A method and system for edge computing and cloud synchronization of ropeway operation data

Abstract

The application relates to the technical field of digital communication, and discloses a ropeway operation data edge computing and cloud synchronization method and system.The method comprises the following steps: filtering useless noise points from operation data collected by a ropeway operation sensor to obtain a standard data set; the mean, variance and trend index of the standard data set are counted to obtain a time domain feature subset, and a dominant frequency component of the frequency domain standard data set is extracted to obtain a frequency domain feature subset; the time domain feature subset and the frequency domain feature subset are weighted and fused to obtain a feature data set; reference statistical features of ropeway historical operation data are extracted, and the distribution position relationship of real-time feature points in the feature data set in the reference statistical features is used to evaluate an initial abnormal state; the initial abnormal state is weighted and adjusted to obtain an abnormal index; and the operation data is synchronized to a cloud server according to the priority corresponding to the abnormal index; and the application can improve the efficiency of ropeway operation data processing.

Description

Technical Field

[0001] This invention relates to the field of digital communication technology, and in particular to a method and system for edge computing and cloud synchronization of cableway operation data. Background Technology

[0002] Traditional cableway operation data processing relies heavily on centralized cloud computing architectures. Raw operational data collected by sensors must be directly transmitted to the cloud for processing, without local preprocessing at the data source. In this model, a large amount of high-frequency noise and abnormal interference values ​​in the raw data simultaneously consume limited transmission bandwidth, significantly increasing data transmission costs and causing a surge in cloud data processing load. This makes it difficult to efficiently clean and standardize data, hindering the rapid generation of accurate standard datasets. This creates fundamental data vulnerabilities for subsequent cableway operation status analysis, impacting the overall accuracy and efficiency of data processing.

[0003] Existing technologies have significant shortcomings in the assessment and cloud synchronization of abnormal cableway operation conditions. On the one hand, feature extraction from operational data is often limited to a single dimension, either the time or frequency domain, lacking a systematic fusion of time and frequency domain features. This results in incomplete extracted feature information and difficulty in accurately capturing potential anomalies caused by the coupling of multiple factors during cableway operation. On the other hand, abnormal condition assessments are not linked to real-time environmental parameters, making the assessment results susceptible to environmental changes and prone to deviating from actual operating conditions. Furthermore, data synchronization to the cloud does not prioritize data according to the severity of the anomaly, and important abnormal data may experience delays due to unreasonable allocation of transmission resources, reducing the timeliness and reliability of cableway operation safety warnings. Summary of the Invention

[0004] This invention provides a method and system for edge computing and cloud synchronization of cableway operation data to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides a method for edge computing and cloud synchronization of cableway operation data, comprising:

[0006] S1. At the edge computing node, useless noise is filtered out from the operation data collected by the cableway operation sensors to obtain the standard dataset of the cableway.

[0007] S2. Calculate the mean, variance and trend index of the standard dataset to obtain the time-domain feature subset of the cableway, and at the same time extract the dominant frequency components of the frequency-domain standard dataset to obtain the frequency-domain feature subset of the cableway.

[0008] S3. Perform weighted fusion of the time-domain feature subset and the frequency-domain feature subset to obtain the feature dataset of the cableway;

[0009] S4. Extract the baseline statistical features of the cableway's historical operation data from the sliding time window, and evaluate the initial abnormal state of the cableway based on the distribution and positional relationship of the real-time feature points in the feature dataset within the baseline statistical features.

[0010] S5. The initial abnormal state is weighted and adjusted according to the real-time environmental parameters of the cableway to obtain the abnormal index of the cableway.

[0011] S6. Synchronize the running data to the cloud server according to the priority corresponding to the abnormal indicators.

[0012] In a preferred embodiment, the step of filtering out unwanted noise from the operating data collected by the cableway operation sensors at the edge computing node to obtain a standard dataset for the cableway includes:

[0013] The edge computing nodes cache the operation data collected by the cableway operation sensors to obtain the raw data stream of the cableway;

[0014] High-frequency noise components are removed from the original data stream to obtain preliminary filtered data for the cableway;

[0015] Outlier removal is performed on the preliminary filtered data to obtain the effective data set of the cableway;

[0016] The data format and units of the effective data set are standardized to obtain the standard dataset of the cableway.

[0017] In a preferred embodiment, the step of statistically analyzing the mean, variance, and trend indicators of the standard dataset to obtain a time-domain feature subset of the cableway, and simultaneously extracting the dominant frequency components of the frequency-domain-modified standard dataset to obtain a frequency-domain feature subset of the cableway, includes:

[0018] The mean, variance, and trend characteristics of the data points in the standard dataset are statistically analyzed to obtain the intermediate time-domain results of the standard dataset.

[0019] By retaining the statistical features in the intermediate time-domain results that meet the preset conditions, a subset of the time-domain features of the cableway is obtained;

[0020] The frequency domain distribution data of the cableway is obtained by performing a frequency domain transformation on the standard dataset.

[0021] The dominant frequency feature set of the cableway is obtained by identifying the frequency components with prominent amplitudes from the frequency domain distribution data.

[0022] By removing redundant frequency components from the dominant frequency feature set, a frequency domain feature subset of the cableway is obtained.

[0023] In a preferred embodiment, the weighted fusion of the time-domain feature subset and the frequency-domain feature subset to obtain the feature dataset of the cableway includes:

[0024] Ensure that the feature points in the time-domain feature subset and the frequency-domain feature subset are consistent in the time dimension to obtain an aligned feature set;

[0025] Based on the importance of the features in the cableway, fusion weights are assigned to the aligned feature set to obtain the weight allocation scheme of the cableway;

[0026] According to the weight allocation scheme, the aligned feature set is weighted and combined to obtain the weighted feature set of the cableway;

[0027] Remove highly correlated duplicate features from the weighted features to obtain the optimized feature set;

[0028] The optimized feature set is standardized and encapsulated to obtain the feature dataset of the cableway.

[0029] In a preferred embodiment, the step of extracting baseline statistical features from the cableway's historical operation data within a sliding time window, and assessing the initial abnormal state of the cableway based on the distribution and positional relationships of real-time feature points in the feature dataset within the baseline statistical features, includes:

[0030] Based on a preset time window length, the historical operation data of the cableway within the corresponding time period is extracted from the historical operation database to obtain the historical data sample set of the cableway.

[0031] The baseline statistical characteristics of the cableway are obtained by statistically analyzing the central trend characteristics and dispersion characteristics of each feature dimension in the historical data sample set.

[0032] The real-time feature points in the feature dataset are matched with the baseline statistical features for distribution matching analysis. Based on the degree of deviation of the feature points from the historical distribution, feature deviation data of the cableway is generated.

[0033] The degree of anomaly of the cableway is quantitatively assessed based on the feature deviation data to obtain a preliminary anomaly score for the cableway.

[0034] The initial anomaly score is weighted and processed to obtain the initial anomaly state of the cableway.

[0035] In a preferred embodiment, the formula for calculating the preliminary anomaly score is as follows:

[0036] ;

[0037] In the formula, For the preliminary anomaly score, The total number of feature points in the feature dataset. The ordinal number of the feature points in the feature dataset. The first feature deviation data Pre-acquisition scaling factor parameters for each feature point Pi It is the arctangent function. The first feature deviation data Preset weight parameters for each feature point The first feature deviation data The deviation value of each feature point.

[0038] In a preferred embodiment, the step of weighting and adjusting the initial abnormal state based on the real-time environmental parameters of the cableway to obtain the abnormality index of the cableway includes:

[0039] Obtain the real-time environmental parameters of the cableway and generate a set of environmental parameters for the cableway;

[0040] Based on preset environmental impact rules, the set of environmental parameters is analyzed to determine the degree of influence of the set of environmental parameters on the cableway's operating status, and the environmental impact factor of the cableway is obtained.

[0041] Based on the aforementioned environmental impact factors, an environmental adaptive adjustment coefficient for the cableway is constructed.

[0042] The environmental adaptive adjustment coefficient is fused with the initial abnormal state to obtain the corrected abnormal state of the cableway;

[0043] The abnormal state of the cableway is mapped to a standard evaluation scale to obtain the abnormal index of the cableway.

[0044] In a preferred embodiment, constructing the environmental adaptive adjustment coefficient of the cableway based on the environmental impact factors includes:

[0045] Establish a correlation mapping between environmental parameters in the environmental parameter set and changes in the cableway's operating status to obtain the influence degree mapping relationship of the cableway.

[0046] According to the cableway operation safety regulations, the threshold range of the environmental parameters is determined, and the safety boundary of the environmental parameters is obtained.

[0047] The real-time environmental parameters of the cableway are compared with the safety boundary to obtain the boundary proximity index of the cableway.

[0048] Based on the boundary proximity index and the influence degree mapping relationship, the current influence degree of the environmental parameters is comprehensively evaluated to obtain the environmental adaptive adjustment coefficient of the cableway.

[0049] In a preferred embodiment, synchronizing the operational data to the cloud server according to the priority corresponding to the abnormal indicator includes:

[0050] Based on the numerical range of the abnormal indicators, the running data is divided into multiple priority categories to obtain the data priority classification result of the running data;

[0051] Based on the data priority classification results, corresponding transmission resources are allocated to running data of different priorities to obtain the transmission resource allocation scheme for the running data;

[0052] According to the aforementioned transmission resource allocation scheme, establish a transmission channel for the cloud server;

[0053] The operational data is transmitted sequentially through the transmission channel according to priority.

[0054] To address the aforementioned problems, the present invention also provides an edge computing and cloud synchronization system for cableway operation data, the system comprising:

[0055] The data cleaning module is used to filter out useless noise from the operating data collected by the cableway operation sensors at the edge computing node, so as to obtain the standard dataset of the cableway.

[0056] The data feature segmentation module is used to statistically analyze the mean, variance, and trend indicators of the standard dataset to obtain the time-domain feature subset of the cableway, and simultaneously extract the dominant frequency components of the frequency-domain standard dataset to obtain the frequency-domain feature subset of the cableway.

[0057] The feature weighting module is used to weight and fuse the time-domain feature subset and the frequency-domain feature subset to obtain the feature dataset of the cableway;

[0058] An abnormal state assessment module is used to extract baseline statistical features of the cableway's historical operation data within a sliding time window, and to assess the initial abnormal state of the cableway based on the distribution and positional relationship of real-time feature points in the feature dataset within the baseline statistical features.

[0059] An abnormal state correction module is used to adjust the initial abnormal state based on the real-time environmental parameters of the cableway to obtain the abnormal index of the cableway.

[0060] The data transmission module is used to synchronize the running data to the cloud server according to the priority corresponding to the abnormal indicators.

[0061] Compared with the prior art, the present invention has the following beneficial effects:

[0062] 1. This invention filters out useless noise from the operational data collected by cableway operation sensors at edge computing nodes, sequentially completing the processes of raw data stream caching, high-frequency noise removal, outlier elimination, and data format and unit unification. This effectively improves data quality, generates accurate standard datasets, and provides a reliable data foundation for subsequent data feature analysis. Simultaneously, by obtaining time-domain feature subsets from the mean, variance, and trend indicators of the statistical standard dataset, and extracting the dominant frequency components of the frequency-domain standard dataset to obtain frequency-domain feature subsets, and then weighted and fused these two feature subsets, a comprehensive integration of time-domain and frequency-domain features can be achieved, forming a feature dataset that better reflects the cableway's operational status. This significantly improves the completeness and accuracy of cableway operation data feature extraction, thereby enhancing the overall accuracy of data processing.

[0063] 2. This invention extracts the baseline statistical features of historical cableway operation data within a sliding time window, combines this with the distribution and positional relationships of real-time feature points in the feature dataset within the baseline statistical features to assess the initial abnormal state, and then weights and adjusts the initial abnormal state based on real-time environmental parameters to generate abnormal indicators. This allows the abnormal assessment results to fully reflect the actual operating environment of the cableway, significantly improving the accuracy of abnormal state judgment. Furthermore, by classifying the operation data according to the priority corresponding to the abnormal indicators and allocating corresponding transmission resources to different priority data for cloud synchronization, it ensures that high-priority critical operation data is transmitted first, effectively improving the targeting and timeliness of data synchronization, and providing efficient data support for cableway operation safety monitoring and subsequent decision-making. Attached Figure Description

[0064] Figure 1 A flowchart illustrating an edge computing and cloud synchronization method for cableway operation data provided in an embodiment of the present invention;

[0065] Figure 2 A functional block diagram of an edge computing and cloud synchronization system for cableway operation data provided in an embodiment of the present invention;

[0066] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0067] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0068] This application provides an edge computing and cloud synchronization method for cableway operation data. The execution entity of this method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the edge computing and cloud synchronization method for cableway operation data can be executed by software or hardware installed on a terminal device or a server device. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0069] Reference Figure 1 The diagram shown is a flowchart illustrating a method for edge computing and cloud synchronization of cableway operation data according to an embodiment of the present invention. In this embodiment, the method for edge computing and cloud synchronization of cableway operation data includes:

[0070] S1. At the edge computing node, useless noise is filtered out from the operation data collected by the cableway operation sensors to obtain the standard dataset of the cableway.

[0071] In this embodiment of the invention, the step of filtering out useless noise from the operating data collected by the cableway operation sensors at the edge computing node to obtain a standard dataset for the cableway includes:

[0072] The edge computing nodes cache the operation data collected by the cableway operation sensors to obtain the raw data stream of the cableway;

[0073] High-frequency noise components are removed from the original data stream to obtain preliminary filtered data for the cableway;

[0074] Outlier removal is performed on the preliminary filtered data to obtain the effective data set of the cableway;

[0075] The data format and units of the effective data set are standardized to obtain the standard dataset of the cableway.

[0076] Specifically, the edge computing node establishes a stable data transmission link with the cableway operation sensors, receives each cableway operation data collected by the sensors in real time, and stores the received data in the local storage unit of the edge computing node in the order of data generation. The node continues to receive and store data until all data of the current required collection cycle is covered, and finally obtains the raw data stream of the cableway.

[0077] Furthermore, for the original data stream of the cableway, a moving average method is used to remove high-frequency noise components. Specifically, a number of consecutive data points are selected from the beginning of the original data stream to form a calculation window. The arithmetic mean of all data points in the window is calculated, and the average value is used to replace the data point in the middle of the window. Then, the calculation window is moved one data point along the data stream direction, and the above operation of calculating the average value and replacing the corresponding data point is repeated until all data points of the original data stream are processed, and finally the preliminary filtered data of the cableway is obtained.

[0078] Furthermore, when removing outliers from the initial filtered data of the cableway, the overall trend of the initial filtered data is first analyzed to determine the reasonable fluctuation range of the data under normal operating conditions. Then, each data point in the initial filtered data is checked one by one to determine whether the data point falls within the reasonable fluctuation range. If a data point exceeds the reasonable fluctuation range, it is determined as an outlier and deleted from the initial filtered data. After all data points have been checked and processed, the effective data set of the cableway is obtained.

[0079] Furthermore, for the effective data set of the cableway, a unified data format and standard unit are first defined. The data format is set to a fixed structure that includes the acquisition time, sensor number, data type, and acquired values. The standard unit is determined according to the data attributes, such as uniformly using millimeters for displacement data and uniformly using kilopascals for pressure data. Then, each data point in the effective data set is processed one by one, and the data structure is adjusted according to the set format to convert the acquired values ​​into the corresponding standard units. After all the data is processed, the standard dataset of the cableway is obtained.

[0080] In summary, by caching the raw data stream locally, removing high-frequency noise, and eliminating outliers, useless interference information can be filtered out directly at the source of the data, avoiding redundant data from occupying transmission bandwidth, reducing data transmission costs, and at the same time reducing the load on subsequent data processing in the cloud, thereby improving overall data processing efficiency.

[0081] In summary, the effective data obtained after filtering out noise can significantly improve data purity and accuracy, providing a reliable data foundation for subsequent statistical analysis of time-domain features and extraction of dominant frequency components in the frequency domain, and ensuring the accuracy of feature extraction results.

[0082] In summary, standardizing the format and units of valid data ensures consistency in standard datasets, eliminates the interference of data format differences on subsequent feature weighting and fusion, and abnormal state assessment, thus ensuring the smooth progress of subsequent data processing and providing high-quality data support for cableway operation status analysis.

[0083] S2. Calculate the mean, variance and trend index of the standard dataset to obtain the time-domain feature subset of the cableway, and at the same time extract the dominant frequency components of the frequency-domain standard dataset to obtain the frequency-domain feature subset of the cableway.

[0084] In this embodiment of the invention, the step of statistically analyzing the mean, variance, and trend indicators of the standard dataset to obtain a time-domain feature subset of the cableway, and simultaneously extracting the dominant frequency components of the frequency-domain standardized dataset to obtain a frequency-domain feature subset of the cableway, includes:

[0085] The mean, variance, and trend characteristics of the data points in the standard dataset are statistically analyzed to obtain the intermediate time-domain results of the standard dataset.

[0086] By retaining the statistical features in the intermediate time-domain results that meet the preset conditions, a subset of the time-domain features of the cableway is obtained;

[0087] The frequency domain distribution data of the cableway is obtained by performing a frequency domain transformation on the standard dataset.

[0088] The dominant frequency feature set of the cableway is obtained by identifying the frequency components with prominent amplitudes from the frequency domain distribution data.

[0089] By removing redundant frequency components from the dominant frequency feature set, a frequency domain feature subset of the cableway is obtained.

[0090] Specifically, all data points are extracted from the standard dataset, and the values ​​of these data points are added together. The sum is divided by the total number of data points to calculate the mean feature. Next, the difference between the value of each data point and the mean feature is calculated. Each difference is squared and then added together. The sum of the squares is divided by the total number of data points to calculate the variance feature. Then, the data points in the standard dataset are arranged in chronological order of collection time, and the overall trend of the data point values ​​over time is observed. For example, when the average value of the data points in the second half of the time is higher than the average value of the data points in the first half of the time, the trend indicator feature is determined to be rising; otherwise, it is falling. The calculated mean feature, variance feature, and trend indicator feature are integrated together to obtain the intermediate time-domain result of the standard dataset.

[0091] Furthermore, first define the preset conditions, which are that the values ​​of statistical features are within the fixed range corresponding to the feature under normal cableway operation. Then, examine each statistical feature in the intermediate time-domain results one by one to determine whether its value is within the preset fixed range. If the value of the statistical feature is within the preset fixed range, the statistical feature is retained. If the value exceeds the preset fixed range, the statistical feature is removed. After all statistical features have been judged, the time-domain feature subset of the cableway is obtained.

[0092] Furthermore, the data points in the standard dataset are arranged in chronological order of acquisition time. The interval between the acquisition times of two adjacent data points is taken as a fixed time interval. Using the fixed time interval as the unit, the values ​​of all data points are decomposed into periodic fluctuation components of different frequencies. Each frequency component corresponds to an amplitude value representing the intensity of the fluctuation. All the frequencies obtained from the decomposition and their corresponding amplitude values ​​are organized into an ordered set to obtain the frequency domain distribution data of the cableway.

[0093] Furthermore, all amplitude values ​​in the frequency domain distribution data are compared to identify those amplitude values ​​that are significantly higher than other amplitude values. The frequencies corresponding to these high amplitude values ​​are determined, and these frequencies and their respective amplitude values ​​are collected together to form the dominant frequency feature set of the cableway.

[0094] Furthermore, examine all frequencies in the dominant frequency feature set, calculate the difference between any two frequencies, and if the difference between the two frequencies is less than a fixed threshold, and the difference between the amplitude values ​​corresponding to these two frequencies is also less than a fixed amplitude threshold, then determine that the latter frequency is a redundant frequency component, remove the redundant frequency component from the dominant frequency feature set, and perform pairwise comparisons on all frequencies in turn to remove redundant frequency components, finally obtaining the frequency domain feature subset of the cableway.

[0095] In summary, the mean, variance, and trend indicators of the statistical standard dataset are used to obtain a subset of time-domain features. This can accurately capture the central trend, dispersion, and dynamic change patterns of cableway operation data, clearly reflect the operational status characteristics of the cableway in the time dimension, provide a reliable time-domain basis for judging whether the operation is within a stable range, and ensure that subtle fluctuations in the data can be detected in a timely manner.

[0096] In summary, simultaneously extracting the dominant frequency components from the frequency-domain standardized dataset to obtain a frequency-domain feature subset can uncover implicit frequency patterns that are difficult to reveal in the time domain dimension, supplementing the information gaps in time-domain features. Both methods extract data features comprehensively from different dimensions, avoiding the limitations of single-dimensional features, and providing a comprehensive and accurate foundation for the subsequent weighted fusion of time-domain and frequency-domain features. This, in turn, supports more accurate identification of the cableway's operational status in subsequent anomaly assessment stages.

[0097] S3. Perform weighted fusion of the time-domain feature subset and the frequency-domain feature subset to obtain the feature dataset of the cableway;

[0098] In this embodiment of the invention, the weighted fusion of the time-domain feature subset and the frequency-domain feature subset to obtain the feature dataset of the cableway includes:

[0099] Ensure that the feature points in the time-domain feature subset and the frequency-domain feature subset are consistent in the time dimension to obtain an aligned feature set;

[0100] Based on the importance of the features in the cableway, fusion weights are assigned to the aligned feature set to obtain the weight allocation scheme of the cableway;

[0101] According to the weight allocation scheme, the aligned feature set is weighted and combined to obtain the weighted feature set of the cableway;

[0102] Remove highly correlated duplicate features from the weighted features to obtain the optimized feature set;

[0103] The optimized feature set is standardized and encapsulated to obtain the feature dataset of the cableway.

[0104] Specifically, the acquisition time period corresponding to each feature point in the time-domain feature subset is extracted, and the acquisition time period corresponding to each feature point in the frequency-domain feature subset is also extracted. The time-domain feature points and frequency-domain feature points are matched one by one according to the same acquisition time period. If a time-domain feature point does not have a corresponding frequency-domain feature point with the same acquisition time period, the time-domain feature point is removed from the time-domain feature subset. If a frequency-domain feature point does not have a corresponding time-domain feature point with the same acquisition time period, the frequency-domain feature point is removed from the frequency-domain feature subset. After completing all matching and removal operations, the remaining time-domain feature points and frequency-domain feature points are integrated into a set to obtain the aligned feature set.

[0105] Furthermore, the basis for judging the importance of cableway features is first clarified as the degree of influence of the feature on the monitoring of cableway operation status. For example, vibration frequency-related features have a greater impact on judging whether the cableway is operating stably and are therefore more important, followed by amplitude-related features. Based on this judgment criterion, each feature in the aligned feature set is classified into importance levels. Features with high importance levels are assigned larger weight values, and features with low importance levels are assigned smaller weight values. Each feature and its corresponding weight value are recorded one by one to form a complete list, thus obtaining the weight allocation scheme for the cableway.

[0106] Furthermore, the first feature point is extracted from the aligned feature set, the weight value corresponding to the feature point in the weight allocation scheme is found, and the value of the feature point is multiplied by the corresponding weight value to obtain the weighted value of the feature point. In the same way, all feature points in the aligned feature set are extracted in sequence and multiplied by their respective weight values ​​to obtain the weighted values ​​of all feature points. These weighted values ​​are then arranged into an ordered set to obtain the weighted feature set of the cableway.

[0107] Furthermore, the first feature in the weighted feature set is selected and compared with all other features in the set one by one. The trend of the values ​​of the two features changing over time is observed. If the trends of the values ​​of the two features are completely consistent or almost consistent, then the two features are determined to be highly correlated duplicate features. The feature that appears later is removed. After the comparison and removal of the first feature is completed, the second feature remaining in the set is selected, and the above operation of comparing with other features and removing highly correlated duplicate features is repeated until all features have been compared and removed, resulting in the optimized feature set.

[0108] Furthermore, a standardized encapsulation format is determined, which includes four items: feature name, feature value, acquisition time, and corresponding weight. The first feature is taken from the optimized feature set, and its name, value, acquisition time, and corresponding weight are filled in according to the standardized format to form a standardized feature record. In the same way, all features in the optimized feature set are processed in sequence to generate corresponding standardized feature records. All standardized feature records are arranged in chronological order of acquisition time and integrated into a complete dataset to obtain the cableway feature dataset.

[0109] In summary, ensuring that the two types of feature points are aligned in the time dimension before fusion can eliminate feature deviations caused by time misalignment, guarantee the consistency of feature information in the time dimension, and lay the foundation for subsequent accurate analysis. Secondly, allocating fusion weights based on the importance of cableway features can highlight features that are more critical to the assessment of operational status, making the fused features more in line with the actual monitoring needs of the cableway and improving the relevance and effectiveness of the features.

[0110] In summary, redundant feature elimination removes highly correlated duplicate information from the weighted feature set, reducing data redundancy, lowering the computational load for subsequent abnormal state assessments, and improving data processing efficiency. Finally, the standardized encapsulation forms a feature dataset, which unifies feature format and scale, avoids format differences interfering with subsequent comparative analysis with historical data, and ensures the smooth implementation of subsequent benchmark statistical feature matching, abnormal score calculation, and other steps, providing high-quality and reliable feature support for accurately assessing the cableway's operational status.

[0111] S4. Extract the baseline statistical features of the cableway's historical operation data from the sliding time window, and evaluate the initial abnormal state of the cableway based on the distribution and positional relationship of the real-time feature points in the feature dataset within the baseline statistical features.

[0112] In this embodiment of the invention, the step of extracting baseline statistical features of the cableway's historical operation data within a sliding time window, and assessing the initial abnormal state of the cableway based on the distribution and positional relationship of real-time feature points in the feature dataset within the baseline statistical features, includes:

[0113] Based on a preset time window length, the historical operation data of the cableway within the corresponding time period is extracted from the historical operation database to obtain the historical data sample set of the cableway.

[0114] The baseline statistical characteristics of the cableway are obtained by statistically analyzing the central trend characteristics and dispersion characteristics of each feature dimension in the historical data sample set.

[0115] The real-time feature points in the feature dataset are matched with the baseline statistical features for distribution matching analysis. Based on the degree of deviation of the feature points from the historical distribution, feature deviation data of the cableway is generated.

[0116] The degree of anomaly of the cableway is quantitatively assessed based on the feature deviation data to obtain a preliminary anomaly score for the cableway.

[0117] The initial anomaly score is weighted and processed to obtain the initial anomaly state of the cableway.

[0118] In this embodiment of the invention, the calculation formula for the preliminary anomaly score is as follows:

[0119]

[0120] In the formula, For the preliminary anomaly score, The total number of feature points in the feature dataset. The ordinal number of the feature points in the feature dataset. The first feature deviation data Pre-acquisition scaling factor parameters for each feature point Pi It is the arctangent function. The first feature deviation data Preset weight parameters for each feature point The first feature deviation data The deviation value of each feature point.

[0121] Specifically, the specific time period corresponding to the preset time window length is clearly defined. For example, if the preset time window length is 7 consecutive days, then the specific time range of 7 days from the current time is determined. All recorded cableway historical operation data within this time range are filtered out in the historical operation database. These data are classified and organized according to feature dimensions to form a set containing historical data of each feature dimension, thus obtaining the historical data sample set of the cableway.

[0122] Furthermore, the historical data sample set is split according to feature dimensions, and each feature dimension is processed separately. For a single feature dimension, all historical data values ​​under that dimension are added together, and the sum is divided by the total number of data under that dimension to calculate the central trend feature of that dimension. Then, the difference between each historical data value under that dimension and the central trend feature is calculated, and each difference is squared and added together. The sum of the squares is divided by the total number of data under that dimension to calculate the dispersion feature of that dimension. The central trend features and dispersion features of all feature dimensions are summarized to obtain the baseline statistical features of the cableway.

[0123] Furthermore, each real-time feature point is extracted from the feature dataset, the feature dimension to which each real-time feature point belongs is determined, the central trend feature and dispersion feature of the corresponding dimension in the benchmark statistical features are found, the difference between the value of the real-time feature point and the central trend feature of the corresponding dimension is compared, and the size of the difference relative to the dispersion feature is observed. If the difference is much larger than the dispersion feature, the deviation is judged to be large; if the difference is close to or smaller than the dispersion feature, the deviation is judged to be small. The deviation of each real-time feature point is recorded with specific description or level to form the feature deviation data of the cableway.

[0124] Furthermore, a correspondence rule is set between feature deviation and anomaly score. For example, a large deviation corresponds to a higher anomaly score, a medium deviation corresponds to a medium anomaly score, and a small deviation corresponds to a lower anomaly score. According to this rule, a specific score is assigned to the deviation of each real-time feature point in the feature deviation data. The scores of all real-time feature points are organized into an ordered list to obtain the preliminary anomaly score of the cableway.

[0125] Furthermore, the importance weight of each feature dimension in the cableway operation status assessment is determined. For example, the feature dimension related to cableway load-bearing capacity has a higher weight than the feature dimension related to ambient temperature. The score corresponding to each feature dimension in the preliminary anomaly score is multiplied by the weight of that dimension to obtain the weighted score of each dimension. The weighted scores of all dimensions are added together to obtain the total weighted score. The cableway status is determined according to the range of the total weighted score. For example, the total weighted score is below a certain value, indicating a normal state, and above that value, indicating an abnormal state, thus obtaining the initial abnormal state of the cableway.

[0126] Specifically, the numerator of the formula is used to calculate the weighted sum of contributions from all feature points. The specific process involves, for each feature point, first calculating the weighted contribution of that feature point... and Multiply the products, then input the product into the arctangent function for processing, and divide the result by 2. Multiply the quotient by the product of the two terms, and then multiply by the feature point. First, obtain the contribution value of a single feature point, then calculate the contribution values ​​of all feature points from the first to the second. By adding the numerators one by one, we get the sum of the numerators.

[0127] Furthermore, the denominator of the formula is used to calculate all feature points. The sum, specifically the process of combining all feature points From the first to the... Add the values ​​one by one to get the value of the denominator.

[0128] Furthermore, the entire formula obtains a weighted average value by dividing the sum of the numerators by the sum of the denominators. This value is the preliminary anomaly score, which comprehensively considers the magnitude of the deviation of each feature point, the importance of the deviation, and the scaling requirements to quantify the degree of anomaly of the cableway and finally outputs a score result that reflects the preliminary anomaly of the cableway.

[0129] In summary, the sliding time window can dynamically extract historical data for the corresponding time period, so that the benchmark statistical characteristics can fit the current operating cycle, avoid the lag of fixed historical data, ensure the timeliness and adaptability of the benchmark, and provide a reference standard that conforms to the current operating scenario for anomaly assessment.

[0130] In summary, the baseline statistical features cover the central trend and dispersion of each feature dimension of historical data, which can comprehensively define the feature range of normal cableway operation, provide clear and complete reference for the comparative analysis of real-time feature points, and avoid evaluation bias caused by one-sided baseline information.

[0131] In summary, by analyzing the distribution of real-time feature points and benchmarks, feature deviation can be quantified, replacing subjective judgment and making anomaly identification more objective. At the same time, by quantifying the initial anomaly score based on deviation and comprehensively weighting it, multi-feature dimension information can be integrated, reducing the risk of misjudgment based on a single feature, significantly improving the accuracy of the initial anomaly state assessment, and laying a reliable foundation for subsequent adjustment of anomaly indicators in conjunction with real-time environmental parameters.

[0132] S5. The initial abnormal state is weighted and adjusted according to the real-time environmental parameters of the cableway to obtain the abnormal index of the cableway.

[0133] In this embodiment of the invention, the step of weighting and adjusting the initial abnormal state based on the real-time environmental parameters of the cableway to obtain the abnormal indicators of the cableway includes:

[0134] Obtain the real-time environmental parameters of the cableway and generate a set of environmental parameters for the cableway;

[0135] Based on preset environmental impact rules, the set of environmental parameters is analyzed to determine the degree of influence of the set of environmental parameters on the cableway's operating status, and the environmental impact factor of the cableway is obtained.

[0136] Based on the aforementioned environmental impact factors, an environmental adaptive adjustment coefficient for the cableway is constructed.

[0137] The environmental adaptive adjustment coefficient is fused with the initial abnormal state to obtain the corrected abnormal state of the cableway;

[0138] The abnormal state of the cableway is mapped to a standard evaluation scale to obtain the abnormal index of the cableway.

[0139] In this embodiment of the invention, constructing the environmental adaptive adjustment coefficient of the cableway based on the environmental impact factors includes:

[0140] Establish a correlation mapping between environmental parameters in the environmental parameter set and changes in the cableway's operating status to obtain the influence degree mapping relationship of the cableway.

[0141] According to the cableway operation safety regulations, the threshold range of the environmental parameters is determined, and the safety boundary of the environmental parameters is obtained.

[0142] The real-time environmental parameters of the cableway are compared with the safety boundary to obtain the boundary proximity index of the cableway.

[0143] Based on the boundary proximity index and the influence degree mapping relationship, the current influence degree of the environmental parameters is comprehensively evaluated to obtain the environmental adaptive adjustment coefficient of the cableway.

[0144] Specifically, temperature sensors, humidity sensors, wind speed sensors, and precipitation sensors are deployed at the cableway operation site. Each sensor continuously collects real-time environmental data of the corresponding type. Data is synchronously acquired from each sensor at fixed intervals. The temperature, humidity, wind speed, and precipitation data acquired at the same time point are integrated into a complete set of environmental data. All complete environmental data are arranged in chronological order of acquisition time to obtain the set of environmental parameters for the cableway.

[0145] Furthermore, the preset environmental impact rules include the impact standards of various environmental parameters on cableway operation, such as no significant impact when wind speed is ≤ 5 meters per second, slight impact when wind speed is 5-10 meters per second, and significant impact when wind speed is > 10 meters per second. Temperature and humidity also have corresponding impact standards. The first data point is taken from the set of environmental parameters, and the impact degree of each parameter in the data is judged according to the rules. The overall impact degree of the data is obtained by combining the impact degree of each parameter. All data are processed in the same way, and the overall impact degree of all data is summarized into a quantitative result to obtain the environmental impact factor of the cableway.

[0146] Furthermore, the correspondence between environmental impact factors and adjustment coefficients is established. For example, the coefficient is 1 when there is no significant impact, 1.2 when there is a slight impact, and 1.5 when there is a significant impact. The impact level corresponding to the environmental impact factor is checked, and the specific value is determined according to the correspondence. This value is used to adjust the initial abnormal state in the future, and the environmental adaptive adjustment coefficient of the cableway is obtained.

[0147] Furthermore, the environmental adaptive adjustment coefficient and the initial abnormal state are extracted. Both are quantitative values ​​with uniform units. The adjustment coefficient value is multiplied by the initial abnormal state value, and the result of the multiplication is used as the abnormal state evaluation value after eliminating environmental interference, thus obtaining the corrected abnormal state of the cableway.

[0148] Furthermore, a pre-defined standard evaluation scale is used to divide the numerical range into multiple intervals, such as 0-0.3 corresponding to normal, 0.3-0.6 corresponding to slight abnormality, and 0.6-1.0 corresponding to severe abnormality. The numerical values ​​that correct abnormal states are extracted, the interval to which the value belongs is determined, and the result corresponding to the interval is determined as the final indicator to obtain the abnormal indicators of the cableway.

[0149] Specifically, the types of parameters included in the environmental parameter set are determined, such as temperature, humidity, and wind speed. The specific changes in the cableway's operating status under different parameter values ​​are continuously recorded. For example, the operating deviation caused by the thermal expansion of the cableway steel cable when the temperature rises to a certain value, and the change in the sway amplitude of the cableway car when the wind speed reaches a certain value. The different values ​​of each environmental parameter are recorded one by one with the corresponding changes in the cableway's operating status, forming a list of the correlation between parameter values ​​and status changes, and obtaining the mapping relationship of the degree of influence of the cableway.

[0150] Furthermore, locate the national or industry-issued safety regulations for cableway operation, and determine the permissible operating range of each environmental parameter in the regulations. For example, the regulations stipulate that the ambient temperature for cableway operation must be between -10 degrees Celsius and 40 degrees Celsius, and the wind speed must be less than 12 meters per second. Organize the permissible ranges of each environmental parameter obtained from the regulations one by one to form a fixed numerical range for each parameter, and obtain the safety boundary of the environmental parameters.

[0151] Furthermore, the real-time environmental parameter values ​​at the current moment are extracted from the environmental parameter set, such as the current real-time temperature and the current real-time wind speed. Each real-time parameter value is compared with the corresponding safety boundary, and the difference between the real-time parameter value and the upper or lower limit of the safety boundary is calculated. If the real-time parameter is in the middle area of ​​the safety boundary, the boundary proximity is low; if it is close to the upper or lower limit, the boundary proximity is high. The proximity judgment results of all parameters are integrated to obtain the boundary proximity index of the cableway.

[0152] Furthermore, examine the proximity of each parameter in the boundary proximity index, and determine the degree of influence of the current value of each parameter on the cableway's operating status by referring to the influence degree mapping relationship. If a parameter has a high boundary proximity and its value has a significant impact on the operating status in the mapping relationship, then the current influence of that parameter is large. If a parameter has a low boundary proximity and its influence in the mapping relationship is small, then the current influence is small. Based on the combined results of the influence degree judgment of all parameters, set the corresponding adjustment value, which is the environmental adaptive adjustment coefficient of the cableway.

[0153] In summary, this operation incorporates environmental factors into the anomaly assessment system, making up for the limitations of the initial anomaly state being based solely on historical operating data. Real-time environmental parameters directly affect the cableway's operating status, and neglecting the environment can easily lead to deviations between the initial assessment and the actual operating conditions. However, by analyzing environmental parameters to determine environmental impact factors, the anomaly assessment can be made more closely aligned with the actual operating scenario of the cableway, reducing misjudgments or omissions caused by environmental interference.

[0154] In summary, the adjustment process is based on preset environmental impact rules and safety boundaries. First, a correlation mapping between environmental parameters and operating status is established. Then, the proximity of the boundary is determined by comparing real-time environmental parameters with the safety boundary. Finally, an environmental adaptive adjustment coefficient is derived, ensuring that the adjustment logic is scientific and based on evidence, avoiding subjective and arbitrary adjustments, and significantly improving the accuracy and reliability of abnormal indicators.

[0155] In summary, after the adjusted abnormal states are mapped to the standard evaluation scale, the resulting abnormal indicators are more uniform and definable. This provides a precise basis for prioritizing data and allocating transmission resources based on the abnormal indicators, ensuring that high-risk abnormal data is synchronized to the cloud first, and further supporting the effectiveness of cableway operation safety monitoring.

[0156] S6. Synchronize the running data to the cloud server according to the priority corresponding to the abnormal indicators.

[0157] In this embodiment of the invention, synchronizing the operational data to the cloud server according to the priority corresponding to the abnormal indicator includes:

[0158] Based on the numerical range of the abnormal indicators, the running data is divided into multiple priority categories to obtain the data priority classification result of the running data;

[0159] Based on the data priority classification results, corresponding transmission resources are allocated to running data of different priorities to obtain the transmission resource allocation scheme for the running data;

[0160] According to the aforementioned transmission resource allocation scheme, establish a transmission channel for the cloud server;

[0161] The operational data is transmitted sequentially through the transmission channel according to priority.

[0162] Specifically, numerical ranges for abnormal indicators are defined. For example, 0 to 0.3 is the normal range, 0.3 to 0.6 is the slightly abnormal range, and 0.6 to 1.0 is the seriously abnormal range. At the same time, three priority categories are defined: low priority, medium priority, and high priority. Each piece of running data is associated with the corresponding abnormal indicator value. The range to which the abnormal indicator value of each piece of running data belongs is determined, and the running data is assigned to the priority category of the corresponding range. After all running data has been classified, a list containing each piece of running data and its priority is compiled to obtain the data priority classification result of the running data.

[0163] Furthermore, examine the priority categories in the data priority classification results. Allocate greater transmission bandwidth and shorter transmission intervals to high-priority running data, medium transmission bandwidth and medium transmission intervals to medium-priority running data, and smaller transmission bandwidth and longer transmission intervals to low-priority running data. For example, allocate 50% of the total bandwidth and 10-second transmission intervals to high-priority data, 30% and 20-second transmission intervals to medium-priority data, and 20% and 30-second transmission intervals to low-priority data. Record the transmission bandwidth value and transmission interval duration corresponding to each priority to form a clear resource allocation list and obtain the transmission resource allocation scheme for running data.

[0164] Furthermore, the transmission bandwidth, transmission interval, and transmission protocol requirements for each priority level of the data operation in the transmission resource allocation scheme are obtained. In the network configuration module of the cloud server, a dedicated transmission channel is created according to the bandwidth parameters required for high priority. The bandwidth value of the channel is set to be consistent with the high priority bandwidth in the allocation scheme. Shared transmission channels are configured for medium and low priority. The bandwidth resources within the channel are allocated according to the bandwidth ratio in the allocation scheme. At the same time, the transmission protocols of all channels are configured to match the scheme requirements. After all channel parameters are configured, the transmission channels of the cloud server corresponding to the transmission resource allocation scheme are obtained.

[0165] Furthermore, firstly, all high-priority running data in the data priority classification results are selected and arranged in chronological order of data generation. These data are then transmitted one by one to the cloud server through the transmission channel configured for high priority. After all high-priority data has been transmitted, medium-priority running data is selected, arranged in chronological order, and transmitted through the corresponding transmission channel. After the medium-priority data transmission is completed, finally, low-priority running data is selected, arranged in chronological order, and transmitted through the corresponding transmission channel, until all priority running data has been transmitted.

[0166] In summary, classifying data priority categories by the range of abnormal indicator values ​​can accurately distinguish the importance of operational data, allowing data with high anomaly risk to receive focused attention, preventing critical security-related data from being overwhelmed by low-priority data, and ensuring that core information is not overlooked.

[0167] In summary, prioritizing transmission resources allows for precise allocation of these resources, tilting bandwidth, channels, and other resources toward high-priority data. This avoids low-priority data consuming too many resources and causing transmission congestion, significantly improving resource utilization efficiency and reducing waste during data transmission.

[0168] In summary, transmitting data sequentially through dedicated transmission channels according to priority ensures that high-priority data arrives at the cloud server first, enabling the cloud to quickly obtain high-risk operation information of the cableway, conduct timely safety assessments and emergency decisions, and significantly improve the timeliness of cableway operation safety early warnings.

[0169] In summary, targeted synchronization reduces the load on the system from invalid data transmission, provides orderly data input for subsequent centralized analysis and data archiving in the cloud, and further optimizes the efficiency and reliability of the overall data processing chain.

[0170] like Figure 2 The diagram shown is a functional block diagram of an edge computing and cloud synchronization system for cableway operation data provided in an embodiment of the present invention.

[0171] The edge computing and cloud synchronization system 100 for cableway operation data described in this invention can be installed in an electronic device. Depending on the functions implemented, the edge computing and cloud synchronization system 100 for cableway operation data may include a data cleaning module 101, a data feature segmentation module 102, a feature weighting module 103, an anomaly state evaluation module 104, an anomaly state correction module 105, and a data transmission module 106. The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and are stored in the memory of the electronic device.

[0172] In this embodiment, the functions of each module / unit are as follows:

[0173] The data cleaning module 101 is used to filter out useless noise from the operating data collected by the cableway operation sensors at the edge computing node to obtain a standard dataset for the cableway.

[0174] The data feature segmentation module 102 is used to statistically analyze the mean, variance, and trend indicators of the standard dataset to obtain the time-domain feature subset of the cableway, and simultaneously extract the dominant frequency components of the frequency-domain standard dataset to obtain the frequency-domain feature subset of the cableway.

[0175] The feature weighting module 103 is used to perform weighted fusion of the time-domain feature subset and the frequency-domain feature subset to obtain the feature dataset of the cableway;

[0176] The abnormal state assessment module 104 is used to extract the baseline statistical features of the cableway's historical operation data in the sliding time window, and to assess the initial abnormal state of the cableway based on the distribution position relationship of the real-time feature points in the feature dataset within the baseline statistical features.

[0177] The abnormal state correction module 105 is used to perform weighted adjustment on the initial abnormal state according to the real-time environmental parameters of the cableway to obtain the abnormal index of the cableway.

[0178] The data transmission module 106 is used to synchronize the running data to the cloud server according to the priority corresponding to the abnormal indicator.

[0179] In the several embodiments provided by this invention, it should be understood that the disclosed methods and systems can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0180] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0181] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0182] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0183] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0184] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for edge computing and cloud synchronization of cableway operation data, characterized in that, The method includes: S1. At the edge computing node, useless noise is filtered out from the operation data collected by the cableway operation sensors to obtain the standard dataset of the cableway. S2. Calculate the mean, variance and trend index of the standard dataset to obtain the time-domain feature subset of the cableway, and at the same time extract the dominant frequency components of the frequency-domain standard dataset to obtain the frequency-domain feature subset of the cableway. S3. Perform weighted fusion of the time-domain feature subset and the frequency-domain feature subset to obtain the feature dataset of the cableway; S4. Extract baseline statistical features from the historical operation data of the cableway within the sliding time window, and assess the initial abnormal state of the cableway based on the distribution and positional relationship of real-time feature points in the feature dataset within the baseline statistical features, including: Based on a preset time window length, the historical operation data of the cableway within the corresponding time period is extracted from the historical operation database to obtain a historical data sample set of the cableway. The baseline statistical characteristics of the cableway are obtained by analyzing the central trend and dispersion characteristics of each feature dimension in the historical data sample set. The real-time feature points in the feature dataset are matched with the baseline statistical features for distribution matching analysis. Based on the degree of deviation of the feature points from the historical distribution, the feature deviation data of the cableway is generated. The degree of anomaly of the cableway is quantitatively assessed based on the feature deviation data to obtain a preliminary anomaly score. The calculation formula for the preliminary anomaly score is as follows: ； In the formula, For preliminary anomaly scoring, The total number of feature points in the feature dataset. The ordinal number of the feature points in the feature dataset. For the feature deviation data, the first Pre-acquisition scaling factor parameters for each feature point Pi It is the arctangent function. For the feature deviation data, the first Preset weight parameters for each feature point For the feature deviation data, the first Deviation values ​​of each feature point; The initial anomaly scores are weighted and processed to obtain the initial anomaly state of the cableway; S5. The initial abnormal state is weighted and adjusted according to the real-time environmental parameters of the cableway to obtain the abnormal index of the cableway. S6. Synchronize the running data to the cloud server according to the priority corresponding to the abnormal indicators.

2. The edge computing and cloud synchronization method for cableway operation data as described in claim 1, characterized in that, The process of filtering out unwanted noise from the operating data collected by the cableway operation sensors at the edge computing node yields a standard dataset for the cableway, including: The edge computing nodes cache the operation data collected by the cableway operation sensors to obtain the raw data stream of the cableway; High-frequency noise components are removed from the original data stream to obtain preliminary filtered data for the cableway; Outlier removal is performed on the preliminary filtered data to obtain the effective data set of the cableway; The data format and units of the effective data set are standardized to obtain the standard dataset of the cableway.

3. The edge computing and cloud synchronization method for cableway operation data as described in claim 1, characterized in that, The mean, variance, and trend indicators of the statistical standard dataset are analyzed to obtain a time-domain feature subset of the cableway. Simultaneously, the dominant frequency components of the frequency-domain standardized dataset are extracted to obtain a frequency-domain feature subset of the cableway, including: The mean, variance, and trend characteristics of the data points in the standard dataset are statistically analyzed to obtain the intermediate time-domain results of the standard dataset. By retaining the statistical features in the intermediate time-domain results that meet the preset conditions, a subset of the time-domain features of the cableway is obtained; The frequency domain distribution data of the cableway is obtained by performing a frequency domain transformation on the standard dataset. The dominant frequency feature set of the cableway is obtained by identifying the frequency components with prominent amplitudes from the frequency domain distribution data. By removing redundant frequency components from the dominant frequency feature set, a frequency domain feature subset of the cableway is obtained.

4. The edge computing and cloud synchronization method for cableway operation data as described in claim 1, characterized in that, The weighted fusion of the time-domain feature subset and the frequency-domain feature subset to obtain the feature dataset of the cableway includes: Ensure that the feature points in the time-domain feature subset and the frequency-domain feature subset are consistent in the time dimension to obtain an aligned feature set; Based on the importance of the features in the cableway, fusion weights are assigned to the aligned feature set to obtain the weight allocation scheme of the cableway; According to the weight allocation scheme, the aligned feature set is weighted and combined to obtain the weighted feature set of the cableway; Remove highly correlated duplicate features from the weighted features to obtain the optimized feature set; The optimized feature set is standardized and encapsulated to obtain the feature dataset of the cableway.

5. The edge computing and cloud synchronization method for cableway operation data as described in claim 1, characterized in that, The step of weighting and adjusting the initial abnormal state based on the real-time environmental parameters of the cableway to obtain the abnormal indicators of the cableway includes: Obtain the real-time environmental parameters of the cableway and generate a set of environmental parameters for the cableway; Based on preset environmental impact rules, the set of environmental parameters is analyzed to determine the degree of influence of the set of environmental parameters on the cableway's operating status, and the environmental impact factor of the cableway is obtained. Based on the aforementioned environmental impact factors, an environmental adaptive adjustment coefficient for the cableway is constructed. The environmental adaptive adjustment coefficient is fused with the initial abnormal state to obtain the corrected abnormal state of the cableway; The abnormal state of the cableway is mapped to a standard evaluation scale to obtain the abnormal index of the cableway.

6. The edge computing and cloud synchronization method for cableway operation data as described in claim 5, characterized in that, The step of constructing the environmental adaptive adjustment coefficient of the cableway based on the environmental impact factors includes: Establish a correlation mapping between environmental parameters in the environmental parameter set and changes in the cableway's operating status to obtain the influence degree mapping relationship of the cableway. According to the cableway operation safety regulations, the threshold range of the environmental parameters is determined, and the safety boundary of the environmental parameters is obtained. The real-time environmental parameters of the cableway are compared with the safety boundary to obtain the boundary proximity index of the cableway. Based on the boundary proximity index and the influence degree mapping relationship, the current influence degree of the environmental parameters is comprehensively evaluated to obtain the environmental adaptive adjustment coefficient of the cableway.

7. The edge computing and cloud synchronization method for cableway operation data as described in claim 1, characterized in that, The step of synchronizing the operational data to the cloud server according to the priority corresponding to the abnormal indicators includes: Based on the numerical range of the abnormal indicators, the running data is divided into multiple priority categories to obtain the data priority classification result of the running data; Based on the data priority classification results, corresponding transmission resources are allocated to running data of different priorities to obtain the transmission resource allocation scheme for the running data; According to the aforementioned transmission resource allocation scheme, establish a transmission channel for the cloud server; The operational data is transmitted sequentially through the transmission channel according to priority.

8. An edge computing and cloud synchronization system for cableway operation data, characterized in that, The system includes: The data cleaning module is used to filter out useless noise from the operating data collected by the cableway operation sensors at the edge computing node, so as to obtain the standard dataset of the cableway. The data feature segmentation module is used to statistically analyze the mean, variance, and trend indicators of the standard dataset to obtain the time-domain feature subset of the cableway, and simultaneously extract the dominant frequency components of the frequency-domain standard dataset to obtain the frequency-domain feature subset of the cableway. The feature weighting module is used to weight and fuse the time-domain feature subset and the frequency-domain feature subset to obtain the feature dataset of the cableway; An abnormal state assessment module is used to extract baseline statistical features from the cableway's historical operation data within a sliding time window, and to assess the initial abnormal state of the cableway based on the distribution and positional relationships of real-time feature points in the feature dataset within the baseline statistical features. This includes: Based on a preset time window length, the historical operation data of the cableway within the corresponding time period is extracted from the historical operation database to obtain a historical data sample set of the cableway. The baseline statistical characteristics of the cableway are obtained by analyzing the central trend and dispersion characteristics of each feature dimension in the historical data sample set. The real-time feature points in the feature dataset are matched with the baseline statistical features for distribution matching analysis. Based on the degree of deviation of the feature points from the historical distribution, the feature deviation data of the cableway is generated. The degree of anomaly of the cableway is quantitatively assessed based on the feature deviation data to obtain a preliminary anomaly score. The calculation formula for the preliminary anomaly score is as follows: ； In the formula, For preliminary anomaly scoring, The total number of feature points in the feature dataset. The ordinal number of the feature points in the feature dataset. For the feature deviation data, the first Pre-acquisition scaling factor parameters for each feature point Pi It is the arctangent function. For the feature deviation data, the first Preset weight parameters for each feature point For the feature deviation data, the first Deviation values ​​of each feature point; The initial anomaly scores are weighted and processed to obtain the initial anomaly state of the cableway; An abnormal state correction module is used to adjust the initial abnormal state based on the real-time environmental parameters of the cableway to obtain the abnormal index of the cableway. The data transmission module is used to synchronize the running data to the cloud server according to the priority corresponding to the abnormal indicators.

Images