Time unification method for low-altitude identification marks based on TSN

Abstract

The invention relates to the technical field of time-sensitive networks, and discloses a TSN-based low-altitude identification mark time unification method, which adopts a TSN-based low-altitude identification mark time unification technology, breaks through the limitation of a traditional clock synchronization method, and improves the time unification efficiency. Accurate clock calibration and synchronization can be provided in a high dynamic environment. Compared with the prior art, the method has the advantages that by combining multiple data acquisition, real-time master and slave clock monitoring and a feedback mechanism, the system can continuously optimize the precision of clock synchronization under different time scales, and the adaptive capacity of the system to external changes is remarkably improved. Meanwhile, the multi-level and multi-dimensional synchronization scheme can effectively reduce clock drift and errors and provide more reliable time reference support, so that the low-altitude identification mark system shows higher stability and accuracy in high-precision space-time positioning and task execution.

Description

Technical Field

[0001] The present invention relates to the technical field of time-sensitive networks, and in particular to a time unification method for low-altitude identification marks based on TSN. Background Art

[0002] Time-Sensitive Networking (TSN), a key technology in the fields of the Industrial Internet, intelligent transportation, and next-generation network communications, is primarily used to achieve low-latency, high-precision, synchronous transmission of multi-source information in complex communication environments. Within the TSN technical architecture, time synchronization is fundamental to achieving coordinated operation of communication nodes, task scheduling, and information fusion. In particular, in low-altitude airspace applications, such as low-altitude target identification and drone swarm collaboration, precise time synchronization directly impacts the reliability and real-time performance of identification results. In these applications, to improve the time consistency and data fusion efficiency of master-slave communication links, TSN-based clock synchronization mechanisms have become a core focus of research and engineering practice.

[0003] At present, in low-altitude identification systems, although a TSN-based time synchronization protocol has been adopted, there are several key problems that are difficult to overcome: first, time drift is easily generated between the initial synchronization and the real-time state, affecting the recognition accuracy; second, the existing synchronization methods are relatively extensive in processing and fusing multi-source data, and fail to fully explore the temporal correlation between various feature parameters; third, the lack of an effective drift monitoring and calibration feedback mechanism leads to a delayed response to abnormal fluctuations or a failure of correction.

[0004] Therefore, we propose a time-unified method for low-altitude identification signs based on TSN to solve the above problems. Summary of the Invention

[0005] The purpose of the present invention is to provide a time unification method for low-altitude identification signs based on TSN to solve the problem proposed in the above background technology that time drift is easily generated between the initial synchronization and the real-time state, affecting the recognition accuracy. The existing synchronization method is relatively extensive in processing and fusing multi-source data, fails to fully explore the temporal correlation between various feature parameters, lacks an effective drift monitoring and calibration feedback mechanism, and causes the system to respond to abnormal fluctuations with lag or correction failure.

[0006] To achieve the above object, the present invention provides the following technical solutions: A time unification method for low-altitude identification signs based on TSN is characterized by the following specific steps: S1, initial collection, collecting multi-source data on the system's initial communication link and performing preprocessing to generate a first data set and a second data set; S2. Master-slave clock synchronization, data coupling of the first data group and the second data group, thereby generating an initial master clock coupling coefficient ZYS and an initial slave clock coupling coefficient CYS, and performing data analysis on the two; S3, re-collecting, collecting multi-source data through a secondary communication link of the system, and performing pre-processing to generate a third data group and a fourth data group; S4, master-slave time monitoring, performing data coupling on the third data group and the fourth data group to generate a real-time master clock coupling coefficient ZRS and a real-time slave clock coupling coefficient CRS, and analyzing the real-time master clock coupling coefficient ZRS and the real-time slave clock coupling coefficient CRS; S5. Master-slave time calibration: data coupling is performed on the initial master clock coupling coefficient ZYS, the initial slave clock coupling coefficient CYS, the real-time master clock coupling coefficient ZRS, and the real-time slave clock coupling coefficient CRS to generate calibration coefficients, and the calibration coefficients are analyzed. S6. Feedback: Feedback all data and analysis results to the visualization terminal.

[0007] Preferably, in step S1, the specific steps of initial collection are as follows: S1.1. Data acquisition: by deploying a multifunctional sensor group and background acquisition software, multi-source information data can be acquired; S1.2. Preprocessing and dimensionlessizing the collected multi-source data, and reorganizing them into a first data group and a second data group; The first data group includes the main signal reception delay ZYA, the main round-trip delay ZYB, the main communication signal-to-noise ratio ZYC, the main synchronization frame efficiency ZYD, the main current offset ZYE, the main offset change rate ZYF, the main frequency stability ZYH and the main calibration feedback error ZYL; The second data group includes slave signal reception delay CYA, slave round-trip delay CYB, slave communication signal-to-noise ratio CYC, slave synchronization frame effectiveness rate CYD, slave current offset CYE, slave offset change rate CYF, slave frequency stability CYH, and slave calibration feedback error CYL.

[0008] Preferably, in step S2, the specific steps of master-slave clock synchronization are as follows: S2.1. Data coupling is performed on the first data set. Multiple data points within the data set are input into a pre-trained deep learning framework. Feature fusion is performed through a multi-layer neural network to calculate the initial master clock coupling coefficient ZYS. The specific calculation formula is as follows; Where: ZYA is the main signal reception delay, ZYB is the main round-trip delay, ZYC is the main communication signal-to-noise ratio, ZYD is the main synchronization frame efficiency, ZYE is the main current offset, ZYF is the main offset change rate, ZYH is the main frequency stability, and ZYL is the main calibration feedback error. S2.2. Data coupling is performed on the second data set. Multiple data points in the data set are input into a pre-trained deep learning framework. Feature fusion is performed through a multi-layer neural network to calculate the initial slave clock coupling coefficient CYS. The specific calculation formula is as follows; Where: CYA is the slave signal reception delay, CYB is the slave round-trip delay, CYC is the slave communication signal-to-noise ratio, CYD is the slave synchronization frame efficiency, CYE is the slave current offset, CYF is the slave offset change rate, CYH is the slave frequency stability, and CYL is the slave calibration feedback error; S2.3. Perform a joint analysis on the calculated initial master clock coupling coefficient ZYS and the initial slave clock coupling coefficient CYS. Based on the analysis results, determine whether the error between the two is reasonable. The specific method is as follows: when When , it means that the error between the initial master clock coupling coefficient ZYS and the initial slave clock coupling coefficient CYS is within a reasonable range and no initialization is required; when When , it means that the error between the initial master clock coupling coefficient ZYS and the initial slave clock coupling coefficient CYS is in an unreasonable range and needs to be initialized.

[0009] Preferably, in step S3, the specific steps of collecting are as follows: S3.1. Data acquisition: acquiring multi-source information data by deploying a multi-functional sensor group and background acquisition software; S3.2. Preprocess and dimensionlessly transform the collected multi-source data, and reorganize them into a third data set and a fourth data set; The third data group includes the main real-time signal reception delay ZRA, the real-time main round-trip delay ZRB, the real-time main communication signal-to-noise ratio ZRC, the real-time main synchronization frame efficiency ZRD, the real-time main current offset ZRE, the real-time main offset change rate ZRF, the real-time main frequency stability ZRH and the real-time main calibration feedback error ZRL; The fourth data group includes real-time signal reception delay CRA, real-time round-trip delay CRB, real-time communication signal-to-noise ratio CRC, real-time synchronization frame efficiency CRD, real-time current offset CRE, real-time offset change rate CYRF, real-time frequency stability CRH and real-time calibration feedback error CRL.

[0010] Preferably, in step S4, the master-slave time monitoring method is as follows: S4.1. Data coupling is performed on the third data set. Multiple data points within the data set are input into a pre-trained deep learning framework. Feature fusion is performed using a multi-layer neural network to calculate the real-time master clock coupling coefficient ZRS. The specific calculation formula is as follows; Where: ZRA is the main real-time signal reception delay, ZRB is the real-time main round-trip delay, ZRC is the real-time main communication signal-to-noise ratio, ZRD is the real-time main synchronization frame efficiency, ZRE is the real-time main current offset, ZRF is the real-time main offset change rate, ZRH is the real-time main frequency stability, and ZRL is the real-time main calibration feedback error; S4.2. Data coupling is performed on the fourth data group. Multiple data points in the data group are input into a pre-trained deep learning framework. Feature fusion is performed through a multi-layer neural network to calculate the real-time slave clock coupling coefficient CRS. The specific calculation formula is as follows; Where: CRA is the real-time slave signal reception delay, CRB is the real-time slave round-trip delay, CRC is the real-time slave communication signal-to-noise ratio, CRD is the real-time slave synchronization frame efficiency, CRE is the real-time slave current offset, CRF is the real-time slave offset change rate, CRH is the real-time slave frequency stability, and CRL is the real-time slave calibration feedback error; S4.3. Analyze the calculated initial master clock coupling coefficient ZYS, initial slave clock coupling coefficient CYS, real-time master clock coupling coefficient ZRS, and real-time slave clock coupling coefficient CRS. Based on the analysis results, determine whether data drift correction is required. The specific method is as follows: when When , it means that the error between the initial master clock coupling coefficient ZYS and the real-time master clock coupling coefficient ZRS is within a reasonable range, and no drift correction is required; when When , it means that the error between the initial master clock coupling coefficient ZYS and the real-time master clock coupling coefficient ZRS is in an unreasonable range and drift correction is required; when When , it means that the error between the initial slave clock coupling coefficient CYS and the real-time slave clock coupling coefficient CRS is within a reasonable range and no drift correction is required; when When , it means that the error between the initial slave clock coupling coefficient CYS and the real-time slave clock coupling coefficient CRS is in an unreasonable range and drift correction is required.

[0011] Preferably, in step S5, the master-slave time calibration is performed in the following manner: S5.1. Extract additional data and preprocess and dimensionlessly convert the extracted data, including the recent drift mean DR1, drift change standard deviation DR2, calibration response delay DR3, calibration influence index DR4, and self-correction index DR5. S5.2. Input the processed data into a pre-trained deep learning framework, perform feature fusion through a multi-layer neural network, and then calculate the drift correction coefficient PYX. The specific calculation formula is as follows;

[0012] Where: DR1 is the recent drift mean, DR2 is the drift change standard deviation, DR3 is the calibration response delay, DR4 is the calibration influence index, and DR5 is the self-correction index; S5.3. Perform a coupling analysis on the drift correction coefficient PYX and the real-time master clock coupling coefficient ZRS. Based on the analysis results, determine the effectiveness of the drift correction coefficient PYX in optimizing the real-time master clock coupling coefficient ZRS. S5.4. Perform coupling analysis on the drift correction coefficient PYX and the real-time slave clock coupling coefficient CRS. Based on the analysis results, determine the effectiveness of the drift correction coefficient PYX in optimizing the real-time slave clock coupling coefficient CRS.

[0013] Preferably, in step S5.3, the specific analysis method is as follows: when When , it means that the error between the initial master clock coupling coefficient ZYS and the real-time master clock coupling coefficient ZRS is within a reasonable range, and the drift correction coefficient PYX is valid; when When , it means that the error between the initial master clock coupling coefficient ZYS and the real-time master clock coupling coefficient ZRS is in an unreasonable range, and the drift correction coefficient PYX is invalid.

[0014] Preferably, in step S5.4, the specific analysis method is as follows: when When , it means that the error between the initial slave clock coupling coefficient CYS and the real-time slave clock coupling coefficient CRS is within a reasonable range, and the drift correction coefficient PYX is valid; At that time, it means that the error between the initial slave clock coupling coefficient CYS and the real-time slave clock coupling coefficient CRS is in an unreasonable range, and the drift correction coefficient PYX is invalid.

[0015] Compared with the prior art, the present invention has the following beneficial effects: 1. This method uses the time unification technology of low-altitude identification marks based on the TSN time-sensitive network, breaking through the limitations of traditional clock synchronization methods and providing accurate clock calibration and synchronization in highly dynamic environments. Compared with existing technologies, this method combines multiple data collections, real-time master-slave clock monitoring and feedback mechanisms, enabling the system to continuously optimize the accuracy of clock synchronization at different time scales, significantly improving the system's adaptability to external changes. At the same time, this multi-level, multi-dimensional synchronization solution can effectively reduce clock drift and errors, providing more reliable time base support, thereby enabling the low-altitude identification mark system to demonstrate higher stability and accuracy in high-precision spatiotemporal positioning and mission execution.

[0016] 2. The master-slave time monitoring in step S4 forms a closed-loop control system from "acquisition-synchronization-monitoring-calibration" in terms of technical architecture. Through real-time coupling coefficient calculation driven by deep learning, the system can dynamically capture clock changes and, combined with an intelligent coupling offset determination model, determine whether to perform clock drift correction. This approach breaks through the bottleneck of traditional static clock synchronization technology, achieving a leap forward in the time unification system from "static accuracy" to "dynamic stability." It is particularly suitable for the complex environments of multiple source nodes and highly dynamic links in low-altitude scenarios, significantly improving the reliability, autonomy, and intelligence of system time synchronization. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A diagram showing the steps of the method of the present invention. DETAILED DESCRIPTION

[0018] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0019] Example 1: Please refer to Figure 1 , a time-unified method for low-altitude identification signs based on TSN, the specific steps are as follows: S1, initial collection, collecting multi-source data on the system's initial communication link and performing preprocessing to generate a first data set and a second data set; S2. Master-slave clock synchronization, data coupling of the first data group and the second data group, thereby generating an initial master clock coupling coefficient ZYS and an initial slave clock coupling coefficient CYS, and performing data analysis on the two; S3, re-collecting, collecting multi-source data through a secondary communication link of the system, and performing pre-processing to generate a third data group and a fourth data group; S4, master-slave time monitoring, performing data coupling on the third data group and the fourth data group to generate a real-time master clock coupling coefficient ZRS and a real-time slave clock coupling coefficient CRS, and analyzing the real-time master clock coupling coefficient ZRS and the real-time slave clock coupling coefficient CRS; S5. Master-slave time calibration: data coupling is performed on the initial master clock coupling coefficient ZYS, the initial slave clock coupling coefficient CYS, the real-time master clock coupling coefficient ZRS, and the real-time slave clock coupling coefficient CRS to generate calibration coefficients, and the calibration coefficients are analyzed. S6. Feedback: Feedback all data and analysis results to the visualization terminal.

[0020] In this embodiment, in step S1, during the system's initial multi-source data collection process for the communication link, data from different sources is preprocessed to generate a first data set and a second data set. The core task of this step is to assess the system's initial operating environment and ensure the accuracy and completeness of the collected data. This initial data collection not only provides basic data support for subsequent clock synchronization and data coupling, but also tests the system's stability and accuracy, reduces data errors, and prevents the spread of system errors. Its goal is to ensure that the collected data can be effectively combined within the time synchronization framework, preparing for subsequent clock calibration and real-time monitoring.

[0021] In step S2, the initial master clock coupling coefficient ZYS and the initial slave clock coupling coefficient CYS are generated by coupling the first and second data groups. This process completes the initial synchronization of the system's master and slave clocks, effectively assessing and controlling the time error between them. The core goal of synchronization is to ensure that the clocks within the system operate consistently, avoiding inconsistent task execution caused by clock drift. Master-slave clock synchronization lays a solid foundation for subsequent data analysis, correction, and feedback mechanisms, and enables the system to maintain a high degree of temporal coordination.

[0022] In step S3, during the re-collection phase, the system performs secondary data collection and preprocessing on the communication link, generating third and fourth data sets. This re-collection enables the system to obtain more accurate and real-time multi-source data, providing a new reference for subsequent real-time master-slave clock synchronization. This step is crucial because it helps the system capture new external variables, such as network latency fluctuations or clock offset changes, allowing it to promptly adjust the system's internal clock to more accurately reflect the current operating environment. Re-collection not only improves the timeliness of the data but also enhances its comprehensiveness and adaptability.

[0023] In step S4, the master-slave time monitoring step generates and analyzes the real-time master clock coupling coefficient ZRS and the real-time slave clock coupling coefficient CRS by coupling the third data group with the fourth data group. Real-time monitoring enables the system to obtain the error between the master and slave clocks at any time and make real-time adjustments. This step ensures that the system can cope with changes such as clock drift and delay fluctuations in dynamic environments. By analyzing real-time data, the system can respond quickly to the current operating status. Real-time master-slave time monitoring is a key part of the system's precise control, ensuring that the system is always in an ideal clock synchronization state and preventing potential clock errors from affecting data processing and task execution.

[0024] In step S5, calibration coefficients are generated and analyzed by coupling the initial master-slave clock coupling coefficients ZYS and CYS with the real-time master-slave clock coupling coefficients ZRS and CRS. Master-slave clock calibration is a core step in ensuring system clock accuracy. Its purpose is to optimize clock synchronization accuracy by combining historical and real-time data, enabling the system to cope with more complex clock drift and calibration challenges. This step can further reduce clock errors, improve system stability and synchronization accuracy, and significantly enhance clock synchronization reliability, particularly in highly dynamic environments.

[0025] In step S6, the system feeds all data and analysis results to the visualization terminal, allowing the operator to view the system's status and performance in real time. This feedback mechanism provides an interactive channel between the user and the system, enabling the system to quickly respond to environmental changes and helping the operator make accurate decisions. Through feedback, the system not only displays the current synchronization and calibration status to the user but also adjusts system parameters according to user needs, thereby improving the system's operability and responsiveness.

[0026] This method uses the time unification technology of low-altitude identification marks based on the TSN time-sensitive network, breaking through the limitations of traditional clock synchronization methods and providing accurate clock calibration and synchronization in highly dynamic environments. Compared with existing technologies, this method combines multiple data collection, real-time master-slave clock monitoring and feedback mechanisms, enabling the system to continuously optimize the accuracy of clock synchronization at different time scales, significantly improving the system's adaptability to external changes. At the same time, this multi-level, multi-dimensional synchronization scheme can effectively reduce clock drift and errors, providing more reliable time base support, thereby enabling the low-altitude identification mark system to demonstrate higher stability and accuracy in high-precision spatiotemporal positioning and mission execution.

[0027] Example 2: Please refer to Figure 1 In step S1, the specific steps of initial collection are as follows: S1.1. Data acquisition: by deploying a multifunctional sensor group and background acquisition software, multi-source information data can be acquired; S1.2. Preprocessing and dimensionlessizing the collected multi-source data, and reorganizing them into a first data group and a second data group; The first data group includes the main signal reception delay ZYA, the main round-trip delay ZYB, the main communication signal-to-noise ratio ZYC, the main synchronization frame efficiency ZYD, the main current offset ZYE, the main offset change rate ZYF, the main frequency stability ZYH and the main calibration feedback error ZYL; The second data group includes slave signal reception delay CYA, slave round-trip delay CYB, slave communication signal-to-noise ratio CYC, slave synchronization frame effectiveness rate CYD, slave current offset CYE, slave offset change rate CYF, slave frequency stability CYH, and slave calibration feedback error CYL.

[0028] In this embodiment, a multifunctional sensor array and accompanying backend acquisition software enable comprehensive multi-source information collection from master and slave nodes in low-altitude environments, including key metrics such as signal latency, communication quality, and frequency stability. Compared to traditional synchronization mechanisms that focus solely on timestamps or single latency, this approach significantly improves the system's perception accuracy and responsiveness to complex environmental changes, laying a solid foundation for subsequent precise synchronization and coupled calculations.

[0029] The collected data undergoes preprocessing and dimensionless processing, effectively eliminating interference between different physical magnitudes and improving the accuracy of data coupling. Especially in dynamic low-altitude scenarios, preprocessed data is more suitable for input into the time-coupling model, reducing system error accumulation and computational complexity.

[0030] The data is clearly organized into a first data group for the master side and a second data group for the slave side. These groups contain eight key parameters: signal reception delay (ZYA / CYA), round-trip delay (ZYB / CYB), communication quality indicator (ZYC / CYC), synchronization frame efficiency (ZYD / CYD), frequency stability (ZYH / CYH), and calibration feedback error (ZYL / CYL). This demonstrates the ability to observe and model the clock states of both the master and slave sides. This structure facilitates bidirectional precision control for subsequent clock coupling coefficient calculations, rather than the traditional unidirectional adjustment of the master control, improving system flexibility and time coordination accuracy.

[0031] Example 3: Please refer to Figure 1 In step S2, the specific steps of master-slave clock synchronization are as follows: S2.1. Data coupling is performed on the first data set. Multiple data points within the data set are input into a pre-trained deep learning framework. Feature fusion is performed through a multi-layer neural network to calculate the initial master clock coupling coefficient ZYS. The specific calculation formula is as follows; Where: ZYA is the main signal reception delay, ZYB is the main round-trip delay, ZYC is the main communication signal-to-noise ratio, ZYD is the main synchronization frame efficiency, ZYE is the main current offset, ZYF is the main offset change rate, ZYH is the main frequency stability, and ZYL is the main calibration feedback error. S2.2. Data coupling is performed on the second data set. Multiple data points in the data set are input into a pre-trained deep learning framework. Feature fusion is performed through a multi-layer neural network to calculate the initial slave clock coupling coefficient CYS. The specific calculation formula is as follows; Where: CYA is the slave signal reception delay, CYB is the slave round-trip delay, CYC is the slave communication signal-to-noise ratio, CYD is the slave synchronization frame efficiency, CYE is the slave current offset, CYF is the slave offset change rate, CYH is the slave frequency stability, and CYL is the slave calibration feedback error; S2.3. Perform a joint analysis on the calculated initial master clock coupling coefficient ZYS and the initial slave clock coupling coefficient CYS. Based on the analysis results, determine whether the error between the two is reasonable. The specific method is as follows: At that time, it means that the error between the initial master clock coupling coefficient ZYS and the initial slave clock coupling coefficient CYS is within a reasonable range and no initialization is required; when When , it means that the error between the initial master clock coupling coefficient ZYS and the initial slave clock coupling coefficient CYS is in an unreasonable range and needs to be initialized.

[0032] In this embodiment, by inputting multiple data points from the first and second data sets into a pre-trained deep learning framework, the system is able to perform feature fusion and optimization using a multi-layer neural network. Compared to traditional physics-based algorithms, this approach can automatically extract complex nonlinear features from the data, capturing details that are difficult to identify with traditional methods. The introduction of deep learning methods makes the calculation of clock coupling coefficients more accurate and intelligent, effectively improving the robustness and real-time responsiveness of the calculation, especially when faced with complex environments or large amounts of data.

[0033] When calculating the initial master-clock coupling coefficient, ZYS, and the initial slave-clock coupling coefficient, CYS, a weighted average and fusion of key indicators such as signal reception delay, round-trip delay, communication signal-to-noise ratio, synchronization frame efficiency, offset, and frequency stability is performed. This eliminates noise interference from a single indicator and improves data accuracy during master-slave clock synchronization. Unlike traditional synchronization methods based on a single parameter, this multi-data fusion approach provides a more comprehensive reflection of system status, enabling more precise synchronization control.

[0034] After the initial calculation of the master clock coupling coefficient ZYS and the slave clock coupling coefficient CYS, the system implements an error determination mechanism to monitor the difference between the two in real time. This mechanism automatically triggers initialization when the difference between the two exceeds a reasonable range, preventing the accumulation of errors from adversely affecting the system. The introduction of error determination enables the system to promptly identify potential clock synchronization issues and automatically adjust for them, significantly enhancing system reliability and self-healing capabilities.

[0035] After the initial calculation of the master clock coupling coefficient ZYS and the slave clock coupling coefficient CYS, the system implements an error determination mechanism to monitor the difference between the two in real time. This mechanism automatically triggers initialization when the difference between the two exceeds a reasonable range, preventing the accumulation of errors from adversely affecting the system. The introduction of error determination enables the system to promptly identify potential clock synchronization issues and automatically adjust for them, significantly enhancing system reliability and self-healing capabilities.

[0036] Using the conditional formula ZYS × 98% ≤ (ZYS - CYS) / ZYS ≤ ZYS, the system accurately determines whether master-slave clock synchronization is ideal. If the error is within a reasonable range, the system does not require initialization, saving unnecessary computing resources. If the error exceeds this range, the system automatically initializes to ensure master-slave clock resynchronization. This mechanism enhances system intelligence, eliminates manual intervention, and effectively reduces the risk of errors during synchronization.

[0037] Step S2 introduces a deep learning framework and multiple data fusion technologies, which greatly improves the system's clock coupling accuracy, computational efficiency, and intelligence level compared to traditional synchronization methods based on manual settings. The adaptive capabilities of deep learning technology enable the system to quickly adjust in complex and dynamically changing environments, avoiding the error problems caused by improper parameter selection in traditional methods. The introduction of the error judgment mechanism enables the system to actively identify problems and respond quickly during the clock synchronization process, thereby improving the system's stability and self-repair capabilities. This improvement makes the time unification method for low-altitude identification signs more robust and reliable when processing large-scale data and coping with complex environments, and significantly optimizes clock synchronization performance.

[0038] Example 4: Please refer to Figure 1 In step S3, the specific steps of collecting are as follows: S3.1. Data acquisition: acquiring multi-source information data by deploying a multi-functional sensor group and background acquisition software; S3.2. Preprocess and dimensionlessly transform the collected multi-source data, and reorganize them into a third data set and a fourth data set; The third data group includes the main real-time signal reception delay ZRA, the real-time main round-trip delay ZRB, the real-time main communication signal-to-noise ratio ZRC, the real-time main synchronization frame efficiency ZRD, the real-time main current offset ZRE, the real-time main offset change rate ZRF, the real-time main frequency stability ZRH and the real-time main calibration feedback error ZRL; The fourth data group includes real-time signal reception delay CRA, real-time round-trip delay CRB, real-time communication signal-to-noise ratio CRC, real-time synchronization frame efficiency CRD, real-time current offset CRE, real-time offset change rate CYRF, real-time frequency stability CRH and real-time calibration feedback error CRL.

[0039] In this embodiment, by deploying a multifunctional sensor array and backend data acquisition software, the system can gather signal information in a real-time, dynamic environment, capturing key metrics such as master-slave clock offset and latency variations. This data acquisition approach not only addresses the inability of traditional methods, which rely on static data and are unable to adapt to environmental changes, but also allows system synchronization strategies to be adjusted based on real-time data, ensuring optimal system time coordination at all times.

[0040] Dimensionless processing of collected multi-source data enables analysis and fusion of data of varying dimensions under the same standard. Dimensionless processing avoids interference between different data units and magnitudes, eliminates synchronization errors caused by differences in data magnitude, and ensures accurate and consistent data processing. This is particularly important for master-slave clock synchronization, which requires refined control and analysis, effectively improving the accuracy of clock coupling and calibration.

[0041] The collected data is organized into third and fourth data groups, respectively covering real-time information about the master and slave clocks, such as signal reception delay, round-trip delay, communication signal-to-noise ratio, synchronization frame efficiency, current offset, offset change rate, frequency stability, and calibration feedback error. This grouping method further refines the existing approach, clearly separating each important indicator from its corresponding real-time data status, facilitating subsequent data analysis and clock synchronization calculations. This structured data organization improves data operability, making system processing and analysis more efficient and intuitive.

[0042] The data collected during the recollection phase not only provides real-time feedback on environmental changes but also provides a basis for dynamic adjustments to the system. In highly dynamic environments, factors such as clock drift, latency fluctuations, and network status changes can affect the synchronization of master and slave clocks. By continuously collecting and processing real-time data, the system can adjust synchronization parameters in real time, reducing error accumulation and enhancing the system's adaptability. This self-adjustment mechanism based on real-time feedback significantly improves the accuracy and stability of clock synchronization compared to traditional static adjustment methods.

[0043] The re-acquisition process in step S3, through real-time data acquisition, dimensionless processing, and refined data structuring, provides the system with more comprehensive, accurate, and efficient data support. These improvements enable the system to cope with dynamic changes in the low-altitude identification environment and adjust clock synchronization strategies in real time, significantly improving clock synchronization accuracy and system stability. Compared with traditional static methods, the re-acquisition phase fully reflects the system's real-time operating status at the data level, enabling more precise clock calibration and correction, and optimizing the spatiotemporal coordination and reliability of the overall system.

[0044] Example 5: In step S4, the master-slave time monitoring method is as follows: S4.1. Data coupling is performed on the third data set. Multiple data points within the data set are input into a pre-trained deep learning framework. Feature fusion is performed using a multi-layer neural network to calculate the real-time master clock coupling coefficient ZRS. The specific calculation formula is as follows; Where: ZRA is the main real-time signal reception delay, ZRB is the real-time main round-trip delay, ZRC is the real-time main communication signal-to-noise ratio, ZRD is the real-time main synchronization frame efficiency, ZRE is the real-time main current offset, ZRF is the real-time main offset change rate, ZRH is the real-time main frequency stability, and ZRL is the real-time main calibration feedback error; S4.2. Data coupling is performed on the fourth data group. Multiple data points in the data group are input into a pre-trained deep learning framework. Feature fusion is performed through a multi-layer neural network to calculate the real-time slave clock coupling coefficient CRS. The specific calculation formula is as follows; Where: CRA is the real-time slave signal reception delay, CRB is the real-time slave round-trip delay, CRC is the real-time slave communication signal-to-noise ratio, CRD is the real-time slave synchronization frame efficiency, CRE is the real-time slave current offset, CRF is the real-time slave offset change rate, CRH is the real-time slave frequency stability, and CRL is the real-time slave calibration feedback error; S4.3. Analyze the calculated initial master clock coupling coefficient ZYS, initial slave clock coupling coefficient CYS, real-time master clock coupling coefficient ZRS, and real-time slave clock coupling coefficient CRS. Based on the analysis results, determine whether data drift correction is required. The specific method is as follows: when When , it means that the error between the initial master clock coupling coefficient ZYS and the real-time master clock coupling coefficient ZRS is within a reasonable range, and no drift correction is required; At that time, the error between the initial master clock coupling coefficient ZYS and the real-time master clock coupling coefficient ZRS was in an unreasonable range and drift correction was required; when When , it means that the error between the initial slave clock coupling coefficient CYS and the real-time slave clock coupling coefficient CRS is within a reasonable range and no drift correction is required; At that time, the error between the initial slave clock coupling coefficient CYS and the real-time slave clock coupling coefficient CRS was in an unreasonable range and drift correction was required.

[0045] In this embodiment, compared to traditional methods that rely solely on initial data calculations, step S4 incorporates the third and fourth data sets of the real-time master-slave data set and uses a pre-trained deep learning model to perform coupling calculations, deriving the real-time master clock coupling coefficient ZRS and the real-time slave clock coupling coefficient CRS, respectively. This real-time monitoring mechanism ensures that the system continuously tracks changes in the operating status of the master and slave clocks, overcoming the limitation of traditional synchronization systems that only calibrate without continuous monitoring, and effectively supporting high-precision time maintenance in low-altitude dynamic environments.

[0046] By accurately comparing and analyzing the real-time coupling coefficients ZRS / CRS with the initial coupling coefficients ZYS / CYS, the system can promptly identify whether time drift or accuracy degradation has occurred between the master and slave clocks. Specifically, by using mathematical judgment criteria such as ZRS × 98% ≤ (ZYS − ZRS) / ZYS and CRS × 98% ≤ (CYS − CRS) / CYS, a system-executable drift identification model is constructed. This effectively avoids the misjudgment and erroneous correction problems caused by overly coarse threshold settings in traditional methods, significantly improving the objectivity and accuracy of the judgment.

[0047] Each coupling coefficient calculation leverages eight real-time metrics: reception latency, round-trip delay, signal-to-noise ratio, frame efficiency, offset, offset rate, frequency stability, and feedback error. Powered by a deep learning model, the system automatically integrates the complex nonlinear relationships between these metrics. This approach is more adaptive and predictive than traditional linear weighted algorithms, maintaining robust judgment even in low-altitude scenarios with high data volatility.

[0048] The system's built-in automatic error tolerance judgment logic intelligently determines whether clock drift correction is necessary based on the ratio of the current master-slave coupling coefficient to the initial one. This automatic correction mechanism not only reduces the burden on operations and maintenance personnel but also enhances the autonomy of the entire time synchronization system. Compared to traditional mechanisms that rely on periodic manual testing and recalibration, this new approach offers greater efficiency and responsiveness, adapting to the demands of future complex, automated low-altitude systems.

[0049] The master-slave time monitoring in step S4 forms a closed-loop control system from "acquisition-synchronization-monitoring-calibration" in terms of technical architecture. Through real-time coupling coefficient calculation driven by deep learning, the system can dynamically capture clock changes and, combined with the coupling offset intelligent judgment model, determine whether to perform clock drift correction. This method breaks through the bottleneck of traditional static clock synchronization technology and achieves a leap forward in the time unification system from "static accuracy" to "dynamic stability." It is particularly suitable for the complex environments of multiple source nodes and highly dynamic links in low-altitude scenarios, significantly improving the reliability, autonomy, and intelligence level of system time synchronization.

[0050] Example 6: Please refer to Figure 1 In step S5, the master-slave time calibration is performed in the following manner: S5.1. Extract additional data and preprocess and dimensionlessly convert the extracted data, including the recent drift mean DR1, drift change standard deviation DR2, calibration response delay DR3, calibration influence index DR4, and self-correction index DR5. S5.2. Input the processed data into a pre-trained deep learning framework, perform feature fusion through a multi-layer neural network, and then calculate the drift correction coefficient PYX. The specific calculation formula is as follows;

[0051] Where: DR1 is the recent drift mean, DR2 is the drift change standard deviation, DR3 is the calibration response delay, DR4 is the calibration influence index, and DR5 is the self-correction index; S5.3. Perform a coupling analysis on the drift correction coefficient PYX and the real-time master clock coupling coefficient ZRS. Based on the analysis results, determine the effectiveness of the drift correction coefficient PYX in optimizing the real-time master clock coupling coefficient ZRS. S5.4. Perform coupling analysis on the drift correction coefficient PYX and the real-time slave clock coupling coefficient CRS. Based on the analysis results, determine the effectiveness of the drift correction coefficient PYX in optimizing the real-time slave clock coupling coefficient CRS.

[0052] In this embodiment, by extracting and preprocessing additional data such as the recent drift mean DR1, drift standard deviation DR2, calibration delay DR3, influence index DR4, and self-correction index DR5, the system no longer relies solely on the coupling coefficient to determine drift, but instead analyzes the drift process itself. This approach builds a more comprehensive and quantifiable drift behavior model, providing a scientific basis for subsequent intelligent corrections and overcoming the drawbacks of traditional methods that ignore drift details and rely solely on deviation magnitude for correction.

[0053] The drift correction factor, PYX, integrates multiple core parameters and is calculated using the feature extraction and nonlinear mapping capabilities of a pretrained neural network. Compared to linear or empirical function methods, this approach offers the advantages of strong adaptability and high generalization. The formula models the positive and negative impacts of various factors. For example, DR3 employs an exponentially stronger penalty for response delay, reflecting the system's sensitivity to time lags. This innovative correction method ensures that the system generates the most meaningful calibration values ​​under various operating conditions.

[0054] Rather than directly using the correction coefficient PYX for unconditional calibration, the system analyzes and verifies it in conjunction with the real-time master clock coupling coefficient ZRS and the slave clock coupling coefficient CRS. This mechanism effectively avoids the side effects of "overcorrection" or "incorrection," ensuring that corrections are only implemented when they have a positive optimization effect, further enhancing the accuracy and robustness of the system calibration process. This verification mechanism also provides traceability and explainability to the system's decision-making process, which will be crucial for future manual review or system self-learning.

[0055] This step, through a mechanism of "learning and calibrating from error behavior," achieves the upgrade of the master-slave time synchronization system to an "autonomous optimization architecture." The system no longer relies on manual intervention to determine the intensity and timing of drift corrections. Instead, it uses a deep learning model to automatically integrate historical data and make autonomous correction decisions. This design is particularly well-suited to the complex high-frequency fluctuations and multi-link switching found in low-altitude intelligent perception scenarios, providing the system with highly robust clock stability.

[0056] Step S5 extracts key dynamic drift features and uses a deep learning model to calculate the intelligent drift correction coefficient PYX, achieving refined and adaptive calibration of the master-slave time coupling relationship. Compared with traditional time synchronization technology, this step significantly improves the responsiveness to drift behavior, the intelligent judgment ability of correction actions, and the overall time stability and adaptability of the system. This mechanism is particularly suitable for complex communication nodes in low-altitude and highly dynamic environments, and strongly supports the "high-precision, high-reliability, and low-latency time unification requirements." Example 7: Please refer to Figure 1 In step S5.3, the specific analysis method is as follows: when When , it means that the error between the initial master clock coupling coefficient ZYS and the real-time master clock coupling coefficient ZRS is within a reasonable range, and the drift correction coefficient PYX is valid; when When , it means that the error between the initial master clock coupling coefficient ZYS and the real-time master clock coupling coefficient ZRS is in an unreasonable range, and the drift correction coefficient PYX is invalid.

[0057] In this embodiment, traditional time synchronization systems often lack rigorous validation standards when triggering calibration actions, making them prone to overcorrection or ineffective correction. This step uses a judgment expression to accurately measure whether the master clock drift correction results meet the standards, effectively establishing a logical closed loop of "calibration action - result verification - policy correction", thereby preventing the correction actions from negatively impacting clock stability. This standard not only takes into account the correction strength and deviation threshold, but also introduces a moderate tolerance rate of 95%, ensuring the system is both rigorous and engineering-tolerant.

[0058] By determining whether PYX is truly having a positive effect on ZRS optimization, the system automatically selects valid correction factors and discards invalid ones, preventing the misapplication of correction errors caused by noisy data, model drift, or mislearning, thereby significantly improving the system's calibration stability and robustness. This is particularly critical in actual low-altitude communication links, where environmental disturbances and frequent node state changes make automated verification mechanisms essential to ensuring calibration quality.

[0059] This step quantifies the PYX effect into comparable metrics, enabling the system to self-verify, self-screen, and self-update. This "verifiable and traceable" mechanism eliminates the calibration process as a "black box" operation, providing a solid data foundation for subsequent manual analysis, model adjustments, and strategy optimization. This feature enables the system to achieve precise and robust time control in a more intelligent manner when facing complex and changing low-altitude recognition scenarios.

[0060] By dynamically measuring the differences between ZRS and ZYS, the system can accumulate correction effect data over long periods of time, which in turn feeds back into model training and parameter updates. This mechanism enables the time calibration strategy to be evolutionary and adaptable to the environment, driving the system's transition from static synchronization to intelligent, evolving synchronization, and laying the foundation for subsequent deployment in more complex environments.

[0061] Step S5.3 establishes a highly reliable time calibration verification mechanism by establishing a scientifically sound judgment formula to accurately verify the drift correction coefficient PYX's optimization effect on the master clock coupling state. This mechanism not only ensures the system has sufficient judgment criteria when performing corrections, but also enhances the controllability and transparency of calibration operations, significantly improving the overall system's time consistency and intelligent adaptability in complex low-altitude scenarios.

[0062] Example 8: Please refer to Figure 1 In step S5.4, the specific analysis method is as follows: At that time, it means that the error between the initial slave clock coupling coefficient CYS and the real-time slave clock coupling coefficient CRS is within a reasonable range, and the drift correction coefficient PYX is valid; when When , it means that the error between the initial slave clock coupling coefficient CYS and the real-time slave clock coupling coefficient CRS is in an unreasonable range, and the drift correction coefficient PYX is invalid.

[0063] In this embodiment, the deviation between the initial slave clock coupling coefficient CYS and the real-time slave clock coupling coefficient CRS is quantified and compared, and the current correction coefficient PYX is introduced as an evaluation variable to clarify the optimization effect of the calibration action in the slave clock path. This design overcomes the limitations of previous reliance on a global unified strategy that ignores individual differences in slave clocks, enabling the system to achieve more fine-grained time correction capabilities.

[0064] In complex low-altitude environments, slave clock nodes are numerous and heterogeneous, making them susceptible to factors such as link latency and device aging. This analysis method dynamically and quantitatively evaluates the calibration status of each slave node, ensuring that corrections are applied only when they are truly effective. This prevents invalid or erroneous corrections from disrupting the overall network timing structure, significantly improving system stability and fault tolerance.

[0065] Corresponding to the master clock correction analysis in S5.3, the same judgment logic framework is applied here to the slave clocks, ensuring consistency, symmetry, and unified scheduling of master and slave time calibration. This provides a unified measurement foundation for subsequent system strategy integration, resource allocation, and collaborative control. This design not only improves the consistency of the system architecture but also enhances the collaborative efficiency of system-level time synchronization.

[0066] The inclusion of a 95% tolerance range in the judgment mechanism reflects the system's tolerance for measurement errors and dynamic environmental fluctuations, making calibration decisions both scientifically rigorous and engineering-adaptable. Furthermore, this formula can be used as a logging tool and a basis for decision-making, facilitating performance review, strategy adjustments, and algorithm self-learning during long-term system operation, laying the foundation for building a system with "time-based self-maintenance capabilities."

[0067] Step S5.4 strengthens the intelligent calibration capabilities of the "slave path" in the master-slave time synchronization system by establishing a correction performance evaluation mechanism for slave clocks. This mechanism, incorporating the dynamic relationship between the drift correction coefficient PYX and the slave clock coupling coefficient, implements a quantitative, verifiable, and flexible correction determination strategy. This improvement significantly enhances the system's adaptability, stability, and controllability in heterogeneous low-altitude environments, providing technical support for high-precision timing management in large-scale, complex master-slave clock networks.

[0068] The contents not described in detail in this specification belong to the prior art known to those skilled in the art.

[0069] Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments, or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A time unification method for low-altitude identification signs based on TSN, characterized by: The specific steps are as follows: S1, initial collection, collecting multi-source data on the system's initial communication link and performing preprocessing to generate a first data set and a second data set; S2. Master-slave clock synchronization, data coupling of the first data group and the second data group, thereby generating an initial master clock coupling coefficient ZYS and an initial slave clock coupling coefficient CYS, and performing data analysis on the two; S3, re-collecting, collecting multi-source data through a secondary communication link of the system, and performing pre-processing to generate a third data group and a fourth data group; S4, master-slave time monitoring, performing data coupling on the third data group and the fourth data group to generate a real-time master clock coupling coefficient ZRS and a real-time slave clock coupling coefficient CRS, and analyzing the real-time master clock coupling coefficient ZRS and the real-time slave clock coupling coefficient CRS; S5. Master-slave time calibration: data coupling is performed on the initial master clock coupling coefficient ZYS, the initial slave clock coupling coefficient CYS, the real-time master clock coupling coefficient ZRS, and the real-time slave clock coupling coefficient CRS to generate calibration coefficients, and the calibration coefficients are analyzed. S6. Feedback: Feedback all data and analysis results to the visualization terminal.

2. The time unification method for low-altitude identification marks based on TSN according to claim 1 is characterized in that: In step S1, the specific steps of initial collection are as follows: S1.

1. Data acquisition: by deploying a multifunctional sensor group and background acquisition software, multi-source information data can be acquired; S1.

2. Preprocessing and dimensionlessizing the collected multi-source data, and reorganizing them into a first data group and a second data group; The first data group includes the main signal reception delay ZYA, the main round-trip delay ZYB, the main communication signal-to-noise ratio ZYC, the main synchronization frame efficiency ZYD, the main current offset ZYE, the main offset change rate ZYF, the main frequency stability ZYH and the main calibration feedback error ZYL; The second data group includes slave signal reception delay CYA, slave round-trip delay CYB, slave communication signal-to-noise ratio CYC, slave synchronization frame effectiveness rate CYD, slave current offset CYE, slave offset change rate CYF, slave frequency stability CYH, and slave calibration feedback error CYL.

3. The time unification method for low-altitude identification marks based on TSN according to claim 2 is characterized in that: In step S2, the specific steps of master-slave clock synchronization are as follows: S2.

1. Data coupling is performed on the first data set. Multiple data points within the data set are input into a pre-trained deep learning framework. Feature fusion is performed through a multi-layer neural network to calculate and obtain the initial master clock coupling coefficient ZYS. S2.

2. Data coupling is performed on the second data set. Multiple data points in the data set are input into a pre-trained deep learning framework. Feature fusion is performed through a multi-layer neural network to calculate and obtain the initial slave clock coupling coefficient CYS. S2.

3. Perform a joint analysis on the calculated initial master clock coupling coefficient ZYS and the initial slave clock coupling coefficient CYS. Based on the analysis results, determine whether the error between the two is reasonable. The specific method is as follows: when When , it means that the error between the initial master clock coupling coefficient ZYS and the initial slave clock coupling coefficient CYS is within a reasonable range and no initialization is required; when When , it means that the error between the initial master clock coupling coefficient ZYS and the initial slave clock coupling coefficient CYS is in an unreasonable range and needs to be initialized.

4. The time unification method for low-altitude identification marks based on TSN according to claim 3 is characterized in that: In step S3, the specific steps of recollection are as follows: S3.

1. Data acquisition: acquiring multi-source information data by deploying a multi-functional sensor group and background acquisition software; S3.

2. Preprocess and dimensionlessly transform the collected multi-source data, and reorganize them into a third data set and a fourth data set; The third data group includes the main real-time signal reception delay ZRA, the real-time main round-trip delay ZRB, the real-time main communication signal-to-noise ratio ZRC, the real-time main synchronization frame efficiency ZRD, the real-time main current offset ZRE, the real-time main offset change rate ZRF, the real-time main frequency stability ZRH and the real-time main calibration feedback error ZRL; The fourth data group includes real-time signal reception delay CRA, real-time round-trip delay CRB, real-time communication signal-to-noise ratio CRC, real-time synchronization frame efficiency CRD, real-time current offset CRE, real-time offset change rate CYRF, real-time frequency stability CRH and real-time calibration feedback error CRL.

5. The time unification method for low-altitude identification marks based on TSN according to claim 4 is characterized in that: In step S4, the master-slave time monitoring method is as follows: S4.

1. Data coupling is performed on the third data set. Multiple data points within the data set are input into a pre-trained deep learning framework. Feature fusion is performed using a multi-layer neural network to calculate the real-time master clock coupling coefficient ZRS. S4.

3. Analyze the calculated initial master clock coupling coefficient ZYS, initial slave clock coupling coefficient CYS, real-time master clock coupling coefficient ZRS, and real-time slave clock coupling coefficient CRS. Based on the analysis results, determine whether data drift correction is required. The specific method is as follows: when When , it means that the error between the initial master clock coupling coefficient ZYS and the real-time master clock coupling coefficient ZRS is within a reasonable range, and no drift correction is required; when When , it means that the error between the initial master clock coupling coefficient ZYS and the real-time master clock coupling coefficient ZRS is in an unreasonable range and drift correction is required; when When , it means that the error between the initial slave clock coupling coefficient CYS and the real-time slave clock coupling coefficient CRS is within a reasonable range and no drift correction is required; when When , it means that the error between the initial slave clock coupling coefficient CYS and the real-time slave clock coupling coefficient CRS is in an unreasonable range and drift correction is required.

6. The time unification method for low-altitude identification marks based on TSN according to claim 5 is characterized in that: In step S5, the master-slave time calibration is performed in the following manner: S5.

1. Extract additional data and preprocess and dimensionlessly convert the extracted data, including the recent drift mean DR1, drift change standard deviation DR2, calibration response delay DR3, calibration influence index DR4, and self-correction index DR5. S5.

2. Input the processed data into a pre-trained deep learning framework, perform feature fusion through a multi-layer neural network, and then calculate the drift correction coefficient PYX. The specific calculation formula is as follows; S5.

3. Perform a coupling analysis on the drift correction coefficient PYX and the real-time master clock coupling coefficient ZRS. Based on the analysis results, determine the effectiveness of the drift correction coefficient PYX in optimizing the real-time master clock coupling coefficient ZRS. S5.

4. Perform coupling analysis on the drift correction coefficient PYX and the real-time slave clock coupling coefficient CRS. Based on the analysis results, determine the effectiveness of the drift correction coefficient PYX in optimizing the real-time slave clock coupling coefficient CRS.

7. The time unification method for low-altitude identification marks based on TSN according to claim 6 is characterized in that: In step S5.3, the specific analysis method is as follows: when When , it means that the error between the initial master clock coupling coefficient ZYS and the real-time master clock coupling coefficient ZRS is within a reasonable range, and the drift correction coefficient PYX is valid; when When , it means that the error between the initial master clock coupling coefficient ZYS and the real-time master clock coupling coefficient ZRS is in an unreasonable range, and the drift correction coefficient PYX is invalid.

8. The time unification method for low-altitude identification marks based on TSN according to claim 7 is characterized in that: In step S5.4, the specific analysis method is as follows: when When , it means that the error between the initial slave clock coupling coefficient CYS and the real-time slave clock coupling coefficient CRS is within a reasonable range, and the drift correction coefficient PYX is valid; when When , it means that the error between the initial slave clock coupling coefficient CYS and the real-time slave clock coupling coefficient CRS is in an unreasonable range, and the drift correction coefficient PYX is invalid.

Images