An intelligent processing method for visualizing electronic information data

Abstract

The present invention relates to the technical field of industrial data analysis, and specifically to an intelligent processing method for visualizing electronic information data, which includes the following steps: collecting data from temperature sensors, pressure sensors, and position sensors in a factory, performing data cleaning and format standardization to obtain standardized sensor data. By collecting data from temperature sensors, pressure sensors, and position sensors in real time, implementing data cleaning and format standardization, the present invention realizes the precise fusion of data from different sources, solves the problems of multi-source data heterogeneity and insufficient collaboration, and improves the comprehensiveness and consistency of data analysis; based on the fused data, implementing intelligent definition and detection of event patterns, capturing the complex associations of temperature anomalies and pressure mutations in real time, deeply mining the potential associations between data, quickly locating the root cause of anomalies, and improving the accuracy and reliability of data analysis.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial data analysis, and particularly to an intelligent processing method for visualizing electronic information data. Background Art

[0002] The technical field of industrial data analysis mainly involves technical methods and systems for collecting, processing, analyzing, and visually presenting various data generated during industrial production processes. Specifically, it includes technical links such as data acquisition, data cleaning, feature extraction, intelligent analysis and modeling, prediction optimization, and interactive visual presentation.

[0003] In practical applications of the prior art, the processes of collecting, processing, analyzing, and presenting industrial data are treated in a fragmented manner, and there is a lack of effective deep integration among these processes, resulting in frequent occurrence of data island phenomena; the event detection and data correlation analysis processes are mostly single-dimensional monitoring, making it difficult to accurately capture abnormal events intertwined with multiple factors under complex working conditions, and thus causing frequent false alarms or missed alarms, increasing the difficulty of fault troubleshooting. Therefore, improvements are needed. Summary of the Invention

[0004] The purpose of the present invention is to solve the drawbacks existing in the prior art, and to propose an intelligent processing method for visualizing electronic information data.

[0005] To achieve the above purpose, the present invention adopts the following technical solutions. An intelligent processing method for visualizing electronic information data includes the following steps:

[0006] Collect data from factory temperature sensors, pressure sensors, and position sensors, perform data cleaning and format standardization to obtain standardized sensor data; use data fusion to integrate the standardized sensor data into a unified data framework to generate a fused sensor data framework;

[0007] Based on the fused sensor data framework, define and implement data flow event patterns, including temperature exceeding the threshold and pressure mutation, perform event detection and correlation analysis to obtain preliminary event correlation results; analyze the preliminary event correlation results through graph theory algorithms to show the relationships between data and generate a data relationship display graph;

[0008] Use the data relationship display graph to perform tracking and optimization analysis on data paths, identify key transmission nodes and potential data flow bottlenecks to obtain key path analysis results; adjust the data processing flow according to the key path analysis results to optimize data transmission and processing efficiency and generate an optimized data processing flow;

[0009] Apply the optimized data processing flow to real-time data monitoring, and combine with augmented reality to visually present the data in real time on the operator's visual interface.

[0010] Preferably, the step of obtaining the standardized sensor data is as follows: collect the original data from the temperature sensors, pressure sensors, and position sensors in the factory, perform error checking and outlier screening for each type of sensor data, delete the error data and outliers, and obtain the preliminary cleaned data;

[0011] Based on the preliminary cleaned data, adjust the data resolution and unify the timestamp format to obtain the format-standardized data;

[0012] According to the format-standardized data, perform data quality inspection, including verifying data integrity and consistency, to obtain the standardized sensor data.

[0013] Preferably, the step of obtaining the fused sensor data framework is as follows: based on the standardized sensor data, align all the sensor data according to the timestamp, perform clustering on the data to form a unified data structure, and obtain the preliminary integrated data;

[0014] Based on the preliminary integrated data, filter the noise in the data, use statistical recognition and correct the outliers in the data to obtain the enhanced integrated data;

[0015] Based on the enhanced integrated data, combine the data source, timestamp accuracy, and sensor type to obtain the fused sensor data framework.

[0016] Preferably, the step of obtaining the preliminary event correlation result is as follows: based on the fused sensor data framework, extract the temperature measurement data sequence of the temperature sensor and the pressure measurement data sequence of the pressure sensor, and arrange them in the chronological order of data acquisition, calculate the time increment for the temperature measurement data sequence, calculate the instantaneous change rate for the pressure measurement data sequence, and obtain the preliminary event data stream;

[0017] According to the preliminary event data stream, calculate the data mutation intensity index, and the calculation formula is:

[0018]

[0019] Wherein, is the data mutation intensity index, is the time increment of the temperature measurement data sequence, is the instantaneous change rate of the pressure measurement data sequence, is the cross change rate of the temperature measurement data sequence and the pressure measurement data sequence, is the smooth change rate of the temperature measurement data sequence, is the cumulative change difference of the pressure measurement data sequence;

[0020] Based on the data mutation intensity index, define and implement the data flow event pattern, set the change threshold of the temperature measurement data sequence and the mutation standard of the pressure measurement data sequence, classify the data mutation intensity index and match the event pattern, identify the eligible event types, and obtain the preliminary event association result.

[0021] Preferably, the steps for obtaining the data relationship display diagram are as follows: Based on the preliminary event association result, extract each event node and the connection relationship, construct an event interaction matrix, and remove the isolated event nodes to obtain an event relationship matrix;

[0022] According to the event relationship matrix, calculate the event centrality index, and the calculation formula is:

[0023]

[0024] Among them, is the event centrality index, is the event node and the event node The interaction frequency between them, is the node and The number of mutual responses between them, is the node and The number of new connections between them, is the node The total interaction time, is the node The number of participating projects, is the number of event nodes in the current network;

[0025] Based on the event centrality index, construct an event association topological structure through graph theory, draw a node distribution diagram, and through the connectivity analysis between nodes, screen the key event flow relationships to form a data relationship display diagram.

[0026] Preferably, the steps for obtaining the critical path analysis result are as follows: According to the data relationship display diagram, calculate the critical path optimization index, and the calculation formula is:

[0027]

[0028] Among them, is the critical path optimization index, is the node The traffic data, is the node The shortest path length to the critical node, is the node The buffer size, is the node Processing speed, is the number of connections for the node ; is the data payload for the node ; is the traffic volatility for the node ; is the number of nodes on the path;

[0029] Based on the critical path optimization index, identify potential bottlenecks and critical transmission nodes in data transmission, analyze which nodes and connections affect the data stream efficiency, and obtain the critical path analysis result.

[0030] Preferably, the step of obtaining the optimized data processing flow is: based on the critical path analysis result, extract the inter-node delay, bandwidth usage, and packet loss rate of the data stream to obtain the data path parameters to be optimized;

[0031] According to the data path parameters to be optimized, calculate the path optimization priority, and the calculation formula is:

[0032]

[0033] where is the path optimization priority, is the bandwidth occupancy ratio of the path ; is the packet loss rate of the path ; is the average transmission time of the path ; is the delay of the path ; is the jitter value of the path ;

[0034] Based on the path optimization priority, adjust the transmission strategy of the data stream, reallocate the traffic load, and generate the optimized data processing flow.

[0035] Preferably, the specific steps of applying the optimized data processing flow to real-time data monitoring and presenting the data visually in real time on the operator's visual interface in combination with augmented reality are:

[0036] According to the optimized data processing flow, select the transmission rate, the occurrence frequency of abnormal events, and the data integrity detection result to generate the input configuration for real-time data monitoring;

[0037] Through the input configuration for real-time data monitoring, convert it into dynamic charts and digital displays of performance indicators to generate a visual data stream;

[0038] Dynamically project the visualized data flow onto the operator's augmented reality field of vision to display the data view.

[0039] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0040] The present invention collects data from temperature sensors, pressure sensors, and position sensors in real time, implements data cleaning and format standardization, realizes the precise fusion of data from different sources, solves the problems of multi-source data heterogeneity and insufficient collaboration, and improves the comprehensiveness and consistency of data analysis; based on the fused data, it implements the intelligent definition and detection of event patterns, captures the complex associations of temperature anomalies and pressure mutations in real time, deeply explores the potential associations between data, quickly locates the root cause of anomalies, and improves the accuracy and reliability of data analysis; combines graph theory algorithms to deeply analyze the implicit relationships between data, visually presents the internal associations and mutual influence paths of multi-dimensional data in the form of a data relationship graph, realizes the visual display of the relationships between data, avoids blind spots and misjudgments in the data analysis process, and improves the data understanding efficiency; at the same time, through data path tracing and optimization analysis, actively identifies key transmission nodes and bottleneck positions in the data flow, timely optimizes the data processing process and data transmission strategy, achieving a double improvement in data processing efficiency and real-time monitoring performance; and uses augmented reality technology to realize the real-time visual presentation of the optimized data processing process, enabling the operator to intuitively master the data dynamics, quickly respond to changes in the production environment, and improve the agility and decision-making accuracy of real-time monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a step schematic diagram of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0042] In order to make the objectives, technical solutions, and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0043] Please refer to Figure 1 , the present invention provides a technical solution, an electronic information data visualization intelligent processing method, including the following steps:

[0044] Collect data from factory temperature sensors, pressure sensors, and position sensors, perform data cleaning and format standardization to obtain standardized sensor data; use data fusion to integrate the standardized sensor data into a unified data framework to generate a fused sensor data framework;

[0045] Based on the integrated sensor data framework, define and implement data stream event patterns, including temperature exceeding the threshold and pressure mutation, for event detection and correlation analysis to obtain preliminary event correlation results; analyze the preliminary event correlation results through graph theory algorithms to show the relationships between data and generate a data relationship display graph;

[0046] Use the data relationship display graph to track and optimize the analysis of the data path, identify key transmission nodes and potential data flow bottlenecks, and obtain the critical path analysis results; adjust the data processing flow according to the critical path analysis results to optimize the data transmission and processing efficiency and generate an optimized data processing flow;

[0047] Apply the optimized data processing flow to real-time data monitoring, and combine it with augmented reality to visually present the data in real time on the operator's visual interface.

[0048] Standardize the steps for obtaining sensor data as follows: collect the original data from temperature sensors, pressure sensors, and position sensors in the factory, perform error checking and outlier screening for each type of sensor data, delete the error data and abnormal points, and obtain the preliminary cleaned data;

[0049] Based on the preliminary cleaned data, adjust the data resolution and unify the timestamp format to obtain format-standardized data;

[0050] According to the format-standardized data, conduct data quality inspection, including verifying data integrity and consistency, to obtain standardized sensor data.

[0051] Specifically, based on the information sources provided by temperature sensors, pressure sensors, and position sensors deployed within the factory area, for each type of sensor data, disassemble and obtain its measurement range and working mode from the factory production line equipment overview materials. For example, the temperature sensor has a range between [range values] and this range can be obtained through the equipment specification. Subsequently, compare each collected raw record of temperature, pressure, and position with the pre-established valid range one by one. For example, compare the temperature value to the interval [temperature interval], the pressure value to the interval [pressure interval], and the position data to the interval [position interval]. If it is found that the range is exceeded, it is marked as a candidate error point. Then, based on the statistically estimated error threshold set by experience and the actual monitoring scenario, check these candidate error points. The statistically estimated error threshold can be initially confirmed by estimating the average temperature and standard deviation and then taking three times the standard deviation range. For example, if the temperature value at a certain moment exceeds or is lower than [threshold value], it is considered abnormal. The same calculation method is applied to pressure and position data, and it is compared again in combination with the abnormal situations recorded in the factory historical operation log. If it is confirmed that there is a measurement anomaly, the corresponding record is deleted. If there is an obvious jump but not outside the allowable range, it is regarded as a suspicious point and the stable situation at adjacent moments is continued to be calculated. It is only excluded after it is determined that it exceeds the threshold set by experience continuously for multiple times. Finally, summarize all the sensor measurement entries after exclusion to obtain the preliminary cleaned data.

[0052] Based on the preliminary cleaned data obtained previously, first determine a unified sampling period and resolution. For example, resample and record the temperature, pressure, and position data at 1-second time intervals. Before performing this resolution adjustment, select an appropriate sampling period according to the production process rhythm and sensor update frequency given in the factory documents. If it is found that the refresh rate of a certain type of sensor is 0.5 seconds or shorter, the resolution can be set to 0.5 seconds without ignoring minor fluctuations. At this time, when unifying the timestamp format, synchronize and align these resolution differences to continuously use UTC time or generate standardized time records by comparing with the internal clock reference of the factory. During this process, if it is detected that some sensors have missing timestamps or jumps exceeding a fixed time span, refer to the upper limit of the time error provided in the device description of each sensor and set a maximum correctable range according to this error limit. For example, when a device description recommends a maximum allowable offset of 0.2 seconds, if the detected offset does not exceed 0.2 seconds, perform linear interpolation compensation; if it exceeds, mark this record as abnormal and discard it. Finally, through this resolution unification and timestamp alignment operation, obtain formatted standardized data.

[0053] Based on the formatted standardized data obtained previously, sequentially perform data integrity verification and consistency checking. First, make a point-by-point comparison of the number of records and the theoretically expected number of samples per second. If it is found that the number is lower than a certain proportional threshold of the number of records that should be collected, for example, 10% as an empirical threshold, it is determined that the integrity is insufficient and a missing record mark is added to the system. At the same time, match the time series of the temperature, pressure, and position data to check whether they are arranged in sequence at each moment and there is no cross-coverage. If it is detected that multiple different measurement values appear repeatedly at the same moment, select the most credible group by comparing with the measurement habits under the same conditions in the factory historical operation log or by the similarity of the values at the previous and subsequent moments, or perform merging according to the stable output error range of this sensor. For example, if a pressure sensor gives two values at the same moment and the device document of this sensor states its error range, retain the record that is closest to the trend at the previous and subsequent moments, mark the other item as a duplicate value and delete it. After all duplicate or conflicting records are cleared, obtain standardized sensor data that passes the integrity and consistency checks.

[0054] The steps to obtain the sensor data fusion framework are as follows: Based on the standardized sensor data, align all sensor data according to the timestamp, perform clustering on the data to form a unified data structure, and obtain preliminary integrated data;

[0055] Based on the preliminary integrated data, filter the noise in the data, use statistical identification and correct the outliers in the data to obtain enhanced integrated data;

[0056] Based on the enhanced integrated data, combined with the data source, timestamp accuracy, and sensor type, a fused sensor data framework is obtained.

[0057] Specifically, according to the standardized sensor data obtained previously, first, the temperature, pressure, and position records at the same moment or within an adjacent 0.1 second are uniformly regarded as the same time slice based on the timestamp. At this time, if it is found that some records exceed this alignment range, they are regarded as independent time slices or adjusted according to the recommended error in the device description. Next, clustering processing is performed on the aligned records. For example, if the distance-based grouping method is used, the Euclidean distance between the sensor readings within the same time slice can be calculated first. If this distance is less than the threshold , then these sensor readings are clustered into one category, where can be determined by analyzing the stable intervals of temperature and pressure during the previous operation of the factory and combining the on-site location distribution. For example, during the test phase, the sensor readings are collected for one week first and the average interval among them is calculated, and let be used as the initial reference. When it is found that the temperature and pressure dispersion within some categories is too large after clustering, then the threshold is corrected to decrease to 0.03 or less. After the sensor readings within each time slice are divided into several groups according to similarity, the temperature, pressure, and position records within each group are used as a comprehensive record and the results are recorded in a unified data structure. If the temperature or pressure difference among the readings in a certain group exceeds the floating limit calculated from the historical stable range in advance, for example, the temperature is allowed to float no more than , and the pressure is allowed to float no more than , then this group is subdivided or marked as possibly having a cross-region phenomenon. Finally, the clustering information of all time slices is integrated to obtain the preliminary integrated data.

[0058] According to the preliminary integrated data obtained previously, noise filtering is performed on the records therein in turn. If the temperature or pressure within a certain record shows continuous sudden jumps within a short time interval and deviates from the average value of other records in the same category by more than three standard deviations, it is regarded as noise interference. Here, the three standard deviations can be obtained by calculating the standard deviation of the historical readings of this category and letting the threshold be to determine. If the temperature satisfies It is then marked as a noise candidate point. Similarly, the same judgment is made on pressure and position. For the records that have been determined to be noise, interpolation or the median of similar records can be used for replacement. Then, statistical identification is performed on the replaced data to check whether there are still large fluctuations at this moment. If it still exceeds the above empirical threshold, correction is carried out again. During this process, manual verification will also be carried out on the records with continuous anomalies. The manual verification threshold can be determined by the longest continuous abnormal time period in the historical curve. For example, if continuous abnormal values of a certain sensor were observed during past operations for 3 seconds, 3 seconds will be regarded as a suspicious interval for additional confirmation. After the above corrections are completed, the corrected data at each moment is summarized and associated according to the previous grouping structure. If a certain group still cannot maintain a relatively close distribution to the records in the same group after compensation, it is re-split into a new group and verification is performed again. After all records have completed noise filtering and anomaly correction, a new integration result is formed to obtain enhanced integrated data.

[0059] Based on the enhanced integrated data obtained previously, corresponding index mappings are established in combination with the data source, timestamp accuracy, and sensor type. For example, temperature readings are distinguished according to whether they come from high-temperature area devices or normal-temperature area devices and their timestamp accuracy is marked as 0.1 second or 0.5 second. Pressure readings are divided into intervals with different maximum pressure-bearing ranges, such as 0 MPa to 2 MPa and 2 MPa to 4 MPa. Position readings are disassembled into different production line segments according to the factory layout. Subsequently, source tags and accuracy tags are added to each record in tabular form. When reading the records, the corresponding accuracy type will be automatically matched according to the source and secondary verification will be carried out. If it is found that the timestamp accuracy does not match the set value, the alignment correction amount is recalculated according to the error range in the corresponding sensor description. If multiple records in the same source are repeatedly identified, the one with the highest stability is selected as the final record. After all data is summarized and mapped in this way, the data items of temperature, pressure, and position are incorporated into a unified index system, enabling subsequent retrieval to quickly locate through the timestamp or sensor type. Finally, a fused sensor data framework is obtained on this basis.

[0060] The steps to obtain the preliminary event association result are as follows: Based on the fused sensor data framework, the temperature measurement data sequence of the temperature sensor and the pressure measurement data sequence of the pressure sensor are extracted and arranged in the time order of data acquisition. The time increment is calculated for the temperature measurement data sequence, and the instantaneous change rate is calculated for the pressure measurement data sequence to obtain the preliminary event data stream;

[0061] According to the preliminary event data stream, calculate the data mutation intensity index. The calculation formula is:

[0062]

[0063] where, is the data mutation intensity indicator, is the time increment of the temperature measurement data series, is the instantaneous rate of change of the pressure measurement data sequence, is the cross-change rate of the temperature measurement data sequence and the pressure measurement data sequence, is the smoothed rate of change of the temperature measurement data sequence, is the cumulative change difference of the pressure measurement data sequence;

[0064] Based on the data mutation intensity index, the data stream event pattern is defined and implemented, the change threshold of the temperature measurement data sequence and the mutation standard of the pressure measurement data sequence are set, the data mutation intensity index is classified and event pattern matched, the event types that meet the conditions are identified, and the preliminary event association results are obtained.

[0065] Specifically, according to the fusion sensor data framework obtained above, first extract the temperature and pressure related entries in its records, gradually read the temperature measurement data sequence and pressure measurement data sequence corresponding to each moment, and sort all moments according to the time standard used in the industrial field. If the time difference between some measurement data is less than 0.02 seconds, they are regarded as the same instantaneous record and marked as the same entry. When the temperature measurement data sequence is in place, the recording time between each consecutive entry is subtracted to obtain the time increment of the temperature measurement data sequence. For example, when extracting, if the timestamp of the previous entry is 152.20 The timestamp of the current entry is 152.23 seconds, so its time increment is recorded as 0.03 seconds. When the field equipment runs faster and the sensor sampling frequency is high, smaller time increment values may also appear. These smaller intervals are also recorded. In the subsequent judgment process, it will be confirmed whether there is an overly tight or abnormal distribution. For the pressure measurement data sequence, it is necessary to extract the numerical difference between adjacent entries and divide it by the corresponding time increment to calculate the instantaneous change rate. For example, in the adjacent entries, the pressure value rises from 1.20MPa to 1.25MPa, and the time difference between the two is 0.05 seconds. The instantaneous change rate can be calculated as MPa / second. If the pressure changes dramatically in a short period of time and exceeds the floating threshold set in the historical record, for example, if it exceeds 0.5MPa / second, the record will be marked as an abnormal candidate. The threshold can be set by comparing the factory's pressure equipment instructions with the monitoring records of the past 100 hours. For example, the maximum normal pressure change rate obtained in the past 100 hours is about 0.4MPa / second, so 0.5MPa / second is selected as an empirical threshold. After completing the time series calculation and instantaneous change rate analysis of all temperature and pressure entries, the corresponding relationship between the temperature time increment and the instantaneous change rate of pressure at each moment is obtained, and finally integrated into a complete record sequence to obtain a preliminary event data stream.

[0066] The benefit of the formula is that by incorporating the product of the time increment and the instantaneous pressure change rate into the square root operation and combining it with the cross-change rate of temperature and pressure, along with the deviation between the smooth change rate and the cumulative change difference, it can quantify the degree of mutual influence between temperature and pressure within a short time period. This quantification method encompasses the combined contributions of time resolution characteristics and differences in different dimensions in multi-dimensional monitoring data, providing a more detailed evaluation basis for subsequent anomaly detection and event recognition in actual industrial scenarios.

[0067] The steps for obtaining the parameter are as follows: It is necessary to read the temperature measurement data sequence records one by one from the preliminary event data stream obtained previously, and perform a difference operation on the timestamps between adjacent entries. If the timestamp of the previous record is and the timestamp of the subsequent record is , then , when the industrial field sensor collects data at a sampling frequency of 1 second, most is about 1 second. In some cases, if the sensor has a high-frequency data collection requirement, an interval of 0.2 seconds or less may occur. For example, in a certain test, three on-site sensors send 5 measurement data per second. After arranging them, we can get seconds. If it is detected that some time intervals deviate significantly from the normal range, the record can be corrected according to the maximum time error specified in the factory equipment instructions. The following example is used to demonstrate the acquisition method. In a two-hour monitoring period, the sensor records a total of 720 temperature data, and each data corresponds to a timestamp. If the time difference between the 250th record and the 249th record is 0.22 seconds, it can be recorded as seconds.

[0068] The steps for obtaining the parameter are as follows: It is necessary to calculate the instantaneous change rate one by one in chronological order in the pressure measurement data sequence. If the pressure value of the previous record is , and the pressure value of the current record is , then , where corresponds to the temperature time interval that coincides with the time of this pressure record. If the industrial field pressure change range is between 0 MPa and 4 MPa, the pressure values at different times can be read, subtracted from the pressure value of the previous moment, and then divided by the corresponding to obtain the specific value of each instantaneous change rate. For example, in a certain monitoring, the pressures of the 120th record and the 119th record are 1.80 MPa and 1.75 MPa respectively, and the time interval is 1 second, then MPa / second.

[0069] The steps for obtaining the parameters are as follows: the cross-changes between the temperature measurement data sequence and the pressure measurement data sequence in the same period need to be reflected. The temperature change and pressure change in each time period can be multiplied by a position correlation coefficient. If the position sensor record shows that the device position remains unchanged during this period, the position correlation coefficient can be 1. If the position switches, 0.8 or other empirical values can be used. The specific quantification method can be based on the formula: ,in is the position correlation coefficient, which needs to be calculated based on the previously obtained position data and the classification of the field area. For example, in the equipment installation document, it is recorded that the change correlation strength between the temperature and pressure in area A of the production line is 0.85, and that in area B is 0.9. By querying the position data at that moment, it is determined that the record is located in area B, so , assuming (here "for example" replaces "assuming") that the temperature changes from becomes , the pressure changes from 1.65MPa to 1.68MPa, then .

[0070] The steps to obtain the parameters are as follows: the smooth change rate of the temperature measurement data sequence needs to be estimated. The average slope of the temperature change in each time window can be taken, and then weighted according to the volatility. If in the past 10 consecutive samples, 9 temperature sampling points have increased continuously, and the increment amplitude is within If the smoothing rate of change is within If the sequence is still in the same area, it is multiplied by a small range coefficient. For example, the small range coefficient can be between 0.7 and 0.9. The specific value can be obtained by statistically analyzing the fluctuation characteristics of temperature sampling in different working intervals. When the statistical results show that the average increment of temperature sampling for 10 consecutive times is If the temperature difference is within 0.8, you can select 0.8 as the small range coefficient. For example, in one monitoring, the total temperature difference of the past 10 samplings is , and the total time interval between the 10 sampling points is 10 seconds, then the basic smoothing value is , then multiply by 0.8 .

[0071] The steps to obtain the parameter, which represents the cumulative change difference of the pressure measurement data sequence, can perform an accumulation process within a monitoring period. Specifically, the difference between each record and the initial record can be accumulated, and then compared with some smaller time periods during the intermediate process. If the cumulative amount exceeds a certain threshold, it indicates that there is a relatively obvious superimposed fluctuation in the pressure. The threshold can be determined in combination with the maximum working range of the device. For example, the normal pressure difference cumulative amount indicated in the factory manual is about 1.0 MPa. Therefore, 1.2 MPa can be selected as the threshold when analyzing on-site data. For example, during a 12-hour monitoring, record the average pressure per hour and accumulate the difference relative to the initial moment in sequence. If the cumulative total reaches 0.6 MPa at the 6th hour and 1.3 MPa at the 12th hour, then at this time exceeds the set threshold of 1.2 MPa. The specific calculation method is to record at each hour subtract and then sum. If the result is greater than 1.2 MPa, then mark the of this time period as 1.3 MPa and record it.

[0072] Substitute the parameter into the formula to calculate 0.06497. This result indicates that during this time period, the combined action amount between the temperature-time increment and the pressure instantaneous change rate is relatively small, and there is no significant temperature-pressure coupling mutation. If E is greater than 1.0, it indicates an obvious mutation. If E is between 0.1 and 1.0, it is in the general change range. When it is less than 0.1, it can be regarded as stable. According to the on-site situation, hierarchical management can be carried out, and further identification of the event type can be carried out subsequently.

[0073] Based on the data mutation intensity index E obtained previously, it is necessary to compare according to the temperature measurement data sequence change threshold and the pressure measurement data sequence mutation standard corresponding to different event types. If the increment of the temperature measurement data sequence at adjacent moments exceeds the temperature rapid change threshold recorded in the industrial manual (for example, set as per second) and the calculation result of E is simultaneously higher than 1.0, it is initially identified as an event concurrent with temperature surge and pressure fluctuation. If the mutation standard of the pressure measurement data sequence is obtained from the on-site operation record, and after statistically analyzing the maximum stable change rate in the past 72 hours, a slightly higher value is taken as the evaluation benchmark (for example, taking 0.5 MPa / second as the empirical benchmark value). When it is detected that the pressure change rate at any moment exceeds this benchmark value and E is significantly greater than 0.8, it will be judged as a high-intensity pressure fluctuation event. When classifying these events, those that meet the dual conditions of temperature surge and pressure fluctuation are classified into the comprehensive event type, and those with only a single pressure mutation are classified into the single type event. Finally, by matching the event patterns and recording the time and type of each event occurrence, all time periods that meet the conditions are sorted out and summarized to obtain the preliminary event association result.

[0074] The steps to obtain the data relationship display diagram are as follows: Based on the preliminary event association results, extract each event node and the connection relationship, construct an event interaction matrix, and remove isolated event nodes to obtain an event relationship matrix;

[0075] According to the event relationship matrix, calculate the event centrality index. The calculation formula is:

[0076]

[0077] Where, is the event centrality index, is the event node and the event node The interaction frequency between them, is the node and The number of mutual responses between them, is the node and The number of new connections between them, is the node The total interaction time, is the node The number of projects participated in, is the number of event nodes in the current network;

[0078] Based on the event centrality index, construct an event association topological structure through graph theory, draw a node distribution diagram, and through the connectivity analysis between nodes, screen the key event flow relationships to form a data relationship display diagram.

[0079] Specifically, based on the preliminary event association results obtained previously, it is necessary to retrieve all the marked event information among them and disassemble the event identifiers and the association records between events. When organizing, first summarize each event identifier with its corresponding time occurrence interval, and at the same time read the interaction description entries between these events. For example, if the mutual influence frequency or time overlap degree of multiple events is recorded during the monitoring period, it is regarded as an event connection relationship once and the respective interaction basis is noted in the table. If some events do not have any time overlap with other events or the interaction frequency is lower than the empirically set threshold, such as less than 2 times, they are marked as isolated event nodes and removed. This empirical threshold can be determined by combining the statistical results of historical monitoring. For example, after analyzing the event interactions hour by hour in the past 72 hours, it is found that the nodes with an interaction frequency lower than 2 times have no significant reference value, so this value is set to 2 times. After all event nodes and their connection relationships are extracted, an event interaction matrix is constructed for the remaining mutually associated nodes. The rows and columns of this matrix correspond to each event identifier respectively, and each cell in the matrix is used to record the interaction intensity or association description entry between the event corresponding to the row and the event corresponding to the column. If different levels of interactions are found between events in the monitoring log, they can be recorded hierarchically in the same cell. For example, the number of time overlaps and the interaction frequency can be filled in separately. After the entire matrix is completed, scan all the row and column elements between nodes to check for duplicate markings or empty records, merge the duplicate markings, and note that the empty records indicate no valid interaction. Finally, remove the nodes that do not have sufficient interaction support and obtain the event relationship matrix.

[0080] The advantage of the formula is that it simultaneously takes into account multiple interaction factors occurring between event nodes and constructs the denominator term through the total interaction time and the number of projects participated by the nodes. In this way, it can quantify the comprehensive activity level and connection attributes of the nodes in the entire network structure. When a certain node has a high interaction frequency, the number of new connections, and the number of responses, it will show an additive increase in the numerator part, while the high number of projects participated is corrected by the logarithmic term in the denominator, thus taking into account the balance between the interaction breadth and the activity.

[0081] The steps for obtaining the parameter are as follows. This parameter represents the interaction frequency between the event node and the event node and needs to search in the previously obtained event interaction matrix or relevant records for the number of times the interaction between the node and For co-occurrence, if it is found that there are 5 associations within the same hour, then , in specific implementation, it is necessary to collect statistical values from the aforementioned 72-hour or longer period, and add up the interaction frequencies within all time windows as the final , for example, within a monitoring period, the interaction frequencies of two event nodes within 4 hours are 2 times, 3 times, 1 time, and 4 times respectively, then the total is 2 + 3 + 1 + 4 = 10. At this time .

[0082] The steps for obtaining the parameter are used to reflect the nodes and nodes The number of mutual responses between them needs to be further subdivided on the basis of interaction frequency statistics. If two event nodes not only appear within the same time period, but also there are multiple reciprocating records of mutual responses between them, then such reciprocating responses can be regarded as mutual responses. Set a recognition interval when recording. For example, set continuous mutual access within 30 seconds as the same response chain. If it is found within 1 minute that node sends 2 trigger signals to node and node also generates 2 responses to node , then this can be regarded as 4 responses, and finally accumulate to obtain the total number of responses. For example, within a monitoring period, the number of responses of two event nodes is accumulated to 12 times after statistics, then .

[0083] The steps for obtaining the parameter are that it represents the number of new connections between nodes and nodes . This requires regarding the interaction that first appears within the current monitoring period as a new connection, and no longer counting the interactions that occur repeatedly into the new connections. When collecting relevant records, an initial identifier can be set for each pair of nodes. If it is first detected that there is an association between node and node , it is counted as 1 new connection. After that, if the same type or same-time period association is observed again, it is regarded as a continuous connection and not counted into the new connections. If the on-site set monitoring period is 12 hours, then the number of times of the first interaction of each pair of nodes within these 12 hours can be counted. For example, by traversing the data log within 12 hours, if it is found that there are 3 newly occurred associations between node and node , then record .

[0084] The steps for obtaining the parameter are that it represents the total interaction time of node , which requires recording the node The duration of each interaction within the monitored period, and accumulate these durations to obtain the total interaction time. For example, in the monitoring, it is set that each event interaction record has start and end timestamps. If a node is continuously active between 10:00 and 10:05 in an interaction, its duration is 5 minutes. If it is active between 11:15 and 11:20 in another interaction, add another 5 minutes. If such interactions occur multiple times, further accumulate. For example, within 24 hours, it is monitored that the node has 6 interactions, with durations of 3 minutes, 5 minutes, 2 minutes, 4 minutes, 6 minutes, and 5 minutes respectively. The sum is 3 + 5 + 2 + 4 + 6 + 5 = 25 minutes. At this time .

[0085] The steps to obtain the parameter are as follows. It represents the number of projects participated by the node . The project list it contains can be viewed in the background information or monitoring records of this node and counted. For multiple parallel projects in the industrial field, if the node participates in event management on multiple production lines or multiple devices successively or simultaneously, then summarize and count all these project numbers. For example, a certain node participated in three production line projects and one maintenance project in the recent week, then it can be counted as 4 participated project numbers. If a new safety inspection project is added to the node during a certain expansion, then add 1 more, forming a new summary value of 5.

[0086] Substitute the parameter into the calculation to get 0.0808. This result indicates that the node shows a moderate centrality level in the current monitoring network. When AC is greater than 1.0, it means that its interaction participation and response are relatively intensive and the number of participated projects is relatively small. When it is less than 0.5, it means that its interaction in the network is relatively limited. Therefore, when analyzing the event flow direction, nodes with higher AC values can be given priority attention to identify active connection areas or frequently recurring event combinations.

[0087] Based on the event centrality index obtained previously, it is necessary to create an associated topological distribution for all nodes from a graphical perspective. First, arrange all nodes in descending order according to their centrality index. If the centrality index is greater than 1.0, mark the node as highly active. If it is between 0.5 and 1.0, consider it as a node in the normal range. If it is less than 0.5, mark it as having sparse interactions. When drawing the node distribution diagram, set more prominent shapes or colors for nodes with high centrality indices, and draw connection lines between each node. For event nodes with significantly high previous interaction frequencies, the connection lines between them can be distinguished by thicker lines. After completing the preliminary diagram, perform a connectivity analysis on the connection relationships between nodes according to on-site monitoring requirements. For example, count the number of lines between nodes one by one. When the number of connection lines exceeds a certain threshold (e.g., 5 lines), it is considered a tight connection. When the number of connections between nodes is less than 2 lines, it is considered a loose connection. Finally, sort out the high-connectivity node groups and their flow relationships, arrange all high-connectivity events in the formed flow order and record them in the associated schematic table, and finally screen the key event flow relationships to form a data relationship display diagram.

[0088] The steps to obtain the critical path analysis result are as follows: According to the data relationship display diagram, calculate the critical path optimization index. The calculation formula is:

[0089]

[0090] Among them, is the critical path optimization index, is the traffic data of node , is the shortest path length from node to the critical node, is the buffer size of node , is the processing speed of node , is the number of connections of node , is the data load of node , is the traffic volatility of node , is the number of nodes on the path;

[0091] Based on the critical path optimization index, identify potential bottlenecks and key transmission nodes in data transmission, analyze which nodes and connections affect the data flow efficiency, and obtain the critical path analysis result.

[0092] Specifically, the advantage of the formula lies in integrating multiple indicators such as the traffic data of nodes, the shortest path length, buffer size, processing speed, number of connections, data load, and traffic volatility into the same operation system. The sum of the numerator reflects the impact of multiple factors on path efficiency, and the denominator is normalized and corrected by the square root of the total traffic volatility. Thus, in a multi-node linkage environment, it is possible to more clearly identify which nodes have a more significant impact on the data flow efficiency along the entire path. At the same time, the bandwidth carrying capacity and load pressure in the actual scenario are fully covered at the numerator end, helping to identify potential bottlenecks in the overall industrial data transmission scenario.

[0093] The steps to obtain the parameter are as follows: This parameter represents the traffic data of the node, and it is necessary to cumulatively count the input and output traffic of the node within the specified monitoring period in the industrial network environment. For example, select a 12-hour monitoring period and accurately record the incoming and outgoing traffic values (in Mbps or MB / s) of the node every hour. Then, sum up the incoming and outgoing traffic values within this monitoring period, and eliminate the duplicate entries according to the actual transmission protocol if necessary. If there are peer-to-peer connections, duplicate statistics need to be excluded. After obtaining a total sum, it can be averaged to the per-second or per-minute level to obtain a stable value. For example, if it is observed that the node transmits a total of 432000 MB of data in 12 hours, then 432000 MB can be divided by (12 hours × 3600 seconds) = 43200 seconds, and finally it is approximately 10 MB / s.

[0094] The steps to obtain the parameter are as follows: This parameter represents the shortest path length from the node to the key node. Usually, in the industrial network layout, the topology between different nodes is statistically analyzed. Here, the shortest path length can be represented by the number of hops or the physical distance between nodes. The number of hops refers to the number of levels of relay devices between nodes, and the physical distance is the total sum of the physical cables or wireless transmission distances between nodes. For example, when using the number of hops as the length measurement, when the node can reach the key node after passing through 3 forwarding devices, then , if the distance (in kilometers) is used for actual monitoring, the total distance from this node to the key node can be obtained by adding up the lengths of each cable and used as . In terms of the acquisition method, the link table of each cable and switch can be sorted out during the topology planning stage. Search each item in this table for all feasible paths from the node to the key node and find the one with the fewest hops or the shortest distance, and then register this value as , for example, the node is recorded during on-site research has a physical transmission distance of 6 kilometers from the key node. Since other paths are farther due to detours or have more hops, 6 kilometers is selected as .

[0095] The steps to obtain the parameter are as follows: This parameter is the buffer size of the node, which represents the maximum capacity of the node to temporarily store data packets. The unit is usually MB or GB. It needs to be checked in the hardware specification of the node device or the system configuration file. It can also be obtained by actual queuing tests to get the real-time available capacity. For example, in a factory network, a core switch device may have a buffer of 512MB or 1GB, while edge devices usually only have 256MB or less. Specifically, it still needs to be verified through tests. If in a continuous transmission stress test, a large number of data packets are continuously sent to the node using the traffic injection method. During this period, record the cache usage when the node starts to lose packets, and then obtain the peak value of the available buffer. When it is finally counted that the node has used 490MB of cache before approaching packet loss, and the hardware description also indicates that the upper limit is 500MB, then can be recorded as 500MB.

[0096] The steps to obtain the parameter are as follows: This parameter is the processing speed of the node, which needs to be comprehensively measured by combining multiple indicators such as the CPU core frequency and network forwarding ability of the node. The typical unit can be Mbps or MB / s, or it can also be characterized by the data packet processing volume (such as p / s). Specifically, it depends on the role of the node in the industrial network. If the node is a switching device, the maximum tolerable data volume can be continuously input to this node in a 12-hour stress test and its stable processing rate can be counted. For example, record that the node can continuously process a traffic of 300MB / s without serious queuing, then = 300MB / s. In the field, to avoid fluctuations, multiple stress tests are usually carried out and the average value is taken and then a safety discount is made. For example, the average value measured multiple times can reach 350MB / s. Considering that short-term peaks may cause queuing, it can be recorded as 300MB / s in the parameter setting.

[0097] The steps to obtain the parameter are as follows: This parameter is the number of connections of the node, which represents the number of nodes directly connected to the node in the network. When each node in the factory network has a unique identifier and its upstream and downstream devices are clearly recorded in the topology table, the number of neighbor nodes directly connected to the node can be counted by scanning the topology table. For example, during a network inspection, it is found that the node In a direct connection state with eight devices, including the upper-level switch, switches at the same level, or other parallel nodes, then = 8.

[0098] The steps to obtain the parameter are as follows: This parameter is the data payload of the node, which generally refers to the comprehensive amount of data processing borne by the node during the monitoring period and the amount of data queuing in the current cache. It is possible to continuously monitor the traffic in and out of the node and the internal cache situation in actual industrial applications, and then convert it into an average load or instantaneous load value. For example, during 24 hours of observation, it is recorded that the average amount of data in the processing queue per second of the node is approximately 200 MB, and it once reached 500 MB during the peak period. After referring to the hardware documentation, the weighted average of multiple measurement values can be taken to obtain a stable value. For example, it is obtained that = 300 MB.

[0099] The steps to obtain the parameter are as follows: This parameter is the traffic volatility of the node. It is necessary to quantify the amplitude or change rate of the traffic fluctuation within the monitoring period, and the standard deviation or coefficient of variation can be used for analysis. For example, for the node record the transmission rate per minute within 12 hours, and split it into 720 sampling points, which are respectively recorded as , first calculate the average value of these sampling points, then calculate the deviation of each sampling point from the average value, then divide the sum of the squared deviations by the total number of sampling points to obtain the variance, and take the square root of the variance to obtain the standard deviation. Then use or directly use, and select the volatility index within a reasonable range. For example, if the average transmission rate of the node is 200 MB / s and the standard deviation is approximately 40 MB / s, then it can be set that .

[0100] Calculation process:

[0101] The first step is to calculate the numerator , for example, when the path contains nodes, the following values are obtained respectively (the units and formats need to be unified in advance):

[0102]

[0103]

[0104]

[0105]

[0106] Calculate the sum of the three items for each node in sequence:

[0107] Node 1:

[0108]

[0109] Node 2:

[0110]

[0111] Node 3:

[0112]

[0113] Node 4:

[0114]

[0115] Add the above results:

[0116]

[0117] In the second step, calculate the denominator , for example, the traffic volatility of these 4 nodes is measured respectively , then:

[0118]

[0119]

[0120] In the third step, combine the numerator and the denominator to obtain the critical path optimization index :

[0121]

[0122] The result shows that when the value exceeds 2.0, it indicates that the entire path still maintains a high comprehensive availability after considering multi-dimensional indicators such as traffic, cache, processing speed, number of connections, data load, and volatility. If it is found in subsequent evaluations that is lower than 1.0, it means there is a conflict between traffic and load, and the buffer capacity or processing capacity of the nodes needs to be carefully checked. If is between 1.0 and 2.0, it can be regarded as having a certain optimization space. By reasonably adjusting the shortest path selection or the load distribution of each node, the data transmission efficiency of the industrial network can be improved and potential bottlenecks can be avoided.

[0123] Based on the critical path optimization index K obtained previously, during the on-site scheduling of the industrial network, it is necessary to centrally compare the node values in all paths, and cross-compare the traffic data of each node with the shortest path length, cache occupancy ratio, and processing rate information according to the calculation result of K. In this process, first open the node topology table drawn in the previous stage, retrieve the actual traffic usage of each node item by item, and extract the currently used capacity of the buffer corresponding to each node. If it is found that the buffer occupancy of some nodes continuously exceeds the on-site experience threshold during multiple monitoring periods (for example, when it reaches 400MB, it is considered a high-load interval), record the corresponding high-load periods and the front and rear transmission nodes associated with the node. After listing them, combine with the K value for comparison. If the K value of a certain node is close to or greater than 2.0, but the actual traffic is still on an increasing trend, it indicates that the network path may tend to be busy but has not yet entered the bottleneck. If the K value is between 1.0 and 2.0, and it is also found during the listing process that its processing speed fluctuates in the front and rear periods, then the traffic trend and data load of this node can be followed up in detail, and at the same time check whether the number of connections has reached the on-site threshold (for example, more than 10 connections will be marked as connection-intensive nodes). Through this comparison, on-site operation and maintenance personnel can sort out the transmission lines one by one, and mark in the topology table which nodes have gathered more connections or experienced high traffic fluctuations. Finally, these nodes are located as potential bottlenecks and the cache accumulation phenomena that occurred during the relevant periods are focused on for sorting. For nodes with a relatively large shortest path length, consider whether to reduce the connection hops by replacing a closer forwarding link. For nodes with too high data load, coordinate with surrounding nodes to share the traffic. When multiple nodes meet the high traffic fluctuations, analyze the peak synchronization situation of their mutual influence. Once it is confirmed that there is a phenomenon of simultaneous arrival of peaks, record it. Finally, comprehensively summarize the list of all key nodes and connections, and it is possible to form a judgment on which data connections are most likely to be blocked and which nodes affect the data flow efficiency on the critical path, and obtain the critical path analysis result.

[0124] The steps to obtain the optimized data processing flow are as follows: Based on the critical path analysis result, extract the node-to-node delay, bandwidth usage, and packet loss rate of the data stream to obtain the data path parameters to be optimized;

[0125] According to the data path parameters to be optimized, calculate the path optimization priority, and the calculation formula is:

[0126]

[0127] where, is the path optimization priority, is the path bandwidth occupancy ratio, is the path packet loss rate, is the path The average transmission time is the delay of path and is the jitter value of path .

[0128] Based on the path optimization priority, adjust the transmission strategy of the data stream, reallocate the traffic load, and generate an optimized data processing flow.

[0129] Specifically, based on the critical path analysis results obtained previously, it is first necessary to check the delay metrics between each node and node in the actual usage scenario of the industrial network. For example, use test data packets to record the round-trip delay one by one and summarize the recording results in chronological order. If it is found that the delay between certain nodes exceeds the pre-set maximum tolerance value, such as 8 milliseconds, it is marked as a high-delay area. At the same time, collect the bandwidth usage situation. The bandwidth occupancy of each link can be measured in the monitoring software, and compare the average and peak bandwidth occupancy in the past 24 hours. If the peak has been maintained at 90% or more occupancy for more than an empirical threshold, such as 30 minutes, it is registered as a bandwidth-intensive link. Record the specific links where these nodes are located and include the measured bandwidth peak in the list. For the packet loss rate, continuous sequence data can be sent within the same monitoring period and the proportion of the number of lost packets to the total number of packets can be statistically calculated. If the loss rate exceeds the preset standard (such as 1%), it is regarded as a potential congestion point. When comparing the packet loss rates of each node, it is also necessary to make a horizontal comparison in combination with the actual transmission volume of each node. When multiple nodes have a high packet loss rate in the same period, it is necessary to determine whether they come from the same link or adjacent links. If a significant increase in packet loss is observed in multiple links, it is necessary to further check whether it is limited by the processing performance of upstream devices or the line quality. Finally, summarize the delay, bandwidth occupancy, and packet loss rate data of all nodes to form a comparable list of entries, and classify these entries as main transmission nodes or auxiliary connections, and at the same time verify whether they correspond to the previously recorded high-traffic fluctuation areas. If some nodes have both a delay significantly greater than 8 milliseconds and a packet loss rate exceeding 1%, they are marked as key nodes to be concerned. After comparing all nodes and links, the high-delay links, high-bandwidth occupancy links, and high-packet loss links can be color-coded using the original topology structure for easy viewing in the graphical interface, and the marked information is summarized into the data path parameters to be optimized to obtain the data path parameters to be optimized.

[0130] The advantage of the formula is that it incorporates several key metrics, namely the bandwidth occupancy ratio, packet loss rate, average transmission time, latency, and jitter value, into a single expression. It quantifies the product of the difference between the bandwidth and the packet loss rate and the transmission time in the numerator, and normalizes it by taking the square root of the sum of the latency and jitter value in the denominator. This allows for a more intuitive measurement of the priority order of the path in terms of overall transmission performance. When the bandwidth occupancy ratio is high and the packet loss rate is low, the overall numerator value is larger. However, if there is high latency or jitter simultaneously, it will increase the denominator. Therefore, the final comprehensive priority can achieve a balance among multiple dimensions.

[0131] The steps to obtain the parameter are as follows: This parameter represents the bandwidth occupancy ratio of the path and it is necessary to conduct time-segmented statistics on the bandwidth usage of the path during the observation period and calculate the ratio with the rated bandwidth upper limit of this path. For example, in an industrial Ethernet link, the rated bandwidth may be 100 MB / s. If it is found during monitoring that the average data transmission reaches 80 MB / s within two consecutive hours, and the short-term peak can reach 90 MB / s, then the occupancy ratio can be calculated to be close to during a certain period. To obtain a more stable , it is necessary to integrate the statistical results of different periods, or the weighted average method can also be used. For example, if the bandwidth occupancy is statistically counted hourly within 8 hours and 8 values are obtained as , then the arithmetic mean is approximately 0.74.

[0132] The steps to obtain the parameter are as follows: This parameter is the packet loss rate of the path and it is necessary to calculate the loss ratio by sending a known number of packets and counting the number of successfully received packets recorded by the receiver. If 10,000 packets are sent in a link and only 9,950 are successfully received, then the loss rate is . To ensure accuracy, tests are usually conducted in multiple periods while excluding extreme situations. If several transmission tests of 10,000 packets each are carried out within 24 hours and the recorded packet loss rates are , then the average of these values can be obtained as .

[0133] The steps to obtain the parameter are as follows: This parameter represents the average transmission time of the path and it is necessary to record the start and end timestamps and calculate the difference during each data transmission, and then calculate the average by combining the multiple transmission durations within the entire monitoring period. For example, when conducting large-scale file transfers on an industrial field link, each file size is the same at 500 MB and 10 transfers are carried out successively. The time taken for each transfer is recorded as Seconds, sum up these values and then divide by 10 to obtain the average value Seconds, and then it can be recorded as .

[0134] The steps for obtaining the parameter are as follows: This parameter is the path of the time delay. The round-trip delay can be detected by means such as ping or trace, or it can be recorded based on the built-in delay monitoring instrument in the industrial production environment. After collecting several one-way or round-trip delay values within a certain period of time, they can be averaged or a relatively stable median can be taken as , for example, perform a test every 10 seconds for 30 minutes to obtain 180 delay values. It is statistically found that most of them are concentrated around 5 milliseconds, with a maximum of 9 milliseconds and a minimum of 4 milliseconds. Sum up all the values and divide by 180 to obtain an average time delay of about 5.3 milliseconds, and then it can be recorded as .

[0135] The steps for obtaining the parameter are as follows: This parameter is the path of the jitter value, which refers to the fluctuation amplitude of the delay between different moments. It can be obtained by calculating the standard deviation of the delay or the maximum-minimum delay difference. For example, after obtaining 180 delay values in 30 minutes, calculate the average delay , and then calculate the difference between each sample and and sum the squares. After obtaining the variance, take the square root to get the standard deviation, or directly take the difference between the maximum and minimum values of the delay. In industrial scenarios, the standard deviation method is more commonly used. If the statistical result shows that the standard deviation of these delay values is 1.2 milliseconds, then can be obtained.

[0136] Calculation process: First step, calculate the numerator , for example , , , then

[0137]

[0138]

[0139] Second step, calculate the denominator , for example milliseconds, milliseconds, then

[0140]

[0141]

[0142] Third step, combine the numerator and the denominator to obtain :

[0143]

[0144] The result shows that when is greater than 2.0, the bandwidth usage of the path is relatively sufficient with a low packet loss rate, and it has a certain advantage in the average transmission time. Even with a 5.3 - millisecond delay and a 1.2 - millisecond jitter, the overall priority is not significantly reduced. If is lower than 1.0, it means that key indicators such as the packet loss rate, bandwidth occupancy, or delay jitter of this path need to be focused on. And when is between 1.0 and 2.0, it belongs to the medium level, and the site can decide whether further optimization is needed based on the actual production requirements.

[0145] Based on the path optimization priority obtained previously, it is possible to check one by one in the network management system whether there is uneven load distribution on the path or a sharp increase in data volume during critical periods. During this process, first mark values for each recorded path, and then identify paths with values greater than 2.0 as high - priority, making them in a more flexible traffic adjustment mode in the congestion prevention strategy. Mark paths in the range of 1.0 to 2.0 as medium - priority, and start the backup scheduling plan when there is a situation exceeding a fixed duration (such as 30 minutes) or a bandwidth occupancy higher than 70%. If is lower than 1.0, it is regarded as low - priority. Check whether the current bandwidth resources are insufficiently configured or whether there is a situation where the packet loss rate is significantly higher than 0.5%. For these low - priority paths, the traffic distribution can be re - planned, and some large - traffic services can be transferred to other higher - priority paths, and confirm the feasible switching links between paths in combination with the topology map. If it is found during the analysis that some nodes are at the intersection of multiple low - priority paths, additional performance detection is required and whether there are hardware failures or connection abnormalities needs to be investigated. After completing the above investigations, a new data stream distribution plan is formed, and the new transmission delay and packet loss rate are recorded to verify the distribution effectiveness. Finally, through multiple corrections and records, a traffic load distribution method beneficial to the factory's business needs is gradually sorted out, and an optimized data - processing process is generated.

[0146] The specific steps to apply the optimized data - processing process to real - time data monitoring and present the data visually in real - time on the operator's visual interface in combination with augmented reality are as follows:

[0147] According to the optimized data - processing process, select the transmission rate, the occurrence frequency of abnormal events, and the data integrity detection results to generate the input configuration for real - time data monitoring;

[0148] The input configuration through real-time data monitoring is converted into digital displays of dynamic charts and performance metrics, generating a visualized data stream;

[0149] The visualized data stream is dynamically projected into the operator's augmented reality vision to display the data view.

[0150] Specifically, according to the optimized data processing flow obtained previously, first query the bandwidth allocation table and data stream allocation recorded therein, and compare the average value and peak information of the transmission rate in each period item by item with the bandwidth upper limit set in the previous round of monitoring. If the transmission rate is significantly close to the rated limit in several periods, it is marked as a high-load section, and the occurrence frequency of abnormal events corresponding to this period is extracted from the on-site monitoring configuration. For example, summarize the number of device alarms occurring per hour in the past 24 hours. If the number of alarms continuously exceeds the empirical threshold (e.g., more than 5 times per hour) in a certain period, then this period is regarded as a state of frequent abnormalities. The 5 - time threshold here can be determined by combining the alarm conditions in the previous week or a longer time range. Then, the types and occurrence times of abnormal alarms are refined and split, for example, distinguishing sources such as temperature overrun and pressure mutation, and mapping them to the previous data stream allocation records. After confirming a high degree of correlation, they are incorporated into the data source of the occurrence frequency of abnormal events. For the data integrity detection results, the previously formulated integrity verification requirements can be referred to. For example, it is stipulated that if the data loss or missing entries exceed 2% of the total number of entries in a batch transmission, it is defined as damaged integrity. When actually comparing the detection statistical table, if it is found that the integrity is damaged by more than 3% in individual periods, then this period is marked as a paragraph with low reliability. When integrating the above three indicators, classification needs to be carried out period by period or node by node, and through centralized summarization of the transmission rate, occurrence frequency of abnormal events, and degree of deviation from integrity, a set of detailed entries covering timestamps, device numbers, and event types is formed. Finally, by correlating these entries, the peak transmission rate, total number of alarms, and integrity indicators corresponding to each period are obtained, and thus combined into the input configuration of real-time data monitoring.

[0151] According to the input configuration monitored by the real-time data obtained previously, first match the high and low transmission rates and the types of abnormal events within the unified coordinate dimension respectively, and then segment the alarm frequency data with time as the horizontal axis. If the transmission rate within a certain specific period has reached more than 70% of the set bandwidth upper limit, and the cumulative number of abnormal events is greater than the empirically set threshold (for example, more than 3 per hour), then mark this period as the key analysis interval. Subsequently, take the proportion of non-compliant entries recorded in the data integrity detection and perform weighting. If the weighted proportion is greater than 1%, then give a hint of deepening the segment color during visualization. After integrating these time period nodes, a criss-crossing time series curve can be formed, and dynamic numerical displays are additionally superimposed on the curve. For example, the transmission rate is displayed on the left side of the vertical coordinate in units of MB / s, and the number of alarms is displayed on the right side. When the cursor stays at a certain time point, the specific percentage of the integrity detection can pop up. The digital display of performance indicators can be added with finer granularity. For example, within a 10-minute or 15-minute time step, the corresponding transmission rate fluctuation curve and event frequency histogram are plotted respectively. After completing these combinations, different alarm types (such as sudden temperature increase and pressure abnormality) are superimposed on the chart with different marks. If it is found that the same type of alarm occurs multiple times at the same node in a short period, the density is marked as increased. Finally, a dynamic chart that can automatically switch the screen over time and a digital display of performance indicators are generated to form a visualized data stream.

[0152] According to the visualized data stream obtained previously, it is necessary to load its chart and digital display layout on the augmented reality device actually used on-site. First, read the transmission rate broken line and alarm mark information corresponding to different nodes and map them to the coordinate positions in the AR scene. If the display area resolution of this device is 1920×1080 pixels, then arrange the curve graph of the transmission rate in the upper area, the alarm indication list in the right area, and present the dynamic progress bar of the integrity check in the lower area. When new data arrival is detected, the values of the corresponding time period will be refreshed. If the set bandwidth threshold is exceeded (for example, 80% utilization rate), the corresponding node position will be highlighted with a brighter color. At the same time, a text pop-up window listing the alarm types or counts of the current time period will be superimposed on the operator's visual interface. If the corresponding integrity anomaly exceeds 2%, color warning will be given at the lower progress bar. During the actual projection process, by tracking the operator's head orientation, when the operator's line of sight focuses on a certain node, the transmission rate and alarm values of this node in the past period of time can be viewed simultaneously. If you need to view historical data for a longer time, you can switch to the adjacent time period through a sliding gesture in the AR view and view the alarm log or integrity check details in more depth. After integrating all the visualization information, project this set of visualized data stream into the operator's augmented reality vision to display the data view.

Claims

1. An intelligent processing method for visualizing electronic information data, characterized in that, Including the following steps: Collect data from temperature sensors, pressure sensors, and position sensors in the factory, perform data cleaning and format standardization to obtain standardized sensor data; use data fusion to integrate the standardized sensor data into a unified data framework to generate a fused sensor data framework; Based on the fused sensor data framework, define and implement data flow event patterns, including temperature exceeding the threshold and pressure mutation, perform event detection and correlation analysis to obtain preliminary event correlation results; Analyze the preliminary event correlation results through graph theory algorithms to show the relationships between data and generate a data relationship display graph; Use the data relationship display graph to perform tracking and optimization analysis on the data path, identify key transmission nodes and potential data flow bottlenecks to obtain key path analysis results; Adjust the data processing flow according to the key path analysis results, optimize the data transmission and processing efficiency to generate an optimized data processing flow; Apply the optimized data processing flow to real-time data monitoring, combine with augmented reality, and visually present the data in real time on the operator's visual interface; The steps for obtaining the preliminary event correlation results are: based on the fused sensor data framework, extract the temperature measurement data sequence of the temperature sensor and the pressure measurement data sequence of the pressure sensor, and arrange them in the time order of data acquisition, calculate the time increment for the temperature measurement data sequence, calculate the instantaneous change rate for the pressure measurement data sequence to obtain a preliminary event data flow; According to the preliminary event data flow, calculate the data mutation intensity index, and the calculation formula is: Among them, is the data mutation intensity index, is the time increment of the temperature measurement data sequence, is the instantaneous change rate of the pressure measurement data sequence, is the cross-change rate of the temperature measurement data sequence and the pressure measurement data sequence, is the smooth change rate of the temperature measurement data sequence, is the cumulative change difference of the pressure measurement data sequence; Based on the data mutation intensity index, define and implement data flow event patterns, set the change threshold for the temperature measurement data sequence and the mutation standard for the pressure measurement data sequence, classify the data mutation intensity index and match the event patterns, identify the event types that meet the conditions to obtain preliminary event correlation results.

2. The electronic information data visualization intelligent processing method according to claim 1, wherein The steps for obtaining the standardized sensor data are: collect the original data from temperature sensors, pressure sensors, and position sensors in the factory, perform error checking and outlier screening for each type of sensor data, delete the error data and abnormal points to obtain preliminary cleaned data; Based on the preliminary cleaned data, adjust the data resolution and unify the timestamp format to obtain format-standardized data; According to the format-standardized data, perform data quality inspection, including verifying data integrity and consistency, to obtain standardized sensor data.

3. The electronic information data visualization intelligent processing method according to claim 1, characterized in that The steps for obtaining the fused sensor data framework are: based on the standardized sensor data, align all sensor data according to the timestamp, perform clustering processing on the data to form a unified data structure to obtain preliminary integrated data; Based on the preliminary integrated data, filter the noise in the data, use statistics to identify and correct the outliers in the data to obtain enhanced integrated data; Based on the enhanced integrated data, combine the data source, timestamp accuracy, and sensor type to obtain a fused sensor data framework.

4. The intelligent processing method for visualizing electronic information data according to claim 1, characterized in that, The steps for obtaining the data relationship display diagram are as follows: Based on the preliminary event association result, extract each event node and connection relationship, construct an event interaction matrix, and remove isolated event nodes to obtain an event relationship matrix; According to the event relationship matrix, calculate the event centrality index, and the calculation formula is: Among them, is the event centrality index, is the event node and the event node is the interaction frequency between them, is the node and is the number of mutual responses between them, is the node and is the number of new connections between them, is the total interaction time of the node , is the number of projects participated by the node , is the number of event nodes in the current network; Based on the event centrality index, construct an event association topology structure through graph theory, draw a node distribution diagram, and through the connectivity analysis between nodes, screen the key event flow relationships to form a data relationship display diagram.

5. The electronic information data visualization intelligent processing method according to claim 1, wherein The steps for obtaining the critical path analysis result are as follows: According to the data relationship display diagram, calculate the critical path optimization index, and the calculation formula is: Among them, is the critical path optimization index, is the traffic data of node ; is the shortest path length from node to the critical node, is the buffer size of node ; is the processing speed of node ; is the number of connections of node ; is the data load of node ; is the traffic volatility of node ; is the number of nodes on the path; Based on the critical path optimization index, identify potential bottlenecks and key transmission nodes in data transmission, and analyze which nodes and connections affect the data flow efficiency to obtain the critical path analysis result.

6. The electronic information data visualization intelligent processing method according to claim 1, wherein The steps for obtaining the optimized data processing flow are as follows: Based on the critical path analysis result, extract the inter-node delay, bandwidth usage, and packet loss rate of the data flow to obtain the data path parameters to be optimized; According to the data path parameters to be optimized, calculate the path optimization priority, and the calculation formula is: Among them, is the path optimization priority, is the bandwidth occupancy ratio of the path, is the packet loss rate of the path, is the average transmission time of the path, is the delay of the path, is the jitter value of the path; Based on the path optimization priority, adjust the transmission strategy of the data flow, reallocate the traffic load, and generate an optimized data processing flow.

7. The electronic information data visualization intelligent processing method according to claim 1, wherein The specific steps for applying the optimized data processing flow to real-time data monitoring and presenting the data visually in real time on the operator's visual interface in combination with augmented reality are as follows: According to the optimized data processing flow, select the transmission rate, the occurrence frequency of abnormal events, and the data integrity detection result to generate the input configuration for real-time data monitoring; Through the input configuration of the real-time data monitoring, convert it into a digital display of dynamic charts and performance indicators to generate a visualized data flow; Dynamically project the visualized data flow into the operator's augmented reality vision to display the data view.

Images