A method and system for the metrological control of an airport ground equipment

Abstract

The application relates to the technical field of metering control processing, and discloses an airport ground equipment metering control method and system, which comprises the following steps: synchronously triggering a sensor module and a multi-dimensional working condition sensing module to collect original metering data of target ground equipment and synchronously collect working condition data; through an edge intelligent calculation module, error compensation is performed on the original metering data according to the original metering data, the working condition data and an error compensation model, a reliable metering value compensated according to time sequence is simulated and generated, and a data reliability data chain is generated according to a state migration generation process of the working condition data, so that a data reliability label coupled with the working condition data according to time sequence is generated; through a reliable data packaging module, the reliable metering value and the data reliability label coupled with the working condition data are standardized and packaged, and are sent to a reliable data management platform. The application is beneficial to determining the original reliability of metering data obtained from a complex interference environment and performing reliable compensation.

Description

Technical Field

[0001] This invention relates to the field of metering control and processing technology, and in particular to a metering control method for airport ground equipment and a metering control system for airport ground equipment. Background Technology

[0002] The efficient and safe operation of modern airports relies heavily on their ground support equipment metering and control systems. These systems use various sensors deployed on equipment such as aircraft refueling trucks, ground power plants, and air conditioning trucks to collect real-time supply data on key media such as fuel flow, electricity, and air pressure. This data is then transmitted to a central monitoring platform for operational scheduling, energy consumption analysis, and billing with airlines.

[0003] Existing airport ground equipment metering and control systems typically employ a layered architecture, primarily consisting of a bottom-level sensing layer and a top-level application layer. The sensing layer comprises physical sensors (such as flow meters, energy meters, and pressure transmitters) directly installed on equipment pipelines or circuits, responsible for converting physical quantities into analog or digital signals. The application layer consists of monitoring software on a central server, responsible for receiving, storing, and displaying this data, and performing statistical analysis, alarm generation, and report generation based on it.

[0004] This traditional architecture reveals a significant technical flaw in practice: a functional disconnect between the perception layer and the application layer, lacking an intermediate layer for on-site intelligent processing and verification of data validity. Specifically, existing systems treat sensors as simple data output modules. The central monitoring software passively receives raw readings from the sensors but has no knowledge of the operating conditions under which these readings were generated; therefore, the sensors themselves lack the ability to assess the reliability of the output results.

[0005] The above reasons will lead to a series of problems:

[0006] Data reliability is severely challenged by extreme operating conditions: This is because the operating environment of airport ground equipment is complex. These strong environmental interferences directly affect sensors and their signal transmission lines, causing noise, drift, and even transient distortion in the measurement signals. The central software receives false data containing unknown errors, which directly affects the accuracy, fairness, and traceability of measurement and settlement.

[0007] When the backend detects data anomalies (such as a significant deviation of a refueling volume from the historical average), technicians struggle to quickly determine whether the issue stems from equipment malfunction, abnormal actual consumption, or environmental interference due to a lack of synchronized on-site environmental information. Troubleshooting often requires post-event manual on-site verification and equipment calibration, resulting in delayed response and high costs. Existing systems lack the capability for real-time diagnosis and dynamic compensation at the very moment data is generated and at the immediate on-site location.

[0008] In summary, the core problem with existing technologies lies in their architecture's inability to guarantee the inherent reliability of measurement data obtained from complex and disruptive environments, leading to a data disconnect between perception and application. Therefore, there is an urgent need for a measurement control method for airport ground equipment that enables edge-intelligent and reliable measurement at the source of data generation. Summary of the Invention

[0009] The main objective of this invention is to provide a metering and control method for airport ground equipment, which aims to solve the technical problem that existing airport ground equipment metering and control systems cannot guarantee the original reliability of metering data obtained from complex interference environments.

[0010] To achieve the above objectives, the present invention provides a metering and control method for airport ground equipment, applied to an airport ground equipment metering and control system. The system includes a trusted metering edge terminal deployed at the target ground equipment site and a trusted data management platform deployed in the airport's central computer room. The trusted metering edge terminal includes a sensor module, a multi-dimensional operating condition sensing module, an edge intelligent computing module, and a trusted data encapsulation module. The airport ground equipment metering and control method includes the following steps:

[0011] The sensor module and the multi-dimensional working condition sensing module are triggered synchronously to collect raw measurement data of the target ground equipment through the sensor module and working condition data through the multi-dimensional working condition sensing module. The working condition data includes vibration spectrum data and electromagnetic field intensity data of the measurement site.

[0012] Through the edge intelligent computing module, the original measurement data, operating condition data and error compensation model are used to perform error compensation on the original measurement data in order to simulate and generate a reliable measurement value after time-series error compensation. The process reliability data chain is generated according to the state transition of the operating condition data, thereby generating a data reliability label coupled with the operating condition data in time sequence.

[0013] The trusted data encapsulation module standardizes and encapsulates trusted measurement values ​​and data trust labels coupled with operating condition data, and then sends them to the trusted data management platform.

[0014] Optionally, the step of using an edge intelligent computing module to perform error compensation on the original measurement data based on the original measurement data, operating condition data, and error compensation model to simulate and generate a reliable measurement value after time-series error compensation, and generating a process reliability data chain based on the state transition of the operating condition data, thereby generating a data reliability label coupled to the operating condition data in a time sequence, includes:

[0015] Raw metering data and operating condition data are received through the edge intelligent computing module;

[0016] The original measurement data and operating condition data are input into the error compensation model to calculate the dynamic error estimate corresponding to the time series under the current operating condition, so as to calculate the reliable measurement value corresponding to the time series after compensating the original measurement data.

[0017] Based on the state transition of the operating condition data, a process credibility data chain is generated, and a data credibility label is generated that is coupled with the original measurement data in a time sequence. The data credibility label includes the credibility level and interference type corresponding to the original measurement data. The interference types include vibration-dominated interference, electromagnetic-dominated interference, and composite interference.

[0018] Optionally, the step of inputting the original measurement data and operating condition data into the error compensation model to calculate the dynamic error estimate corresponding to the time series under the current operating condition, so as to calculate the reliable measurement value corresponding to the time series after compensating the original measurement data, includes:

[0019] Extract the feature vectors of the working condition data in the time series. The feature vectors include vibration feature vectors and electromagnetic feature vectors. The vibration feature vector is the characteristic frequency amplitude of the vibration spectrum data, and the electromagnetic feature vector is the average field strength of the electromagnetic field strength data in the specified frequency band.

[0020] The original measurement data and the feature vector under the time series are input into the error compensation model to calculate the dynamic error estimate corresponding to the time series under the current operating condition, so as to calculate the reliable measurement value corresponding to the time series after compensating the original measurement data.

[0021] Optionally, the method further includes:

[0022] In the controlled environment parameters, the observation and measurement data collected by the sensor module of the target ground equipment under the condition of known interference are obtained. The interference conditions include vibration interference and electromagnetic field interference.

[0023] Within controlled environmental parameters, comparative measurement data are acquired by the target ground equipment through sensor modules under conditions where no known interference is applied;

[0024] Based on the observed measurement data and the control measurement data, determine the amount of error imposed by the interference-free conditions in the controlled environment;

[0025] Construct a sample dataset of interference conditions and error quantities;

[0026] The sample dataset is input into the neural network model for training to obtain the error compensation model.

[0027] Optionally, the step of generating a process reliability data chain based on the state transition of the operating condition data and generating a data reliability label coupled to the original measurement data in a time sequence includes:

[0028] Evaluation factors are calculated in real time, including environmental steady-state factors, compensated confidence factors, and process consistency factors.

[0029] Based on the numerical change trend of the evaluation factors, the evaluation module of the credibility status is driven to perform state transition. According to the state transition sequence of the evaluation module within the time interval of this measurement task, a process credibility data chain is generated. The status of the evaluation module includes initialization status, data validity status, credibility compensation status, risk warning status, and data invalid status.

[0030] Based on the final state of the evaluation module at the end of the task, the final credibility level of this measurement task is generated. Based on the final credibility level and the process credibility data chain, a data credibility label coupled with the original measurement data in time sequence is generated.

[0031] Optionally, the step of calculating the evaluation factors in real time includes:

[0032] Based on the real-time vibration spectrum data and real-time electromagnetic field intensity data of the target ground equipment, as well as the historical vibration spectrum data and historical electromagnetic field intensity data, the distance between the current eigenvector and the historical baseline eigenvector in the multivariate statistical space is calculated to determine the environmental steady-state factor.

[0033] Calculate the distance from the real-time vibration spectrum data and real-time electromagnetic field intensity data of the target ground equipment to the feature space cluster center of the historical training dataset used to train the error compensation model, in order to determine the compensation confidence factor.

[0034] The time series of compensated reliable measurements are compared with a set reference time series to determine the process consistency factor.

[0035] Optionally, the step of driving the credibility status evaluation module to perform state transitions based on the numerical change trend of evaluation factors, and generating a process credibility data chain based on the state transition sequence of the evaluation module within the time interval of this measurement task, includes:

[0036] Define the status types of the evaluation module, and the corresponding evaluation factor value range for each status type;

[0037] Based on the numerical change trend of the evaluation factors, the evaluation module is driven to migrate between different state types to form a state migration sequence of the evaluation module.

[0038] A process credibility data chain is generated based on the state type change events, the timestamps of the state type change events, and the evaluation factor types that drive the state type change events in the state transition sequence.

[0039] Optionally, the step of mapping and generating a final credibility level for this measurement task based on the final state of the evaluation module at the end of the task, and generating a data credibility label coupled to the original measurement data in a time sequence based on the final credibility level and the process credibility data chain, includes:

[0040] The final state of the evaluation module at the end of the task is mapped to the final credibility level of this measurement task for quality control.

[0041] Extract summary information from the process credibility data chain to generate a credibility assessment summary;

[0042] The final credibility level, credibility assessment summary, and storage index identifier of the process credibility data chain are encapsulated into a structured data credibility label;

[0043] The data credibility labels are time-series associated and bound with the corresponding compensated credibility measurement values.

[0044] Optionally, the step of standardizing and encapsulating the trusted measurement values ​​and the data trustworthiness labels coupled with the operating condition data through the trusted data encapsulation module, and sending them to the trusted data management platform, includes:

[0045] The trusted data encapsulation module encapsulates trusted measurement values, raw measurement data, operating condition data, error estimates, data trust labels coupled with operating condition data, timestamps, and target ground equipment IDs into trusted data packets, which are then uploaded to the trusted data management platform.

[0046] To achieve the above objectives, the present invention also provides an airport ground equipment metering control system, which applies the airport ground equipment metering control method; the system includes a trusted metering edge terminal deployed at the target ground equipment site and a trusted data management platform deployed in the airport central computer room; the trusted metering edge terminal includes a sensor module, a multi-dimensional operating condition perception module, an edge intelligent computing module and a trusted data encapsulation module;

[0047] The sensor module is used to collect raw metering data from the target ground equipment;

[0048] The multi-dimensional working condition sensing module is used to collect working condition data, which includes vibration spectrum data and electromagnetic field intensity data at the metering site.

[0049] The edge intelligent computing module is used to perform error compensation on the original measurement data based on the original measurement data, operating condition data and error compensation model, so as to simulate and generate a reliable measurement value after time-series error compensation, and generate a process reliability data chain based on the state transition of the operating condition data, thereby generating a data reliability label coupled with the operating condition data in time sequence.

[0050] The trusted data encapsulation module is used to standardize and encapsulate trusted measurement values ​​and data trust labels coupled with operating condition data, and send them to the trusted data management platform.

[0051] The technical solution of this invention helps to solve the technical problem that existing airport ground equipment metering control systems cannot guarantee the original reliability of metering data obtained from complex interference environments. Specifically, this invention constructs an edge trustworthy layer with real-time computing and intelligent judgment capabilities between the traditional perception layer and the application layer by deploying independent trusted metering edge terminals on the target ground equipment. The trusted metering edge terminal not only synchronously collects raw metering data and multi-dimensional operating condition data, but also completes error compensation and reliability assessment using edge intelligent computing modules at the first moment and on the first site when the data is generated. This allows the data to complete the transformation from raw signal to trusted information with quality proof before leaving the equipment, generating a process reliability data chain that corresponds to the original metering data and trusted metering values ​​in time sequence. From the system architecture perspective, this eliminates the possibility of untrusted raw data being erroneously transmitted to the upper layer, solving the long-standing problem of the disconnect between perception and application. Furthermore, by synchronously collecting multi-dimensional operating condition data of vibration spectrum and electromagnetic field intensity and precisely coupling it with the raw metering data in the time domain, the physical environment of each metering operation is completely and quantitatively recorded. Therefore, the system in this invention no longer passively receives an isolated, meaningless reading, but can clearly know the intensity and spectral characteristics of the vibration and electromagnetic interference that generated the reading. This is equivalent to making the sensor's working process transparent and traceable throughout, providing a unique data foundation for subsequent accurate compensation and reliability judgment. The edge intelligent computing module uses an error compensation model, taking real-time collected multi-dimensional operating condition data as input, dynamically calculating the estimated value of the measurement error introduced under the current interference environment, and compensating the original measurement data in real time to generate a reliable measurement value. This method directly models and eliminates the mapping relationship between interference and error, effectively dealing with the unique, rapidly changing composite interference of airports, thus ensuring the high accuracy and high reliability of the final output data even in harsh environments, solving the pain point of the sharp drop in accuracy of traditional systems under complex operating conditions. Therefore, the airport ground equipment measurement control method in this invention can obtain the original reliability of measurement data from a complex interference environment and obtain a reliable measurement value after error compensation. Attached Figure Description

[0052] Figure 1 This is a flowchart illustrating the airport ground equipment metering and control method in the first embodiment of the present invention.

[0053] Figure 2 This is a schematic diagram of the functional modules in this invention;

[0054] Figure 3This is a schematic diagram of the data processing procedure in this invention;

[0055] Figure 4 This is a schematic diagram illustrating how the evaluation module migrates between different state types based on changes in the values ​​of evaluation factors.

[0056] The objectives, features, and advantages of this invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0057] It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the invention.

[0058] In the following description, the use of suffixes such as "unit," "component," or "element" to denote elements is solely for the purpose of illustrative purposes and has no specific meaning in itself. Therefore, "unit," "component," or "element" may be used interchangeably.

[0059] Please see Figures 1 to 3 The first embodiment of the present invention provides an airport ground equipment metering and control method, applied to an airport ground equipment metering and control system. The system includes a trusted metering edge terminal deployed at the target ground equipment site and a trusted data management platform deployed in the airport central computer room. The trusted metering edge terminal includes a sensor module, a multi-dimensional operating condition sensing module, an edge intelligent computing module, and a trusted data encapsulation module. The airport ground equipment metering and control method includes the following steps:

[0060] Step S10: Synchronously trigger the sensor module and the multi-dimensional working condition sensing module to collect the raw measurement data of the target ground equipment through the sensor module and collect the working condition data through the multi-dimensional working condition sensing module. The working condition data includes the vibration spectrum data and electromagnetic field intensity data of the measurement site.

[0061] Step S20: Through the edge intelligent computing module, error compensation is performed on the original measurement data based on the original measurement data, operating condition data and error compensation model to simulate and generate a reliable measurement value after time-series error compensation. A process reliability data chain is generated based on the state transition of the operating condition data, thereby generating a data reliability label coupled with the operating condition data in time sequence.

[0062] Step S30: The trusted measurement value and the data trustworthiness label coupled with the operating condition data are standardized and encapsulated by the trusted data encapsulation module and sent to the trusted data management platform.

[0063] The technical solution of this invention helps to solve the technical problem that existing airport ground equipment metering control systems cannot guarantee the original reliability of metering data obtained from complex interference environments. Specifically, this invention constructs an edge trustworthy layer with real-time computing and intelligent judgment capabilities between the traditional perception layer and the application layer by deploying independent trusted metering edge terminals on the target ground equipment. The trusted metering edge terminal not only synchronously collects raw metering data and multi-dimensional operating condition data, but also completes error compensation and reliability assessment using edge intelligent computing modules at the first moment and on the first site when the data is generated. This allows the data to complete the transformation from raw signal to trusted information with quality proof before leaving the equipment, generating a process reliability data chain that corresponds to the original metering data and trusted metering values ​​in time sequence. From the system architecture perspective, this eliminates the possibility of untrusted raw data being erroneously transmitted to the upper layer, solving the long-standing problem of the disconnect between perception and application. Furthermore, by synchronously collecting multi-dimensional operating condition data of vibration spectrum and electromagnetic field intensity and precisely coupling it with the raw metering data in the time domain, the physical environment of each metering operation is completely and quantitatively recorded. Therefore, the system in this invention no longer passively receives an isolated, meaningless reading, but can clearly know the intensity and spectral characteristics of the vibration and electromagnetic interference that generated the reading. This is equivalent to making the sensor's working process transparent and traceable throughout, providing a unique data foundation for subsequent accurate compensation and reliability judgment. The edge intelligent computing module uses an error compensation model, taking real-time collected multi-dimensional operating condition data as input, dynamically calculating the estimated value of the measurement error introduced under the current interference environment, and compensating the original measurement data in real time to generate a reliable measurement value. This method directly models and eliminates the mapping relationship between interference and error, effectively dealing with the unique, rapidly changing composite interference of airports, thus ensuring the high accuracy and high reliability of the final output data even in harsh environments, solving the pain point of the sharp drop in accuracy of traditional systems under complex operating conditions. Therefore, the airport ground equipment measurement control method in this invention can obtain the original reliability of measurement data from a complex interference environment and obtain a reliable measurement value after error compensation.

[0064] The process credibility data chain is a complete causal chain of decisions made by the system based on what evidence, following what logical rules, and making what state judgment. It is a structured data object with evidentiary value used for post-event auditing and accountability, rather than a simple operation log.

[0065] Furthermore, this invention provides a data credibility tag deeply coupled with all operating condition data in this measurement process. This tag is generated based on a comprehensive analysis of information such as synchronous operating conditions, compensation processes, and model confidence levels, transforming data credibility from a vague internal judgment into explicit information that can be transmitted, verified, and audited. When this data with credibility tags is uploaded to the management platform, users can immediately know its credibility level while viewing the original data results, and can also obtain the credible measurement value after error compensation. This provides a basis for subsequent accurate settlement, operational analysis, and responsibility determination, establishing a full-chain trust from the data source to the final application.

[0066] This invention shifts the quality control node from reactive to proactive through real-time processing and tag generation at trusted metering edge terminals. Once a risk indicator appears during the compensation process or reliability assessment, the system immediately reflects this through tag status and can trigger real-time alarms, allowing maintenance personnel to intervene before the operation is completed. Simultaneously, the accumulated massive amounts of coupled operational condition-error-reliability data enable the analysis of interference patterns and reliability characteristics for different equipment, aircraft positions, and flight types. This allows for proactive preventative maintenance, such as equipment health prediction and interference source localization, significantly enhancing the intelligence level of the airport ground support system.

[0067] Data collected by ground equipment at airport targets is subject to high-intensity vibrations and complex electromagnetic interference generated by airport operations; meanwhile, high-power ground power supplies generate strong current surges and electromagnetic harmonics upon startup. These interference factors severely disrupt the raw measurement data collected by the sensor modules.

[0068] Specifically, to ensure synchronized triggering of the sensor module and the multi-dimensional operating condition sensing module, a high-precision central timer is set up within the trusted metering edge terminal. This timer generates a unified sampling clock pulse, which is then distributed to the sensor module and the multi-dimensional operating condition sensing module via hardware wiring. This hardware-level synchronization method physically ensures the alignment of sampling times across all data channels, enabling subsequent analysis of the instantaneous impact of vibration and electromagnetic transient interference on metering readings.

[0069] During each sampling, the sensor module and the multi-dimensional condition sensing module not only record the sampled value but also obtain a unified and unique timestamp from the high-precision system clock. After all data enters the edge intelligent computing module, the system aligns and resamples the data streams of all channels based on this timestamp to ensure analysis and processing under the same time reference.

[0070] According to the first embodiment of the airport ground equipment metering and control method of the present invention, and in the second embodiment of the airport ground equipment metering and control method of the present invention, step S20 includes:

[0071] Step S21: Receive raw metering data and operating condition data through the edge intelligent computing module;

[0072] Step S22: Input the original measurement data and operating condition data into the error compensation model, calculate the dynamic error estimate corresponding to the time series under the current operating condition, and calculate the reliable measurement value corresponding to the time series after compensating the original measurement data.

[0073] Step S23: Generate a process reliability data chain based on the state transition of the working condition data, and generate a data reliability label that is coupled with the original measurement data in time sequence. The data reliability label includes the reliability level and interference type corresponding to the original measurement data. The interference type includes vibration-dominated interference, electromagnetic-dominated interference, and composite interference.

[0074] Specifically, the sensor module is used to collect raw metering data of the target ground equipment (for example, the target ground equipment can be a circuit breaker, air conditioner, well equipment, power supply, and the target ground equipment can also be the raw metering data of the medium or energy supplied to or obtained from the aircraft), and its specific composition depends on the type of target ground equipment.

[0075] For example, if the target ground equipment is a ground static power source, the sensor module includes a three-phase power metering chip (such as the ADE9000 series) to synchronously collect the effective values ​​of voltage and current of the three phases A, B, and C, as well as the calculated electrical parameters such as active power, reactive power, apparent power, energy, power factor, frequency, and harmonic content.

[0076] For example, if the target ground equipment is a ground air supply vehicle, the sensor module includes a thermal mass flow meter and a pressure / temperature transmitter to collect the mass flow rate, pressure, and temperature of the supplied air.

[0077] The core task of the multi-dimensional working condition sensing module is to quantitatively characterize the complex physical interference environment at the metering site, and the working condition data it collects is the key input for solving metering errors.

[0078] Regarding vibration spectrum data: its acquisition can be achieved using a triaxial industrial-grade vibration accelerometer (such as the IEPE type). This sensor is directly mounted on a rigid structure near the main metering sensor (such as a flow meter or electricity meter), or on a critical vibration transmission path of the equipment frame, to sense multi-directional, broadband mechanical vibrations caused by uneven ground, the equipment's own engine, aircraft auxiliary power units, aircraft engine operation, etc.

[0079] The acquired raw vibration acceleration time-domain signal is transmitted to the edge intelligent computing module. The computing unit preprocesses the signal (e.g., DC removal and filtering) and then transforms it from the time domain to the frequency domain using a Fast Fourier Transform (FFT) to obtain the vibration spectrum. This spectrum clearly shows the vibration energy distribution of different frequency components (e.g., the fundamental frequency and its harmonics corresponding to the aircraft engine's rotational speed). The vibration energy amplitude at a specific frequency is one of the key feature inputs for the subsequent error compensation model, because different types of equipment have different sensitivities to vibrations at specific frequencies.

[0080] Regarding electromagnetic field strength data: Data acquisition can be achieved using a broadband electromagnetic field strength probe (e.g., covering 100kHz to 6GHz) and a matching conditioning circuit. This probe is placed inside the equipment control cabinet or near cables to detect radiated and conducted electromagnetic interference generated by high-power frequency converters (such as terrestrial power supplies), high-frequency switching power supplies, wireless communication equipment (walkie-talkies, HF radios), radar, etc.

[0081] After the acquired radio frequency signals are conditioned and converted from analog to digital, the edge intelligent computing module can perform frequency domain analysis to obtain the field strength amplitude or power spectral density in specific frequency bands of interest (such as the civil aviation VHF communication band of 118-137MHz, or the GPS L1 band of 1575.42MHz). Electromagnetic interference may enter the sensor signal line or power supply circuit through inductive coupling, causing reading drift or impulse noise. Therefore, its real-time intensity is another core input for error compensation.

[0082] Furthermore, if further error elimination is required, optional supplementary operating condition data can be added: to further improve model accuracy, the multi-dimensional operating condition sensing module can also include ambient temperature and humidity sensors and key equipment temperature sensors (such as motor winding temperature and power device heatsink temperature). Temperature and humidity may affect the zero-point drift and sensitivity of sensor circuits, while the equipment's own temperature is an indirect reflection of its thermal stability and load status.

[0083] On the time axis t, the sensor data stream and the operating condition data stream (including vibration spectrum) Electromagnetic field strength The data is fed into a first-in-first-out (FIFO) synchronous data buffer in strict synchronization. The buffer ensures that at any given moment during analysis... The edge intelligent computing module can acquire meter readings and their corresponding complete operating condition data at the same time. This precise alignment and correlation of physical data from the same time series but different dimensions is the prerequisite for achieving accurate error correlation analysis and compensation in this invention, and also the technical basis for generating credibility tags that are coupled with the time series of operating condition data.

[0084] In a second embodiment of the airport ground equipment metering and control method of the present invention, and in a third embodiment of the airport ground equipment metering and control method of the present invention, step S22 includes:

[0085] Step S221: Extract the feature vector of the working condition data under time series. The feature vector includes vibration feature vector and electromagnetic feature vector. The vibration feature vector is the characteristic frequency amplitude of the vibration spectrum data, and the electromagnetic feature vector is the average field strength of the electromagnetic field strength data in the specified frequency band.

[0086] Step S222: Input the original measurement data and the feature vector under the time series into the error compensation model to calculate the dynamic error estimate corresponding to the time series under the current operating condition, so as to calculate the reliable measurement value corresponding to the time series after compensating the original measurement data.

[0087] The purpose of extracting the feature vectors of operating condition data in time series is to transform the synchronously collected, high-dimensional, unstructured raw operating condition data stream into a set of low-dimensional structured numerical features, which can then be used as input to the error compensation model.

[0088] (1) For vibration spectrum data, the original vibration signal from the multi-dimensional working condition sensing module is usually the time-domain waveform output by the triaxial accelerometer. The system first preprocesses the data, then performs a Fast Fourier Transform on the data for each time window (e.g., 256 ms in length, 100 ms in sliding step) to obtain the vibration spectrum corresponding to each axis. .

[0089] Determine a set of characteristic frequencies. Each characteristic frequency refers to a frequency strongly correlated with a known interference source. The set of characteristic frequencies is as follows: For each characteristic frequency, in the vibration spectrum Take a narrow band The peak amplitude within the range is used as the intensity characteristic of this characteristic frequency component. .

[0090] Therefore, the vibration characteristic vector within the time window is:

[0091] ;

[0092] (2) The original electromagnetic field data is the time-domain signal or preliminary frequency-domain spectrum obtained by scanning within a wide frequency band using a broadband probe. The system also converts it to the frequency domain to obtain the electromagnetic spectrum. .

[0093] Based on the characteristics of the airport's electromagnetic environment, several designated frequency bands are predefined. These frequency bands have a clear correlation with interference.

[0094] For each specified frequency band The average field strength over the entire frequency band is calculated and used as the characteristic of the interference intensity in that frequency band. , Therefore, the electromagnetic eigenvector is .

[0095] (3) The vibration feature vector and electromagnetic feature vector within the same spatiotemporal window are concatenated into a joint feature vector. , using an input error compensation model.

[0096] The error compensation model is a supervised learning model, which essentially learns a complex nonlinear mapping function F between the operating condition feature vector and the sensor error. In a preferred embodiment, this model is a deep neural network, and the number of nodes in its input layer is... The dimensions are the same, and the output layer is usually a single node, corresponding to the error estimate.

[0097] The error compensation model simultaneously receives raw measurement data from the sensor module that is strictly synchronized with time t. The compensation calculation shall be performed according to the following formula:

[0098] ;

[0099] in, The compensated reliable measurement value corresponding to the time series. This is the estimated dynamic error value corresponding to the time sequence under the current operating conditions.

[0100] According to the third embodiment of the airport ground equipment metering and control method of the present invention, and in the fourth embodiment of the airport ground equipment metering and control method of the present invention, the method further includes:

[0101] Step S40: In the controlled environment parameters, acquire the observation and measurement data collected by the sensor module of the target ground equipment under the condition of known interference, wherein the interference conditions include vibration interference and electromagnetic field interference.

[0102] Step S50: In the controlled environment parameters, obtain the control measurement data collected by the sensor module of the target ground equipment under the condition that no known interference is applied;

[0103] Step S60: Determine the amount of error imposed by the interference-free conditions in the controlled environment based on the observed measurement data and the control measurement data;

[0104] Step S70: Construct a sample dataset of interference conditions and error quantities;

[0105] Step S80: Input the sample dataset into the neural network model for training to obtain the error compensation model.

[0106] In a controlled laboratory environment, a typical complex interference condition of airport ground equipment under the conditions of aircraft engine start-up, high-power power supply start-up, and wireless communication equipment operation is simulated. The interference conditions are vibration spectrum and electromagnetic field that can be independently controlled and accurately quantified.

[0107] The sensor module simultaneously collects observation and measurement data under the combined interference conditions, as well as control measurement data under conditions without the interference.

[0108] For each set of synchronously collected observation and measurement data and control measurement data, the difference constitutes the calibration error under the specific known composite interference condition.

[0109] Construct a sample dataset with the feature vector of the specific known composite interference condition as input and the calibration error quantity as output;

[0110] Using the sample dataset, a neural network model is trained to establish the nonlinear mapping relationship from the multidimensional working condition feature vector to the dynamic error estimate, thereby obtaining the error compensation model.

[0111] Since both the observational and control measurement data are collected under the same controlled environmental parameters, the resulting training data is purer and eliminates interference caused by environmental changes.

[0112] According to the third embodiment of the airport ground equipment metering and control method of the present invention, and the fifth embodiment of the airport ground equipment metering and control method of the present invention, step S23 includes:

[0113] Step S231: Calculate the evaluation factors in real time, including environmental steady-state factors, compensated confidence factors, and process consistency factors.

[0114] Step S232: Based on the numerical change trend of the evaluation factors, drive the evaluation module of the credibility status to perform state transition. According to the state transition sequence of the evaluation module within the time interval of this measurement task, generate the process credibility data chain. The status of the evaluation module includes initialization status, data validity status, credibility compensation status, risk warning status, and data invalid status.

[0115] Step S233: Based on the final state of the evaluation module at the end of the task, the final credibility level of this measurement task is generated by mapping. Based on the final credibility level and the process credibility data chain, a data credibility label coupled with the original measurement data in time sequence is generated.

[0116] Real-time calculation of evaluation factors is used to quantify the credibility of measurement data from different dimensions. A set of dynamic evaluation indicators can be obtained based on real-time calculation of evaluation factors.

[0117] This embodiment also defines an evaluation module. By driving the evaluation module to perform state transitions, the evaluation module can be made to have state memory capability and logical judgment capability.

[0118] The generation of the process credibility data chain is to record every state transition event of the evaluation module in a timeline. For each transition, not only is the timestamp of the transition recorded, but also the key evaluation factors that triggered the transition and the associated original data fragments are recorded simultaneously. The resulting state transition sequence and the accompanying evidence information together constitute an immutable and fully traceable process credibility data chain, thus recording the complete logical process by which the system judges data quality.

[0119] In this embodiment, the final conclusion of the dynamic evaluation is also packaged with the process data to generate a structured tag rich in credible information.

[0120] The data credibility label includes user-readable summary information, namely the final credibility registration obtained based on the final state mapping, and key summaries extracted from the process credibility data chain.

[0121] The data credibility label also includes a machine-readable index, which is a unique index identifier that points to the complete stored process credibility data chain.

[0122] In the fifth embodiment of the airport ground equipment metering and control method of the present invention, and in the sixth embodiment of the airport ground equipment metering and control method of the present invention, step S231 includes:

[0123] Step S2311: Based on the real-time vibration spectrum data and real-time electromagnetic field intensity data of the target ground equipment, as well as the historical vibration spectrum data and historical electromagnetic field intensity data, calculate the distance between the current feature vector and the historical baseline feature vector in the multivariate statistical space to determine the environmental steady-state factor.

[0124] Step S2312: Calculate the distance from the real-time vibration spectrum data and real-time electromagnetic field intensity data of the target ground equipment to the feature space cluster center of the historical training dataset used to train the error compensation model, in order to determine the compensation confidence factor;

[0125] Step S2313: Compare the time series of the compensated reliable measurement values ​​with the set reference time series to determine the process consistency factor.

[0126] The environmental steady-state factor is used to evaluate the stability of the current operating environment. The system compares the real-time collected vibration and electromagnetic operating condition data with the operating condition baseline model established during the equipment's historical normal operation. By calculating the statistical distance between the current data and the baseline in a multivariate feature space and normalizing it, the environmental steady-state factor is obtained. An environmental steady-state factor close to 1 indicates that the current environment is highly consistent with historical normal conditions and is stable and reliable; an environmental steady-state factor value close to 0 indicates an abnormal deviation in the environment, with unknown interference or drastic changes.

[0127] The compensation confidence factor is used to evaluate the reliability of the current output of the error compensation model. Its calculation is based on the distribution of the current operating condition feature vector in the feature space of the model training data. The compensation confidence factor can be represented by calculating the distance from the current feature vector to the cluster center of the model training samples. The closer the distance, the more common the current operating condition, and the higher the confidence level (approaching 1); the farther the distance, the more likely the operating condition is to be in an area where the model training is insufficient, and in this case, even if the model provides a compensation value, its confidence level should decrease (approaching 0).

[0128] The process consistency factor is used to verify whether the compensated measurement data conforms to physical laws and business logic over time. The system analyzes the time series of the compensated reliable measurement values. For example, for the aircraft refueling process, the flow rate should monotonically and non-decreasing over time in the set reference time series. The system can calculate the local derivative of the series or compare it with the output of a simple time series prediction model trained on historical normal data or the set reference time series. If the actual data deviates significantly from the expected logic (monotonicity) or the predicted value (or the set reference time series), it indicates that there may be anomalies such as instantaneous jumps or packet loss in the data, and the process consistency factor will be significantly reduced.

[0129] Specifically, the compensation confidence factor is calculated as follows:

[0130] The model training samples were used to obtain Q cluster centers through a clustering algorithm: Each cluster center They are all vectors with the same dimension as the feature vectors. .

[0131] Real-time acquisition and extraction of current feature vectors .

[0132] ;

[0133] in, For the current feature vector To the cluster center Euclidean distance; For the current feature vector The p-th dimension; For the q-th cluster center The p-th dimension; , respectively representing the vibration amplitude or electromagnetic field strength;

[0134] ;

[0135] in, For the current feature vector The minimum distance to each cluster center The corresponding cluster centers are , This represents the typical operating condition that is closest to the current operating condition, i.e., the nearest neighbor cluster;

[0136] ;

[0137] To compensate for the confidence factor; for The corresponding maximum radius within the cluster represents the total radius of all training samples within that cluster. The maximum distance; The relaxation coefficient is used to define the boundary of confidence decay. ;when exist When within the scope, it is considered very familiar; when Exceed At that point, it was considered to have exceeded the reliable range, and the confidence level dropped to 0.

[0138] Please refer to Figure 4 According to the fifth embodiment of the airport ground equipment metering and control method of the present invention, and the seventh embodiment of the airport ground equipment metering and control method of the present invention, step S232 includes:

[0139] Step S2321: Define the state type of the evaluation module and the numerical range of the evaluation factors corresponding to each state type;

[0140] Step S2322: Based on the numerical change trend of the evaluation factors, drive the evaluation module to migrate between different state types to form a state migration sequence of the evaluation module.

[0141] Step S2323: Generate a process credibility data chain based on the state type change events, state type change event timestamps, and evaluation factor types driving the state type change events in the state transition sequence.

[0142] The initialization state refers to the default state when the task starts or after the system is reset. In this state, initial data is being acquired and evaluation conditions are not available.

[0143] The data validity state represents a basically reliable state. In this state, the raw data acquisition is normal, and no significant interference requiring error compensation is detected, or although interference exists, it is still within the system's default tolerance. Data in this state can be recorded, but has not undergone active compensation.

[0144] The credible compensation state represents a high-confidence state. Entering this state indicates that the system has detected significant disturbances and activated the error compensation model, which is operating with high confidence. The compensated credible measurement values ​​output at this time, corresponding to the time series, are intelligently corrected and reliable results, serving as recommended data for high-precision settlement and core analysis.

[0145] The risk warning status represents a suspicious or abnormal state. This is a critical intermediate buffer state, indicating that the system has detected one or more risk signals that may lead to unreliable data, but has not yet reached the criteria for complete failure. This status triggers a real-time alarm, prompting operations and maintenance personnel to pay attention.

[0146] The data invalid state represents an invalid state. Entering this state indicates that the data has been determined to be unusable due to hardware failure, communication interruption, extremely untrusted operating conditions, or manual verification. Data generated in this state will be explicitly marked and should not be used for any formal settlement or analysis.

[0147] For each state (except the initial state), a corresponding multidimensional evaluation factor numerical range is defined, which is based on the environmental steady-state factors. Compensation confidence factor and process consistency factor This constitutes a multidimensional space. For example, the numerical space of evaluation factors corresponding to the valid state of data can be: This indicates that the environment is stable, the model has basic confidence, and the process logic is normal.

[0148] The evaluation factor range for the credible compensation state, based on the data validity state, adds the condition that the error compensation model is in an active state.

[0149] The evaluation factor range for risk warning status is dynamically triggered, for example, defined as: { The descent exceeds the gradient value ΔP within the time increment} or { <0.3}, etc., meaning that any key evaluation factor experiences a rapid decline or falls below the safety threshold.

[0150] State transitions are dynamically triggered by the real-time numerical combinations of evaluation factors and their temporal trends. The system checks the current evaluation factor values ​​in each calculation cycle (e.g., 10 times per second) and determines whether a state should be switched based on a set of predefined state transition rules.

[0151] According to the fifth embodiment of the airport ground equipment metering and control method of the present invention, and the eighth embodiment of the airport ground equipment metering and control method of the present invention, step S233 includes:

[0152] Step S2331: Map the final state of the evaluation module at the end of the task to the final credibility level of this measurement task for quality control.

[0153] Step S2332: Extract summary information from the process credibility data chain to generate a credibility assessment summary;

[0154] Step S2333: Encapsulate the final credibility level, credibility assessment summary, and storage index identifier of the process credibility data chain into a structured data credibility label.

[0155] Step S2334: Time-series association binding of data credibility labels with corresponding compensated credibility measurement values.

[0156] This data credibility label is strictly coupled with the compensated credibility measurement value in time. For short tasks, a single overall label can be generated; for long tasks or tasks with frequently changing states, sub-labels can be generated in segments. Finally, the data credibility label and the corresponding time-series credibility measurement value data are sent to the trusted data management platform to ensure that the credibility of any data can be checked and verified at any time when it is used.

[0157] In summary, this invention creatively elevates data credibility to a dynamically interpretable, and fully evidence-supported intelligent evaluation system. It not only provides a conclusion on whether the data is credible, but more importantly, it offers a complete logical chain and original evidence explaining why the data is credible. This fundamentally establishes a transparent trust mechanism for data quality, providing reliable technical support for high-value settlement and refined operation and maintenance.

[0158] In any of the second to eighth embodiments of the airport ground equipment metering and control method of the present invention, in the ninth embodiment of the airport ground equipment metering and control method of the present invention, step S30 includes:

[0159] Step S31: Through the trusted data encapsulation module, the trusted measurement value, the original measurement data, the operating condition data, the error estimate, the data trustworthiness label coupled with the operating condition data, the timestamp, and the target ground equipment ID are encapsulated into a trusted data packet and uploaded to the trusted data management platform.

[0160] The airport ground equipment metering and control method also includes:

[0161] Step S90: The trusted data management platform accesses trusted data streams from multiple aircraft stands and various types of equipment (fueling trucks, power supply trucks, and air conditioning trucks) within the airport.

[0162] Step S100: In real time, the vibration spectrum data and electromagnetic field intensity data of each machine position are aggregated to generate a real-time interference intensity map of the entire field, so as to visualize the interference intensity of different time sequences in each region.

[0163] Step S110: Based on the changes in interference intensity at different times in each region, determine the triggering time for synchronously triggering sensor modules and multi-dimensional operating condition sensing modules in each region to collect raw measurement data and operating condition data.

[0164] Therefore, by going through steps S90 to S110, we can return to step S10 to adjust the timing of the synchronous trigger sensor module and the multi-dimensional working condition sensing module so as to minimize the impact of interference intensity on the original measurement data.

[0165] To achieve the above objectives, the present invention also provides an airport ground equipment metering control system, which applies the airport ground equipment metering control method; the system includes a trusted metering edge terminal deployed at the target ground equipment site and a trusted data management platform deployed in the airport central computer room; the trusted metering edge terminal includes a sensor module, a multi-dimensional operating condition perception module, an edge intelligent computing module and a trusted data encapsulation module;

[0166] The sensor module is used to collect raw metering data from the target ground equipment;

[0167] The multi-dimensional working condition sensing module is used to collect working condition data, which includes vibration spectrum data and electromagnetic field intensity data at the metering site.

[0168] The edge intelligent computing module is used to perform error compensation on the original measurement data based on the original measurement data, operating condition data and error compensation model, so as to simulate and generate a reliable measurement value after time-series error compensation, and generate a process reliability data chain based on the state transition of the operating condition data, thereby generating a data reliability label coupled with the operating condition data in time sequence.

[0169] The trusted data encapsulation module is used to standardize and encapsulate trusted measurement values ​​and data trust labels coupled with operating condition data, and send them to the trusted data management platform.

[0170] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms, or by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a readable storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device to enter the methods described in the various embodiments of the present invention.

[0171] In the description of this specification, references to terms such as "one embodiment," "another embodiment," "other embodiments," or "first embodiment to Xth embodiment," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, method steps, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0172] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0173] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0174] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A method for metering and controlling airport ground equipment, characterized in that, The system is applied to a metering and control system for airport ground equipment. The system includes a trusted metering edge terminal deployed at the target ground equipment site and a trusted data management platform deployed in the airport's central computer room. The trusted metering edge terminal includes a sensor module, a multi-dimensional operating condition sensing module, an edge intelligent computing module, and a trusted data encapsulation module; the airport ground equipment metering control method includes the following steps: The sensor module and the multi-dimensional working condition sensing module are triggered synchronously to collect raw measurement data of the target ground equipment through the sensor module and working condition data through the multi-dimensional working condition sensing module. The working condition data includes vibration spectrum data and electromagnetic field intensity data of the measurement site. Through the edge intelligent computing module, the original measurement data, operating condition data and error compensation model are used to perform error compensation on the original measurement data in order to simulate and generate a reliable measurement value after time-series error compensation. The process reliability data chain is generated according to the state transition of the operating condition data, thereby generating a data reliability label coupled with the operating condition data in time sequence. The trusted data encapsulation module standardizes and encapsulates trusted measurement values ​​and data trust labels coupled with operating condition data, and sends them to the trusted data management platform. The sensor module is used to collect raw metering data of the target ground equipment, including circuit breakers, air conditioners, well equipment, power supplies, and equipment used to supply or obtain media or energy from the aircraft; vibration spectrum data is used to sense multi-directional, broadband mechanical vibrations caused by uneven ground, the equipment's own engines, aircraft auxiliary power units, and aircraft engine operation; electromagnetic field strength data is used to sense radiating and conducted electromagnetic interference generated by high-power frequency converters, high-frequency switching power supplies, wireless communication equipment, and radar. Among them, the feature vector of the working condition data in time series is extracted, and the synchronously collected, high-dimensional, unstructured raw working condition data stream is transformed into a set of low-dimensional structured numerical features, which are used as the input of the error compensation model. For vibration spectrum data, the raw vibration signal from the multi-dimensional working condition sensing module is the time-domain waveform output by the triaxial accelerometer. The system first preprocesses the time-domain waveform, then performs a Fast Fourier Transform on the data for each time window to obtain the vibration spectrum corresponding to each axis. Determine a set of characteristic frequencies, where each characteristic frequency is a frequency correlated with the strength of a known interference source. The set of characteristic frequencies is... For each characteristic frequency, in the vibration spectrum Take a narrow band The peak amplitude within the range is used as the intensity feature of the characteristic frequency component. Therefore, the vibration characteristic vector within the time window is: ； The raw electromagnetic field data is a time-domain signal or a preliminary frequency-domain spectrum obtained by scanning within a wide bandwidth using a broadband probe; the system also converts the raw electromagnetic field data to the frequency domain to obtain the electromagnetic spectrum. Based on the characteristics of the airport's electromagnetic environment, several designated frequency bands are predefined. The specified frequency bands have a clear interference correlation; for each specified frequency band The average field strength over the entire frequency band is calculated and used as the characteristic of the interference intensity in that frequency band. , Therefore, the electromagnetic eigenvector is ; The vibration feature vector and electromagnetic feature vector within the same spatiotemporal window are concatenated into a joint feature vector. The input error compensation model is used. The error compensation model is a supervised learning model with a single output node representing the error estimate. It also receives raw measurement data from the sensor module, strictly synchronized with the data at time t. The compensation calculation shall be performed according to the following formula: ； in, The compensated reliable measurement value corresponding to the time series. This is the estimated dynamic error value corresponding to the time sequence under the current operating conditions.

2. The airport ground equipment metering and control method according to claim 1, characterized in that, The steps of using an edge intelligent computing module to perform error compensation on the original measurement data based on the original measurement data, operating condition data, and error compensation model to simulate and generate a reliable measurement value after time-series error compensation, and generating a process reliability data chain based on the state transition of the operating condition data, thereby generating a data reliability label coupled to the operating condition data in a time sequence, include: Raw metering data and operating condition data are received through the edge intelligent computing module; The original measurement data and operating condition data are input into the error compensation model to calculate the dynamic error estimate corresponding to the time series under the current operating condition, so as to calculate the reliable measurement value corresponding to the time series after compensating the original measurement data. Based on the state transition of the operating condition data, a process credibility data chain is generated, and a data credibility label is generated that is coupled with the original measurement data in a time sequence. The data credibility label includes the credibility level and interference type corresponding to the original measurement data. The interference types include vibration-dominated interference, electromagnetic-dominated interference, and composite interference.

3. The airport ground equipment metering and control method according to claim 2, characterized in that, The step of inputting the original measurement data and operating condition data into the error compensation model to calculate the dynamic error estimate corresponding to the time series under the current operating condition, and then calculating the reliable measurement value corresponding to the time series after compensating the original measurement data, includes: Extract the feature vectors of the working condition data in the time series. The feature vectors include vibration feature vectors and electromagnetic feature vectors. The vibration feature vector is the characteristic frequency amplitude of the vibration spectrum data, and the electromagnetic feature vector is the average field strength of the electromagnetic field strength data in the specified frequency band. The original measurement data and the feature vector under the time series are input into the error compensation model to calculate the dynamic error estimate corresponding to the time series under the current operating condition, so as to calculate the reliable measurement value corresponding to the time series after compensating the original measurement data.

4. The airport ground equipment metering and control method according to claim 3, characterized in that, The method further includes: In the controlled environment parameters, the observation and measurement data collected by the sensor module of the target ground equipment under the condition of known interference are obtained. The interference conditions include vibration interference and electromagnetic field interference. Within controlled environmental parameters, comparative measurement data are acquired by the target ground equipment through sensor modules under conditions where no known interference is applied; Based on the observed measurement data and the control measurement data, determine the amount of error imposed by the interference-free conditions in the controlled environment; Construct a sample dataset of interference conditions and error quantities; The sample dataset is input into the neural network model for training to obtain the error compensation model.

5. The airport ground equipment metering and control method according to claim 3, characterized in that, The step of generating a process reliability data chain based on the state transition of operating condition data and generating a data reliability label coupled with the original measurement data in a time sequence includes: Evaluation factors are calculated in real time, including environmental steady-state factors, compensated confidence factors, and process consistency factors. Based on the numerical change trend of the evaluation factors, the evaluation module of the credibility status is driven to perform state transition. According to the state transition sequence of the evaluation module within the time interval of this measurement task, a process credibility data chain is generated. The status of the evaluation module includes initialization status, data validity status, credibility compensation status, risk warning status, and data invalid status. Based on the final state of the evaluation module at the end of the task, the final credibility level of this measurement task is generated. Based on the final credibility level and the process credibility data chain, a data credibility label coupled with the original measurement data in time sequence is generated.

6. The airport ground equipment metering and control method according to claim 5, characterized in that, The step of real-time calculation of evaluation factors includes: Based on the real-time vibration spectrum data and real-time electromagnetic field intensity data of the target ground equipment, as well as the historical vibration spectrum data and historical electromagnetic field intensity data, the distance between the current eigenvector and the historical baseline eigenvector in the multivariate statistical space is calculated to determine the environmental steady-state factor. Calculate the distance from the real-time vibration spectrum data and real-time electromagnetic field intensity data of the target ground equipment to the feature space cluster center of the historical training dataset used to train the error compensation model, in order to determine the compensation confidence factor. The time series of compensated reliable measurements are compared with a set reference time series to determine the process consistency factor.

7. The airport ground equipment metering and control method according to claim 5, characterized in that, The step of driving the credibility status evaluation module to perform state transitions based on the numerical change trend of evaluation factors, and generating a process credibility data chain based on the state transition sequence of the evaluation module within the time interval of this measurement task, includes: Define the status types of the evaluation module, and the corresponding evaluation factor value range for each status type; Based on the numerical change trend of the evaluation factors, the evaluation module is driven to migrate between different state types to form a state migration sequence of the evaluation module. A process credibility data chain is generated based on the state type change events, the timestamps of the state type change events, and the evaluation factor types that drive the state type change events in the state transition sequence.

8. The airport ground equipment metering and control method according to claim 5, characterized in that, The steps of mapping and generating a final credibility level for this measurement task based on the final state of the evaluation module at the end of the task, and generating a data credibility label coupled to the original measurement data in a time sequence based on the final credibility level and the process credibility data chain, include: The final state of the evaluation module at the end of the task is mapped to the final credibility level of this measurement task for quality control. Extract summary information from the process credibility data chain to generate a credibility assessment summary; The final credibility level, credibility assessment summary, and storage index identifier of the process credibility data chain are encapsulated into a structured data credibility label. The data credibility labels are time-series associated and bound with the corresponding compensated credibility measurement values.

9. The airport ground equipment metering and control method according to any one of claims 2 to 8, characterized in that, The step of standardizing and encapsulating trusted measurement values ​​and data trustworthiness labels coupled with operating condition data through a trusted data encapsulation module, and sending them to the trusted data management platform, includes: The trusted data encapsulation module encapsulates trusted measurement values, raw measurement data, operating condition data, error estimates, data trust labels coupled with operating condition data, timestamps, and target ground equipment IDs into trusted data packets, which are then uploaded to the trusted data management platform.

10. A metering and control system for airport ground equipment, characterized in that, The airport ground equipment metering control method as described in any one of claims 1 to 9 is applied; the system includes a trusted metering edge terminal deployed at the target ground equipment site and a trusted data management platform deployed in the airport central computer room; The trusted metering edge terminal includes a sensor module, a multi-dimensional working condition sensing module, an edge intelligent computing module, and a trusted data encapsulation module; The sensor module is used to collect raw measurement data from the target ground equipment; The multi-dimensional working condition sensing module is used to collect working condition data, which includes vibration spectrum data and electromagnetic field intensity data at the metering site. The edge intelligent computing module is used to perform error compensation on the original measurement data based on the original measurement data, operating condition data and error compensation model, so as to simulate and generate a reliable measurement value after time-series error compensation, and generate a process reliability data chain based on the state transition of the operating condition data, thereby generating a data reliability label coupled with the operating condition data in time sequence. The trusted data encapsulation module is used to standardize and encapsulate trusted measurement values ​​and data trust labels coupled with operating condition data, and send them to the trusted data management platform. The sensor module is used to collect raw metering data of the target ground equipment, including circuit breakers, air conditioners, well equipment, power supplies, and equipment used to supply or obtain media or energy from the aircraft; vibration spectrum data is used to sense multi-directional, broadband mechanical vibrations caused by uneven ground, the equipment's own engines, aircraft auxiliary power units, and aircraft engine operation; electromagnetic field strength data is used to sense radiating and conducted electromagnetic interference generated by high-power frequency converters, high-frequency switching power supplies, wireless communication equipment, and radar. Among them, the feature vector of the working condition data in time series is extracted, and the synchronously collected, high-dimensional, unstructured raw working condition data stream is transformed into a set of low-dimensional structured numerical features, which are used as the input of the error compensation model. For vibration spectrum data, the raw vibration signal from the multi-dimensional working condition sensing module is the time-domain waveform output by the triaxial accelerometer. The system first preprocesses the time-domain waveform, then performs a Fast Fourier Transform on the data for each time window to obtain the vibration spectrum corresponding to each axis. Determine a set of characteristic frequencies, where each characteristic frequency is a frequency correlated with the strength of a known interference source. The set of characteristic frequencies is... For each characteristic frequency, in the vibration spectrum Take a narrow band The peak amplitude within the range is used as the intensity feature of the characteristic frequency component. Therefore, the vibration characteristic vector within the time window is: ； The raw electromagnetic field data is a time-domain signal or a preliminary frequency-domain spectrum obtained by scanning within a wide bandwidth using a broadband probe; the system also converts the raw electromagnetic field data to the frequency domain to obtain the electromagnetic spectrum. Based on the characteristics of the airport's electromagnetic environment, several designated frequency bands are predefined. The specified frequency bands have a clear interference correlation; for each specified frequency band The average field strength over the entire frequency band is calculated and used as the characteristic of the interference intensity in that frequency band. , Therefore, the electromagnetic eigenvector is ; The vibration feature vector and electromagnetic feature vector within the same spatiotemporal window are concatenated into a joint feature vector. The input error compensation model is used. The error compensation model is a supervised learning model with a single output node representing the error estimate. It also receives raw measurement data from the sensor module, strictly synchronized with the data at time t. The compensation calculation shall be performed according to the following formula: ； in, The compensated reliable measurement value corresponding to the time series. This is the estimated dynamic error value corresponding to the time sequence under the current operating conditions.

Images