Asphaltene content dynamic detection method and system based on micro-fluidic chip and medium

Abstract

The invention discloses an asphaltene content dynamic detection method and system based on a micro-fluidic chip and a medium. Relates to the technical field of oil-gas field detection. The method is improved on the basis of the prior art, Raman spectrum data of each group of crude oil detection samples are collected based on a micro-fluidic chip, the Raman scattering effect of a sample solution is realized, modified nano-material particles are arranged to enhance the Raman effect, the surfaces of silver nano-particles are modified through a cross-linking agent, and the Raman scattering effect of the sample solution is enhanced. According to the present invention, with the convolutional neural network, the asphaltene molecule adsorption capacity is improved so as to detect the asphaltene sample with the low concentration, and the asphaltene concentration is detected based on the convolutional neural network so as to effectively improve the flexibility and the accuracy of the data processing and analysis.

Description

Technical Field

[0001] The present invention relates to the technical field of oil and gas field detection, and particularly relates to a dynamic detection method, system and medium for asphaltene content based on a microfluidic chip. Background Art

[0002] Crude oil is composed of saturates, aromatics, resins and asphaltenes. Among them, asphaltene is the substance with the relatively largest molecular weight in crude oil. Asphaltene is generally a complex structural compound composed of heavy hydrocarbons containing nitrogen, sulfur and oxygen elements and containing a small amount of metal or non-metal trace elements. The asphaltene deposited from crude oil is a dark amorphous solid, generally with a diameter between 2 and 35 nm. The asphaltene content in crude oil is generally between 8% and 30%. The asphaltene content in the crude oil of the same oilfield is not stable and will change with the changes of temperature, pressure and dissolved gas content. Asphaltene molecules will aggregate with each other to form solid particles with larger sizes. The flocculated asphaltene will block the pore throats of the formation, reduce the relative permeability of crude oil and reduce the production efficiency. Asphaltene deposition will also cause blockage of the wellbore and electric pump.

[0003] The precipitation and deposition of asphaltene will have an adverse impact on the exploitation, transportation and processing of crude oil. In the face of this problem, research has been carried out on the physical and chemical properties and precipitation characteristics of asphaltene. One of the basic problems is how to accurately and efficiently measure the asphaltene content in crude oil. Usually, a precipitant (n-pentane, n-hexane or n-heptane) is added to the crude oil to make the asphaltene aggregate and precipitate, and then the precipitated asphaltene particles are measured through steps such as separation and weighing to obtain the asphaltene content of the crude oil. However, these traditional methods have the problems of poor real-time performance and long test period.

[0004] In the prior art, the asphaltene content in crude oil is detected online by the standard curve method. Compared with the conventional method, it can obtain results faster and can realize online detection. However, for asphaltene samples with a lower concentration, this method may have a smaller decrease in laser intensity, resulting in ineffective detection. And the detection depends on the change of light intensity, which may be interfered by other components or impurities, resulting in poor selectivity. At the same time, this method depends on the standard curve, resulting in lower flexibility in data processing and analysis.

[0005] Summary of the Invention

[0006] The technical problem to be solved by the present invention is that for the existing on-line detection method of asphaltene content, for asphaltene samples with relatively low concentration, there is a problem that the decrease in laser intensity is small, resulting in ineffective detection, and the detection depends on the change in the intensity of light and is easily interfered by other components or impurities; the object of the present invention is to provide a dynamic detection method, system and medium for asphaltene content based on a microfluidic chip, to improve the method on the basis of the existing technology, to realize the surface-enhanced Raman scattering effect of the sample solution based on the microfluidic chip, and to set modified nanomaterial particles to enhance the Raman effect, and to modify the surface of silver nanoparticles with a cross-linking agent to improve its adsorption capacity for asphaltene molecules, so that asphaltene samples with relatively low concentration can also be detected, and at the same time, the asphaltene concentration is detected based on a convolutional neural network, effectively improving the flexibility and accuracy of data processing and analysis.

[0007] The present invention is realized through the following technical solutions:

[0008] This solution provides a dynamic detection method for asphaltene content based on a microfluidic chip, including:

[0009] Construct several groups of crude oil detection samples, and collect Raman spectral data of each group of crude oil detection samples based on a microfluidic chip;

[0010] Preprocess the Raman spectral data;

[0011] Input the preprocessed Raman spectral data into a neural network to train an asphaltene concentration detection model;

[0012] Collect Raman spectral data of the crude oil solution to be measured based on a microfluidic chip, preprocess the Raman spectral data of the crude oil solution to be measured, and then input it into the asphaltene concentration detection model to obtain the asphaltene content of the crude oil solution to be measured.

[0013] A further optimized solution is that the construction of several groups of crude oil detection samples includes the following method:

[0014] Add n-heptane solvent to several groups of crude oil solution samples with known asphaltene concentration; in each group of crude oil solution samples, the ratio of n-heptane solvent to crude oil solution is Z;

[0015] Based on the ultrasonic oscillation method, mix the n-heptane solvent and the crude oil solution sample evenly to obtain a crude oil detection sample.

[0016] A further optimized solution is that the collection of Raman spectral data of each group of crude oil detection samples based on a microfluidic chip includes the following method:

[0017] S1, embed a hollow flow channel in the microfluidic chip, and set modified nanomaterial particles on the inner wall of the flow channel;

[0018] S2. Introduce the crude oil detection sample into the flow channel of the microfluidic chip and flow at a flow rate v, and irradiate the crude oil detection sample with a laser;

[0019] S3. Randomly collect Raman spectroscopic data at n different position points in the flow channel to obtain the Raman spectroscopic data of the current group of crude oil detection samples;

[0020] S4. Repeat steps S1 - S3 to obtain the Raman spectroscopic data of each group of crude oil detection samples; during the process of obtaining the Raman spectroscopic data of different groups of crude oil detection samples, keep the control parameters consistent; the control parameters include: the size and shape of the flow channel, the wavelength and power of the laser, the flow rate of the crude oil detection sample, and the acquisition range and acquisition method of the Raman spectroscopic data.

[0021] A further optimized scheme is that the modified nanomaterial particles include silver nanoparticles and a modifier; the modifier is coated on the surface of the silver nanoparticles.

[0022] A further optimized scheme is that the modifier includes polyethyleneimine, and the material of the microfluidic chip is methyl silicone.

[0023] A further optimized scheme is that the pretreatment method includes:

[0024] Perform smoothing filtering on the Raman spectroscopic data based on the following formula:

[0025]

[0026] where, represents the signal value at the k - th position point after smoothing filtering, H represents the normalization factor, ω represents the width of the filtering window, h i represents the smoothing coefficient, x k+i represents the original input signal value at the k + i - th position point; i represents the offset index relative to the k - th point within the filtering window, i ∈ (-ω, ω);

[0027] Perform normalization on the Raman spectroscopic data after smoothing filtering.

[0028] A further optimized scheme is that the normalization of the Raman spectroscopic data after smoothing filtering includes the method:

[0029] Perform normalization on the Raman spectroscopic data after smoothing filtering according to the following formula:

[0030]

[0031] where, x norm represents the spectral signal output after normalization, x represents the original spectral signal, n represents the dimension of the original spectral signal x, and j = 1, 2, …, n.

[0032] A further optimization solution is that the Raman spectral data of the crude oil solution to be measured is collected based on a microfluidic chip, and after preprocessing the Raman spectral data of the crude oil solution to be measured, it is input into the asphaltene concentration detection model to obtain the asphaltene content of the crude oil solution to be measured, including the method:

[0033] Add n-heptane solvent to the crude oil solution to be measured so that the ratio of the n-heptane solvent to the crude oil solution to be measured is Z;

[0034] Collect n groups of Raman spectral data of the crude oil solution to be measured based on the microfluidic chip, and after preprocessing the n groups of Raman spectral data of the crude oil solution to be measured, input them into the asphaltene concentration detection model to obtain n groups of asphaltene concentrations;

[0035] Calculate the asphaltene content of the crude oil solution to be measured based on the following formula:

[0036]

[0037] where C z represents the asphaltene content of the crude oil solution to be measured, C max represents the maximum concentration among the n groups of asphaltene concentrations in the crude oil solution to be measured, C min represents the minimum concentration among the n groups of asphaltene concentrations in the crude oil solution to be measured, C avg represents the average concentration among the n groups of asphaltene concentrations in the crude oil solution to be measured; α represents the maximum concentration weight; β represents the minimum concentration weight; γ represents the average concentration weight.

[0038] This solution also provides a method for a dynamic detection system of asphaltene content based on a microfluidic chip, which is used to implement the above-mentioned method for dynamic detection of asphaltene content based on a microfluidic chip. The system includes:

[0039] A sampling module, which is used to construct several groups of crude oil detection samples and collect the Raman spectral data of each group of crude oil detection samples based on a microfluidic chip;

[0040] A preprocessing sample module, which is used to preprocess the Raman spectral data;

[0041] A model training module, which is used to input the preprocessed Raman spectral data into a neural network to train an asphaltene concentration detection model;

[0042] A detection module, which is used to collect the Raman spectral data of the crude oil solution to be measured based on a microfluidic chip, and after preprocessing the Raman spectral data of the crude oil solution to be measured, input it into the asphaltene concentration detection model to obtain the asphaltene content of the crude oil solution to be measured.

[0043] The present solution also provides a computer-readable medium, on which a computer program is stored. When the computer program is executed by a processor, the dynamic detection method of asphaltene content based on a microfluidic chip as described above can be realized.

[0044] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0045] 1. The dynamic detection method, system and medium of asphaltene content based on a microfluidic chip provided by the present invention; on the basis of the prior art, the method is improved. The surface-enhanced Raman scattering effect of the sample solution is realized based on the microfluidic chip, and its adsorption capacity for asphaltene molecules is improved, so that asphaltene samples with relatively low concentrations can also be detected;

[0046] 2. The dynamic detection method, system and medium of asphaltene content based on a microfluidic chip provided by the present invention; modified nanomaterial particles are arranged on the flow channel to enhance the Raman effect, and the surface of silver nanoparticles is modified by a crosslinking agent to improve its adsorption capacity for asphaltene molecules;

[0047] 3. The dynamic detection method, system and medium of asphaltene content based on a microfluidic chip provided by the present invention; the asphaltene concentration is detected based on a convolutional neural network, effectively improving the flexibility and accuracy of data processing and analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can also be obtained based on these drawings without creative efforts. In the drawings:

[0049] Figure 1 is a schematic flowchart of the dynamic detection method of asphaltene content based on a microfluidic chip;

[0050] Figure 2 is a schematic structural diagram of the dynamic detection system of asphaltene content based on a microfluidic chip. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0051] In order to make the purpose, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below in combination with the embodiments and the drawings. The illustrative embodiments of the present invention and their descriptions are only used to explain the present invention and do not limit the present invention.

[0052] Existing on-line detection methods for asphaltene content have problems in that for asphaltene samples with relatively low concentrations, the decrease in laser intensity is small, resulting in ineffective detection, and the detection depends on the change in light intensity and is susceptible to interference from other components or impurities. In view of this, the following embodiments are provided in this solution to solve the above technical problems.

[0053] Embodiment 1

[0054] This embodiment provides a dynamic detection method for asphaltene content based on a microfluidic chip, as Figure 1 shown, including:

[0055] Step 1, construct several groups of crude oil detection samples, and collect Raman spectral data of each group of crude oil detection samples based on a microfluidic chip;

[0056] In Step 1, the construction of several groups of crude oil detection samples; includes the method:

[0057] S1.1, add n-heptane solvent to several groups of crude oil solution samples with known asphaltene concentrations; in each group of crude oil solution samples, the ratio of n-heptane solvent to crude oil solution is Z; in this embodiment, the ratio Z is set to 30 mL / g.

[0058] S1.2, mix the n-heptane solvent and the crude oil solution sample evenly based on the ultrasonic oscillation method to obtain a crude oil detection sample.

[0059] Asphaltenes are a type of macromolecular compound and usually have low solubility in organic solvents (such as n-heptane). By introducing n-heptane, the solubility of asphaltenes in the solution can be effectively reduced, thereby promoting the precipitation of asphaltenes from the solution. N-heptane can selectively precipitate asphaltenes and does not have a significant precipitation effect on other low-molecular substances (such as light hydrocarbons). This selectivity makes n-heptane very suitable for the separation and detection of asphaltenes.

[0060] In Step 1, the collection of Raman spectral data of each group of crude oil detection samples based on a microfluidic chip, includes the method:

[0061] S1, embed a hollow flow channel in the microfluidic chip, and set modified nanomaterial particles on the inner wall of the flow channel; the modified nanomaterial particles include silver nanoparticles and a modifier; the modifier is coated on the surface of the silver nanoparticles. The modifier includes polyethyleneimine, and the material of the microfluidic chip is methyl silicone.

[0062] S2, introduce the crude oil detection sample into the flow channel of the microfluidic chip to flow at a flow rate v, and irradiate the crude oil detection sample with laser light;

[0063] S3. Randomly collect Raman spectral data at n different position points in the flow channel to obtain the Raman spectral data of the current group of crude oil detection samples.

[0064] S4. Repeat steps S1 - S3 to obtain the Raman spectral data of each group of crude oil detection samples; during the process of obtaining the Raman spectral data of different groups of crude oil detection samples, keep consistent control parameters; the control parameters include: the size and shape of the flow channel, the wavelength and power of the laser, the flow rate of the crude oil detection sample, and the acquisition range and acquisition method of the Raman spectral data.

[0065] In this embodiment, the flow channel is set as a rectangular hollow channel with a diameter of 100 microns and a length of 10 cm, and the material of the microfluidic chip is methyl silicone; this solution constructs a microfluidic chip based on polydimethylsiloxane (PDMS), and the main reasons are as follows: Polydimethylsiloxane has good optical transparency, which is convenient for optical detection, such as fluorescence and transmission optical analysis. The material is soft and easy to process, and can withstand a certain degree of deformation, suitable for manufacturing complex microfluidic structures.

[0066] The modified nanomaterial particles laid on the inner wall of the flow channel are used to enhance the Raman scattering signal. Some characteristics of the surface of the material to be measured and the concentration of the analyte in the solution, etc., will all affect the effect of Raman signal enhancement. And when the analyte adsorbs onto the rough or nanoscale noble metal surface, the Raman scattering signal will be significantly enhanced. Compared with spontaneous Raman, its enhancement factor can reach 10 8 orders of magnitude.

[0067] On the surface of silver nanoparticles, crosslinking agents are used to modify the silver nanoparticles. Polyethyleneimine is a polymer with a high molecular weight, containing a large number of functional groups such as amino and hydroxyl groups. These functional groups can interact with the polar functional groups in asphaltene molecules, thereby enhancing the adsorption ability. The amino groups of polyethyleneimine can provide positive charges, which enables it to have electrostatic interactions with the negative charges or polar parts that may exist in asphaltene molecules, thereby enhancing the adsorption. By modifying the surface of silver nanoparticles, polyethyleneimine can improve its hydrophilicity in polar solvents and lipophilicity in non-polar environments, which enables silver nanoparticles to better interact with complex organic substances such as asphaltene.

[0068] In this embodiment, the flow rate of the crude oil detection sample in the flow channel is controlled at 50 μL / min, the laser wavelength used is 532 nm, the acquisition range of the spectrum is 800 - 4000 cm -1 , and the spectral resolution is 5 cm -1For each spectrum, the integration time is 10 seconds, the number of integrations is 2 times, and the laser power is 16 mW; for the Raman spectrum detection of asphaltene, the typical acquisition range is from 800 to 4000 cm-1, the key analysis region is between 1000 and 1800 cm-1, and the spectral resolution is usually between 1 and 10 cm-1. The specific acquisition range and resolution can be adjusted according to the experimental equipment and research objectives.

[0069] Step 2: Preprocess the Raman spectrum data; the preprocessing method includes:

[0070] Perform smoothing filtering on the Raman spectrum data based on the following formula:

[0071]

[0072] where, represents the signal value at the k-th position after smoothing filtering, H represents the normalization factor, ω represents the width of the filtering window, h i represents the smoothing coefficient, x k+i represents the original input signal value at the k + i-th position; i represents the offset index relative to the k-th point within the filtering window, i ∈ (-ω, ω);

[0073] Perform normalization on the Raman spectrum data after smoothing filtering. Specifically, perform normalization on the Raman spectrum data after smoothing filtering according to the following formula:

[0074]

[0075] where, x norm represents the spectral signal output after normalization, x represents the original spectral signal, n represents the dimension of the original spectral signal x, and j = 1, 2,..., n.

[0076] The purpose of smoothing filtering is to remove high-frequency components. Normalization is a very important step in the spectral preprocessing process because during the spectral acquisition process, it may be affected by factors such as laser power fluctuations or unevenness of the analyte, and the intensities of the spectra measured for the same type of sample may be different. Normalization can reduce the influence of the above factors on the spectral intensity level.

[0077] Step 3: Input the preprocessed Raman spectrum data into a neural network to train an asphaltene concentration detection model; the specific implementation method of this step includes:

[0078] Mark the corresponding asphaltene concentration for the preprocessed Raman spectrum; use the preprocessed Raman spectrum as a sample and the corresponding marked asphaltene concentration as a label to train the neural network to obtain an asphaltene concentration detection model;

[0079] The initial neural network is a convolutional neural network, which consists of an input layer, a convolutional layer, a pooling layer, a fully connected layer, and an output layer. The activation function in the convolutional layer is the ReLU function, and the specific expression of the ReLU function is:

[0080] ReLU(s l(p,q) ) = max(0, s l(p,q) )

[0081] where l represents the l-th corresponding convolutional layer, and s l(p,q) represents the q-th eigenvalue of the p-th feature map in the l-th corresponding convolutional layer;

[0082] For the fully connected layer, the number of neurons in the fully connected layer is set to 64, the learning rate of the initial neural network is set to 0.001, and the number of training epochs is 50; using the preprocessed Raman spectrum as a sample, there are a total of m crude oil detection samples, and 5 spectra are collected for each crude oil detection sample, and a total of 5*m spectra are used as the input samples of the asphaltene concentration detection model.

[0083] Step 4: Collect the Raman spectrum data of the crude oil solution to be measured based on the microfluidic chip, preprocess the Raman spectrum data of the crude oil solution to be measured, and input it into the asphaltene concentration detection model to obtain the asphaltene content of the crude oil solution to be measured. This step specifically includes the following methods:

[0084] S41: Add n-heptane solvent to the crude oil solution to be measured so that the solvent-oil ratio of the n-heptane solvent to the crude oil solution to be measured is Z;

[0085] S42: Collect n groups of Raman spectrum data of the crude oil solution to be measured based on the microfluidic chip, preprocess the n groups of Raman spectrum data of the crude oil solution to be measured, and input them into the asphaltene concentration detection model to obtain n groups of asphaltene concentrations; during the collection of n groups of asphaltene concentrations, keep the flow rate of the crude oil detection sample in the flow channel controlled at 50 μL / min, the laser wavelength used is 532 nm, the spectral collection range is 800 - 4000 cm -1 , the spectral resolution is 5 cm -1 , the integration time of each spectrum is 10 seconds, the number of integrations is 2 times, and the laser power is 16 mW; in this embodiment, 5 groups of asphaltene concentrations are collected.

[0086] S43: Calculate the asphaltene content of the crude oil solution to be measured based on the following formula:

[0087]

[0088] where C z represents the asphaltene content of the crude oil solution to be measured, C max represents the maximum concentration among the n groups of asphaltene concentrations in the crude oil solution to be measured, C minrepresents the minimum concentration among n groups of asphaltene concentrations in the crude oil solution to be measured, C avg represents the average concentration of n groups of asphaltene concentrations in the crude oil solution to be measured; α represents the maximum concentration weight; β represents the minimum concentration weight; γ represents the average concentration weight. Among them, C max , C min and C avg The formulas for calculation are as follows:

[0089] C max = max(C1, C2, C3, C4, C5)

[0090] C min = min(C1, C2, C3, C4, C5)

[0091]

[0092] In the formula, C1, C2, C3, C4, and C5 are respectively 5 asphaltene concentration data in the crude oil solution to be measured.

[0093] In this embodiment, through the dynamic measurement method of surface-enhanced Raman scattering technology, flowing the sample solution in the flow channel can make the sample mix evenly. Modified nanomaterial particles are set on the inner wall of the flow channel to enhance the Raman effect, and the surface of silver nanoparticles is modified by a cross-linking agent to improve its adsorption capacity for asphaltene molecules, so that asphaltene samples with lower concentrations can also be detected. At the same time, a convolutional neural network is used to detect the asphaltene concentration, effectively improving the flexibility and accuracy of data processing and analysis.

[0094] Example 2

[0095] This embodiment provides a dynamic detection system method for asphaltene content based on a microfluidic chip, which is used to implement the dynamic detection method for asphaltene content based on a microfluidic chip described in Example 1. As Figure 2 shown, the system includes:

[0096] A sampling module, which is used to construct several groups of crude oil detection samples and collect Raman spectrum data of each group of crude oil detection samples based on the microfluidic chip;

[0097] A preprocessing sample module, which is used to preprocess the Raman spectrum data;

[0098] A model training module, which is used to input the preprocessed Raman spectrum data into a neural network to train an asphaltene concentration detection model;

[0099] A detection module, which is used to collect Raman spectrum data of the crude oil solution to be measured based on the microfluidic chip, preprocess the Raman spectrum data of the crude oil solution to be measured, and then input it into the asphaltene concentration detection model to obtain the asphaltene content of the crude oil solution to be measured.

[0100] Example 3

[0101] This embodiment provides a computer-readable medium, on which a computer program is stored. When the computer program is executed by a processor, it can implement the dynamic detection method for asphaltene content based on a microfluidic chip as described in Example 1. The specific steps are as follows:

[0102] Step 1: Construct several groups of crude oil detection samples, and collect Raman spectral data of each group of crude oil detection samples based on a microfluidic chip;

[0103] Step 2: Preprocess the Raman spectral data;

[0104] Step 3: Input the preprocessed Raman spectral data into a neural network to train an asphaltene concentration detection model;

[0105] Step 4: Collect Raman spectral data of the crude oil solution to be measured based on a microfluidic chip, preprocess the Raman spectral data of the crude oil solution to be measured, and then input it into the asphaltene concentration detection model to obtain the asphaltene content of the crude oil solution to be measured.

[0106] The above specific implementation manners further elaborate on the purpose, technical solutions, and beneficial effects of the present invention. It should be understood that the above are only specific implementation manners of the present invention and are not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A dynamic detection method for asphaltene content based on a microfluidic chip, characterized in that Comprising: Constructing several groups of crude oil detection samples, and collecting Raman spectroscopy data of each group of crude oil detection samples based on a microfluidic chip; Preprocessing the Raman spectroscopy data; Inputting the preprocessed Raman spectroscopy data into a neural network to train an asphaltene concentration detection model; Collecting Raman spectroscopy data of the crude oil solution to be measured based on a microfluidic chip, preprocessing the Raman spectroscopy data of the crude oil solution to be measured, and inputting it into the asphaltene concentration detection model to obtain the asphaltene content of the crude oil solution to be measured.

2. The dynamic detection method for asphaltene content based on a microfluidic chip according to claim 1, wherein The constructing several groups of crude oil detection samples; includes the method: Adding n-heptane solvent to several groups of crude oil solution samples with known asphaltene concentrations; in each group of crude oil solution samples, the ratio of n-heptane solvent to crude oil solution is Z; Based on the ultrasonic oscillation method, mixing the n-heptane solvent and the crude oil solution sample evenly to obtain a crude oil detection sample.

3. The dynamic detection method for asphaltene content based on a microfluidic chip according to claim 2, wherein The collecting Raman spectroscopy data of each group of crude oil detection samples based on a microfluidic chip, includes the method: S1, embedding a hollow flow channel in the microfluidic chip, and setting modified nanomaterial particles on the inner wall of the flow channel; S2, introducing the crude oil detection sample into the flow channel of the microfluidic chip to flow at a flow rate v, and irradiating the crude oil detection sample with laser; S3, randomly collecting Raman spectroscopy data at n different position points in the flow channel to obtain the Raman spectroscopy data of the current group of crude oil detection samples; S4, repeating steps S1 - S3 to obtain the Raman spectroscopy data of each group of crude oil detection samples; During the process of obtaining the Raman spectroscopy data of different groups of crude oil detection samples, maintaining consistent control parameters; the control parameters include: the size and shape of the flow channel, the wavelength and power of the laser, the flow rate of the crude oil detection sample, and the collection range and collection method of the Raman spectroscopy data.

4. The dynamic detection method for asphaltene content based on a microfluidic chip according to claim 3, wherein The modified nanomaterial particles include silver nanoparticles and a modifier; the modifier is coated on the surface of the silver nanoparticles.

5. The dynamic detection method of asphaltene content based on a microfluidic chip according to claim 4, characterized in that, The modifier includes polyethyleneimine, and the material of the microfluidic chip is methyl silicone.

6. The dynamic detection method for asphaltene content based on a microfluidic chip according to claim 3, characterized in that, The method of the preprocessing includes: Performing smoothing filtering processing on the Raman spectroscopy data based on the following formula: Among them, represents the signal value of the k-th position point after smooth filtering; H represents the normalization factor, ω represents the width of the filtering window, and h i represents the smoothing coefficient, and x k+i represents the original input signal value of the (k + i)-th position point; i represents the offset index relative to the k-th point within the filtering window, and i ∈ (-ω, ω); Performing normalization processing on the Raman spectroscopy data after smoothing filtering processing.

7. The dynamic detection method for asphaltene content based on a microfluidic chip according to claim 6, characterized in that, The performing normalization processing on the Raman spectroscopy data after smoothing filtering processing, includes the method: Performing normalization processing on the Raman spectroscopy data after smoothing filtering processing according to the following formula: where x norm represents the spectral signal output by the normalization process, x represents the original spectral signal, n represents the dimension of the original spectral signal x, and j = 1, 2, …, n.

8. The dynamic detection method for asphaltene content based on a microfluidic chip according to claim 3, characterized in that, The collecting Raman spectroscopy data of the crude oil solution to be measured based on a microfluidic chip, preprocessing the Raman spectroscopy data of the crude oil solution to be measured, and inputting it into the asphaltene concentration detection model to obtain the asphaltene content of the crude oil solution to be measured, includes the method: Adding n-heptane solvent to the crude oil solution to be measured, so that the ratio of n-heptane solvent to the crude oil solution to be measured is Z; Collecting n groups of Raman spectroscopy data of the crude oil solution to be measured based on a microfluidic chip, preprocessing the Raman spectroscopy data of the n groups of crude oil solution to be measured, and inputting it into the asphaltene concentration detection model to obtain n groups of asphaltene concentrations; Calculating the asphaltene content of the crude oil solution to be measured based on the following formula: Among them, C z represents the asphaltene content of the crude oil solution to be measured, C max represents the maximum concentration among the n groups of asphaltene concentrations in the crude oil solution to be measured, C min represents the minimum concentration among the n groups of asphaltene concentrations in the crude oil solution to be measured, C avg represents the average concentration among the n groups of asphaltene concentrations in the crude oil solution to be measured; α represents the maximum concentration weight; β represents the minimum concentration weight; γ represents the average concentration weight.

9. The method of a dynamic detection system for asphaltene content based on a microfluidic chip, characterized in that, For implementing the dynamic detection method of asphaltene content based on a microfluidic chip according to any one of claims 1 - 8, the system includes: A sampling module for constructing several groups of crude oil detection samples and collecting Raman spectral data of each group of crude oil detection samples based on a microfluidic chip; A preprocessing sample module for preprocessing the Raman spectral data; A model training module for inputting the preprocessed Raman spectral data into a neural network to train an asphaltene concentration detection model; A detection module for collecting Raman spectral data of a crude oil solution to be measured based on a microfluidic chip, preprocessing the Raman spectral data of the crude oil solution to be measured and then inputting it into the asphaltene concentration detection model to obtain the asphaltene content of the crude oil solution to be measured.

10. A computer-readable medium having a computer program stored thereon, characterized in that, The computer program, when executed by a processor, can implement the dynamic detection method for asphaltene content based on a microfluidic chip as described in any one of claims 1-8.

Images