals at temperatures ranging from -10℃ to 50℃. The signals are then input into the optimized quantitative model for data analysis. The blending ratio determination and result output module 504 outputs the diesel-aviation kerosene blending ratio of the sample to be tested. A blending ratio ≥ 5% is considered unqualified. Through this method, the goal of rapid, accurate, and non-destructive testing of aviation kerosene at the transportation site is achieved.

[0043] Regarding the system in the above embodiments, the specific ways in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0044] For the system embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this application according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0045] Beneficial effects: Rapid and efficient testing represents a qualitative leap in regulatory response efficiency: Traditional laboratory gas chromatography requires sample transfer (2 hours), pretreatment (1 hour), and chromatographic separation (4-8 hours), with a single testing cycle exceeding 7 hours, extending to 24 hours in some remote areas. This is completely unsuitable for the dynamic transportation needs of tanker trucks, which travel an average of 300-500 kilometers per day. This project's instrument testing process takes ≤5 minutes, from on-site sampling to result output in one go, achieving "testing completed before the vehicle leaves the station." Regulatory personnel can immediately take measures such as stopping non-compliant vehicles and holding them accountable. This represents a 48-288 times increase in efficiency compared to traditional methods, allowing for the completion of daily random inspections of 30 vehicles within 4 hours, completely resolving the industry pain points of "delayed testing and ineffective control."

[0046] Portability adaptable to various scenarios, breaking the limitations of fixed locations: Traditional laboratory testing equipment is bulky (e.g., the main unit of a gas chromatograph measures 120cm×80cm×60cm) and weighs over 50kg, requiring fixed installation in a temperature- and humidity-controlled laboratory and cannot be moved. The instrument in this project weighs ≤10kg and is only 1 / 10 the size of traditional equipment. It adopts a portable design, allowing regulatory personnel to carry it with them to service areas, provincial border checkpoints, remote road sections, and any other scenario. The waterproof and dustproof casing and wide temperature range design of -10℃ to 50℃ enable it to adapt to complex working conditions such as the severe winters in Northeast China, the high temperatures in South China, and the dusty conditions in the mountainous areas of Southwest China, completely eliminating the constraints of "fixed laboratory + dedicated personnel operation" and achieving "full-scenario coverage and all-time supervision".

[0047] The high precision directly addresses the pain points, ensuring no missed detections of low-proportion adulteration: Traditional manual inspections have a very low detection rate for low-proportion adulteration (below 10%). While laboratory gas chromatography can detect adulteration with an accuracy of 0.1%, its delayed detection makes timely control impossible. This project's model, trained on standard samples and validated with 50 blind samples in the field, achieves a detection error of ≤2% and a 99% accuracy rate for identifying adulteration with a 5% proportion. It can accurately detect drivers' "small-amount, high-frequency" fuel theft, solving the core contradiction of traditional methods: "either not detecting it at all, or not being able to detect it in time."

[0048] Environmentally friendly and economical, with both cost reduction and safety improvements: Traditional gas chromatography requires 20-50 mL of jet fuel sample (which cannot be recovered after testing) and 50 mL of chemical reagents (methanol, acetonitrile, etc.) for a single test. Testing 4000 batches annually would... Wasting 120 tons of aviation kerosene and generating 200 liters of chemical waste not only wastes energy but also poses safety risks such as reagent leakage and personnel poisoning. This project's instrument requires only 1-5 mL of sample, and the sample can be recycled back to a tanker truck after testing, reducing aviation kerosene waste by 0.8 tons annually; it requires no chemical reagents, reducing reagent consumption by 500 liters and waste disposal costs by 100,000 yuan annually, while avoiding the health hazards of chemical reagents to operators, achieving "zero waste in testing and zero risk in operation."

[0049] This project addresses a key industry pain point: current near-infrared fuel testing equipment, both domestic and international, primarily targets general indicators such as gasoline octane number and diesel cetane number, lacking specific optimization for the "diesel-jet kerosene blending" scenario, and is prohibitively expensive (over 600,000 RMB per unit for imported equipment). This project, closely aligned with the actual needs of regulating jet kerosene transportation theft, specifically developed a spectral feature extraction algorithm and quantitative model to accurately match the differences in chemical composition between the two. The cost per instrument is controlled below 300,000 RMB, and the operating procedures are tailored to the habits of regulatory personnel, allowing for independent operation after just one day of training. This achievement fills the industry gap in rapid on-site testing of diesel-jet kerosene and is the first technical solution specifically designed for regulating jet kerosene transportation theft, directly resolving the regulatory dilemmas faced by enterprises: difficulty in detection, difficulty in prosecution, and weak deterrence.

[0050] Accordingly, this application also provides an electronic device, comprising: one or more processors; a memory for storing one or more programs; and when the one or more programs are executed by the one or more processors, causing the one or more processors to implement the above-described rapid detection method for diesel fuel blending based on near-infrared spectroscopy. Figure 7 The diagram shown is a hardware structure diagram of any device with data processing capabilities, which is part of a rapid detection system for diesel fuel and aviation kerosene based on near-infrared spectroscopy provided in an embodiment of the present invention. Except for... Figure 7 In addition to the processor, memory, and network interface shown, any data processing device in the embodiment may also include other hardware depending on the actual function of the data processing device, which will not be described in detail here.

[0051] Accordingly, this application also provides a computer-readable storage medium storing computer instructions, which, when executed by a processor, implement the aforementioned rapid detection method for diesel fuel blending based on near-infrared spectroscopy. The computer-readable storage medium can be an internal storage unit of any data-processing device as described in any of the foregoing embodiments, such as a hard disk or memory. The computer-readable storage medium can also be an external storage device, such as a plug-in hard disk, smart media card (SMC), SD card, flash card, etc., equipped on the device. Furthermore, the computer-readable storage medium can include both internal storage units of any data-processing device and external storage devices. The computer-readable storage medium is used to store the computer program and other programs and data required by the data-processing device, and can also be used to temporarily store data that has been output or will be output.

[0052] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein.

[0053] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope.

Claims

1. A rapid detection method for diesel fuel and jet fuel blending based on near-infrared spectroscopy, characterized in that, Includes the following steps: Standard samples of jet fuel and diesel fuel from different origins and batches were collected, and parallel samples were prepared with a blending ratio of 0% to 100%. Spectral data were collected using a near-infrared spectrometer under constant temperature conditions. Based on the preprocessed spectral data, combined with the absorption differences between diesel and jet fuel at characteristic wavelengths, a quantitative analysis model covering the full blending ratio was constructed using partial least squares method combined with data weighted optimization strategy. The model was then cross-validated using leave-one-out method. Collect 1-5 mL of the oil sample to be tested and place it directly into a portable near-infrared detector. Scan the spectral signal at an environment of -10℃ to 50℃ and input the signal into the optimized quantitative model for data analysis. The model outputs the diesel-jet fuel blending ratio of the sample to be tested, and a blending ratio of ≥5% is considered unqualified.

2. The rapid detection method for diesel fuel and aviation kerosene based on near-infrared spectroscopy as described in claim 1, characterized in that, In the process of collecting standard samples of jet fuel and diesel fuel covering different origins and batches, preparing parallel samples with a blending ratio of 0% to 100%, and acquiring spectral data using a near-infrared spectrometer under constant temperature conditions: Aviation kerosene and diesel fuel from different origins and multiple production batches that meet the corresponding national standards were selected as basic standard samples. The gradient was designed with a mixing ratio of 0% to 100%, with a low ratio range of 1% to 5% where the ratio was set more densely. Parallel samples containing blank controls were prepared for each ratio. Under constant temperature conditions, near-infrared spectrometers with a specified wavelength range were used to collect spectral data of each standard sample according to preset parameters. The wavelength range of the near-infrared spectrometer was 780~2526nm.

3. The rapid detection method for diesel fuel and aviation kerosene based on near-infrared spectroscopy as described in claim 2, characterized in that, Following the steps of acquiring spectral data of each standard sample under constant temperature conditions using a near-infrared spectrometer with a specified wavelength range and according to preset parameters: A four-step purification method, consisting of baseline correction, smoothing and denoising, multivariate scattering correction, and standard normal variable transformation, was used to preprocess the acquired raw spectral data to eliminate interference factors.

4. The rapid detection method for diesel fuel and aviation kerosene based on near-infrared spectroscopy as described in claim 1, characterized in that, Based on preprocessed spectral data and considering the absorption differences between diesel and jet fuel at characteristic wavelengths, a quantitative analysis model covering the full blending ratio is constructed using partial least squares method combined with a data weighted optimization strategy. The model is then validated using the leave-one-out method. Extract the absorption peak information of diesel and jet fuel at characteristic wavelengths from the preprocessed spectral data to determine the spectral differences between the two. A preliminary quantitative correlation model for the full mixing ratio was constructed by using partial least squares method combined with an optimization strategy that weights data from low-proportion mixed samples. The model was repeatedly tested using leave-one-out cross-validation, and the model parameters were continuously adjusted to enhance the contribution of the characteristic wavelengths.

5. The rapid detection method for diesel fuel and aviation kerosene based on near-infrared spectroscopy as described in claim 4, characterized in that, After repeatedly testing the model using leave-one-out cross-validation, continuously adjusting the model parameters, and strengthening the contribution of characteristic wavelengths: Validate model performance, correlation coefficient (R²) 2 With a detection error of ≤2% and a result ≥0.98, the final optimized quantitative analysis model is formed.

6. The rapid detection method for diesel fuel and aviation kerosene based on near-infrared spectroscopy as described in claim 1, characterized in that, In the process of collecting 1-5 mL of oil sample to be tested, directly placing it into a portable near-infrared spectral analyzer, scanning to acquire spectral signals in an environment of -10℃ to 50℃, and inputting the signals into an optimized quantitative model for data analysis: Collect 1-5 mL of sample from the designated location of the oil sample to be tested and use it directly. No pretreatment is required for the sample. Place the spare sample into the detection pool of the portable near-infrared detector, where the instrument is in an operating environment of -10℃ to 50℃; The instrument is started to perform a spectral scan on the sample, quickly acquiring the spectral signal of the sample to be tested, and then converting the spectral signal into data.

7. The rapid detection method for diesel fuel and aviation kerosene based on near-infrared spectroscopy as described in claim 6, characterized in that, After starting the instrument to perform a spectral scan on the sample, quickly acquiring the spectral signal of the sample to be tested, and then converting the spectral signal into data: The converted spectral signal is input into the optimized quantitative analysis model, which then automatically performs data comparison and analysis.

8. The rapid detection method for diesel fuel and aviation kerosene based on near-infrared spectroscopy as described in claim 1, characterized in that, In the step where the model outputs the diesel-jet fuel blending ratio of the sample to be tested, and the sample is deemed unqualified when the blending ratio is ≥5%: Receive the specific numerical value of the diesel-jet fuel blending ratio of the sample to be tested, output by the quantitative analysis model; According to the preset judgment criteria, determine whether the mixing ratio reaches or exceeds the threshold of 5%; Generate a test result report, clearly indicating the mixing ratio and the judgment conclusion.

9. The rapid detection method for diesel fuel and aviation kerosene based on near-infrared spectroscopy as described in claim 8, characterized in that, In the step of determining whether the mixing ratio reaches or exceeds the 5% threshold by comparing it with the preset judgment criteria: If the blending ratio is ≥5%, the oil sample to be tested is deemed unqualified; if it is less than 5%, it is deemed qualified.

10. A rapid detection system for diesel fuel and jet fuel blending based on near-infrared spectroscopy, applied to the rapid detection method for diesel fuel and jet fuel blending based on near-infrared spectroscopy as described in claim 1, characterized in that, It includes a spectral acquisition module, a model building module, a signal analysis module, and a doping ratio determination and result output module; among which: The spectral acquisition module is used to collect standard samples of jet fuel and diesel fuel covering different origins and batches, prepare parallel samples with a mixing ratio of 0% to 100%, and collect spectral data using a near-infrared spectrometer under constant temperature conditions. The model building module is used to construct a quantitative analysis model covering the full blending ratio based on preprocessed spectral data, combined with the absorption difference between diesel and jet fuel at characteristic wavelengths, using partial least squares method combined with data weighting optimization strategy, and cross-validating the model through leave-one-out method. The signal analysis module is used to perform near-infrared detection on oil samples, scan and acquire spectral signals in an environment of -10℃ to 50℃, and input the signals into an optimized quantitative model for data analysis. The blending ratio determination and result output module is used to output the diesel-jet fuel blending ratio of the sample to be tested. When the blending ratio is ≥5%, it is determined to be unqualified.

Images