CN116070153A - Method, device, equipment and medium for predicting fault parameters of phased array T/R assembly - Google Patents
Method, device, equipment and medium for predicting fault parameters of phased array T/R assembly Download PDFInfo
- Publication number
- CN116070153A CN116070153A CN202310201031.2A CN202310201031A CN116070153A CN 116070153 A CN116070153 A CN 116070153A CN 202310201031 A CN202310201031 A CN 202310201031A CN 116070153 A CN116070153 A CN 116070153A
- Authority
- CN
- China
- Prior art keywords
- fault
- model
- data
- historical
- assembly
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 71
- 238000001514 detection method Methods 0.000 claims abstract description 30
- 238000012360 testing method Methods 0.000 claims abstract description 19
- 238000007781 pre-processing Methods 0.000 claims abstract description 13
- 238000003062 neural network model Methods 0.000 claims description 36
- 238000012545 processing Methods 0.000 claims description 23
- 238000004422 calculation algorithm Methods 0.000 claims description 17
- 230000006870 function Effects 0.000 claims description 16
- 230000001186 cumulative effect Effects 0.000 claims description 15
- 238000013519 translation Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 9
- 238000009825 accumulation Methods 0.000 claims description 5
- 238000010606 normalization Methods 0.000 claims description 3
- 238000012423 maintenance Methods 0.000 abstract description 10
- 238000002955 isolation Methods 0.000 abstract 1
- 238000013461 design Methods 0.000 description 30
- 238000012549 training Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 6
- 238000013528 artificial neural network Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 238000003745 diagnosis Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/40—Means for monitoring or calibrating
- G01S7/4004—Means for monitoring or calibrating of parts of a radar system
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Abstract
The invention discloses a method, a device, equipment and a medium for predicting fault parameters of a phased array T/R assembly, which comprise the following steps: acquiring historical fault quantity data of a phased array T/R assembly for preprocessing; inputting the historical fault quantity data into a combined prediction model to predict the fault quantity data of the T/R assembly; acquiring the association relation between each test item and each workshop replaceable unit of the T/R assembly according to the historical performance detection result, and establishing a fault database of the T/R assembly; the support vector model based on the decision directed acyclic graph is trained and predicted. The invention can ensure higher prediction precision, namely, the fault quantity of the T/R assembly can be accurately predicted, thereby providing data support for the maintenance and inventory strategy of the T/R assembly; the fault isolation device can directly isolate faults of the T/R assembly to one or more workshop replaceable units, so that the subsequent fault maintenance time of the T/R assembly is reduced, and the equipment guarantee capability is improved.
Description
Technical Field
The invention belongs to the technical field of phased arrays, in particular to a method, a device, equipment and a medium for predicting fault parameters of a phased array T/R component.
Background
The large phased array radar T/R (Transmitter and Receiver) has a large number of components and frequent faults, so that a reasonable replacement maintenance strategy needs to be established for the T/R components, the number of the faulty T/R components in the phased array is monitored and predicted in time, the relation between the number of faults and the operation time of the phased array is found, and the method has important significance in maximizing the fighting capacity of equipment and improving the preparation and maintenance support capacity.
The existing phased array T/R component fault prediction methods comprise a linear regression analysis method, a gray model method, a support vector machine method, a neural network method and the like, wherein the gray prediction method is particularly suitable for predicting small sample data, but the prediction accuracy is not high, and the neural network prediction method has higher prediction accuracy but needs a large number of training samples.
Disclosure of Invention
The invention aims to provide a method, a device, equipment and a medium for predicting fault parameters of a phased array T/R component, which are used for solving the technical problems of low prediction precision or need of a large number of training samples in the prior art.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
a first aspect provides a method for predicting failure parameters of a phased array T/R assembly, comprising:
acquiring historical fault quantity data of the phased array T/R component, and preprocessing the historical fault quantity data by adopting a moving average algorithm;
the preprocessed historical fault quantity data are input into a combined prediction model to predict the fault quantity data of the T/R component, wherein the combined prediction model comprises an improved gray model and a BP neural network model, and the improved gray model comprises improved model initial conditions, improved model background values and data updating of an improved model;
acquiring a historical performance detection result of the T/R component measured by the automatic test system, acquiring an association relation between each test item and each workshop replaceable unit of the T/R component according to the historical performance detection result, and establishing a fault database of the T/R component according to the association relation;
and calling a fault database to train and predict a support vector model based on the decision directed acyclic graph, and carrying out positioning detection on the replaceable unit of the specific fault workshop of the T/R assembly.
In one possible design, obtaining historical fault amount data for a phased array T/R assembly and preprocessing the historical fault amount data using a moving average algorithm includes:
obtaining fault quantity data of the phased array T/R assembly in a historical time period, and expressing the historical fault quantity data by adopting the following formula:
wherein ,
indicating the cumulative operating time of all T/R components, < >>
Representing the amount of T/R component failure in the first period of time,/I>
Representing the amount of T/R component failure in the second time period, and so on; />
Moving average processing is carried out on the historical fault quantity data based on preset translation parameters, and fault quantity data after the historical fault quantity data are accumulated are obtained, wherein the steps are as follows:
according to the historical fault quantity data and the fault quantity data after moving average processing, accumulated fault quantity data are obtained as follows:
wherein ,
representing the failure amount data after accumulation of the historical failure amount data after the moving average processing, +.>
Representing translation parameters->
Integer and->
。
In one possible design, the improved gray model includes improved model initial conditions, improved model background values, and data updates for the improved model, including:
according to the accumulated fault amount data, the initial condition values of the improved gray model are obtained as follows:
according to the accumulated fault amount data, the background value of the improved gray model is obtained as follows:
wherein ,
and />
Respectively indicate->
The%>
Cumulative operation duration and->
Cumulative working time length->
and />
Respectively represent +.>
Accumulated fault quantity data of accumulated working time length +.>
Accumulated fault amount data of accumulated working time length;
according to the background value of the improved gray model, a least square method is adopted to calculate differential parameters in a first-order micro equation, accumulated fault quantity data is calculated and updated through the differential parameters, and updated historical fault quantity data is obtained through the updated accumulated fault quantity data, and the method comprises the following steps:
wherein ,
data representing updated historical fault quantity, < >>
and />
Respectively represent +.>
Updating accumulated failure amount data and +.>
The accumulated fault amount data is updated for each accumulated operating time.
In one possible design, inputting the preprocessed historical fault amount data into the combined prediction model to predict fault amount data for the T/R assembly includes:
the updated historical fault quantity data are input into a serial improved gray model and a BP neural network model, and the fault quantity data of the T/R component are predicted, wherein the prediction result is as follows:
wherein ,
predictive value representing the amount of failure of the T/R component, < >>
Trend predictive value representing T/R component fault quantity using improved gray model, i.e. updated historical fault quantity data +.>
And the interference predicted value of the T/R component fault quantity adopting the BP neural network model is expressed. />
In one possible design, inputting the preprocessed historical fault amount data into the combined prediction model to predict fault amount data for the T/R assembly includes:
the updated historical fault quantity data is input into a parallel improved gray model and a BP neural network model, the fault quantity data of the T/R component is predicted, and the prediction result is as follows:
wherein ,
representing the type of predictive model, i.e. modified gray model and BP neural network model, +.>
A weighting coefficient representing each prediction model;
wherein before the updated historical fault amount data is input into the parallel improved gray model and the BP neural network model, the method further comprises the following steps: the weighting coefficients of each prediction model are determined according to the availability of each prediction model.
In one possible design, before invoking the failure database to train and predict the decision directed acyclic graph based support vector model, further comprising:
and carrying out normalization processing on fault data of the fault database by adopting a mapmin max function.
In one possible design, the support vector model of the decision directed acyclic graph includes
A radial basis function is adopted as a kernel function of each classifier, a grid parameter optimizing algorithm is adopted to optimize the width coefficient and the penalty factor of the radial basis function, wherein +_>
Representing the number of shop interchangeable units for one of the channels of each T/R assembly.
A second aspect provides a phased array T/R assembly fault parameter prediction apparatus, comprising:
the historical data processing module is used for acquiring historical fault quantity data of the phased array T/R component and preprocessing the historical fault quantity data by adopting a moving average algorithm;
the fault prediction module is used for inputting the preprocessed historical fault quantity data into the combined prediction model to predict the fault quantity data of the T/R component, wherein the combined prediction model comprises an improved gray model and a BP neural network model, and the improved gray model comprises an improved model initial condition, an improved model background value and data updating of the improved model;
the database establishing module is used for acquiring a historical performance detection result of the T/R component measured by the automatic test system, acquiring an association relation between each test item and each workshop replaceable unit of the T/R component according to the historical performance detection result, and establishing a fault database of the T/R component according to the association relation;
the fault positioning detection module is used for calling a fault database to train and predict a support vector model based on the decision-directed acyclic graph and performing positioning detection on a specific fault workshop replaceable unit of the T/R assembly.
In one possible design, when acquiring the historical fault amount data of the phased array T/R assembly and preprocessing the historical fault amount data by using a moving average algorithm, the historical data processing module is specifically configured to:
obtaining fault quantity data of the phased array T/R assembly in a historical time period, and expressing the historical fault quantity data by adopting the following formula:
wherein ,
indicating the cumulative operating time of all T/R components, < >>
Representing the amount of T/R component failure in the first period of time,/I>
Representing the amount of T/R component failure in the second time period, and so on;
moving average processing is carried out on the historical fault quantity data based on preset translation parameters, and fault quantity data after the historical fault quantity data are accumulated are obtained, wherein the steps are as follows:
according to the historical fault quantity data and the fault quantity data after moving average processing, accumulated fault quantity data are obtained as follows:
wherein ,
indicating that the historical fault amount data is accumulated after the moving average processingPost-accumulation fault quantity data, < >>
Representing translation parameters->
Integer and->
。
In one possible design, the improved gray model includes improved model initial conditions, improved model background values, and data updates for the improved model, including in particular:
according to the accumulated fault amount data, the initial condition values of the improved gray model are obtained as follows:
according to the accumulated fault amount data, the background value of the improved gray model is obtained as follows:
wherein ,
and />
Respectively indicate->
The%>
Cumulative operation duration and->
Cumulative working time length->
and />
Respectively represent +.>
Accumulated fault quantity data of accumulated working time length +.>
Accumulated fault amount data of accumulated working time length;
according to the background value of the improved gray model, a least square method is adopted to calculate differential parameters in a first-order micro equation, accumulated fault quantity data is calculated and updated through the differential parameters, and updated historical fault quantity data is obtained through the updated accumulated fault quantity data, and the method comprises the following steps:
wherein ,
data representing updated historical fault quantity, < >>
and />
Respectively represent +.>
Updating accumulated failure amount data and +.>
The accumulated fault amount data is updated for each accumulated operating time.
In one possible design, when the pre-processed historical fault amount data is input into the combined prediction model to predict the fault amount data of the T/R component, the fault prediction module is specifically configured to:
the updated historical fault quantity data are input into a serial improved gray model and a BP neural network model, and the fault quantity data of the T/R component are predicted, wherein the prediction result is as follows:
wherein ,
predictive value representing the amount of failure of the T/R component, < >>
Trend predictive value representing T/R component fault quantity using improved gray model, i.e. updated historical fault quantity data +.>
And the interference predicted value of the T/R component fault quantity adopting the BP neural network model is expressed.
In one possible design, when the pre-processed historical fault amount data is input into the combined prediction model to predict the fault amount data of the T/R component, the fault prediction module is specifically configured to:
the updated historical fault quantity data is input into a parallel improved gray model and a BP neural network model, the fault quantity data of the T/R component is predicted, and the prediction result is as follows:
wherein ,
representing the type of predictive model, i.e. modified gray model and BP neural network model, +.>
A weighting coefficient representing each prediction model;
wherein before the updated historical fault amount data is input into the parallel improved gray model and the BP neural network model, the method further comprises the following steps: the weighting coefficients of each prediction model are determined according to the availability of each prediction model.
In a third aspect, the present invention provides a computer device comprising a memory, a processor and a transceiver in sequential communication, wherein the memory is adapted to store a computer program, the transceiver is adapted to receive and transmit messages, and the processor is adapted to read the computer program and perform a method of predicting a failure parameter of a phased array T/R assembly as described in any one of the possible designs of the first aspect.
In a fourth aspect, the invention provides a computer readable storage medium having instructions stored thereon which, when executed on a computer, perform a method of predicting a phased array T/R assembly failure parameter as described in any one of the possible designs of the first aspect.
In a fifth aspect, the invention provides a computer program product comprising instructions which, when run on a computer, cause the computer to perform a method of predicting a phased array T/R assembly fault parameter as described in any one of the possible designs of the first aspect.
Compared with the prior art, the invention has the beneficial effects that:
the method comprises the steps of obtaining historical fault quantity data of a phased array T/R assembly, and preprocessing the historical fault quantity data by adopting a moving average algorithm; the method comprises the steps of inputting the preprocessed historical fault quantity data into a combined prediction model to predict the fault quantity data of the T/R component, wherein the combined prediction model comprises an improved gray model and a BP neural network model, and the improved gray model comprises an improved model initial condition, an improved model background value and data updating of the improved model, so that the technical defects that the accuracy of the existing gray model is low and training data required by the existing BP neural network is large are overcome, and for the condition that the data sample of the T/R component is insufficient and the fault data fluctuation is strong, the method can ensure high prediction accuracy, namely can accurately predict the fault quantity of the T/R component, and therefore data support is provided for maintenance and inventory strategies of the T/R component.
In addition, the invention obtains the association relation between each test item and each workshop replaceable unit of the T/R assembly according to the historical performance detection result by obtaining the historical performance detection result of the T/R assembly measured by the automatic test system, and establishes a fault database of the T/R assembly according to the association relation; and calling a fault database to train and predict a support vector model based on the decision-directed acyclic graph, and carrying out positioning detection on a specific fault workshop replaceable unit of the T/R component, so that the fault of the T/R component can be directly isolated to one or more workshop replaceable units, the subsequent fault maintenance time of the T/R component is reduced, and the equipment guarantee capability is improved.
Drawings
FIG. 1 is a flow chart of a method of predicting failure parameters of a phased array T/R assembly in an embodiment of the application.
Detailed Description
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the present invention will be briefly described below with reference to the accompanying drawings and the description of the embodiments or the prior art, and it is obvious that the following description of the structure of the drawings is only some embodiments of the present invention, and other drawings can be obtained according to these drawings without inventive effort to a person skilled in the art. It should be noted that the description of these examples is for aiding in understanding the present invention, but is not intended to limit the present invention.
Examples
In order to solve the technical problems that the prediction accuracy is not high or a large number of training samples are needed in the prior art, the embodiment of the application provides a prediction method for the fault parameters of a phased array T/R assembly, which overcomes the technical defects that the accuracy of the existing gray model is not high and the training data required by the existing BP neural network is large, and can ensure higher prediction accuracy for the situation that the T/R assembly has insufficient data samples and strong fluctuation of fault data, namely, can accurately predict the fault quantity of the T/R assembly, thereby providing data support for the maintenance and inventory strategy of the T/R assembly; in addition, the method can directly isolate the faults of the T/R assembly to one or more workshop replaceable units, thereby reducing the subsequent fault maintenance time of the T/R assembly and improving the equipment guarantee capability.
The method for predicting the fault parameters of the phased array T/R component provided by the embodiment of the application will be described in detail below.
It should be noted that, the method for predicting the fault parameters of the phased array T/R component provided in the embodiments of the present application may be applied to any terminal device using an operating system, where the operating system includes, but is not limited to, a Windows system, a Mac system, a Linux system, a Chrome OS system, a UNIX operating system, an IOS system, an android system, and the like, and is not limited herein; the terminal device includes, but is not limited to, an IPAD tablet computer, a personal mobile computer, an industrial computer, a personal computer, etc., which are not limited herein. For convenience of description, the embodiments of the present application will be described with reference to an industrial computer as a main body of execution, unless specifically described otherwise. It will be appreciated that the execution subject is not limited to the embodiments of the present application, and in other embodiments, other types of terminal devices may be used as the execution subject.
As shown in fig. 1, a flowchart of a method for predicting a phased array T/R assembly fault parameter according to an embodiment of the present application is provided, where the method for predicting a phased array T/R assembly fault parameter includes, but is not limited to, implementation by steps S1 to S4:
s1, acquiring historical fault quantity data of a phased array T/R assembly, and preprocessing the historical fault quantity data by adopting a moving average algorithm;
it should be noted that, the historical fault amount data refers to fault amount data of the T/R component of each period of time, such as fault amount data of each day, in a period of time, for example, a period of time, where a data sample range of the historical fault amount data is not restricted, but since the gray model is suitable for a small sample amount scenario, the number of the historical fault amount data in the embodiment of the present application is not too large. Since the number of faults in each time period of the phased array T/R assembly relatively fluctuates, the historical fault amount data needs to be preprocessed in order to reduce the influence of bad data and self-checking errors on the prediction accuracy.
In one possible design of step S1, obtaining historical fault amount data of the phased array T/R assembly, and preprocessing the historical fault amount data using a moving average algorithm includes:
1) Obtaining fault quantity data of the phased array T/R assembly in a historical time period, and expressing the historical fault quantity data by adopting the following formula:
wherein ,
indicating the cumulative operating time of all T/R components, < >>
Representing the amount of T/R component failure in the first period of time,/I>
Representing the amount of T/R component failure in the second time period, and so on;
2) Moving average processing is carried out on the historical fault quantity data based on preset translation parameters, and fault quantity data after the historical fault quantity data are accumulated are obtained, wherein the steps are as follows:
3) According to the historical fault quantity data and the fault quantity data after moving average processing, accumulated fault quantity data are obtained as follows:
wherein ,
representing the failure amount data after accumulation of the historical failure amount data after the moving average processing, +.>
Representing translation parameters->
Integer and->
。
S2, inputting the preprocessed historical fault quantity data into a combined prediction model to predict the fault quantity data of the T/R component, wherein the combined prediction model comprises an improved gray model and a BP neural network model, and the improved gray model comprises an improved model initial condition, an improved model background value and data updating of the improved model;
in step S2, it should be noted that, because the structure of the T/R component of the large phased array is complex and is affected by multiple factors such as the failure rate parameter and the external environment, the number of component failures per day is relatively unstable, and the existing gray model has poor prediction effect on the samples with large data fluctuation, so if the existing gray model is directly adopted to predict the failure rate of the T/R component, a large error will be brought, and therefore, the existing gray model needs to be improved to meet the prediction requirement of the failure rate of the phased array T/R component. The background value of the existing gray model is an average value of adjacent data, namely the background value is fixed, and the prediction effect on high data fluctuation in a short time is poor; in addition, the existing gray model takes the first data of the historical fault quantity data as an initial value, but a best fit curve in practical application does not need to pass through a certain point of the historical fault quantity data; in addition, the existing gray model models by using historical fault quantity data, but the data weight of the historical fault quantity is larger as the prediction time is shorter, so that the existing gray model is not suitable for long-term fault quantity prediction.
Based on the above, in one possible design of step S2, the modified gray model includes modified model initial conditions, modified model background values, and data updates of the modified model, including:
1) According to the accumulated fault amount data, the initial condition values of the improved gray model are obtained as follows:
2) Since the selection of the background value is an important factor affecting the accuracy of the gray model, the data is usually set by using a trapezoidal rule, but if the data relatively fluctuates easily in a section, a larger error is generated, so that the background value needs to be optimized, and after the historical fault amount data is accumulated, the fault amount data after the moving average processing is carried out on the historical fault amount data
Approximately->
The background values for the modified gray model are as follows:
wherein ,
and />
Respectively indicate->
The%>
Cumulative operation duration and->
Cumulative working time length->
and />
Respectively represent +.>
Accumulated fault quantity data of accumulated working time length +.>
Accumulated fault amount data of accumulated working time length; />
3) Since the existing gray model processes the weights of different periods equally, the closer the prediction time is, the larger the weight of the data is not considered, so the embodiment of the present application solves the above problem by constructing a linearly increasing weight matrix P, where the expression of the weight matrix P is as follows:
wherein ,
representing an increased weight factor,/->
；
4) According to the background value of the improved gray model, a least square method is adopted to calculate differential parameters in a first-order micro equation, accumulated fault quantity data is calculated and updated through the differential parameters, and updated historical fault quantity data is obtained through the updated accumulated fault quantity data, and the method comprises the following steps:
wherein ,
data representing updated historical fault quantity, < >>
and />
Respectively represent +.>
Updating accumulated failure amount data and +.>
The accumulated fault amount data is updated for each accumulated operating time.
Wherein, it should be noted that the differential parameters in the first-order differential equation
Can be calculated by least square method, i.e. +.>
And parameter->
and />
The calculation can be performed by the following matrix:
parameters are set
Substituting the data into the first-order differential equation to obtain updated and accumulated fault quantity data.
In one possible design of step S2, inputting the preprocessed historical fault amount data into the combined prediction model to predict the fault amount data of the T/R component includes:
the updated historical fault quantity data are input into a serial improved gray model and a BP neural network model, and the fault quantity data of the T/R component are predicted, wherein the prediction result is as follows:
wherein ,
predictive value representing the amount of failure of the T/R component, < >>
Trend predictive value representing T/R component fault quantity using improved gray model, i.e. updated historical fault quantity data +.>
And the interference predicted value of the T/R component fault quantity adopting the BP neural network model is expressed.
In the BP neural network model, preferably, the data is normalized by using a premnmx function, the input layer and the hidden layer use tan sig functions, the output layer use a pulse function, a momentum gradient descent algorithm is used in training, the result is displayed once every 1000 times, the learning rate is set to 0.05, the iteration number is set to 3000, the mean square error of the target is set to 0.00001, and the BP neural network model in the parallel prediction model described below is the same.
In one possible design, inputting the preprocessed historical fault amount data into the combined prediction model to predict fault amount data for the T/R assembly includes:
the updated historical fault quantity data is input into a parallel improved gray model and a BP neural network model, the fault quantity data of the T/R component is predicted, and the prediction result is as follows:
wherein ,
representing the type of predictive model, i.e. modified gray model and BP neural network model, +.>
A weighting coefficient representing each prediction model;
wherein before the updated historical fault amount data is input into the parallel improved gray model and the BP neural network model, the method further comprises the following steps: the weighting coefficients of each prediction model are determined according to the availability of each prediction model.
It should be noted that, the key problem of the parallel improved gray model and BP neural network model is how to determine the weight of each prediction model, and common weight determining methods include an arithmetic average method, a geometric method and a harmonic average method, or a maximum or minimum objective function weight determination entropy method weight determination and gray correlation weight determination are adopted. In the prior art, the present embodiments use availability to determine the weight of each single prediction method. Specifically, the relative precision sequence of each prediction model is calculated firstly, then the average value and the variance of the precision sequence are calculated, the availability of each model is obtained by using the average value and the variance, and finally the weighting coefficient of each prediction model is determined based on the availability
The following are provided:
s3, acquiring a historical performance detection result of the T/R component measured by the automatic test system, acquiring association relations between each test item and each workshop replaceable unit of the T/R component according to the historical performance detection result, and establishing a fault database of the T/R component according to the association relations;
it should be noted that the T/R assembly is generally divided into a receiving channel, a transmitting channel and a common channel, and is composed of 9 shop replaceable units SRUs. The receiving channel comprises 4 SRUs, namely an amplifying module SRU1, a gain control module SRU2, a mixing module SRU3 and a filtering module SRU4; the transmitting channel comprises 4 SRUs, namely a phase shifting module SRU5, a mixing module SRU6, a filtering module SRU7 and an amplifying module SRU8; the common channel is mainly composed of SRU10 transceiver switches. Because the communication among the channels of the T/R component is not large and can be easily isolated, the phased array radar BIT equipment can directly diagnose faults to the channel level of the T/R component. Because there is no link between SRU level faults between channels of the T/R module, and the principle and method of SRU level fault diagnosis of each channel are the same, preferably, in the embodiment of the present application, the SRU level fault positioning detection method of the T/R module is selected by taking the SRU level fault diagnosis of the receiving channel of the T/R module as an example.
It should be noted that, the historical performance detection result of the T/R component refers to a score result of each test item, taking a receiving channel of the T/R component as an example, the test items include, but are not limited to, receiving amplitude consistency, receiving phase consistency, receiving channel gain control range, receiving port standing wave, receiving attenuation precision, receiving gain, receiving in-band flatness, noise coefficient, receiving 1dB compression point, and the like, and a fault database of the T/R component is established according to the association relationship when each replaceable unit of each workshop fails alone.
S4, calling a fault database to train and predict a support vector model based on the decision-directed acyclic graph, and carrying out positioning detection on a specific fault workshop replaceable unit of the T/R component.
In one possible design of step S4, before invoking the failure database to train and predict the decision directed acyclic graph based support vector model, further comprising:
and carrying out normalization processing on fault data of the fault database by adopting a mapmin max function.
In one possible design of step S4, the support vector model of the decision directed acyclic graph includes
A radial basis function is adopted as a kernel function of each classifier, a grid parameter optimizing algorithm is adopted to optimize the width coefficient and the penalty factor of the radial basis function, wherein +_>
Representing the number of shop interchangeable units for one of the channels of each T/R assembly.
Based on the disclosure, the embodiment of the application pretreats the historical fault quantity data by acquiring the historical fault quantity data of the phased array T/R component and adopting a moving average algorithm; the method comprises the steps of inputting the preprocessed historical fault quantity data into a combined prediction model to predict the fault quantity data of the T/R component, wherein the combined prediction model comprises an improved gray model and a BP neural network model, and the improved gray model comprises an improved model initial condition, an improved model background value and data updating of the improved model, so that the technical defects that the accuracy of the existing gray model is low and training data required by the existing BP neural network is large are overcome, and for the condition that the data sample of the T/R component is insufficient and the fault data fluctuation is strong, the method can ensure high prediction accuracy, namely can accurately predict the fault quantity of the T/R component, and therefore data support is provided for maintenance and inventory strategies of the T/R component.
In addition, the invention obtains the association relation between each test item and each workshop replaceable unit of the T/R assembly according to the historical performance detection result by obtaining the historical performance detection result of the T/R assembly measured by the automatic test system, and establishes a fault database of the T/R assembly according to the association relation; and calling a fault database to train and predict a support vector model based on the decision-directed acyclic graph, and carrying out positioning detection on a specific fault workshop replaceable unit of the T/R component, so that the fault of the T/R component can be directly isolated to one or more workshop replaceable units, the subsequent fault maintenance time of the T/R component is reduced, and the equipment guarantee capability is improved.
A second aspect provides a phased array T/R assembly fault parameter prediction apparatus, comprising:
the historical data processing module is used for acquiring historical fault quantity data of the phased array T/R component and preprocessing the historical fault quantity data by adopting a moving average algorithm;
the fault prediction module is used for inputting the preprocessed historical fault quantity data into the combined prediction model to predict the fault quantity data of the T/R component, wherein the combined prediction model comprises an improved gray model and a BP neural network model, and the improved gray model comprises an improved model initial condition, an improved model background value and data updating of the improved model;
the database establishing module is used for acquiring a historical performance detection result of the T/R component measured by the automatic test system, acquiring an association relation between each test item and each workshop replaceable unit of the T/R component according to the historical performance detection result, and establishing a fault database of the T/R component according to the association relation;
the fault positioning detection module is used for calling a fault database to train and predict a support vector model based on the decision-directed acyclic graph and performing positioning detection on a specific fault workshop replaceable unit of the T/R assembly.
In one possible design, when acquiring the historical fault amount data of the phased array T/R assembly and preprocessing the historical fault amount data by using a moving average algorithm, the historical data processing module is specifically configured to:
obtaining fault quantity data of the phased array T/R assembly in a historical time period, and expressing the historical fault quantity data by adopting the following formula:
wherein ,
indicating the cumulative operating time of all T/R components, < >>
Representing the amount of T/R component failure in the first period of time,/I>
Representing the amount of T/R component failure in the second time period, and so on;
moving average processing is carried out on the historical fault quantity data based on preset translation parameters, and fault quantity data after the historical fault quantity data are accumulated are obtained, wherein the steps are as follows:
according to the historical fault quantity data and the fault quantity data after moving average processing, accumulated fault quantity data are obtained as follows:
wherein ,
representing the failure amount data after accumulation of the historical failure amount data after the moving average processing, +.>
Representing translation parameters->
Integer and->
。
In one possible design, the improved gray model includes improved model initial conditions, improved model background values, and data updates for the improved model, including in particular:
according to the accumulated fault amount data, the initial condition values of the improved gray model are obtained as follows:
according to the accumulated fault amount data, the background value of the improved gray model is obtained as follows:
wherein ,
and />
Respectively indicate->
The%>
Cumulative operation duration and->
Cumulative working time length->
and />
Respectively represent +.>
Accumulated fault quantity data of accumulated working time length +.>
Accumulated fault amount data of accumulated working time length;
according to the background value of the improved gray model, a least square method is adopted to calculate differential parameters in a first-order micro equation, accumulated fault quantity data is calculated and updated through the differential parameters, and updated historical fault quantity data is obtained through the updated accumulated fault quantity data, and the method comprises the following steps:
wherein ,
data representing updated historical fault quantity, < >>
and />
Respectively represent +.>
Updating accumulated failure amount data and +.>
Each accumulated working timeAnd updating the accumulated fault quantity data.
In one possible design, when the pre-processed historical fault amount data is input into the combined prediction model to predict the fault amount data of the T/R component, the fault prediction module is specifically configured to:
the updated historical fault quantity data are input into a serial improved gray model and a BP neural network model, and the fault quantity data of the T/R component are predicted, wherein the prediction result is as follows:
wherein ,
predictive value representing the amount of failure of the T/R component, < >>
Trend predictive value representing T/R component fault quantity using improved gray model, i.e. updated historical fault quantity data +.>
And the interference predicted value of the T/R component fault quantity adopting the BP neural network model is expressed.
In one possible design, when the pre-processed historical fault amount data is input into the combined prediction model to predict the fault amount data of the T/R component, the fault prediction module is specifically configured to:
the updated historical fault quantity data is input into a parallel improved gray model and a BP neural network model, the fault quantity data of the T/R component is predicted, and the prediction result is as follows:
wherein ,
representing the kind of predictive model, i.e. modified ashColor model and BP neural network model, +.>
A weighting coefficient representing each prediction model;
wherein before the updated historical fault amount data is input into the parallel improved gray model and the BP neural network model, the method further comprises the following steps: the weighting coefficients of each prediction model are determined according to the availability of each prediction model.
The working process, working details and technical effects of the foregoing apparatus provided in the second aspect of the present embodiment may be referred to as the method described in the foregoing first aspect or any one of the possible designs of the first aspect, which are not described herein again.
In a third aspect, the present invention provides a computer device comprising a memory, a processor and a transceiver in sequential communication, wherein the memory is adapted to store a computer program, the transceiver is adapted to receive and transmit messages, and the processor is adapted to read the computer program and perform a method of predicting a failure parameter of a phased array T/R assembly as described in any one of the possible designs of the first aspect.
By way of specific example, the Memory may include, but is not limited to, random-Access Memory (RAM), read-Only Memory (ROM), flash Memory (Flash Memory), first-in first-out Memory (First Input First Output, FIFO), and/or first-in last-out Memory (First Input Last Output, FILO), etc.; the processor may not be limited to use with a microprocessor of the STM32F105 family; the transceiver may be, but is not limited to, a WiFi (wireless fidelity) wireless transceiver, a bluetooth wireless transceiver, a GPRS (General Packet Radio Service, general packet radio service technology) wireless transceiver, and/or a ZigBee (ZigBee protocol, low power local area network protocol based on the ieee 802.15.4 standard), etc. In addition, the computer device may include, but is not limited to, a power module, a display screen, and other necessary components.
The working process, working details and technical effects of the foregoing computer device provided in the third aspect of the present embodiment may be referred to the above first aspect or any one of the possible designs of the first aspect, which are not described herein.
In a fourth aspect, the invention provides a computer readable storage medium having instructions stored thereon which, when executed on a computer, perform a method of predicting a phased array T/R assembly failure parameter as described in any one of the possible designs of the first aspect.
The computer readable storage medium refers to a carrier for storing data, and may include, but is not limited to, a floppy disk, an optical disk, a hard disk, a flash Memory, and/or a Memory Stick (Memory Stick), etc., where the computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable devices.
The working process, working details and technical effects of the foregoing computer readable storage medium provided in the fourth aspect of the present embodiment may refer to the method as described in the foregoing first aspect or any one of the possible designs of the first aspect, which are not repeated herein.
In a fifth aspect, the invention provides a computer program product comprising instructions which, when run on a computer, cause the computer to perform a method of predicting a phased array T/R assembly fault parameter as described in any one of the possible designs of the first aspect.
The working process, working details and technical effects of the foregoing computer program product containing instructions provided in the fifth aspect of the present embodiment may be referred to as the method described in the foregoing first aspect or any one of the possible designs of the first aspect, which are not repeated herein.
Finally, it should be noted that: the foregoing description is only of the preferred embodiments of the invention and is not intended to limit the scope of the invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A method for predicting fault parameters of a phased array T/R assembly, comprising:
acquiring historical fault quantity data of the phased array T/R component, and preprocessing the historical fault quantity data by adopting a moving average algorithm;
the preprocessed historical fault quantity data are input into a combined prediction model to predict the fault quantity data of the T/R component, wherein the combined prediction model comprises an improved gray model and a BP neural network model, and the improved gray model comprises improved model initial conditions, improved model background values and data updating of an improved model;
acquiring a historical performance detection result of the T/R component measured by the automatic test system, acquiring an association relation between each test item and each workshop replaceable unit of the T/R component according to the historical performance detection result, and establishing a fault database of the T/R component according to the association relation;
and calling a fault database to train and predict a support vector model based on the decision directed acyclic graph, and carrying out positioning detection on the replaceable unit of the specific fault workshop of the T/R assembly.
2. The method for predicting fault parameters of a phased array T/R assembly of claim 1, wherein obtaining historical fault amount data of the phased array T/R assembly and preprocessing the historical fault amount data using a moving average algorithm comprises:
obtaining fault quantity data of the phased array T/R assembly in a historical time period, and expressing the historical fault quantity data by adopting the following formula:
wherein ,
indicating the cumulative operating time of all T/R components, < >>
Representing the amount of T/R component failure in the first period of time,/I>
Representing the amount of T/R component failure in the second time period, and so on;
moving average processing is carried out on the historical fault quantity data based on preset translation parameters, and fault quantity data after the historical fault quantity data are accumulated are obtained, wherein the steps are as follows:
according to the historical fault quantity data and the fault quantity data after moving average processing, accumulated fault quantity data are obtained as follows:
wherein ,
representing the failure amount data after accumulation of the historical failure amount data after the moving average processing, +.>
Representing translation parameters->
Integer and->
。
3. The method of claim 2, wherein the modified gray model comprises modified model initial conditions, modified model background values, and modified model data updates, comprising:
according to the accumulated fault amount data, the initial condition values of the improved gray model are obtained as follows:
according to the accumulated fault amount data, the background value of the improved gray model is obtained as follows:
wherein ,
and />
Respectively indicate->
The%>
Cumulative operation duration and->
Cumulative working time length->
and />
Respectively represent +.>
Accumulated fault amount data for accumulated operating time period and the first
Accumulated fault amount data of accumulated working time length;
according to the background value of the improved gray model, a least square method is adopted to calculate differential parameters in a first-order micro equation, accumulated fault quantity data is calculated and updated through the differential parameters, and updated historical fault quantity data is obtained through the updated accumulated fault quantity data, and the method comprises the following steps:
wherein ,
data representing updated historical fault quantity, < >>
and />
Respectively represent +.>
Updating accumulated failure amount data and +.>
The accumulated fault amount data is updated for each accumulated operating time.
4. A method of predicting failure parameters of a phased array T/R assembly as claimed in claim 3, wherein inputting the pre-processed historical failure amount data into the combined prediction model predicts failure amount data of the T/R assembly, comprising:
the updated historical fault quantity data are input into a serial improved gray model and a BP neural network model, and the fault quantity data of the T/R component are predicted, wherein the prediction result is as follows:
wherein ,
predictive value representing the amount of failure of the T/R component, < >>
Trend predictive value representing T/R component fault quantity using improved gray model, i.e. updated historical fault quantity data +.>
And the interference predicted value of the T/R component fault quantity adopting the BP neural network model is expressed.
5. A method of predicting failure parameters of a phased array T/R assembly as claimed in claim 3, wherein inputting the pre-processed historical failure amount data into the combined prediction model predicts failure amount data of the T/R assembly, comprising:
the updated historical fault quantity data is input into a parallel improved gray model and a BP neural network model, the fault quantity data of the T/R component is predicted, and the prediction result is as follows:
wherein ,
representing the type of predictive model, i.e. modified gray model and BP neural network model, +.>
A weighting coefficient representing each prediction model;
wherein before the updated historical fault amount data is input into the parallel improved gray model and the BP neural network model, the method further comprises the following steps: the weighting coefficients of each prediction model are determined according to the availability of each prediction model.
6. The method for predicting fault parameters of a phased array T/R assembly of claim 1, further comprising, prior to invoking the fault database to train and predict the decision directed acyclic graph based support vector model:
and carrying out normalization processing on fault data of the fault database by adopting a mapmin max function.
7. The method for predicting failure parameters of a phased array T/R assembly of claim 1, wherein the support vector model of the decision directed acyclic graph comprises
A radial basis function is adopted as a kernel function of each classifier, a grid parameter optimizing algorithm is adopted to optimize the width coefficient and the penalty factor of the radial basis function, wherein +_>
Representing the number of shop interchangeable units for one of the channels of each T/R assembly.
8. A phased array T/R assembly fault parameter prediction apparatus, comprising:
the historical data processing module is used for acquiring historical fault quantity data of the phased array T/R component and preprocessing the historical fault quantity data by adopting a moving average algorithm;
the fault prediction module is used for inputting the preprocessed historical fault quantity data into the combined prediction model to predict the fault quantity data of the T/R component, wherein the combined prediction model comprises an improved gray model and a BP neural network model, and the improved gray model comprises an improved model initial condition, an improved model background value and data updating of the improved model;
the database establishing module is used for acquiring a historical performance detection result of the T/R component measured by the automatic test system, acquiring an association relation between each test item and each workshop replaceable unit of the T/R component according to the historical performance detection result, and establishing a fault database of the T/R component according to the association relation;
the fault positioning detection module is used for calling a fault database to train and predict a support vector model based on the decision-directed acyclic graph and performing positioning detection on a specific fault workshop replaceable unit of the T/R assembly.
9. A computer device comprising a memory, a processor and a transceiver connected in sequence, wherein the memory is configured to store a computer program, the transceiver is configured to send and receive messages, and the processor is configured to read the computer program and perform the method for predicting the failure parameters of the phased array T/R assembly according to any one of claims 1 to 7.
10. A computer readable storage medium having instructions stored thereon which, when executed on a computer, perform the method of predicting a phased array T/R assembly fault parameter as claimed in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310201031.2A CN116070153A (en) | 2023-03-06 | 2023-03-06 | Method, device, equipment and medium for predicting fault parameters of phased array T/R assembly |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310201031.2A CN116070153A (en) | 2023-03-06 | 2023-03-06 | Method, device, equipment and medium for predicting fault parameters of phased array T/R assembly |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116070153A true CN116070153A (en) | 2023-05-05 |
Family
ID=86171563
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310201031.2A Pending CN116070153A (en) | 2023-03-06 | 2023-03-06 | Method, device, equipment and medium for predicting fault parameters of phased array T/R assembly |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116070153A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117272118A (en) * | 2023-11-17 | 2023-12-22 | 成都天奥集团有限公司 | T/R component health state prediction method, system, equipment and medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108427867A (en) * | 2018-01-22 | 2018-08-21 | 中国科学院合肥物质科学研究院 | One kind being based on Grey BP Neural Network interactions between protein Relationship Prediction method |
| CN111310990A (en) * | 2020-02-07 | 2020-06-19 | 北京联合大学 | Improved gray combination model-based track quality prediction method and system |
| CN111539515A (en) * | 2020-04-21 | 2020-08-14 | 中国电子科技集团公司第三十八研究所 | Complex equipment maintenance decision method based on fault prediction |
| CN111681765A (en) * | 2020-04-29 | 2020-09-18 | 华南师范大学 | Multi-model fusion method of medical question-answering system |
| CN112488171A (en) * | 2020-11-25 | 2021-03-12 | 江南大学 | Variable mode decomposition SRU fault prediction method |
| US20210125200A1 (en) * | 2019-10-28 | 2021-04-29 | Jilin Jianzhu University | Method and system for predicting medium-long term water demand of water supply network |
| CN112836168A (en) * | 2021-02-03 | 2021-05-25 | 中国工商银行股份有限公司 | Resource reservation quantity determining method, device and storage medium |
| CN113312715A (en) * | 2021-05-10 | 2021-08-27 | 暨南大学 | Tramcar groove rail distortion irregularity prediction method |
| CN113592131A (en) * | 2021-04-22 | 2021-11-02 | 福建师范大学 | Method for predicting annual production of construction waste based on improved gray GM (1,1) model |
| CN115130054A (en) * | 2022-07-08 | 2022-09-30 | 神华神东电力有限责任公司 | Mining subsidence prediction method and device, storage medium and electronic equipment |
| CN115238977A (en) * | 2022-07-13 | 2022-10-25 | 湖南科技大学 | Building settlement prediction method based on improved non-equidistant gray model |
-
2023
- 2023-03-06 CN CN202310201031.2A patent/CN116070153A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108427867A (en) * | 2018-01-22 | 2018-08-21 | 中国科学院合肥物质科学研究院 | One kind being based on Grey BP Neural Network interactions between protein Relationship Prediction method |
| US20210125200A1 (en) * | 2019-10-28 | 2021-04-29 | Jilin Jianzhu University | Method and system for predicting medium-long term water demand of water supply network |
| CN111310990A (en) * | 2020-02-07 | 2020-06-19 | 北京联合大学 | Improved gray combination model-based track quality prediction method and system |
| CN111539515A (en) * | 2020-04-21 | 2020-08-14 | 中国电子科技集团公司第三十八研究所 | Complex equipment maintenance decision method based on fault prediction |
| CN111681765A (en) * | 2020-04-29 | 2020-09-18 | 华南师范大学 | Multi-model fusion method of medical question-answering system |
| CN112488171A (en) * | 2020-11-25 | 2021-03-12 | 江南大学 | Variable mode decomposition SRU fault prediction method |
| CN112836168A (en) * | 2021-02-03 | 2021-05-25 | 中国工商银行股份有限公司 | Resource reservation quantity determining method, device and storage medium |
| CN113592131A (en) * | 2021-04-22 | 2021-11-02 | 福建师范大学 | Method for predicting annual production of construction waste based on improved gray GM (1,1) model |
| CN113312715A (en) * | 2021-05-10 | 2021-08-27 | 暨南大学 | Tramcar groove rail distortion irregularity prediction method |
| CN115130054A (en) * | 2022-07-08 | 2022-09-30 | 神华神东电力有限责任公司 | Mining subsidence prediction method and device, storage medium and electronic equipment |
| CN115238977A (en) * | 2022-07-13 | 2022-10-25 | 湖南科技大学 | Building settlement prediction method based on improved non-equidistant gray model |
Non-Patent Citations (5)
| Title |
|---|
| CHUANG ZHANG 等: "Application of optimized grey discrete Verhulst-BP neural network model in settlement prediction of foundation pit", 《ENVIRONMENTAL EARTH SCIENCES》, pages 180 - 182 * |
| 王挺 等: "基于多分类 SVM的 T/R组件 SRU级故障诊断", 《现代电子技术》, vol. 42, no. 23, pages 67 - 71 * |
| 赵建忠;徐廷学;叶文;张磊;: "基于数据融合和改进MUGM(1,m,w)的导弹装备故障预测", 《系统工程与电子技术》, vol. 37, no. 04, pages 832 - 837 * |
| 黄泽均: "多源信息融合的海洋渔船状态监控技术研究与应用", 《中国优秀硕士学位论文全文数据库农业科技辑》, pages 052 - 15 * |
| 黄魁 等: "基于灰色神经网络组合模型的故障预测", 《系统工程与电子技术》, vol. 42, no. 1, pages 238 - 244 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117272118A (en) * | 2023-11-17 | 2023-12-22 | 成都天奥集团有限公司 | T/R component health state prediction method, system, equipment and medium |
| CN117272118B (en) * | 2023-11-17 | 2024-02-13 | 成都天奥集团有限公司 | T/R component health state prediction method, system, equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107231436B (en) | Method and device for scheduling service | |
| EP3644581B1 (en) | Edge-cloud collaboration system for analyzing internet of things data and operating method thereof | |
| CN108268366B (en) | Test case execution method and device | |
| US20190347548A1 (en) | Selecting a neural network architecture for a supervised machine learning problem | |
| US9119086B1 (en) | Evaluating 3G and voice over long term evolution voice quality | |
| CN110598802A (en) | Memory detection model training method, memory detection method and device | |
| CN105095614A (en) | Method and device for updating prediction model | |
| CN103945442A (en) | System anomaly detection method based on linear prediction principle in mobile communication system | |
| CN116070153A (en) | Method, device, equipment and medium for predicting fault parameters of phased array T/R assembly | |
| US20240010100A1 (en) | Processing of status data of a battery for aging estimation | |
| US8214312B2 (en) | System and method for calibrating radio frequency power of communication devices | |
| CN113837596B (en) | Fault determination method and device, electronic equipment and storage medium | |
| CN113672467A (en) | Operation and maintenance early warning method and device, electronic equipment and storage medium | |
| CN106162559A (en) | For estimating equipment and the method for position in a wireless communication system | |
| CN106656368A (en) | Communication system monitoring method and apparatus | |
| Scanzio et al. | Predicting Wi‐Fi link quality through artificial neural networks | |
| US20200213875A1 (en) | Apparatus and method for monitoring performance of network device in wireless communication system | |
| CN107371175A (en) | A kind of self-organizing network fault detection method using cooperation prediction | |
| CN114279554A (en) | Multi-place synchronous self-adaptive performance testing method and system of low-temperature flutter sensor | |
| US11128391B1 (en) | System and method for predicting wireless channel path loss | |
| CN102957572A (en) | Method and device for evaluating performance of system | |
| CN104254083A (en) | Method and device for predicting business hot spots | |
| CN110515752B (en) | Disk equipment service life prediction method and device | |
| CN107688878B (en) | Air Quality Forecast method and device | |
| CN114866438A (en) | Abnormal hidden danger prediction method and system under cloud architecture |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230505 |
|
| RJ01 | Rejection of invention patent application after publication |