Intelligent identification method and device for chromatographic peak

Abstract

The invention discloses an intelligent identification method and device for chromatographic peaks, and the method comprises the steps: defining a primary chromatogram according to a detection mode and a to-be-detected fluid, and defining an abnormal region based on the identification of the primary chromatogram; according to the method, the optimization part is output according to autonomous optimization of the abnormal region, the final chromatogram is defined according to multiple interaction of the optimization part and the primary chromatogram, the accuracy of the final chromatogram is ensured, multi-stage control is carried out on the chromatographic test of the fluid to be detected, and optimization of the primary chromatogram, optimization of the abnormal region and optimization of the final chromatogram are sequentially completed. Furthermore, a plurality of peak shape features are defined according to each peak value region and the contour recognition system, and a chromatographic peak is defined according to the plurality of peak shape features, the to-be-detected fluid and the intelligent recognition system, so that the chromatographic peak is intelligently recognized, and multi-dimensional control of the plurality of peak shape features, the to-be-detected fluid and the intelligent recognition system is realized. The intelligent identification effect of the chromatographic peak is ensured; and the accuracy of the chromatographic peak is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of chromatographic peaks, and in particular, to an intelligent recognition method and device for chromatographic peaks. Background Art

[0002] With the development of technology, chromatographic peaks, as part of a chromatogram, are formed based on the on-line detection of a fluid to be detected. The chromatogram contains chromatographic peaks and presents them externally. In the prior art, a chromatogram is introduced and needs to be recognized. During the recognition process, the chromatogram is not the final chromatogram, and it is impossible to ensure the multi-level control of the chromatogram, resulting in poor intelligent recognition effect of chromatographic peaks. Summary of the Invention

[0003] The purpose of the present invention is to overcome the deficiencies of the prior art, and the present invention provides an intelligent recognition method and device for chromatographic peaks.

[0004] An embodiment of the present invention provides an intelligent recognition method for chromatographic peaks, which is applied to the intelligent recognition scenario of chromatographic peaks;

[0005] The intelligent recognition method for chromatographic peaks includes:

[0006] Defining a detection posture according to the information of the fluid to be detected and the detection scenario;

[0007] Defining a detection mode based on the flow state of the fluid to be detected, the corresponding detection posture, and the environmental level;

[0008] Defining a primary chromatogram according to the detection mode and the fluid to be detected, and defining an abnormal area based on the recognition of the primary chromatogram;

[0009] Outputting an optimized part according to the self-optimization of the abnormal area, and defining the final chromatogram according to the multiple interactions between the optimized part and the primary chromatogram;

[0010] In the final chromatogram, defining multiple distribution areas based on the final chromatogram and the previous area data of the fluid to be detected, and defining a peak area according to the multiple distribution areas and the peak range corresponding to the fluid to be detected;

[0011] Defining multiple peak shape features according to each peak area and the contour recognition system, and defining chromatographic peaks according to the multiple peak shape features, the fluid to be detected, and the intelligent recognition system to perform intelligent recognition of chromatographic peaks.

[0012] In addition, an embodiment of the present invention also provides an intelligent recognition device for chromatographic peaks. The intelligent recognition device for chromatographic peaks includes:

[0013] A detection posture module for defining a detection posture according to the information of the fluid to be detected and the detection scenario;

[0014] A detection mode module, configured to define a detection mode based on the flow state of the fluid to be detected, the corresponding detection posture, and the environmental level;

[0015] An abnormal area module, configured to define a primary chromatogram according to the detection mode and the fluid to be detected, and define an abnormal area based on the recognition of the primary chromatogram;

[0016] A chromatogram module, configured to output an optimized part according to the autonomous optimization of the abnormal area, and define a final chromatogram according to the multiple interactions between the optimized part and the primary chromatogram;

[0017] A peak area module, configured to define multiple distribution areas in the final chromatogram based on the final chromatogram and the previous area data of the fluid to be detected, and define a peak area according to the multiple distribution areas and the peak range corresponding to the fluid to be detected;

[0018] An identification module, configured to define multiple peak shape features according to each peak area and the contour recognition system, and define a chromatographic peak according to the multiple peak shape features, the fluid to be detected, and the intelligent recognition system, so as to perform intelligent recognition on the chromatographic peak.

[0019] In an embodiment of the present invention, through the method in the embodiment of the present invention, an abnormal area is defined based on the recognition of the primary chromatogram; an optimized part is output according to the autonomous optimization of the abnormal area, and a final chromatogram is defined according to the multiple interactions between the optimized part and the primary chromatogram, which is compatible with the optimization of the abnormal area, and performs multiple interactions on the optimized part and the primary chromatogram, ensuring the accuracy of the final chromatogram, and performing multi-level control on the chromatographic test of the fluid to be detected, and successively completing the optimization of the primary chromatogram, the abnormal area, and the final chromatogram.

[0020] Further, in the final chromatogram, a chromatographic peak is defined according to multiple peak shape features, the fluid to be detected, and the intelligent recognition system, so as to perform intelligent recognition on the chromatographic peak, which is compatible with the overall consideration of multiple peak shape features, the fluid to be detected, and the intelligent recognition system, realizes multi-dimensional control of multiple peak shape features, the fluid to be detected, and the intelligent recognition system, ensures the intelligent recognition effect of the chromatographic peak, and improves the accuracy of the chromatographic peak. Description of the Drawings

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0022] Figure 1It is a schematic flow chart of the intelligent recognition method of chromatographic peaks in the embodiments of the present invention;

[0023] Figure 2 It is a schematic flow chart of S11 in the intelligent recognition method of chromatographic peaks in the embodiments of the present invention;

[0024] Figure 3 It is a schematic flow chart of S12 in the intelligent recognition method of chromatographic peaks in the embodiments of the present invention;

[0025] Figure 4 It is a schematic flow chart of S13 in the intelligent recognition method of chromatographic peaks in the embodiments of the present invention;

[0026] Figure 5 It is a schematic flow chart of S14 in the intelligent recognition method of chromatographic peaks in the embodiments of the present invention;

[0027] Figure 6 It is a schematic flow chart of S15 in the intelligent recognition method of chromatographic peaks in the embodiments of the present invention;

[0028] Figure 7 It is a schematic flow chart of S16 in the intelligent recognition method of chromatographic peaks in the embodiments of the present invention;

[0029] Figure 8 It is a schematic diagram of the structural composition of the intelligent recognition device of chromatographic peaks in the embodiments of the present invention. Detailed implementation manners

[0030] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0031] Please refer to Figures 1 to 8 , an intelligent recognition method of chromatographic peaks, which is applied to the intelligent recognition scenario of chromatographic peaks; the intelligent recognition method of chromatographic peaks includes:

[0032] Step S11: Define the detection posture according to the information of the fluid to be detected and the detection scenario;

[0033] Step S12: Define the detection mode based on the flow state of the fluid to be detected, the corresponding detection posture, and the environmental level;

[0034] Step S13: Define a primary chromatogram according to the detection mode and the fluid to be detected, and define an abnormal area based on the recognition of the primary chromatogram;

[0035] Step S14: Output the optimized part according to the autonomous optimization of the abnormal area, and define the final chromatogram based on the multiple interactions between the optimized part and the primary chromatogram;

[0036] Step S15: In the final chromatogram, define multiple distribution areas based on the final chromatogram and the previous area data of the fluid to be detected, and define the peak area according to the multiple distribution areas and the peak range corresponding to the fluid to be detected;

[0037] Step S16: Define multiple peak shape features according to each peak area and the contour recognition system, and define the chromatographic peak according to the multiple peak shape features, the fluid to be detected and the intelligent recognition system, so as to perform intelligent recognition on the chromatographic peak.

[0038] Reference Figure 2 , in step S11, define the detection posture according to the information of the fluid to be detected and the detection scenario;

[0039] In the specific implementation process of the present invention, the specific steps may be:

[0040] S111: Collect the position where the fluid to be detected is located;

[0041] S112: Determine the information of the detection fluid according to the detection of the position where the fluid to be detected is located;

[0042] S113: Associate the information of the detection fluid and the detection scenario;

[0043] S114: Perform multiple interactions on the information of the detection fluid and the detection scenario;

[0044] S115: Define the detection posture based on the information of the fluid to be detected and the detection scenario. At this time, the detection posture is the optimal detection posture of the fluid to be detected.

[0045] In the embodiments of the present application, according to the experimental environment and the characteristics of the fluid to be detected, a suitable positioning technology is selected. Common positioning technologies include sensor networks, RFID (Radio Frequency Identification), machine vision, etc. Using the selected positioning technology, the position information where the fluid to be detected is located is collected in real time. Ensure that the collected data is accurate, reliable, and can be updated in real time.

[0046] Based on the collected position information, establish a position monitoring system. This system should be able to display the position of the fluid to be detected in real time and support alarm and early warning functions. According to the experimental requirements and safety specifications, formulate a control strategy for the position of the fluid to be detected. Including restrictions on position movement, real-time monitoring and alarm of position changes, etc. Through an automated control system or manual intervention, execute the position control strategy. Ensure that the fluid to be detected moves within the predetermined position range to avoid analysis errors or safety risks caused by abnormal positions.

[0047] Associate the collected location information with other information of the fluid to be detected (such as chemical composition, physical state, etc.). Ensure that there is a corresponding information record for the fluid at each location. At the location where the fluid to be detected is located, use appropriate detection means (such as chromatographs, mass spectrometers, etc.) to obtain fluid information. Ensure the accuracy and reliability of the detection results.

[0048] Therefore, associate the information of the fluid to be detected and the detection scenario; perform multiple interactions on the information of the fluid to be detected and the detection scenario; define the detection posture based on the information of the fluid to be detected and the detection scenario. At this time, the detection posture is the optimal detection posture of the fluid to be detected, realizing the overall consideration of the information of the fluid to be detected and the detection scenario, ensuring the multi-dimensional control of the information of the fluid to be detected and the detection scenario, and thus ensuring the accuracy of the detection posture.

[0049] Specifically, collect the basic information of the fluid to be detected, including chemical composition, physical state, concentration range, etc. This information can be obtained through pre-experiment pretreatment, literature review or laboratory databases. Define the detection scenario according to the analysis purpose and experimental conditions. The detection scenario should cover all factors that may affect the detection results, such as experimental environment, equipment configuration, detection technology, etc. Associate the information of the fluid to be detected with the detection scenario to establish an information model. This model should be able to reflect the interaction and influence between fluid information and scenario factors.

[0050] Use information technology means to achieve real-time interaction between the information of the fluid to be detected and the detection scenario data. Verify the accuracy and reliability of the information model through experiments. During the experiment, collect and analyze the real-time changes of fluid information and scenario factors, and correct and optimize the model. According to the experimental results, give feedback and make adjustments to the information of the fluid to be detected and the detection scenario. This includes adjusting experimental conditions, optimizing equipment configuration, improving detection technology, etc.

[0051] On the basis of comprehensively considering the information of the fluid to be detected and the detection scenario, define the optimal detection posture of the fluid to be detected. The optimal detection posture should be able to maximize the accuracy and reliability of the detection results while minimizing experimental errors and interferences. Use simulation technology or experimental verification methods to optimize the optimal detection posture. This includes adjusting the fluid flow rate, changing the detector position, optimizing chromatographic conditions, etc. During the experiment, perform fluid detection and data analysis according to the optimal detection posture. Ensure that the experimental conditions are consistent with the defined optimal detection posture to achieve accurate detection results.

[0052] By correlating the detected fluid information with the detection scenario and performing multiple interactions, multi-dimensional control of the detection process is achieved. This includes the integrity of the fluid information, the accuracy of the detection scenario, the stability of the experimental conditions, etc. On the basis of defining the optimal detection posture, through optimization and implementation, the accuracy of the detection results is ensured. This includes improving the sensitivity, selectivity, and accuracy of the detection, while reducing experimental errors and interferences.

[0053] Reference Figure 3 , in step S12, a detection mode is defined based on the flow state of the fluid to be detected, the corresponding detection posture, and the environmental level;

[0054] In the specific implementation process of the present invention, the specific steps may be:

[0055] S121: Freeze the detection posture of the fluid to be detected;

[0056] S122: Collect multiple flow parameters based on the on-line monitoring of the fluid to be detected;

[0057] S123: Define the flow state of the fluid to be detected according to the multiple interactions of multiple flow parameters;

[0058] S124: Define the corresponding detection environment space based on the position where the fluid to be detected is located;

[0059] S125: Define the corresponding environmental level based on the detection environment space;

[0060] S126: Correlate the flow state of the fluid to be detected, the corresponding detection posture, and the environmental level, and perform multiple interactions on the flow state of the fluid to be detected, the corresponding detection posture, and the environmental level;

[0061] S127: Define the detection mode according to the multiple interactions of the flow state of the fluid to be detected, the corresponding detection posture, and the environmental level.

[0062] In the embodiments of the present application, according to the characteristics and analysis requirements of the fluid to be detected, its optimal detection posture is determined. The detection posture may involve multiple aspects such as the flow direction, flow rate, pressure, temperature, etc. of the fluid. Before the experiment starts, ensure that the experimental device and instruments can detect the fluid according to the determined detection posture. This may include adjusting the layout of the fluid channel, setting the flow rate controller, installing temperature sensors and pressure gauges, etc. During the experiment, verify whether the detection posture meets the requirements by real-time monitoring and analyzing the fluid parameters. According to the monitoring results, make necessary adjustments to the detection posture to ensure that the fluid is in the best detection state.

[0063] Develop a control mechanism for the detection posture of the fluid to be detected. This should include regularly detecting the stability of the fluid posture, promptly responding to abnormal changes in the fluid posture, and taking necessary corrective measures. Use an automated monitoring system to continuously monitor the changes in the fluid posture. By setting thresholds and alarm mechanisms, promptly detect and handle abnormalities in the fluid posture. Record the historical data of the fluid posture for subsequent analysis and optimization. Use data analysis tools to explore the correlation between the fluid posture and the detection results, providing a basis for improving the detection process.

[0064] According to the analysis requirements and fluid characteristics, select key flow parameters for monitoring. These parameters may include flow rate, pressure, temperature, concentration, etc. Deploy corresponding sensors and monitoring devices in the experimental setup to collect flow parameters in real time. Ensure that the accuracy and stability of the monitoring devices meet the analysis requirements. Use a data acquisition system to collect monitoring data in real time. Preprocess and analyze the data to extract useful information for subsequent experimental optimization and result verification.

[0065] Through an online monitoring system, continuously track the flow state of the fluid to be detected. This helps to promptly detect abnormal changes in fluid parameters and take corresponding countermeasures. Regularly calibrate the monitoring devices to ensure their accuracy and stability. Verify and calibrate the collected flow parameters to improve the accuracy and reliability of the data. Based on the online monitoring results and data analysis results, optimize and improve the experimental setup and detection process. This includes adjusting the fluid posture, improving the monitoring devices, and optimizing the data analysis algorithm.

[0066] At this time, the flow state of the fluid to be detected is defined based on the multiple interactions of multiple flow parameters, realizing the multiple interactions of multiple flow parameters, ensuring the overall consideration of multiple flow parameters, improving the detection accuracy of the flow state of the fluid to be detected, and facilitating the further processing of the flow state of the fluid to be detected.

[0067] Specifically, according to the analysis requirements and fluid characteristics, select key flow parameters for monitoring. These parameters may include flow rate, pressure, temperature, concentration, viscosity, etc. Use high-precision sensors and monitoring devices to collect data of these flow parameters in real time. Preprocess and analyze the collected data to extract useful information. This may include steps such as data smoothing, filtering, and outlier detection.

[0068] Analyze the interactions and influences between individual flow parameters. Use tools such as statistical methods, machine learning algorithms, or expert systems to explore the correlations between these parameters. Based on the results of the multiple interaction analysis, define the flow state of the fluid to be detected. This may involve dividing the flow state into different categories or intervals, each representing specific flow characteristics. Extract key features from the definition of the flow state, which can comprehensively reflect the flow characteristics of the fluid.

[0069] Integrate multiple flow parameters into a unified framework for overall consideration and analysis. Construct a model that can describe the multiple interactions between multiple flow parameters. This model can be a physical model, a statistical model, or a machine learning model. Verify the accuracy and reliability of the model through experiments. Optimize and improve the model based on the verification results.

[0070] Utilize high-precision monitoring devices and sensors to monitor flow parameters in real time and accurately. Based on the real-time monitoring results, provide timely feedback to the flow state definition and detection process for necessary adjustments and optimizations. Correct the errors in the collected data to reduce the impact of measurement errors on the accuracy of flow state detection.

[0071] Conduct in-depth analysis and mining of the flow state data to extract more useful information. This may include trend analysis, association rule mining, clustering analysis, etc. Provide support for experimental decision-making based on the flow state data and analysis results. For example, adjust the experimental conditions or optimize the experimental process according to the change trend of the flow state. Set up warning and alarm mechanisms to issue alerts in a timely manner when the flow state is abnormal for corresponding countermeasures.

[0072] Therefore, define the corresponding detection environment space based on the location of the fluid to be detected; define the corresponding environmental level based on the detection environment space, introduce the detection environment space, and further control the detection environment space to further ensure the accuracy of the environmental level.

[0073] Specifically, clarify the specific location of the fluid to be detected in the experimental device or analysis system. This may involve key components such as fluid channels, reactors, detectors, etc. Divide the physical space around the fluid to be detected into a detection environment space according to its location. This space should cover all environmental factors that may affect the detection results, such as temperature, humidity, pressure, gas composition, etc.

[0074] Identify and determine the key factors or parameters that affect the detection environment space. These parameters may include temperature range, humidity level, pressure fluctuation, gas concentration, etc. Divide the detection environment space into different environmental levels according to the characteristics and importance of the environmental parameters. Each level represents specific environmental conditions and requirements to ensure the consistency and accuracy of the detection results.

[0075] Deploy high-precision environmental monitoring devices in the detection environment space, such as temperature sensors, hygrometers, pressure sensors, etc. Ensure that these devices can monitor the changes of environmental parameters in real time and accurately. Use the environmental monitoring devices to monitor the environmental parameters in the detection environment space in real time. This helps to detect abnormal changes in environmental parameters in a timely manner and take corresponding countermeasures. According to the real-time monitoring results, implement environmental control strategies, such as adjusting temperature, humidity, pressure, etc. This helps to keep the detection environment space within the specified environmental level to ensure the accuracy of detection results.

[0076] Calibrate and verify the environmental monitoring devices regularly to ensure their accuracy and reliability. This helps to reduce measurement errors and improve the monitoring accuracy of environmental parameters. Record and analyze the historical data of environmental parameters to understand the trends and patterns of environmental changes. This helps to predict possible future environmental changes and take corresponding countermeasures in advance. According to the real-time monitoring results and data analysis results, dynamically adjust the environmental level. This helps to adapt to the changes of different detection requirements and environmental conditions and ensure the accuracy and reliability of detection results. Set up an abnormal handling and alarm mechanism to send an alarm in time when the environmental parameters exceed the specified range. This helps to detect and handle environmental problems in a timely manner and prevent adverse effects on detection results.

[0077] Furthermore, associate the flow state of the fluid to be detected, the corresponding detection posture, and the environmental level, and perform multiple interactions on the flow state of the fluid to be detected, the corresponding detection posture, and the environmental level; define the detection mode according to the multiple interactions of the flow state of the fluid to be detected, the corresponding detection posture, and the environmental level, realizing the multiple interactions of the flow state of the fluid to be detected, the corresponding detection posture, and the environmental level, ensuring the multi-dimensional control of the flow state of the fluid to be detected, the corresponding detection posture, and the environmental level, and improving the accuracy of the detection mode.

[0078] Specifically, use high-precision sensors and monitoring devices to monitor the flow state of the fluid to be detected in real time, including key parameters such as flow rate, pressure, temperature, concentration, etc. Determine the optimal detection posture according to the characteristics of the fluid to be detected and the analysis requirements, including the flow direction of the fluid, flow rate adjustment, pressure control, etc. Evaluate the environmental parameters such as temperature, humidity, gas composition, etc. in the detection environment space to determine the corresponding environmental level.

[0079] Analyze the interaction and influence among the flow state, detection posture, and environmental level. This may involve statistical methods, machine learning algorithms, etc. to reveal the correlation and dependence among them. Based on the analysis of the interaction relationship, construct a model that can describe the multiple interactions among the flow state, detection posture, and environmental level. The model can be a physical model, statistical model, or machine learning model, which can predict and explain the interaction among these elements.

[0080] According to the multiple interaction model, design a detection mode. This mode should be able to comprehensively consider the effects of flow state, detection posture, and environmental level to ensure the accuracy and reliability of the detection results. Optimize the parameters in the detection mode to improve the precision and efficiency of the detection. This may involve adjusting control parameters such as flow rate, pressure, temperature, etc., and optimizing the environmental level, etc.

[0081] Utilize real-time monitoring technology to track the changes in flow state, detection posture, and environmental level in real time and promptly feedback them to the detection mode. This helps to promptly detect and correct deviations, ensuring the stability and accuracy of the detection process. Set up an exception handling and alarm mechanism to issue an alarm promptly when an abnormality occurs in the flow state, detection posture, or environmental level. This helps to quickly respond to and handle potential problems, preventing adverse effects on the detection results. Conduct in-depth analysis and mining of the data on flow state, detection posture, and environmental level to extract more useful information. This helps to understand their interactions and effects and further optimize the detection mode. Continuously improve and optimize the detection mode based on the real-time monitoring results, exception handling experience, and data analysis results. This includes adjusting parameter settings, optimizing the detection process, etc., to improve the precision and efficiency of the detection.

[0082] Reference Figure 4 , in step S13, define a primary chromatogram according to this detection mode and the fluid to be detected, and define an abnormal area based on the identification of the primary chromatogram;

[0083] In the specific implementation process of the present invention, the specific steps may be:

[0084] S131: Freeze this detection mode;

[0085] S132: Associate this detection mode with the fluid to be detected, and trigger corresponding dynamic detection based on this detection mode and the fluid to be detected;

[0086] S133: Define a primary chromatogram based on the dynamic detection of the fluid to be detected;

[0087] S134: Freeze the primary chromatogram and perform dynamic identification on the primary chromatogram;

[0088] S135: Define multiple abnormal features based on the identification of the primary chromatogram, and define corresponding abnormal areas according to the multiple abnormal features.

[0089] In the embodiments of the present application, the detection mode is fixed and further controlled. At the same time, the detection mode and the fluid to be detected are associated, and corresponding dynamic detection is triggered based on the detection mode and the fluid to be detected, which takes into account the overall situation of the detection mode and the fluid to be detected, realizes multi-dimensional control of the detection mode and the fluid to be detected, ensures the triggering of dynamic detection, and improves the timeliness of dynamic detection.

[0090] Specifically, fix the optimized and verified detection mode to ensure its stability and repeatability. Develop detailed operation manuals and standard operating procedures (SOPs) to guide the testers to correctly execute the detection mode. Establish a control mechanism for the detection mode, including regular calibration, equipment maintenance, personnel training, etc. Ensure that all equipment and instruments in the detection process meet the established standards and requirements. Deploy a real-time monitoring and feedback system to continuously track the execution status and performance indicators of the detection mode. According to the feedback results, adjust and optimize the detection mode in a timely manner to ensure that it is always in the best state.

[0091] Deeply analyze the physical and chemical properties of the fluid to be detected, and understand its key parameters such as composition, concentration, viscosity, etc. According to the fluid characteristics, adjust the relevant parameters in the detection mode to ensure the accuracy and reliability of the detection. Establish a dynamic association mechanism between the detection mode and the fluid to be detected. When the characteristics of the fluid to be detected change, the adjustment of the detection mode can be automatically triggered to meet the new detection requirements.

[0092] Based on the association mechanism between the detection mode and the fluid to be detected, when changes in fluid characteristics or environmental conditions are detected, dynamic detection is automatically triggered. Dynamic detection includes means such as real-time adjustment of detection parameters, increasing the detection frequency, and introducing new detection technologies. During the dynamic detection process, multiple dimensions such as the flow state, detection posture, environmental level, and the characteristics of the fluid to be detected are comprehensively considered. Through multi-dimensional control, ensure the comprehensiveness and accuracy of the detection results. Record all data during the dynamic detection process and conduct in-depth analysis. Through data analysis, discover potential problems and improvement points to provide a basis for subsequent optimization of the detection mode.

[0093] Establish a real-time response mechanism to ensure that measures can be taken promptly when abnormalities or changes are detected. This includes means such as automatic alarm, emergency shutdown, and adjustment of detection parameters. Throughout the detection process, always consider the detection mode and the fluid to be detected as a whole. Through collaborative optimization, ensure the best match between the detection mode and the fluid characteristics, and improve the detection efficiency and accuracy. Continuously improve and iterate the detection mode based on the results and feedback of dynamic detection. Through continuous optimization, ensure that the detection mode can always adapt to the changing detection requirements and fluid characteristics.

[0094] Therefore, a primary chromatogram is defined based on the dynamic detection of the fluid to be detected; the primary chromatogram is frozen and dynamically identified; multiple abnormal features are defined based on the identification of the primary chromatogram, corresponding abnormal regions are defined according to the multiple abnormal features, the primary chromatogram is introduced, and further control of the primary chromatogram is carried out, thereby realizing the identification of the primary chromatogram, ensuring the abnormal investigation of the primary chromatogram, and ensuring the accuracy of multiple abnormal features.

[0095] Specifically, a high-precision chromatograph and dynamic detection technology are used to detect the fluid to be detected in real time or regularly. The detection data, including key information such as the position, intensity, and shape of chromatographic peaks, are collected and analyzed. Based on the dynamic detection data, a primary chromatogram is constructed. This figure should clearly show the characteristics such as the position and intensity of each chromatographic peak. Ensure the accuracy and integrity of the primary chromatogram to provide a reliable basis for subsequent analysis.

[0096] Freeze the constructed primary chromatogram to ensure its stability and repeatability in subsequent analysis. Standardize the primary chromatogram to eliminate the influence of instrument errors and operation differences. Establish a dynamic identification mechanism for the primary chromatogram, which can monitor and analyze the changes in the chromatogram in real time. This includes identifying newly emerging chromatographic peaks, changes in chromatographic peak intensity, and variations in chromatographic peak shape.

[0097] Based on the dynamic identification results of the primary chromatogram, multiple abnormal features are defined. These features may include the offset of chromatographic peaks, abnormal changes in intensity, the appearance of new unknown peaks, etc. Each abnormal feature is described and classified in detail for subsequent abnormal investigation and feature identification. According to the definition of abnormal features, corresponding abnormal regions are delineated on the primary chromatogram. These regions should clearly indicate the position and scope of the abnormal features.

[0098] Introduce an abnormal investigation mechanism for the primary chromatogram to deeply analyze the identified abnormal features and abnormal regions. This includes steps such as comparing historical data, consulting relevant literature, and conducting reexaminations to confirm the authenticity and cause of the abnormality. According to the results of the abnormal investigation, optimize the primary chromatogram. This may include means such as adjusting detection conditions, improving sample processing methods, and introducing new chromatographic techniques. Ensure that the optimized chromatogram can better reflect the true situation of the fluid to be detected and improve the accuracy and reliability of the detection. Continuously monitor and update the primary chromatogram to adapt to the changing detection requirements and fluid characteristics. Through regular reexaminations and data analysis, timely discover and handle new abnormal features and abnormal regions.

[0099] Verify and confirm the identified multiple abnormal features to ensure their authenticity and accuracy. This may include using different detection methods, introducing third-party verification, etc. Establish an abnormal feature database, and organize and classify the identified abnormal features. This helps with quick identification and troubleshooting in subsequent detections, improving detection efficiency and accuracy. Continuously improve the recognition accuracy and detection efficiency of abnormal features through continuous learning and optimization. This includes introducing new recognition algorithms, improving detection processes, enhancing personnel skills, etc.

[0100] Reference Figure 5 , S14: Output the optimized part according to the autonomous optimization of the abnormal region, and define the final chromatogram based on the multiple interactions between the optimized part and the primary chromatogram;

[0101] In the specific implementation process of the present invention, the specific steps may be:

[0102] S141: Freeze the abnormal region;

[0103] S142: Autonomously optimize the abnormal region, and define multiple optimization parameters under the autonomous optimization of the abnormal region;

[0104] S143: Output the optimized part according to the multiple interactions between the multiple optimization parameters and the primary chromatogram;

[0105] S144: Associate the optimized part and the primary chromatogram, and perform multiple interactions on the optimized part and the primary chromatogram;

[0106] S145: Define the final chromatogram based on the multiple interactions between the optimized part and the primary chromatogram.

[0107] At this time, freeze the abnormal region, further control the abnormal region. At the same time, autonomously optimize the abnormal region, and define multiple optimization parameters under the autonomous optimization of the abnormal region. The autonomous optimization of the abnormal region is introduced, ensuring the technical effect of the autonomous optimization of the abnormal region, thereby introducing multiple optimization parameters and realizing the autonomous optimization of the abnormal region.

[0108] Specifically, based on the collected chromatographic data, draw the primary chromatogram. Carefully analyze the primary chromatogram, and identify the regions that are different from the normal chromatogram. These regions are the abnormal regions. Precise position the identified abnormal regions and mark their specific positions on the chromatogram. Record the main features of the abnormal regions, such as the offset of chromatographic peaks, abnormal changes in intensity, the appearance of new peaks, etc.

[0109] Based on the main features of the abnormal area, a preliminary analysis of possible causes of the abnormality is conducted. This may involve factors such as changes in fluid composition, unstable testing conditions, instrument errors, etc. Develop specific control measures based on the causes of the preliminary analysis. This may include adjusting testing conditions, optimizing sample processing methods, calibrating and maintaining instruments, etc. Further control the abnormal area in accordance with the established control measures. Monitor the control effect in real time and adjust the control measures as needed.

[0110] According to the main characteristics of the abnormal area and the effect of the control measures, set the goal of autonomous optimization. This may include reducing the offset of the chromatographic peak, stabilizing the intensity of the chromatographic peak, eliminating new peaks, etc. Based on the optimization goals, formulate specific autonomous optimization strategies. This may involve adjusting the selection of chromatographic columns, changing the composition and proportion of mobile phases, optimizing detection conditions, etc. In the autonomous optimization strategy, introduce multiple optimization parameters. These parameters may include the temperature of the chromatographic column, flow rate, gradient elution program, detection wavelength, etc. Autonomously optimize the abnormal area according to the formulated autonomous optimization strategy and the introduced optimization parameters. Monitor the optimization effect in real time and adjust the optimization parameters and strategies as needed.

[0111] Conduct technical effect evaluation on abnormal areas after self-optimization. This includes comparing chromatograms before and after optimization, analyzing the improvement of abnormal areas, and verifying the effectiveness of optimization parameters. Conduct verification experiments by introducing standard products or samples of known concentrations. Ensure that the chromatogram after self-optimization can accurately reflect the actual situation of the fluid to be tested and that the abnormal areas have been effectively improved. Based on the results of technical effect evaluation and optimization verification, continuously improve the self-optimization strategy and introduced optimization parameters. Ensure that the accuracy and reliability of chromatographic analysis are continuously improved.

[0112] Furthermore, the optimized part is output according to the multiple interactions of multiple optimization parameters and primary chromatograms, multiple optimization parameters and primary chromatograms are associated, and multiple interactions are performed on multiple optimization parameters and primary chromatograms, thereby realizing multiple interactions of multiple optimization parameters and primary chromatograms and ensuring the accuracy of the optimized part.

[0113] Specifically, a series of optimization parameters are determined based on the needs and goals of the chromatographic analysis. These parameters may include the choice of chromatographic column, composition and ratio of mobile phase, flow rate, temperature, gradient elution program, detection wavelength, etc. The primary chromatogram is carefully analyzed to identify the areas or features that need to be optimized. This may involve aspects such as resolution, symmetry, sensitivity, and detection limit of the chromatographic peaks. Based on the analysis results of the optimization parameters and the primary chromatogram, the relationship between them is established. The impact of each optimization parameter on a specific area or feature of the primary chromatogram is clarified.

[0114] Based on the correlation between the optimization parameters and the primary chromatogram, a series of experimental schemes are designed. These schemes should cover different combinations of optimization parameters to explore their effects on the chromatogram. According to the experimental schemes, the optimization parameters are adjusted one by one and chromatographic data are collected. The chromatograms after each experiment, as well as the associated optimization parameter settings, are recorded. Multiple interaction analyses are performed on the collected chromatograms and optimization parameters. This may involve methods such as statistical analysis, graphical display, and model construction to reveal the relationship between the optimization parameters and the chromatogram characteristics. Based on the results of the multiple interaction analysis, the optimized part is determined. This may involve adjusting the values of certain optimization parameters to improve specific regions or characteristics of the chromatogram.

[0115] Verification experiments are carried out on the determined optimized part. The chromatograms before and after optimization are compared to evaluate whether the optimization effect meets the expectations. According to the verification results, necessary adjustments and optimizations are made to the optimized part. This may involve fine-tuning the values of the optimization parameters or introducing new optimization strategies. In practical applications, the performance of the optimized part is continuously monitored. As needed, continuous improvements are made to the optimization parameters and strategies to ensure the accuracy and stability of chromatographic analysis.

[0116] Therefore, by correlating the optimized part and the primary chromatogram, and performing multiple interactions on the optimized part and the primary chromatogram; defining the final chromatogram based on the multiple interactions of the optimized part and the primary chromatogram, the multiple interactions of the optimized part and the primary chromatogram are achieved, and the accuracy of the final chromatogram is improved.

[0117] Specifically, on the primary chromatogram, the regions or characteristics that need to be optimized are identified, and these are the optimized parts. The optimized parts may involve aspects such as the resolution, sensitivity, symmetry, and baseline stability of chromatographic peaks. According to the specific requirements of the optimized parts, the correlation with the primary chromatogram is established. This may involve adjusting chromatographic conditions (such as flow rate, temperature, mobile phase ratio, etc.), optimizing the selection of chromatographic columns, and improving sample pretreatment steps.

[0118] Based on the correlation between the optimized part and the primary chromatogram, a series of experimental schemes are designed. These schemes should cover different optimization strategies and adjustment parameters to explore their effects on the chromatogram. According to the experimental schemes, the optimization parameters are adjusted one by one and the experiments are carried out. The chromatogram data after each experiment, as well as the associated optimization parameter settings, are recorded. Multiple interaction analyses are performed on the collected chromatogram data and optimization parameters. This may involve methods such as statistical analysis, graphical display, and model construction to reveal the complex relationship between the optimization parameters and the chromatogram characteristics. Based on the results of the multiple interaction analysis, iterative adjustments are made to the optimized part. This may involve fine-tuning the values of the optimization parameters, introducing new optimization strategies, or adjusting experimental conditions.

[0119] During the iterative optimization process, continuously evaluate the optimization effect. Compare the chromatograms before and after optimization to ensure that the optimized part meets the expected goals. When the optimization effect meets the requirements, determine the final chromatogram. This chromatogram should accurately reflect the true composition and characteristics of the fluid to be detected. Conduct verification experiments by introducing standard substances or samples with known concentrations to ensure the accuracy and reliability of the final chromatogram.

[0120] Through the multiple interactions between the optimized part and the primary chromatogram, the accuracy of the final chromatogram is improved. This interaction not only considers the influence of individual optimization parameters but also their interactions and overall effects. In practical applications, continuously monitor the performance of the final chromatogram. According to needs, continuously improve the optimization strategy and parameters to ensure the accuracy and stability of chromatographic analysis.

[0121] At the same time, the final chromatogram is defined based on the multiple interactions between the optimized part and the primary chromatogram, which is compatible with the optimization of abnormal regions. By performing multiple interactions on the optimized part and the primary chromatogram, the accuracy of the final chromatogram is ensured, and multi-level control of the chromatographic test of the fluid to be detected is carried out. The optimization of the primary chromatogram, abnormal regions, and the final chromatogram are completed in sequence.

[0122] Specifically, prepare the fluid sample to be detected and process it according to the standard sample treatment method. Use a chromatographic instrument to collect data and obtain the primary chromatogram. Carefully analyze the primary chromatogram to identify characteristics such as the distribution, intensity, and resolution of chromatographic peaks. Pay special attention to identifying abnormal regions, such as peak shifts, abnormal intensities, and the appearance of new peaks.

[0123] Clearly mark the abnormal regions on the primary chromatogram. Record the main characteristics of the abnormal regions, such as location, size, and shape. According to the characteristics of the abnormal regions, formulate targeted optimization strategies. This may involve adjusting chromatographic conditions (such as flow rate, temperature, mobile phase ratio), changing the chromatographic column, improving sample pretreatment, etc. Adjust the experimental conditions according to the optimization strategy and re-collect chromatographic data. Record the chromatograms after each optimization and the associated optimization parameter settings. Compare the chromatograms before and after optimization to evaluate the improvement of the abnormal regions. If the optimization effect is not ideal, continue to adjust the optimization strategy and repeat the experiment.

[0124] Conduct multiple interaction analyses between the optimized part (especially the optimization results of abnormal regions) and the primary chromatogram. This may involve methods such as statistical analysis, graphical display, and model construction to reveal the complex relationships between optimization parameters and chromatogram characteristics. According to the results of the multiple interaction analysis, determine the optimal combination of optimization parameters. These parameters should be able to effectively improve abnormal regions while ensuring the accuracy of the chromatogram.

[0125] Re - collect chromatographic data using a determined combination of optimization parameters. Ensure stable experimental conditions to obtain a reliable final chromatogram. Conduct validation experiments by introducing reference standards or samples with known concentrations. Ensure the accuracy and reliability of the final chromatogram to meet the analysis requirements.

[0126] During the entire chromatographic test process, implement multi - level control measures. Conduct strict quality control at every step, from sample preparation, data collection, optimization of abnormal regions to the definition of the final chromatogram. Continuously pay attention to the development trends of chromatographic analysis techniques. Continuously improve the optimization strategies and parameters as needed to adapt to different types of fluid samples and analysis requirements.

[0127] Reference Figure 6 , S15: In the final chromatogram, define multiple distribution regions based on the final chromatogram and the historical region data of the fluid to be detected. Define the peak region according to the multiple distribution regions and the peak range corresponding to the fluid to be detected;

[0128] In the specific implementation process of the present invention, the specific steps can be:

[0129] S151: Freeze the final chromatogram;

[0130] S152: Associate the data platform and the fluid to be detected, and trace the data of the fluid to be detected;

[0131] S153: Define the historical region data of the fluid to be detected based on the data tracing of the fluid to be detected;

[0132] S154: Associate the final chromatogram and the historical region data of the fluid to be detected, and define multiple distribution regions according to the final chromatogram and the historical region data of the fluid to be detected;

[0133] S155: Collect the peak range corresponding to the fluid to be detected;

[0134] S156: Perform multiple matches on the multiple distribution regions and the peak range corresponding to the fluid to be detected, and define the peak region based on the multiple matches of the multiple distribution regions and the peak range corresponding to the fluid to be detected.

[0135] In the embodiment of the present application, freezing the final chromatogram, controlling the final chromatogram, at the same time, associating the data platform and the fluid to be detected, and tracing the data of the fluid to be detected; defining the historical region data of the fluid to be detected based on the data tracing of the fluid to be detected, realizing the data tracing of the fluid to be detected, ensuring the accuracy of the historical region data of the fluid to be detected, and making full use of the historical region data of the fluid to be detected.

[0136] Specifically, based on the optimization strategy and the results of multiple interaction analyses, finalize the chromatogram. Ensure that the chromatogram is clear, accurate, and free of abnormal or interfering peaks. Conduct strict quality control on the final chromatogram, including verification of indicators such as peak area, peak height, resolution, and symmetry. Calibrate using internal or external standards to ensure the accuracy and stability of the instrument. Record the final chromatogram and related data in a dedicated data platform or database. Ensure the integrity, traceability, and security of the data.

[0137] Associate the chromatographic data of the fluid to be tested with the data platform. Ensure that the data can be uploaded, updated, and queried in real time. Integrate the chromatographic data of the fluid to be tested and other relevant information (such as sample source, processing procedure, analysis conditions, etc.) on the data platform. Use data analysis tools to preprocess, clean, and standardize the data.

[0138] Establish a data traceability mechanism for the fluid to be tested to ensure that the data of each step of the analysis process is traceable. This includes the entire process from sample collection, processing, analysis to result reporting. Based on the data traceability mechanism, define the historical regional data of the fluid to be tested. This data may include historical chromatograms, analysis results, calibration curves, etc. Through data traceability and quality control measures, ensure the accuracy of the historical regional data. Review and correct abnormal or inconsistent data.

[0139] Use the historical regional data to analyze and compare with the current chromatogram of the fluid to be tested. This helps to identify trends, abnormalities, and potential problems. Based on the data analysis results, provide decision support for subsequent sample processing, optimization of analysis conditions, and result interpretation. Continuously optimize the analysis process and methods to improve the accuracy and efficiency of the analysis. Organize the historical regional data and analysis results into a knowledge base or report for internal or external sharing within the team. This helps to enhance the professional level of the team and promote knowledge exchange and cooperation.

[0140] Therefore, associate the final chromatogram and the historical regional data of the fluid to be tested, and define multiple distribution regions based on the final chromatogram and the historical regional data of the fluid to be tested, which accommodates the overall consideration of the final chromatogram and the historical regional data of the fluid to be tested, realizes the multi-dimensional control of the final chromatogram and the historical regional data of the fluid to be tested, and ensures the accuracy of multiple distribution regions.

[0141] Specifically, integrate the final chromatogram data with the historical data of the fluid to be detected. This includes characteristic data such as the intensity, position, and resolution of chromatographic peaks, as well as historical analysis results, trends, and anomaly information in the historical data. Clean the integrated data to remove duplicate, invalid, or anomalous data points. Use quality control methods to verify the accuracy and reliability of the data. Correlate the final chromatogram data with the historical data based on key information such as time, sample source, and analysis conditions. Ensure the correspondence between the data is accurate and error-free.

[0142] Conduct a distribution analysis on the integrated and correlated data. Use statistical methods (such as histograms, box plots, etc.) to reveal the distribution characteristics of the data. Divide multiple distribution regions based on the distribution characteristics of the data. These regions can be divided based on characteristics such as the intensity and position of chromatographic peaks, or based on the trends and anomaly information in the historical data. Use statistical methods (such as cluster analysis, regression analysis, etc.) to determine the boundaries of each distribution region. Ensure the accuracy and reliability of the boundaries for subsequent analysis and comparison.

[0143] Conduct a multi-dimensional analysis on each distribution region, including chromatographic characteristics, historical data, analysis results, etc. This helps to reveal the correlations and differences between different distribution regions. Use quality control methods and reference standards to evaluate the accuracy of multiple distribution regions. Ensure the accuracy and reliability of each distribution region. Interpret the meaning and potential problems of different distribution regions based on the analysis results. Compile a detailed report recording the analysis process, results, and conclusions. Continuously optimize and improve the analysis process and methods based on the analysis results and report. Continuously introduce new technologies and tools to improve the accuracy and efficiency of the analysis.

[0144] Furthermore, collect the peak range corresponding to the fluid to be detected; perform multiple matches on the multiple distribution regions and the peak range corresponding to the fluid to be detected, and define a peak region based on the multiple matches of the multiple distribution regions and the peak range corresponding to the fluid to be detected, which is compatible with the multiple matches of the multiple distribution regions and the peak range corresponding to the fluid to be detected, ensuring multi-dimensional control of the multiple distribution regions and the peak range corresponding to the fluid to be detected, and ensuring the accuracy of the peak region.

[0145] Specifically, use a chromatograph to analyze the fluid to be detected to obtain a chromatogram. Carefully analyze the chromatogram to identify the main chromatographic peaks of the fluid to be detected. Determine the peak range of the fluid to be detected based on characteristics such as the intensity, position, and shape of the chromatographic peaks. This usually involves measuring the starting point, apex, and ending point of the peak and recording the corresponding retention time and intensity values.

[0146] Review and organize the data of multiple previously defined distribution regions. This data should include information such as characteristic peaks, peak ranges, retention times, etc. for each distribution region. Develop a multiple matching strategy, considering factors such as the overlap of peak ranges, the proximity of retention times, and the similarity of chromatographic peak shapes. Use statistical methods or machine learning algorithms to assist in the matching process and improve the accuracy and efficiency of matching. Match the peak range of the fluid to be detected with multiple distribution regions one by one. Record the results of each match, including the degree of match, similarity scores, etc.

[0147] Based on the results of multiple matching, define the peak region of the fluid to be detected. This may involve selecting the distribution region with the highest degree of match or the highest similarity score as a reference for the peak region. Conduct multi-dimensional control over the defined peak region, including verification of chromatographic characteristics, comparison with historical data, and consistency check of analysis results. Use quality control methods and reference standards to evaluate the accuracy of the peak region. Ensure that the definition of the peak region not only conforms to the characteristics of multiple distribution regions but also accurately reflects the chromatographic characteristics of the fluid to be detected. Review and correct any inconsistent or abnormal data to ensure the accuracy of the peak region.

[0148] According to the analysis results, interpret the meaning and potential problems of the peak region. Prepare a detailed report recording the analysis process, results, and conclusions. Emphasize the accuracy assurance measures and results of the peak region in the report.

[0149] Reference Figure 7 ,S16: Define multiple peak shape characteristics based on each peak region and the contour recognition system, and define chromatographic peaks based on multiple peak shape characteristics, the fluid to be detected, and the intelligent recognition system to perform intelligent recognition of chromatographic peaks;

[0150] In the specific implementation process of the present invention, the specific steps may be:

[0151] S161: Fix each peak region;

[0152] S162: Define the contour recognition system based on the final chromatogram and the multiple interactions of the fluid to be detected;

[0153] S163: Associate each peak region and the contour recognition system;

[0154] S164: Define multiple peak shape characteristics based on each peak region and the contour recognition system;

[0155] S165: Associate multiple peak shape characteristics, the fluid to be detected, and the intelligent recognition system, define the first chromatographic peak position parameter based on multiple peak shape characteristics and the fluid to be detected, and define the second chromatographic peak position parameter based on multiple peak shape characteristics and the intelligent recognition system;

[0156] S166: Define a chromatographic peak based on the first chromatographic peak position parameter, the second chromatographic peak position parameter, and the fluid to be detected, so as to perform intelligent identification of the chromatographic peak.

[0157] In the specific implementation process of the present invention, freeze each peak region; define a contour recognition system based on the final chromatogram and the multiple interactions of the fluid to be detected, realize the multiple interactions of the final chromatogram and the fluid to be detected, ensure the accuracy of the contour recognition system, and fully consider the multiple interactions of the final chromatogram and the fluid to be detected.

[0158] Specifically, carefully analyze the final chromatogram and identify all significant chromatographic peaks. Freeze each peak region according to the characteristics of the chromatographic peak, such as intensity, position, shape, etc. Use quality control methods and reference standards to verify the frozen peak regions. Ensure that each peak region accurately reflects the chromatographic characteristics of the fluid to be detected.

[0159] Based on the multiple interactions between the final chromatogram and the fluid to be detected, analyze the characteristics of the chromatographic peak, such as shape, width, symmetry, tail shape, etc. Consider the physical and chemical properties of the fluid to be detected, as well as the influence of chromatographic analysis conditions (such as column temperature, mobile phase composition, flow rate, etc.) on contour recognition. Extract key contour features from the multiple interaction analysis. These features should be able to accurately describe the contour structure of the chromatographic peak and be used for subsequent contour recognition. Use machine learning or deep learning algorithms to construct a contour recognition system. Use the extracted contour features as input to train the model to identify new chromatographic peak contours. Use quality control methods and reference standards to verify the contour recognition system. According to the verification results, optimize the system to improve the accuracy and robustness of the recognition.

[0160] During the process of defining the contour recognition system, fully consider the multiple interactions between the final chromatogram and the fluid to be detected. This includes the interaction between chromatographic peaks, the interaction between the components of the fluid to be detected, and the influence of chromatographic conditions on the peak shape, etc. Through a strict verification and optimization process, ensure the accuracy of the contour recognition system. Use actual samples for testing, evaluate the recognition effect of the system, and make necessary adjustments according to the test results.

[0161] According to the analysis results, explain the significance and potential applications of the contour recognition system. Write a detailed report recording the analysis process, results, and conclusions. Emphasize the accuracy and reliability of the contour recognition system, as well as the method of realizing multiple interactions in the report.

[0162] Furthermore, associate each peak region with the contour recognition system; define multiple peak shape features based on each peak region and the contour recognition system, which is compatible with the overall consideration of each peak region and the contour recognition system, realizes the multi-dimensional control of each peak region and the contour recognition system, and ensures the accuracy of multiple peak shape features.

[0163] Specifically, carefully analyze each peak region, including characteristics such as the position, intensity, and shape of the peak. Ensure that each peak region accurately reflects the corresponding chromatographic peak in the chromatogram. Based on the contour characteristics of the chromatographic peak (such as shape, width, symmetry, tail, etc.), construct a contour recognition system. This system should be able to accurately identify and describe the contour of the chromatographic peak. Associate each peak region with the contour recognition system. This includes matching the characteristics of the peak region with the output of the contour recognition system to ensure consistency in describing the chromatographic peak.

[0164] Extract key peak shape characteristics from the associated peak regions and contour recognition system. These characteristics should be able to comprehensively and accurately describe the contour and shape of the chromatographic peak. Define multiple peak shape characteristics based on the extracted characteristics. These characteristics may include peak symmetry, sharpness, width, tail shape, etc. Verify the defined peak shape characteristics using quality control methods and reference standards. Ensure that each characteristic accurately reflects the contour characteristics of the chromatographic peak.

[0165] Conduct multi-dimensional control over the defined multiple peak shape characteristics. This includes considering the overall consistency between the peak region and the contour recognition system, the correlation between the characteristics, and their accuracy in describing the chromatographic peak. Through a strict verification and optimization process, ensure the precision of the multiple peak shape characteristics. Test with actual samples to evaluate the accuracy of the characteristics in describing the chromatographic peak and make necessary adjustments based on the test results.

[0166] According to the analysis results, explain the significance and potential applications of each peak region, the contour recognition system, and the defined multiple peak shape characteristics. Compile a detailed report recording the analysis process, results, and conclusions. Emphasize the association between each peak region and the contour recognition system, the precision of the multiple peak shape characteristics, and the methods for achieving multi-dimensional control in the report.

[0167] Therefore, associate multiple peak shape characteristics, the fluid to be detected, and the intelligent recognition system. Define the first chromatographic peak position parameter based on the multiple peak shape characteristics and the fluid to be detected, and define the second chromatographic peak position parameter based on the multiple peak shape characteristics and the intelligent recognition system; define the chromatographic peak according to the first chromatographic peak position parameter, the second chromatographic peak position parameter, and the fluid to be detected for intelligent recognition of the chromatographic peak. Introduce multiple peak shape characteristics, the fluid to be detected, and the intelligent recognition system, and conduct multiple interactions among the multiple peak shape characteristics, the fluid to be detected, and the intelligent recognition system to ensure the precision of the chromatographic peak.

[0168] Specifically, extract multiple key peak shape features from the chromatogram, such as peak symmetry, sharpness, width, height, tail shape, etc. Ensure that these features can comprehensively and accurately describe the contour and shape of the chromatographic peak. Analyze the physical and chemical properties of the fluid to be detected and its behavior under chromatographic conditions. Understand key information such as the retention time and elution order of each component in the fluid to be detected. Use machine learning or deep learning algorithms to construct an intelligent recognition system. This system should be able to intelligently identify chromatographic peaks based on multiple peak shape features and information about the fluid to be detected. Associate multiple peak shape features, the fluid to be detected, and the intelligent recognition system. This includes matching the peak shape features with the properties of the fluid to be detected and corresponding the output of the intelligent recognition system with the actual position of the chromatographic peak.

[0169] Based on multiple peak shape features and information about the fluid to be detected, define the position parameters of the first chromatographic peak. These parameters may include the peak retention time, peak top position, peak width, etc. According to multiple peak shape features and the output of the intelligent recognition system, define the position parameters of the second chromatographic peak. These parameters may include the peak position predicted by the intelligent recognition system, the confidence level of the peak, etc. Use quality control methods and reference standards to verify the defined position parameters. According to the verification results, optimize the parameters to improve the accuracy and robustness of chromatographic peak position recognition.

[0170] According to the position parameters of the first chromatographic peak, the position parameters of the second chromatographic peak, and information about the fluid to be detected, define the chromatographic peak. The chromatographic peak should include key information such as the peak position, intensity, shape, etc. Use the intelligent recognition system to intelligently identify the defined chromatographic peak. The recognition results should include key information such as the category, concentration, purity, etc. of the chromatographic peak. Use actual samples for testing to verify the accuracy and reliability of the intelligent recognition. According to the test results, make necessary adjustments and optimizations to the intelligent recognition system.

[0171] During the process of defining chromatographic peak position parameters and performing intelligent recognition, fully consider the multiple interactions of multiple peak shape features, the fluid to be detected, and the intelligent recognition system. This includes the interaction between peak shape features, the influence of the fluid to be detected on the peak shape, and the contribution of the intelligent recognition system to peak position recognition, etc. Through a strict verification and optimization process, ensure the accuracy of the chromatographic peak. Use multiple methods and means to verify the chromatographic peak, including quality control methods, reference standard tests, actual sample tests, etc. According to the verification results, make necessary adjustments and optimizations to the analysis process to improve the accuracy and recognition efficiency of the chromatographic peak.

[0172] At the same time, by accommodating the overall consideration of multiple peak shape features, the fluid to be detected, and the intelligent recognition system, multi-dimensional control of multiple peak shape features, the fluid to be detected, and the intelligent recognition system is achieved, ensuring the intelligent recognition effect of chromatographic peaks and improving the accuracy of chromatographic peaks.

[0173] Specifically, multiple key peak shape features are extracted from the chromatogram, including but not limited to peak symmetry, sharpness, width, height, tail shape, etc. The physical and chemical properties of the fluid to be detected are deeply analyzed, as well as its behavioral characteristics under chromatographic conditions, such as retention time, elution order, etc. A smart recognition system is constructed and optimized, which should be able to integrate multiple peak shape features and information of the fluid to be detected to achieve efficient and accurate chromatographic peak recognition. During the analysis process, ensure multi-dimensional control over multiple peak shape features, the fluid to be detected, and the smart recognition system. This includes precise measurement of peak shape features, in-depth understanding of the properties of the fluid to be detected, and continuous monitoring and optimization of the performance of the smart recognition system.

[0174] Using machine learning algorithms, select the most influential features for chromatographic peak recognition from multiple peak shape features for fusion. Through feature fusion, improve the comprehensive understanding ability of the smart recognition system for chromatographic peak profiles and properties. Use quality control methods and standard sample data to train the smart recognition system to ensure that the model can accurately identify chromatographic peaks. Evaluate the model performance through strategies such as cross-validation and holdout method to ensure its stability and generalization ability on different samples and datasets. According to the verification results, make necessary adjustments and optimizations to the smart recognition system to improve its recognition accuracy and efficiency. With the accumulation of new data and knowledge, regularly update the smart recognition system to maintain its ability to keep up with the times.

[0175] Based on the output of the smart recognition system, combined with multiple peak shape features and information of the fluid to be detected, accurately locate and identify chromatographic peaks. Ensure that the recognition results can accurately reflect key information such as the position, intensity, and shape of chromatographic peaks. Conduct error analysis on the recognition results to identify potential error sources, such as instrument noise, sample contamination, etc. According to the error analysis results, make necessary corrections to the recognition results to improve the accuracy of chromatographic peaks. Establish a continuous monitoring mechanism to monitor and record the chromatographic peak recognition process in real time. According to the monitoring results, promptly adjust the analysis process and optimize the smart recognition system to improve the recognition effect and accuracy of chromatographic peaks.

[0176] In the embodiment of the present invention, through the method in the embodiment of the present invention, the final chromatogram is defined based on the multiple interactions between the optimized part and the primary chromatogram, which is compatible with the optimization of the abnormal area and conducts multiple interactions on the optimized part and the primary chromatogram, ensuring the accuracy of the final chromatogram and conducting multi-level control over the chromatographic test of the fluid to be detected, and successively completing the optimization of the primary chromatogram, the abnormal area, and the final chromatogram.

[0177] Furthermore, in the final chromatogram, chromatographic peaks are defined based on multiple peak shape features, the fluid to be detected, and the intelligent recognition system to perform intelligent recognition of the chromatographic peaks, achieving multi-dimensional control of multiple peak shape features, the fluid to be detected, and the intelligent recognition system, ensuring the intelligent recognition effect of the chromatographic peaks and improving the accuracy of the chromatographic peaks.

[0178] Please refer to Figure 8 , Figure 8 which is a schematic structural composition diagram of the intelligent recognition device for chromatographic peaks in an embodiment of the present invention.

[0179] As Figure 8 shown, an intelligent recognition device for chromatographic peaks, the intelligent recognition device for chromatographic peaks includes:

[0180] A detection attitude module 21, configured to define a detection attitude according to the information of the fluid to be detected and the detection scenario;

[0181] A detection mode module 22, configured to define a detection mode based on the flow state of the fluid to be detected, the corresponding detection attitude, and the environmental level;

[0182] An abnormal area module 23, configured to define a primary chromatogram according to the detection mode and the fluid to be detected, and define an abnormal area based on the recognition of the primary chromatogram;

[0183] A chromatogram module 24, configured to output an optimized part according to the autonomous optimization of the abnormal area, and define the final chromatogram according to the multiple interactions between the optimized part and the primary chromatogram;

[0184] A peak area module 25, configured to define multiple distribution areas in the final chromatogram based on the final chromatogram and the previous area data of the fluid to be detected, and define a peak area according to the multiple distribution areas and the peak range corresponding to the fluid to be detected;

[0185] An identification module 26, configured to define multiple peak shape features according to each peak area and the contour recognition system, and define a chromatographic peak according to the multiple peak shape features, the fluid to be detected, and the intelligent recognition system to perform intelligent recognition of the chromatographic peak.

[0186] The above has introduced in detail the intelligent recognition method and device for chromatographic peaks provided by the embodiments of the present invention. Specific examples are used in this article to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. An intelligent identification method for chromatographic peaks, characterized in that: Applied to intelligent identification scenarios of chromatographic peaks; The intelligent identification method of the chromatographic peak comprises: Defining the detection posture according to the information of the fluid to be detected and the detection scene; Defining a detection mode based on the flow state of the fluid to be detected, the corresponding detection posture and the environmental level; defining a primary chromatogram according to the detection mode and the fluid to be detected, and defining an abnormal area based on the identification of the primary chromatogram; Outputting an optimized portion according to autonomous optimization of the abnormal region, and defining a final chromatogram according to multiple interactions of the optimized portion and the primary chromatogram; In the final chromatogram, a plurality of distribution regions are defined based on the final chromatogram and previous region data of the fluid to be detected, and a peak region is defined according to the peak ranges corresponding to the plurality of distribution regions and the fluid to be detected; A plurality of peak shape features are defined according to each peak region and a contour recognition system, and a chromatographic peak is defined according to the plurality of peak shape features, a fluid to be detected and an intelligent recognition system, so as to perform intelligent recognition on the chromatographic peak.

2. The intelligent identification method of chromatographic peaks according to claim 1, characterized in that: Defining the detection posture according to the information of the fluid to be detected and the detection scene includes: Collect the location of the fluid to be tested; Determine information about the detected fluid based on the detection of the position of the fluid to be detected; Correlate the information of the detected fluid and the detection scene; Multiple interactions are performed on the information of the detected fluid and the detection scene; The detection posture is defined based on the information of the fluid to be detected and the detection scene. At this time, the detection posture is the optimal detection posture for the fluid to be detected.

3. The intelligent identification method of chromatographic peaks according to claim 2, characterized in that: The detection mode is defined based on the flow state of the fluid to be detected, the corresponding detection posture and the environmental level, including: Freeze the detection posture of the fluid to be detected; Collecting multiple flow parameters based on online monitoring of the fluid to be tested; Defining the flow state of the fluid to be detected according to multiple interactions of multiple flow parameters; Defining a corresponding detection environment space based on the location of the fluid to be detected; Define the corresponding environmental level based on the detection environment space; Associating the flow state of the fluid to be detected, the corresponding detection posture and the environmental level, and performing multiple interactions on the flow state of the fluid to be detected, the corresponding detection posture and the environmental level; The detection mode is defined according to the flow state of the fluid to be detected, the corresponding detection posture and the multiple interactions of the environmental level.

4. The intelligent identification method of chromatographic peaks according to claim 3, characterized in that: Defining a primary chromatogram according to the detection mode and the fluid to be detected, and defining an abnormal area based on the identification of the primary chromatogram, comprises: Freeze the detection mode; Associating the detection mode with the fluid to be detected, and triggering corresponding dynamic detection based on the detection mode and the fluid to be detected; defining a primary chromatogram based on dynamic detection of the fluid to be detected; Freeze the primary chromatogram and perform dynamic recognition on the primary chromatogram; A plurality of abnormal features are defined based on the identification of the primary chromatogram, and corresponding abnormal regions are defined according to the plurality of abnormal features.

5. The intelligent identification method of chromatographic peaks according to claim 4, characterized in that: The step of outputting the optimized part according to the autonomous optimization of the abnormal region and defining the final chromatogram according to multiple interactions of the optimized part and the primary chromatogram includes: Freeze the abnormal area; Autonomous optimization of abnormal areas is performed, and multiple optimization parameters are defined under autonomous optimization of abnormal areas; Outputting optimized parts based on multiple optimization parameters and multiple interactions of primary chromatograms; Associating the optimized part and the primary chromatogram, and performing multiple interactions on the optimized part and the primary chromatogram; The final chromatogram is defined based on multiple interactions of the optimized parts and primary chromatograms.

6. The intelligent identification method of chromatographic peaks according to claim 5, characterized in that: In the final chromatogram, a plurality of distribution areas are defined based on the final chromatogram and previous area data of the fluid to be detected, and a peak area is defined according to the peak ranges corresponding to the plurality of distribution areas and the fluid to be detected, including: Freeze the final chromatogram; Associate the data platform with the fluid to be tested, and trace the data of the fluid to be tested; Defining the previous regional data of the fluid to be detected based on the data traceability of the fluid to be detected; The final chromatogram and the previous regional data of the fluid to be detected are associated, and a plurality of distribution regions are defined according to the final chromatogram and the previous regional data of the fluid to be detected.

7. The intelligent identification method of chromatographic peaks according to claim 6, characterized in that: In the final chromatogram, a plurality of distribution areas are defined based on the final chromatogram and the previous area data of the fluid to be detected, and a peak area is defined according to the peak range corresponding to the plurality of distribution areas and the fluid to be detected, and further includes: Collect the peak value range corresponding to the fluid to be detected; Multiple matching is performed on the peak ranges corresponding to the multiple distribution areas and the fluid to be detected, and the peak area is defined based on the multiple matching of the peak ranges corresponding to the multiple distribution areas and the fluid to be detected.

8. The intelligent identification method of chromatographic peaks according to claim 7, characterized in that: The method of defining a plurality of peak shape features according to each peak region and the contour recognition system, and defining a chromatographic peak according to the plurality of peak shape features, the fluid to be detected and the intelligent recognition system, so as to perform intelligent recognition on the chromatographic peak, includes: Freeze each peak area; Defining a profile recognition system based on the final chromatogram and multiple interactions of the fluid to be detected; Correlate each peak region and contour recognition system; Based on the individual peak areas, a profile recognition system defines multiple peak shape features.

9. The intelligent identification method of chromatographic peaks according to claim 8, characterized in that: The method further comprises: defining a plurality of peak shape features according to each peak region and the contour recognition system, and defining a chromatographic peak according to the plurality of peak shape features, the fluid to be detected and the intelligent recognition system, so as to perform intelligent recognition on the chromatographic peak; Associating multiple peak shape features, fluids to be detected, and intelligent recognition systems, defining first chromatographic peak position parameters based on the multiple peak shape features and the fluids to be detected, and defining second chromatographic peak position parameters based on the multiple peak shape features and the intelligent recognition system; The chromatographic peak is defined according to the first chromatographic peak position parameter, the second chromatographic peak position parameter and the fluid to be detected, so as to perform intelligent identification on the chromatographic peak.

10. An intelligent device for identifying chromatographic peaks, characterized in that: The intelligent recognition device for chromatographic peaks is applied to the intelligent recognition method for chromatographic peaks as claimed in any one of claims 1 to 9, and the intelligent recognition device for chromatographic peaks comprises: A detection posture module, used to define the detection posture according to the information of the fluid to be detected and the detection scene; A detection mode module, used to define a detection mode based on the flow state of the fluid to be detected, the corresponding detection posture and the environmental level; an abnormal region module, for defining a primary chromatogram according to the detection mode and the fluid to be detected, and defining an abnormal region based on the identification of the primary chromatogram; A chromatogram module, for outputting an optimized portion according to autonomous optimization of an abnormal region, and defining a final chromatogram according to multiple interactions of the optimized portion and the primary chromatogram; A peak region module, used to define multiple distribution regions in the final chromatogram based on the final chromatogram and previous region data of the fluid to be detected, and to define a peak region according to the peak range corresponding to the multiple distribution regions and the fluid to be detected; The recognition module is used to define multiple peak shape features according to each peak area and the contour recognition system, and to define chromatographic peaks according to the multiple peak shape features, the fluid to be detected and the intelligent recognition system, so as to perform intelligent recognition on the chromatographic peaks.

Images