Essential oil production digital visual management and control system and method based on data analysis

Abstract

The invention relates to the technical field of visual management and control, in particular to an essential oil production digital visual management and control system and method based on data analysis. The method comprises the following steps: obtaining essential oil raw material data and carrying out component content identification, removing abnormal values to generate standard raw material components, obtaining historical process data, matching the standard raw material components according to the data, obtaining a reference process, carrying out production simulation to generate essential oil parameters, and carrying out multi-dimensional quality evaluation on simulation process parameters. The method comprises the following steps: optimizing a matching reference process, forming a quality compensation essential oil process, carrying out scene simulation on the process, evaluating process risks, implementing safety compensation treatment, obtaining a safety compensation essential oil process, carrying out production control adjustment on standard raw material components based on the process, carrying out visual rendering, and constructing a digital visual view of essential oil production. According to the invention, a more efficient and safer digital visual management and control method for essential oil production is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of visual management and control, and particularly to a digital visual management and control system and method for essential oil production based on data analysis. Background Art

[0002] Traditional essential oil production methods face problems of low efficiency and unstable quality. Many production enterprises rely on experience and manual operations, lacking scientific data support and systematic management means, resulting in difficulty in achieving precise control during the production process, affecting product consistency and market competitiveness. In addition, the components of essential oils are complex and variable, and the quality differences of different raw materials pose challenges to the standardization of production processes. Enterprises often lack effective data analysis and decision-making basis when selecting raw materials and formulating processes. At the same time, the accumulation of historical process data provides potential references for optimizing production, but how to effectively match these data with the current raw material components remains an urgent problem to be solved. The traditional production process is difficult to flexibly adapt to the changes of different batches of raw materials, leading to low production efficiency and waste of resources. In addition, the lack of real-time monitoring and prediction of production risks makes it difficult for enterprises to take effective countermeasures in case of emergencies, thus increasing production uncertainty and safety hazards. Summary of the Invention

[0003] Based on this, it is necessary to provide a digital visual management and control system and method for essential oil production based on data analysis to solve at least one of the above technical problems.

[0004] To achieve the above object, a digital visual management and control method for essential oil production based on data analysis includes the following steps:

[0005] Step S1: Obtain essential oil raw material data; identify the component content of the essential oil raw material data to obtain the raw material component content; perform interquartile range outlier rejection on the raw material component content to generate standard raw material components;

[0006] Step S2: Obtain historical process data; perform adapted process matching on the standard raw material components according to the historical process data to obtain a matching reference process; perform production simulation on the standard raw material components based on the matching reference process to generate essential oil production parameters for the simulation process;

[0007] Step S3: Perform multi-dimensional quality evaluation on the essential oil production parameters for the simulation process to obtain quality evaluation data; perform actual combination optimization on the matching reference process according to the quality evaluation data to generate a quality-compensated essential oil process;

[0008] Step S4: Perform scenario simulation deduction on the quality-compensated essential oil process to generate process prediction risks; perform safety compensation processing on the quality-compensated essential oil process according to the process prediction risks to obtain a safety-compensated essential oil process;

[0009] Step S5: Based on the quality compensation essential oil process and the safety compensation essential oil process, adjust the production control of the standard raw material components, and perform visual rendering to construct a digital visual view of essential oil production.

[0010] Through obtaining essential oil raw material data and identifying the component contents, the present invention ensures the accuracy of the raw material components. The standard raw material components generated by removing outliers using the interquartile range improve the reliability of the data. Obtaining historical process data and performing adaptive process matching on the standard raw material components ensures the best combination of the process and the raw materials. Based on the matched reference process, production simulation is carried out, and the essential oil parameters generated by the simulated process provide a scientific basis for actual production. The simulated process parameters are evaluated through multi-dimensional quality assessment to ensure that the quality of the essential oil meets the standards. The quality assessment data is used to optimize the actual combination of the matched reference process, and the generated quality compensation essential oil process improves the stability of production. Scenario simulation and deduction are used to predict the risks of the quality compensation essential oil process to ensure the safety during the production process. The safety compensation treatment makes the process have higher reliability in actual applications. Based on the quality compensation essential oil process and the safety compensation essential oil process, the production control of the standard raw material components is adjusted, and visual rendering is performed. The constructed digital visual view of essential oil production improves the intelligent level of production management, overall improves the efficiency and safety of essential oil production, and promotes the scientific and precise production decision-making.

[0011] Preferably, step S1 includes the following steps:

[0012] Step S11: Obtain essential oil raw material data; perform near-infrared spectroscopy analysis on the essential oil raw material data to obtain raw material spectral characteristic data;

[0013] Step S12: Perform wavelet transform decomposition on the raw material spectral characteristic data to obtain spectral component band data; perform raw material identification on the spectral component band data to generate raw material component contents;

[0014] Step S13: Estimate the distribution probability of the raw material component contents to generate the raw material component distribution probability;

[0015] Step S14: Calculate the interquartile range of the raw material component distribution probability to obtain the upper and lower limit thresholds of the distribution;

[0016] Step S15: Identify outliers in the raw material component distribution probability based on the upper and lower limit thresholds of the distribution to obtain the abnormal raw material component distribution;

[0017] Step S16: Remove outliers from the raw material cost contents based on the abnormal raw material component distribution to generate standard raw material components.

[0018] The digital visualization control system for essential oil production based on data analysis in the present invention obtains essential oil raw material data and performs near-infrared spectroscopy analysis, providing accurate identification of raw material characteristics. By using wavelet transform to decompose spectral feature data, the accuracy of component analysis is improved. The distribution probability estimation provides a quantitative basis for the characteristics of raw material components, and the upper and lower limit thresholds generated by the interquartile range calculation provide a scientific basis for outlier identification. The identification of abnormal raw material component distributions ensures the raw material quality during the production process, and the outlier removal further optimizes the raw material cost content. The generated standard raw material components provide reliable data support for subsequent production. The entire system realizes a closed-loop from raw material acquisition to standardized management, effectively improving production efficiency and product consistency, and promoting the intelligent and visual management of essential oil production.

[0019] Preferably, step S2 includes the following steps:

[0020] Step S21: Obtain historical process data; perform time series decomposition on the historical process data to obtain process trend characteristics;

[0021] Step S22: Conduct correlation analysis on the process trend characteristics and standard raw material components to obtain process similarity data; perform hierarchical clustering on the process similarity data to generate process classification data;

[0022] Step S23: Perform adaptive process matching on the standard raw material components according to the process classification data to obtain a matching reference process;

[0023] Step S24: Conduct production site simulation on the matching reference process to generate an essential oil production simulation site;

[0024] Step S25: Perform production response simulation on the standard raw material components based on the essential oil production simulation site to generate simulation process essential oil production parameters.

[0025] The digital visualization control system for essential oil production based on data analysis in the present invention obtains historical process data and performs time series decomposition, revealing the trend characteristics of the process and providing data support for subsequent process optimization. The process similarity data formed by the correlation analysis of the process trend characteristics and standard raw material components promotes the effective comparison and selection between different processes. The process classification data generated by hierarchical clustering makes process management more systematic and structured. The realization of adaptive process matching makes the combination between standard raw material components and the best process more accurate. The introduction of production site simulation provides a reproduction of the real scenario for actual production. The generated essential oil production simulation site lays a foundation for the optimization of process parameters. The production response simulation based on the simulation site ensures the scientificity and feasibility of essential oil production parameters. The entire system improves the intelligence and flexibility of the essential oil production process and enhances the stability of production efficiency and product quality.

[0026] Preferably, step S3 includes the following steps:

[0027] Step S31: Perform principal component decomposition on the essential oil parameters of the simulation process to obtain dimension-reduced parameters; perform grey relational degree mapping on the dimension-reduced parameters to generate quality-related parameters;

[0028] Step S32: Perform hierarchical analysis on the quality-related parameters to obtain quality weight data; perform multi-dimensional quality evaluation on the essential oil parameters of the simulation process according to the quality weight data to obtain quality evaluation data;

[0029] Step S33: Screen the preferred process for the essential oil parameters of the simulation process according to the quality evaluation data to obtain preferred process parameters;

[0030] Step S34: Based on the preferred process parameters, perform preferred replacement optimization on the matching reference process to generate a quality compensation essential oil process.

[0031] Through the digital visualization control system for essential oil production based on data analysis, the present invention performs principal component decomposition on the essential oil parameters of the simulation process, realizes the dimension reduction of data, reduces complexity and highlights key information. The application of grey relational degree mapping generates quality-related parameters, enhancing the correlation between parameters and product quality. Hierarchical analysis improves the scientificity of quality weight data, forming a systematic evaluation of each quality index. The multi-dimensional quality evaluation using quality weight data provides a quantitative quality standard for essential oil production. The preferred process screening ensures the optimal combination of essential oil parameters, and the generated preferred process parameters provide a data basis for the replacement and optimization of the matching reference process. The formation of the quality compensation essential oil process improves the quality control ability during production. The entire system enhances the intelligence level of essential oil production and the consistency and reliability of product quality through scientific data analysis and optimization.

[0032] Preferably, step S34 includes the following steps:

[0033] Decompose the preferred process parameters into a process chain to obtain a process unit sequence; perform parameter sensitivity analysis on the process unit sequence to obtain sensitivity indicators;

[0034] Identify key process units based on the sensitivity indicators to obtain an optimization target sequence; perform process adaptability evaluation on the optimization target sequence based on a preset adaptability reference value to obtain an adaptability indicator;

[0035] Perform reference process matching based on the adaptability indicator to obtain a process matching scheme; perform replacement optimization simulation on the process matching scheme to obtain a simulated optimized process;

[0036] Perform anomaly detection on the simulated optimization process. When the anomaly detection result indicates no anomaly, determine that the process matching scheme is a feasible scheme, and perform corresponding target replacement optimization on the optimization target sequence and the matching reference process based on the feasible scheme to generate a quality compensation essential oil process.

[0037] Through the digital visualization control system for essential oil production based on data analysis, the present invention decomposes the process chain of the preferred process parameters, realizes a systematic understanding of each process unit. The application of parameter sensitivity analysis identifies the key indicators affecting production quality, providing a clear direction for subsequent optimization. The identification of key process units ensures the rational allocation of resources. The formation of the optimization target sequence provides a specific target for process improvement. The setting of the fitness reference value makes the process fitness evaluation more scientific. The generation of the fitness index strengthens the quantitative analysis of process matching. The formation of the reference process matching scheme improves the flexibility of the production process. The implementation of the replacement optimization simulation provides a safety guarantee for process adjustment. The introduction of anomaly detection ensures the effectiveness and reliability of the process scheme. When it is determined that the process matching scheme is a feasible scheme, further target replacement optimization improves the accuracy of production. Finally, the generated quality compensation essential oil process realizes the intelligentization of the production process and the stable control of quality.

[0038] Preferably, step S4 includes the following steps:

[0039] Step S41: Decompose the quality compensation essential oil process hierarchically to obtain process link tree data;

[0040] Step S42: Perform a fault propagation simulation on the process link tree data to generate simulated fault propagation data; based on the simulated fault propagation data, conduct a fault scenario deduction on the quality compensation essential oil process to generate process prediction risks;

[0041] Step S43: Design risk avoidance based on the process prediction risks to obtain a risk avoidance strategy;

[0042] Step S44: Map the parameters of the quality compensation essential oil process according to the risk avoidance strategy to generate avoidance adjustment parameters; based on the avoidance adjustment parameters, perform safety compensation processing on the quality compensation essential oil process to obtain a safety compensation essential oil process.

[0043] Through the digital visualization control system for essential oil production based on data analysis, the present invention hierarchically decomposes the quality compensation essential oil process, constructs clear tree-shaped data of process links. The application of fault propagation simulation reveals potential fault paths, and the generated simulated fault propagation data provides an important basis for process prediction risks. The implementation of fault scenario deduction improves the risk identification ability. The introduction of risk avoidance design provides a systematic response strategy for process safety. The formulation of risk avoidance strategies enhances the control of uncertain factors. The application of parameter mapping ensures the effective combination of risk management and process optimization. The generated avoidance adjustment parameters provide a quantitative guarantee for the safety of the quality compensation essential oil process. The implementation of safety compensation processing ultimately improves the reliability and stability of the production process. Through comprehensive risk management and optimization design, the entire system realizes the intelligentization and safety of the essential oil production process.

[0044] Preferably, step S42 includes the following steps:

[0045] Dynamically hierarchically analyze the tree-shaped data of process links to generate a time-series correlation tree diagram;

[0046] Based on the time-series correlation tree diagram, perform node conflict detection to obtain a link conflict matrix;

[0047] Perform fault path simulation on the link conflict matrix to generate a multi-path fault propagation model;

[0048] Based on the multi-path fault propagation model, perform fault propagation simulation to generate simulated fault propagation data;

[0049] Based on the simulated fault propagation data, perform process time-series evolution on the quality compensation essential oil process to obtain process prediction risks.

[0050] Through the digital visualization control system for essential oil production based on data analysis, the present invention dynamically hierarchically analyzes the tree-shaped data of process links to generate a time-series correlation tree diagram, providing a visual basis for the dynamic monitoring of the process flow. The implementation of node conflict detection identifies potential conflicts between links, and the generated link conflict matrix provides structured data support for fault analysis. The application of fault path simulation forms a multi-path fault propagation model, enhancing the understanding of complex fault propagation mechanisms. The fault propagation simulation based on the multi-path fault propagation model generates simulated fault propagation data, providing an empirical basis for the risk assessment of the quality compensation essential oil process. The implementation of process time-series evolution improves the prediction ability of the impact of process changes on risks, ultimately realizing the comprehensive monitoring and management of quality assurance. The entire system makes the risk identification and response in the essential oil production process more scientific, systematic and efficient.

[0051] Preferably, step S44 includes the following steps:

[0052] Perform parameter mapping on the quality compensation essential oil process according to the risk avoidance strategy to obtain a parameter mapping correlation matrix;

[0053] Conduct quality constraint analysis on the quality compensation essential oil process to obtain quality maintenance constraints;

[0054] Based on the quality maintenance constraints, perform constraint condition matching on the parameter mapping correlation matrix to generate avoidance adjustment parameters;

[0055] Deduce the avoidance path for the avoidance adjustment parameters to obtain a simulated safety compensation path; perform safety adjustment according to the simulated safety compensation path to generate a candidate safety compensation essential oil process;

[0056] Perform quality numerical matching on the candidate safety compensation essential oil process and the quality compensation essential oil process. When the quality numerical values are the same, determine that the candidate safety compensation essential oil process is the safety compensation essential oil process.

[0057] Through the digital visualization control system for essential oil production based on data analysis, the present invention generates a parameter mapping correlation matrix by performing parameter mapping on the quality compensation essential oil process according to the risk avoidance strategy, providing a systematic data basis for process optimization. The implementation of quality constraint analysis ensures the stability of product quality, and the generated quality maintenance constraints provide a key basis for subsequent parameter matching. The application of constraint condition matching improves the scientificity of parameter mapping, and the generated avoidance adjustment parameters provide quantitative support for the safety of the process. The implementation of avoidance path deduction promotes the formation of a simulated safety compensation path, providing a practical and feasible path for risk management. The implementation of safety adjustment generates a candidate safety compensation essential oil process, and the process of quality numerical matching ensures the consistency of the candidate solution with the original process. When the quality numerical values are the same, determine that the candidate safety compensation essential oil process is the safety compensation essential oil process, ultimately realizing the effective combination of quality assurance and risk control in the essential oil production process, and the entire system improves the intelligence and safety of the production process.

[0058] Preferably, step S5 includes the following steps:

[0059] Step S51: Perform fusion parameter mapping on the quality compensation essential oil process and the safety compensation essential oil process to obtain fusion process parameters; perform production control adjustment according to the fusion process parameters to obtain an adjusted production process;

[0060] Step S52: Perform 3D modeling based on the adjusted production process to obtain a 3D process flow model;

[0061] Step S53: Perform dynamic coloring of the process flow model according to the essential oil raw material data to generate process state rendering data; perform visualization processing on the process state rendering data to obtain a visualization scene;

[0062] Step S54: Perform real-time view conversion on the visualization scene to generate a digital visualization view of essential oil production.

[0063] Through the digital visualization control system for essential oil production based on data analysis, the present invention generates integrated process parameters by performing integrated parameter mapping on the quality compensation essential oil process and the safety compensation essential oil process, providing a scientific basis for the optimization of the production process. The implementation of production control adjustment ensures the efficiency and flexibility of the production process. The application of 3D modeling enhances the visualization performance of the process flow, making complex processes more intuitive and understandable. The dynamic coloring of the process flow model is based on essential oil raw material data, generating process state rendering data for providing dynamic feedback for real-time monitoring. The implementation of visualization processing strengthens the effectiveness of information transmission. The generated visualization scene provides intuitive support for production decision-making. The application of real-time view conversion enables users to quickly switch different perspectives to generate a digital visualization view of essential oil production, ultimately realizing the comprehensive monitoring and optimization of the essential oil production process and improving the intelligent level and efficiency of production management.

[0064] The present invention also provides a digital visualization control system for essential oil production based on data analysis, which is used to execute the digital visualization control method for essential oil production based on data analysis as described above. The digital visualization control system for essential oil production based on data analysis includes:

[0065] A data preprocessing module, which is used to obtain essential oil raw material data; identify the component content of the essential oil raw material data to obtain the raw material component content; perform interquartile range outlier removal on the raw material component content to generate standard raw material components;

[0066] A production simulation module, which is used to obtain historical process data; perform adaptive process matching on the standard raw material components according to the historical process data to obtain matching reference processes; perform production simulation on the standard raw material components based on the matching reference processes to generate essential oil parameters for simulated process production;

[0067] A quality compensation module, which is used to perform multi-dimensional quality evaluation on the essential oil parameters for simulated process production to obtain quality evaluation data; perform actual combination optimization on the matching reference processes according to the quality evaluation data to generate a quality compensation essential oil process;

[0068] A safety compensation module, which is used to perform scenario simulation deduction on the quality compensation essential oil process to generate process prediction risks; perform safety compensation processing on the quality compensation essential oil process according to the process prediction risks to obtain a safety compensation essential oil process;

[0069] A visualization rendering module, which is used to perform production control adjustment on the standard raw material components based on the quality compensation essential oil process and the safety compensation essential oil process, and perform visualization rendering to construct a digital visualization view of essential oil production.

[0070] The digital visual management and control system for essential oil production based on data analysis in the present invention realizes the efficient acquisition of essential oil raw material data and accurate component identification through the data preprocessing module. The interquartile range anomaly rejection ensures the standardization of raw material components. The production simulation module matches the process by combining historical process data, improving the scientificity and reliability of production parameters. The quality compensation module conducts multi-dimensional evaluation on the simulated process parameters to ensure that the quality of essential oils meets the requirements. The safety compensation module predicts process risks through scenario simulation and deduction, enhancing the safety of the production process. The visual rendering module displays the production management and control information in an intuitive view, improving the understanding and decision-making efficiency of managers on the production process. The overall system realizes the intelligent management of the essential oil production process, promoting the improvement of production efficiency and product quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] Figure 1 FIG. is a schematic flow chart of the steps of a digital visual management and control method for essential oil production based on data analysis;

[0072] Figure 2 FIG. is a schematic detailed implementation step flow chart of step S2;

[0073] Figure 3 FIG. is a schematic detailed implementation step flow chart of step S3.

[0074] The realization, functional features and advantages of the object of the present invention will be further described in conjunction with the embodiments with reference to the drawings. DETAILED IMPLEMENTATION MANNER

[0075] The technical method of the present invention will be clearly and completely described below with reference to the drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those skilled in the art within the scope of the present invention without creative efforts based on the embodiments of the present invention belong to the scope of protection of the present invention.

[0076] In addition, the drawings are only schematic diagrams of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings represent the same or similar parts, and thus the repeated description of them will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor methods and / or microcontroller methods.

[0077] It should be understood that although terms such as "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0078] To achieve the above object, please refer to Figures 1 to 3 , a digital visualization control method for essential oil production based on data analysis, comprising the following steps:

[0079] Step S1: Obtain essential oil raw material data; identify the component content of the essential oil raw material data to obtain the raw material component content; perform interquartile range anomaly rejection on the raw material component content to generate standard raw material components;

[0080] Step S2: Obtain historical process data; perform adaptive process matching on the standard raw material components according to the historical process data to obtain a matching reference process; perform production simulation on the standard raw material components based on the matching reference process to generate essential oil production parameters for the simulation process;

[0081] Step S3: Perform multi-dimensional quality evaluation on the essential oil production parameters of the simulation process to obtain quality evaluation data; perform actual combination optimization on the matching reference process according to the quality evaluation data to generate a quality-compensated essential oil process;

[0082] Step S4: Perform scenario simulation deduction on the quality-compensated essential oil process to generate process prediction risks; perform safety compensation processing on the quality-compensated essential oil process according to the process prediction risks to obtain a safety-compensated essential oil process;

[0083] Step S5: Based on the quality-compensated essential oil process and the safety-compensated essential oil process, adjust the production control of the standard raw material components and perform visual rendering to construct a digital visualization view of essential oil production.

[0084] The present invention ensures the accuracy of raw material components by obtaining essential oil raw material data and identifying the component contents. The standard raw material components generated by removing outliers using the interquartile range improve the reliability of the data. By obtaining historical process data and performing process matching for the standard raw material components, the optimal combination of the process and the raw materials is ensured. Based on the matching reference process, production simulation is carried out, and the essential oil production parameters generated by the simulation process provide a scientific basis for actual production. The simulation process parameters are evaluated through multi-dimensional quality assessment to ensure that the quality of the essential oil meets the standards. The quality assessment data is used to optimize the actual combination of the matching reference process, and the quality compensation essential oil process generated improves the stability of production. Scenario simulation and deduction are used to predict the risks of the quality compensation essential oil process to ensure the safety during the production process. Safety compensation processing makes the process more reliable in actual applications. Based on the quality compensation essential oil process and the safety compensation essential oil process, production control and adjustment are carried out for the standard raw material components, and visual rendering is performed. The digital visual view of essential oil production constructed improves the intelligent level of production management, overall enhancing the efficiency and safety of essential oil production and promoting the scientific and precise production decision-making.

[0085] In an embodiment of the present invention, refer to Figure 1 , which is a schematic diagram of the step flow of the digital visual control method for essential oil production based on data analysis according to the present invention. In this example, the digital visual control method for essential oil production based on data analysis includes the following steps:

[0086] Step S1: Obtain essential oil raw material data; identify the component contents of the essential oil raw material data to obtain the raw material component contents; perform interquartile range outlier removal on the raw material component contents to generate standard raw material components;

[0087] In this embodiment, a high-performance liquid chromatograph (HPLC) is used to analyze the components of the essential oil raw material samples, extract the content data of all key components, record the obtained component data in tabular form, perform interquartile range analysis on the original component content data using Python data analysis tools, calculate the upper quartile (Q3) and the lower quartile (Q1) of each component, define the data removal threshold according to the formulas Q3 + 1.5×(Q3 - Q1) and Q1 - 1.5×(Q3 - Q1), remove the outlier data beyond the range. After the outlier removal is completed, the remaining data is used to generate the standard raw material component content through mean calculation and stored in the CSV file format as the input data for subsequent process matching.

[0088] Step S2: Obtain historical process data; perform process matching for the standard raw material components according to the historical process data to obtain the matching reference process; perform production simulation on the standard raw material components based on the matching reference process to generate the essential oil production parameters of the simulation process;

[0089] In this embodiment, the API interface of the historical process database is called to obtain the process data of similar essential oils produced in the past 5 years. According to the extracted standard raw material components, a matching algorithm based on cosine similarity is used to calculate the similarity of the historical process data. The top five process records with the highest matching degree are selected as the matching reference processes. After selection, the Aspen Plus chemical simulation software is used to perform production simulation on the matching reference processes. The component content and parameters of the standard raw material components are input, and the key parameters such as temperature, pressure, flow rate, and essential oil extraction rate obtained during the simulation process are saved as the essential oil production parameters of the simulation process and output in the JSON file format.

[0090] Step S3: Conduct a multi-dimensional quality evaluation on the essential oil production parameters of the simulation process to obtain quality evaluation data; perform actual combination optimization on the matching reference process according to the quality evaluation data to generate a quality-compensated essential oil process.

[0091] In this embodiment, an essential oil quality evaluation system is used to evaluate the essential oil production parameters of the simulation process. The evaluation dimensions include odor stability, color uniformity, viscosity distribution, impurity content, etc. The principal component analysis (PCA) method is used to reduce the dimension of the multi-dimensional evaluation results, calculate the comprehensive quality score, optimize the matching reference process in combination with the score results, reduce the impurity content by adjusting the extraction temperature and flow rate, adjust the final essential oil extraction rate to ensure the target quality, and at the same time update the matching reference process parameters according to the optimized process conditions to generate a quality-compensated essential oil process and store it in the XML file format.

[0092] Step S4: Conduct a scenario simulation deduction on the quality-compensated essential oil process to generate process prediction risks; perform safety compensation processing on the quality-compensated essential oil process according to the process prediction risks to obtain a safety-compensated essential oil process.

[0093] In this embodiment, the AnyLogic simulation platform is used to conduct a scenario simulation on the quality-compensated essential oil process. The input variables are set as the temperature fluctuation range (±5°C), pressure change range (±10%), and impurity content change range (±2%). The simulation results show that the risk probability of exceeding the impurity content in extreme cases is 15%. Based on this result, the Matlab tool is used to perform fuzzy logic safety compensation on the process parameters, reduce the risk by increasing the condensation equipment and adjusting the solvent dosage, and use the optimized parameters as the final process conditions of the safety-compensated essential oil process. All parameters are output as a standardized PDF report.

[0094] Step S5: Based on the quality-compensated essential oil process and the safety-compensated essential oil process, adjust the production control of the standard raw material components and perform visual rendering to construct a digital visual view of essential oil production.

[0095] In this embodiment, the parameters in the process of calling the safety compensation essential oil are used, and the standard raw material components are used as input data. The industrial control system SCADA (Data Acquisition and Monitoring) module is used to collect and adjust the real-time data of the production process, and the parameters such as extraction temperature, pressure, and flow rate are monitored in real time. Through the Tableau visualization tool, a digital visualization view of essential oil production is generated. The view includes multi-dimensional dynamic displays such as production efficiency, essential oil quality, and impurity content. All the rendered data is saved in the SQL database for subsequent analysis and optimization.

[0096] Preferably, step S1 includes the following steps:

[0097] Step S11: Obtain essential oil raw material data; perform near-infrared spectroscopy analysis on the essential oil raw material data to obtain raw material spectral characteristic data;

[0098] Step S12: Decompose the raw material spectral characteristic data by wavelet transform to obtain spectral component band data; identify the raw materials for the spectral component band data to generate the raw material component content;

[0099] Step S13: Estimate the distribution probability of the raw material component content to generate the raw material component distribution probability;

[0100] Step S14: Calculate the interquartile range of the raw material component distribution probability to obtain the upper and lower limit thresholds of the distribution;

[0101] Step S15: Identify outliers for the raw material component distribution probability based on the upper and lower limit thresholds of the distribution to obtain the abnormal raw material component distribution;

[0102] Step S16: Eliminate outliers from the raw material cost content based on the abnormal raw material component distribution to generate the standard raw material components.

[0103] In this embodiment, 50 batches of essential oil raw material samples are obtained from different suppliers through an essential oil raw material sampling device, and the weight of each batch of samples is 1 kilogram. A near-infrared spectroscopy analyzer (NIRS) is used to perform spectral analysis on each batch of samples. The samples are placed in the sample cell of the spectrometer, and the samples are scanned under the condition that the spectral wavelength range is 800 - 2500 nm, the resolution is set to 4 nm, spectral data is collected, and the absorbance information of the samples is recorded. The wavelet transform decomposition is performed on the spectral feature data using the MATLAB tool, and the Daubechies wavelet function (db4) is selected to decompose the spectral signal into 5 layers, decomposing the spectral data into a low-frequency component and multiple high-frequency components. By extracting the low-frequency component and the first and second layer high-frequency components, spectral component band data is generated. The decomposed band data is input into a support vector machine model (SVM) for raw material identification. The model is based on a pre-trained standard raw material database and outputs the raw material component content of each sample, including the percentage content of key components such as terpene compounds, ester compounds, and aromatic compounds, and performs a distribution probability estimation on the raw material component content. For each component, the kernel density estimation (KDE) method is used to calculate its probability distribution, the Gaussian kernel function is selected and the bandwidth parameter is set to 0.5, the probability distribution result of each component is output in the form of a PDF (probability density function), and the distribution curve is plotted. The interquartile range of the raw material component probability distribution data is calculated. For each component, its first quartile (Q1) and third quartile (Q3) of the distribution are calculated. According to the formulas upper limit threshold = Q3 + 1.5×(Q3 - Q1) and lower limit threshold = Q1 - 1.5×(Q3 - Q1), the upper and lower limit thresholds of the distribution are generated, and the upper and lower limit threshold data is stored as an Excel file. The upper and lower limit threshold data file is read, combined with the probability distribution data, and logical judgment conditions are used to mark outliers. For each component, if the probability density value of a certain data point is lower than the lower limit threshold or higher than the upper limit threshold, then this data point is marked as abnormal data. An array containing outlier marks is generated through the NumPy library, and the abnormal raw material component distribution results are stored as a CSV file. According to the abnormal raw material component distribution file, all data points marked as normal are screened out, and after removing the outliers, the mean and standard deviation of each component are recalculated. A numerical matrix of standard raw material components is generated using the data after removal. The matrix contains the average content of each component in the raw material and the corresponding confidence interval (95% confidence level). Finally, the standard raw material component data is stored in CSV format for the subsequent optimization and simulation stages of the essential oil production process.

[0104] Preferably, step S2 includes the following steps:

[0105] Step S21: Obtain historical process data; perform time series decomposition on the historical process data to obtain process trend characteristics;

[0106] Step S22: Conduct correlation analysis on the process trend characteristics and standard raw material components to obtain process similarity data; perform hierarchical clustering on the process similarity data to generate process classification data;

[0107] Step S23: Perform adaptive process matching on the standard raw material components according to the process classification data to obtain a matching reference process;

[0108] Step S24: Conduct production site simulation on the matching reference process to generate an essential oil production simulation site;

[0109] Step S25: Perform production response simulation on the standard raw material components based on the essential oil production simulation site to generate simulation process essential oil production parameters.

[0110] In this embodiment, process data including parameters such as temperature, pressure, raw material ratio, and distillation time is extracted from the historical database of essential oil production, and the time accuracy is at the minute level. The Pandas tool is used to preprocess the data, including filling missing values using linear interpolation, removing abnormal data points, and normalizing the time axis. Subsequently, the seasonal decomposition function (seasonal_decompose) in the statsmodels library is called to decompose the process data. The additive model (additive) is selected to split the time series into a trend term, a seasonal term, and a residual term. The extracted trend term is used as process feature data. The historical process trend feature data is combined with the standard raw material composition data, and the correlation between process features and raw material components is quantified by calculating the Pearson correlation coefficient. Further, the multivariate linear regression method is used to analyze the impact of changes in raw material components on process features. The learning rate is set to 0.01, and the iteration is performed 1000 times to obtain the weight matrix as process similarity data. The hierarchical clustering method is used to analyze the process similarity data. The hierarchical clustering algorithm in the Scipy library is called, and complete linkage is selected as the clustering method. The distance threshold is set to 0.5 to generate the process classification result and store it as a dendrogram file. The category related to a specific standard raw material composition is extracted from the process classification result. The weighted scoring algorithm is adopted. Weights of 0.6 and 0.4 are assigned to the key indicators (such as terpene content and ester content) in the raw material components, and the matching scores are calculated one by one for the process trend features within the category. The process with the highest score is selected as the reference process, and the parameters of the matching reference process, including the operating pressure of the distillation column, the temperature gradient, and the raw material ratio, are imported using the Aspen Plus simulation tool. The essential oil production distillation process model is selected for the simulation model. The number of distillation trays is set to 50, and the feed flow rate is set to 2 kg / h. After the simulation runs, the essential oil yield, purity, and waste data are output. A three-dimensional virtual production scenario is generated through the simulation results. The information such as the equipment status and material flow is presented in a graphical form using the CAD tool. Combining the production simulation scenario data with the standard raw material composition data, a dynamic response model of essential oil production is established using COMSOL Multiphysics. The range of the main raw material components (such as the terpene content is 45%-55%) is input into the model, and the simulation step size is set to 0.1 second, and the iteration is performed 500 times to simulate the changes in essential oil yield and quality under different process conditions. The output simulation result is a parameter table containing the optimal temperature, the best distillation time, and the raw material ratio, and the data is saved as an Excel format file to provide a key decision-making basis for the production process.

[0111] Preferably, step S3 includes the following steps:

[0112] Step S31: Perform principal component decomposition on the essential oil parameters of the simulation process to obtain the dimension-reduced parameters; perform grey relational mapping on the dimension-reduced parameters to generate quality-related parameters;

[0113] Step S32: Perform hierarchical analysis on the quality-related parameters to obtain quality weight data; perform multi-dimensional quality evaluation on the essential oil parameters of the simulation process according to the quality weight data to obtain quality evaluation data;

[0114] Step S33: Screen the optimal process for the essential oil parameters of the simulation process according to the quality evaluation data to obtain the optimal process parameters;

[0115] Step S34: Based on the optimal process parameters, perform optimal replacement and optimization on the matching reference process to generate the quality-compensated essential oil process.

[0116] In this embodiment, for the multi-dimensional dataset of the essential oil parameters in the simulation process, the PCA (Principal Component Analysis) algorithm in the scikit-learn library in Python is called for dimensionality reduction. The principal component retention rate is set to 95%, and the high-dimensional data is reduced to three-dimensional parameters, including the distillation temperature influence factor, the pressure change influence factor, and the time fluctuation influence factor. The dimensionality-reduced data is calculated for the grey relational degree through the grey system analysis module in MATLAB. Taking the distillation output quality indicators (such as terpene content, purity) as the reference sequence, the normalization method is used to calculate the correlation coefficient of each parameter, and the Analytic Hierarchy Process (AHP) is called to calculate the weight of the quality-related parameters. The terpene content, ester ratio, and volatile organic compound index are set as the top-level criteria, and the comparison matrix is input, where the weight of the terpene content is 0.5, the weight of the ester ratio is 0.3, and the weight of the volatile organic compound is 0.2. The consistency ratio of the comparison matrix is ensured to be lower than 0.1 through the consistency test, and the quality weight data is calculated using the matrix eigenvector. Subsequently, through the weighted scoring model, the quality weight data is combined with the essential oil parameters in the simulation process to construct a multi-dimensional quality evaluation model, score the simulation results of different processes, and output the quality evaluation data. Based on the quality evaluation data, the Genetic Algorithm is applied to screen the optimal process. The optimization goal is set to maximize the quality score, the initial population size is input as 50, the number of iterations is 100, the crossover probability is 0.8, and the mutation probability is 0.05. The combination parameters of pressure, temperature, and time are optimized for the essential oil parameters in the simulation process. The fitness of the population after each iteration is evaluated to screen out the optimal parameter combination, generate the optimal process parameters, and take the optimal process parameters as the input to gradually optimize and adjust the matching reference process. The distillation column pressure, temperature, and operating time are reset using the Aspen Plus simulation tool, and the optimal parameters are applied to the matching reference process to run the simulation to verify the quality improvement effect. During the optimization process, real-time quality monitoring points are set, including the outlet essential oil yield, purity, and residue content, and a real-time feedback mechanism is used to adjust the input parameters to ensure that the output meets the standard quality requirements. Finally, the optimized quality compensation essential oil process is generated, and the process parameters are recorded as an electronic file for digital storage and subsequent production guidance.

[0117] Preferably, step S34 includes the following steps:

[0118] Decompose the optimal process parameters into a process chain to obtain a process unit sequence; perform parameter sensitivity analysis on the process unit sequence to obtain sensitivity indicators;

[0119] Identify key process units based on sensitivity indicators to obtain an optimization target sequence; perform process adaptability evaluation on the optimization target sequence based on a preset adaptability reference value to obtain an adaptability indicator;

[0120] Perform reference process matching based on the adaptability indicator to obtain a process matching plan; perform replacement optimization simulation on the process matching plan to obtain a simulated optimized process;

[0121] Perform anomaly detection on the simulated optimized process. When the anomaly detection result shows no anomaly, determine that the process matching plan is a feasible plan, and perform corresponding target replacement optimization on the optimization target sequence and the matching reference process based on the feasible plan to generate a quality compensation essential oil process.

[0122] In this embodiment, the preferred process parameters are imported, and the entire process chain is decomposed into multiple independent process units according to the process logic, including a pretreatment unit, a distillation unit, a separation unit and a purification unit. For each unit, the input and output parameters and key operating variables, such as temperature, pressure, time, etc., are recorded. Subsequently, Python is used to write a script, and SALib (sensitivity analysis library) is called to perform parameter sensitivity analysis. Based on the Sobol method, the sensitivity of the input parameters to the output quality indicators (such as terpene content and essential oil purity) is calculated, and the parameters with higher sensitivity are screened out to form a sensitivity index data table. The sensitivity index is input into the decision tree analysis module of MATLAB, and the key process units are identified according to the sensitive parameter proportion and sensitivity ranking. Output the optimization target sequence, including the operating variables and corresponding process units that need to be optimized. According to the optimization target sequence, ASPEN Plus is used to evaluate the adaptability of each process unit, and the fitness reference value is set to 80%. According to the evaluation logic, it is judged whether the actual fitness value reaches the reference standard. The fitness index is generated by simulation, including the specific fitness score and optimization suggestions for each process unit. Call the database matching module to match the optimization target sequence with the historical reference process library. The matching algorithm uses a time series similarity algorithm based on DTW (Dynamic Time Warping) to select the process parameter set closest to the optimization target and form a process matching scheme. Subsequently, an industrial simulation platform (such as ANSYS Fluent or COMSOL Multiphysics) is used to simulate the matching scheme for replacement optimization, and multi-parameter optimization conditions are set, including a pressure of 0.8MPa, a temperature range of 90-120℃, and a time of 180 minutes. Anomaly detection is performed through a real-time monitoring module deployed on the simulation platform. The detection method uses an anomaly detection algorithm based on LOF (Local Outlier Factor), and the key parameters of the simulated optimization process are input and compared with the historical normal parameter range. When the test result shows that the anomaly score is less than the threshold of 0.1, it is confirmed that there is no anomaly in the process matching scheme. Based on the feasible solution, according to the optimization target sequence, the operating parameters of the matching reference process are optimized one by one for target replacement, the key unit operating conditions are adjusted, and the optimization results are verified by precise simulation. Finally, the quality compensation essential oil process is generated, and all optimization parameters and results are stored in the database for subsequent essential oil production.

[0123] Preferably, step S4 comprises the following steps:

[0124] Step S41: performing hierarchical decomposition on the quality compensation essential oil process to obtain tree data of process links;

[0125] Step S42: Conduct a fault propagation simulation on the process link tree data to generate simulated fault propagation data; based on the simulated fault propagation data, deduce the fault scenarios of the quality compensation essential oil process to generate process prediction risks;

[0126] Step S43: Based on the process prediction risks, conduct a risk avoidance design to obtain a risk avoidance strategy;

[0127] Step S44: According to the risk avoidance strategy, perform parameter mapping on the quality compensation essential oil process to generate avoidance adjustment parameters; based on the avoidance adjustment parameters, conduct safety compensation processing on the quality compensation essential oil process to obtain a safety compensation essential oil process.

[0128] In this embodiment, the complete process of the quality compensation essential oil process is imported into the process decomposition module. By defining operation nodes, data nodes, and association logics, the process flow is decomposed into four main links: raw material feeding, parameter adjustment, reaction control, and product extraction. At the same time, each main link is further refined into sub-links, including temperature control, pressure maintenance, flow rate adjustment, etc. When performing a fault propagation simulation on the tree-shaped data of the process link, a Petri net model (a mathematical modeling tool for describing distributed systems) is used for modeling. Each process link is regarded as a node, and process parameters are regarded as edges. By constructing a fault propagation simulation script on the MATLAB platform, a propagation analysis is carried out on the fault sources set in the simulation. Assuming that the initial fault is an abnormal 10% increase in the reaction temperature, fault results such as a 5% reduction in the separation efficiency and a 12% extension of the purification time in the downstream link are obtained through the calculation of the propagation path. The generated simulated fault propagation data is sorted out by Excel, including three parts of data content: fault nodes, propagation paths, and influence degrees. When performing a fault scenario deduction on the quality compensation essential oil process based on the simulated fault propagation data, a dynamic scenario deduction method is adopted. The fault propagation data is imported into the AnyLogic simulation platform, and deduction parameters are set, such as the initial process variable change range of ±10% and the deduction time of 360 seconds. The process prediction risks generated by the simulation calculation include specific data such as an increase in the raw material waste rate, a decrease in the output efficiency, and an increase in the product quality fluctuation range. The deduction results are output in the form of a line chart and a risk probability distribution. When performing a risk avoidance design based on the process prediction risks, the FMEA (Failure Mode and Effects Analysis) method is used to analyze the risk points. The high-risk points are defined as process conditions where the temperature fluctuation exceeds 15%, the pressure deviation exceeds 20%, and the flow rate adjustment exceeds 10%. An improved genetic algorithm is used to design a risk avoidance strategy. The optimized objective function includes the minimization of the fault propagation path and the maximization of the quality stability. The generated risk avoidance strategy is recorded in the form of text and charts, including the priority of parameter adjustment and the specific steps of risk response. When performing parameter mapping on the quality compensation essential oil process according to the risk avoidance strategy, a Python script is used to map the parameter adjustment content in the avoidance strategy to the original parameter set of the quality compensation essential oil process. By generating avoidance adjustment parameters based on the parameter mapping algorithm, the relevance between parameters is considered during the mapping process. For example, the coordinated adjustment range of temperature and pressure is controlled within ±5%. The finally generated avoidance adjustment parameters are output in the form of a matrix. When performing a safety compensation process on the quality compensation essential oil process based on the avoidance adjustment parameters, the automatic control system is called to adjust the compensation parameters in real time. The adjusted process parameters are input into the simulation model for verification. When the simulation results show that the purity, yield, and quality of the final product all meet the standards, it is confirmed that the safety compensation essential oil process is generated. The adjusted process parameters are saved in the database in the form of a data table.

[0129] Preferably, step S42 includes the following steps:

[0130] Perform dynamic hierarchical parsing on the process link tree data to generate a timing correlation tree diagram;

[0131] Based on the timing correlation tree diagram, perform node conflict detection to obtain a link conflict matrix;

[0132] Perform fault path simulation on the link conflict matrix to generate a multi-path fault propagation model;

[0133] Based on the multi-path fault propagation model, perform fault propagation simulation to generate simulated fault propagation data;

[0134] Based on the simulated fault propagation data, perform process timing evolution on the quality compensation essential oil process to obtain process prediction risks.

[0135] In this embodiment, when performing dynamic hierarchical parsing on the process step tree data, a dynamic parsing algorithm based on the improved Analytic Hierarchy Process (AHP) is used. The process step tree data is input into the parsing module, and each process node is hierarchically parsed according to the time dimension. The parsing parameter is set to a time interval of 10 seconds. During parsing, temporal correlation analysis is performed on the process nodes at each level to construct a correlation relationship matrix. A temporal correlation tree diagram is generated through the visualization tool Gephi. The temporal correlation tree diagram represents the chronological order and coupling strength between each process step in the form of nodes and edges. The size of the nodes in the diagram is dynamically adjusted according to the importance of the steps, and the thickness of the edges represents the weight of the temporal correlation. When performing node conflict detection based on the temporal correlation tree diagram, a node analysis method based on the conflict detection algorithm is used to analyze the attributes of each node and its connecting edges in the temporal correlation tree diagram. The conflict threshold is set to the correlation weight exceeding 0.If the time interval is 8 or less than 5 seconds, the conflict attributes of each node are detected one by one in the Python environment through a custom script, and the detection results are stored as a link conflict matrix. The conflict matrix contains the conflict attribute values and conflict path numbers of each link. For example, if the number of input-output timing correlation conflicts of a certain node is detected to be 3, when simulating the fault path of the link conflict matrix, a path analysis model based on an improved Monte Carlo algorithm is used. The link conflict matrix is used as input data. By setting the number of fault simulation times to 1000 and the random seed value to 42, a multi-path fault propagation model is constructed. In the fault propagation model, propagation paths are generated based on the conflict paths, including direct propagation paths and indirect propagation paths. Path simulation calculations are performed through MATLAB scripts, and the propagation probability distribution and path priority list of the multi-path fault propagation model are output. The simulation data is stored as an Excel file, including path numbers, fault probabilities, and propagation influence ranges. When performing fault propagation simulation based on the multi-path fault propagation model, a propagation simulation method based on the state space method is adopted. The multi-path fault propagation model is imported into the simulation module in the AnyLogic simulation platform. The propagation time step is set to 1 second, and the total simulation time is 600 seconds. By dynamically calculating the state transition probabilities of each propagation path, simulated fault propagation data is generated. The data contains the state transition situation and time series change situation of the propagation path. The output propagation data is displayed in tabular form, and the fields include propagation path number, fault state, transition time, and influence parameters. When performing process timing evolution on the quality compensation essential oil process based on the simulated fault propagation data, an evolution algorithm based on timing analysis is used to analyze the simulated data period by period. By setting the evolution step to 10 seconds and the evolution depth to 10 steps, the change trend of process parameters in each time period is analyzed and process prediction risk data is generated. The risk data represents the risk levels and time evolution of each process link in the form of a heat map. The generated process prediction risk data includes link numbers, risk levels, evolution paths, and affected parameters. The prediction data is imported into the data visualization platform Tableau for dynamic display, and the results are stored as a risk prediction table in the SQL database.

[0136] Preferably, step S44 includes the following steps:

[0137] Perform parameter mapping on the quality compensation essential oil process according to the risk avoidance strategy to obtain a parameter mapping correlation matrix;

[0138] Perform quality constraint analysis on the quality compensation essential oil process to obtain a quality maintenance constraint;

[0139] Match the constraint conditions of the parameter mapping correlation matrix based on the quality maintenance constraint to generate avoidance adjustment parameters;

[0140] Perform avoidance path deduction on the avoidance adjustment parameters to obtain a simulated safety compensation path; perform safety adjustment based on the simulated safety compensation path to generate a candidate safety compensation essential oil process;

[0141] Perform quality value matching on the candidate safety compensation essential oil process and the quality compensation essential oil process. When the quality values are the same, determine that the candidate safety compensation essential oil process is the safety compensation essential oil process.

[0142] In this embodiment, when performing parameter mapping on the quality compensation essential oil process according to the risk avoidance strategy, a mapping model based on multi-parameter correlation analysis is used. The input risk avoidance strategy parameter matrix is loaded into the mapping module. During the mapping process, a hierarchical progressive analysis method is adopted to decompose each risk parameter in the strategy step by step. The mapping parameter analysis step size is set to 5. The analysis results are normalized using the pandas library in the Python environment and a parameter mapping correlation matrix is generated. The matrix contains the correlation relationship between process parameters and the risk avoidance strategy, and the correlation weight is represented in numerical form. When performing quality constraint analysis on the quality compensation essential oil process, a constraint detection algorithm based on a multi-dimensional quality analysis model is used. The key quality parameters of the quality compensation essential oil process, such as volatile oil content, density, and refractive index, are input into the constraint analysis module. Through a quality assessment algorithm based on limiting conditions, the fluctuation range of each parameter is compared with the process specification value. The constraint parameter range is set to ±2%. The analysis results are output in tabular form and a quality maintenance constraint is generated. The constraint results include the quality parameter number, the defined range, and the deviation value. When performing constraint condition matching on the parameter mapping correlation matrix based on the quality maintenance constraint, a matrix processing model based on a constraint matching algorithm is used. The quality maintenance constraint is used as a condition input, and condition matching calculations are performed on each parameter of the parameter mapping correlation matrix. The matching threshold is set to 0.85. During the calculation process, parameters that do not meet the constraint conditions are eliminated. The output result is the avoidance adjustment parameter. The avoidance adjustment parameter includes the adjustment direction, adjustment amplitude, and the corresponding risk reduction weight of each process link. When performing avoidance path deduction on the avoidance adjustment parameter, a simulation method based on a dynamic path deduction model is used. The avoidance adjustment parameter is loaded into the deduction module through the AnyLogic simulation platform. The deduction step size is set to 1 second, and the total deduction time is 300 seconds. Dynamic simulation is performed on each adjustment path to generate a simulated safety compensation path. The path results include time series data, path status, and the change situation of the adjusted parameters. When performing safety adjustment according to the simulated safety compensation path, a parameter optimization model based on a multi-path adjustment algorithm is used. The simulated safety compensation path data is loaded through a MATLAB script, and multi-constraint optimization is performed on the adjustment value of each parameter in the path. The constraint condition during the optimization process is the defined range defined in the quality maintenance constraint, and a candidate safety compensation essential oil process is generated. The candidate process data includes the process link number, the adjusted quality parameters, and their corresponding safety weights. When performing quality numerical matching on the candidate safety compensation essential oil process and the quality compensation essential oil process, a quality comparison method based on a numerical matching algorithm is used. Each quality parameter of the candidate safety compensation essential oil process and the quality compensation essential oil process is compared one by one through a Python script. The matching accuracy is set to 0.001. When all quality parameter values are the same, the output determination result is the safety compensation essential oil process. The matching results are output in the form of a report and stored as a PDF format document.

[0143] Preferably, step S5 includes the following steps:

[0144] Step S51: Perform fusion parameter mapping on the quality compensation essential oil process and the safety compensation essential oil process to obtain fusion process parameters; adjust production control according to the fusion process parameters to obtain an adjusted production process;

[0145] Step S52: Perform 3D modeling based on the adjusted production process to obtain a 3D process flow model;

[0146] Step S53: Dynamically color the process flow model according to the essential oil raw material data to generate process status rendering data; perform visualization processing on the process status rendering data to obtain a visualization scene;

[0147] Step S54: Perform real-time view conversion on the visualization scene to generate a digital visualization view of essential oil production.

[0148] In this embodiment, when performing fusion parameter mapping on the quality compensation essential oil process and the safety compensation essential oil process, a parameter mapping model based on a multi-process fusion algorithm is adopted. The parameter matrices of the quality compensation essential oil process and the safety compensation essential oil process are respectively loaded into the mapping module. Python scripts are used to calculate the two sets of parameters one by one using the numpy library. The mapping rule takes the weighted average algorithm as the core, and the weight ratio is set as 60% for the quality compensation essential oil process and 40% for the safety compensation essential oil process. The generated fusion process parameters include the process step number, step description, and adjusted parameter values. After mapping, they are stored in the JSON file format. The fusion process parameters are loaded into the production control system, and based on these parameters, the equipment at each link of the production line is adjusted. Adjustment instructions are sent through the PLC (Programmable Logic Controller), and the execution frequency is set to 5 Hz. When performing 3D modeling based on the adjusted production process, the modeling function in Autodesk Maya software is used to import the adjusted production process data into the modeling module. The data format is converted through Python scripts, and the conversion rule is to parse the XML format into the OBJ file format. Each process step is represented by a 3D lattice, and polygon modeling tools are used to visually design the equipment, pipelines, and key nodes of the process flow. The modeling accuracy is set to 0.01 mm. During the modeling process, key process points are marked in blue. The generated 3D process flow model contains the structural parameters and coordinate data of all process links. When dynamically coloring the process flow model according to the essential oil raw material data, the Unity engine is used to load the essential oil raw material data and the 3D process flow model. The essential oil raw material data is stored in the form of a CSV file. After loading, it is parsed through a C# script. The parsing rule is to extract key raw material parameters, including volatility, color depth, and consistency. These parameters are mapped to each link in the process flow model. Through the dynamic coloring module, gradient colors are applied. The volatility parameter is represented by a yellow gradient, the color depth is represented by a red gradient, and the consistency is represented by a green gradient. The generated process state rendering data contains the coloring state and the corresponding parameter values of each link. When visualizing the process state rendering data, a rendering technology based on OpenGL (Open Graphics Library) is adopted. The process state rendering data in PNG format is loaded into the rendering engine, the display resolution is set to 1920×1080, the rendering algorithm adopts a frame-by-frame update mode, and the update interval for each frame is 16 ms. The display content includes the 3D structure of the process flow model, the dynamic coloring state, and the parameter values. Control signals are input through the touch screen to adjust the viewing angle and magnification ratio of the display. The visualization scene is output as a real-time dynamic display screen. When performing real-time view conversion on the visualization scene, a real-time rendering technology based on WebGL (Web Graphics Library) is used. The visualization scene data is loaded into the Web application end, and real-time interaction functions are implemented through JavaScript scripts. The conversion rules include view rotation, zooming, and local magnification. The set rotation rate is 15° / second, the zoom ratio range is from 1:1 to 1:50, and local magnification is performed by selecting the range with the cursor. Each operation will update the converted view data in real time and synchronize it to the server. The generated digital visualization view of essential oil production is displayed in full screen through a Web browser and stored in the HTML5 file format.

[0149] The present invention also provides a digital visualization control system for essential oil production based on data analysis, which is used to execute the digital visualization control method for essential oil production based on data analysis as described above. The digital visualization control system for essential oil production based on data analysis includes:

[0150] A data preprocessing module, which is used to obtain essential oil raw material data; identify the component content of the essential oil raw material data to obtain the raw material component content; perform quartile range outlier rejection on the raw material component content to generate standard raw material components;

[0151] A production simulation module, which is used to obtain historical process data; perform adaptive process matching on the standard raw material components according to the historical process data to obtain a matching reference process; perform production simulation on the standard raw material components based on the matching reference process to generate essential oil parameters for the simulated process production;

[0152] A quality compensation module, which is used to conduct multi-dimensional quality evaluation on the essential oil parameters produced by the simulation process to obtain quality evaluation data; and optimize the actual combination of the matching reference process according to the quality evaluation data to generate a quality-compensated essential oil process;

[0153] A safety compensation module, which is used to conduct scenario simulation and deduction on the quality-compensated essential oil process to generate process prediction risks; and perform safety compensation processing on the quality-compensated essential oil process according to the process prediction risks to obtain a safety-compensated essential oil process;

[0154] A visualization rendering module, which is used to adjust the production control of the standard raw material components based on the quality-compensated essential oil process and the safety-compensated essential oil process, and perform visualization rendering to construct a digital visualization view of essential oil production.

[0155] Through the digital visualization control system for essential oil production based on data analysis, the present invention realizes the efficient acquisition of essential oil raw material data and accurate component identification through the data preprocessing module. The interquartile range anomaly rejection ensures the standardization of raw material components. The production simulation module matches the process by combining historical process data, improving the scientificity and reliability of production parameters. The quality compensation module conducts multi-dimensional evaluation on the simulation process parameters to ensure that the essential oil quality meets the requirements. The safety compensation module predicts process risks through scenario simulation and deduction, enhancing the safety of the production process. The visualization rendering module displays the production control information in an intuitive view, improving the understanding and decision-making efficiency of managers for the production process. The overall system realizes the intelligent management of the essential oil production process, promoting the improvement of production efficiency and product quality.

[0156] Therefore, from any perspective, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, it is intended to cover all changes falling within the meaning and scope of the equivalent elements of the application documents within the present invention.

[0157] The above are only specific implementation manners of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art. The general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but rather conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A digital visualization control method for essential oil production based on data analysis, characterized in that: The following steps are involved: Step S1: Acquire essential oil raw material data; identify the component content of the essential oil raw material data to obtain the raw material component content; remove the interquartile range abnormalities of the raw material component content to generate standard raw material components; Step S2: Acquire historical process data; perform process matching on the standard raw material components according to the historical process data to obtain a matching reference process; Perform production simulation on standard raw material ingredients based on matching reference process to generate simulation process parameters for essential oil production; Step S3: Perform multi-dimensional quality evaluation on the parameters of essential oil produced by the simulation process to obtain quality evaluation data; According to the quality assessment data, the matching reference process is actually combined and optimized to generate the quality compensation essential oil process; Step S4: Perform scenario simulation on the quality compensation essential oil process to generate process prediction risks; According to the process prediction risk, the quality compensation essential oil process is subjected to safety compensation treatment to obtain the safety compensation essential oil process; Step S5: Based on the quality compensation essential oil process and the safety compensation essential oil process, the standard raw material composition is adjusted for production control, and visual rendering is performed to construct a digital visualization view of essential oil production.

2. The digital visualization control method for essential oil production based on data analysis according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: acquiring essential oil raw material data; performing near infrared spectroscopy analysis on the essential oil raw material data to obtain raw material spectral characteristic data; Step S12: performing wavelet transform decomposition on the raw material spectral characteristic data to obtain spectral component band data; performing raw material identification on the spectral component band data to generate the raw material component content; Step S13: Estimating the distribution probability of the raw material component content to generate the raw material component distribution probability; Step S14: Calculate the interquartile range of the raw material component distribution probability to obtain the upper and lower limit thresholds of the distribution; Step S15: performing outlier identification on the raw material component distribution probability based on the upper and lower distribution thresholds to obtain abnormal raw material component distribution; Step S16: based on the abnormal raw material composition distribution, outliers are eliminated from the raw material cost content to generate a standard raw material composition.

3. The digital visualization control method for essential oil production based on data analysis according to claim 1, characterized in that, Step S2 includes the following steps: Step S21: Acquire historical process data; perform time series decomposition on the historical process data to obtain process trend characteristics; Step S22: performing correlation analysis on process trend characteristics and standard raw material components to obtain process similarity data; performing hierarchical clustering on the process similarity data to generate process classification data; Step S23: matching the standard raw material components with the process according to the process classification data to obtain a matching reference process; Step S24: performing a production field simulation on the matching reference process to generate an essential oil production simulation field; Step S25: Performing production response simulation on the standard raw material components based on the essential oil production simulation field to generate simulation process parameters for essential oil production.

4. The digital visualization control method for essential oil production based on data analysis according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: performing principal component deconstruction on the parameters of essential oil produced by the simulation process to obtain dimension reduction parameters; performing grey correlation mapping on the dimension reduction parameters to generate quality-related parameters; Step S32: Performing hierarchical analysis on the quality-related parameters to obtain quality weight data; performing multi-dimensional quality evaluation on the parameters of essential oil produced by the simulation process according to the quality weight data to obtain quality evaluation data; Step S33: Screening the optimal process parameters for the production of essential oils by the simulation process according to the quality evaluation data to obtain the optimal process parameters; Step S34: Based on the preferred process parameters, the matching reference process is optimized by preferred replacement to generate a quality-compensated essential oil process.

5. The digital visualization control method for essential oil production based on data analysis according to claim 4, characterized in that, Step S34 includes the following steps: Decompose the process chain of the optimal process parameters to obtain the process unit sequence; perform parameter sensitivity analysis on the process unit sequence to obtain the sensitivity index; Based on the sensitivity index, the key process units are identified to obtain the optimized target sequence; based on the preset fitness reference value, the process fitness of the optimized target sequence is evaluated to obtain the fitness index; Based on the fitness index, reference process matching is performed to obtain a process matching solution; replacement optimization simulation is performed on the process matching solution to obtain a simulated optimized process; The simulated optimization process is detected for anomalies. When the result of the anomaly detection is that there is no anomaly, the process matching solution is determined to be a feasible solution. Based on the feasible solution, the optimization target sequence and the matching reference process are optimized for corresponding target replacement to generate a quality compensated essential oil process.

6. The digital visualization control method for essential oil production based on data analysis according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: performing hierarchical decomposition on the quality compensation essential oil process to obtain tree data of process links; Step S42: performing fault propagation simulation on the process link tree data to generate simulated fault propagation data; performing fault scenario deduction on the quality compensation essential oil process based on the simulated fault propagation data to generate process prediction risk; Step S43: performing risk avoidance design based on process prediction risk to obtain a risk avoidance strategy; Step S44: mapping parameters of the quality compensation essential oil process according to the risk avoidance strategy to generate avoidance adjustment parameters; performing safety compensation processing on the quality compensation essential oil process based on the avoidance adjustment parameters to obtain a safety compensation essential oil process.

7. The digital visualization control method for essential oil production based on data analysis according to claim 6, characterized in that: Step S42 includes the following steps: Dynamically analyze the tree data of process links in layers and generate a time-series correlation tree diagram; Perform node conflict detection based on the time-series association tree diagram to obtain the link conflict matrix; Perform fault path simulation on the link conflict matrix to generate a multi-path fault propagation model; Perform fault propagation simulation based on a multi-path fault propagation model to generate simulated fault propagation data; The process time series evolution of the quality compensation essential oil process is carried out based on the simulated fault propagation data to obtain the process prediction risk.

8. The digital visualization control method for essential oil production based on data analysis according to claim 6, characterized in that: Step S44 includes the following steps: According to the risk avoidance strategy, the quality compensation essential oil process is parameter mapped to obtain the parameter mapping correlation matrix; Conduct quality constraint analysis on the quality compensation essential oil process to obtain quality maintenance constraints; Based on the quality preservation constraint, the parameter mapping association matrix is ​​matched with the constraint conditions to generate the avoidance adjustment parameters; Perform avoidance path deduction on avoidance adjustment parameters to obtain simulated safety compensation path; perform safety adjustment according to the simulated safety compensation path to generate candidate safety compensation essential oil processes; The quality values ​​of the candidate safety compensation essential oil process and the quality compensation essential oil process are matched. When the quality values ​​are consistent, the candidate safety compensation essential oil process is determined to be the safety compensation essential oil process.

9. The digital visualization control method for essential oil production based on data analysis according to claim 1, characterized in that: Step S5 includes the following steps: Step S51: mapping the fusion parameters of the quality compensation essential oil process and the safety compensation essential oil process to obtain fusion process parameters; adjusting the production control according to the fusion process parameters to obtain an adjusted production process; Step S52: Perform three-dimensional modeling based on the adjusted production process to obtain a three-dimensional process flow model; Step S53: dynamically coloring the process flow model according to the essential oil raw material data to generate process state rendering data; visualizing the process state rendering data to obtain a visualization scene; Step S54: Perform real-time view conversion on the visualization scene to generate a digital visualization view of essential oil production.

10. A digital visualization control system for essential oil production based on data analysis, characterized in that: Used to execute the digital visualization control method for essential oil production based on data analysis as claimed in claim 1, the digital visualization control system for essential oil production based on data analysis comprises: The data preprocessing module is used to obtain the essential oil raw material data; identify the component content of the essential oil raw material data to obtain the raw material component content; remove the interquartile range abnormalities of the raw material component content to generate the standard raw material composition; The production simulation module is used to obtain historical process data; match the standard raw material components with the adaptation process according to the historical process data to obtain a matching reference process; and perform production simulation on the standard raw material components based on the matching reference process to generate simulation process production essential oil parameters; The quality compensation module is used to perform multi-dimensional quality evaluation on the parameters of essential oil produced by the simulation process to obtain quality evaluation data; According to the quality assessment data, the matching reference process is actually combined and optimized to generate the quality compensation essential oil process; The safety compensation module is used to simulate and deduce the quality compensation essential oil process to generate process prediction risks; perform safety compensation processing on the quality compensation essential oil process according to the process prediction risks to obtain the safety compensation essential oil process; The visualization rendering module is used to adjust the production control of standard raw material ingredients based on the quality compensation essential oil process and the safety compensation essential oil process, and perform visualization rendering to build a digital visualization view of essential oil production.

Images