Weather radar health degree calculation method and device, equipment and storage medium

Abstract

The embodiment of the invention provides a weather radar health degree calculation method and device, equipment and a storage medium, and is applied to the technical field of radars. The method comprises the following steps: acquiring XML state data and alarm code data of the weather radar; calculating data characteristics according to the XML state data, and calculating key alarm code frequency characteristics according to the alarm code data; the parameter health degree and the state health degree of the subsystem are calculated according to the data features, and the alarm health degree of the subsystem is calculated according to the key alarm code frequency features; and on the basis of a preset radar health degree calculation formula, the weather radar health degree is calculated according to the parameter health degree and the state health degree of the subsystem and the alarm health degree of the subsystem. In this way, the method for constructing the layered health degree of the weather radar can be provided from three dimensions of parameter interval analysis, state analysis and alarm analysis, the method breaks through the limitation of a traditional single threshold value or data driving model, and the robustness and interpretability of the health degree are remarkably improved.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of data processing, in particular to the technical field of radar, and specifically to a weather radar health degree calculation method and device, equipment and a storage medium. BACKGROUND

[0002] CINRAD (Cooperative Instrumentation Network for Regional and Mesoscale Applications) is a radar system for regional and mesoscale meteorological observation, mainly used for monitoring precipitation, wind field and weather conditions. At present, the intelligent operation and maintenance of the new generation of CINRAD weather radar faces the technical bottleneck of health state quantitative evaluation. Its technology mainly relies on a fixed threshold alarm mechanism, which is difficult to distinguish between environmental interference and real degradation signals, resulting in a high false alarm rate. At the same time, based on the strong coupling of multiple source monitoring parameters of the radar system, such as transmitter power, filtering power, and receiving channel noise coefficient, the current single parameter analysis method is easily disturbed by redundant data, and cannot extract key degradation features. In addition, the gradual degradation and sudden failure superposition effect of the health state of the radar system need to be combined with time sequence dynamic modeling and physical failure mechanism, which increases the technical difficulty of health state recognition and characterization of the weather radar. SUMMARY

[0003] The present disclosure provides a weather radar health degree calculation method, device, equipment and a storage medium.

[0004] According to a first aspect of the present disclosure, a weather radar health degree calculation method is provided. The method comprises:

[0005] Obtaining XML state data and alarm code data of a weather radar; the subsystem corresponding to the XML state data is a transmitter and a receiver, and the subsystem corresponding to the alarm code data is a transmitter, a receiver, an antenna and other systems;

[0006] According to the XML state data, data features are calculated, and according to the alarm code data, key alarm code frequency features are calculated;

[0007] According to the data features, parameter health degrees and state health degrees of the subsystems are calculated, and according to the key alarm code frequency features, alarm health degrees of the subsystems are calculated;

[0008] Based on a preset radar health degree calculation formula, according to the parameter health degrees and the state health degrees of the subsystems and the alarm health degrees of the subsystems, a weather radar health degree is calculated.

[0009] Aspects and any possible implementation thereof as described above, further provide an implementation, wherein the data features comprise transmitter data features and receiver data features; and the critical alarm code frequency features comprise transmitter critical alarm code frequency features, receiver critical alarm code frequency features, antenna critical alarm code frequency features, and other system critical alarm code frequency features.

[0010] wherein the transmitter data features comprise transmitter temperature, horizontal channel phase noise, vertical channel phase noise, horizontal channel pre-and post-filter power difference, vertical channel pre-and post-filter power difference, transmitter peak power, horizontal channel antenna peak power, and vertical channel antenna peak power; and the receiver data features comprise short burst noise level, long burst noise level, current vertical channel noise level, current horizontal channel noise level, horizontal channel noise temperature coefficient, short burst system calibration constant variation, long burst system calibration constant variation, reflectivity expected value and measured value difference 1, reflectivity expected value and measured value difference 2, reflectivity expected value and measured value difference 3, reflectivity expected value and measured value difference 4, velocity expected value and measured value difference 1, velocity expected value and measured value difference 2, velocity expected value and measured value difference 3, velocity expected value and measured value difference 4, spectral width expected value and measured value difference 1, spectral width expected value and measured value difference 2, spectral width expected value and measured value difference 3, spectral width expected value and measured value difference 4, ZDR calibration value, and system calibration constant variation.

[0011] Aspects and any possible implementation thereof as described above, further provide an implementation, wherein the calculating the parameter health and state health of the sub-systems according to the data features comprises:

[0012] calculating the parameter health of the transmitter and the receiver respectively according to the transmitter data features and the receiver data features based on parameter interval analysis;

[0013] calculating the state health of the transmitter and the receiver respectively according to the transmitter data features and the receiver data features based on time series network model bias analysis.

[0014] Aspects and any possible implementation thereof as described above, further provide an implementation, wherein the calculating the alarm health of the sub-systems according to the critical alarm code frequency features comprises:

[0015] calculating the alarm health of the transmitter, the receiver, the antenna, and other systems respectively according to the transmitter critical alarm code frequency features, the receiver critical alarm code frequency features, the antenna critical alarm code frequency features, and other system critical alarm code frequency features based on alarm code frequency analysis.

[0016] According to any possible implementation of the aspect as described above, further provided is an implementation, wherein the calculating the weather radar health degree based on the preset radar health degree calculation formula comprises:

[0017] calculating the transmitter health degree according to the transmitter parameter health degree, the transmitter state health degree and the transmitter alarm health degree, calculating the receiver health degree according to the receiver parameter health degree, the receiver state health degree and the receiver alarm health degree, calculating the antenna health degree according to the antenna alarm health degree, and calculating the other system health degree according to the other system alarm health degree;

[0018] calculating the weather radar health degree according to the transmitter health degree, the receiver health degree, the antenna health degree and the other system health degree based on the preset radar health degree calculation formula.

[0019] According to any possible implementation of the aspect as described above, further provided is an implementation, wherein the preset radar health degree calculation formula comprises:

[0020]

[0021] wherein, h 总 represents the total health degree, h n represents the sub health degree, h 总 is obtained by weighting the mean value and the minimum value of the sub health degree.

[0022] According to any possible implementation of the aspect as described above, further provided is an implementation, wherein the XML state data comprises the time of the sub system, the transmitter temperature, the horizontal channel phase noise, the vertical channel phase noise, the horizontal channel power before filtering, the horizontal channel power after filtering, the vertical channel power before filtering, the vertical channel power after filtering, the transmitter peak power, the horizontal channel antenna peak power, the vertical channel antenna peak power, the short pulse noise level, the current vertical channel noise level, the current horizontal channel noise level, the horizontal channel noise coefficient, the short pulse system calibration constant, the long pulse system calibration constant, the reflectivity expected value 1, the reflectivity expected value 2, the reflectivity expected value 3, the reflectivity expected value 4, the reflectivity measurement value 1, the reflectivity measurement value 2, the reflectivity measurement value 3, the reflectivity measurement value 4, the velocity expected value 1, the velocity expected value 2, the velocity expected value 3, the velocity expected value 4, the velocity measurement value 1, the velocity measurement value 2, the velocity measurement value 3, the velocity measurement value 4, the spectrum expected value 1, the spectrum expected value 2, the spectrum expected value 3, the spectrum expected value 4, the spectrum measurement value 1, the spectrum measurement value 2, the spectrum measurement value 3, the spectrum measurement value 4, the ZDR calibration value and the system calibration constant change; and the alarm code data comprises the alarm time of the sub system, the alarm code and the alarm meaning.

[0023] According to a second aspect of the present disclosure, a weather radar health degree calculation apparatus is provided. The apparatus comprises:

[0024] an acquisition module configured to acquire XML state data and alarm code data of the weather radar, wherein the XML state data corresponds to subsystems of a transmitter and a receiver, and the alarm code data corresponds to subsystems of the transmitter, the receiver, an antenna, and other systems;

[0025] a calculation module configured to calculate data features according to the XML state data, and calculate key alarm code frequency features according to the alarm code data;

[0026] the calculation module is further configured to calculate parameter health degrees and state health degrees of the subsystems according to the data features, and calculate alarm health degrees of the subsystems according to the key alarm code frequency features;

[0027] the calculation module is further configured to calculate a weather radar health degree based on a preset radar health degree calculation formula, according to the parameter health degrees and the state health degrees of the subsystems and the alarm health degrees of the subsystems.

[0028] According to a third aspect of the present disclosure, an electronic device is provided. The electronic device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the method as described above when executing the program.

[0029] According to a fourth aspect of the present disclosure, a computer readable storage medium is provided, which stores a computer program, and the program is executed by a processor to implement the method as described above.

[0030] The weather radar health degree calculation method provided in the embodiments of the present application can obtain XML state data and alarm code data of the weather radar, the subsystem corresponding to the XML state data is the transmitter and the receiver, the subsystem corresponding to the alarm code data is the transmitter, the receiver, the antenna and other systems, key parameters are screened through expert experience, data of the parameters of each subsystem and the alarm code are combined, and the limitation of a single threshold or a data driven model is broken through; then, data characteristics are calculated according to the XML state data, key alarm code frequency characteristics are calculated according to the alarm code data, the data are processed in characteristics, the single parameter analysis method is broken out of the trouble of being easily disturbed by redundant data, and thus key degradation characteristics are extracted, that is, the data dimensions required for calculating the health degree are constructed; then, the parameter health degree and the state health degree of the subsystem are calculated according to the data characteristics, the alarm health degree of the subsystem is calculated according to the key alarm code frequency characteristics, and thus the health degree calculation in multiple dimensions is performed from three dimensions of parameter interval analysis, state analysis and alarm analysis, and the hierarchical health degree construction of the weather radar is performed; then, the health degree of the weather radar is calculated according to the parameter health degree and the state health degree of the subsystem and the alarm health degree of the subsystem based on a preset radar health degree calculation formula, and thus the calculation of the health degree of each subsystem and the health degree of the weather radar is realized; based on this, a weather radar health degree modeling method based on experience data fusion can be proposed, key parameters are screened through expert experience, the hierarchical health degree construction method of the weather radar is proposed from the three dimensions of parameter interval analysis, state analysis and alarm analysis, the method breaks through the limitation of the traditional single threshold or data driven model, and the robustness and the explainability of the health degree are significantly improved.

[0031] It should be understood that the content described in the summary section is not intended to limit or define key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become apparent through the following description. BRIEF DESCRIPTION OF DRAWINGS

[0032] The above and other features, advantages, and aspects of embodiments of the present disclosure will become more apparent by describing in detail the following embodiments with reference to the attached drawings. The drawings are intended to better understand the present scheme and do not limit the present disclosure. In the drawings, the same or similar reference numerals refer to the same or similar elements, in which:

[0033] Figure 1 A flowchart of a weather radar health degree calculation method according to an embodiment of the present disclosure is shown;

[0034] Figure 2 A schematic diagram of a time sequence network structure according to an embodiment of the present disclosure is shown;

[0035] Figure 3 A schematic diagram of a weather radar health degree calculation process according to an embodiment of the present disclosure is shown;

[0036] Figure 4 A flowchart illustrating weather radar health degree calculation according to an embodiment of the present disclosure is shown.

[0037] Figure 5 A block diagram illustrating a weather radar health degree calculation device according to an embodiment of the present disclosure is shown.

[0038] Figure 6 A block diagram illustrating an exemplary electronic device capable of implementing an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0039] In order to make the objects, technical solutions and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be described clearly and completely below with reference to the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are some but not all of the embodiments of the present disclosure. Based on the embodiments in the present disclosure, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present disclosure.

[0040] In addition, the term “and / or” herein is only to describe the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can represent the three cases of A alone, A and B together, and B alone. In addition, the character “ / ” herein generally represents an “or” relationship between the front and rear associated objects.

[0041] In the present disclosure, a weather radar health degree modeling method based on experience data fusion can be proposed. By screening key parameters based on expert experience, a weather radar hierarchical health degree construction method is proposed from three dimensions of parameter interval analysis, state analysis and alarm analysis. This method breaks through the limitations of traditional single threshold or data-driven model, and significantly improves the robustness and interpretability of health degree.

[0042] Figure 1 A flowchart illustrating a weather radar health degree calculation method 100 according to an embodiment of the present disclosure is shown.

[0043] In block 110, XML state data and alarm code data of the weather radar are obtained. The subsystem corresponding to the XML state data is the transmitter and the receiver, and the subsystem corresponding to the alarm code data is the transmitter, the receiver, the antenna and other systems.

[0044] In some embodiments, the XML state data and the alarm code data of the weather radar can be obtained by data acquisition on the standard control output device.

[0045] In some embodiments, the sampling frequency of the XML state data can be set to 1 minute to 10 minutes.

[0046] In some embodiments, the XML state data includes, but is not limited to, time, transmitter temperature, horizontal channel phase noise, vertical channel phase noise, horizontal channel power before filtering, horizontal channel power after filtering, vertical channel power before filtering, vertical channel power after filtering, transmitter peak power, horizontal channel antenna peak power, vertical channel antenna peak power, short pulse noise level, current vertical channel noise level, current horizontal channel noise level, horizontal channel noise figure, short pulse system calibration constant, long pulse system calibration constant, reflectivity expected value 1, reflectivity expected value 2, reflectivity expected value 3, reflectivity expected value 4, reflectivity measured value 1, reflectivity measured value 2, reflectivity measured value 3, reflectivity measured value 4, velocity expected value 1, velocity expected value 2, velocity expected value 3, velocity expected value 4, velocity measured value 1, velocity measured value 2, velocity measured value 3, velocity measured value 4, spectral width expected value 1, spectral width expected value 2, spectral width expected value 3, spectral width expected value 4, spectral width measured value 1, spectral width measured value 2, spectral width measured value 3, spectral width measured value 4, ZDR calibration value, and system calibration constant change. The alarm code data includes alarm time, alarm code, and alarm meaning of each subsystem. The alarm code data can be data including time, alarm code, and alarm meaning collected when the weather radar control system generates an alarm.

[0047] In some embodiments, the XML state data and the alarm code data of the weather radar can be key data selected based on expert experience.

[0048] In block 120, data features are calculated according to the XML state data, and key alarm code frequency features are calculated according to the alarm code data.

[0049] In some embodiments, for the XML state data, data features can be calculated by calculating empirical features and numerical features of parameters. For the alarm code data, key alarm code frequency features can be directly calculated.

[0050] In some embodiments, the data features include transmitter data features and receiver data features, and the key alarm code frequency features include transmitter key alarm code frequency features, receiver key alarm code frequency features, antenna key alarm code frequency features, and other system key alarm code frequency features.

[0051] wherein the transmitter data features include transmitter temperature, horizontal channel phase noise, vertical channel phase noise, horizontal channel pre-and post-filter power difference, vertical channel pre-and post-filter power difference, transmitter peak power, horizontal channel antenna peak power, and vertical channel antenna peak power; and the receiver data features include short pulse noise level, long pulse noise level, current vertical channel noise level, current horizontal channel noise level, horizontal channel noise temperature coefficient, short pulse system calibration constant variation, long pulse system calibration constant variation, reflectivity expected value and measured value difference 1, reflectivity expected value and measured value difference 2, reflectivity expected value and measured value difference 3, reflectivity expected value and measured value difference 4, velocity expected value and measured value difference 1, velocity expected value and measured value difference 2, velocity expected value and measured value difference 3, velocity expected value and measured value difference 4, spectral width expected value and measured value difference 1, spectral width expected value and measured value difference 2, spectral width expected value and measured value difference 3, spectral width expected value and measured value difference 4, ZDR calibration value, and system calibration constant variation.

[0052] In some embodiments, the calculation of the data features is as follows:

[0053] The experience features are calculated according to business experience rules, and the specific calculation of the related business features is as follows:

[0054] Horizontal channel pre-and post-filter power difference = horizontal channel post-filter power - horizontal channel pre-filter power;

[0055] Vertical channel pre-and post-filter power difference = vertical channel post-filter power - vertical channel pre-filter power;

[0056] Short pulse system calibration constant variation = short pulse system calibration constant maximum - short pulse system calibration constant minimum;

[0057] Long pulse system calibration constant variation = long pulse system calibration constant maximum - long pulse system calibration constant minimum;

[0058] Reflectivity expected value and measured value difference i = reflectivity measured value i - reflectivity expected value i, i = 1, 2, 3, 4;

[0059] Velocity expected value and measured value difference i = velocity measured value i - velocity expected value i, i = 1, 2, 3, 4;

[0060] Spectral width expected value and measured value difference i = spectral width measured value i - spectral width expected value i, i = 1, 2, 3, 4;

[0061] The numerical features are the average values of each parameter in the XML state data every 6 minutes;

[0062] The obtained data features are X = {x1, x2,..., xn}, n = 29, x i are empirical characteristic parameters and numerical characteristic parameters, and the correspondence between all data characteristics and subsystems is shown in Table 1.

[0063] Table 1: Correspondence between all data characteristics and subsystems

[0064]

[0065]

[0066] In some embodiments, the calculation of the critical alarm code frequency characteristic is as follows:

[0067] The critical alarm code frequency characteristic is the frequency of occurrence of critical alarm codes related to each subsystem;

[0068] The critical alarm code frequency characteristic is S = {s 发射机 , s 接收机 , s 天线 , s 其他系统}, s is the ratio of the number of occurrences of critical alarm codes in the subsystem in 24 hours to the total number of alarm codes in 24 hours, and the correspondence between all critical alarm code frequency characteristics and subsystems is shown in Table 2.

[0069] Table 2: Correspondence between all critical alarm code frequency characteristics and subsystems

[0070]

[0071] In block 130, the parameter health degree and state health degree of the subsystem are calculated according to the data characteristics, and the alarm health degree of the subsystem is calculated according to the critical alarm code frequency characteristic.

[0072] In some embodiments, the calculation of the parameter health degree and state health degree of the subsystem according to the data characteristics specifically includes:

[0073] Based on parameter interval analysis, the parameter health degree of the transmitter and receiver is calculated according to the transmitter data characteristics and receiver data characteristics, respectively;

[0074] Based on timing network model deviation analysis, the state health degree of the transmitter and receiver is calculated according to the transmitter data characteristics and receiver data characteristics, respectively.

[0075] In some embodiments, the calculation of the alarm health degree of the subsystem according to the critical alarm code frequency characteristic specifically includes:

[0076] Based on the alarm code frequency analysis, the alarm health degree of the transmitter, receiver, antenna and other systems is calculated according to the frequency characteristics of the key alarm codes of the transmitter, receiver, antenna and other systems.

[0077] In some embodiments, the rationality of the parameter distribution can be calculated by parameter interval analysis to obtain the parameter health degree of the subsystem (transmitter, receiver).

[0078] Specifically, based on the transmitter data characteristics and receiver data characteristics, the frequency of each parameter exceeding the threshold interval per hour is counted, and the abnormal parameter over-limit frequency is punished to form the parameter health degree of the subsystem. The threshold interval can set the upper and lower limit interval of each parameter according to expert experience.

[0079] For example, the parameter health degree of a certain subsystem is:

[0080]

[0081] Where, h 参数 represents the parameter health degree of a certain subsystem, n (count(每小时参数i超限)) represents the number of times that the i-th parameter of the subsystem exceeds the limit per hour.

[0082] In some embodiments, the state health degree of the subsystem (transmitter, receiver) can be calculated by the time sequence network model deviation analysis method, i.e. state correlation analysis, to analyze the time sequence correlation fluctuation between multiple parameters.

[0083] Specifically, the time sequence network model is a 1-layer CNN convolution layer + 12-layer LSTM + 1-layer self-attention layer, the training data range is the historical normal operation data of all weather radars (excluding the fault period), and the constructed subsystem time sequence network model is: 分系统 Y 分系统 = F (x); the network parameter settings are shown in Table 3, and the network structure diagram is shown in Figure 2 .

[0084] Table 3: Network parameter settings of time sequence network model

[0085]

[0086] For example, to calculate the state health degree of a certain subsystem, the independent variable X is the key target quantity of the subsystem; the dependent variable Y is the data characteristics of the subsystem except the key target quantity; the key target quantity of the transmitter system is the peak power of the horizontal channel antenna; the key target quantity of the receiver system is the noise coefficient of the horizontal channel; according to whether the residual (the difference between the predicted value and the actual value of the independent variable Y) exceeds the 3-sigma interval, it is determined as a single-time abnormality, and the abnormal frequency is counted to obtain the state health degree of the subsystem:

[0087]

[0088] wherein h 状态(分系统) represents the state health degree of a subsystem, y 分系统 represents the actual value of the key target quantity of the subsystem, represents the predicted value of the key target quantity of the subsystem, and σ represents the standard deviation of the key target quantity of the subsystem.

[0089] In some embodiments, when the frequency of the alarm code of a subsystem exceeds a threshold limit, it is considered that the subsystem has an alarm abnormality, i.e., alarm code frequency analysis, to obtain the alarm health degree of the subsystem (transmitter, receiver, antenna and other systems).

[0090] For example, the alarm health degree of a certain subsystem is:

[0091]

[0092] wherein h 报警 represents the alarm health degree of a subsystem s 分系统 represents the frequency of the alarm code of the subsystem.

[0093] In block 140, based on a preset radar health degree calculation formula, the weather radar health degree is calculated according to the parameter health degree and the state health degree of the subsystem and the alarm health degree of the subsystem.

[0094] In some embodiments, the health degree calculation of the weather radar is divided into three layers, i.e., the weather radar health degree, the subsystem health degree and the subsystem dimension health degree.

[0095] In some embodiments, the above-mentioned calculation of the weather radar health degree based on the preset radar health degree calculation formula according to the parameter health degree and the state health degree of the subsystem and the alarm health degree of the subsystem includes:

[0096] Based on the preset radar health degree calculation formula, the transmitter health degree is calculated according to the transmitter parameter health degree, the transmitter state health degree and the transmitter alarm health degree, the receiver health degree is calculated according to the receiver parameter health degree, the receiver state health degree and the receiver alarm health degree, the antenna health degree is calculated according to the antenna alarm health degree, and the other system health degree is calculated according to the other system alarm health degree.

[0097] Based on the preset radar health degree calculation formula, the weather radar health degree is calculated according to the transmitter health degree, the receiver health degree, the antenna health degree and the other system health degree.

[0098] In some embodiments, the above-mentioned preset radar health degree calculation formula includes:

[0099] In some embodiments, the above-mentioned preset radar health degree calculation formula includes:

[0100] wherein h 总 represents the total health degree, h n represents the sub-health degree, h 总 is obtained by weighting the mean value and the minimum value of the sub-health degree, and comprehensively considers the trend consistency and volatility of the sub-health degree.

[0101] As Figure 3 shown, the detailed calculation process of the weather radar health degree is as follows:

[0102]

[0103] In some embodiments, the calculation of the radar health degree can also calculate the health degree of each subsystem and the weather radar health degree by using the health degree calculation formula. As Figure 4 shown, the XML state parameter and alarm code data are collected, and first, feature processing is performed, and then dimension health degree calculation (parameter interval analysis, state correlation analysis, alarm code frequency analysis) is performed, and finally, health degree calculation is performed.

[0104] According to the embodiments of the present disclosure, the following technical effects are achieved:

[0105] The XML state data and alarm code data of the weather radar can be obtained; the subsystem corresponding to the XML state data is the transmitter and the receiver, and the subsystem corresponding to the alarm code data is the transmitter, the receiver, the antenna and other systems, so as to select key parameters through expert experience, combine the parameters of each subsystem with the alarm code, break through the limitations of a single threshold or data-driven model; then, data features are calculated according to the XML state data, and key alarm code frequency features are calculated according to the alarm code data, so as to process the data features, break the problem of single parameter analysis method being easily disturbed by redundant data, and extract key degradation features, i.e., extract the data dimensions required for calculating the health degree; then, the parameter health degree and the state health degree of the subsystem are calculated according to the data features, and the alarm health degree of the subsystem is calculated according to the key alarm code frequency features, so as to calculate the dimension health degree from multiple angles, i.e., from the three dimensions of parameter interval analysis, state analysis and alarm analysis, to construct the hierarchical health degree of the weather radar; then, based on the preset radar health degree calculation formula, the weather radar health degree is calculated according to the parameter health degree and the state health degree of the subsystem and the alarm health degree of the subsystem, so as to realize the calculation of the health degree of each subsystem and the weather radar health degree; based on this, a weather radar health degree modeling method based on experience data fusion can be proposed, key parameters are selected through expert experience, a weather radar hierarchical health degree construction method is proposed from the three dimensions of parameter interval analysis, state analysis and alarm analysis, which breaks through the limitations of traditional single threshold or data-driven model, and significantly improves the robustness and interpretability of the health degree.

[0106] It should be noted that, for the foregoing method embodiments, for the sake of simple description, they are all described as a combination of a series of actions, but those skilled in the art should know that the present disclosure is not limited by the order of the described actions, because according to the present disclosure, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present disclosure.

[0107] The above is the introduction of the method embodiment, and the scheme of the present disclosure will be further described through the device embodiment.

[0108] Figure 5 A block diagram of a weather radar health degree calculation device 500 according to an embodiment of the present disclosure is shown. As shown, the device 500 includes: Figure 5

[0109] The acquisition module 510 is configured to acquire XML state data and alarm code data of the weather radar; the subsystem corresponding to the XML state data is the transmitter and the receiver, and the subsystem corresponding to the alarm code data is the transmitter, the receiver, the antenna and other systems.

[0110] The calculation module 520 is configured to calculate data features according to the XML state data and calculate key alarm code frequency features according to the alarm code data.

[0111] The calculation module 520 is further configured to calculate parameter health degrees and state health degrees of the subsystems according to the data features, and calculate alarm health degrees of the subsystems according to the key alarm code frequency features.

[0112] The calculation module 520 is further configured to calculate the weather radar health degree based on a preset radar health degree calculation formula, according to the parameter health degrees and the state health degrees of the subsystems and the alarm health degrees of the subsystems.

[0113] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the described modules can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0114] In the technical scheme of the present disclosure, the acquisition, storage and application of user personal information involved all comply with the relevant legal regulations and do not violate public order and good customs.

[0115] According to the embodiments of the present disclosure, the present disclosure further provides an electronic device, a readable storage medium and a computer program product.

[0116] Figure 6 ​A block diagram of an exemplary electronic device 600 capable of implementing embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present disclosure described and / or claimed in this document.

[0117] The electronic device 600 includes a computing unit 601 that can perform various appropriate actions and processes in accordance with a computer program stored in a ROM 602 or a computer program loaded from the storage unit 608 into a RAM 603. Various programs and data required for the operation of the electronic device 600 can also be stored in the RAM 603. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. An I / O interface 605 is also connected to the bus 604.

[0118] Various components in the electronic device 600 are connected to the I / O interface 605, including an input unit 606, such as a keyboard, a mouse, and the like; an output unit 607, such as various types of displays, speakers, and the like; a storage unit 608, such as a magnetic disk, an optical disk, and the like; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, and the like. The communication unit 609 allows the electronic device 600 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0119] The computing unit 601 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, and the like. The computing unit 601 performs various methods and processes described above, such as the method 100. For example, in some embodiments, the method 100 can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 608.

[0120] In some embodiments, parts or all of the computer program can be loaded onto the electronic device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded onto the RAM 603 and executed by the computation unit 601, one or more steps of the above-described method 100 can be performed. Alternatively, in other embodiments, the computation unit 601 can be configured to perform the method 100 by other any suitable means, for example by means of firmware.

[0121] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a programmable logic device (PLD), a computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0122] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces the functions / operations specified in the flowcharts and / or the block diagrams. The program code can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0123] In the context of this disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0124] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0125] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0126] The computer system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server can arise by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0127] It should be understood that the various forms of flow shown above can be used to reorder, add, or remove steps. For example, the steps recited in the present disclosure can be performed in parallel, in series, or in a different order, as long as the desired results of the technology disclosed in the present disclosure are achieved, which is not limited herein.

[0128] The specific implementation described above does not constitute a limitation on the protection scope of the present disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for calculating the health status of a weather radar, characterized in that, include: Obtain the XML status data and alarm code data from the weather radar; The subsystems corresponding to the XML status data are the transmitter and receiver, and the subsystems corresponding to the alarm code data are the transmitter, receiver, antenna, and other systems. Calculate data features based on the XML status data, and calculate key alarm code frequency features based on the alarm code data; The parameter health and status health of the subsystem are calculated based on the data characteristics, and the alarm health of the subsystem is calculated based on the frequency characteristics of the key alarm codes. Based on the preset radar health calculation formula, the weather radar health is calculated according to the parameter health, status health, and alarm health of the subsystem.

2. The method according to claim 1, characterized in that, The data features include transmitter data features and receiver data features; the key alarm code frequency features include transmitter key alarm code frequency features, receiver key alarm code frequency features, antenna key alarm code frequency features, and other system key alarm code frequency features. The transmitter data features include transmitter temperature, horizontal channel phase noise, vertical channel phase noise, power difference before and after horizontal channel filtering, power difference before and after vertical channel filtering, transmitter peak power, horizontal channel antenna peak power, and vertical channel antenna peak power. The receiver data features include short-pulse noise level, long-pulse noise level, current vertical channel noise level, current horizontal channel noise level, horizontal channel noise temperature coefficient, short-pulse system calibration constant variation, and long-pulse system calibration constant variation. Values, differences between expected and measured reflectance values ​​1, 2, 3, 4, ...

3. The method according to claim 2, characterized in that, The calculation of the subsystem's parameter health and status health based on the data characteristics includes: Based on parameter range analysis, the parameter health of the transmitter and receiver is calculated according to the transmitter data characteristics and receiver data characteristics, respectively. Based on the deviation analysis of the time-series network model, the state health of the transmitter and receiver is calculated according to the transmitter data characteristics and receiver data characteristics, respectively.

4. The method according to claim 3, characterized in that, The calculation of the subsystem's alarm health status based on the frequency characteristics of the key alarm codes includes: Based on alarm code frequency analysis, the alarm health of the transmitter, receiver, antenna, and other systems is calculated according to the frequency characteristics of the transmitter's key alarm codes, receiver's key alarm codes, antenna's key alarm codes, and other system key alarm codes.

5. The method according to claim 4, characterized in that, The calculation of weather radar health based on a preset radar health calculation formula, according to the parameter health, status health, and alarm health of the subsystem, includes: Based on the preset radar health calculation formula, the transmitter health is calculated according to the transmitter parameter health, transmitter status health, and transmitter alarm health; the receiver health is calculated according to the receiver parameter health, receiver status health, and receiver alarm health; the antenna health is calculated according to the antenna alarm health; and the health of other systems is calculated according to the alarm health of other systems. Based on a preset radar health calculation formula, the health of the weather radar is calculated according to the health of the transmitter, the health of the receiver, the health of the antenna, and the health of other systems.

6. The method according to claim 5, characterized in that, The preset radar health calculation formula includes: Among them, h 总 h represents the overall health level. n h represents the child's health status. 总 It is obtained by weighting the mean and minimum values ​​of the sub-health scores.

7. The method according to any one of claims 1 to 6, characterized in that, The XML status data includes the subsystem's time, transmitter temperature, horizontal channel phase noise, vertical channel phase noise, horizontal channel power before filtering, horizontal channel power after filtering, vertical channel power before filtering, vertical channel power after filtering, transmitter peak power, horizontal channel antenna peak power, vertical channel antenna peak power, short-pulse noise level, current vertical channel noise level, current horizontal channel noise level, horizontal channel noise figure, short-pulse system calibration constant, long-pulse system calibration constant, expected reflectivity 1, expected reflectivity 2, expected reflectivity 3, and so on. The data includes: emissivity expected value 4, reflectivity measurement value 1, reflectivity measurement value 2, reflectivity measurement value 3, reflectivity measurement value 4, velocity expected value 1, velocity expected value 2, velocity expected value 3, velocity expected value 4, velocity measurement value 1, velocity measurement value 2, velocity measurement value 3, velocity measurement value 4, spectrum expected value 1, spectrum expected value 2, spectrum expected value 3, spectrum expected value 4, spectrum measurement value 1, spectrum measurement value 2, spectrum measurement value 3, spectrum measurement value 4, ZDR calibration value, and system calibration constant changes; the alarm code data includes the subsystem's alarm time, alarm code, and alarm meaning.

8. A weather radar health status calculation device, characterized in that, include: The acquisition module is used to acquire XML status data and alarm code data from the weather radar; The subsystems corresponding to the XML status data are the transmitter and receiver, and the subsystems corresponding to the alarm code data are the transmitter, receiver, antenna, and other systems. The calculation module is used to calculate data features based on the XML status data and to calculate key alarm code frequency features based on the alarm code data. The calculation module is also used to calculate the parameter health and status health of the subsystem based on the data characteristics, and to calculate the alarm health of the subsystem based on the frequency characteristics of the key alarm codes. The calculation module is also used to calculate the health of the weather radar based on a preset radar health calculation formula, according to the parameter health, status health, and alarm health of the subsystem.

9. An electronic device, characterized in that, include: At least one processor; as well as A memory that is communicatively connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method described in any one of claims 1-7.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-7.

Images