Method for establishing Akafen powder identification model based on partial least squares discriminant analysis

Abstract

The invention discloses a method for establishing an akafen powder identification model based on partial least square discriminant analysis, and belongs to the technical field of drug inspection and analysis. Comprising the following steps: S1, collecting original data; s2, data preprocessing and standardization; s3, preparing a response variable; s4, carrying out PLS-DA modeling; s5, calculating a predicted response value; and S6, converting into a binary classification result. According to the method for modeling by utilizing partial least square discriminant analysis provided by the invention, by setting and selecting modeling parameters such as original data, the number of principal components and a threshold value, the obtained akafen powder infrared qualitative analysis model can be used for effectively and qualitatively identifying whether an unknown sample belongs to akafen powder or not.

Description

Technical Field

[0001] The present invention belongs to the technical field of drug inspection, and in particular, relates to the technical field of a detection method for acetaminophen powder based on a cluster analysis method. Background Art

[0002] With the rapid expansion of the global pharmaceutical market and the growing demand for healthcare, the quality control and safety monitoring of drugs are particularly critical. Acacia phenol powder is mainly a compound preparation composed of aspirin, acetaminophen and caffeine, of which aspirin and acetaminophen can inhibit prostaglandin synthesis and have antipyretic and analgesic effects; caffeine is a central nervous system stimulant that can enhance the antipyretic and analgesic effects of the above-listed drugs. Acacia phenol powder is one of the commonly used clinical drugs for treating fever caused by the common cold or influenza and relieving mild to moderate pain. The product has a large output and a wide market demand, and is very common in daily market supervision and random inspections. Due to the high market share of this product and the large number of random inspections each year, a large amount of manpower, material resources and financial resources need to be repeatedly consumed in inspections and tests, and the daily inspection cycle is long, requiring the consumption of a large amount of chemical reagents, reference substances, etc., which pollutes the environment and causes waste of resources. Therefore, as a drug widely used in clinical practice, the safe and effective use of Acacia phenol powder depends on a strict quality control process to ensure that it can be accurately distinguished from other drugs. However, traditional methods of drug identification, including chromatography and mass spectrometry, although highly accurate, usually involve complex sample processing, long analysis cycles and high operating costs, which limit their application in routine rapid drug testing.

[0003] As a non-destructive, highly sensitive and selective analytical method, infrared spectroscopy (IR) has brought innovative solutions to the field of chemical and pharmaceutical analysis. By analyzing the absorption characteristics of molecules in the near-infrared region, IR technology can provide detailed information on molecular structure and chemical composition. If combined with advanced data processing technology and algorithms, it will have the potential to achieve rapid and accurate analysis of complex samples.

[0004] The Chinese patent application number CN201510433848.8 discloses a near-infrared qualitative identification feature extraction method, which includes the following steps: Step 1: Use a near-infrared spectrometer to collect near-infrared spectrum data of a modeling sample; Step 2: Add historical near-infrared spectrum data of samples of the same substance; Step 3: Preprocess the near-infrared spectrum data of the modeling sample and the historical near-infrared spectrum data sample data; Step 4: Perform partial least square feature extraction on all preprocessed sample data and obtain a partial least square space; Step 5: Project the near-infrared spectrum data of the preprocessed modeling sample to the constructed partial least square space; Step 6: Perform orthogonal linear discriminant analysis feature extraction on the near-infrared spectrum data of the projected modeling sample to complete the extraction method. In order to eliminate the change in PLS dimension caused by factors such as test date and different varieties, the robustness of the near-infrared qualitative analysis model can be improved by adding historical near-infrared spectra of samples of the same substance to construct a partial least square space. The invention discloses a modeling process for partial least squares discriminant analysis of infrared spectral data, and uses the obtained model for qualitative identification. However, the application does not clearly indicate how to adjust the modeling process for acetaminophen powder. For acetaminophen powder with complex infrared spectral data, mutual interference between the infrared peaks of the main components, and no so-called "historical data", the technical solution of the application is often not able to perform the task of rapid identification of acetaminophen powder.

[0005] A Chinese patent with application number CN201911015073.7 discloses a method for quickly identifying the authenticity of traditional Chinese medicine based on infrared spectroscopy technology, including collecting infrared spectra of medicinal materials, deducting the influence of background peaks, and exporting data after coordinate normalization, baseline correction and automatic smoothing for second-order derivative, PCA, PLS-DA and HCA identification analysis; a Chinese patent with application number CN202211574761.9 discloses a method for discriminating high-temperature Daqu using infrared spectroscopy technology in the field of food testing technology, which also includes collecting typical samples of high-temperature Daqu and obtaining infrared spectral data of the samples, using any one of partial least squares method, partial least squares discriminant analysis method or orthogonal partial least squares discriminant analysis method to establish an infrared spectroscopy technology category analysis model, and then bringing the infrared spectral data of the sample to be tested into the model to obtain the Daqu type of the sample. The two patents respectively point out solutions for establishing rapid identification of Chinese medicinal materials and high-temperature Daqu, and both disclose methods for collecting infrared spectral data of original samples, performing partial least squares discriminant analysis, and establishing identification models. However, they still directly analyze and model special original spectral data. For scenarios where adulteration may exist in corporate production lines or market supervision, the above methods are not well targeted.

[0006] In summary, although the above patents all disclose methods of collecting infrared spectral data of medicinal materials and performing partial least squares discriminant analysis to establish identification models, none of them indicate whether the process is applicable to acetaminophen powder, and there is no targeted identification of adulteration and doping. Therefore, finding a near-infrared spectral qualitative analysis model for acetaminophen powder and establishing a targeted identification method have become technical problems that need to be solved urgently by those skilled in the art. Summary of the invention

[0007] In view of the existence of adulteration and doping in the production process of acetaminophen powder, when infrared spectroscopy is used for detection, in addition to the large number of overlapping peaks in the infrared spectral data caused by its own complex components, it will also be affected by other additives, resulting in inaccurate detection results and a long time consumption. The purpose of the present invention is to provide a method for modeling using partial least squares discriminant analysis to obtain an infrared qualitative analysis model of acetaminophen powder, which can accurately and efficiently distinguish acetaminophen powder drugs from non-acetaminophen powder drugs.

[0008] The technical solution adopted by the present invention to solve the technical problem is:

[0009] A method for establishing an identification model of acetaminophen powder based on partial least squares discriminant analysis comprises the following steps:

[0010] S1: Raw data collection: Raw data are collected as modeling samples and organized into a data matrix, wherein the raw data include: infrared spectral data of standard acetaminophen powder samples and infrared spectral data of other standard samples, and the number ratio of the standard acetaminophen powder samples to the other standard samples is 90-150:5-20, preferably: infrared spectral data of 90 standard acetaminophen powder samples and infrared spectral data of 5 other standard samples, wherein the 90 standard acetaminophen powder samples are selected from different batches of commercially available standard products from different pharmaceutical factories across the country, and the 5 other standard samples are preferably: Aciprofloxacin Capsules, Compound Aciprofloxacin Tablets, Compound Aciprofloxacin Granules, Vitamin C and Sucrose, all of which are commercially available standard products from any batches.

[0011] In this step, standard acetaminophen powder samples and other standard samples are collected separately, and infrared scanning is performed to obtain corresponding spectral data. The infrared spectral data of other standard products are used together as the original data for modeling, and Aminopeptide Capsules, Compound Aminopeptide Tablets, Compound Aminopeptide Granules, Vitamin C and Sucrose are selected as the preferred six other standard samples. The above five drugs can usually be used as adulterants in the production process of acetaminophen powder. Among them, Aminopeptide Capsules is a powder, and its color is similar to that of acetaminophen powder. The preparation contains the same acetaminophen and caffeine ingredients as acetaminophen powder, and the infrared spectra are similar. The functions, indications and use indications are similar to those of acetaminophen powder; Compound Aminopeptide Tablets is a powder, and its color is similar to that of acetaminophen powder. The preparation contains the same acetaminophen and caffeine ingredients as acetaminophen powder, and the infrared spectra are similar. The functions, indications and use indications are similar to those of acetaminophen powder; Compound Aminopeptide Granules is a powder. It is in powder form and its color is similar to that of acetaminophen powder. The preparation contains the same acetaminophen and caffeine as acetaminophen powder, has similar infrared spectra, and has similar functions, indications and use as acetaminophen powder. Vitamin C and sucrose are general additives in the pharmaceutical process, and usually serve as background peaks to interfere with the detection process. In addition, their raw materials are sourced from a wide range of sources, and their production, circulation and use are not strictly regulated. They are cheap and have a wide range of uses, and are easily used in the production of fake and inferior drugs. Adding these two drugs to the cluster analysis process can make the classification results more accurate and make the obtained infrared qualitative analysis model more credible.

[0012] The above other standard drugs were added to participate in the modeling process and used as category 1 in the partial least squares discriminant analysis, that is, "non-acacophane powder". In addition to considering the actual adulteration in production and life, general additives such as vitamin C and sucrose were selected. At the same time, drugs that overlap and interfere with acacophane powder in the infrared spectrum were selected, such as: aminocaphate yellow capsules, compound aminocaphate tablets and compound aminocaphate granules, so that the obtained model can take into account the commonality of the infrared spectrum of acacophane powder and the difference from similar substances. And further make the detection method using the analysis model more credible.

[0013] The original data is organized into a data matrix, that is, the infrared spectrum data of the standard acetaminophen powder sample and the infrared spectrum data of other standard samples are organized into a two-dimensional matrix, where each row represents the infrared spectrum data of a sample, and each column represents the absorption value of a wavelength or frequency point, which is more convenient for the subsequent data modeling process. For example: row: The first row represents the wave number 4000, 3999, 3998...600cm -1 , each subsequent row corresponds to the projection rate of each sample at the corresponding wave number, such as the second row represents the projection rate of the first standard sample at 4000, 3999, 3998…600cm -1The corresponding transmittance T% is shown below; Column: The first column is the sample name, and the subsequent columns represent the transmittance T% values ​​of different samples at different wave numbers.

[0014] S2: Data preprocessing and standardization: Perform Z-Score standardization preprocessing on the above data matrix to obtain standardized data.

[0015] In this step, the data matrix is ​​standardized. Z-Score standardization is a key step in data preprocessing, also known as standard deviation standardization. It is a commonly used data standardization method that aims to eliminate the impact of dimension by adjusting the scale of the data and reduce the variability between different samples. Specifically, the Z-Score value of each spectral data point is calculated by subtracting the average value of the entire data set at that wave number point from its original value, and then dividing it by the standard deviation of that wave number point. The mathematical formula is expressed as: Z = (X-μ) / σ, where X corresponds to the spectral intensity value of each sample at a specific wave number (or frequency), μ is the average spectral intensity value of all samples at that wave number, and σ is the standard deviation of the spectral intensity values ​​of all samples at that wave number. In this way, the data at each wave number point is converted to a distribution centered on 0, and the standard deviation of the distribution is 1.

[0016] The data after Z-Score standardization has a unified dimension and scale, which is crucial for subsequent model building and analysis. It not only helps to improve the convergence speed of the model, but also enhances the adaptability of the model to features of different scales, especially when using distance calculation algorithms. In addition, Z-Score standardization can also improve the generalization ability of the model, making it more robust and having better predictive performance for unknown samples. By performing Z-Score standardization on the spectral data of the selected 95 samples, the consistency and comparability of the data can be ensured, creating favorable conditions for establishing an accurate and effective IR qualitative analysis model. This preprocessing step is an indispensable part of the data processing process of this study, and provides a solid foundation for in-depth analysis and understanding of the spectral differences between samples.

[0017] S3: Prepare response variables: Create response variables to represent the classification labels of the above original data, which are divided into category 0 and category 1. Category 0 represents the category to which Acacia phenol belongs, and category 1 represents the category to which other drugs belong.

[0018] Among them, category 1 is "abnormal samples". In order to improve the model's ability to identify abnormal situations, as many samples of this type as possible should be collected or increased through technical means, and abnormal samples should fully represent all known abnormal types. In addition, it should be ensured that the collected standard acetaminophen powder samples, that is, category 0, can cover all possible production situations, including those from different production lines and different production batches.

[0019] S4: PLS-DA modeling: Use partial least squares discriminant analysis to model the above standardized data and obtain the PLS-DA model, that is, the partial least squares discriminant analysis model.

[0020] PLS-DA is an application of partial least squares regression (PLSR), a supervised learning algorithm used to build a predictive model that can discover the relationship between two matrices (such as spectral data and corresponding attributes or categories). In PLS-DA, the algorithm looks for the direction of data projection that can better explain the variance of the response variable. PLS-DA is specifically used for classification problems. It identifies which features are most important for distinguishing different categories by finding the components that maximize the differences between categories. When performing PLS-DA, data that has been standardized by Z-Score helps to enhance the model's ability to capture the correlation between variables, so that the model's performance in high-dimensional data is optimized. The standardization process ensures that PLS-DA can identify the spectral features that are most relevant to the classification in a balanced data environment, thereby improving the accuracy of the classification.

[0021] In this step, a classification model based on partial least squares discriminant analysis (PLS-DA) was constructed to distinguish two different categories, namely, acetaminophen powder and non-acetaminophen powder.

[0022] S5: Calculate predicted response value: Calculate the continuous predicted value of the above partial least squares discriminant analysis model.

[0023] In this step, the predicted response value (Yfit) is calculated. By multiplying the offset term and the standardized raw spectral data with the regression coefficient, the partial least squares discriminant analysis model generates a continuous prediction value (usually a probability or score) corresponding to each raw data. These prediction values ​​represent the possibility that the corresponding sample belongs to a certain category. For example, a prediction value close to 1 indicates that the sample is more likely to belong to category 1, while a prediction value close to 0 indicates that the sample is more likely to belong to category 0.

[0024] S6: Convert to binary classification result: set a threshold, preferably 0.5, to classify the continuous prediction value into the above category 0 or the above category 1.

[0025] In this step, the continuous predicted response value is converted into a binary classification result, and a threshold is set to classify the predicted value into category 0 or category 1. The continuous predicted value of the PLS-DA model is calculated, and an appropriate threshold is determined based on these predicted values, preferably 0.5 in this application, so as to convert the continuous predicted value into a discrete classification result. If the predicted value is greater than or equal to 0.5, the sample is classified as category 1, otherwise it is classified as category 0.

[0026] The threshold is the critical value for converting the continuous prediction value into a binary classification result. In this application, by analyzing the ROC curve of the model, the threshold that balances the true positive rate (TPR) and the false positive rate (FPR) is selected, which is usually the best point under the ROC curve, and then a threshold that optimizes the model performance is obtained. In some cases, the classification performance can be optimized by adjusting the threshold. For example, when the categories in the obtained results are unbalanced, the recognition rate of a certain category in the model can be improved by changing the threshold.

[0027] Compared with the prior art, the embodiments of the present invention have at least the following beneficial effects:

[0028] 1. PLS-DA was used to build a prediction model that can discover the relationship between two matrices (spectral data and corresponding attributes or categories). PLS-DA is used for classification problems. It can maximize the components of the differences between categories to identify which features are most important for distinguishing different categories, thereby accurately classifying the original data set into acetaminophen and non-acetaminophen, so as to better apply it to the identification of acetaminophen.

[0029] 2. In addition to acetaminophen powder, the application also selected other common adulterants or similar substances to participate in the modeling process. The resulting qualitative analysis method can not only optimize the quality control in the drug production process and improve the efficiency of drug testing, but also serve as an important safety measure in the drug circulation and consumption links, greatly reducing the risk of drug confusion and misuse, and protecting consumer health.

[0030] 3. Before executing PLS-DA, Z-Score standardization is used to enable cluster analysis to more sensitively capture subtle differences between samples, thereby improving the accuracy and reliability of modeling; and after obtaining the predicted response value, the appropriate threshold is selected according to the degree of difference between different categories of drugs in the original data to make the qualitative identification process more accurate.

[0031] 4. The identification model of this application can not only optimize the quality control in the drug production process and improve the efficiency of drug inspection, but also serve as an important safety measure in the drug circulation and consumption links, greatly reducing the risk of drug confusion and misuse, and protecting consumer health. In addition, this application also aims to explore the application potential of infrared spectroscopy technology in drug quality control and safety supervision, provide scientific and efficient technical support for drug regulatory authorities and the pharmaceutical industry, and promote the widespread application of infrared spectroscopy technology in the field of pharmaceutical analysis. Through this research, it is expected to contribute to ensuring drug quality and safety and protecting public health, and also provide new ideas and methods for research in related scientific and technological fields. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical scheme and advantages of the embodiments of the present invention clearer, the technical scheme in the embodiments of the present invention will be described clearly and completely below. If the specific conditions are not specified in the embodiments, they are carried out according to conventional conditions or conditions recommended by the manufacturer. If the manufacturer of the reagents or instruments used is not specified, they are all conventional products that can be purchased commercially.

[0033] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments may be combined with each other. The present invention will be described in detail below with reference to specific embodiments.

[0034] The present invention is further described below in conjunction with embodiments.

[0035] Example

[0036] The instruments and equipment used in this embodiment include: Perkin Elmer Spectrum 100 Fourier transform infrared spectrometer; application software version: Spectrum IR 10.6.2.1159, MATLAB R2023b 23.2.0.2365128; computer model: Lenovo; operating system: Microsoft Windows 11Pro for Workstations; processor: IntelCore i7-12800HX@4.80GHz; installed memory (RAM): 32.00GB; system type: 64-bit operating system.

[0037] The standard acetaminophen powder sample selected in this example comes from:

[0038] Chongqing Heping Pharmaceutical Co., Ltd. 37 batches (batch number: 230244, 230344, 230238, 230342, 230228, 230204, 221138, 221235, 221206, 221207, 230209, 230207, 220807, 230215, 230 40, 230417, 230435, 230314, 230451, 230540).

[0039] 22 batches from Baiyunshan Hejigong Pharmaceutical Factory of Guangzhou Baiyunshan Pharmaceutical Group Co., Ltd. (Batch No.: J1782 for 2 batches, K1076 for 2 batches, K1094 for 2 batches, J1757, K1123, J1780, K1075, J1759, J1737, J1341, J1428, J1830, J1794, J1781, J1769, J1766, K1146, J1220, K1006).

[0040] 12 batches from Chongqing Shengao Biochemical Pharmaceutical Co., Ltd. (batch numbers: 221202 for a total of 2 batches, 230304 for a total of 2 batches, 230102 for a total of 2 batches, 230103, 230301, 230302, 230104, 230305, 221101).

[0041] 4 batches of Sichuan Zilinggong Pharmaceutical Co., Ltd. (Batch numbers: 230305, 230301, 230404, 230101).

[0042] 3 batches from Guangdong Nanguo Pharmaceutical Co., Ltd. (Batch numbers: 230315, 230404, 230225).

[0043] 3 batches from Gaitianli Pharmaceutical Holding Group Huadong Pharmaceutical Co., Ltd. (Batch No.: 2302001 for a total of 2 batches, and 2302002).

[0044] 2 batches from Chongqing Core Pharmaceutical (Group) Co., Ltd. (batch numbers: 833004, 813009).

[0045] 2 batches from Chongqing Dikang Changjiang Pharmaceutical Co., Ltd. (batch numbers: 230301, 230401).

[0046] 2 batches from Youhua Pharmaceutical (Leshan) Co., Ltd. (batch numbers: 2023005, 2023001).

[0047] 1 batch from Guizhou Miyi Health Pharmaceutical Co., Ltd. (batch number: 1230204).

[0048] 1 batch from Kangmeibaoning (Sichuan) Pharmaceutical Co., Ltd. (batch number: 221205).

[0049] 1 batch from Yunnan Yizhihao Pharmaceutical Co., Ltd. (batch number: 23020901).

[0050] Other standard samples selected in this embodiment include: Compound Paracetamol Granules, Sichuan Emeishan Pharmaceutical Co., Ltd., product batch number: 20220901 (250 mg of paracetamol, 15 mg of caffeine, 1 mg of chlorpheniramine maleate, 10 mg of artificial bezoar); Aminocacin Capsules, Sichuan Deyuan Pharmaceutical Group Co., Ltd., product batch number: 230401 (250 mg of paracetamol, 15 mg of caffeine, 1 mg of chlorpheniramine maleate, 10 mg of artificial bezoar); Compound acetaminophen tablets, Sichuan Yike Pharmaceutical Co., Ltd., product batch number: 211202 (acetaminophen 250 mg, amantadine hydrochloride 100 mg, chlorpheniramine maleate 2 mg, artificial bezoar 10 mg, caffeine 15 mg); Vitamin C tablets, Sichuan Yike Pharmaceutical Co., Ltd., product batch number: 230403; Sucrose, China Food and Drug Inspection Institute, product batch number: 111507-202105.

[0051] S1: Original data collection: Collect the infrared spectral data of the above 90 standard acetaminophen powder samples and the infrared spectral data of 5 other standard samples, and organize them into a data matrix. Among them, the 5 other standard samples are: Acetophenone Capsules, Compound Acetophenone Tablets, Compound Acetophenone Granules, Vitamin C and Sucrose.

[0052] S2: Data preprocessing and standardization: Perform Z-Score standardization preprocessing on the above data matrix to obtain standardized data.

[0053] S3: Prepare response variables: Create response variables to represent the classification labels of the above original data, which are category 0 and category 1. Category 0 represents the category of Acacia phenol powder, and category 1 represents the category of other drugs.

[0054] S4: PLS-DA modeling: Partial least squares discriminant analysis was used to model the standardized preprocessed data to obtain the PLS-DA model.

[0055] S5: Calculate predicted response value: Calculate the continuous predicted value of the above partial least squares discriminant analysis model.

[0056] S6: Convert to binary classification result: Set the threshold to 0.5 and classify the continuous prediction value into the above category 0 or the above category 1.

[0057] Experimental example

[0058] The identification model obtained in the embodiment is used for qualitative identification to test its reliability and stability. 19 batches of acetaminophen powder samples were purchased from Chongqing Dikang Changjiang Pharmaceutical Co., Ltd., Chongqing Shengao Biochemical Pharmaceutical Co., Ltd., Guizhou Guangzheng Pharmaceutical Co., Ltd., and Yunnan Yizhihao Pharmaceutical Co., Ltd.; 3 batches of compound acetaminophen capsules, 4 batches of compound acetaminophen granules and other 10 batches of drugs with similar functions and indications were selected from the Sichuan Provincial Drug Supervision Sampling Task undertaken by Neijiang Food and Drug Inspection and Testing Center in 2023 and 2024 for verification. The information of each sample and the model judgment results are shown in Table 1. The "yes / no" of the judgment result in the table indicates whether the sample belongs to the acetaminophen powder category.

[0059] The 36 samples involved in this verification were reviewed and tested in accordance with the "National Drug Standards". High performance liquid chromatography and other methods were used to determine the content of the main components of samples 1 to 36. The results are shown in Table 1.

[0060] Table 11 to 36 sample identification and verification results

[0061]

[0062]

[0063] It can be seen from Table 1 that the identification model obtained in the present application can accurately determine the category to which each sample belongs, with an accuracy rate of 100%.

[0064] The embodiments described above are part of the embodiments of the present invention, rather than all of the embodiments. The detailed description of the embodiments of the present invention is not intended to limit the scope of the application claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

Claims

1. A method for establishing an identification model of acetaminophen powder based on partial least squares discriminant analysis, characterized in that: The following steps are involved: S1: Raw data collection: Collect raw data as modeling samples and organize them into a data matrix, wherein the raw data include: infrared spectrum data of standard acetaminophen powder samples and infrared spectrum data of other standard samples; S2: Data preprocessing and standardization: Perform Z-Score standardization preprocessing on the data matrix to obtain standardized data; S3: Prepare response variables: Create response variables for representing the classification labels of the original data, which are divided into category 0 and category 1. Category 0 represents the category to which Acacia phenol belongs, and category 1 represents the category to which other drugs belong; S4: PLS-DA modeling: using partial least squares discriminant analysis to model the standardized data to obtain a partial least squares discriminant analysis model; S5: Calculate predicted response value: calculate the continuous predicted value of the partial least squares discriminant analysis model; S6: Convert to binary classification result: set a threshold to classify the continuous prediction value into category 0 or category 1.

2. The method for establishing an identification model of acetaminophen powder based on partial least squares discriminant analysis according to claim 1, characterized in that: The quantity ratio of the standard acetaminophen powder sample to the other standard samples is 90-150:5-20.

3. The method for establishing an identification model of acetaminophen powder based on partial least squares discriminant analysis according to claim 1, characterized in that: There are 90 standard acetaminophen powder samples and 5 other standard samples.

4. A method for establishing an identification model of acetaminophen powder based on partial least squares discriminant analysis according to any one of claims 1 to 3, characterized in that: The other standard samples include: Aminopeptide Capsules, Compound Aminopeptide Tablets, Compound Aminopeptide Granules, Vitamin C and Sucrose.

5. The method for establishing an identification model of acetaminophen powder based on partial least squares discriminant analysis according to claim 1, characterized in that: In S6, the threshold is set to 0.5.

Images