Ultrashort wave power amplifier assembly multi-parameter fusion health baseline construction method and device

Abstract

The invention discloses an ultra-short wave power amplifier component multi-parameter fusion health baseline construction method and device, and relates to the technical field of data processing.The method comprises the steps that operation data of multiple sets of power amplifier devices are obtained, each set of operation data is recorded to be generated by the preset flight times, and the flight times are recorded to be the preset flight times; determining an operation principle and a fault mechanism of each group of power amplifier equipment based on each group of operation data, establishing a screening model, determining an input data label and an output data label of the screening model according to the operation principle and the fault mechanism, extracting a target data set from the operation data based on the input data label and the output data label, and performing data processing on the target data set; a timestamp is adopted to align and merge a target data set so as to generate a multi-parameter fusion health baseline of a playback device and construct a data set, factors such as operation characteristics and a time sequence relation can be comprehensively considered, and the influence of coupling characteristics of data on parameter representation of an abnormal mode is analyzed; and accurate detection of faults and accurate evaluation of the equipment health state are realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a method and device for constructing a multi-parameter fusion health baseline of an ultrashort wave power amplifier assembly. BACKGROUND

[0002] An airborne power amplifier device is one of the key core components of an aircraft. Due to external factors such as electromagnetic interference, mechanical vibration, and the like, and due to reasons such as aging of the equipment itself, drift of device indicators, wear and tear, and the like, the airborne power amplifier device can occur abnormal work, which seriously affects the normal execution of the aircraft task.

[0003] In related technologies, the traditional maintenance mode mainly includes two kinds of post-maintenance and planned maintenance. Post-maintenance is a maintenance remedy performed after the occurrence of an electronic device fault, which is a maintenance mode driven by fault events, and has high maintenance cost and is difficult to avoid adverse consequences caused by device abnormal work. Planned maintenance is a regular maintenance and component replacement of electronic devices according to reliability theory, which is a maintenance mode driven by time, and frequent maintenance, disassembly and replacement result in low operation efficiency and high maintenance cost.

[0004] In order to solve the problems of insufficient maintenance of post-maintenance and excessive maintenance of planned maintenance, a condition-based maintenance mode based on equipment state monitoring and taking fault diagnosis algorithm as the core has gradually developed. Therefore, how to provide effective data support for performance monitoring, state evaluation and fault prediction of the equipment is a problem to be solved. SUMMARY

[0005] In view of the above problems, the present application provides a method and device for constructing a multi-parameter fusion health baseline of an ultrashort wave power amplifier assembly, to at least solve the problems existing in related technologies.

[0006] In a first aspect, the present application provides a method for constructing a multi-parameter fusion health baseline of an ultrashort wave power amplifier assembly, which comprises: obtaining a plurality of sets of running data of power amplifier devices, wherein each set of running data is recorded by a predetermined number of flights; determining the running principle and fault mechanism of the power amplifier devices of each set based on each set of running data; establishing a screening model, and determining the input data label and output data label of the screening model according to the running principle and fault mechanism; extracting a target data set from the running data based on the input data label and output data label; aligning and merging the target data set using a timestamp to generate a multi-parameter fusion health baseline of the power amplifier device and construct a data set.

[0007] In some embodiments, the aligning and merging the target data set by using the time stamp comprises: merging the functional record data in the target data set and reading PTT data, obtaining a first time stamp of any of the PTT data; finding a corresponding working mode and wave channel number based on the first time stamp and the PTT data; merging the PTT data, the working mode and the wave channel number.

[0008] In some embodiments, the aligning and merging the target data set by using the time stamp further comprises: determining monitoring data in the target data set and obtaining a second time stamp of the monitoring data; finding any PTT data in a preset time period before the second time stamp and selecting a target PTT data farthest from the second time stamp; merging the monitoring data, the target PTT data and the functional record data.

[0009] In some embodiments, the multi-parameter fusion health baseline construction method of the ultrashort wave power amplifier assembly further comprises: dividing the data set into a test set and a training set, and dividing into a support set and a query set; randomly selecting N categories from all categories in the data set; randomly selecting K samples from the selected category samples to form a support set, and selecting X samples from the remaining samples of the selected category to form a query set, wherein the support set has samples, and the query set has samples.

[0010] In some embodiments, the multi-parameter fusion health baseline construction method of the ultrashort wave power amplifier assembly further comprises: performing feature extraction on each sample in the support set to obtain the encoding of each sample; summing and averaging the encodings of all samples under each category in the support set to obtain a prototype representation of each label category; when a data sample is input, using the encoding of the data sample to generate a corresponding encoding representation; calculating the distance between the encoding representation of the new data sample and each category prototype representation based on the Euclidean distance; converting the distance into a probability based on an activation function to determine the probability that the data sample belongs to the corresponding output label, and calculating the category with the highest output probability.

[0011] In some embodiments, the method for constructing a multi-parameter fusion health baseline of the ultra-short wave power amplifier assembly further comprises: The normal range of the power values of different working modes and wave channels in the data set is determined by using a quantile-based statistical method.

[0012] In some embodiments, the method for determining the normal range of the power values of different working modes and wave channels in the data set by using the quantile-based statistical method comprises: reading the related parameters in the data set; grouping the related parameters according to the working modes and wave channel numbers, and cyclically calculating the quantiles of the power values corresponding to each group of related parameters; determining the upper and lower bounds of the quantiles, and constructing the power value health baseline of each group of data based on the relationship between the input samples and the output labels to determine the normal range of the power values of different working modes and wave channels.

[0013] In a second aspect, the embodiments of the present application provide a device for constructing a multi-parameter fusion health baseline of an ultra-short wave power amplifier assembly, comprising: an acquisition module configured to acquire running data of a plurality of groups of power amplifier devices, wherein each group of running data is recorded by a preset number of flights; a determination module configured to determine the running principles and failure mechanisms of the power amplifier devices in each group based on the running data of each group; a screening module configured to establish a screening model, and determine input data labels and output data labels of the screening model according to the running principles and failure mechanisms; an extraction module configured to extract a target data set from the running data based on the input data labels and the output data labels; a generation module configured to align and merge the target data set by using timestamps to generate a multi-parameter fusion health baseline of the power amplifier devices and construct a data set.

[0014] The method and device for constructing a multi-parameter fusion health baseline of an ultra-short wave power amplifier assembly provided by the embodiments of the present application can comprehensively consider factors such as running characteristics and time sequence relationships, analyze the influence of the coupling characteristics of data on the parameter representation of abnormal modes, and accurately detect faults and accurately evaluate the health status of devices.

[0015] It should be understood that the matters described in this section are not intended to identify key or essential features of embodiments of the application, nor is it intended to limit the scope of the application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0016] The application will be described in more detail in the following based on embodiments and with reference to the drawings.

[0017] Figure 1 A flowchart of a multi-parameter fusion health baseline construction method of an ultrashort wave power amplifier assembly is shown in an embodiment of the application. Figure 2 A schematic diagram of an exemplary multi-parameter fusion health baseline construction is shown in an embodiment of the application. Figure 3 A schematic diagram of a training flow of an exemplary multi-parameter fusion health baseline construction method of an ultrashort wave power amplifier assembly is shown in an embodiment of the application. Figure 4 A schematic diagram of support set and query set division is shown in an embodiment of the application. Figure 5 A structural block diagram of a multi-parameter fusion health baseline construction device of an ultrashort wave power amplifier assembly is shown in an embodiment of the application. DETAILED DESCRIPTION

[0018] In order to make the objectives, technical solutions and advantages of the application clearer, further detailed description will be made to the application in combination with embodiments and drawings, and the exemplary embodiments and their descriptions are only used to explain the application and do not limit the application.

[0019] In order to solve the problems of insufficient maintenance of after-service and excessive maintenance of planned maintenance, a condition-based maintenance mode based on equipment state monitoring and taking fault diagnosis algorithm as the core has gradually developed. The key problem of the condition-based maintenance mode is how to construct a health assessment model according to equipment state measurement data, and the construction of a health baseline plays a crucial role in state assessment. The establishment of a multi-parameter fusion health baseline in the application can provide a benchmark model based on historical data, equipment specifications and operating conditions for abnormal detection and health assessment, and provides effective data support for subsequent performance monitoring, state assessment and fault prediction.

[0020] In response to the above problems, the applicant proposed a method and device for constructing a multi-parameter fusion health baseline for ultra-short wave power amplifier components. The method for constructing a multi-parameter fusion health baseline for ultra-short wave power amplifier components comprehensively considers factors such as the system operation characteristics and timing relationships related to ultra-short wave power amplifier components, analyzes the influence of the coupling characteristics of the system operation monitoring data on the parameter characterization of the abnormal mode, and constructs anomaly detection data sets and health assessment data sets for electronic equipment based on different types of parameters such as power amplifier device status, control parameters, temperature, power value, module monitoring results, etc. By using a small sample learning method, it can fully learn an effective classification model under the condition of a small number of fault samples, thereby realizing accurate detection of faults and accurate assessment of the health status of equipment.

[0021] Among them, the method for constructing a multi-parameter fusion health baseline of an ultrashort wave power amplifier component is described in detail in subsequent embodiments.

[0022] The following describes the application scenarios of the method for constructing a multi-parameter fusion health baseline for an ultrashort wave power amplifier component provided by an embodiment of the present invention: See also Figure 1 , Figure 1 This is a flow chart of a method for constructing a multi-parameter fusion health baseline for an ultrashort wave power amplifier component provided in an embodiment of the present invention. In this embodiment, the method for constructing a multi-parameter fusion health baseline for an ultrashort wave power amplifier component can be applied to Figure 5 The ultrashort wave power amplifier assembly multi-parameter fusion health baseline construction device 300 is shown. Figure 1 The process shown is described in detail. The method for constructing a multi-parameter fusion health baseline of an ultrashort wave power amplifier component may include S110 to S150.

[0023] S110: Acquire multiple sets of operating data of power amplifier devices, wherein each set of operating data is recorded as being generated by a preset number of flights.

[0024] In an embodiment of the present application, multiple groups of operating data of power amplifier devices are collected, where each group of operating data files is the operating data of the power amplifier devices generated during one flight.

[0025] S120: Determine the operating principle and failure mechanism of the power amplifier equipment in each group based on each group of operating data.

[0026] S130: Establish a screening model, and determine the input data label and output data label of the screening model according to the operating principle and failure mechanism.

[0027] In the embodiments of the present application, for each set of operation data, the input is confirmed according to the operation principle and failure mechanism of the power amplifier type device, which can include: power amplifier temperature, power indication, power measured value, standing wave state, PTT effective bit and wave channel number. The output label can include "normal", "standing wave failure", "power indication failure", "input excitation failure" and "false alarm", etc. S140: extracting a target data set from the operation data based on the input data label and the output data label.

[0028] In the embodiments of the present application, the required data can be extracted from the original data of the airborne power amplifier type device, and then the data is cleaned to filter out incomplete data, as shown in Figure 2 The data can be extracted according to the demand analysis from the original data, and the data can be cleaned.

[0029] S150: aligning and merging the target data set by using the time stamp to generate a multi-parameter fusion health baseline of the power amplifier type device and construct a data set.

[0030] In some embodiments, S150 includes S151 to S153.

[0031] S151: merging the function record data in the target data set and reading the PTT data to obtain the first time stamp of any one PTT data.

[0032] S152: finding the corresponding working mode and wave channel number based on the first time stamp and the PTT data.

[0033] S153: merging the PTT data, the working mode and the wave channel number.

[0034] In the embodiments of the present application, according to the system operation principle, the time sequence relationship between the data is followed, the time stamp is used to align and merge the module monitoring parameters and the function use parameters, and a complete data is combined. Specifically, the function record data is first merged, the PTT data is read line by line, the time stamp of one PTT data is obtained, and then the corresponding working mode and wave channel number are found. (The time stamp of the wave channel number working mode is before the PTT data and is closest to the time stamp of the PTT), and the PTT data is merged with the wave channel number and the working mode data.

[0035] In some embodiments, S150 further includes S154 to S156.

[0036] S154: determining the monitoring data in the target data set and obtaining the second time stamp of the monitoring data.

[0037] S155: find any PTT data before the preset time period of the second timestamp, and select the target PTT data farthest from the second timestamp.

[0038] S156: data merging of the monitoring data, the target PTT data and the function record data.

[0039] In the embodiment of the application, the row-by-row acquisition module monitors the data to obtain the timestamp of the module monitoring data, then finds a PTT within 6 seconds before the timestamp (the PTT effective time is 4-6 seconds), and selects the PTT farthest from the module monitoring data timestamp, and then merges the module monitoring data and the function record data. Repeat this operation until all data merging of this group is completed.

[0040] Repeat steps S151-S156 to complete the collection, processing and data merging of multiple groups of running data, and form a health baseline construction data set of the power amplifier device multi-parameter fusion.

[0041] In some embodiments, data set division is performed.

[0042] Referring to Figure 1 and Figure 4 , the merged data set can be divided into a test set and a training set, which needs to be divided into a support set and a query set.

[0043] First, for all categories, randomly select categories.

[0044] In the selected category samples, randomly select samples to form a support set, wherein there are samples.

[0045] Then, in the remaining samples of the selected category, select samples to form a query set, wherein there are samples.

[0046] In some embodiments, the prototype network is constructed.

[0047] The multi-parameter fusion health baseline construction method of the ultrashort wave power amplifier assembly further comprises: perform feature extraction on each sample in the support set to obtain the encoding of each sample; sum all the encodings of the samples under each category in the support set and take the average value as the prototype representation of each label category; When a data sample is input, use the encoding of the data sample to generate a corresponding encoding representation; based on the Euclidean distance, calculate the distance between the encoding representation of the new data sample and each category prototype representation. The distance is converted into probability based on an activation function to determine the probability that the data sample belongs to the corresponding output label, and the class with the highest output probability is calculated.

[0048] In the specific implementation, the method comprises the following steps: First, for each support set containing n classes of data, the encoding of each sample is used Feature extraction is performed on the sample to obtain the encoding representation of each sample as follows:

[0049] Among them, is a query sample, and the number of samples in each class can be different, for example, the first class query sample can be represented as ( ), is a sample label, and is a feature extraction network, which is used to obtain the feature encoding of the query sample .

[0050] After obtaining the encoding representation of each sample, the sum of the encoding of all samples under each classification is calculated, and the result is taken as the prototype vector of each label classification.

[0051] The distance between the encoding representation of the new sample and the prototype representation of each classification is calculated based on the Euclidean distance, and finally the distance is converted into the form of probability by the Softmax activation function, representing the probability that the data sample belongs to the corresponding output label. The class with the highest output probability, the expression is:

[0052] Among them, is the probability that the query sample belongs to the first class label, is the prototype vector of the first class label, is a feature extraction network, is a distance measurement function, is an exponential function.

[0053] In some embodiments, the method for constructing a multi-parameter fusion health baseline of an ultrashort wave power amplifier assembly further comprises: A statistical method based on quantiles is used to determine the normal range of power values in different working modes and wave channels in the data set, specifically including: Reading related parameters in the data set; ​According to the working mode and the channel number, the related parameters are grouped, and the quantile of the power value corresponding to each group of related parameters is calculated in a loop; The upper and lower bounds of the quantile are determined, and the power value health baseline of each group of data is constructed based on the relationship between the input sample and the output label to determine the normal range of the power value of different working modes and channels.

[0054] In the specific embodiment, referring to Figure 3 As shown in the figure, by reading the mode, channel, power value measured value and power control value of the data set, then grouping the data according to the mode and channel, and finally calculating the 2.5% quantile of the power value of each group of data as the lower bound and the 97.5% quantile as the upper bound, combined with the relationship between the input sample and the output label generated in step 4, the power value health baseline of each group of data is constructed, and the dynamic health baseline of the power amplifier is finally formed and saved.

[0055] In some embodiments, the data in each packet can be sorted by timestamp, and the data with incorrect timestamp due to unsynchronized system time at power-on can be deleted.

[0056] In summary, the present application considers the system running characteristics, timing relationship and other factors, analyzes the influence of the coupling characteristics of the system running monitoring data on the parameter representation of the abnormal mode, and constructs the electronic equipment abnormal detection data set and the health evaluation data set according to different types of parameters such as the state of the power amplifier, the control parameter, the temperature, the power value and the module monitoring result. Under the condition of a small amount of fault samples, an effective classification model can be learned, accurate detection of faults and accurate evaluation of the health state of the equipment are realized, and effective data support is provided for performance monitoring, state evaluation and fault prediction.

[0057] Please refer to Figure 5 , Figure 5 A structure block diagram of a multi-parameter fusion health baseline construction device for an ultrashort wave power amplifier assembly provided by the present application, comprising: an acquisition module 310, a determination module 320, a screening module 330, an extraction module 340 and a generation module 350, wherein: The acquisition module 310 is used for acquiring running data of multiple groups of power amplifier devices, wherein each group of running data records is generated by a preset flight number.

[0058] The determination module 320 is used for determining the running principle and fault mechanism of the power amplifier device of each group based on each group of running data.

[0059] The screening module 330 is used for establishing a screening model, and determining the input data label and output data label of the screening model according to the running principle and fault mechanism.

[0060] The extraction module 340 is configured to extract the target data set from the running data based on the input data label and the output data label.

[0061] The generation module 350 is configured to align and merge the target data set by using the time stamp to generate the multi-parameter fusion health baseline of the ultra-short wave power amplifier assembly and construct the data set.

[0062] It should be noted that the device embodiments in the present application correspond to the foregoing method embodiments, and the specific principles of the device embodiments can be referred to the content in the foregoing method embodiments, which will not be described here.

[0063] In several embodiments provided in the present embodiment, the coupling between the modules can be electrical, mechanical or other forms of coupling.

[0064] In addition, each functional module in each embodiment of the present application can be integrated in one processing module, or each module can exist physically, or two or more modules can be integrated in one module. The integrated module can be realized in the form of hardware or in the form of a software functional module.

[0065] The present application also provides an electronic device that can execute the above-mentioned ultra-short wave power amplifier assembly multi-parameter fusion health baseline construction method. The electronic device can be a communication device, a mobile phone, a computer or a portable computer, etc.

[0066] The electronic device further includes a processor and a memory. The memory stores a program that can execute the content in the foregoing embodiments, and the processor can execute the program stored in the memory.

[0067] The present application also provides a computer readable storage medium. The computer readable storage medium stores program codes, and the program codes can be called by a processor to execute the method described in the foregoing method embodiments.

[0068] The present application further provides a computer program product or a computer program. The computer program product or the computer program includes computer instructions stored in a computer readable storage medium. A processor of a computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions to make the computer device execute the ultra-short wave power amplifier assembly multi-parameter fusion health baseline construction method described in the various optional implementation manners.

[0069] The above examples are only used to illustrate the technical solutions of the present application, and are not intended to limit the present application; although the present application has been described in detail with reference to the foregoing examples, those skilled in the art will understand that the technical solutions recorded in the foregoing examples can be modified, or some technical features can be replaced by equivalent features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for constructing a multi-parameter fusion health baseline for an ultrashort wave power amplifier component, characterized in that: The method for constructing a multi-parameter fusion health baseline of an ultrashort wave power amplifier component includes: Acquire multiple sets of operating data of power amplifier devices, wherein each set of operating data is recorded as being generated by a preset number of flights; Determine the operating principle and failure mechanism of each group of power amplifier equipment based on each group of operating data; Establishing a screening model, and determining input data labels and output data labels of the screening model according to the operating principle and failure mechanism; extracting a target data set from the operational data based on the input data labels and the output data labels; The target data set is aligned and merged using timestamps to generate a multi-parameter fusion health baseline for the power amplifier device and construct a data set.

2. The method for constructing a multi-parameter fusion health baseline for an ultrashort wave power amplifier component according to claim 1, characterized in that: The aligning and merging the target data sets using timestamps includes: Merging the function record data in the target data set and reading the PTT data to obtain a first timestamp of any piece of the PTT data; Finding a corresponding working mode and channel number based on the first timestamp and PTT data; The PTT data, working mode and channel number are combined.

3. The method for constructing a multi-parameter fusion health baseline for an ultrashort wave power amplifier component according to claim 2, characterized in that: The aligning and merging the target data sets using timestamps further includes: Determining monitoring data in the target data set, and obtaining a second timestamp of the monitoring data; Searching for any PTT data within a preset time period before the second timestamp, and selecting the target PTT data farthest from the second timestamp; The monitoring data, the target PTT data and the functional recording data are merged.

4. The method for constructing a multi-parameter fusion health baseline for an ultrashort wave power amplifier assembly according to claim 1, characterized in that: The method for constructing a multi-parameter fusion health baseline of an ultrashort wave power amplifier component further includes: Dividing the dataset into a test set and a training set, and further into a support set and a query set; For all categories in the data set, randomly select N categories; According to the selected category samples, K samples are randomly selected to form the support set, and X samples are selected from the remaining samples of the selected category to form the query set, where the support set has samples, and the query set has samples.

5. The method for constructing a multi-parameter fusion health baseline for an ultrashort wave power amplifier assembly according to claim 4, characterized in that: The method for constructing a multi-parameter fusion health baseline of an ultrashort wave power amplifier component further includes: Performing feature extraction on each sample in the support set to obtain a code for each sample; Sum and average the encodings of all samples under each category in the support set to serve as the prototype representation of each label category; When a data sample is input, encoding is applied to the data sample to generate a corresponding encoded representation; Calculate the distance between the encoding representation of the new data sample and each classification prototype representation based on the Euclidean distance; The distance is converted into probability based on the activation function to determine the probability that the data sample belongs to the corresponding output label, and the category with the highest output probability is calculated.

6. The method for constructing a multi-parameter fusion health baseline for an ultrashort wave power amplifier assembly according to claim 2, characterized in that: The method for constructing a multi-parameter fusion health baseline of an ultrashort wave power amplifier component further includes: The quantile-based statistical method is used to determine the normal range of power values ​​for different operating modes and channels in the data set.

7. The method for constructing a multi-parameter fusion health baseline for an ultrashort wave power amplifier assembly according to claim 6, characterized in that: The quantile-based statistical method is used to determine the normal range of power values ​​for different operating modes and channels in the data set, including: Read relevant parameters in the data set; Group the relevant parameters according to the working mode and channel number, and cyclically calculate the quantile of the power value corresponding to each group of relevant parameters; The upper and lower bounds of the quantiles are determined, and a healthy baseline of the power value of each set of data is constructed based on the relationship between the input samples and the output labels to determine the normal range of power values ​​in different working modes and channels.

8. A device for constructing a multi-parameter fusion health baseline for an ultrashort wave power amplifier component, characterized in that: The device comprises: An acquisition module is used to acquire operating data of multiple groups of power amplifier devices, wherein each group of operating data is recorded as being generated by a preset number of flights; A determination module, configured to determine the operating principle and failure mechanism of each group of power amplifier devices based on each group of operating data; A screening module, configured to establish a screening model and determine input data labels and output data labels of the screening model according to the operating principle and failure mechanism; an extraction module, configured to extract a target data set from the operation data based on the input data label and the output data label; A generation module is used to align and merge the target data set using a timestamp to generate a multi-parameter fusion health baseline of the power amplifier device and construct a data set.

9. An electronic device, characterized in that: The electronic device includes a memory and a processor, wherein the memory stores a program code that can be run on the processor. When the program code is executed by the processor, the method for constructing a multi-parameter fusion health baseline of an ultrashort wave power amplifier component according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores program code, and the program code can be called by one or more processors to execute the method for constructing a multi-parameter fusion health baseline of an ultrashort wave power amplifier component according to any one of claims 1 to 7.

Images