Air separation process whole flow data monitoring and visual management method and system

Abstract

The invention relates to the technical field of data processing, in particular to a whole-process data monitoring and visual management method and system for an air separation process, and the method comprises the steps: collecting key parameter data in the air separation process, and input data vectors and output data vectors among equipment; constructing a parameter correlation model to analyze the input data vector and the output data vector to obtain data deviation; if the data deviation exceeds a dynamic threshold value, triggering a multi-level alarm mechanism, and generating a block chain log record; generating a hash value for the key parameter data, and marking an abnormal link; a bimodal anomaly detection model is constructed to analyze an abnormal link, an equipment performance attenuation coefficient and an inter-equipment anomaly influence relation coefficient are obtained, and a comprehensive anomaly score is generated through a fusion technology; when the comprehensive abnormal score is greater than a preset threshold value, constructing a fault tree model to reversely trace an abnormal data link for the abnormal link, and positioning a fault source; and full-process data monitoring and management are realized through a visual interface.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and system for monitoring and visualizing the whole-process data of an air separation process. Background Art

[0002] In the field of industrial system data governance, the traditional air separation unit monitoring system faces multiple technical bottlenecks. The existing architecture is limited by the structural contradictions of heterogeneous data sources, which are specifically manifested as follows: 1) The multimodal data capture dimension is missing. The measured data shows that the existing system can only obtain the basic physical quantity parameters of the equipment (accounting for about 35% of the actual process feature dimensions), and cannot build a complete digital twin covering deep-level process parameters such as phase change process and energy efficiency characteristics; 2) The distributed data storage architecture has timing alignment defects. When processing asynchronous data streams from sensor networks, equipment controllers and process simulation systems, the timestamp synchronization error rate of cross-source data is as high as 17%; 3) There is a performance bottleneck in the visualization rendering pipeline. When the traditional graphical interface simultaneously presents more than 32 dimensions of process parameters, the dynamic refresh rate drops to less than 12fps, resulting in the loss of important working condition features; 4) The real-time computing framework is not scalable enough. When the batch processing mechanism based on the relational database writes more than 150,000 data points per second, the system throughput drops by 63%; 5) The data association analysis capability is weak. Traditional statistical methods are difficult to analyze the 48-dimensional feature space nonlinear relationship implicit in the dynamic equilibrium of the distillation tower. During the peak production load period during holidays, these problems directly caused delays of more than 45 minutes in process failure tracing.

[0003] Current technology improvements focus on optimizing the physical layer communication protocol, and there are three key limitations at the data governance level: First, the multi-source heterogeneous data fusion process produces significant information entropy attenuation, and the use of traditional ETL tools results in a 28% loss in process feature fidelity; second, the visualization engine is limited to the two-dimensional plane mapping paradigm and cannot achieve dynamic thermodynamic trajectory projection of process parameters in three-dimensional phase space; third, time series data processing uses an offline batch computing mode, and the response delay to millisecond-level process events exceeds 800ms. The essence of these problems lies in the lack of a full life cycle computing system for high-dimensional industrial data.

[0004] Therefore, a method and system for data monitoring and visualization management of the entire air separation process is proposed. Summary of the invention

[0005] The object of the present invention is to provide a method and system for monitoring and visualizing the data of the whole process of an air separation process, by collecting key parameter data, input data vectors and output data vectors between devices in the air separation process; constructing a parameter association model to analyze the input data vector and the output data vector to obtain data deviation; if the data deviation exceeds the dynamic threshold, triggering a multi-level alarm mechanism, and generating a blockchain log record; generating a hash value for the key parameter data, and marking an abnormal link; constructing a dual-modal anomaly detection model to analyze the abnormal link, obtain the equipment performance attenuation coefficient and the abnormal influence relationship coefficient between devices, and generate a comprehensive anomaly score through fusion technology; when the comprehensive anomaly score is greater than a preset threshold, constructing a fault tree model to reversely trace the abnormal data link of the abnormal link to locate the fault source; and realizing full-process data monitoring and management through a visual interface.

[0006] To achieve the above object, the present invention provides the following technical solutions: A method for monitoring and visualizing the whole process data of an air separation process, comprising: S1. Collect key parameter data in the air separation process; deploy sensors through edge computing nodes, analyze and preprocess key parameter data, and obtain input data vectors and output data vectors between upstream and downstream equipment in the air separation process; S2. Construct a parameter association model to analyze the input data vector and the output data vector, obtain the logical relationship of key parameters, and combine the dynamic threshold to obtain the data deviation; if the data deviation exceeds the dynamic threshold, trigger a multi-level alarm mechanism and generate a blockchain log record; S3. Generate a hash value for the key parameter data to form an encrypted data packet; recalculate the hash value after decrypting the data packet and compare it with the original hash value; when there is inconsistency, automatically trigger a data retransmission request and mark the abnormal link; S4. Construct a dual-modal anomaly detection model to analyze abnormal links, obtain the equipment performance attenuation coefficient and the abnormal impact relationship coefficient between devices, and generate a comprehensive anomaly score through fusion technology; when the comprehensive anomaly score is greater than the preset threshold, construct a fault tree model to reversely trace the abnormal data link of the abnormal link and locate the source of the fault; and realize full-process data monitoring and management through a visual interface.

[0007] Preferably, the key parameter data include pressure, temperature, flow rate and oxygen content; The preprocessing includes data cleaning, data synchronization and data normalization, and filtering noise using a sliding window mean algorithm; The blockchain log record includes storing the abnormal timestamp, equipment ID and operator information to the steel plant private chain node; Visual management includes real-time display of equipment status, data trend analysis, abnormal alarm prompts and fault tracing results.

[0008] Preferably, the parameter association model includes a feature extraction module, an association analysis module, a threshold calculation module and a data consistency verification module; The feature extraction module obtains the key data feature vector by extracting features from the input data vector and the output data vector; the association analysis module analyzes the key data feature vector through linear regression to generate the logical relationship of key parameters and predict the downstream equipment input data; the threshold calculation module calculates the dynamic threshold through the normal fluctuations and errors of the air separation process historical data; the data consistency verification module obtains the deviation by comparing the downstream equipment input data with the actual input data.

[0009] Preferably, the dual-modal anomaly detection model includes a data partitioning module, a temporal modal analysis module, a spatial modal analysis module and a modal fusion module; The data partitioning module obtains abnormal time series data and abnormal spatial topology data by analyzing the abnormal link; and removes noise and normalizes the abnormal time series data and abnormal spatial topology data; The time series modal analysis module uses a long short-term memory network to analyze the change trend of equipment parameters over time, obtains the long-term operation law of the equipment, and generates the equipment performance attenuation coefficient; The spatial modal analysis module analyzes the propagation path and intensity of anomalies in the device network through a graph convolutional network, and generates anomaly impact relationship coefficients between devices; The modality fusion module generates a comprehensive anomaly score by integrating the temporal and spatial analysis results through weighted fusion technology.

[0010] Preferably, the specific calculation formula of the comprehensive abnormality score is: ; in, For equipment The comprehensive abnormality score, is the equipment performance attenuation coefficient weight, is the equipment performance attenuation coefficient, is the weight of the abnormal impact relationship coefficient between devices, For equipment About equipment Abnormal influence relationship coefficient, For equipment A collection of directly connected devices.

[0011] Preferably, the fault tree model includes an event module, a traceability analysis module, a probability calculation module and a positioning module; The event module decomposes the abnormal link event into basic events, intermediate events and top events; the traceability analysis module starts from the top event and traces back along the logical structure to identify all possible paths that lead to the abnormality; the probability calculation module evaluates the possibility of each fault path by calculating the occurrence probability of each event in the fault tree; the positioning module determines the fault source by comprehensively analyzing the logical relationship, feature matching degree and probability distribution of the fault path, and generates a positioning result of the fault source.

[0012] An air separation process data monitoring and visualization management system, including: The data acquisition and processing unit is used to collect key parameter data in the air separation process. By deploying sensors on edge computing nodes, the key parameter data is analyzed and preprocessed to obtain the input data vector and output data vector between the upstream and downstream equipment of the air separation process. A parameter association model construction unit, used to construct a parameter association model to analyze the input data vector and the output data vector, obtain the logical relationship of key parameters, and obtain the data deviation in combination with the dynamic threshold; if the data deviation exceeds the dynamic threshold, a multi-level alarm mechanism is triggered and a blockchain log record is generated; The abnormal link acquisition unit is used to generate a hash value for the key parameter data to form an encrypted data packet; after decrypting the data packet, the hash value is recalculated and compared with the original hash value; when there is inconsistency, a data retransmission request is automatically triggered and an abnormal link is marked; The fault analysis and tracing unit is used to build a dual-modal anomaly detection model to analyze abnormal links, obtain the equipment performance attenuation coefficient and the abnormal impact relationship coefficient between devices, and generate a comprehensive anomaly score through fusion technology; when the comprehensive anomaly score is greater than the preset threshold, a fault tree model is built to trace the abnormal data link back to the abnormal link and locate the source of the fault; and the whole process data is monitored and managed through a visual interface.

[0013] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention deploys sensors through edge computing nodes to achieve comprehensive collection of input and output data between upstream and downstream equipment in the air separation process. Based on this, a parameter association model is constructed to analyze the logical relationship of key parameters, and the data deviation is monitored in real time in combination with dynamic thresholds. If the deviation exceeds the standard, a multi-level alarm is triggered and recorded in the blockchain log. The comprehensiveness of data collection and the accuracy of anomaly detection are significantly improved. The blockchain log ensures the transparency and immutability of abnormal event records, further enhancing the reliability of the system.

[0014] 2. The present invention generates hash values ​​and forms encrypted data packets during data transmission to ensure data integrity and security. If there is inconsistency, data retransmission is triggered and abnormal links are marked, which significantly improves transmission reliability. In addition, the abnormal link identification function can quickly locate the problem link, avoid abnormal spread, improve system stability and data processing efficiency, and provide stronger data protection for air separation process.

[0015] 3. The present invention uses a dual-modal anomaly detection model, combined with time series and space analysis, to deeply analyze abnormal links, generate equipment performance attenuation coefficients and abnormal impact relationship coefficients between equipment, and calculates comprehensive anomaly scores through fusion technology. When the score exceeds the threshold, a fault tree model is automatically constructed for reverse tracing to accurately locate the source of the fault, thereby improving the accuracy of troubleshooting. The visualization interface intuitively presents the operation status of the entire process, helping operators to quickly respond to anomalies. Compared with the prior art, the present invention greatly improves the efficiency of fault management and decision-making support capabilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic diagram of a method for monitoring and visualizing the whole-process data of an air separation process provided by the present invention; Figure 2 A schematic diagram of the structure of a data monitoring and visualization management system for the entire process of air separation process provided by the present invention; Figure 3 A schematic diagram of the structure of a parameter association model provided by an embodiment of the present invention; Figure 4 A schematic diagram of full-process data monitoring of an air separation process provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] The air separation process is an industrial process that separates air into important gases such as nitrogen, oxygen, and argon. It is widely used in many fields such as chemical industry, metallurgy, and energy. In the operation process of the air separation unit, multiple key links and complex process control are involved, and it is usually necessary to rely on accurate data monitoring and management systems to ensure its efficient and safe operation. However, the existing technology still has some obvious deficiencies in the data flow and monitoring management of the air separation unit. First, the current air separation process data acquisition system mainly relies on decentralized sensor equipment, and the data collection of each link is not comprehensive and accurate enough, and it is impossible to accurately reflect the operating status of the entire air separation unit in real time. Secondly, the data processing and storage methods of each link in the air separation unit are different, and there is a lack of unified standards and intelligent data flow interfaces, which leads to low data flow efficiency between different links and difficulty in achieving seamless docking and integration of data. Furthermore, most of the existing air separation process data monitoring systems only monitor local links, especially in terms of equipment operation status and fault diagnosis. There is a lack of a global monitoring and visualization management platform for the entire air separation process, which makes it difficult to support more efficient decision analysis and process optimization. In addition, the real-time monitoring and early warning mechanism of traditional systems is also relatively weak, often relying on manual records or regular sampling, with poor real-time performance and unable to quickly respond to abnormal changes in the process. Although some modern data monitoring technologies have begun to be applied, it is still difficult to achieve rapid early warning of system failures or fine-tuning of the process due to low data update frequency or imperfect feedback mechanism.

[0019] Embodiment 1 Based on this, the present invention provides a method and system for monitoring and visualizing the whole process data of air separation process. Figure 1 to Figure 2 , the technical solution is as follows: As an embodiment of the present invention, refer to Figure 1 S1 in the figure is applied to the data acquisition and processing unit of a full-process data monitoring and visualization management system for air separation process. The data acquisition and processing unit is used to collect key parameter data in the air separation process. Sensors are deployed through edge computing nodes to analyze and preprocess key parameter data to obtain input data vectors and output data vectors between upstream and downstream equipment in the air separation process.

[0020] S1. Collect key parameter data in the air separation process; deploy sensors through edge computing nodes to collect output data and input data between upstream and downstream equipment in the air separation process, and perform preprocessing to generate input data vectors and output data vectors between equipment; Furthermore, the key parameter data include pressure, temperature, flow rate and oxygen content; the preprocessing includes data cleaning, data synchronization and data normalization, and the sliding window mean algorithm is used to filter noise; In the air separation process, the collection and monitoring of key parameter data is essential to ensure the stable operation of each system part. The following is a detailed description of the main system parts and their key parameters: Air compression system: monitor the inlet and outlet pressure of the compressor to ensure that the compression process operates within a safe and efficient range; monitor the inlet and outlet temperature of the compressor to prevent overheating and damage to the equipment; Precooling and purification system: monitor the temperature of the air in the precooler to ensure effective reduction of the air temperature; monitor the air flow to ensure the precooling effect; Heat exchange system: monitor the inlet and outlet temperatures of the heat exchanger to ensure heat exchange efficiency; monitor the flow rate of the cooling medium to ensure heat exchange effect; Distillation separation system: monitor the temperature of each tray of the distillation tower to ensure the separation effect; monitor the top and bottom pressures of the distillation tower to maintain appropriate separation conditions; monitor the flow of products and waste gases to ensure product output and purity; Expansion refrigeration system: monitor the inlet and outlet temperatures of the expander to ensure the refrigeration effect; monitor the inlet and outlet pressures of the expander to maintain appropriate expansion conditions; Product delivery and storage system: monitor the delivery pressure of product gas to ensure the safety of the delivery process; monitor the temperature of product gas to prevent excessive temperature from affecting product quality.

[0021] Through real-time monitoring and management of the above key parameters, the stable operation of each system of the air separation process can be effectively guaranteed. For some key parameter data, please refer to Table 1.

[0022] Table 1 is used to record the key parameter data (such as pressure, temperature, flow rate, etc.) of each system part in the air separation process. It is collected through edge computing nodes and sensors to ensure the comprehensiveness and accuracy of data collection and provide a basis for subsequent analysis.

[0023] Table 1 Data collection table of key parameters of air separation process

[0024] As an embodiment of the present invention, refer to Figure 1 S2 in the figure is applied to a parameter association model construction unit of an air separation process full-process data monitoring and visualization management system. The parameter association model construction unit is used to construct a parameter association model to analyze the input data vector and the output data vector, obtain the logical relationship of key parameters, and combine the dynamic threshold to obtain the data deviation; if the data deviation exceeds the dynamic threshold, a multi-level alarm mechanism is triggered and a blockchain log record is generated.

[0025] S2. Construct a parameter association model to analyze the input data vector and the output data vector, obtain the logical relationship of key parameters, and combine the dynamic threshold to obtain the data deviation; if the data deviation exceeds the dynamic threshold, trigger a multi-level alarm mechanism and generate a blockchain log record; the blockchain log record includes storing the abnormal timestamp, equipment ID and operator information to the private chain node of the steel plant; Furthermore, the parameter association model includes a feature extraction module, an association analysis module, a threshold calculation module and a data consistency verification module. Figure 3 ; The feature extraction module obtains the key data feature vector by extracting features from the input data vector and the output data vector; the association analysis module analyzes the key data feature vector through linear regression to generate the logical relationship of key parameters and predict the downstream equipment input data; the threshold calculation module calculates the dynamic threshold through the normal fluctuations and errors of the air separation process historical data; the data consistency verification module obtains the deviation by comparing the downstream equipment input data with the actual input data.

[0026] The parameter association model is trained on historical air separation process data through random forest algorithm to learn the logical relationship between key parameters; the model parameters are optimized through cross-validation and other methods to improve performance; the trained association analysis model can predict the input data of downstream equipment according to the input data, and the specific data can be referred to Table 2; Table 2 Parameter association model training data table

[0027] Table 2 is used to show the historical data samples used in the training of the parameter association model, including input features (such as pressure and temperature) and output features (such as flow), as well as labels indicating whether they are abnormal, to reveal the logical relationship between key parameters.

[0028] In this embodiment, a parameter association model is established to analyze the input and output data vectors to reveal the logical relationship between key parameters. Combined with dynamic thresholds, data deviations are identified. When the data deviation exceeds the set threshold, a multi-level alarm mechanism is triggered and a blockchain log record is generated to ensure data security and traceability.

[0029] As an embodiment of the present invention, refer to Figure 1 S3 in the figure is applied to an abnormal link acquisition unit of an air separation process full-process data monitoring and visualization management system. The abnormal link acquisition unit is used to generate a hash value for the key parameter data to form an encrypted data packet; after decrypting the data packet, the hash value is recalculated and compared with the original hash value; when there is inconsistency, a data retransmission request is automatically triggered and the abnormal link is marked.

[0030] S3. Generate a hash value for the key parameter data to form an encrypted data packet; recalculate the hash value after decrypting the data packet and compare it with the original hash value; when there is inconsistency, automatically trigger a data retransmission request and mark the abnormal link; In this embodiment, a hash value is generated for the key parameter data to form an encrypted data packet. After decryption, the hash value is recalculated and compared with the original hash value. When there is inconsistency, a data retransmission request is automatically triggered and the abnormal link is marked to ensure the accuracy and integrity of data transmission.

[0031] As an embodiment of the present invention, refer to Figure 1 S4 in the figure is applied to the fault analysis and tracing unit of a full-process data monitoring and visualization management system for air separation process. The fault analysis and tracing unit is used to construct a dual-modal anomaly detection model to analyze abnormal links, obtain the equipment performance attenuation coefficient and the abnormal impact relationship coefficient between equipment, and generate a comprehensive anomaly score through fusion technology; when the comprehensive anomaly score is greater than the preset threshold, a fault tree model is constructed to reversely trace the abnormal data link of the abnormal link to locate the source of the fault; and the visualization of the full-process data monitoring and management is realized through a visualization interface, including real-time display of equipment status, data trend analysis, abnormal alarm prompts and fault tracing results.

[0032] S4. Construct a dual-modal anomaly detection model to analyze abnormal links, obtain the equipment performance attenuation coefficient and the abnormal impact relationship coefficient between devices, and generate a comprehensive anomaly score through fusion technology; when the comprehensive anomaly score is greater than the preset threshold, construct a fault tree model to reversely trace the abnormal data link of the abnormal link and locate the source of the fault; and realize full-process data monitoring and management through a visual interface.

[0033] Furthermore, the dual-modal anomaly detection model includes a data partitioning module, a temporal modal analysis module, a spatial modal analysis module and a modal fusion module; The data partitioning module obtains abnormal time series data and abnormal spatial topology data by analyzing the abnormal link; and removes noise and normalizes the abnormal time series data and abnormal spatial topology data; The time series modal analysis module uses a long short-term memory network to analyze the change trend of equipment parameters over time, obtains the long-term operation law of the equipment, and generates the equipment performance attenuation coefficient; The spatial modal analysis module analyzes the propagation path and intensity of anomalies in the device network through a graph convolutional network, and generates anomaly impact relationship coefficients between devices; The modality fusion module generates a comprehensive anomaly score by integrating the temporal and spatial analysis results through weighted fusion technology.

[0034] Build a dual-modal anomaly detection model, analyze the abnormal links, and obtain the equipment performance attenuation coefficient and the abnormal impact relationship coefficient between devices. Generate a comprehensive anomaly score through fusion technology. When the comprehensive anomaly score exceeds the preset threshold, build a fault tree model, trace back the abnormal data link, and locate the fault source. Through the visual interface, realize the monitoring and management of the whole process data, and improve the intelligence level of the system.

[0035] Furthermore, the specific calculation formula of the comprehensive abnormality score is: ; in, For equipment The comprehensive abnormality score, is the equipment performance attenuation coefficient weight, is the equipment performance attenuation coefficient, is the weight of the abnormal impact relationship coefficient between devices, For equipment About equipment Abnormal influence relationship coefficient, For equipment A collection of directly connected devices.

[0036] In this embodiment, the calculation method of the comprehensive anomaly score optimizes the accuracy of the anomaly score by weighted fusion of the equipment performance attenuation coefficient and the anomaly impact relationship coefficient, making the prediction of equipment failure more scientific and reliable.

[0037] Furthermore, the fault tree model includes an event module, a traceability analysis module, a probability calculation module and a positioning module; The event module decomposes the abnormal link event into basic events, intermediate events and top events; the traceability analysis module starts from the top event and traces back along the logical structure to identify all possible paths that lead to the abnormality; the probability calculation module evaluates the possibility of each fault path by calculating the occurrence probability of each event in the fault tree; the positioning module determines the fault source by comprehensively analyzing the logical relationship, feature matching degree and probability distribution of the fault path, and generates a positioning result of the fault source.

[0038] The introduction of the fault tree model can effectively trace various events in abnormal links and evaluate the possibility of fault paths through probability calculation. Comprehensive analysis of fault paths can quickly locate the source of faults, improving the maintenance efficiency and response speed of the system.

[0039] The present invention realizes data collection, analysis and monitoring of the whole process of air separation process by combining advanced technologies such as edge computing, blockchain and deep learning. First, the key parameter data in the air separation process is collected in real time through edge computing nodes and sensors, and the data is preprocessed to ensure the accuracy and real-time performance of the data. By constructing a parameter association model, the relationship between input and output data between devices can be effectively analyzed, potential data deviations can be discovered in time, and the dynamic threshold trigger alarm mechanism can be combined to effectively ensure the stability of system operation. The use of blockchain technology for data recording ensures the immutability and traceability of data, and improves the security and reliability of the system. In addition, the dual-modal anomaly detection model uses deep learning technology, comprehensive time series and spatial data analysis, accurately identifies equipment anomalies and their mutual influence, and effectively improves the accuracy of equipment fault warning. At the same time, the fault tree model can accurately trace the abnormal link, quickly locate the source of the fault, and optimize the fault handling process. The visual management interface displays the equipment status, data trend and abnormal alarm in real time, enhances the decision-making support capabilities of managers, and comprehensively improves the monitoring efficiency and operation and maintenance level of the air separation process. These innovations jointly promote the intelligent data management of the whole process of air separation process.

[0040] Embodiment 2 See also Figure 1 to Figure 2 The present invention provides an air separation process full process data monitoring and visualization management method applied to an air separation process full process data monitoring and visualization management system. The technical solution is as follows: As an embodiment of the present invention, refer to Figure 1 S1 in the figure is applied to the data acquisition and processing unit of a full-process data monitoring and visualization management system for air separation process. The data acquisition and processing unit is used to collect key parameter data in the air separation process. Sensors are deployed through edge computing nodes to analyze and preprocess key parameter data to obtain input data vectors and output data vectors between upstream and downstream equipment in the air separation process.

[0041] S1. Collect key parameter data in the air separation process; deploy sensors through edge computing nodes, analyze and preprocess key parameter data, and obtain input data vectors and output data vectors between upstream and downstream equipment in the air separation process; Furthermore, the key parameter data include pressure, temperature, flow rate and oxygen content; the preprocessing includes data cleaning, data synchronization and data normalization, and the sliding window mean algorithm is used to filter noise; As an embodiment of the present invention, refer to Figure 1S2 in the figure is applied to a parameter association model construction unit of an air separation process full-process data monitoring and visualization management system. The parameter association model construction unit is used to construct a parameter association model to analyze the input data vector and the output data vector, obtain the logical relationship of key parameters, and combine the dynamic threshold to obtain the data deviation; if the data deviation exceeds the dynamic threshold, a multi-level alarm mechanism is triggered and a blockchain log record is generated.

[0042] S2. Construct a parameter association model to analyze the input data vector and the output data vector, obtain the logical relationship of the key parameters, and combine the dynamic threshold to obtain the data deviation; if the data deviation exceeds the dynamic threshold, trigger a multi-level alarm mechanism and generate a blockchain log record; the blockchain log record includes storing the abnormal timestamp, equipment ID and operator information to the private chain node of the steel plant, refer to Table 3; Table 3 Abnormal link marking table

[0043] Table 3 is used to record abnormal link information detected during data transmission, including abnormal time, device ID, operator, and abnormal type, to ensure data security and traceability.

[0044] Furthermore, the parameter association model includes a feature extraction module, an association analysis module, a threshold calculation module and a data consistency verification module; The feature extraction module obtains the key data feature vector by extracting features from the input data vector and the output data vector; the association analysis module analyzes the key data feature vector through linear regression to generate the logical relationship of key parameters and predict the downstream equipment input data; the threshold calculation module calculates the dynamic threshold through the normal fluctuations and errors of the air separation process historical data; the data consistency verification module obtains the deviation by comparing the downstream equipment input data with the actual input data.

[0045] As an embodiment of the present invention, refer to Figure 1 S3 in the figure is applied to an abnormal link acquisition unit of an air separation process full-process data monitoring and visualization management system. The abnormal link acquisition unit is used to generate a hash value for the key parameter data to form an encrypted data packet; after decrypting the data packet, the hash value is recalculated and compared with the original hash value; when there is inconsistency, a data retransmission request is automatically triggered and the abnormal link is marked.

[0046] S3. Generate a hash value for the key parameter data to form an encrypted data packet; recalculate the hash value after decrypting the data packet and compare it with the original hash value; when there is inconsistency, automatically trigger a data retransmission request and mark the abnormal link; S4. Construct a dual-modal anomaly detection model to analyze abnormal links, obtain the equipment performance attenuation coefficient and the abnormal impact relationship coefficient between devices, and generate a comprehensive anomaly score through fusion technology; when the comprehensive anomaly score is greater than the preset threshold, construct a fault tree model to reversely trace the abnormal data link of the abnormal link and locate the source of the fault; and realize full-process data monitoring and management through a visual interface.

[0047] Furthermore, the dual-modal anomaly detection model includes a data partitioning module, a temporal modal analysis module, a spatial modal analysis module and a modal fusion module; The data partitioning module obtains abnormal time series data and abnormal spatial topology data by analyzing the abnormal link; and removes noise and normalizes the abnormal time series data and abnormal spatial topology data; The time series modal analysis module uses a long short-term memory network to analyze the change trend of equipment parameters over time, obtains the long-term operation law of the equipment, and generates the equipment performance attenuation coefficient; The equipment performance attenuation coefficient is calculated by the time series modal analysis module and is used to measure the degree of attenuation of equipment performance over time. The specific steps and formula are as follows: Data foundation: Time series data of key equipment parameters collected from edge computing nodes (such as historical and real-time values ​​of pressure, temperature, etc.); The specific calculation method is as follows: Feature extraction: extract trend features from time series data, such as the rate of change of parameters over time; Model prediction: Use the LSTM model to predict parameter values ​​under normal operating conditions based on historical data; Attenuation calculation: compare the actual parameter value with the predicted value and calculate the degree of performance attenuation; Equipment performance attenuation coefficient The calculation formula is: ; in, is the length of the evaluation time window, For equipment In time The actual key parameter values, Devices predicted by the LSTM model In time The parameter value represents the expected value under normal operating conditions. For equipment Reference parameter values ​​under normal operating conditions; Indicates the average deviation of device performance. The smaller the value, the milder the performance degradation, and the larger the value, the more severe the degradation. The spatial modal analysis module analyzes the propagation path and intensity of anomalies in the device network through a graph convolutional network, and generates anomaly impact relationship coefficients between devices; The coefficient of abnormal impact relationship between devices is calculated by the spatial modal analysis module to quantify the transmission intensity of abnormalities between devices. The specific steps and formula are as follows: Data foundation: device connection relationship diagram built based on preprocessed spatial topology data, and related data of abnormal links.

[0048] The specific calculation method is as follows: the equipment in the air separation process is used as a node, and the input-output relationship between the equipment is used as an edge to construct a device network diagram; the GCN model is used to learn the abnormal propagation path and intensity between the equipment, and the influence relationship is calculated through the node embedding vector; the abnormal influence relationship coefficient between the equipment The specific calculation is: ; in, is the activation function, is the learnable weight matrix in GCN, used to adjust the feature importance, Will and concatenated into a vector, representing the characteristics of the device pair, is the bias term.

[0049] The modality fusion module generates a comprehensive anomaly score by integrating the temporal and spatial analysis results through weighted fusion technology.

[0050] Furthermore, the specific calculation formula of the comprehensive abnormality score is: ; in, For equipment The comprehensive abnormality score, is the equipment performance attenuation coefficient weight, is the equipment performance attenuation coefficient, is the weight of the abnormal impact relationship coefficient between devices, For equipment About equipment Abnormal influence relationship coefficient, For equipment A collection of directly connected devices.

[0051] Furthermore, the fault tree model includes an event module, a traceability analysis module, a probability calculation module and a positioning module; The event module decomposes abnormal link events into basic events, intermediate events and top events; the highest-level event of the top event abnormal data link, such as "abnormal input pressure of the distillation tower"; the subsystem or component failure caused by the intermediate event leading to the top event, such as "compressor abnormality"; the direct cause of the failure of the basic event leading to the intermediate event or the top event, such as "valve leakage" or "sensor failure".

[0052] The traceability analysis module starts from the top event and traces back along the logical structure to identify all possible paths that lead to the anomaly. The event nodes in the fault tree are connected through logic gates (such as "AND gate" and "OR gate") to reflect the causal relationship between events. For example, "abnormal input pressure of the distillation tower" may be caused by "compressor failure" or "valve leakage" (connected by "OR gate").

[0053] The traceability analysis module starts from the top event, traces down layer by layer, builds a fault tree and identifies all possible fault paths. Taking "abnormal input pressure of distillation tower" as an example, possible fault paths include: Path 1: Sensor failure → data abnormality; Path 2: Valve leakage → pressure fluctuation; Path 3: Compressor failure → insufficient output pressure.

[0054] The probability calculation module evaluates the possibility of each fault path by calculating the probability of occurrence of each event in the fault tree; Probability of basic events: Based on historical failure data, equipment reliability data, and expert evaluation, determine the probability of occurrence of basic events. For example, the probability of a valve leaking , the probability of sensor failure .

[0055] Probability of intermediate events and top events: According to the type of logic gate, calculate the probability of the upper event: "OR Gate": Event or The probability of occurrence is: ; AND Gate: Events or The probability of simultaneous occurrence is: .

[0056] Assume that the top event in the fault tree, “abnormal input pressure of distillation column”, is caused by “compressor failure” (probability ) and "Valve Leakage" (Probability ) are connected through an “OR gate”, then the probability of the top event is: ; By calculating layer by layer, the probability calculation module provides a quantitative possibility assessment for each fault path.

[0057] The positioning module determines the fault source by comprehensively analyzing the logical relationship, feature matching degree and probability distribution of the fault path, and generates a positioning result of the fault source.

[0058] Feature matching: Use the fault features in the expert knowledge base to match the manifestation of real-time abnormal data. For example, if the abnormal data is manifested as "high-frequency pressure fluctuations", and the knowledge base records that "valve leakage often manifests as high-frequency pressure fluctuations", then the matching degree of the "valve leakage" path is higher. Probability distribution: Based on the output of the probability calculation module, evaluate the probability of occurrence of each path, see Table 4 for examples; Table 4 Fault tree model analysis table

[0059] Table 4 is used to record the occurrence probability of each basic event in the fault tree model and the possibility assessment of the fault path, which is used to reversely trace the abnormal link and locate the fault source.

[0060] The present invention aims to improve the monitoring accuracy and management efficiency of air separation process. First, by deploying edge computing nodes and sensors in the air separation process, key parameter data such as pressure, temperature, flow rate and oxygen content are collected in real time. The collected data is preprocessed to generate input and output data vectors between devices, providing a reliable data basis for subsequent analysis. Then, a parameter association model is constructed to analyze the input and output data vectors to reveal the logical relationship between key parameters. Combined with dynamic thresholds, data deviations are discovered in time, a multi-level alarm mechanism is triggered, and blockchain technology is used to record abnormal information to ensure data security and traceability. In addition, a hash value is generated for the key parameter data to form an encrypted data packet. After decryption, the hash value is recalculated and compared with the original hash value to ensure the accuracy and integrity of data transmission. When inconsistency is found, a data retransmission request is automatically triggered, and the abnormal link is marked to improve the self-healing ability of the system. In terms of anomaly detection, a dual-modal anomaly detection model is constructed to comprehensively analyze time series and spatial data to accurately identify equipment anomalies and their mutual influence. Through fusion technology, a comprehensive abnormality score is generated. When the score exceeds the preset threshold, a fault tree model is constructed to trace the abnormal data link backwards and quickly locate the fault source. For details, refer to Figure 4 . Finally, through the visual interface, the equipment status, data trends and abnormal alarms are displayed in real time, the decision-making support capabilities of managers are enhanced, and the monitoring efficiency and operation and maintenance level of the air separation process are comprehensively improved. In summary, the present invention realizes intelligent data management of the entire air separation process by integrating advanced technologies such as edge computing, blockchain and deep learning, and improves the stability, security and intelligence level of the system.

[0061] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for monitoring and visualizing the whole process data of an air separation process, characterized in that: include: S1. Collect key parameter data in air separation process; By deploying sensors on edge computing nodes, key parameter data are analyzed and preprocessed to obtain input data vectors and output data vectors between upstream and downstream equipment in the air separation process. S2. Construct a parameter association model to analyze the input data vector and the output data vector, obtain the logical relationship of key parameters, and combine the dynamic threshold to obtain the data deviation; if the data deviation exceeds the dynamic threshold, trigger a multi-level alarm mechanism and generate a blockchain log record; S3. Generate a hash value for the key parameter data to form an encrypted data packet; recalculate the hash value after decrypting the data packet and compare it with the original hash value; when there is inconsistency, automatically trigger a data retransmission request and mark the abnormal link; S4. Build a dual-modal anomaly detection model to analyze abnormal links, obtain the device performance attenuation coefficient and the anomaly impact relationship coefficient between devices, and generate a comprehensive anomaly score through fusion technology; When the comprehensive abnormality score is greater than the preset threshold, a fault tree model is constructed to trace the abnormal data link in reverse to locate the fault source; and the whole process data is monitored and managed through a visual interface.

2. The method for monitoring and visualizing the whole process data of air separation process according to claim 1, characterized in that: The key parameter data include pressure, temperature, flow rate and oxygen content; The preprocessing includes data cleaning, data synchronization and data normalization, and filtering noise using a sliding window mean algorithm; The blockchain log record includes storing the abnormal timestamp, equipment ID and operator information to the steel plant private chain node; Visual management includes real-time display of equipment status, data trend analysis, abnormal alarm prompts and fault tracing results.

3. The method for monitoring and visualizing the whole process data of an air separation process according to claim 1, characterized in that: The parameter association model includes a feature extraction module, an association analysis module, a threshold calculation module and a data consistency verification module; The feature extraction module obtains a key data feature vector by extracting features from the input data vector and the output data vector; The association analysis module analyzes the key data feature vector through linear regression to generate the logical relationship of key parameters and predict the downstream equipment input data; the threshold calculation module calculates the dynamic threshold through the normal fluctuations and errors of the air separation process historical data; the data consistency verification module obtains the deviation by comparing the downstream equipment input data with the actual input data.

4. The method for monitoring and visualizing the whole process data of air separation process according to claim 1, characterized in that: The dual-modal anomaly detection model includes a data partitioning module, a temporal modal analysis module, a spatial modal analysis module and a modal fusion module; The data partitioning module obtains abnormal time series data and abnormal spatial topology data by analyzing the abnormal link; and removes noise and normalizes the abnormal time series data and abnormal spatial topology data; The time series modal analysis module uses a long short-term memory network to analyze the change trend of equipment parameters over time, obtains the long-term operation law of the equipment, and generates the equipment performance attenuation coefficient; The spatial modal analysis module analyzes the propagation path and intensity of anomalies in the device network through a graph convolutional network, and generates anomaly impact relationship coefficients between devices; The modality fusion module generates a comprehensive anomaly score by integrating the temporal and spatial analysis results through weighted fusion technology.

5. The method for monitoring and visualizing the whole process data of air separation process according to claim 4, characterized in that: The specific calculation formula of the comprehensive abnormality score is: ； in, For equipment The comprehensive abnormality score, is the equipment performance attenuation coefficient weight, is the equipment performance attenuation coefficient, is the weight of the abnormal impact relationship coefficient between devices, For equipment About equipment Abnormal influence relationship coefficient, For equipment A collection of directly connected devices.

6. The method for monitoring and visualizing the whole process data of air separation process according to claim 1, characterized in that: The fault tree model includes an event module, a traceability analysis module, a probability calculation module and a positioning module; The event module decomposes the abnormal link event into basic events, intermediate events and top events; the tracing analysis module starts from the top event and traces back along the logical structure to identify all possible paths leading to the abnormality; The probability calculation module evaluates the possibility of each fault path by calculating the occurrence probability of each event in the fault tree; the positioning module determines the fault source and generates the positioning result of the fault source by comprehensively analyzing the logical relationship, feature matching degree and probability distribution of the fault path.

7. A data monitoring and visualization management system for the whole process of air separation process, characterized in that: include: Data acquisition and processing unit, used to collect key parameter data in air separation process; By deploying sensors on edge computing nodes, key parameter data are analyzed and preprocessed to obtain input data vectors and output data vectors between upstream and downstream equipment in the air separation process. A parameter association model construction unit, used to construct a parameter association model to analyze the input data vector and the output data vector, obtain the logical relationship of key parameters, and obtain the data deviation in combination with the dynamic threshold; if the data deviation exceeds the dynamic threshold, a multi-level alarm mechanism is triggered and a blockchain log record is generated; The abnormal link acquisition unit is used to generate a hash value for the key parameter data to form an encrypted data packet; after decrypting the data packet, the hash value is recalculated and compared with the original hash value; when there is inconsistency, a data retransmission request is automatically triggered and an abnormal link is marked; The fault analysis and tracing unit is used to build a dual-modal anomaly detection model to analyze abnormal links, obtain the equipment performance attenuation coefficient and the anomaly impact relationship coefficient between devices, and generate a comprehensive anomaly score through fusion technology; When the comprehensive abnormality score is greater than the preset threshold, a fault tree model is constructed to trace the abnormal data link in reverse to locate the fault source; and the whole process data is monitored and managed through a visual interface.

Images