Spatial-temporal data alignment and fusion method based on equipment map driving

Abstract

The invention discloses a spatio-temporal data alignment and fusion method based on device map driving. The method comprises the following steps: device identification and mapping; aligning the time dimension data; and carrying out spatial dimension data alignment and spatio-temporal data fusion of a fusion device. According to the method, a mode of combining a domain model, forward reasoning, backward reasoning and hybrid reasoning is adopted, so that rapid and accurate diagnosis of the power grid fault reason is realized; a reasoning path is automatically optimized by introducing a reinforcement learning algorithm, so that the system can perform adaptive adjustment, the fault diagnosis and disposal efficiency is continuously improved, and the dependence on manual intervention is reduced; based on SCADA, PMU and intelligent sensor data acquired in real time, the system can quickly generate a corresponding scheduling instruction after a fault occurs, so that quick recovery of power supply of a power grid is realized; the multi-level and hierarchical fault classification and disposal scheme effectively improves the emergency response capability and safety of the power grid in a complex fault scene.

Description

Technical Field

[0001] This invention relates to the field of power system management, and in particular to a spatiotemporal data alignment and fusion method based on device map-driven approach. Background Technology

[0002] The safe and stable operation of modern power systems relies on precise dispatching and equipment monitoring. Especially in the context of smart grids, the rapid increase in equipment, sensors, and data acquisition terminals has generated a massive amount of multi-source heterogeneous data. This data comes not only from different power equipment and sensors but also from other external systems such as meteorological and GIS data, exhibiting diverse formats, timestamps, and transmission protocols. Therefore, effectively aligning and fusing multi-source data to improve the real-time monitoring accuracy and dispatching decision-making capabilities of power systems has become a major challenge in the current technological field. However, most existing data processing methods fail to fully consider the temporal alignment of multi-source data and the dynamic enhancement of data quality. This results in the inability to guarantee the temporal consistency and accuracy of data when faced with equipment response time delays, network transmission latency, and external environmental interference, thus limiting the performance of power systems in real-time response and decision support.

[0003] Chinese patent CN117350447A discloses a multi-source heterogeneous power data fusion algorithm applicable to power grids. This method uses intelligent algorithms to fuse data from different devices and sensors, aiming to improve the operating efficiency and fault detection capabilities of the power grid. While this technology has made some progress in multi-source data fusion, it still fails to effectively guarantee data synchronization when dealing with issues such as power equipment response time delays and network transmission latency, making it difficult to achieve time-series consistency. Furthermore, this technology fails to fully utilize dynamic data augmentation techniques, thus affecting data quality and classification accuracy. Especially when facing complex power systems and sudden events, the system's response capability still needs improvement.

[0004] Chinese Patent CN119149904A discloses a method for aligning multi-source data in power systems, focusing on ensuring time-series alignment of different data sources through delay estimation and data synchronization techniques. While this technology has achieved some success in solving data synchronization problems in power systems, its processing capabilities for high-frequency data and complex power equipment remain insufficient. Specifically, in environments with large-scale equipment and multiple real-time data sources, existing synchronization methods still cannot meet the timeliness and accuracy requirements for real-time scheduling and fault diagnosis. Furthermore, existing solutions fail to adequately consider how to utilize dynamic data augmentation techniques to address equipment and environmental interference, improve data quality, and thus optimize the decision support capabilities of the power system. Summary of the Invention

[0005] Purpose of the invention: The purpose of this invention is to provide a spatiotemporal data alignment and fusion method based on device map-driven approach.

[0006] Technical solution: The present invention includes the following steps:

[0007] (1) Equipment identification and mapping;

[0008] (2) Time dimension data alignment;

[0009] (3) Spatial dimension data alignment;

[0010] (4) Spatiotemporal data fusion of fusion devices.

[0011] Furthermore, step (1) includes a unique device identifier and a device data mapping.

[0012] Furthermore, the unique device identifier employs a unique identification method that includes device type, installation location, manufacturer, device model, and operating history.

[0013] Furthermore, the device data mapping automatically identifies and adapts to the data formats and communication protocols of different devices by introducing intelligent protocol recognition and dynamic data format conversion technology; by introducing adaptive standardization algorithms, the system automatically identifies the differences between different devices; and by integrating machine learning and data pattern recognition technologies, the system automatically adjusts the mapping rules when devices are changed, upgraded, or added.

[0014] Furthermore, step (2) includes unified data stamping and delay compensation.

[0015] Furthermore, the delay compensation mechanism includes:

[0016] The timestamp T of device i i (t) and the timestamp T of device j j There is a time delay ΔT between (t) and ij The data alignment process can then be represented as:

[0017] T j (t)=T i (t)+ΔT ij

[0018] The dynamic time alignment mechanism can dynamically adjust the time alignment when device response time or network transmission latency changes. The mathematical model is expressed as:

[0019] T corrected (t)=T(t)+ΔT dynamic (t)

[0020] Where: T(t) is the original timestamp, ΔTdynamic (t) is the dynamically adjusted time delay.

[0021] Furthermore, step (4) includes spatiotemporal coordination, device-based spatiotemporal analysis model, and dynamic spatiotemporal correction and optimization.

[0022] Furthermore, the spatiotemporal coordination includes:

[0023] Assume the health state S(t) of the equipment is a joint function of time t and spatial location p, expressed by the following formula:

[0024] S(t,p)=f(T(t),P(p),E(t,p))

[0025] Where T(t) is the temporal behavior of the device, P(p) is the spatial location of the device, and E(t,p) is a function of environmental factors that change with time and space.

[0026] Furthermore, the device-based spatiotemporal analysis model includes:

[0027] Assuming that the health status of equipment is jointly determined by its temporal and spatial location, equipment load, and environmental influences, the following regression model can be used to describe the health status of the equipment:

[0028] H(t,p)=α0+α1T(t)+α2P(p)+α3L(t,p)+α4E(t,p)

[0029] Where: H(t, p) is the health status function of the equipment, reflecting the health status of the equipment in the time and space dimensions; α0, α1, α2, α3, α4 are regression coefficients obtained by fitting historical data; T(t), P(p), L(t, p) and E(t, p) are the equipment's temporal behavior, spatial location, load and environmental factors, respectively.

[0030] Furthermore, the dynamic spatiotemporal correction and optimization includes:

[0031] A dynamic spatiotemporal correction mechanism is introduced, which dynamically adjusts the parameters in the spatiotemporal analysis model by monitoring the device's response time and changes in environmental data in real time. This is achieved through a feedback control system, in which the device state is adjusted according to environmental changes and spatiotemporal deviations.

[0032] H(t,p)=H(t,p)+ΔH(t,p)

[0033] Wherein, ΔH(t, p) is the correction amount caused by time delay and spatial deviation, adjusted through a real-time feedback mechanism. The calculation of the correction amount depends on the difference between the device's historical data and real-time monitoring data.

[0034] Beneficial Effects: Compared with existing technologies, this invention has the following significant advantages: It employs a combination of domain models, forward reasoning, backward reasoning, and hybrid reasoning to achieve rapid and accurate diagnosis of power grid fault causes; by introducing reinforcement learning algorithms to automatically optimize the reasoning path, the system can adaptively adjust and continuously improve the efficiency of fault diagnosis and handling, reducing reliance on manual intervention; based on real-time collected SCADA, PMU, and smart sensor data, the system can quickly generate corresponding dispatch instructions after a fault occurs, thereby achieving rapid restoration of power grid supply. The multi-level, hierarchical fault classification and handling scheme effectively improves the emergency response capability and safety of the power grid in complex fault scenarios. Attached Figure Description

[0035] Figure 1 This is a flowchart of the present invention;

[0036] Figure 2 Flowchart for device data mapping;

[0037] Figure 3 This is a flowchart for dynamic time delay correction. Detailed Implementation

[0038] The technical solution of the present invention will be further described below with reference to the accompanying drawings.

[0039] like Figure 1 As shown, the present invention includes the following steps:

[0040] (1) Equipment Identification and Mapping

[0041] (1.1) Unique Device Identifier

[0042] Equipment identification and mapping is one of the core technologies for equipment identification, data exchange, and cross-system integration in power systems. To ensure accurate matching and efficient data flow among devices within a power system, each device must have a unique identifier. This identifier is not merely a simple number; it carries various attribute information about the device, such as equipment type, installation location, manufacturer, model, and operational history. To minimize identifier conflicts between devices, globally unique identification methods (such as UUIDs) are used, and these identifiers are closely linked to the device's lifecycle management information, ensuring accurate tracking and recording of data throughout the device's lifecycle.

[0043] In power systems, equipment identifiers are used not only to distinguish different devices but also to associate them with multiple subsystems. For example, power dispatching systems, monitoring systems, and GIS (Geographic Information Systems) all rely on these unique identifiers to accurately locate and identify equipment. The use of equipment identifiers must also ensure cross-platform compatibility to avoid identification errors or data loss due to inconsistent formats across different platforms.

[0044] (1.2) Device Data Mapping

[0045] Equipment data mapping is a key technology for achieving information sharing and integration among devices in power systems. With the expansion of power system scale and the increase in equipment types, the diversity and complexity of data sources are becoming increasingly prominent. In this context, equipment data mapping must break through the limitations of traditional static rules and adopt more innovative solutions to ensure efficient and accurate data exchange between different devices. In this process, the effective integration of data formats, protocol standards, and device identifiers is crucial, and mapping rules must possess high flexibility and scalability to cope with increasingly complex equipment and data environments.

[0046] To achieve cross-system and cross-platform data integration, a unified data format and protocol must first be adopted. This is not merely a simple data conversion issue, but rather ensuring the consistency and reliability of data throughout its entire lifecycle. By introducing intelligent protocol recognition and dynamic data format conversion technologies, the system can automatically identify and adapt to the data formats and communication protocols of different devices. For example, for data from different sources such as sensors, SCADA systems, and GIS systems, the system can intelligently identify the data source type and adjust the data format according to the real-time status and needs of the devices. This dynamic adaptation mechanism reduces manual intervention while improving the real-time performance and accuracy of data exchange. Based on data formats such as JSON and XML, and with optimizations to communication protocols such as Modbus and OPC, seamless data connection and conversion between devices are achieved.

[0047] Besides standardizing data formats, data standardization and preprocessing are also key innovations in device data mapping. In power systems, different devices may use different units, ranges, or data precisions, and these differences often lead to information loss or inconsistencies during data processing. By introducing adaptive standardization algorithms, the system can automatically identify differences between different devices and perform unit conversion, precision matching, and attribute unification in real time. For example, power data may be in kilowatts (kW) and megawatts (MW), and sensor temperature data may use different precision standards. Through adaptive standardization, these data can be uniformly converted, ensuring that information is not erroneous due to inconsistent units or precision differences during subsequent data analysis, processing, and display.

[0048] The design of equipment data mapping rules is crucial for ensuring efficient data flow and accurate interpretation. To adapt to the variability of equipment and data sources in power systems, mapping rules should possess intelligent and dynamic adjustment capabilities. By integrating machine learning and data pattern recognition technologies, the system can automatically adjust mapping rules when equipment is changed, upgraded, or added. Specifically, the system can analyze new equipment data formats and interaction requirements in real time, automatically generating or optimizing existing mapping rules. In this way, as the types of equipment continue to increase, the data integration capability of the power system can be continuously improved without human intervention. This self-learning mechanism provides strong data support for the long-term operation of large-scale power systems, greatly enhancing the system's flexibility and scalability.

[0049] In large-scale power systems, equipment hierarchies are complex, and the data structures and attributes of different devices vary significantly. Multi-level data mapping and virtualization management offer an innovative solution. Virtualization technology allows for hierarchical management of equipment data, resolving the mapping challenges arising from the diverse types and complex hierarchies of equipment. Mapping data from different equipment levels (such as transformers, circuit breakers, and protection devices in a substation) requires consideration not only of the equipment's inherent attributes but also its location and function within the system. Virtualization management unifies the management of data from different equipment levels, enabling the data to flow and exchange within the same platform, thereby improving the overall system efficiency and operability.

[0050] (2) Time dimension data alignment

[0051] (2.1) Unified Data Stamp

[0052] Time-dimensional data alignment is crucial for ensuring that device data from different data sources can be analyzed and processed synchronously on the same time scale. To achieve time alignment, all collected data needs to be assigned a unified timestamp to accurately pinpoint the collection time of each data point and enable smooth time correlation between different data sources. To eliminate the impact of time zone differences, systems typically adopt a globally unified time standard, such as Coordinated Universal Time (UTC), and convert all collected data into UTC timestamps. Using a unified UTC time ensures data temporal consistency, providing a precise time basis for subsequent data integration and analysis.

[0053] (2.2) Delay Compensation

[0054] In practical applications, factors such as device response latency, data transmission latency, and differences in device sampling frequencies can lead to time discrepancies between different data sources. To address this issue, systems typically employ time synchronization mechanisms to ensure that data from different devices and sensors are time-aligned. Common time synchronization technologies include Network Time Protocol (NTP), Global Positioning System (GPS) synchronization, and IEEE 1588 Precision Time Protocol (PTP). NTP is widely used to synchronize device time, ensuring they operate based on a unified standard time; while PTP is suitable for scenarios requiring high precision, providing microsecond-level time synchronization, which is crucial, especially in real-time data analysis. Through these synchronization mechanisms, systems can ensure that data from different devices and sensors are time-aligned, reducing erroneous analysis and judgments caused by time discrepancies.

[0055] While time synchronization mechanisms provide a unified time reference for devices, slight time deviations may still exist in the data during actual acquisition and transmission due to factors such as network latency, device response time, and differences in sampling frequency. If these deviations are not compensated for, they can affect the accuracy of the analysis, especially in applications like power systems that require high-precision time series analysis. To ensure accurate alignment in the time dimension, delay compensation algorithms have emerged. These algorithms can predict and correct time deviations caused by network transmission, device response, and other factors. Through intelligent algorithms or pattern recognition based on historical data, they compensate for delays, thereby improving data synchronization and the reliability of analysis results.

[0056] A dynamic time delay correction mechanism can further optimize the time delay correction process. This mechanism continuously monitors the synchronization between device data and historical data, and automatically adjusts the data timestamp by combining real-time analysis of latency changes in the data stream. This mechanism can not only adapt to changes in device response time or network transmission latency, but also dynamically adjust the time alignment based on latency changes in the real-time data stream.

[0057] The timestamp T of device i i (t) and the timestamp T of device j j There is a time delay ΔT between (t) and ij The data alignment process can then be represented as:

[0058] T j (t)=T i (t)+ΔT ij

[0059] A dynamic time delay correction mechanism can further optimize time delay correction. This mechanism continuously monitors the synchronization between device data and historical data, and automatically adjusts data timestamps by analyzing latency changes in the data stream in real time. Through real-time monitoring of the data source, this correction mechanism can dynamically adjust the time alignment when device response time or network transmission latency changes. The mathematical model for this process can be expressed as:

[0060] T corected (t)=T(t)+ΔT dynamic (t)

[0061] Where: T(t) is the original timestamp, ΔT dynamic (t) represents the dynamically adjusted time delay, which is continuously adjusted over time based on the synchronization of real-time data. The dynamic adjustment mechanism monitors the delay changes of each data source in real time, utilizing synchronization patterns in historical data and variation patterns in real-time data to adjust the timestamp correction value. This mechanism typically relies on a feedback control system that dynamically adjusts the delay correction parameters by comparing time differences between devices.

[0062] (3) Spatial dimension data alignment

[0063] (3.1) Unified coordinate system

[0064] The core task of spatial data alignment is to ensure that equipment data from different regions and spatial locations can be effectively integrated and compared under a unified coordinate system. In power systems, equipment is typically distributed across vast geographical areas, involving a wide variety of equipment types, and these devices may be affected by different geographical environments, climatic conditions, and operating environments. For example, substations may be located in urban areas, while high-voltage transmission lines cross mountains, forests, and other regions. The geographical distribution differences of equipment necessitate the use of a unified and high-precision coordinate system when performing spatial data alignment.

[0065] To ensure accurate and consistent spatial positioning of equipment, the system typically selects a globally standardized geographic coordinate system, such as the WGS-84 coordinate system. This coordinate system provides globally unique and accurate spatial positioning for equipment, representing its specific location through longitude and latitude information. In power systems, the spatial position of each piece of equipment should be clearly marked in this coordinate system to ensure accurate location and display of the equipment in a Geographic Information System (GIS). The accuracy of the coordinate data is particularly important in this process, as it directly affects the accuracy of subsequent operations such as distance measurement between equipment, power flow analysis, and fault diagnosis.

[0066] In practical applications, the location of equipment may change slightly due to environmental changes (such as facility upgrades, road construction, etc.), thus requiring regular updates to the equipment's location coordinates. By employing modern positioning technologies, such as GPS and remote sensing, changes in the equipment's location can be tracked in real time, ensuring the updating and maintenance of the coordinate system and supporting continuous alignment of spatial data.

[0067] (3.2) Constructing the spatial topology

[0068] In power systems, equipment not only requires precise geographical location, but also a clear understanding of the geographical relationships between equipment, especially their electrical connections. The construction of spatial topology networks is a crucial component of spatial alignment, providing a visually intuitive and structured spatial view of the power system through the spatial locations and electrical connections of the equipment.

[0069] Spatial topology focuses not only on the physical location of equipment but also on the power flow, control, and communication relationships between them. By constructing a spatial topology network, equipment in a power system can be categorized according to geographical location, and a comprehensive analysis can be conducted based on the relative positions of the equipment, physical connections (such as power lines and substations), and power transmission relationships. This type of analysis helps to deeply understand key issues such as equipment function, potential fault propagation paths, power flow, and load distribution, playing a crucial role, especially in power system fault diagnosis and emergency response.

[0070] For example, the geographical location and electrical connections of substations and transmission lines directly affect the stability and fault propagation of the power system. By constructing spatial topology, the system can simulate power flow and its propagation patterns between devices, identify interactions between devices, and identify potential fault points in advance. For instance, if a substation experiences a fault, topology analysis can help determine whether this fault will lead to overload or power outages on downstream lines, thus providing dispatchers with crucial decision-making information.

[0071] The construction of spatial topology can be further optimized by integrating Geographic Information System (GIS) data with power system data. A GIS platform can combine spatial and electrical data of power equipment to achieve linked analysis of equipment location and power flow. Simultaneously, through intelligent algorithms and big data analytics, the topology network can be updated in real time, dynamically monitoring the operating status of power equipment, fault locations, and power transmission paths, thereby improving the operating efficiency and fault handling capabilities of the power system.

[0072] (4) Spatiotemporal data fusion of fusion devices

[0073] (4.1) Spatiotemporal collaboration

[0074] The fusion of spatiotemporal data from equipment refers to the comprehensive processing of equipment data across both temporal and spatial dimensions to more accurately achieve goals such as fault prediction, status monitoring, and performance optimization. As power systems become increasingly complex, equipment not only needs real-time monitoring of its health status and load changes, but also requires consideration of the impact of environmental factors and geographical location on its operation. This makes the fusion of spatiotemporal data from equipment particularly important, providing a comprehensive and multi-dimensional perspective to support decision-making and system optimization.

[0075] Spatiotemporal fusion is a key technology in this process. It comprehensively analyzes the operating status of equipment by combining its temporal behavior (such as load changes and failure occurrences) with spatial distribution information (such as equipment location and environmental influences). For example, the health status of equipment is not only affected by factors such as load and temperature, but also closely related to its environmental conditions, location, and interactions with other equipment. These factors, varying across different time and spatial dimensions, intertwine to influence equipment performance and failure modes.

[0076] To mathematically express this spatiotemporal collaborative process, we can use a spatiotemporal joint probability model to describe the relationship between the device's health state and its location. Assuming the device's health state S(t) is a joint function of time t and spatial location p, it can be expressed by the following formula:

[0077] S(t,p)=f(T(t),P(p),E(t,p))

[0078] Where: T(t) is the temporal behavior of the equipment (e.g., load changes, working cycle, etc.), P(p) is the spatial location of the equipment (e.g., the geographical coordinates of the equipment), and E(t, p) is a function of environmental factors (e.g., climate, temperature, humidity, etc.) as they change with time and space.

[0079] (4.2) Based on the equipment spatiotemporal analysis model

[0080] Spatiotemporal data fusion methods based on equipment spatiotemporal analysis models can provide targeted analysis solutions for spatiotemporal data of different equipment in power systems. Power systems contain a wide variety of equipment, each with potentially different operating modes, fault characteristics, and environmental adaptability. Therefore, when performing spatiotemporal data fusion, it is necessary to establish independent spatiotemporal analysis models for each type of equipment to ensure that the assessment of its operating status and potential faults is targeted and accurate.

[0081] The construction of spatiotemporal analysis models is based on multi-dimensional data of equipment, including spatial location information, historical fault records, real-time monitoring data, and environmental data. This information helps analyze the behavioral patterns of equipment under different loads, environmental conditions, and operating states. For example, for different equipment within a substation, spatiotemporal analysis models can combine information such as equipment health status, grid load, and climate data to predict equipment failure risks and assess the reliability and maintenance requirements of equipment under different operating conditions.

[0082] In power systems, each type of equipment operates under different conditions and exhibits different fault characteristics. Therefore, it is necessary to establish independent spatiotemporal analysis models for each type of equipment. By analyzing the behavioral patterns of equipment in different time and spatial dimensions, the health status of the equipment can be dynamically assessed, further supporting intelligent scheduling and load allocation. To achieve this, a spatiotemporal regression model can be used to fit the spatiotemporal data of the equipment. Assuming that the health status of the equipment is jointly determined by the equipment's temporal and spatial location, load, and environmental influences, we can use the following regression model to describe the health status of the equipment:

[0083] H(t,p)=α0+α1T(t)+α2P(p)+α3L(t,p)+α4E(t,p)

[0084] Where: H(t, p) is the health status function of the equipment, reflecting the health status of the equipment in the time and space dimensions; α0, α1, α2, α3, α4 are regression coefficients obtained by fitting historical data; T(t), P(p), L(t, p) and E(t, p) are the equipment's temporal behavior, spatial location, load and environmental factors, respectively.

[0085] (4.3) Dynamic spatiotemporal correction and optimization

[0086] To further optimize the spatiotemporal data fusion process, especially when the operating status of equipment is affected by environmental changes, load fluctuations, and other factors, we can introduce a dynamic spatiotemporal correction mechanism. This mechanism dynamically adjusts the parameters in the spatiotemporal analysis model by monitoring the equipment's response time and changes in environmental data in real time. This can be achieved through a feedback control system, where the equipment status adjusts according to environmental changes and spatiotemporal deviations.

[0087] H(t,p)=H(t,p)+ΔH(t,p)

[0088] Wherein: ΔH(t, p) is the correction amount caused by time delay and spatial deviation, which can be adjusted through a real-time feedback mechanism. The calculation of the correction amount depends on the difference between the device's historical data and real-time monitoring data.

[0089] The goal of the dynamic correction mechanism is to automatically adjust the parameters in the spatiotemporal analysis model by monitoring the synchronization between device data and historical data in real time, taking into account latency and environmental changes, to ensure accurate alignment of device data in time and space. Through this correction mechanism, the system can adapt to factors such as device response time, load fluctuations, and changes in the external environment, optimizing the spatiotemporal data fusion process.

Claims

1. A spatiotemporal data alignment and fusion method based on device map-driven approach, characterized in that, Includes the following steps; (1) Equipment identification and mapping; (2) Time dimension data alignment; (3) Spatial dimension data alignment; (4) Spatiotemporal data fusion of fusion devices.

2. The spatiotemporal data alignment and fusion method based on device map driving according to claim 1, characterized in that, Step (1) includes a unique device identifier and device data mapping.

3. The spatiotemporal data alignment and fusion method based on device map driving according to claim 2, characterized in that, The unique device identifier uses a unique identification method that includes device type, installation location, manufacturer, device model, and operating history.

4. The spatiotemporal data alignment and fusion method based on device map driving according to claim 2, characterized in that, The device data mapping automatically identifies and adapts to the data formats and communication protocols of different devices by introducing intelligent protocol recognition and dynamic data format conversion technology; by introducing adaptive standardization algorithms, the system automatically identifies the differences between different devices; and by integrating machine learning and data pattern recognition technologies, the system automatically adjusts the mapping rules when devices are changed, upgraded, or added.

5. The spatiotemporal data alignment and fusion method based on device map driving according to claim 1, characterized in that, Step (2) includes unified data stamping and delay compensation.

6. The spatiotemporal data alignment and fusion method based on device map driving according to claim 5, characterized in that, The delay compensation mechanism includes: The timestamp T of device i i (t) and the timestamp T of device j j There is a time delay ΔT between (t) and ij The data alignment process can then be represented as: T j (t)=T i (t)+ΔT ij The dynamic time alignment mechanism can dynamically adjust the time alignment when device response time or network transmission latency changes. The mathematical model is expressed as: T corrected (t)=T(t)+ΔT dynamic (t) Where: T(t) is the original timestamp, ΔT dynamic (t) is the dynamically adjusted time delay.

7. The spatiotemporal data alignment and fusion method based on device map driving according to claim 1, characterized in that, Step (4) includes spatiotemporal coordination, device-based spatiotemporal analysis model, and dynamic spatiotemporal correction and optimization.

8. The spatiotemporal data alignment and fusion method based on device map driving according to claim 7, characterized in that, The spatiotemporal coordination includes: Assume the health state S(t) of the equipment is a joint function of time t and spatial location p, expressed by the following formula: S(t,p)=f(T(t),P(p),E(t,p)) Where T(t) is the temporal behavior of the device, P(p) is the spatial location of the device, and E(t,p) is a function of environmental factors that change with time and space.

9. The spatiotemporal data alignment and fusion method based on device map driving according to claim 7, characterized in that, The device-based spatiotemporal analysis model includes: Assuming that the health status of equipment is jointly determined by its temporal and spatial location, equipment load, and environmental influences, the following regression model can be used to describe the health status of the equipment: H(t,p)=α0+α1T(t)+α2P(p)+α3L(t,p)+α4E(t,p) Where: H(t, p) is the health status function of the equipment, reflecting the health status of the equipment in the time and space dimensions; α0, α1, α2, α3, α4 are regression coefficients obtained by fitting historical data; T(t), P(p), L(t, p) and E(t, p) are the equipment's temporal behavior, spatial location, load and environmental factors, respectively.

10. The spatiotemporal data alignment and fusion method based on device map driving according to claim 7, characterized in that, The dynamic spatiotemporal correction and optimization include: A dynamic spatiotemporal correction mechanism is introduced, which dynamically adjusts the parameters in the spatiotemporal analysis model by monitoring the device's response time and changes in environmental data in real time. This is achieved through a feedback control system, in which the device state is adjusted according to environmental changes and spatiotemporal deviations. H(t,p)=H(t,p)+ΔH(t,p) Wherein, ΔH(t, p) is the correction amount caused by time delay and spatial deviation, adjusted through a real-time feedback mechanism. The calculation of the correction amount depends on the difference between the device's historical data and real-time monitoring data.

Images