An aircraft seat power controller status detection method, system and apparatus

Abstract

This invention discloses a state detection method, system, and device for aircraft seat power controllers, relating to the field of aircraft seat power controller technology. The invention acquires multi-dimensional feature vector information of the aircraft seat power controller in real time, then combines this information with the controller's operating specifications and stored historical operating data to construct a reference baseline information adapted to the controller. Next, it calculates the deviation between the real-time features and the reference baseline using Mahalanobis distance, further calculating the current power controller's health index. After completing the real-time state analysis of the power controller, and combining preset health warning information, it determines whether the controller has health anomalies by using degradation trend parameters in conjunction with the health index. Furthermore, it can calculate the anomaly contribution degree for each feature dimension to accurately locate the specific parameters where the anomaly occurred, thus facilitating the identification of the power controller's fault location.

Description

Technical Field

[0001] This invention relates to the field of aircraft seat power controller technology, and in particular to a status detection method, system and device for an aircraft seat power controller. Background Technology

[0002] As a core terminal component of the aircraft cabin power supply system, the aircraft seat power controller is responsible for providing stable voltage output and on / off control for various electrical devices on the seat. It operates for a long time under intermittent loads, mechanical vibrations, and wide-range temperature alternating environments. Its internal filter capacitors, power switching devices, and connection terminals are prone to progressive aging, such as increased ESR of the output capacitor and increased contact resistance. Ultimately, this can lead to output voltage drops, excessive ripple, or even power outages.

[0003] Currently, the testing of aircraft seat power controllers mostly relies on ground staff to manually check each one, which is not only inefficient but also prone to missing hidden faults due to human judgment errors. Some existing automatic testing solutions can only detect a single parameter and cannot cover the multi-dimensional anomaly identification of the controller in all working states. Summary of the Invention

[0004] The purpose of this invention is to address the shortcomings of existing technologies in detecting aircraft seat power controllers, and to propose a state detection method, system, and device for aircraft seat power controllers.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: The present invention provides a state detection method for an aircraft seat power controller in a first aspect, comprising: The operating specifications of the power controller are obtained, and multiple operating parameter information of the power controller is collected in real time to obtain the multi-dimensional feature vector information of the power controller. Based on the power controller's operating specifications, the multi-dimensional feature vector information of the power controller is analyzed in real time to obtain the power controller's real-time status information. Obtain historical operating data from the power controller and formulate health warning information for the power controller; Based on the health warning information of the power controller, the health status information of the power controller is judged to determine the abnormal health status of the power controller. Obtain the power controller's operating information and predict its health status based on its health condition and operating specifications.

[0006] In one feasible solution, the method for obtaining real-time status information of the power controller includes: Based on the power controller's operating specifications and its historical operating data, determine the power controller's reference information. Based on the reference information of the power controller, the multi-dimensional feature vector information of the power controller is analyzed in real time to obtain the real-time status characteristics of the power controller. Based on the power controller's operating specifications and historical operating data, the real-time status characteristics of the power controller are mapped to obtain the power controller's health index.

[0007] In one feasible approach, the method for obtaining the health index of the power controller includes: Formula 1; Formula 2; In Equation 1, The Mahalanobis distance between the real-time feature vector samples of the power controller and the reference information is given. This is a sample of the current real-time feature vector of the power controller. To reference the mean vector in the baseline information, It is the inverse of the covariance matrix. For transpose operation, This is the difference vector between the current real-time feature vector sample and the mean vector; In Equation 2, For health index, Scaling factor The scaling factor. This is the sharpening factor.

[0008] In one feasible approach, the method for obtaining the real-time status characteristics of the power controller further includes: Based on the real-time status characteristics of the power controller, the inverse covariance matrix in the reference information of the power controller is dynamically and recursively updated. The mean vector is updated using the following formulas respectively. Covariance Matrix : Formula 3; Equation 4; Formula 5; In equations 3 to 5 above, The mean forgetting factor, For dynamic covariance forgetting factor, Basic forgetting factor, The standard deviation of the historical Mahalanobis distance. and These are the mean vector and covariance matrix before the update, respectively. This refers to the multidimensional feature vector information.

[0009] In one feasible approach, the method for determining the abnormal health status of the power controller includes: Based on the health warning information of the power controller and combined with the health index of the power controller, calculate the degradation trend information of the power controller. Based on the multidimensional feature vector information of the power controller, the contribution of the feature dimensions of the power controller's degradation trend information is analyzed, and the abnormal condition data of the power controller in different dimensions are determined respectively. Based on the real-time status characteristics of the power controller, the abnormal status data of the power controller in different dimensions are analyzed to determine the abnormal status parameters of the power controller.

[0010] In one feasible approach, the method for calculating the degradation trend information of the power controller includes: Formula 6; In Equation 6, For degradation trend parameters, and These are preset weights, For the health index at the sampling interval The change within, This refers to the current health index.

[0011] In one feasible approach, the method for determining the abnormal condition data of different dimensions of the power controller includes: Formula 7; In Equation 7, The percentage of anomaly contribution for any feature. and These are respectively the first of the multidimensional feature vector information and the mean vector. One portion, The first covariance inverse matrix is ​​the... Line 1 Column elements, Let be the dimension of the feature vector.

[0012] In one feasible approach, the multidimensional feature vector information includes at least: The input DC bus voltage deviation rate, output USB terminal voltage deviation rate, output current load rate, normalized internal hot spot temperature, and output ripple coefficient are all selected.

[0013] In a second aspect, the present invention also provides a status detection system for an aircraft seat power controller, employing the status detection method for an aircraft seat power controller described in any one of the first aspects above, wherein the detection system further includes: A parameter acquisition module is used to acquire multiple operating parameters of the power controller in real time. A benchmark construction module is used to determine the reference benchmark information of the power controller based on the power controller's operating specifications and past operating data. A status analysis module is used to analyze the health index of the power controller. A health assessment module is used to determine the current health status of the power controller by combining health warning information and health index. A trend prediction module that predicts the future health of the power controller.

[0014] In a third aspect, the present invention also provides a status detection device for an aircraft seat power controller, the detection device comprising: The detection end is electrically connected to the power supply terminal of the power controller of the aircraft seat, and is used to collect multiple operating parameter information of the power controller; The storage terminal is used to store the power controller's operating specifications and past operating data; The processing end is electrically connected to the detection end and the storage unit respectively, and is used to execute a state detection method for an aircraft seat power controller as described in any one of the first aspects; The output terminal is used to output the prediction results of the power controller's abnormal health status and usage conditions.

[0015] The beneficial effects of this invention are as follows: This invention acquires multi-dimensional feature vector information of the aircraft seat power controller in real time, and then constructs a reference benchmark information adapted to the controller by combining the power controller's operating specifications and stored past operating data. Then, it calculates the deviation between the real-time features and the reference benchmark by using Mahalanobis distance, and further calculates the current power controller's health index. After completing the real-time status analysis of the power controller, it combines preset health warning information with degradation trend parameters and the health index to determine whether the controller has health anomalies. It can also calculate the anomaly contribution degree by each feature dimension to accurately locate the specific parameters where the anomaly occurred, so as to find the fault location of the power controller. Attached Figure Description

[0016] Figure 1This is a schematic diagram of the overall process of a state detection method for an aircraft seat power controller provided in an embodiment of the present invention; Figure 2 This is a partial flowchart of a state detection method for an aircraft seat power controller provided in an embodiment of the present invention; Figure 3 This is a schematic diagram illustrating the process of determining the health abnormality of the power controller in a status detection method for an aircraft seat power controller provided in an embodiment of the present invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0018] Furthermore, if the embodiments of this invention involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the meaning of "and / or" throughout the text includes three parallel solutions; for example, "A and / or B" includes solution A, solution B, or a solution where both A and B are satisfied simultaneously. Furthermore, the technical solutions of the various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. When the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed by this invention.

[0019] Reference Figure 1 and Figure 3As shown, to address the shortcomings of existing technologies in detecting aircraft seat power controllers, this invention provides a state detection method for aircraft seat power controllers. This method acquires multi-dimensional feature vector information of the aircraft seat power controller in real time, then combines this information with the controller's operating specifications and stored historical operating data to construct a reference baseline. The deviation between the real-time features and the reference baseline is calculated using Mahalanobis distance to further calculate the current power controller's health index. After completing the real-time state analysis of the power controller, and combining preset health warning information, the method uses degradation trend parameters and the health index to determine if the controller has any health anomalies. Furthermore, the anomaly contribution can be calculated for each feature dimension to accurately pinpoint the specific parameters causing the anomaly, thus facilitating the identification of the power controller's fault location. This method, through multi-dimensional parameter acquisition and dynamically updated baseline comparison, enables multi-dimensional anomaly identification across the entire operating state of the controller. It eliminates the need for manual inspection, improving detection efficiency, and avoids the omission of hidden faults due to human error, effectively improving the detection effect for aircraft seat power controllers.

[0020] Specifically, a state detection method for an aircraft seat power controller includes: acquiring the operating specifications of the power controller and collecting multiple operating parameter information of the power controller in real time to obtain multi-dimensional feature vector information of the power controller; that is, by deploying multi-dimensional sensors, the operating parameters of the power controller during operation are collected in real time, and then the multi-dimensional feature vector information of the power controller is formed. It should be noted that the multi-dimensional feature vector information of the power controller includes, but is not limited to, any one or a combination of the following: input DC bus voltage deviation rate, output USB terminal voltage deviation rate, output current load rate, normalized value of internal hot spot temperature, and output ripple coefficient. This enables a comprehensive analysis and detection of the power controller's state.

[0021] After obtaining the multi-dimensional operating parameters of the power controller, the multi-dimensional feature vector information of the power controller is analyzed in real time according to the working specifications of the power controller to obtain the real-time status information of the power controller. Then, combined with the power controller's past working data, a health warning threshold adapted to the power controller is formulated. Then, the obtained health index is compared with the preset health warning threshold to determine whether there is a health abnormality in the power controller.

[0022] Reference Figure 2 Specifically, in this embodiment, to facilitate understanding of how to obtain the real-time status information of the power controller through its multi-dimensional feature vector information, the method for obtaining the real-time status information of the power controller includes: Based on the power controller's operating specifications and its historical operating data, reference baseline information for the power controller is determined (including the mean vector of multiple operating parameters of the power controller under normal conditions). Then, based on this reference baseline information, real-time status analysis can be performed on the power controller's multi-dimensional feature vector information to determine its real-time status characteristics. It should be noted that, in this embodiment, the historical operating data of the power controller includes, but is not limited to, data collected and statistically analyzed from power controllers of the same model and specifications under normal operating conditions. Alternatively, it can be data collected and statistically analyzed from the power controller under normal operating conditions after it leaves the factory or undergoes a major overhaul. Specifically, the method for obtaining the real-time status characteristics of the power controller includes: Formula 1; In Equation 1, The Mahalanobis distance between the real-time feature vector samples of the power controller and the reference information is given. This is a sample of the current real-time feature vector of the power controller. To reference the mean vector in the baseline information, It is the inverse of the covariance matrix. The transpose operation converts a column vector into a row vector to facilitate matrix multiplication. This is the difference vector between the current real-time feature vector sample and the mean vector.

[0023] like Figure 2 As shown, in this embodiment, to facilitate subsequent observation of the power controller's real-time status, the real-time status characteristics of the power controller can be mapped based on the power controller's operating specifications and historical operating data to obtain the power controller's health index. Specifically, the method for obtaining the power controller's health index includes: Formula 2; In Equation 2, For health index, Scaling factor The scaling factor. This is the sharpening factor. In this embodiment, the Mahalanobis distance between the real-time feature vector sample in the multi-dimensional feature vector information of the power controller and the mean vector in the reference information can be calculated using Equation 1. That is, by calculating the Mahalanobis distance between the real-time feature vector sample and the reference mean vector and the reference covariance matrix, the Mahalanobis distance can be converted into a health index between 0 and 100 using Equation 2. The closer the health index is to 100, the better the health status of the power controller; the closer it is to 0, the higher the risk of failure.

[0024] In this embodiment, to ensure the accuracy of the detection method for the power controller, after each detection, the mean vector and covariance matrix of the reference benchmark are dynamically and recursively updated based on the real-time characteristics of the current detection. This ensures that the benchmark can adapt to the normal, slow aging process of the controller and avoids misjudgments. Specifically, the dynamic recursive update method is as follows: based on the real-time status characteristics of the power controller, the inverse covariance matrix in the reference benchmark information of the power controller is dynamically and recursively updated. The mean vector is updated using the following formulas respectively. Covariance Matrix : Formula 3; Equation 4; Formula 5; In equations 3 to 5 above, The mean forgetting factor, For dynamic covariance forgetting factor, Basic forgetting factor, The standard deviation of the historical Mahalanobis distance. and These are the mean vector and covariance matrix before the update, respectively. The multidimensional feature vector information refers to the parameters of the power controller as it slowly drifts with device aging during long-term operation. By dynamically and recursively updating the mean vector and covariance matrix of the reference information, the disconnect between the reference information and the actual operating state can be avoided. This ensures that the calculation of the health index always matches the current actual baseline state of the power controller, preventing systematic deviations in the health assessment results due to a fixed reference. The larger the Mahalanobis distance, the smaller the value of the dynamic covariance forgetting factor β, and the higher the degree of preservation of the original covariance matrix, thus avoiding excessive interference from abnormal fluctuation parameters with the stability of the reference.

[0025] like Figure 3As shown in this embodiment, to facilitate rapid location of abnormal parameters after a power controller malfunctions, a health anomaly is determined when the health index falls below a preset health warning threshold. At this point, the anomaly contribution of each feature dimension to the Mahalanobis distance can be further calculated. The greater the anomaly contribution, the higher the impact of that parameter on the overall anomaly. This allows for rapid location of the specific parameter dimension causing the anomaly, directly pinpointing the direction of troubleshooting, significantly shortening troubleshooting time, and facilitating rapid handling by maintenance personnel. Specifically, the method for determining the abnormal health status of the power controller includes: calculating the deterioration trend information of the power controller based on its health warning information and its health index; then analyzing the contribution of each feature dimension to the deterioration trend information based on the multi-dimensional feature vector information of the power controller to determine the abnormal status data of different dimensions of the power controller; and finally, analyzing the abnormal status data of different dimensions of the power controller based on its real-time status characteristics to determine the abnormal parameters of the power controller.

[0026] To facilitate understanding of how to calculate the degradation trend information of a power controller, the following example is provided. Specifically, the method for calculating the degradation trend information of a power controller includes: Formula 6; In Equation 6, For degradation trend parameters, and These are preset weights, For the health index at the sampling interval The change within, The current health index is used. In this embodiment, Equation 6 combines the current health level and the rate of change of health level to comprehensively consider the overall degradation degree of the power controller. The weights can be calibrated and adjusted according to the actual aging patterns of power controllers for different aircraft seat models, ensuring that the degradation trend parameter accurately reflects the actual degradation progress of the power controller. It should be noted that calculating the degradation trend parameter by combining the current health level and the rate of change of health level using Equation 6 avoids the inability to identify potential risks caused by sudden changes in aging rate when relying solely on a single health level value.

[0027] After identifying a power controller malfunction, a contribution analysis of the characteristic dimensions of the power controller's degradation trend information can be performed to determine the abnormal condition data for different dimensions of the power controller. To facilitate understanding of how to perform the contribution analysis of the characteristic dimensions of the power controller's degradation trend information, the following explanation is provided. Specifically, the method for determining the abnormal condition data for different dimensions of the power controller includes: Formula 7; In Equation 7, The percentage of anomaly contribution for any feature. and These are respectively the first of the multidimensional feature vector information and the mean vector. One portion, The first covariance inverse matrix is ​​the... Line 1 Column elements, Let be the dimension of the feature vector. In this embodiment, the contribution ratio of each feature dimension to the current total anomaly can be calculated using Equation 7. The feature dimension with the highest contribution ratio is the parameter dimension most likely to cause the abnormal fault. Maintenance personnel can directly check the circuit module corresponding to this parameter without having to check each component one by one, which greatly improves maintenance efficiency and shortens the fault handling time.

[0028] In one feasible solution, to accurately predict the lifespan of the power controller and reduce the occurrence of events affecting flight operations due to malfunctions, the method for predicting the health status of the power controller in this invention includes: developing a double exponential smoothing model with an adaptive smoothing coefficient based on the power controller's operating specifications, and performing trend prediction on a time series composed of the health index; then calculating the remaining lifespan of the power controller based on the prediction results and a set functional failure threshold (which can be preset in advance based on the normal operation failure status of the power controller). Specifically, the double exponential smoothing model with an adaptive smoothing coefficient is as follows: Formula 8; Equation 9; The predicted value is: Formula 10; The remaining service life is: Formula 11; In Equations 9 and 10, ; In equations 8 to 11 above, The current health index. For level terms, For trend items, For the future Health prediction value after each sampling interval The set functional failure threshold, The sampling interval is... , The adaptive smoothing coefficient allows for trend prediction based on the time series of the health index. This predicts in advance when the health index will drop to the functional failure threshold, thus determining the remaining lifespan of the power controller. This enables operators to plan replacements in advance, preventing sudden power controller failures during flight operations that could impact passenger experience and reducing disruptions to flight schedules. The adaptive smoothing coefficient automatically adjusts based on recent fluctuations in health index. It increases when health index changes are stable to retain more historical information, and decreases when health index changes are rapid to respond more quickly to trend changes. This improves the accuracy of remaining lifespan prediction, adapting to the prediction needs of power controllers with different aging rates. Ultimately, this enhances the accuracy of remaining lifespan prediction, helping maintenance personnel to develop replacement plans in advance and perform preventative maintenance before the power controller completely fails, avoiding functional failures during flight.

[0029] In a second aspect, the present invention also provides a status detection system for an aircraft seat power controller, employing the status detection method for an aircraft seat power controller described in any one of the first aspects above. The detection system further includes: a parameter acquisition module, a benchmark construction module, a status analysis module, a health assessment module, and a trend prediction module. The parameter acquisition module is used to acquire multiple operating parameters of the power controller in real time. The benchmark construction module is used to determine reference benchmark information for the power controller based on its operating specifications and past operating data. The status analysis module is used to analyze the health index of the power controller. The health assessment module is used to determine the current health status of the power controller by combining health warning information and the health index. The trend prediction module predicts the subsequent health usage of the power controller. In this embodiment, the detection system acquires multi-dimensional operating parameters of the aircraft seat power controller during operation through a parameter acquisition module (including but not limited to: input DC bus voltage deviation rate, output USB terminal voltage deviation rate, output current load rate, normalized internal hot spot temperature value, and output ripple coefficient, any one or more of these). Then, a benchmark construction module constructs a reference benchmark containing a mean vector and a covariance matrix. This allows the state analysis module to calculate the Mahalanobis distance between the real-time feature samples and the reference benchmark, converting it to obtain the current health index. Simultaneously, the reference benchmark information is dynamically and recursively updated to ensure the accuracy of the health calculation. Subsequently, a health judgment module compares the real-time health index with a preset threshold to obtain a health status judgment result. Finally, a trend prediction module, combining the current health status, historical operating load statistics, and rated lifespan specifications, predicts or obtains the remaining healthy service life of the power controller.

[0030] In some implementations, the detection system can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet), and end-to-end networks (e.g., ad hoc end-to-end networks), as well as any currently known or future-developed networks.

[0031] It should be noted that the functions described above in this document can be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that can be used include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), etc.

[0032] In a third aspect, this invention also provides a status detection device for an aircraft seat power controller. The detection device includes a detection end, a storage end, a processing end, and an output end. The detection end is electrically connected to the power supply end of the aircraft seat power controller and is used to collect multiple operating parameter information of the power controller. The storage end is used to store the operating specification information and past operating data of the power controller. The processing end is electrically connected to the detection end and the storage end respectively, and is used to execute a status detection method for an aircraft seat power controller as described in any one of the first aspects. The output end is used to output the health anomaly status and usage prediction results of the power controller. In this embodiment, the detection device directly collects multi-dimensional operating parameters from the power supply circuit and internal monitoring points of the aircraft seat power controller through the detection end. The storage end pre-stores the corresponding model and specification operating parameter standards and the historical detection data of the power controller throughout its entire lifecycle. Then, the processing end performs health calculation, degradation trend analysis, and abnormal parameter location according to the detection method in the first aspect. Finally, the health status determination and remaining life prediction results are displayed to maintenance personnel through the output end, facilitating timely location of degradation dimensions.

[0033] A fourth aspect of the present invention provides a computer-readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements a state detection method for an aircraft seat power controller as described in any one of the first aspects. The computer-readable medium in this embodiment may be written in one or more programming languages ​​or a combination thereof to perform computer program code for carrying out operations of some embodiments of the present disclosure. These programming languages ​​include object-oriented programming languages—such as Java, Smalltalk, and C++—and conventional procedural programming languages—such as the "C" language or similar programming languages. The program code may be executed entirely on a user's computer, partially on a user's computer, as a standalone software package, partially on a user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0034] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0035] In particular, according to some embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts.

[0036] A fifth aspect of the present invention provides an electronic device, comprising: one or more processors; a storage device storing one or more programs thereon; wherein, when the one or more programs are executed by the one or more processors, the one or more processors implement a state detection method for an aircraft seat power controller as described in the first aspect. The computer-readable medium may be included in the electronic device or may exist independently, i.e., not assembled into the electronic device. The computer-readable medium carries one or more programs that, when executed by the electronic device, enable the electronic device to implement the state detection method for an aircraft seat power controller as described in the first aspect.

[0037] The sixth aspect of the present invention provides a computer program product, including a computer program that, when executed by a processor, implements a state detection method for an aircraft seat power controller as described in the first aspect.

[0038] The above description is merely a selection of preferred embodiments of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in the embodiments of this disclosure.

Claims

1. A state detection method for an aircraft seat power controller, characterized in that, include: The operating specifications of the power controller are obtained, and multiple operating parameter information of the power controller is collected in real time to obtain the multi-dimensional feature vector information of the power controller. Based on the power controller's operating specifications, the multi-dimensional feature vector information of the power controller is analyzed in real time to obtain the power controller's real-time status information. Obtain historical operating data from the power controller and formulate health warning information for the power controller; Based on the health warning information of the power controller, the health status information of the power controller is judged to determine the abnormal health status of the power controller. Obtain the power controller's operating information and predict its health status based on its health condition and operating specifications.

2. The method of claim 1, wherein, The method for obtaining real-time status information of the power controller includes: Based on the power controller's operating specifications and its historical operating data, determine the power controller's reference information. Based on the reference information of the power controller, the multi-dimensional feature vector information of the power controller is analyzed in real time to obtain the real-time status characteristics of the power controller. Based on the power controller's operating specifications and historical operating data, the real-time status characteristics of the power controller are mapped to obtain the power controller's health index.

3. A method of detecting a state of a power supply controller for an aircraft seat according to claim 2, characterized in that, The method for obtaining the health index of the power controller includes: Formula 1; Formula 2; In formula 1, Mahalanobis distance of the real-time feature vector sample of the power supply controller and the reference benchmark information, the current real-time feature vector sample of the power supply controller, the mean vector in the reference benchmark information, the covariance inverse matrix, the transpose operation, the difference vector of the current real-time feature vector sample and the mean vector; In formula 2, is a health index, is a scaling factor, is a scale factor, is a sharpening factor.

4. The method of claim 3, wherein the method further comprises: The method for obtaining the real-time status characteristics of the power controller further includes: Based on the real-time status characteristics of the power controller, the inverse covariance matrix in the reference information of the power controller is dynamically and recursively updated. The mean vector and the covariance matrix are updated respectively by the following equations and : Formula 3; Equation 4; Formula 5; In equations 3 to 5 above, The mean forgetting factor, For dynamic covariance forgetting factor, Basic forgetting factor, The standard deviation of the historical Mahalanobis distance. and These are the mean vector and covariance matrix before the update, respectively. This refers to the multidimensional feature vector information.

5. A method of detecting a state of a power supply controller for an aircraft seat according to any one of claims 1 to 4, characterized in that, The method for determining the abnormal health status of the power controller includes: Based on the health warning information of the power controller and combined with the health index of the power controller, calculate the degradation trend information of the power controller. Based on the multidimensional feature vector information of the power controller, the contribution of the feature dimensions of the power controller's degradation trend information is analyzed, and the abnormal condition data of the power controller in different dimensions are determined respectively. Based on the real-time status characteristics of the power controller, the abnormal status data of the power controller in different dimensions are analyzed to determine the abnormal status parameters of the power controller.

6. A method of detecting a state of a power supply controller for an aircraft seat according to claim 5, characterized in that, The method for calculating the degradation trend information of the power controller includes: Formula 6; In Equation 6, For degradation trend parameters, and These are preset weights, For the health index at the sampling interval The change within, This refers to the current health index.

7. A method of detecting the state of a power controller for an aircraft seat according to claim 6, characterized in that, The methods for determining different dimensions of abnormal condition data of the power controller include: Formula 7; In Equation 7, The percentage of anomaly contribution for any feature. and These are respectively the first of the multidimensional feature vector information and the mean vector. One portion, The first covariance inverse matrix is ​​the... Line number Column elements, Let be the dimension of the eigenvectors.

8. The state detection method for an aircraft seat power controller according to claim 1, characterized in that, The multidimensional feature vector information includes at least: The input DC bus voltage deviation rate, output USB terminal voltage deviation rate, output current load rate, normalized internal hot spot temperature, and output ripple coefficient are all selected.

9. A status detection system for an aircraft seat power controller, characterized in that, The state detection method for an aircraft seat power controller according to any one of claims 1 to 8, wherein the detection system further comprises: A parameter acquisition module is used to acquire multiple operating parameters of the power controller in real time. A benchmark construction module is used to determine the reference benchmark information of the power controller based on the power controller's operating specifications and past operating data. A status analysis module is used to analyze the health index of the power controller. A health assessment module is used to determine the current health status of the power controller by combining health warning information and health index. A trend prediction module that predicts the future health of the power controller.

10. A status detection device for an aircraft seat power controller, characterized by, The detection equipment also includes: The detection end is electrically connected to the power supply terminal of the power controller of the aircraft seat, and is used to collect multiple operating parameter information of the power controller; The storage terminal is used to store the power controller's operating specifications and past operating data; The processing end is electrically connected to the detection end and the storage unit respectively, and is used to execute the state detection method for an aircraft seat power controller as described in any one of claims 1 to 8; The output terminal is used to output the prediction results of the power controller's abnormal health status and usage conditions.

Images