CN117560098B - Method and device for predicting radiation performance parameters of radio frequency communication equipment - Google Patents
Method and device for predicting radiation performance parameters of radio frequency communication equipment Download PDFInfo
- Publication number
- CN117560098B CN117560098B CN202410040309.7A CN202410040309A CN117560098B CN 117560098 B CN117560098 B CN 117560098B CN 202410040309 A CN202410040309 A CN 202410040309A CN 117560098 B CN117560098 B CN 117560098B
- Authority
- CN
- China
- Prior art keywords
- training data
- data set
- loss
- deep learning
- learning model
- 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.)
- Active
Links
- 238000004891 communication Methods 0.000 title claims abstract description 105
- 230000005855 radiation Effects 0.000 title claims abstract description 103
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000012549 training Methods 0.000 claims abstract description 358
- 238000013136 deep learning model Methods 0.000 claims abstract description 120
- 238000012545 processing Methods 0.000 claims abstract description 37
- 238000000605 extraction Methods 0.000 claims abstract description 20
- 238000004364 calculation method Methods 0.000 claims abstract description 18
- 230000006870 function Effects 0.000 claims description 26
- 238000004590 computer program Methods 0.000 claims description 20
- 230000005540 biological transmission Effects 0.000 claims description 9
- 238000005457 optimization Methods 0.000 claims description 4
- 230000004927 fusion Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 description 7
- 230000005670 electromagnetic radiation Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003595 spectral effect Effects 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/10—Monitoring; Testing of transmitters
- H04B17/15—Performance testing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/20—Monitoring; Testing of receivers
- H04B17/29—Performance testing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Monitoring And Testing Of Transmission In General (AREA)
Abstract
The disclosure relates to the technical field of communication, and provides a method and a device for predicting radiation performance parameters of radio frequency communication equipment. The method comprises the following steps: inputting each training data in each training data set into a deep learning model, outputting the data characteristics of each training data through a characteristic extraction and processing network, and outputting the radiation performance parameters of each training data through a classification network; calculating the radiation performance parameter of each piece of training data and the predicted result loss between the labels, and calculating the first characteristic contrast loss between the data characteristics of the three pieces of training data in each training data set; and optimizing model parameters of the deep learning model according to the predicted result loss and the first characteristic contrast loss obtained by calculation of each training data set, and predicting radiation performance parameters of various types of radio frequency communication equipment by utilizing the optimized deep learning model. By adopting the technical means, the problem of low radiation performance efficiency of the radio frequency communication equipment in the prior art is solved.
Description
Technical Field
The present disclosure relates to the field of communications technologies, and in particular, to a method and an apparatus for predicting a radiation performance parameter of a radio frequency communication device.
Background
The radio frequency communication device is a device for transmitting information by using a radio frequency technology, and in order to ensure the safety of the device, optimize the performance of the device, evaluate the interference condition of the device, ensure the health of human bodies and the like, the electromagnetic radiation level of the device transmitted through space in the running process needs to be known. The radiation performance of the radio frequency communication device can only be tested by the related electromagnetic tool at present, and the method has low efficiency.
Disclosure of Invention
In view of this, embodiments of the present application provide a method, an apparatus, an electronic device, and a computer readable storage medium for predicting radiation performance parameters of a radio frequency communication device, so as to solve the problem of low radiation performance efficiency of a radio frequency communication device in the prior art.
In a first aspect of embodiments of the present application, a method for predicting a radiation performance parameter of a radio frequency communication device is provided, including: obtaining a training data set, wherein the training data set comprises: the system comprises a plurality of training data sets, a plurality of data transmission units and a plurality of data receiving units, wherein each training data set comprises three pieces of training data related to the same type of radio frequency communication equipment, each piece of training data comprises three pieces of data of the radio frequency communication equipment, namely working state, working frequency and working power, one piece of data in any two pieces of training data in each training data set is different, the other two pieces of data in each training data set are the same, labels of the two pieces of training data in each training data set are the same, and labels of the other piece of training data are different; inputting each training data in each training data set into a deep learning model, outputting the data characteristics of each training data through a characteristic extraction and processing network of the deep learning model, and outputting the radiation performance parameters of each training data through a classification network of the deep learning model; calculating the radiation performance parameter of each piece of training data and the predicted result loss between the labels, and calculating the first characteristic contrast loss between the data characteristics of the three pieces of training data in each training data set; and optimizing model parameters of the deep learning model according to the predicted result loss and the first characteristic contrast loss obtained by calculation of each training data set, and predicting radiation performance parameters of various types of radio frequency communication equipment by utilizing the optimized deep learning model.
In a second aspect of the embodiments of the present application, there is provided an apparatus for predicting a radiation performance parameter of a radio frequency communication device, including: an acquisition module configured to acquire a training data set, wherein the training data set comprises: the system comprises a plurality of training data sets, a plurality of data transmission units and a plurality of data receiving units, wherein each training data set comprises three pieces of training data related to the same type of radio frequency communication equipment, each piece of training data comprises three pieces of data of the radio frequency communication equipment, namely working state, working frequency and working power, one piece of data in any two pieces of training data in each training data set is different, the other two pieces of data in each training data set are the same, labels of the two pieces of training data in each training data set are the same, and labels of the other piece of training data are different; the processing module is configured to input each piece of training data in each training data set into the deep learning model, output the data characteristics of each piece of training data through the characteristic extraction and processing network of the deep learning model, and output the radiation performance parameters of each piece of training data through the classification network of the deep learning model; the calculation module is configured to calculate the radiation performance parameter of each piece of training data and the predicted result loss between the labels, and calculate the first feature contrast loss between the data features of the three pieces of training data in each training data set; and the optimizing module is configured to optimize model parameters of the deep learning model according to the predicted result loss and the first characteristic contrast loss obtained by calculation of each training data set, and predict radiation performance parameters of various types of radio frequency communication equipment by using the optimized deep learning model.
In a third aspect of the embodiments of the present application, there is provided an electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the above method when executing the computer program.
In a fourth aspect of the embodiments of the present application, there is provided a computer readable storage medium storing a computer program which, when executed by a processor, implements the steps of the above method.
Compared with the prior art, the embodiment of the application has the beneficial effects that: obtaining a training data set, wherein the training data set comprises: the system comprises a plurality of training data sets, a plurality of data transmission units and a plurality of data receiving units, wherein each training data set comprises three pieces of training data related to the same type of radio frequency communication equipment, each piece of training data comprises three pieces of data of the radio frequency communication equipment, namely working state, working frequency and working power, one piece of data in any two pieces of training data in each training data set is different, the other two pieces of data in each training data set are the same, labels of the two pieces of training data in each training data set are the same, and labels of the other piece of training data are different; inputting each training data in each training data set into a deep learning model, outputting the data characteristics of each training data through a characteristic extraction and processing network of the deep learning model, and outputting the radiation performance parameters of each training data through a classification network of the deep learning model; calculating the radiation performance parameter of each piece of training data and the predicted result loss between the labels, and calculating the first characteristic contrast loss between the data characteristics of the three pieces of training data in each training data set; and optimizing model parameters of the deep learning model according to the predicted result loss and the first characteristic contrast loss obtained by calculation of each training data set, and predicting radiation performance parameters of various types of radio frequency communication equipment by utilizing the optimized deep learning model. By adopting the technical means, the problem of low radiation performance efficiency of the radio frequency communication equipment in the prior art is solved, and the radiation performance efficiency of the radio frequency communication equipment is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following description will briefly introduce the drawings that are needed in the embodiments or the description of the prior art, it is obvious that the drawings in the following description are only some embodiments of the present disclosure, and other drawings may be obtained according to these drawings without inventive effort for a person of ordinary skill in the art.
Fig. 1 is a flowchart of a method for predicting radiation performance parameters of a radio frequency communication device according to an embodiment of the present application;
fig. 2 is a flowchart of another method for predicting radiation performance parameters of a radio frequency communication device according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of an apparatus for predicting radiation performance parameters of a radio frequency communication device according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system configurations, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to one skilled in the art that the present disclosure may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present disclosure with unnecessary detail.
Fig. 1 is a flowchart of a method for predicting radiation performance parameters of a radio frequency communication device according to an embodiment of the present application. The method of predicting radiation performance parameters of the radio frequency communication device of fig. 1 may be performed by a computer or a server. As shown in fig. 1, the method for predicting radiation performance parameters of a radio frequency communication device includes:
s101, acquiring a training data set, wherein the training data set comprises: the system comprises a plurality of training data sets, a plurality of data transmission units and a plurality of data receiving units, wherein each training data set comprises three pieces of training data related to the same type of radio frequency communication equipment, each piece of training data comprises three pieces of data of the radio frequency communication equipment, namely working state, working frequency and working power, one piece of data in any two pieces of training data in each training data set is different, the other two pieces of data in each training data set are the same, labels of the two pieces of training data in each training data set are the same, and labels of the other piece of training data are different;
s102, inputting each training data in each training data set into a deep learning model, outputting data characteristics of each training data through a characteristic extraction and processing network of the deep learning model, and outputting radiation performance parameters of each training data through a classification network of the deep learning model;
S103, calculating the radiation performance parameter of each piece of training data and the predicted result loss between the labels, and calculating the first characteristic comparison loss between the data characteristics of the three pieces of training data in each training data set;
s104, optimizing model parameters of the deep learning model according to the predicted result loss and the first characteristic contrast loss obtained by calculation of each training data set, and predicting radiation performance parameters of various types of radio frequency communication equipment by utilizing the optimized deep learning model.
Radio frequency communication devices can be classified into radio communication devices, microwave communication devices, radio frequency amplifiers and other radio frequency devices, mixed signal devices and radio frequency sensors and actuators, depending on the type of device. Radio communication apparatus: such devices operate primarily in the radio frequency range, such as broadcast, television, mobile communications, satellite communications, and the like. Electromagnetic radiation from these devices comes primarily from antennas and radio frequency amplifiers; microwave communication device: such devices operate in the microwave frequency range, such as radar, communication satellites, microwave relay stations, and the like. Electromagnetic radiation of microwave communication equipment mainly comes from the antenna, the microwave amplifier and other components; radio frequency amplifiers and other radio frequency devices: such devices include various radio frequency amplifiers, oscillators, frequency converters, etc., which operate in the radio and microwave frequency bands. Electromagnetic radiation from these devices comes mainly from rf output ports and antennas; mixed signal device: such devices include cell phones, cordless phones, bluetooth devices, etc., which operate in the radio and microwave frequency bands and contain both analog and digital signal processing functions. Electromagnetic radiation from these devices comes primarily from antennas, radio frequency amplifiers and digital signal processing parts; a radio frequency sensor and an actuator: such devices include various radio frequency sensors, remote sensors, wireless energy transfer devices, etc., which operate in the radio and microwave frequency bands. Electromagnetic radiation from these devices comes primarily from antennas and radio frequency sensors. The characteristics of the radiation performance parameters of the same type of radio frequency communication device are similar, so that one training data set is three pieces of training data about the same type of radio frequency communication device.
An operational state of a radio frequency communication device comprising: a transmitting state, a receiving state, an idle state, a sleep state, a standby state, a configuration state, and the like. A transmitting state in which the radio frequency communication device transmits radio waves through the antenna to transfer information; a receiving state in which the device captures signals from other transmitting sources; an idle state, in which the device may be in an idle state when it is not performing a transmitting or receiving operation, in which state the device may still be in a ready state, monitoring for possible communication requests; sleep state, in order to save power, the radio frequency communication device may enter a sleep state in which the device shuts down most of its functions, but still is able to respond to certain specific signals or interrupts to wake up the device back into an active state; a standby state, which is a state in which the device is ready to respond to a communication request immediately, but at which time the device does not actively transmit or receive a signal; if the equipment detects some errors or abnormal conditions, such as overheat, abnormal power supply, hardware faults and the like, the equipment can enter the fault state, stop normal work and trigger some protection measures or alarms; a configuration state in which the device may accept external configuration or programming, such as setting parameters of communication frequency, power level, data rate, etc.
The operating frequency and operating power of the radio frequency communication device are the frequencies and powers, respectively, commonly employed by radio frequency communication devices.
One of any two pieces of training data in each training data set is different from the other two pieces of data which are identical, for example, in one training data set: the working states of the first training data and the second training data are different, and the working frequency and the working power of the first training data and the second training data are the same; the working frequencies of the second training data and the third training data are different, and the working states and the working powers of the second training data and the third training data are the same; the working power of the first training data is different from that of the third training data, and the working states and the working frequencies of the first training data and the third training data are the same.
The labels of two pieces of training data in each training data set are the same, and the labels of the other pieces of training data are different, for example, in one training data set: the labels of the first training data and the second training data are the same, and the label of the third training data is different from the labels of the other two training data in the training data set.
The radiation performance parameters include radiation intensity, radiation direction and spectral distribution. Radiation intensity: the amount of radiant energy, typically in decibels (dB), of a device in a particular direction or frequency band is indicated. Radiation direction: indicating the directionality of the radiant energy of the device, i.e. in which directions the radiant energy is mainly concentrated. Spectral distribution: representing the radiant energy distribution of the device at different frequencies.
The deep learning model used in the embodiments of the present application may be any commonly used deep learning model, such as a convolutional neural network, a recurrent neural network, or a long-short-term memory network. An internal network of the deep learning model can be divided into a feature extraction and processing network and a classification network according to the action, wherein the feature extraction and processing network is used for extracting and processing the input features, and the classification network is used for classifying based on the features output by the feature extraction and processing network. In general, the last full-connection layer and the activation layer in a deep learning model are used as classification networks, and the whole network before the classification network is regarded as a feature extraction and processing network.
According to the technical scheme provided by the embodiment of the application, the training data set is obtained, wherein the training data set comprises: the system comprises a plurality of training data sets, a plurality of data transmission units and a plurality of data receiving units, wherein each training data set comprises three pieces of training data related to the same type of radio frequency communication equipment, each piece of training data comprises three pieces of data of the radio frequency communication equipment, namely working state, working frequency and working power, one piece of data in any two pieces of training data in each training data set is different, the other two pieces of data in each training data set are the same, labels of the two pieces of training data in each training data set are the same, and labels of the other piece of training data are different; inputting each training data in each training data set into a deep learning model, outputting the data characteristics of each training data through a characteristic extraction and processing network of the deep learning model, and outputting the radiation performance parameters of each training data through a classification network of the deep learning model; calculating the radiation performance parameter of each piece of training data and the predicted result loss between the labels, and calculating the first characteristic contrast loss between the data characteristics of the three pieces of training data in each training data set; and optimizing model parameters of the deep learning model according to the predicted result loss and the first characteristic contrast loss obtained by calculation of each training data set, and predicting radiation performance parameters of various types of radio frequency communication equipment by utilizing the optimized deep learning model. By adopting the technical means, the problem of low radiation performance efficiency of the radio frequency communication equipment in the prior art is solved, and the radiation performance efficiency of the radio frequency communication equipment is improved.
Further, calculating a predicted outcome loss between the radiation performance parameter and the tag for each piece of training data, and calculating a first feature contrast loss between data features of three pieces of training data in each training data set, including: calculating the radiation performance parameter of each piece of training data and the predicted result loss between the labels through a cross entropy loss function; first feature contrast loss between data features of three pieces of training data in each training data set is calculated through a triplet loss function.
The cross entropy loss function and the triplet loss function are common loss functions and are therefore not described in detail here. Because there are three pieces of training data for one training data set, one for each predicted outcome loss, one for each training data set. Three pieces of training data in each training data set correspond to a first feature contrast loss.
Further, calculating a first feature contrast loss between data features of three pieces of training data in each training data set by a triplet loss function, comprising: taking any piece of training data in each training data set as a target sample, taking the training data which is the same as the label of the target sample in the training data set as a positive sample of the target sample, and taking the training data which is different from the label of the target sample as a negative sample of the target sample; a first feature contrast loss between the data features of the target sample and its positive and negative samples in each training data set is calculated by a triplet loss function.
The three pieces of training data in each training data set correspond to a second feature contrast loss.
Further, optimizing model parameters of the deep learning model according to the predicted result loss and the first feature contrast loss obtained by calculation of each training data set, including: calculating three predicted result losses and a first characteristic comparison loss of each training data set, and carrying out weighted summation to obtain a total loss corresponding to each training data set; and optimizing model parameters of the deep learning model according to the total loss corresponding to each training data set.
Further, after calculating the first feature contrast loss between the data features of the three pieces of training data in each training data set, the method further includes: feature fusion is carried out on the data features of the training data with the same two labels in each training data set, so that the data set features corresponding to each training data set are obtained; taking the labels of the training data with the same labels in the two training data sets as the labels of the training data sets; randomly determining a training data set from a plurality of training data sets as a target data set, randomly determining training data which is the same as the label of the target data set in the plurality of training data sets as a positive sample of the target data set, and randomly determining training data which is different from the label of the target data set as a negative sample of the target data set; calculating a second feature contrast loss between the target data set and the data set features of the positive and negative samples thereof by the triplet loss function; and optimizing model parameters of the deep learning model according to the calculated predicted result loss, the first characteristic comparison loss and the second characteristic comparison loss.
And combining the data characteristics of the training data with the same labels in each training data set to serve as the data set characteristics corresponding to the training data set. It will be appreciated that a plurality of target data sets, as well as positive and negative samples thereof, may be randomly determined from a plurality of training data sets. Each target data set and its positive and negative samples correspond to a second feature contrast loss.
In some embodiments the deep learning model is multi-stage trained: first stage training is carried out on the deep learning model: predicting the radiation performance parameters of each piece of training data by using the deep learning model, calculating the predicted result loss between the radiation performance parameters of each piece of training data and the labels, and optimizing the model parameters of the deep learning model according to the calculated predicted result loss; training the deep learning model in a second stage: processing by using the deep learning model trained in the first stage to obtain the data characteristics of each training data in each training data set, calculating first characteristic comparison loss among the data characteristics of three training data in each training data set, and optimizing model parameters of the deep learning model according to the calculated first characteristic comparison loss; training the deep learning model in a third stage: and processing the deep learning model trained in the second stage to obtain a target data set and data set characteristics of positive samples and negative samples thereof, calculating second characteristic contrast loss between the target data set and the data set characteristics of the positive samples and the negative samples thereof, and optimizing model parameters of the deep learning model according to the calculated second characteristic contrast loss.
The first stage training is conventional classification training. The second stage training is to strengthen the classification of different kinds of data of the same type of equipment by the deep learning model based on the first stage training. The third stage training is to strengthen the classification of data of different types of devices by the deep learning model based on the second stage training. The training method of each stage training is a conventional classification training method.
Fig. 2 is a flowchart of another method for predicting radiation performance parameters of a radio frequency communication device according to an embodiment of the present application. As shown in fig. 2, the method for predicting radiation performance parameters of a radio frequency communication device includes:
s201, after receiving the type, the working state, the working frequency and the working power of the target radio frequency communication equipment to be predicted, inputting the type, the working state, the working frequency and the working power of the target radio frequency communication equipment into an optimized deep learning model, extracting and processing the characteristics of the deep learning model to output the corresponding target data characteristics of the target radio frequency communication equipment through a network, and outputting the target radiation performance parameters of the target radio frequency communication equipment through a classification network of the deep learning model;
S202, acquiring two pieces of historical data of a target radio frequency communication device, wherein the two pieces of historical data comprise the type, the historical working state, the historical working frequency and the historical working power of the target radio frequency communication device and the historical radiation performance parameters, the difference value of the historical radiation performance parameter and the target radiation performance parameter of one piece of historical data is in a preset range, and the difference value of the historical radiation performance parameter and the target radiation performance parameter of the other piece of historical data exceeds the preset range;
s203, inputting the two pieces of history data into an optimized deep learning model, and outputting history data features corresponding to the two pieces of history data through a feature extraction and processing network of the deep learning model;
s204, calculating a third feature contrast loss between the two historical data features and the target data feature;
s205, when the third feature contrast loss is larger than the preset loss, determining a target reward according to the third feature contrast loss, and optimizing model parameters of the deep learning model according to the target reward.
In the embodiment of the application, model parameters of the deep learning model are optimized in an reasoning stage (stage of formal use) of the deep learning model. Embodiments of the present application are similar to reinforcement learning, but differ in that rewards are determined by a third feature contrast loss between historical data features and target data features. The greater the third feature contrast loss, the less the target prize.
And when the third characteristic contrast loss is smaller than the preset loss, taking the target radiation performance parameter as the radiation performance parameter of the target radio frequency communication equipment.
Any combination of the above optional solutions may be adopted to form an optional embodiment of the present application, which is not described herein in detail.
The following are device embodiments of the present disclosure that may be used to perform method embodiments of the present disclosure. For details not disclosed in the embodiments of the apparatus of the present disclosure, please refer to the embodiments of the method of the present disclosure.
Fig. 3 is a schematic diagram of an apparatus for predicting radiation performance parameters of a radio frequency communication device according to an embodiment of the present application. As shown in fig. 3, the apparatus for predicting radiation performance parameters of a radio frequency communication device includes:
an acquisition module 301 configured to acquire a training data set, wherein the training data set comprises: the system comprises a plurality of training data sets, a plurality of data transmission units and a plurality of data receiving units, wherein each training data set comprises three pieces of training data related to the same type of radio frequency communication equipment, each piece of training data comprises three pieces of data of the radio frequency communication equipment, namely working state, working frequency and working power, one piece of data in any two pieces of training data in each training data set is different, the other two pieces of data in each training data set are the same, labels of the two pieces of training data in each training data set are the same, and labels of the other piece of training data are different;
The processing module 302 is configured to input each piece of training data in each training data set into the deep learning model, output the data characteristics of each piece of training data through the characteristic extraction and processing network of the deep learning model, and output the radiation performance parameters of each piece of training data through the classification network of the deep learning model;
a calculation module 303 configured to calculate a predicted outcome loss between the radiation performance parameter and the tag for each piece of training data, and to calculate a first feature contrast loss between data features of the three pieces of training data in each training data set;
the optimizing module 304 is configured to optimize model parameters of the deep learning model according to the predicted result loss and the first feature contrast loss calculated by each training data set, and predict radiation performance parameters of various types of radio frequency communication devices by using the optimized deep learning model.
According to the technical scheme provided by the embodiment of the application, the training data set is obtained, wherein the training data set comprises: the system comprises a plurality of training data sets, a plurality of data transmission units and a plurality of data receiving units, wherein each training data set comprises three pieces of training data related to the same type of radio frequency communication equipment, each piece of training data comprises three pieces of data of the radio frequency communication equipment, namely working state, working frequency and working power, one piece of data in any two pieces of training data in each training data set is different, the other two pieces of data in each training data set are the same, labels of the two pieces of training data in each training data set are the same, and labels of the other piece of training data are different; inputting each training data in each training data set into a deep learning model, outputting the data characteristics of each training data through a characteristic extraction and processing network of the deep learning model, and outputting the radiation performance parameters of each training data through a classification network of the deep learning model; calculating the radiation performance parameter of each piece of training data and the predicted result loss between the labels, and calculating the first characteristic contrast loss between the data characteristics of the three pieces of training data in each training data set; and optimizing model parameters of the deep learning model according to the predicted result loss and the first characteristic contrast loss obtained by calculation of each training data set, and predicting radiation performance parameters of various types of radio frequency communication equipment by utilizing the optimized deep learning model. By adopting the technical means, the problem of low radiation performance efficiency of the radio frequency communication equipment in the prior art is solved, and the radiation performance efficiency of the radio frequency communication equipment is improved.
In some embodiments, the calculation module 303 is further configured to calculate a predicted outcome loss between the tag and the radiation performance parameter of each piece of training data by a cross entropy loss function; first feature contrast loss between data features of three pieces of training data in each training data set is calculated through a triplet loss function.
In some embodiments, the calculation module 303 is further configured to take any piece of training data in each training data set as a target sample, take training data in the training data set that is the same as the label of the target sample as a positive sample of the target sample, and take training data that is different from the label of the target sample as a negative sample of the target sample; a first feature contrast loss between the data features of the target sample and its positive and negative samples in each training data set is calculated by a triplet loss function.
In some embodiments, the optimization module 304 is further configured to calculate three predicted result losses and a first feature comparison loss for each training data set, and perform weighted summation to obtain a total loss corresponding to each training data set; and optimizing model parameters of the deep learning model according to the total loss corresponding to each training data set.
In some embodiments, the optimization module 304 is further configured to perform feature fusion on the data features of the training data with the same two labels in each training data set to obtain the data set features corresponding to each training data set; taking the labels of the training data with the same labels in the two training data sets as the labels of the training data sets; randomly determining a training data set from a plurality of training data sets as a target data set, randomly determining training data which is the same as the label of the target data set in the plurality of training data sets as a positive sample of the target data set, and randomly determining training data which is different from the label of the target data set as a negative sample of the target data set; calculating a second feature contrast loss between the target data set and the data set features of the positive and negative samples thereof by the triplet loss function; and optimizing model parameters of the deep learning model according to the calculated predicted result loss, the first characteristic comparison loss and the second characteristic comparison loss.
In some embodiments, the optimization module 304 is further configured to multi-stage train the deep learning model: first stage training is carried out on the deep learning model: predicting the radiation performance parameters of each piece of training data by using the deep learning model, calculating the predicted result loss between the radiation performance parameters of each piece of training data and the labels, and optimizing the model parameters of the deep learning model according to the calculated predicted result loss; training the deep learning model in a second stage: processing by using the deep learning model trained in the first stage to obtain the data characteristics of each training data in each training data set, calculating first characteristic comparison loss among the data characteristics of three training data in each training data set, and optimizing model parameters of the deep learning model according to the calculated first characteristic comparison loss; training the deep learning model in a third stage: and processing the deep learning model trained in the second stage to obtain a target data set and data set characteristics of positive samples and negative samples thereof, calculating second characteristic contrast loss between the target data set and the data set characteristics of the positive samples and the negative samples thereof, and optimizing model parameters of the deep learning model according to the calculated second characteristic contrast loss.
In some embodiments, the optimizing module 304 is further configured to input the type, the operating state, the operating frequency, and the operating power of the target radio frequency communication device to the optimized deep learning model after receiving the type, the operating state, the operating frequency, and the operating power of the target radio frequency communication device to be predicted, extract and process the characteristics of the deep learning model, output the target data characteristics corresponding to the target radio frequency communication device through the network, and output the target radiation performance parameters of the target radio frequency communication device through the classification network of the deep learning model; acquiring two pieces of historical data of the target radio frequency communication equipment, wherein the two pieces of historical data comprise the type, the historical working state, the historical working frequency and the historical working power of the target radio frequency communication equipment and the historical radiation performance parameters, the difference value of the historical radiation performance parameter and the target radiation performance parameter of one piece of historical data is in a preset range, and the difference value of the historical radiation performance parameter and the target radiation performance parameter of the other piece of historical data exceeds the preset range; inputting the two pieces of history data into an optimized deep learning model, and outputting history data features corresponding to the two pieces of history data through a feature extraction and processing network of the deep learning model; calculating a third feature contrast loss between the two historical data features and the target data feature; and when the third characteristic contrast loss is larger than the preset loss, determining target rewards according to the third characteristic contrast loss, and optimizing model parameters of the deep learning model according to the target rewards.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic of each process, and should not limit the implementation process of the embodiment of the present application in any way.
Fig. 4 is a schematic diagram of an electronic device 4 provided in an embodiment of the present application. As shown in fig. 4, the electronic apparatus 4 of this embodiment includes: a processor 401, a memory 402 and a computer program 403 stored in the memory 402 and executable on the processor 401. The steps of the various method embodiments described above are implemented by processor 401 when executing computer program 403. Alternatively, the processor 401, when executing the computer program 403, performs the functions of the modules/units in the above-described apparatus embodiments.
Illustratively, the computer program 403 may be partitioned into one or more modules/units, which are stored in the memory 402 and executed by the processor 401 to complete the present disclosure. One or more of the modules/units may be a series of computer program instruction segments capable of performing a specific function for describing the execution of the computer program 403 in the electronic device 4.
The electronic device 4 may be a desktop computer, a notebook computer, a palm computer, a cloud server, or the like. The electronic device 4 may include, but is not limited to, a processor 401 and a memory 402. It will be appreciated by those skilled in the art that fig. 4 is merely an example of the electronic device 4 and is not meant to be limiting of the electronic device 4, and may include more or fewer components than shown, or may combine certain components, or different components, e.g., the electronic device may also include an input-output device, a network access device, a bus, etc.
The processor 401 may be a central processing unit (Central Processing Unit, CPU) or other general purpose processor, digital signal processor (Digital Signal Processor, DSP), application specific integrated circuit (Application Specific Integrated Circuit, ASIC), field programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 402 may be an internal storage unit of the electronic device 4, for example, a hard disk or a memory of the electronic device 4. The memory 402 may also be an external storage device of the electronic device 4, for example, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card) or the like, which are provided on the electronic device 4. Further, the memory 402 may also include both internal storage units and external storage devices of the electronic device 4. The memory 402 is used to store computer programs and other programs and data required by the electronic device. The memory 402 may also be used to temporarily store data that has been output or is to be output.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working process of the units and modules in the above system may refer to the corresponding process in the foregoing method embodiment, which is not described herein again.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.
In the embodiments provided in the present disclosure, it should be understood that the disclosed apparatus/electronic device and method may be implemented in other manners. For example, the apparatus/electronic device embodiments described above are merely illustrative, e.g., the division of modules or elements is merely a logical functional division, and there may be additional divisions of actual implementations, multiple elements or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection via interfaces, devices or units, which may be in electrical, mechanical or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present disclosure may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated modules/units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the present disclosure may implement all or part of the flow of the method of the above-described embodiments, or may be implemented by a computer program to instruct related hardware, and the computer program may be stored in a computer readable storage medium, where the computer program, when executed by a processor, may implement the steps of the method embodiments described above. The computer program may comprise computer program code, which may be in source code form, object code form, executable file or in some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth. It should be noted that the content of the computer readable medium can be appropriately increased or decreased according to the requirements of the jurisdiction's jurisdiction and the patent practice, for example, in some jurisdictions, the computer readable medium does not include electrical carrier signals and telecommunication signals according to the jurisdiction and the patent practice.
The above embodiments are merely for illustrating the technical solution of the present disclosure, and are not limiting thereof; although the present disclosure has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the disclosure, and are intended to be included in the scope of the present disclosure.
Claims (6)
1. A method of predicting a radiation performance parameter of a radio frequency communication device, comprising:
obtaining a training data set, wherein the training data set comprises: the system comprises a plurality of training data sets, a plurality of data transmission units and a plurality of data receiving units, wherein each training data set comprises three pieces of training data related to the same type of radio frequency communication equipment, each piece of training data comprises three pieces of data of the radio frequency communication equipment, namely working state, working frequency and working power, one piece of data in any two pieces of training data in each training data set is different, the other two pieces of data are the same, labels of the two pieces of training data in each training data set are the same, and labels of the other pieces of training data are different;
Inputting each training data in each training data set into a deep learning model, outputting the data characteristics of each training data through a characteristic extraction and processing network of the deep learning model, and outputting the radiation performance parameters of each training data through a classification network of the deep learning model;
calculating the radiation performance parameter of each piece of training data and the predicted result loss between the labels, and calculating the first characteristic contrast loss between the data characteristics of the three pieces of training data in each training data set;
optimizing model parameters of the deep learning model according to the predicted result loss and the first characteristic contrast loss obtained by calculation of each training data set, and predicting radiation performance parameters of various types of radio frequency communication equipment by utilizing the optimized deep learning model;
calculating a predicted result loss between the radiation performance parameter and the label of each piece of training data, and calculating a first feature comparison loss between data features of three pieces of training data in each training data set, wherein the method comprises the following steps: calculating the radiation performance parameter of each piece of training data and the predicted result loss between the labels through a cross entropy loss function; calculating first feature contrast loss among data features of three pieces of training data in each training data set through a triplet loss function;
Wherein, calculate the first characteristic contrast loss between the data characteristic of three pieces of training data in each training data group through the triplet loss function, include: taking any piece of training data in each training data set as a target sample, taking training data which are the same as the label of the target sample in the training data set as a positive sample of the target sample, and taking training data which are different from the label of the target sample as a negative sample of the target sample; calculating a first feature contrast loss between the data features of the target sample and the positive and negative samples thereof in each training data set through a triplet loss function;
the model parameters of the deep learning model are optimized according to the predicted result loss and the first characteristic contrast loss obtained by calculation of each training data set, and the model parameters comprise: calculating three predicted result losses and a first characteristic comparison loss of each training data set, and carrying out weighted summation to obtain a total loss corresponding to each training data set; optimizing model parameters of the deep learning model according to the total loss corresponding to each training data set;
wherein predicting radiation performance parameters of various types of radio frequency communication devices by using the optimized deep learning model comprises: after the type, the working state, the working frequency and the working power of the target radio frequency communication equipment to be predicted are received, inputting the type, the working state, the working frequency and the working power of the target radio frequency communication equipment into an optimized deep learning model, outputting target data characteristics corresponding to the target radio frequency communication equipment through a characteristic extraction and processing network of the deep learning model, and outputting target radiation performance parameters of the target radio frequency communication equipment through a classification network of the deep learning model; acquiring two pieces of historical data of the target radio frequency communication equipment, wherein the two pieces of historical data comprise the type, the historical working state, the historical working frequency and the historical working power of the target radio frequency communication equipment and the historical radiation performance parameters, the difference value of the historical radiation performance parameter of one piece of historical data and the target radiation performance parameter is in a preset range, and the difference value of the historical radiation performance parameter of the other piece of historical data and the target radiation performance parameter exceeds the preset range; inputting the two pieces of history data into an optimized deep learning model, and outputting history data features corresponding to the two pieces of history data through a feature extraction and processing network of the deep learning model; calculating a third feature contrast loss between the two historical data features and the target data feature; and when the third characteristic comparison loss is larger than a preset loss, determining a target reward according to the third characteristic comparison loss, and optimizing model parameters of the deep learning model according to the target reward.
2. The method of claim 1, wherein after calculating the first feature contrast loss between the data features of the three pieces of training data in each training data set, the method further comprises:
feature fusion is carried out on the data features of the training data with the same two labels in each training data set, so that the data set features corresponding to each training data set are obtained;
taking the labels of the training data with the same labels in the two training data sets as the labels of the training data sets;
randomly determining a training data set from a plurality of training data sets as a target data set, randomly determining training data which is the same as the label of the target data set in the plurality of training data sets as a positive sample of the target data set, and randomly determining training data which is different from the label of the target data set as a negative sample of the target data set;
calculating a second feature contrast loss between the target data set and the data set features of the positive and negative samples thereof through a triplet loss function;
and optimizing model parameters of the deep learning model according to the calculated predicted result loss, the first characteristic contrast loss and the second characteristic contrast loss.
3. The method according to claim 1, wherein the method further comprises:
performing multi-stage training on the deep learning model:
performing first-stage training on the deep learning model: predicting the radiation performance parameters of each piece of training data by using the deep learning model, calculating the predicted result loss between the radiation performance parameters of each piece of training data and the labels, and optimizing the model parameters of the deep learning model according to the calculated predicted result loss;
training the deep learning model in a second stage: processing the deep learning model after training in the first stage to obtain the data characteristics of each training data in each training data set, calculating first characteristic comparison loss among the data characteristics of three training data in each training data set, and optimizing model parameters of the deep learning model according to the calculated first characteristic comparison loss;
and training the deep learning model in a third stage: and processing the deep learning model trained in the second stage to obtain a target data set and data set characteristics of positive samples and negative samples thereof, calculating second characteristic contrast loss between the target data set and the data set characteristics of the positive samples and the negative samples thereof, and optimizing model parameters of the deep learning model according to the calculated second characteristic contrast loss.
4. An apparatus for predicting a radiation performance parameter of a radio frequency communication device, comprising:
an acquisition module configured to acquire a training data set, wherein the training data set comprises: the system comprises a plurality of training data sets, a plurality of data transmission units and a plurality of data receiving units, wherein each training data set comprises three pieces of training data related to the same type of radio frequency communication equipment, each piece of training data comprises three pieces of data of the radio frequency communication equipment, namely working state, working frequency and working power, one piece of data in any two pieces of training data in each training data set is different, the other two pieces of data are the same, labels of the two pieces of training data in each training data set are the same, and labels of the other pieces of training data are different;
the processing module is configured to input each piece of training data in each training data set into a deep learning model, output the data characteristics of each piece of training data through a characteristic extraction and processing network of the deep learning model, and output the radiation performance parameters of each piece of training data through a classification network of the deep learning model;
the calculation module is configured to calculate the radiation performance parameter of each piece of training data and the predicted result loss between the labels, and calculate the first feature contrast loss between the data features of the three pieces of training data in each training data set;
The optimizing module is configured to optimize model parameters of the deep learning model according to the predicted result loss and the first characteristic contrast loss obtained by calculation of each training data set, and the optimized deep learning model is utilized to predict radiation performance parameters of various types of radio frequency communication equipment;
the calculation module is further configured to calculate a predicted outcome loss between the tag and the radiation performance parameter of each piece of training data by a cross entropy loss function; calculating first feature contrast loss among data features of three pieces of training data in each training data set through a triplet loss function;
the calculation module is further configured to take any piece of training data in each training data set as a target sample, take training data which is the same as the label of the target sample in the training data set as a positive sample of the target sample, and take training data which is different from the label of the target sample as a negative sample of the target sample; calculating a first feature contrast loss between the data features of the target sample and the positive and negative samples thereof in each training data set through a triplet loss function;
the optimization module is further configured to calculate three predicted result losses and a first characteristic comparison loss for each training data set, and perform weighted summation to obtain a total loss corresponding to each training data set; optimizing model parameters of the deep learning model according to the total loss corresponding to each training data set;
The optimizing module is further configured to input the type, the working state, the working frequency and the working power of the target radio frequency communication equipment to be predicted into an optimized deep learning model after receiving the type, the working state, the working frequency and the working power of the target radio frequency communication equipment, output target data characteristics corresponding to the target radio frequency communication equipment through a characteristic extraction and processing network of the deep learning model, and output target radiation performance parameters of the target radio frequency communication equipment through a classification network of the deep learning model; acquiring two pieces of historical data of the target radio frequency communication equipment, wherein the two pieces of historical data comprise the type, the historical working state, the historical working frequency and the historical working power of the target radio frequency communication equipment and the historical radiation performance parameters, the difference value of the historical radiation performance parameter of one piece of historical data and the target radiation performance parameter is in a preset range, and the difference value of the historical radiation performance parameter of the other piece of historical data and the target radiation performance parameter exceeds the preset range; inputting the two pieces of history data into an optimized deep learning model, and outputting history data features corresponding to the two pieces of history data through a feature extraction and processing network of the deep learning model; calculating a third feature contrast loss between the two historical data features and the target data feature; and when the third characteristic comparison loss is larger than a preset loss, determining a target reward according to the third characteristic comparison loss, and optimizing model parameters of the deep learning model according to the target reward.
5. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of claims 1 to 3 when the computer program is executed.
6. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the method according to any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410040309.7A CN117560098B (en) | 2024-01-11 | 2024-01-11 | Method and device for predicting radiation performance parameters of radio frequency communication equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410040309.7A CN117560098B (en) | 2024-01-11 | 2024-01-11 | Method and device for predicting radiation performance parameters of radio frequency communication equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117560098A CN117560098A (en) | 2024-02-13 |
| CN117560098B true CN117560098B (en) | 2024-04-02 |
Family
ID=89813253
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410040309.7A Active CN117560098B (en) | 2024-01-11 | 2024-01-11 | Method and device for predicting radiation performance parameters of radio frequency communication equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117560098B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020037055A1 (en) * | 2018-08-15 | 2020-02-20 | View, Inc. | Control methods and systems using external 3d modeling and neural networks |
| CN114692665A (en) * | 2020-12-25 | 2022-07-01 | 西南电子技术研究所（中国电子科技集团公司第十研究所） | Radiation source open set individual identification method based on metric learning |
| CN115378518A (en) * | 2022-09-19 | 2022-11-22 | 深圳市中承科技有限公司 | Radio frequency communication equipment space radiation testing system and method based on deep learning |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11651550B2 (en) * | 2020-09-02 | 2023-05-16 | Treadstone Media Labs Private Limited | Artificial intelligence based methods and systems for generating 3-Dimensional model from 2-Dimensional humanoid sketches |
-
2024
- 2024-01-11 CN CN202410040309.7A patent/CN117560098B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020037055A1 (en) * | 2018-08-15 | 2020-02-20 | View, Inc. | Control methods and systems using external 3d modeling and neural networks |
| CN114692665A (en) * | 2020-12-25 | 2022-07-01 | 西南电子技术研究所（中国电子科技集团公司第十研究所） | Radiation source open set individual identification method based on metric learning |
| CN115378518A (en) * | 2022-09-19 | 2022-11-22 | 深圳市中承科技有限公司 | Radio frequency communication equipment space radiation testing system and method based on deep learning |
Non-Patent Citations (2)
| Title |
|---|
| 全智.基于深度学习的射频电路空间辐射测试系统.仪器仪表学报.2022,第43卷(第12期),全文. * |
| 基于深度学习的射频电路空间辐射测试系统;全智;仪器仪表学报;20221231;第43卷(第12期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117560098A (en) | 2024-02-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110926782A (en) | Circuit breaker fault type judgment method and device, electronic equipment and storage medium | |
| US11039403B2 (en) | Transmission power regulation of antennas | |
| CN109963325B (en) | Positioning method, device and equipment based on base station | |
| CN115103385B (en) | Millimeter wave communication system and related test method | |
| Arjona et al. | Fast fuzzy anti‐collision protocol for the RFID standard EPC Gen‐2 | |
| CN117560098B (en) | Method and device for predicting radiation performance parameters of radio frequency communication equipment | |
| CN110022563B (en) | Method and device for adjusting multi-carrier same coverage | |
| EP2774424B1 (en) | A method of minimizing power consumption during operation of a battery operated mobile wireless information device | |
| Ali et al. | Effect of spectrum sensing and transmission duration on spectrum hole utilisation in cognitive radio networks | |
| Hanafy et al. | Rakeness with block sparse Bayesian learning for efficient ZigBee‐based EEG telemonitoring | |
| CN109117020B (en) | Positioning method and device of touch position, storage medium and electronic device | |
| Abdelfattah et al. | Optimal sensing energy and sensing interval in cognitive radio networks with energy harvesting | |
| CN112383660B (en) | Throughput rate testing method and device of intelligent terminal, storage medium and terminal | |
| CN111565431B (en) | Relay selection method and device of SWIPT cognitive radio network based on neural network | |
| Ni et al. | Optimization of time-switching energy harvesting receivers over multiple transmission blocks | |
| CN109286972B (en) | Wireless communication method, system, equipment and computer readable storage medium | |
| CN113139563A (en) | Optimization method and device of image classification model | |
| CN114828190B (en) | Method and device for controlling transmitting power, electronic equipment and storage medium | |
| CN114614926B (en) | Simulation test method and device of communication system and electronic equipment | |
| EP4155778A1 (en) | Selective cellular interference mitigation for gnss | |
| CN116056199A (en) | System and method for configuring transmit power levels based on body proximity | |
| CN115314134A (en) | Wi-Fi signal self-adaptive control method, system and mobile terminal | |
| CN113853008A (en) | Method for reducing energy consumption of wireless access point | |
| CN115707078A (en) | Method and device for reporting P-MPR (Peer-to-Peer message) and terminal equipment | |
| CN115022946A (en) | Radio frequency power consumption optimization method and device and electronic equipment |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |