Auxiliary system for extracting artemisinin

Abstract

The invention provides an auxiliary system for artemisinin extraction, which comprises a processor and a memory, and is characterized in that the processor acquires dynamic data, static data and parameter data influencing extraction efficiency and purity of each node in an artemisinin extraction process, and generates multi-dimensional feature data; the dynamic data comprises real-time dynamic data of each node at different time points in the artemisinin extraction process, and the static data comprises the geometrical shape, capacity, weight and volume of each node; arranging the nodes according to the sequence of the artemisinin extraction process to obtain a node sequence; initializing a node discrimination coefficient, wherein the node discrimination coefficient is a weight influencing extraction efficiency and purity parameters; training and updating the node discrimination coefficient to obtain a discrimination threshold value; and determining an abnormal node according to a comparison result of the discrimination threshold value and the node discrimination coefficient, and taking real-time dynamic data and static data of the abnormal node and parameter data correspondingly influencing the extraction efficiency and purity as a first type of data.

Description

Technical Field

[0001] The invention belongs to the field of artemisinin extraction, and particularly relates to an auxiliary system for artemisinin extraction. Background Art

[0002] At present, artemisinin is an important antimalarial drug, and the efficiency and quality of its extraction process are directly related to the efficacy and production cost of the drug. In order to improve the extraction efficiency and purity of artemisinin, the auxiliary system plays a vital role in the artemisinin extraction process.

[0003] The artemisinin extraction auxiliary systems currently used in the market have significant defects in many aspects, which limit their effectiveness and reliability in practical applications. First, the existing auxiliary systems often fail to meet the high standards of the modern pharmaceutical industry in terms of extraction efficiency. Many systems rely on traditional extraction methods, such as solvent extraction, which are often inefficient and time-consuming when processing large amounts of artemisia annua raw materials, resulting in extended production cycles and increased production costs.

[0004] Traditional methods are easily affected by environmental factors during the extraction process, such as changes in temperature and humidity, which further reduce the stability and consistency of the extraction. Secondly, the current auxiliary systems are insufficient in terms of extraction purity. The extraction process of artemisinin is often accompanied by the generation of other impurities. The existing systems are not advanced enough in the separation and purification of artemisinin, resulting in low purity of the final product, affecting the efficacy and safety of the drug. In addition, many systems fail to effectively control the generation of impurities during the processing process, resulting in complex and costly subsequent purification steps.

[0005] Many auxiliary systems are complex to operate and maintain, lacking user-friendly interfaces and intuitive operation instructions. Operators may need a long period of training to master the use of the system in actual use, which increases labor and training costs. At the same time, when the system fails, the maintenance and troubleshooting process is relatively cumbersome, which may cause the production line to stagnate and increase production losses. In addition, existing auxiliary systems are also insufficient in energy efficiency. Many systems consume high energy when running, especially under high load conditions, which leads to increased production costs. In addition, the system's energy management is not optimized enough, which may lead to energy waste, further aggravating the energy consumption problem. Today, when environmental protection is increasingly valued, it is particularly important to develop more energy-saving and efficient auxiliary systems.

[0006] The current auxiliary systems are generally low in intelligence and automation, lack data monitoring and feedback mechanisms, and cannot monitor the status of the extraction process in real time. This makes it difficult for the system to carry out effective fault warning and adjustment during operation, reducing the flexibility and response speed of production. Therefore, in order to solve the above problems, there is an urgent need for a new auxiliary system for artemisinin extraction that can achieve high efficiency, high purity, user-friendly operation interface, and intelligent monitoring and control, so as to improve the overall efficiency and product quality of artemisinin extraction and meet the high standards of production technology in the modern pharmaceutical industry. Summary of the invention

[0007] The present invention proposes an auxiliary system for artemisinin extraction, which solves the problems of efficiency and purity monitoring in the traditional extraction process. Through comprehensive analysis of real-time dynamic data and static data, abnormal nodes can be intelligently identified and extraction parameters can be optimized, thereby improving the extraction efficiency and product purity of artemisinin.

[0008] The technical solution of the present invention is implemented as follows: an auxiliary system for artemisinin extraction, comprising a processor and a memory, wherein the processor acquires dynamic data, static data and parameter data affecting extraction efficiency and purity of each node in the artemisinin extraction process, and generates multidimensional feature data;

[0009] The dynamic data includes the real-time dynamic data of each node at different time points during the artemisinin extraction process, and the static data includes the geometric shape, capacity, weight and volume of each node; the nodes are arranged in the order of the artemisinin extraction process to obtain a node sequence; the node discrimination coefficient is initialized, and the node discrimination coefficient is the weight of the parameter affecting the extraction efficiency and purity; the node discrimination coefficient is trained and updated to obtain a discrimination threshold;

[0010] The abnormal nodes are determined based on the comparison results of the discrimination threshold and the node discrimination coefficient, and the real-time dynamic data, static data and corresponding parameter data affecting the extraction efficiency and purity of the abnormal nodes are taken as the first category of data; the real-time dynamic data, static data and corresponding parameter data affecting the extraction efficiency and purity of the remaining nodes are taken as the second category of data, and the frequent item sets containing each parameter data are screened out through association rule analysis to generate association rules;

[0011] The parameter data affecting the extraction efficiency and purity are determined according to the association rules, an adjustment command is generated, the adjustment command is sent to the corresponding node, the parameter data is adjusted, and the process parameters in the artemisinin extraction process are adjusted.

[0012] Traditional artemisinin extraction systems often rely on manual monitoring and empirical judgment, and lack real-time data collection of each node in the extraction process. This leads to fluctuations in extraction efficiency and instability in product purity. This system uses a processor to obtain dynamic and static data of each node in the artemisinin extraction process, and can monitor the status of each node in the extraction process in real time. This real-time data collection capability enables the system to respond to changes in the extraction process in a timely manner, ensuring the stability and consistency of the extraction process.

[0013] Existing technologies usually use a single empirical formula or fixed process parameters for parameter optimization, which lacks flexibility and adaptability. The artemisinin extraction process is affected by many factors, including temperature, pressure, time, etc. Traditional methods make it difficult to effectively adjust these parameters to adapt to different extraction conditions. However, this system can intelligently identify key parameters that affect extraction efficiency and purity by generating multidimensional feature data and training and updating node discrimination coefficients. This data-driven parameter optimization method enables the system to adaptively adjust under different extraction conditions, improving the flexibility and pertinence of the extraction.

[0014] Existing technologies have limited capabilities in anomaly detection and processing. Traditional systems often rely on manual judgment to identify problematic nodes, which may lead to delays and misjudgments. However, this system can automatically identify abnormal nodes by initializing the node discrimination coefficient and comparing the discrimination threshold with the node discrimination coefficient. This intelligent anomaly detection mechanism enables the system to respond quickly to potential problems and reduce losses caused by equipment failures or parameter anomalies.

[0015] Existing artemisinin extraction systems often lack depth in data analysis and decision support. This system can screen out frequent item sets that affect extraction efficiency and purity through association rule analysis, thereby generating association rules. This data-driven analysis method enables the system to extract valuable information from historical data and provide a scientific basis for subsequent process optimization. Traditional methods often rely on experience and intuition, lack of systematic analysis and verification, resulting in insufficient scientificity and accuracy in decision-making.

[0016] Existing technologies often lack automation and intelligence in adjusting process parameters, and the operation process is cumbersome. However, this system generates adjustment commands and sends them to corresponding nodes to achieve automated parameter adjustment. This automated design not only improves operational efficiency and reduces the need for manual intervention, but also ensures precise control of the extraction process, further improving the extraction efficiency and product purity of artemisinin.

[0017] As a preferred embodiment, the dynamic data, static data and parameter data affecting the extraction efficiency and purity of each node in the artemisinin extraction process are collected to generate multidimensional feature data, including: normalizing the dynamic data and static data; arranging the dynamic data and static data in chronological order to obtain an original data sequence; segmenting the original data sequence to obtain multiple data subsequences; constructing a first type of data matrix with the data subsequences as rows and the first eigenvectors as columns; constructing the parameter data affecting the extraction efficiency and purity corresponding to each node into a second eigenvector, and arranging the second eigenvectors in chronological order to obtain a second type of data matrix; wherein the first eigenvector includes the normalized dynamic data and static data of each node; and the second eigenvector includes the normalized parameter data affecting the extraction efficiency and purity of each node.

[0018] As a preferred embodiment, each node is arranged in the order of the artemisinin extraction process. After obtaining the node sequence, a third type of data matrix is ​​constructed according to the arrangement order of the node sequence, with each node as a row and the third eigenvector as a column; wherein the second eigenvector includes parameter data of each node that affects the extraction efficiency and purity; the discrimination threshold is multiplied by the corresponding parameter data affecting the extraction efficiency and purity in the second type of data matrix corresponding to each node to obtain the third type of data matrix.

[0019] As a preferred implementation, the node discrimination coefficient is trained and updated, and the obtained discrimination threshold includes obtaining historical training data, the historical training data includes historical process data and label data; wherein the label data is a label marked with parameter data corresponding to each node; based on the historical process data, a classification data matrix is ​​constructed; based on the classification data matrix, a neural network model is used for training to obtain a judgment threshold; wherein the network model includes a feature extraction layer, an activation layer and a classification layer connected in sequence.

[0020] As a preferred implementation, the abnormal node determination process includes taking the real-time dynamic data, static data and corresponding parameter data affecting the extraction efficiency and purity of the abnormal node as the first category of data; otherwise, taking the real-time dynamic data, static data and corresponding parameter data affecting the extraction efficiency and purity of the remaining nodes as the second category of data, and through association rule analysis, screening out frequent item sets containing each parameter data to generate association rules.

[0021] After adopting the above technical solution, the beneficial effect of the present invention is that through real-time data collection and analysis, the system can timely monitor various parameters in the extraction process to ensure the stability of the extraction process. The acquisition of real-time dynamic data enables operators to quickly identify potential problems and adjust parameters in time to avoid losses caused by delays. This timely monitoring not only improves production efficiency, but also reduces downtime caused by problems, ensuring the continuity and efficiency of the production process.

[0022] The system's intelligent parameter optimization capability improves the flexibility and adaptability of the extraction process. By analyzing historical and real-time data, the system can automatically identify the key factors that affect extraction efficiency and purity, and make corresponding adjustments based on actual conditions. This intelligent decision support can help manufacturers better adapt to market demand, optimize production processes, and improve product quality.

[0023] The introduction of anomaly detection and processing mechanisms has significantly improved the security and reliability of the system. By automatically identifying abnormal nodes, the system can implement corresponding measures in a timely manner, reducing the risks caused by equipment failure or parameter abnormalities. This rapid response capability enables enterprises to improve their production stability, ensure product consistency and reliability, and thus enhance market competitiveness.

[0024] The application of data analysis module provides enterprises with a more scientific basis for decision-making. Through association rule analysis, the system can dig out potential optimization paths and help production enterprises make more intelligent decisions in future production. This data-driven management method improves the operational efficiency and management level of enterprises and provides strong support for continuous improvement.

[0025] The automated design of the system reduces the reliance on manual operation, reduces labor costs, and improves production efficiency. Operators can focus more on production monitoring and data analysis, improving the level of intelligence in the production process. This automated operation model not only improves the production capacity of the enterprise, but also lays the foundation for the future transformation of intelligent manufacturing. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0027] Figure 1 The figure is a flow chart of the system of the present invention. DETAILED DESCRIPTION

[0028] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0029] Example:

[0030] like Figure 1 As shown, an auxiliary system for artemisinin extraction includes a processor and a memory, wherein the processor acquires dynamic data, static data and parameter data affecting extraction efficiency and purity of each node in the artemisinin extraction process, and generates multi-dimensional feature data;

[0031] The dynamic data includes the real-time dynamic data of each node at different time points during the artemisinin extraction process, and the static data includes the geometric shape, capacity, weight and volume of each node; the nodes are arranged in the order of the artemisinin extraction process to obtain a node sequence; the node discrimination coefficient is initialized, and the node discrimination coefficient is the weight of the parameter affecting the extraction efficiency and purity; the node discrimination coefficient is trained and updated to obtain a discrimination threshold;

[0032] The abnormal nodes are determined based on the comparison results of the discrimination threshold and the node discrimination coefficient, and the real-time dynamic data, static data and corresponding parameter data affecting the extraction efficiency and purity of the abnormal nodes are taken as the first category of data; the real-time dynamic data, static data and corresponding parameter data affecting the extraction efficiency and purity of the remaining nodes are taken as the second category of data, and the frequent item sets containing each parameter data are screened out through association rule analysis to generate association rules;

[0033] The parameter data affecting the extraction efficiency and purity are determined according to the association rules, an adjustment command is generated, the adjustment command is sent to the corresponding node, the parameter data is adjusted, and the process parameters in the artemisinin extraction process are adjusted.

[0034] The core of the entire workflow lies in the acquisition of dynamic and static data, node identification, anomaly detection, and the generation and execution of adjustment commands. The system starts with the data acquisition stage, and the processor collects dynamic and static data from each node in the artemisinin extraction process. Dynamic data includes real-time data of each node at different time points, such as temperature, pressure, flow rate, etc. These data are crucial for evaluating the real-time status of the extraction process. Static data involves parameters such as the geometry, capacity, weight, and volume of each node. This information helps to understand the physical characteristics of the equipment and its performance during the extraction process. By integrating this data, the system generates multi-dimensional feature data, laying the foundation for subsequent analysis.

[0035] Next, the system arranges each node in the order of the artemisinin extraction process to form a node sequence. This serialization process provides a logical order for subsequent node discrimination and data analysis, allowing the system to more clearly identify the role of each node in the entire extraction process. Initializing the node discrimination coefficient is another key step. The node discrimination coefficient is used to indicate the influence of each parameter on the extraction efficiency and purity. By training and updating these coefficients, the system can derive the discrimination threshold of each parameter for effective comparison in subsequent processing.

[0036] When detecting abnormal nodes, the system compares the discrimination threshold and the node discrimination coefficient. If the discrimination coefficient of a node exceeds the set threshold range, the system will mark it as an abnormal node. At this time, the real-time dynamic data, static data and corresponding parameter data that affect the extraction efficiency and purity of the abnormal node will be classified as the first category of data for in-depth analysis. The data of the remaining nodes are marked as the second category of data. By analyzing these two types of data, the system can identify key parameters that may affect the extraction process.

[0037] During the data analysis phase, the system uses association rule analysis technology to screen out frequent item sets containing each parameter data and generate association rules. These rules can reveal the potential relationship between different parameters, thus helping the system understand which factors have a significant impact on the extraction efficiency and purity of artemisinin.

[0038] Based on the generated association rules, the system can determine the specific parameter data that affects the extraction efficiency and purity, and generate adjustment commands accordingly. These adjustment commands will be sent to the corresponding nodes to adjust the corresponding parameters to optimize the artemisinin extraction process. This process may involve real-time adjustment of process parameters such as temperature, pressure, and flow rate to ensure that the extraction process is always in the best state and maximize the yield and purity of artemisinin.

[0039] The method of collecting dynamic data, static data and parameter data affecting extraction efficiency and purity of each node in the process of artemisinin extraction to generate multidimensional feature data includes: normalizing dynamic data and static data; arranging dynamic data and static data in chronological order to obtain an original data sequence; segmenting the original data sequence to obtain multiple data subsequences; constructing a first type of data matrix with the data subsequences as rows and the first feature vectors as columns; constructing the parameter data affecting extraction efficiency and purity corresponding to each node into a second feature vector, and arranging the second feature vectors in chronological order to obtain a second type of data matrix; wherein the first feature vector includes the normalized dynamic data and static data of each node; and the second feature vector includes the normalized parameter data affecting extraction efficiency and purity of each node.

[0040] In the process of artemisinin extraction, the dynamic data, static data and parameter data affecting the extraction efficiency and purity of each node are collected and processed, and the steps of generating multidimensional feature data reflect significant differences from the existing technology. The traditional extraction process often relies on a single, static data collection method, lacking comprehensive analysis and processing of dynamic changes. This solution constructs the original data sequence by normalizing the dynamic and static data and arranging them in chronological order. This method not only improves the comparability of the data, but also ensures that the impact of time factors on the extraction efficiency and purity can be fully considered during the analysis. In addition, by processing the original data sequence in segments, generating multiple data subsequences and constructing the first and second data matrices, this systematic feature extraction method makes the data analysis more comprehensive and detailed, and provides a solid data foundation for subsequent efficiency and purity optimization.

[0041] Each node is arranged in the order of the artemisinin extraction process to obtain a node sequence, and then a third type of data matrix is ​​constructed according to the arrangement order of the node sequence, with each node as a row and the third eigenvector as a column; wherein the second eigenvector includes parameter data of each node that affects the extraction efficiency and purity; the discrimination threshold is multiplied by the corresponding parameter data affecting the extraction efficiency and purity in the second type of data matrix corresponding to each node to obtain the third type of data matrix.

[0042] After arranging each node in the order of the artemisinin extraction process, the step of constructing the third type of data matrix shows the further innovation of this scheme. In the prior art, there is often a lack of in-depth analysis of the mutual influence between nodes. This scheme combines the node sequence with the feature vector to systematically analyze the influence of each node on the extraction efficiency and purity. By multiplying the discrimination threshold with the parameter data in the second type of data matrix to obtain the third type of data matrix, this method not only enhances the operability of the data, but also provides a quantitative basis for subsequent judgments and decisions. Compared with traditional methods, this scheme has a deeper level of dynamic analysis of the relationship between nodes and can more scientifically guide the optimization of the extraction process.

[0043] The node discrimination coefficient is trained and updated to obtain a discrimination threshold, which includes obtaining historical training data, the historical training data including historical process data and label data; wherein the label data is a label marked with parameter data corresponding to each node; based on the historical process data, a classification data matrix is ​​constructed; based on the classification data matrix, a neural network model is used for training to obtain a judgment threshold; wherein the network model includes a feature extraction layer, an activation layer and a classification layer connected in sequence.

[0044] In terms of training and updating the node discrimination coefficient, this solution obtains historical training data, including historical process data and label data, constructs a classification data matrix, and uses a neural network model for training to obtain a judgment threshold. The main difference between this process and the existing technology is that traditional methods often rely on experience or simple statistical analysis and lack a systematic learning and adjustment mechanism. This solution introduces a neural network model and uses deep learning methods to mine potential relationships in the data, thereby improving the accuracy and adaptability of the discrimination threshold. The step-by-step connection design of the feature extraction layer, activation layer, and classification layer provides a stronger expression capability for the learning of complex data relationships and significantly improves the level of intelligence.

[0045] The process of determining the abnormal node includes taking the real-time dynamic data, static data and corresponding parameter data affecting the extraction efficiency and purity of the abnormal node as the first category of data; otherwise, taking the real-time dynamic data, static data and corresponding parameter data affecting the extraction efficiency and purity of the remaining nodes as the second category of data, and screening out frequent item sets containing each parameter data through association rule analysis to generate association rules.

[0046] In the process of determining abnormal nodes, this solution demonstrates its difference from the existing technology by systematically analyzing the real-time dynamic data, static data and corresponding parameter data that affect the extraction efficiency and purity of the nodes. The existing technology often lacks real-time monitoring and analysis of abnormal states, while this solution uses association rule analysis to screen out frequent item sets and generate association rules, so that abnormal nodes can be identified more effectively. The data discriminant coefficient of the node and its difference are defined, and a method for quantitative anomaly detection is provided in combination with the preset threshold and the distance of the node discriminant coefficient vector. This method not only improves the accuracy of anomaly detection, but also can find potential abnormal patterns in multi-dimensional data. Compared with the traditional single indicator analysis method, it is more comprehensive and in-depth.

[0047] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. An auxiliary system for artemisinin extraction, characterized in that: It includes a processor and a memory, wherein the processor acquires dynamic data, static data and parameter data affecting extraction efficiency and purity of each node in the process of artemisinin extraction, and generates multi-dimensional feature data; The dynamic data includes the real-time dynamic data of each node at different time points during the artemisinin extraction process, and the static data includes the geometric shape, capacity, weight and volume of each node; Arrange each node according to the order of the artemisinin extraction process to obtain a node sequence; Initialize the node discrimination coefficient, which is the weight of the parameters affecting extraction efficiency and purity; Train and update the node discrimination coefficient to obtain the discrimination threshold; The abnormal nodes are determined based on the comparison results of the discrimination threshold and the node discrimination coefficient, and the real-time dynamic data, static data and corresponding parameter data affecting the extraction efficiency and purity of the abnormal nodes are taken as the first category of data; the real-time dynamic data, static data and corresponding parameter data affecting the extraction efficiency and purity of the remaining nodes are taken as the second category of data, and the frequent item sets containing each parameter data are screened out through association rule analysis to generate association rules; The parameter data affecting the extraction efficiency and purity are determined according to the association rules, an adjustment command is generated, the adjustment command is sent to the corresponding node, the parameter data is adjusted, and the process parameters in the artemisinin extraction process are adjusted.

2. The auxiliary system for artemisinin extraction according to claim 1, characterized in that: The method of collecting dynamic data, static data and parameter data affecting extraction efficiency and purity of each node in the process of artemisinin extraction to generate multidimensional feature data includes: normalizing dynamic data and static data; arranging dynamic data and static data in chronological order to obtain an original data sequence; segmenting the original data sequence to obtain multiple data subsequences; constructing a first type of data matrix with the data subsequences as rows and the first feature vectors as columns; constructing the parameter data affecting extraction efficiency and purity corresponding to each node into a second feature vector, and arranging the second feature vectors in chronological order to obtain a second type of data matrix; wherein the first feature vector includes the normalized dynamic data and static data of each node; and the second feature vector includes the normalized parameter data affecting extraction efficiency and purity of each node.

3. The auxiliary system for artemisinin extraction according to claim 2, characterized in that: Each node is arranged in the order of the artemisinin extraction process to obtain a node sequence, and then a third type of data matrix is ​​constructed according to the arrangement order of the node sequence, with each node as a row and the third eigenvector as a column; wherein the second eigenvector includes parameter data of each node that affects the extraction efficiency and purity; the discrimination threshold is multiplied by the corresponding parameter data affecting the extraction efficiency and purity in the second type of data matrix corresponding to each node to obtain the third type of data matrix.

4. The auxiliary system for artemisinin extraction according to claim 1, characterized in that: The node discrimination coefficient is trained and updated to obtain a discrimination threshold, which includes obtaining historical training data, the historical training data including historical process data and label data; wherein the label data is a label marked with parameter data corresponding to each node; based on the historical process data, a classification data matrix is ​​constructed; based on the classification data matrix, a neural network model is used for training to obtain a judgment threshold; wherein the network model includes a feature extraction layer, an activation layer and a classification layer connected in sequence.

5. The auxiliary system for artemisinin extraction according to claim 1, characterized in that: The process of determining the abnormal node includes taking the real-time dynamic data, static data and corresponding parameter data affecting the extraction efficiency and purity of the abnormal node as the first category of data; otherwise, taking the real-time dynamic data, static data and corresponding parameter data affecting the extraction efficiency and purity of the remaining nodes as the second category of data, and screening out frequent item sets containing each parameter data through association rule analysis to generate association rules.

Images