Method for establishing Akafen powder identification model based on clustering analysis method

Abstract

The invention discloses a method for establishing an akafen powder identification model based on a clustering analysis method, 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, carrying out clustering analysis; and S4, model establishment and evaluation. The invention provides a method for modeling by utilizing hierarchical clustering analysis, and by setting and selecting modeling parameters such as original data, distance measurement, a linking method, cutoff parameter distance and the like, the obtained infrared qualitative analysis model of the akafen powder can be used for effectively and qualitatively identifying whether an unknown sample belongs to the akafen powder or not.

Description

Technical Field

[0001] The present invention belongs to the technical field of drug inspection, and specifically, relates to the technical field of establishing an acetaminophen powder identification model 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 provides innovative solutions for the field of chemical and pharmaceutical analysis. By analyzing the absorption characteristics of molecules to infrared spectra, 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 with application number CN202011642155.7 discloses a method, device and medium for identifying honeysuckle based on infrared spectroscopy. The method includes: establishing a honeysuckle identification model by cluster analysis using a data set A pre-processed with infrared spectra of different standard honeysuckle samples and their identification information; the pre-processing includes: selecting characteristic peak bands from the one-dimensional spectrum of the infrared spectrum, and performing vector normalization (SNV) standard normal variable transformation processing; inputting the corresponding data set B of the honeysuckle sample to be tested into the identification model to obtain the identification information of the honeysuckle sample to be tested; the identification information includes base information, and / or origin information, and / or harvest period information. The application collects infrared spectra of different standard honeysuckle samples, pre-processes these spectral data, and uses the SIMCA cluster analysis method to establish an identification model based on honeysuckle samples of different bases, origins and harvest periods, that is, using a sample set with identification information (i.e., a data set A labeled with base, origin, harvest period, etc.) to "train" the cluster analysis model. In the process, the model will learn how to assign samples to different categories based on the characteristics of the spectral data. In other words, the identification information of the honeysuckle in this application is known, and it is only necessary to train different infrared spectral data models to achieve a complete match with the identification information. However, for the acetaminophen powder, which has complex infrared spectral data, mutual interference between the infrared peaks of the main components and unclear characteristics, and has no known identification information, there is no way to use this method to train the corresponding model based on the collected data.

[0005] The Chinese patent application number CN200810052425.1 discloses a method for identifying Chinese herbal medicines by combining infrared spectroscopy with cluster analysis, comprising the following steps: (1) selecting a standard sample of Chinese herbal medicines of the same type; (2) performing infrared spectroscopy detection on the standard sample to obtain an infrared spectrum; (3) using a cluster analysis method to establish a standard infrared model of the Chinese herbal medicine for the obtained infrared spectrum; (4) using the standard infrared model to compare with the infrared spectrum of the Chinese herbal medicine sample to be tested, and then directly analyzing and identifying the Chinese herbal medicine. The application introduces the application of cluster analysis to the identification and classification of infrared spectra of Chinese herbal medicines such as Danshen, Millettia reticulata, and Pinellia ternata, and finds some statistics that can measure the similarity between samples. Based on this, some samples with a high degree of similarity are clustered into one category, and samples with a distant degree of similarity are clustered into a large classification unit. Finally, the classification system is intuitively represented by a graph (a pedigree graph or a clustering graph, a clustering graph, etc.) to clearly reflect the closeness and distance between samples or variables. This method classifies patterns according to the differences between different objects and the law of distance function, classifying similar objects into one category and dissimilar objects into another category. The key is to select appropriate features. In other words, the cluster analysis of this application is to find commonalities in the infrared spectrum data set of similar drugs to obtain modeling results, but it does not cluster different types of drugs together, find the commonalities of the target drugs and their specificity, especially the degree of accuracy of subtle features. This application does not take into account the damage of similar medicinal materials to the accuracy of the model.

[0006] The Chinese patent with application number CN202110448025.8 discloses a method for tracing the origin of millet based on mid-infrared spectroscopy technology and feature extraction, comprising the following steps: Step 1, respectively collect infrared spectra of millet samples from different origins for preprocessing; Step 2, first perform principal component analysis on the infrared spectral data preprocessed in step 1, then group the variable data using the window analysis method, respectively use support vector machines to establish classification models, and then use the hierarchical clustering analysis method to determine a group of variable data with small correlations, and construct a millet origin identification model; Step 3, collect infrared spectra of millet samples of unknown origin, preprocess them, input the millet origin identification model, and output the origin of the millet sample. This method is based on the millet origin tracing method based on mid-infrared spectroscopy technology and feature extraction, and can quickly identify the origin of millet. Similarly, the application also simply uses a certain analysis method to model the original data under the premise of known classification, and still does not point out how to deal with the acetaminophen powder medicine with more complicated situations and unknown features.

[0007] In summary, although the above patents all point out that cluster analysis can be used to process the infrared spectral data of drugs and establish an analysis model, since the infrared spectral data of acetaminophen powder includes a large number of overlapping peaks that interfere with the detection, direct modeling using the above method often has many problems. Therefore, finding an infrared spectral qualitative analysis model for acetaminophen powder and establishing a detection method has become a technical problem that needs to be urgently solved by technical personnel in this field. Summary of the invention

[0008] The infrared spectrum data of Acacia phenol powder has many overlapping peaks and is difficult to classify. In particular, when cluster analysis is used, precise preprocessing and feature extraction are required to ensure the effectiveness of clustering. The purpose of the present invention is to provide a method for modeling using hierarchical cluster analysis to obtain an infrared qualitative analysis model of Acacia phenol powder, which can effectively determine whether an unknown sample belongs to Acacia phenol powder, thereby achieving qualitative identification.

[0009] The technical solution adopted by the present invention to solve its technical problem is:

[0010] A detection method for acetaminophen powder based on cluster analysis method comprises the following steps:

[0011] S1: Raw data collection: Raw data are collected as modeling samples, and the raw data include: infrared spectral data of standard acetaminophen powder samples and infrared spectral data of other standard samples; the ratio of the number of standard acetaminophen powder samples to the number of 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: Aciclovine Capsules, Compound Aciclovine Tablets, Compound Aciclovine Granules, Vitamin C and Sucrose, all of which are commercially available standard products of any batch.

[0012] 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 Aciclovine Capsules, Compound Aciclovine Tablets, Compound Aciclovine 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, the product of Aciprofloxacin Capsules is in powder form 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 are similar to those of acetaminophen powder; the product of Compound Aciprofloxacin Tablets is in powder form 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 are similar to those of acetaminophen powder; the product of Compound Aciprofloxacin Granules is in powder form 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 are similar to those of acetaminophen powder; Vitamin C and sucrose are general additives in the pharmaceutical process. The sources of raw materials are wide, the production, circulation and use are not strictly supervised, and they are cheap and widely used, so they are easily used in the production of fake and inferior drugs. In addition, due to the similar infrared absorption peaks with acetaminophen powder, adding the above drugs as the basis for classification and adjusting the modeling strategy accordingly can make the results of cluster analysis and classification more accurate and make the obtained infrared qualitative analysis model more credible.

[0013] S2: Data preprocessing and standardization: Perform Z-Score standardization preprocessing on the above raw data to obtain standardized data.

[0014] In this step, Z-Score standardization is used as a key step in data preprocessing for spectral data collected by infrared spectroscopy (IR). Z-Score standardization, also known as standard deviation standardization, is a data standardization method that aims to eliminate the impact of dimension by adjusting the scale of the data while reducing 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 wavenumber point from its original value, and then dividing it by the standard deviation of that wavenumber 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 wavenumber (or frequency), μ is the average spectral intensity value of all samples at that wavenumber, and σ is the standard deviation of the spectral intensity values ​​of all samples at that wavenumber. In this way, the data at each wavenumber point is converted to a distribution centered on 0 with a standard deviation of 1.

[0015] 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.

[0016] S3: Cluster analysis: The euclidean distance metric and complete linkage were used to perform hierarchical clustering on the above standardized data and produce a dendrogram.

[0017] In this application, the cluster analysis method used is hierarchical clustering, and the complete linkage method is adopted, which is an agglomerative clustering strategy that can merge the most distant clusters in each clustering process. Agglomerative clustering is suitable for small to medium-sized data sets, can generate detailed hierarchical structures, and has certain intuitiveness and ease of operation in practical applications.

[0018] In the specific data processing process, the distances between all samples are first calculated to form a distance matrix. Then, according to the selected link strategy, the most similar samples or sample groups are gradually merged. By repeating this merging process, all samples are finally merged into one group, and the entire merging history is recorded and displayed in the form of a dendrogram. The application selects the Euclidean distance and the fully linked method, and selects the infrared spectrum data of other standard samples added. Compared with Acacia phenol powder, for its main components, that is, the infrared spectra of caffeine, acetaminophen and aspirin, the classification strategy of Euclidean distance and the fully linked classification strategy can better avoid misunderstandings of data structure.

[0019] Depend on Figure 1 It can be seen that under the original data and classification strategy selected in the present application, the dendrogram obtained in the embodiment is easy to prune, and then the dendrogram is cut by selecting different height values ​​to form different numbers of clusters; in addition, when using the full link method, since the clusters are merged based on the distance of the farthest point, outliers or outliers may have a greater impact on the clustering results, making the modeling results more sensitive to outliers, thereby enhancing its credibility.

[0020] S4: Model establishment and evaluation: The cutoff parameter distance is adopted, that is, the distance threshold is 201-318, preferably 201, to cut the above-mentioned dendrogram, divide the standardized data into different clusters, and obtain two main clusters, namely, acetaminophen powder and non-acetaminophen powder, so as to establish an infrared qualitative analysis model.

[0021] In this step, in the resulting dendrogram, look for a longer vertical line segment, and cut at this height to form a more reasonable cluster. In the actual operation process, it is also necessary to evaluate the stability of the model. By evaluating the test, it is possible to test whether the model can accurately capture the patterns and relationships in the data, thereby verifying the validity of the model, and ensuring that the model can effectively qualitatively identify whether the unknown sample belongs to the acetaminophen powder class. Because the evaluation test generally involves dividing the data into a training set and a test set, the model is established on the training set, and is evaluated on the test set, and the performance of the model on the unseen data is checked, thereby evaluating its generalization ability, and preventing the model from overfitting the training data. By evaluating the different parameter settings of multiple models or the same model, their performance can be compared, and the best model or parameter is selected, which helps to improve the prediction accuracy and reliability of the model.

[0022] In summary, cluster analysis, as an unsupervised learning method, can group a group of objects by processing raw data, so that members within the group are more similar than members between groups. In the present application, cluster analysis is used to find the intrinsic structure in the infrared spectral data of multiple groups of drugs mainly composed of acetaminophen powder. As a drug containing multiple chemical components, the infrared spectrum of acetaminophen powder contains complex waveforms and peaks of various chemical components. These peaks often interfere with each other in the actual detection process, especially when there is adulteration and doping, the interference between the infrared spectrum absorption peaks will cause difficulties in the infrared detection process. Combined with the characteristics of hierarchical cluster analysis, since complex data itself will naturally form a series of groups according to its characteristics, these groups often cannot be pre-set, but can be automatically discovered by algorithms, even if these groups are very close in infrared spectral data. Further, hierarchical cluster analysis can identify similarities at different levels, which is particularly important for identifying variants of different chemical structures in chemical analysis, so that hierarchical cluster analysis can effectively process the infrared spectral data of acetaminophen powder and its analogs, and make individual distinctions while finding the commonalities therein.

[0023] Compared with the prior art, the embodiments of the present invention have at least the following beneficial effects:

[0024] 1. The infrared spectrum data of Acacia phenol powder includes a large number of overlapping peaks. This application uses cluster analysis to explore the natural grouping of multiple groups of drugs based on the infrared spectrum samples of Acacia phenol powder under the framework of unsupervised learning, and obtains the infrared qualitative analysis model of Acacia phenol powder.

[0025] 2. Before the hierarchical cluster analysis, Z-Score standardization is used to make the cluster analysis more sensitive to the subtle differences between samples, thereby improving the accuracy and reliability of clustering; and in the process of hierarchical cluster analysis, appropriate distance measurement and linkage methods are selected to avoid misunderstanding of data structure due to improper selection.

[0026] 3. In addition to acetaminophen powder, other common adulterants were added to the modeling process in the application. The resulting identification model can not only be used to optimize quality control in the drug production process and improve the efficiency of drug testing, but also can be used as an important safety measure in the drug circulation and consumption process, greatly reducing the risk of drug confusion and misuse, and protecting consumer health. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments and comparative examples are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0028] Figure 1 A dendrogram of cluster analysis of an embodiment. DETAILED DESCRIPTION

[0029] 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.

[0030] 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.

[0031] The present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0032] Example

[0033] like Figure 1 As shown, Figure 1A dendrogram of cluster analysis of an embodiment.

[0034] 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 R2023b23.2.0.2365128; 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.

[0035] The standard acetaminophen powder sample selected in this example comes from:

[0036] 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).

[0037] 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).

[0038] 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).

[0039] 4 batches of Sichuan Zilinggong Pharmaceutical Co., Ltd. (Batch numbers: 230305, 230301, 230404, 230101).

[0040] 3 batches from Guangdong Nanguo Pharmaceutical Co., Ltd. (Batch numbers: 230315, 230404, 230225).

[0041] 3 batches from Gaitianli Pharmaceutical Holding Group Huadong Pharmaceutical Co., Ltd. (Batch No.: 2302001 for a total of 2 batches, and 2302002).

[0042] 2 batches from Chongqing Core Pharmaceutical (Group) Co., Ltd. (batch numbers: 833004, 813009).

[0043] 2 batches from Chongqing Dikang Changjiang Pharmaceutical Co., Ltd. (batch numbers: 230301, 230401).

[0044] 2 batches from Youhua Pharmaceutical (Leshan) Co., Ltd. (batch numbers: 2023005, 2023001).

[0045] 1 batch from Guizhou Miyi Health Pharmaceutical Co., Ltd. (batch number: 1230204).

[0046] 1 batch from Kangmeibaoning (Sichuan) Pharmaceutical Co., Ltd. (batch number: 221205).

[0047] 1 batch from Yunnan Yizhihao Pharmaceutical Co., Ltd. (batch number: 23020901).

[0048] 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.

[0049] S1: Original data collection: Collect infrared spectral data of the above 90 standard acetaminophen powder samples and infrared spectral data of 5 other standard samples. The 5 other standard samples are: Acetophenone Capsules, Compound Acetophenone Tablets, Compound Acetophenone Granules, Vitamin C and Sucrose.

[0050] S2: Data preprocessing and standardization: Perform Z-Score standardization preprocessing on the above raw data to obtain standardized data.

[0051] S3: Cluster analysis: The euclidean distance metric and complete linkage were used to perform hierarchical clustering on the above standardized data to generate a dendrogram, such as Figure 1 shown.

[0052] S4: Model establishment: Set the distance threshold to 201, cut the above dendrogram, divide the clustering results, and obtain two main clusters, namely, acetaminophen powder and non-acetaminophen powder, to obtain the infrared qualitative analysis model.

[0053] Use the bootstrap method to evaluate the stability of hierarchical clustering. Set the number of repetitions to 100, generate bootstrap samples each time through sampling with replacement, and perform hierarchical clustering on the bootstrap samples. Then, calculate the Rand Index of the bootstrap sample clustering results and the original clustering results to measure the similarity between the two, and record the stability score each time. Finally, calculate the average stability score of all bootstrap samples.

[0054] After calculation, the average clustering stability of this embodiment is: 0.924020. The clustering stability score shows that the clustering method is quite stable on this data set, which means that the clustering has good resistance to random fluctuations or noise in the data. Even under the influence of sampling changes or potential noise, the clustering results do not change much, and the results are unlikely to be caused by random factors or the specificity of a single sampling.

[0055] Experimental example

[0056] 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 Tasks undertaken by Neijiang Food and Drug Inspection and Testing Center in 2023 and 2024 for verification. The information of each sample and the judgment results of the use model 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.

[0057] The 36 samples participating in the verification were reviewed and tested in accordance with the national drug implementation standards under their respective varieties. High performance liquid chromatography and other methods were used to determine the content of the main components of samples No. 1 to 36. The results are shown in Table 1.

[0058] Table 11 to 36 sample identification and verification results

[0059]

[0060]

[0061] 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%.

[0062] 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 cluster analysis, characterized in that: The following steps are involved: S1: Raw data collection: Collect raw data as modeling samples, the raw data including: infrared spectrum data of standard acetaminophen powder sample and infrared spectrum data of other standard samples; S2: Data preprocessing and standardization: The raw data is preprocessed by Z-Score standardization to obtain standardized data; S3: Cluster analysis: performing hierarchical clustering on the standardized data to generate a dendrogram; S4: Model establishment and evaluation: The dendrogram is cut and the standardized data is divided into different clusters by setting a distance threshold, thereby obtaining two main clusters, namely, acetaminophen powder and non-acetaminophen powder, and obtaining an infrared qualitative analysis model.

2. The method for establishing an identification model of acetaminophen powder based on cluster analysis according to claim 1, characterized in that: The number 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 cluster analysis according to claim 1 or 2, characterized in that: Said S1 includes: infrared spectrum data of 90 standard acetaminophen powder samples and infrared spectrum data of 5 other standard samples.

4. The method for establishing an identification model of acetaminophen powder based on cluster analysis according to claim 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 cluster analysis according to claim 1, characterized in that: In S3, hierarchical clustering is performed on the standardized data using Euclidean distance metric and complete linkage.

6. The method for establishing an identification model of acetaminophen powder based on cluster analysis according to claim 1, characterized in that: In S4, the distance threshold is 201-318 to cut the dendrogram.

7. The method for establishing an identification model of acetaminophen powder based on cluster analysis according to claim 6, characterized in that: The distance threshold is 201.

Images