A method and system for detecting the quality of heavy oil based on multispectral fusion

Abstract

The present invention relates to the field of heavy oil quality detection, in particular to a heavy oil quality detection method and system based on multi-spectrum fusion. When preprocessing multi-spectrum data by using the moving average detrending method, the multi-spectrum data is first classified into extreme value interval multi-spectrum data and ordinary interval multi-spectrum data, and then different methods are used for data preprocessing according to different data types. For the ordinary interval multi-spectrum data, the conventional moving average detrending method is used for data preprocessing, and for the extreme value interval multi-spectrum data, the window attenuation method is used for preprocessing. And when encountering extreme value points, the method of skipping the extreme value points and then restoring the initial window is adopted, which can effectively reduce the influence of the detrending algorithm on the extreme value points in the multi-spectrum data and improve the accuracy of data processing; at the same time, the window attenuation and the method of skipping extreme value points also reduce the time of data preprocessing to a certain extent and improve the efficiency of data preprocessing.

Description

Technical Field

[0001] The present invention relates to the field of heavy oil quality detection, and particularly to a heavy oil quality detection method and system based on multi-spectrum fusion. Background Art

[0002] Heavy oil is an important energy resource, and its quality detection is of great significance for oil processing, transportation, and use. Traditional heavy oil quality detection methods mainly rely on chemical analysis and physical tests, which are usually time-consuming, complex to operate, and destructive to samples. In recent years, spectral technology has been widely used in oil product detection, but single spectral technology often has limitations and cannot comprehensively reflect the complex characteristics of heavy oil.

[0003] Multi-spectrum fusion technology can achieve complementary advantages by integrating different types of spectral data, thereby providing more comprehensive and reliable detection results. For example, in the detection of mineral oil, the multi-spectrum fusion method combining infrared spectroscopy and Raman spectroscopy has been proven to significantly improve the detection accuracy. However, the current multi-spectrum fusion technology for heavy oil quality detection is still in the development stage, and the data preprocessing process is accurate and efficient. Therefore, there is a lack of efficient and accurate detection systems and methods. Summary of the Invention

[0004] In order to solve the above technical problems, the present invention provides a heavy oil quality detection method and system based on multi-spectrum fusion to solve the problems existing in the prior art.

[0005] The present invention provides a heavy oil quality detection method based on multi-spectrum fusion, including the following steps:

[0006] S1: Perform multi-spectrum acquisition on a heavy oil sample to obtain multi-spectrum data;

[0007] S2: Perform data preprocessing operations on the multi-spectrum data to obtain preprocessed multi-spectrum data;

[0008] The preprocessing operations include standard normal variate transformation preprocessing and moving average detrending algorithm preprocessing;

[0009] The specific operation of performing data preprocessing on the multi-spectrum data using the moving average detrending algorithm is as follows:

[0010] S2.a: Perform Fourier transform on the multi-spectrum data to obtain frequency-domain multi-spectrum data;

[0011] S2.b: Identify the extreme points of the multi-spectrum data according to the frequency-domain multi-spectrum data and mark them;

[0012] S2.c: Use the multi - spectral data within a preset range on both sides of the extreme point as the multi - spectral data in the extreme - value interval; use the other multi - spectral data as the multi - spectral data in the normal interval;

[0013] S2.d: Use the first moving average method for data pre - processing of the multi - spectral data in the normal interval;

[0014] S2.e: Use the second moving average method for data pre - processing of the multi - spectral data in the extreme - value interval;

[0015] S3: Perform data fusion operations on the pre - processed multi - spectral data;

[0016] S4: Establish a heavy - oil quality detection model;

[0017] S5: Detect the quality of the heavy oil.

[0018] Preferably, in S2.b, identify the extreme points of the multi - spectral data in the frequency domain through a threshold method; specifically: set the highest value of a preset multiple of the multi - spectral data in the frequency domain as the upper threshold, set the lowest value of a preset multiple of the multi - spectral data in the frequency domain as the lower threshold, traverse the multi - spectral data in the frequency domain, take the local maximum points higher than the upper threshold as extreme points, and take the local minimum points lower than the lower threshold as extreme points.

[0019] Preferably, the preset multiple is 0.5.

[0020] Preferably, in S2.c, the formula for determining the preset range is:

[0021] ;

[0022] In the formula, D is the number of data points in the preset range, a is a coefficient, is the sampling frequency of the i - th multi - spectral data, and D < 20.

[0023] Preferably, in S2.d, the formula for the first moving average method is:

[0024]

[0025] In the formula, is the i - th multi - spectral data after pre - processing by the first moving average method, is the original i - th multi - spectral data, and n is the number of data moving cycles.

[0026] Preferably, in the step S2.e, for the multi-spectrum data in the extreme value interval, the data preprocessing is performed by the second moving average method as follows: set the initial window period number n1, and then perform data preprocessing on the multi-spectrum data with sequentially decaying window period numbers; when moving to the marked extreme point, skip the extreme point, and then set the initial window period number n1 for the value after the extreme point, and then perform data preprocessing on the multi-spectrum data with sequentially decaying window period numbers. The determination formula for the sequentially decaying period number n is:

[0027]

[0028]

[0029] where s is the window period number decay coefficient s.

[0030] Preferably, in the step S3, the wavelet feature fusion method is used to perform data fusion operation on the preprocessed multi-spectrum data.

[0031] Preferably, the step S3 is specifically as follows: perform multi-layer wavelet transform on the multi-spectrum data to obtain a plurality of high-frequency wavelet data and a plurality of low-frequency wavelet data, fuse the high-frequency wavelet data by setting large absolute values, and fuse the low-frequency wavelet data by removing the average value.

[0032] Preferably, in the step S4, the heavy oil quality detection model is a support vector machine model.

[0033] According to another aspect of the present invention, there is provided a heavy oil quality detection system based on multi-spectrum fusion. The detection system adopts the above-mentioned heavy oil quality detection method based on multi-spectrum fusion. The system includes:

[0034] A multi-spectrum data acquisition module for performing multi-spectrum acquisition on a heavy oil sample to obtain multi-spectrum data;

[0035] A data preprocessing module for performing data preprocessing operation on the multi-spectrum data to obtain preprocessed multi-spectrum data;

[0036] A data fusion module for performing data fusion operation on the preprocessed multi-spectrum data;

[0037] A heavy oil quality detection model establishment module for establishing a heavy oil quality detection model;

[0038] A quality detection module for performing quality detection on the heavy oil.

[0039] The embodiments of the present invention have the following technical effects:

[0040] When using the moving average detrending method for preprocessing multi-spectral data, first classify the multi-spectral data into extreme interval multi-spectral data and ordinary interval multi-spectral data, and then use different methods for data preprocessing according to different data types. For ordinary interval multi-spectral data, use the conventional moving average detrending method for data preprocessing. For extreme interval multi-spectral data, use the window attenuation method for preprocessing. And when encountering extreme points, use the method of skipping extreme points and then restoring the initial window, which can effectively reduce the influence of the detrending algorithm on extreme points in multi-spectral data and improve the accuracy of data processing; at the same time, the window attenuation and extreme point skipping methods also reduce the data preprocessing time to a certain extent and improve the efficiency of data preprocessing. Brief Description of the Drawings

[0041] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for use in the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0042] Figure 1 It is a flowchart of a heavy oil quality detection method based on multi-spectral fusion provided by an embodiment of the present invention;

[0043] Figure 2 It is a flowchart of the data preprocessing operation for the multi-spectral data using the moving average detrending algorithm provided by an embodiment of the present invention. Specific Embodiments

[0044] To make the objectives, technical solutions, and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments of the present invention belong to the scope protected by the present invention.

[0045] Embodiment 1, as shown in Figure 1 shows a flowchart of a heavy oil quality detection method based on multi-spectral fusion. As shown in Figure 1 shown, a heavy oil quality detection method based on multi-spectral fusion includes the following steps:

[0046] S1: Perform multi-spectral acquisition on a heavy oil sample to obtain multi-spectral data;

[0047] During the multi-spectral acquisition of the heavy oil sample, the multi-spectral includes: near-infrared spectral band and Raman spectral band;

[0048] Among them, near-infrared light is an electromagnetic wave with a frequency between ultraviolet-visible light and mid-infrared light. Near-infrared spectroscopy mainly involves the vibrational energy level transitions of chemical bonds such as C-H, O-H, and N-H in molecules. After these bonds absorb near-infrared light of a specific wavelength, they will transition from the ground state to the excited state, generating an absorption spectrum. The wavelength range of near-infrared spectroscopy is usually 780 - 2500 nanometers, between visible light and infrared light. The light energy in this range is relatively low, mainly triggering the overtone and combination frequency transitions of molecular vibrations. Heavy oil is mainly composed of hydrocarbons and a small amount of sulfur-containing, nitrogen-containing, and oxygen-containing compounds. The chemical bonds (such as C-H, O-H, N-H, etc.) in these compounds will absorb light of specific wavelengths in the near-infrared region (780 - 2500 nm), generating characteristic absorption peaks.

[0049] The principle of Raman spectroscopy for detecting crude oil is based on the Raman scattering effect. When a laser irradiates a crude oil sample, photons interact with the molecules in the sample, causing a change in the photon energy, thereby generating scattered light. The difference between the frequency of the scattered light and the frequency of the incident light is called the Raman shift, which is related to the vibration mode and chemical bonds of the sample molecules. By analyzing the characteristic peaks and their intensities in the Raman spectrum, information about different chemical components in the crude oil, such as hydrocarbon compounds, sulfur-containing compounds, nitrogen-containing compounds, etc., can be obtained. In practical applications, Raman spectroscopy technology can be used for component analysis, quality control, and quality detection of heavy oil.

[0050] Among them, a near-infrared spectrometer is used to collect data on the heavy oil. The collection parameters of the near-infrared spectrometer are: the wavelength of the detection light source is near-infrared light of 850 nm, the number of scans is 32 times, and the resolution is 3.5 cm -1 ;

[0051] A Raman spectrometer is used to collect data on the heavy oil. The collection parameters of the Raman spectrometer are: the wavenumber range of the spectral collection of the Raman spectrometer is 250 - 2340 cm -1 , the central wavelength is 785 nm, the laser power is 400 mW, and the integration time is 500 ms.

[0052] S2: Perform data preprocessing operations on the multi-spectrum data to obtain preprocessed multi-spectrum data;

[0053] Multi-spectrum data is relatively vulnerable to external factors. For example, temperature, noise, and light will all affect the collected multi-spectrum data, resulting in a certain difference between the multi-spectrum obtained by the collection instrument and the true multi-spectrum, thereby interfering with the extraction of effective information from the multi-spectrum. Therefore, before performing multi-spectrum data analysis, data preprocessing operations must be carried out to reduce or eliminate the influence of interfering data.

[0054] In this step, the preprocessing operations include standard normal variate transformation (SNV) preprocessing and moving average detrending algorithm preprocessing;

[0055] Among them, the standard normal variate transformation preprocessing calculates the average reflectance value or absorbance value for the spectral data at each wavelength position in the multi-spectral data, then subtracts the average value at its corresponding wavelength position from the spectral data of each sample, calculates the standard deviation, and divides the spectral data of each sample by the standard deviation at its corresponding wavelength position to obtain the standard normal variate transformation preprocessing data;

[0056] The detrending method is a data processing method mainly used to eliminate the long-term trend or periodic variation in time series data in order to more accurately analyze the random fluctuations or other specific characteristics of the data. Its core principle is to perform mathematical processing on the original data to remove the trend component, thereby obtaining a more stable data sequence; As a kind of detrending algorithm, for spectral data, the moving average detrending algorithm is generally used to preprocess the multi-spectral data. However, the moving average detrending method is likely to change the amplitude of the extreme points too much during the preprocessing of multi-spectral data, resulting in distortion of the preprocessed multi-spectral data and causing errors in the quality detection of heavy oil;

[0057] In this embodiment, as Figure 2 shown, the specific operation of using the moving average detrending algorithm to preprocess the multi-spectral data is as follows:

[0058] S2.a: Perform Fourier transform on the multi-spectral data to obtain frequency-domain multi-spectral data;

[0059] The Fourier transform is a mathematical tool that can decompose a complex signal into a series of sine wave components of different frequencies. In spectroscopy, the Fourier transform converts data with the intensity of light changing over time or space into a spectrum with the intensity of light changing over frequency. In this way, the characteristics in the spectrum, such as extreme points like absorption peaks and emission peaks, can be observed and analyzed more intuitively;

[0060] S2.b: Identify the extreme points of the multi-spectral data based on the frequency-domain multi-spectral data and mark them;

[0061] In this step, the extreme points of the frequency-domain multi-spectral data are identified by the threshold method; specifically: set the highest value of a preset multiple of the frequency-domain multi-spectral data as the upper threshold, set the lowest value of a preset multiple of the frequency-domain multi-spectral data as the lower threshold, traverse the frequency-domain multi-spectral data, and take the local maximum points higher than the upper threshold as extreme points and the local minimum points lower than the lower threshold as extreme points;

[0062] As a preferred embodiment, the preset multiple is 0.5;

[0063] S2.c: Use the multi-spectral data within a preset range on both sides of the extreme point as the multi-spectral data in the extreme value interval; use the other multi-spectral data as the multi-spectral data in the ordinary interval;

[0064] Among them, in this step, the determination formula for the preset range is:

[0065] ;

[0066] In the formula, D is the number of data points in the preset range, a is a coefficient, is the sampling frequency of the i-th multi-spectral data; in this embodiment, D < 20;

[0067] Thus, the multi-spectral data in the extreme value interval consists of 2D + 1 data points;

[0068] S2.d: Perform data preprocessing on the multi-spectral data in the ordinary interval using the first moving average method;

[0069] Among them, the formula for the first moving average method is:

[0070]

[0071] In the formula, is the i-th multi-spectral data after preprocessing by the first moving average method, is the original i-th multi-spectral data, and n is the period number of data movement;

[0072] S2.e: Perform data preprocessing on the multi-spectral data in the extreme value interval using the second moving average method;

[0073] Among them, performing data preprocessing on the multi-spectral data in the extreme value interval using the second moving average method is: set the initial window period number n1, and then perform data preprocessing on the multi-spectral data using window period numbers that decrease sequentially; skip the extreme point when moving to the marked extreme point, and then set the initial window period number n1 for the value after the extreme point, and then perform data preprocessing on the multi-spectral data using window period numbers that decrease sequentially;

[0074] Among them, the determination formula for the sequentially decreasing window period number n is:

[0075]

[0076]

[0077] Among them, s is the window period number decay coefficient s, that is, each time the window moves, the value decays by s on the basis of the initial window period number;

[0078] In this step, when preprocessing the multi-spectral data by using the moving average detrending method, first classify the multi-spectral data into extreme value interval multi-spectral data and ordinary interval multi-spectral data, and then use different methods for data preprocessing according to different data types. For the ordinary interval multi-spectral data, use the conventional moving average detrending method for data preprocessing. For the extreme value interval multi-spectral data, use the window attenuation method for preprocessing. And when encountering extreme points, use the method of skipping extreme points and then restoring the initial window, which can effectively reduce the influence of the detrending algorithm on the extreme points in the multi-spectral data and improve the accuracy of data processing; at the same time, the window attenuation and the method of skipping extreme points also reduce the time of data preprocessing to a certain extent and improve the efficiency of data preprocessing.

[0079] S3: Perform data fusion operation on the preprocessed multi-spectral data;

[0080] In this step, use the wavelet feature fusion method to perform data fusion operation on the preprocessed multi-spectral data;

[0081] Specifically, S3 is specifically as follows: perform multi-layer wavelet transform on the multi-spectral data to obtain a number of high-frequency wavelet data and a number of low-frequency wavelet data. For the high-frequency wavelet data, use the method of setting large absolute values for fusion, and for the low-frequency wavelet data, use the method of removing the average value for fusion.

[0082] S4: Establish a heavy oil quality detection model;

[0083] Among them, the heavy oil quality detection model is a support vector machine model. Support Vector Machine (SVM for short) is a powerful supervised learning algorithm widely used in classification and regression tasks. The core idea of SVM is to find an optimal hyperplane to separate data points of different classes while maximizing the classification margin.

[0084] The input of the support vector machine model is the fused data, and the output of the support vector machine model is the quality parameters of heavy oil, such as density, viscosity, sulfur content, etc.

[0085] S5: Perform quality detection on the heavy oil;

[0086] Input the multi-spectral data of the heavy oil sample to be measured into the heavy oil quality detection model to obtain its quality detection result.

[0087] Embodiment 2, the present invention also provides a heavy oil quality detection system based on multi-spectral fusion. The detection system uses the heavy oil quality detection method based on multi-spectral fusion in Embodiment 1. The system includes:

[0088] A multi-spectral data acquisition module, which is used to perform multi-spectral acquisition on heavy oil samples to obtain multi-spectral data;

[0089] A data preprocessing module, which is used to perform data preprocessing operations on the multi-spectral data to obtain preprocessed multi-spectral data;

[0090] A data fusion module, which is used to perform data fusion operations on the preprocessed multi-spectral data;

[0091] A heavy oil quality detection model establishment module, which is used to establish a heavy oil quality detection model;

[0092] A quality detection module, which is used to detect the quality of the heavy oil.

[0093] Embodiment 3. The present invention also provides an electronic device, which includes one or more processors and a memory.

[0094] The processor can be a central processing unit (CPU) or other forms of processing units with data processing capabilities and / or instruction execution capabilities, and can control other components in the electronic device to perform desired functions.

[0095] The memory can include one or more computer program products, and the computer program products can include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory can include, for example, random access memory (RAM) and / or cache memory, etc. The non-volatile memory can include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions can be stored on the computer-readable storage medium, and the processor can run the program instructions to implement the heavy oil quality detection method based on multi-spectral fusion and / or other desired functions of any embodiment of the present application described above. Various contents such as initial external parameters and thresholds can also be stored in the computer-readable storage medium.

[0096] In one example, the electronic device can further include: an input device and an output device, and these components are interconnected through a bus system and / or other forms of connection mechanisms (not shown). The input device can include, for example, a keyboard, a mouse, etc. The output device can output various information to the outside, including early warning prompt information, braking force, etc. The output device can include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0097] Of course, for simplicity, components such as buses, input / output interfaces, etc. are omitted. In addition, according to specific application scenarios, the electronic device may further include any other appropriate components.

[0098] In addition to the above methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions that, when run on a processor, cause the processor to implement the functions of the heavy oil quality detection method based on multi-spectrum fusion provided by any embodiment of the present application.

[0099] The computer program product can be written in any combination of one or more programming languages for programming code to perform the operations of the embodiments of the present application. The programming languages include object-oriented programming languages such as Java, C++, etc., and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computing device, partially on the user's device, executed as an independent software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0100] In addition, an embodiment of the present application may also be a computer-readable storage medium, on which computer program instructions are stored, and the computer program instructions, when run on a processor, cause the processor to implement the heavy oil quality detection method based on multi-spectrum fusion provided by any embodiment of the present application.

[0101] The computer-readable storage medium may adopt any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may, for example, include but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or components, or any combination of the above. More specific examples (non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0102] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the technical solutions of the embodiments of the present invention.

Claims

1. A heavy oil quality detection method based on multi-spectral fusion, characterized in that: The following steps are involved: S1: Perform multi-spectral acquisition on heavy oil samples to obtain multi-spectral data; S2: performing a data preprocessing operation on the multi-spectral data to obtain preprocessed multi-spectral data; The preprocessing operation includes standard normal variable transformation preprocessing and moving average detrending algorithm preprocessing; The data preprocessing operation of the multi-spectral data using the moving average detrending algorithm is specifically as follows: S2.a: Performing Fourier transform on the multi-spectral data to obtain frequency domain multi-spectral data; S2.b: identifying extreme points of the multi-spectral data according to the frequency domain multi-spectral data, and marking them; S2.c: The multi-spectral segment data within the preset range on both sides of the extreme value point are used as the extreme value interval multi-spectral segment data; the other multi-spectral segment data are used as the common interval multi-spectral segment data; S2.d: For the multi-spectral data in the common interval, the first moving average method is used for data preprocessing; in S2.d, the formula of the first moving average method is: In the formula, is the i-th multi-spectral data after preprocessing by the first moving average method, is the original i-th multi-spectral data, n is the number of cycles of data movement; S2.e: For the multi-spectral data in the extreme value interval, the second moving average method is used for data preprocessing; specifically, it includes: setting the initial window period number n1, and then using the window period number that decays in sequence to preprocess the multi-spectral data; when moving to the marked extreme point, skipping the extreme point, and then setting the initial window period number n1 at the value after the extreme point, and then using the window period number that decays in sequence to preprocess the multi-spectral data; wherein the formula for determining the window period number n that decays in sequence is: Where s is the window cycle number attenuation coefficient s, and D is the number of data points in the preset range; S3: performing a data fusion operation on the preprocessed multi-spectral data; S4: Establish a heavy oil quality detection model; S5: Performing quality inspection on the heavy oil.

2. The heavy oil quality detection method based on multi-spectral fusion according to claim 1 is characterized in that: In S2.b, the extreme points of the frequency domain multi-spectral data are identified by a threshold method; specifically: the highest value of the preset multiples of the frequency domain multi-spectral data is set as an upper threshold, and the lowest value of the preset multiples of the frequency domain multi-spectral data is set as a lower threshold, and the frequency domain multi-spectral data is traversed, and the local maximum points above the upper threshold are taken as extreme points, and the local minimum points below the lower threshold are taken as extreme points.

3. The heavy oil quality detection method based on multi-spectral fusion according to claim 2 is characterized in that: The preset multiple is 0.

5.

4. The heavy oil quality detection method based on multi-spectral fusion according to claim 2 is characterized in that: In S2.c, the formula for determining the preset range is: ； In the formula, D is the number of data points in the preset range, a is the coefficient, is the sampling frequency of the i-th multi-spectral data, D<20.

5. The heavy oil quality detection method based on multi-spectral fusion according to claim 1 is characterized in that: In S3, a wavelet feature fusion method is used to perform a data fusion operation on the preprocessed multi-spectral data.

6. The heavy oil quality detection method based on multi-spectral fusion according to claim 5 is characterized in that: The S3 is specifically: performing multi-layer wavelet transform on the multi-spectral data to obtain a plurality of high-frequency wavelet data and a plurality of low-frequency wavelet data, fusing the high-frequency wavelet data by setting a large absolute value, and fusing the low-frequency wavelet data by taking an average value.

7. The heavy oil quality detection method based on multi-spectral fusion according to claim 1 is characterized in that: In S4, the heavy oil quality detection model is a support vector machine model.

8. A heavy oil quality detection system based on multi-spectral fusion, characterized in that: The detection system adopts the heavy oil quality detection method based on multi-spectral fusion according to any one of claims 1 to 7, and the system comprises: A multi-spectral data acquisition module is used to perform multi-spectral acquisition on heavy oil samples to obtain multi-spectral data; A data preprocessing module, used for performing a data preprocessing operation on the multi-spectral data to obtain preprocessed multi-spectral data; A data fusion module, used for performing a data fusion operation on the preprocessed multi-spectral data; A heavy oil quality detection model building module is used to build a heavy oil quality detection model; The quality detection module is used to perform quality detection on the heavy oil.

Images