CN110909463B - Active control and protection method and system for high-power millimeter wave gyrotron traveling wave tube - Google Patents
Active control and protection method and system for high-power millimeter wave gyrotron traveling wave tube Download PDFInfo
- Publication number
- CN110909463B CN110909463B CN201911113360.1A CN201911113360A CN110909463B CN 110909463 B CN110909463 B CN 110909463B CN 201911113360 A CN201911113360 A CN 201911113360A CN 110909463 B CN110909463 B CN 110909463B
- Authority
- CN
- China
- Prior art keywords
- data
- ignition
- neural network
- module
- prediction 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
Images
Classifications
-
- 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
- G06N3/045—Combinations of networks
-
- 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
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01J—ELECTRIC DISCHARGE TUBES OR DISCHARGE LAMPS
- H01J25/00—Transit-time tubes, e.g. klystrons, travelling-wave tubes, magnetrons
- H01J25/34—Travelling-wave tubes; Tubes in which a travelling wave is simulated at spaced gaps
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Ignition Installations For Internal Combustion Engines (AREA)
Abstract
The invention belongs to the technical field of high-power millimeter waves, and particularly provides an active control and protection method and system of a high-power millimeter wave gyrotron traveling wave tube based on neural network prediction, which are used for overcoming the defect of passive control and protection of the existing automatic test system. According to the method, the ignition label is added to historical sample data, a neural network prediction model is built and trained, the ignition label prediction is carried out on the test data collected in real time through the prediction model, and the predicted value of the ignition label is continuous Th within a time period T1The number of times of 1 or the predicted value of the ignition tag of 1 is greater than Th2And the automatic control basic control and protection module adopts emergency turn-off treatment to realize active control and protection of automatic test of the high-power millimeter wave gyrotron traveling wave tube, and can effectively reduce the ignition times of the device, thereby improving the ignition protection safety of the device, reducing the occurrence rate of the event of damaging the gyrotron traveling wave tube due to ignition and having good economic effect.
Description
Technical Field
The invention belongs to the technical field of high-power millimeter waves, and relates to an automatic test system for a high-power millimeter wave gyrotron traveling wave tube; the active control and protection method and system for the high-power millimeter wave gyrotron traveling wave tube based on the neural network prediction are used for achieving prediction of whether the device is ignited or not in the current operation state and achieving active control and protection of the device through control over the control and protection module.
Background
The high-power millimeter wave gyrotron traveling wave tube has wide application in the fields of national defense, scientific research, civil communication and the like, and has the advantages of high power, wide frequency band and high gain. Generally, in the test or normal operation of the device, when the voltage applied to the vacuum device exceeds a certain value, the phenomenon of sparking or high-voltage breakdown occurs, the sparking is that electric sparks with certain colors are burst between electrodes, similar to electric discharge, and the sound of the electric discharge can be heard at the same time of sparking, wherein the sound is formed by instant air discharge of sparking. Most of the gas discharged by ignition is absorbed by electrodes and other gas absorbing materials in the tube, the rest part forms plasma discharge with larger current density between the electrodes, when the current density is high to a certain degree, the plasma discharge can cause short circuit breakdown on the electrodes, thus causing serious damage or even scrapping of devices and generating economic loss; meanwhile, the vacuum degree in the device can be reduced by multiple times of ignition, and the performance of the device is influenced; therefore, the device is prevented from being in a sparking state for a long time, and when sparking occurs, timely alarming and power-off processing are required. The development cycle of the electric vacuum device is long, and the cost is high, so that the control and protection system is very important.
A control protection system in the existing automatic test system is passive control protection, and is used for judging whether parameters exceed a preset threshold value or not according to real-time acquisition of device parameters, and when the parameters exceed the threshold value, the device is considered to have abnormal conditions such as ignition and the like and is powered off. Because the reasonable setting of the threshold requires certain experience, the parameter acquisition of the device equipment can be delayed to a certain extent, and the control and protection processing mode can not take processing measures before the device is ignited, and can find and take measures only after the device is ignited for a period of time.
Based on the method, the invention provides an active control and protection method and system of a high-power millimeter wave gyrotron traveling wave tube based on neural network prediction.
Disclosure of Invention
The invention aims to overcome the defects of passive control and protection of the existing automatic test system in the background art, and provides an active control and protection method and system with learning capacity, so as to realize active control and protection of a high-power millimeter wave gyrotron traveling wave tube and reduce damage to devices caused by fire striking.
In order to achieve the purpose, the invention adopts the technical scheme that:
an active control and protection method for a high-power millimeter wave gyrotron traveling wave tube comprises the following steps:
s1, establishing a neural network prediction model;
s11, collecting and establishing a neural network prediction model training sample set;
the training sample data comprises: magnetic field current (a), compensation magnetic field current (a), cathode voltage (KV), cathode current (a), titanium pump current (nA), ignition tag: the ignition state is 1, and the non-ignition state is 0; the ignition tag is used for marking whether the current state is ignited or not;
setting sampling frequency, and sampling historical data to obtain training sample data; in the sampling process, the ignition labels corresponding to the first Q (Q is more than or equal to 3 and less than or equal to 5) moments when the ignition occurs are marked as an ignition state 1;
s12, establishing a neural network prediction model by a BP neural network method according to the training sample set;
adopting a BP neural network, wherein the number N of input layer nodes is equal to 5, the number L of output layer nodes is equal to 1, and the initial value of the number M of hidden layer nodes is 3; setting a Loss function Loss as a mean square error and training times nb _ epoch, and training a BP neural network according to training sample data to obtain a neural network prediction model;
s2, predicting whether the current state of the device is subjected to ignition or not through a neural network prediction model, and whether warning is needed or not and corresponding processing is adopted;
s21, acquiring working state data of the device in real time, storing the working state data in a database, and inputting the acquired data of the magnetic field current (A), the compensation magnetic field current (A), the cathode voltage (KV), the cathode current (A) and the titanium pump current (nA) into a neural network prediction model to obtain a predicted value of the ignition tag corresponding to the real-time state;
s22, in the time period T, when the predicted value of the ignition label is continuous Th1The number of times of 1 or the predicted value of the ignition tag of 1 is greater than Th2When so, a warning is issued and emergency shutdown processing is taken.
In step S22, the threshold Th1Threshold value Th2And the preset time period T can be set according to the actual application environment.
Further, the active control and protection method further comprises the following steps:
and S3, taking the data of the magnetic field current (A), the compensation magnetic field current (A), the cathode voltage (KV), the cathode current (A) and the titanium pump current (nA) obtained in the step S2 as sample data, adding ignition labels according to the real ignition state, marking the ignition labels corresponding to the first Q moments at the ignition moment as the ignition state 1 to obtain new training samples, adding the new training samples into a training sample set for training a neural network prediction model next time, and correcting the neural network prediction model.
An active control and protection system of a high-power millimeter wave gyrotron traveling wave tube comprises: the system comprises a data acquisition module, a data storage module, a data preprocessing module, a neural network prediction module, a remote control module and a basic control and protection module; wherein:
the data acquisition module is used for acquiring sample data required by establishing the neural network prediction model, and comprises: acquiring data of magnetic field current (A), compensation magnetic field current (A), cathode voltage (KV), cathode current (A), titanium pump current (nA) and current waveform and frequency spectrum data; it should be noted that the waveform and spectrum data are used to determine whether the device is in a sparking state;
the data preprocessing module is used for preprocessing the original data acquired by the data acquisition module, and comprises: converting data format, merging data, removing data duplicate and removing abnormal value;
the data storage module is in a database form and is used for storing the original data acquired by the data acquisition module and the data preprocessed by the data preprocessing module;
the neural network prediction module is connected with the data preprocessing module, preprocessed data are input into the neural network prediction model, and the neural network prediction model outputs a predicted value of the ignition tag;
the remote control module is positioned at the client, and in a time period T, when the predicted value of the ignition tag is continuous Th1The number of times of 1 or the predicted value of the ignition tag of 1 is greater than Th2When the system is used, a warning is sent out, and an instruction is sent out to the basic control and protection module;
the basic control and protection module is used for realizing passive control and protection and active control and protection operation; wherein, the active control is: after receiving a remote control module instruction, carrying out emergency shutdown processing on the data acquisition module; the passive control is as follows: and when the data value acquired by the data acquisition module exceeds a set threshold value, carrying out emergency shutdown processing on the acquisition module.
The working principle of the invention is as follows:
in the invention, specific historical data is selected, an ignition label (1 for ignition and 0 for no ignition) for judging whether the device in a corresponding state is ignited or not is added, the first Q pieces of data in the actual ignition state are all marked as the ignition state 1, the data after the label is added are used as sample data, a neural network prediction model is established by a BP neural network method, namely the neural network extracts the characteristics of state parameters before ignition, and whether the device works and is ignited or not can be predicted according to a real-time input state. When the neural network prediction model predicts that the ignition label in the current state is 1, true ignition is not necessarily performed, but if the predicted ignition labels are all continuously 1 or the predicted ignition labels exceed a certain number of 1 within a preset time length, the device is reasonably believed to be ignited at a next high probability, a warning is given out, and emergency shutdown processing is performed; therefore, early warning and active control and protection before ignition are realized.
In conclusion, the beneficial effects of the invention are as follows:
according to the method, the ignition label is added to historical sample data, a neural network prediction model is built and trained, the ignition label prediction is carried out on the test data collected in real time through the prediction model, and the predicted value of the ignition label is continuous Th within a time period T1The number of times of 1 or the predicted value of the ignition tag of 1 is greater than Th2And the automatic control basic control and protection module adopts emergency turn-off treatment to realize active control and protection of automatic test of the high-power millimeter wave gyrotron traveling wave tube, and can effectively reduce the ignition times of the device, thereby improving the ignition protection safety of the device, reducing the occurrence rate of the event of damaging the gyrotron traveling wave tube due to ignition and having good economic effect.
Drawings
Fig. 1 is a block diagram of an active control and protection system of a high-power millimeter wave gyrotron traveling wave tube according to the present invention.
FIG. 2 is a block diagram illustrating a neural network prediction model according to an embodiment of the present invention.
Fig. 3 is a diagram of a BP neural network structure in the embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail with reference to the following embodiments and the accompanying drawings.
Example 1
The embodiment provides an active control and protection method of a high-power millimeter wave gyrotron traveling wave tube based on neural network prediction, which comprises the following steps:
s1, establishing a neural network prediction model; the method specifically comprises the following steps:
s11, collecting a sample data set required by establishing a neural network prediction model;
the required sample data includes: magnetic field current (a), compensation magnetic field current (a), cathode voltage (KV), cathode current (a), titanium pump current (nA), ignition tag: 1 is ignited and 0 is not ignited; the ignition tag is used for marking whether the current state is ignited or not;
furthermore, considering the acquisition delay of data during actual sparking and the requirement for reducing the sparking frequency of the device as much as possible, labels corresponding to the first 5 states (the sampling rate of actual samples is 0.5 second/time, namely the data in the first 2.5 seconds) at the actual sparking moment are marked as sparking state 1; thus, when the ignition label in the current state is predicted to be 1, true ignition is not necessarily achieved, but if the predicted ignition labels are all continuously 1 or the number of the predicted ignition labels exceeds a certain number of 1 within a certain time period, the device is reasonably believed to be ignited at a next high probability, so that warning needs to be given out and whether emergency shutdown processing is needed or not is judged according to the prediction result;
step S12, establishing a neural network prediction model by a BP neural network method according to the sample data;
specifically, a BP neural network (Back Propagation network) is adopted in the invention, the BP neural network is composed of nonlinear transfer function neurons and can learn and store a large amount of input-output mode mapping relations, the learning rule of the BP neural network is to use a gradient descent method and continuously adjust the connection weight of the network through Back Propagation so as to minimize the loss function of the neural network;
number of input layer nodes N: selecting according to the number of attributes of the sample; the input variables in the invention are: the input layer is determined to be 5 nodes because of the magnetic field current (A), the compensation magnetic field current (A), the cathode voltage (KV), the cathode current (A) and the titanium pump current (nA);
number of output layer nodes L: depending on the number of predicted nodes; the output variables of the invention are: the label of striking sparks (striking sparks is 1, not striking sparks is 0), so that the output layer is determined to be 1 node;
number of hidden layer nodes M: there are generally three empirical formulas:
in this embodiment, the number N of input layer nodes is 5, and the number L of output layer nodes is 1, so that the number M of hidden layer nodes is 3 as an initial value; the number of the neural network layers is simply 3, so that the structure of the neural network is shown in FIG. 3;
here, the number of hidden layer nodes of the neural network can be dynamically adjusted according to the prediction result, and the prediction result can be dynamically adjusted according to the situation according to the number of different hidden layer nodes;
the Loss function Loss of the model is then chosen to be "mean _ squared _ error", i.e. the mean squared error:
wherein, YiFor the value of the ignition tag in the sample,
the network prediction value is obtained, and n is the number of samples;
selecting an optimization mode as 'adam', namely adaptive moment estimation, and dynamically adjusting the learning rate of each parameter by using first moment estimation and second moment estimation of the gradient;
then setting the training times nb _ epoch;
inputting the sample data collected in the step S11 into the constructed neural network structure, and training to obtain a trained neural network model;
s2, predicting whether the current state of the device is subjected to ignition or not through a neural network prediction model, and whether warning is needed or not and controlling a basic control and protection module to take corresponding processing or not, wherein the process is shown in figure 2; the method specifically comprises the following steps:
s21, acquiring the working state of a device in real time, putting the acquired data on a server, and inputting the acquired data of the magnetic field current (A), the compensation magnetic field current (A), the cathode voltage (KV), the cathode current (A) and the titanium pump current (nA) into a trained neural network prediction model to obtain a predicted value of whether the device corresponding to the device in the real-time state is a fire label;
in step S22, since the first 5 pieces of data in the actual ignition state are all marked as ignition state 1 in the sample data, when a single 1 is predicted to appear, the actual ignition is performed certainly, but if the predicted ignition tag value appears to be 1 or exceeds a certain number of 1 within a certain time period T, a warning is issued and whether emergency shutdown processing is performed is determined according to the number of predicted ignition tags 1.
Further, the active control and protection method further comprises the following steps:
step S3, using the data of the magnetic field current (A), the compensation magnetic field current (A), the cathode voltage (KV), the cathode current (A) and the titanium pump current (nA) obtained in the step S2 as sample data, and adding ignition label data according to whether the actual ignition is performed, and correcting the neural network prediction model;
specifically, in each test, the process data of each state parameter of the device operation is acquired by a data acquisition module, stored in an original database in the database, added with label data of whether to strike fire or not to the original data, programmed and controlled, and when each actual striking fire occurs, labels corresponding to the first 5 states at the actual striking fire occurrence time are all marked as a striking fire state 1 (the sampling rate of the actual sample is 0.5 second/time, namely the data in the first 2.5 seconds) and are used as samples for next prediction model training. With the operation of an automatic testing system, model training samples are continuously increased, a prediction model is continuously corrected, the capability of continuously improving and improving prediction precision is realized, the self-learning capability is realized, whether the device is ignited in the next time or not is predicted according to a mathematical model, early warning information can be sent out before actual ignition occurs, and if necessary (the number of the predicted results in a certain time is 1 and exceeds a certain threshold value), the basic control and protection module is automatically controlled to be switched off emergently, so that the active control and protection of the automatic test of the high-power millimeter wave gyrotron traveling wave tube are realized, the ignition frequency of the device can be effectively reduced, the safety of the ignition protection of the device is improved, the occurrence rate of the event that the gyrotron traveling wave tube is damaged due to ignition is reduced, and the good economic effect is realized.
Example 2
On the basis of embodiment 1, the present invention provides an active control and protection system for a high-power millimeter wave gyrotron traveling wave tube, as shown in fig. 1, including:
the system comprises a data acquisition module, a data storage module, a data preprocessing module, a neural network prediction module, a remote control module and a basic control and protection module; wherein:
the data acquisition module acquires sample data required for establishing a neural network prediction model, wherein the sample data comprises magnetic field current (A), compensation magnetic field current (A), cathode voltage (KV), cathode current (A), titanium pump current (nA) data, current waveform acquisition, frequency spectrum data acquisition and the like; whether the device is ignited or not is related to the current waveform and spectrum data besides the first 5 attribute values, so that the waveform and spectrum data need to be collected in more comprehensive analysis;
the basic control and protection module is connected with the data acquisition module and mainly realizes two functions: when the data acquisition module finds that the device actually has abnormal ignition, namely the acquired data value exceeds a set threshold value, the data acquisition module is subjected to emergency shutdown processing, and the process belongs to passive control; when the data is predicted to generate abnormal ignition in a period of time by the neural network prediction module in the current state, the remote module sends an instruction to control the basic control and protection module and carry out emergency shutdown processing on the acquisition module, which belongs to active control and protection;
the data storage module is in a database form and is used for storing the acquired test data and the data processed by the data preprocessing module;
specifically, in each test, the process data of each state parameter of the device operation is acquired by a data acquisition module, stored in an original database in a storage module database, added with tag data of whether to strike fire or not, programmed and controlled, and when each actual striking fire happens, tags corresponding to the first 5 states at the actual striking fire moment are all marked as a striking fire state 1 (the sampling rate of the actual samples is 0.5 second/time, namely the data in the first 2.5 seconds) and used as samples for next prediction model training;
the data preprocessing module completes preprocessing of the acquired original data: the method comprises the steps of data format conversion, data combination, data duplication removal, abnormal value removal and the like, and the processed data are stored in a database again;
the neural network prediction module is connected with the data preprocessing module and is suitable for establishing a neural network prediction model according to sample data and the data of whether the device ignites the label value or not, the data uploaded by the data acquisition module is processed to be used as test data and used as the input of the neural network prediction model, and the prediction about whether the system is ignited or not when the system is operated at the current state is obtained;
the remote control module is positioned at the client, and when the neural network prediction module predicts that the current state is more likely to cause ignition, the corresponding warning is sent out, and the control basic control and protection module is used for performing emergency shutdown processing;
specifically, the test data collected in real time is predicted through the prediction model, when the prediction result is 1 (ignition), the device is not actually ignited, and when the predicted ignition labels are all continuously 1 or have more than a certain number of 1 in a preset time period, an instruction is sent out to control the basic control and protection module to adopt emergency shutdown processing.
While the invention has been described with reference to specific embodiments, any feature disclosed in this specification may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise; all of the disclosed features, or all of the method or process steps, may be combined in any combination, except mutually exclusive features and/or steps.
Claims (3)
1. An active control and protection method for a high-power millimeter wave gyrotron traveling wave tube comprises the following steps:
step S1, establishing a neural network prediction model;
step S11, collecting and establishing a neural network prediction model training sample set;
the training sample data comprises: magnetic field current (a), compensation magnetic field current (a), cathode voltage (KV), cathode current (a), titanium pump current (nA), ignition tag: the ignition state is 1, and the non-ignition state is 0; the ignition tag is used for marking whether the current state is ignited or not;
setting sampling frequency, and sampling historical data to obtain training sample data; in the sampling process, before the ignition moment occursQThe ignition labels corresponding to all the moments are marked as the ignition state 1, wherein the number of the ignition labels is not less than 3Q≤5；
Step S12, establishing a neural network prediction model by a BP neural network method according to the training sample set;
using BP neural network, in which the number of nodes of the input layerNNumber of output layer nodes =5L=1, number of hidden layer nodesMThe initial value is 3; setting a loss functionLossTraining the BP neural network according to training sample data to obtain a neural network prediction model, wherein the training times nb _ epoch are mean square errors;
step S2, predicting whether the current state of the device will strike fire or not through the neural network prediction model, and whether warning is needed or not and corresponding processing is adopted;
step S21, acquiring working state data of the device in real time, storing the working state data in a database, inputting the acquired data of the magnetic field current (A), the compensation magnetic field current (A), the cathode voltage (KV), the cathode current (A) and the titanium pump current (nA) into a neural network prediction model, and acquiring a predicted value of the ignition label corresponding to the real-time state;
step S22 time periodTWhen the predicted value of the ignition label is continuousTh 1The number of times of the order of 1 or the predicted value of the ignition tag of 1 is greater thanTh 2When so, a warning is issued and emergency shutdown processing is taken.
2. The active control and protection method for the high-power millimeter wave gyrotron traveling wave tube according to claim 1, wherein the active control and protection method further comprises:
step S3, the magnetic field current (A), the compensation magnetic field current (A), the cathode voltage (KV) and the cathode obtained in the step S2Taking data of current (A) and titanium pump current (nA) as sample data, adding a sparking tag according to the real sparking state, and simultaneously adding the data before the sparking momentQAnd marking the ignition labels corresponding to each moment as the ignition state 1 to obtain new training samples, and adding the new training samples into the training sample set for training the neural network prediction model next time to correct the neural network prediction model.
3. An active control and protection system of a high-power millimeter wave gyrotron traveling wave tube comprises: the system comprises a data acquisition module, a data storage module, a data preprocessing module, a neural network prediction module, a remote control module and a basic control and protection module; wherein:
the data acquisition module is used for acquiring sample data required by establishing the neural network prediction model, and comprises: acquiring data of magnetic field current (A), compensation magnetic field current (A), cathode voltage (KV), cathode current (A), titanium pump current (nA) and current waveform and frequency spectrum data; it should be noted that the waveform and spectrum data are used to determine whether the device is in a sparking state;
the data preprocessing module is used for preprocessing the original data acquired by the data acquisition module, and comprises: converting data format, merging data, removing data duplicate and removing abnormal value;
the data storage module is in a database form and is used for storing the original data acquired by the data acquisition module and the data preprocessed by the data preprocessing module;
the neural network prediction module is connected with the data preprocessing module, preprocessed data are input into the neural network prediction model, and the neural network prediction model outputs a predicted value of the ignition tag;
the remote control module is located at the client side and used for time periodTWhen the predicted value of the ignition label is continuousTh 1The number of times of the order of 1 or the predicted value of the ignition tag of 1 is greater thanTh 2When the system is used, a warning is sent out, and an instruction is sent out to the basic control and protection module;
the basic control and protection module is used for realizing passive control and protection and active control and protection operation; wherein, the active control is: after receiving a remote control module instruction, carrying out emergency shutdown processing on the data acquisition module; the passive control is as follows: and when the data value acquired by the data acquisition module exceeds a set threshold value, carrying out emergency shutdown processing on the acquisition module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911113360.1A CN110909463B (en) | 2019-11-14 | 2019-11-14 | Active control and protection method and system for high-power millimeter wave gyrotron traveling wave tube |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911113360.1A CN110909463B (en) | 2019-11-14 | 2019-11-14 | Active control and protection method and system for high-power millimeter wave gyrotron traveling wave tube |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110909463A CN110909463A (en) | 2020-03-24 |
| CN110909463B true CN110909463B (en) | 2022-06-03 |
Family
ID=69817705
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911113360.1A Active CN110909463B (en) | 2019-11-14 | 2019-11-14 | Active control and protection method and system for high-power millimeter wave gyrotron traveling wave tube |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110909463B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113471035B (en) * | 2021-06-23 | 2022-05-03 | 电子科技大学 | Thermal measurement pretreatment and storage monitoring system for filament of gyrotron traveling wave tube |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5500621A (en) * | 1995-04-03 | 1996-03-19 | Martin Marietta Corp. | Travelling-wave tube protection arrangement |
| CN105433964A (en) * | 2014-07-25 | 2016-03-30 | 上海西门子医疗器械有限公司 | X-ray device |
| CN107317077A (en) * | 2017-06-20 | 2017-11-03 | 电子科技大学 | A kind of novel high-power millimeter wave bicone water load |
| CN107632521A (en) * | 2017-08-30 | 2018-01-26 | 中国矿业大学 | A kind of potentiostat control strategy based on decision tree and neutral net |
| CN107728478A (en) * | 2017-09-27 | 2018-02-23 | 吉林大学 | Fuel cell excess oxygen coefficient network response surface method |
| CN108446808A (en) * | 2018-04-08 | 2018-08-24 | 广东电网有限责任公司 | A kind of short-term load forecasting method of glowworm swarm algorithm optimization neural network |
| CN109314566A (en) * | 2016-06-10 | 2019-02-05 | At&T知识产权部有限合伙公司 | Host node equipment and the method being used therewith |
| CN109460002A (en) * | 2018-09-27 | 2019-03-12 | 电子科技大学 | Efficiently Control protection system and method in a kind of high-power millimeter wave test process |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180316540A1 (en) * | 2017-04-27 | 2018-11-01 | Avago Technologies General Ip (Singapore) Pte. Ltd. | Receive-side nonlinear power amplifier distortion cancellation |
-
2019
- 2019-11-14 CN CN201911113360.1A patent/CN110909463B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5500621A (en) * | 1995-04-03 | 1996-03-19 | Martin Marietta Corp. | Travelling-wave tube protection arrangement |
| CN105433964A (en) * | 2014-07-25 | 2016-03-30 | 上海西门子医疗器械有限公司 | X-ray device |
| CN109314566A (en) * | 2016-06-10 | 2019-02-05 | At&T知识产权部有限合伙公司 | Host node equipment and the method being used therewith |
| CN107317077A (en) * | 2017-06-20 | 2017-11-03 | 电子科技大学 | A kind of novel high-power millimeter wave bicone water load |
| CN107632521A (en) * | 2017-08-30 | 2018-01-26 | 中国矿业大学 | A kind of potentiostat control strategy based on decision tree and neutral net |
| CN107728478A (en) * | 2017-09-27 | 2018-02-23 | 吉林大学 | Fuel cell excess oxygen coefficient network response surface method |
| CN108446808A (en) * | 2018-04-08 | 2018-08-24 | 广东电网有限责任公司 | A kind of short-term load forecasting method of glowworm swarm algorithm optimization neural network |
| CN109460002A (en) * | 2018-09-27 | 2019-03-12 | 电子科技大学 | Efficiently Control protection system and method in a kind of high-power millimeter wave test process |
Non-Patent Citations (2)
| Title |
|---|
| W波段回旋行波管新型曲线阴极磁控注入电子枪优化设计;董坤等;《红外与毫米波学报》;20160815;第35卷(第4期);483-487,495 * |
| 基于BP神经网络模型的行波管慢波结构内部温度反演研究;娄继琳等;《2016真空电子学分会第二十届学术年会论文集（下）》;20160823;340-344 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110909463A (en) | 2020-03-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Nakhodchi et al. | Steeleye: An application-layer attack detection and attribution model in industrial control systems using semi-deep learning | |
| CN110909463B (en) | Active control and protection method and system for high-power millimeter wave gyrotron traveling wave tube | |
| CN110443037B (en) | Power monitoring network security situation perception method based on improved AHP method | |
| CN109687410B (en) | Cascading failure set construction method based on maximum entropy increase | |
| CN109444667A (en) | Power distribution network initial failure classification method and device based on convolutional neural networks | |
| CN104538222B (en) | High-voltage switch gear phase-controlled device based on artificial neural network and method | |
| El Chamie et al. | Physics-based features for anomaly detection in power grids with micro-pmus | |
| CN114814467A (en) | Power distribution network fault positioning method | |
| CN114817865A (en) | Big data-based operation fault prediction system for radio frequency power amplifier | |
| CN112731827A (en) | Monitoring system for intelligent sensor for power equipment | |
| CN115588961B (en) | Setting value self-adaptive setting method based on power distribution network full-model protection | |
| CN109103992B (en) | Power transmission line real-time reliable monitoring system applied to smart power grid | |
| CN116107290A (en) | Industrial equipment fault monitoring method, device, system and storage medium | |
| CN115766081A (en) | Abnormal flow detection method and device for power industrial control cloud platform | |
| Kreimel et al. | Neural net-based anomaly detection system in substation networks | |
| CN115115131A (en) | Multi-center power system fault prediction method and system based on transfer learning | |
| CN113792620A (en) | Tokamak edge local area model real-time identification algorithm based on deep neural network | |
| CN113569947A (en) | Arc detection method and system | |
| Sourav et al. | Machine Learning Assisted Bad Data Detection for High-Throughput Substation Communication | |
| CN115919544B (en) | Tympanic membrane therapeutic instrument fault prediction system based on artificial intelligence | |
| CN105424224A (en) | Isolating switch state monitoring method and device | |
| CN112234594B (en) | Surge protection system and method | |
| CN113671335B (en) | Boost converter power switching tube and diode unified monitoring method | |
| CN117096956B (en) | Harmonic control method and system of high-voltage frequency converter | |
| CN112383545B (en) | Anti-crawler system, device and deployment method applicable to electric SCADA (supervisory control and data acquisition) system |
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 |