CN113705781A - Satellite small station fault judgment method based on neural network - Google Patents
Satellite small station fault judgment method based on neural network Download PDFInfo
- Publication number
- CN113705781A CN113705781A CN202110936456.9A CN202110936456A CN113705781A CN 113705781 A CN113705781 A CN 113705781A CN 202110936456 A CN202110936456 A CN 202110936456A CN 113705781 A CN113705781 A CN 113705781A
- Authority
- CN
- China
- Prior art keywords
- layer
- output
- neural network
- small station
- error
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield 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
Abstract
The invention provides a satellite small station fault judgment method based on a neural network, and relates to the technical field of satellite systems; the method comprises the following steps: starting, initializing parameters, outputting results of a hidden layer unit, outputting results of a layer unit, calculating deviation between an output layer and a hidden layer, correcting the deviation according to a weight, judging whether the deviation reaches a fault threshold value, outputting a corresponding fault result, and displaying the result according to a default rule; the invention has the beneficial effects that: the method is used for analyzing and judging the faults of the satellite small station so as to evaluate the safety and the existing problems of the satellite small station.
Description
Technical Field
The invention relates to the technical field of satellite systems, in particular to a satellite small station fault judgment method based on a neural network.
Background
The safety state of the satellite small station is closely related to the operation state and changes of other systems under the satellite small station. The operating characteristics and state of the satellite small station are directly related to the operating and safety state of the whole satellite small station. Although various information about the satellite stations may be obtained by various means, the limited real-time monitoring data may provide incomplete information and may be influenced by various factors. Therefore, the satellite small station is a complex system limited by various influence factors, fault judgment is performed on the satellite small station, the related work is wide, the comprehensiveness is strong, and a very ideal evaluation model and an evaluation method need to be selected to improve the fault judgment precision.
The artificial neural network is a technical system for simulating the structure and function of a human brain neural network by using engineering technical means, and is a large-scale parallel nonlinear dynamical system. It is not a true picture of the human cranial nervous system, but rather it is a somewhat abstract and simulated structure that has been greatly simplified to preserve its primary properties. Currently, in practical application of artificial neural networks, the most widely used network is a radial basis function neural network model, which is a multilayer mapping network and adopts a learning mode of minimum mean square error. Because the artificial neural network tries to form a novel information processing system in a mode of simulating the organization of a human brain nervous system, the artificial neural network has the characteristics of adaptivity, self-learning, parallelism, nonlinearity, fault tolerance and knowledge processing intensification, and provides a new path with infinite potential for solving the non-structural problem.
In the current safety situation of the satellite substation in China, fault judgment needs to be carried out on a fault system of the satellite substation, and according to scientific procedures and methods, dangerous factors, the possibility of accidents, loss and damage degree in the satellite substation are investigated, analyzed and demonstrated, so that the overall safety of the system is evaluated, existing problems are solved, and effective safety measures are provided.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides a satellite small station fault judgment method based on a neural network, and the method is used for analyzing and judging the faults of the satellite small station so as to evaluate the safety and the existing problems of the satellite small station.
The technical scheme adopted by the invention for solving the technical problems is as follows: in a method for judging a fault of a satellite small station based on a neural network, the improvement is that the method comprises the following steps:
s10, initializing parameters, establishing a three-layer radial basis function neural network fault judgment model consisting of an input layer, a hidden layer and an output layer, and initializing the neural network;
s20, training the neural network by adopting the example sample, and carrying out example verification by using another sample, wherein the sample acts on the input layer and is input into the hidden layer by the input layer, so that the result output of the hidden layer is realized; each input node of the input layer corresponds to a feature of a sample;
s30, inputting the output of each unit of the hidden layer to an output layer, and realizing the result output of the output layer; an output node of the output layer is equal to a corresponding security level;
s40, checking the output error of each unit of the output layer, correcting the weight according to the error, judging whether the error is less than a specified value, outputting a response fault result when the error is less than the specified value, and returning to the step S20 when the error is not less than the specified value;
and when the security level of the check sample is consistent with the actual security level, the network training is successful.
Further, in step S10, the three-layer radial basis function neural network fault determination model is established by analyzing and sorting the original data of the satellite substation and combining with the index system of the satellite substation.
Further, in step S20, the sample features corresponding to the input nodes of the input layer include: and (3) mapping the jitter, the delay, the throughput, the packet loss rate, the C/N dynamic range of a single carrier, the minimum efficiency, the beam number, the terminal antenna size, the information rate, the symbol rate, the modulation mode, the bandwidth, the allowance, the efficiency, the power amplifier and a fault system diagram of the satellite small station.
Further, in step S30, the number of hidden layer nodes of the hidden layer is one.
Further, in step S30, each output node of the output layer corresponds to a security level.
Furthermore, the number of the nodes of the output layer is eight, and the corresponding security levels are normal online, offline, warning, activated, inactivated, not synchronized with configuration, not accessed to the network after configuration, synchronized with configuration and accessed to the network.
Further, in step S20, the training of the neural network is to use an error back propagation algorithm, and includes the following steps:
s201, in a forward propagation process, an input signal is transmitted from an input layer to an output layer through a hidden layer, an output signal is generated at an output end, in the signal transmission process, the weight value of a network is fixed and unchanged, the state of each layer of neuron only affects the state of the next layer of neuron, and if the expected output cannot be obtained at the output layer, the next step is carried out;
s202, back propagation of error signals is carried out, the difference value between the actual output and the expected output of an output layer is the error, the error signals are propagated forward layer by layer from the output end, in the propagation process, the weight of the network is adjusted through error feedback, and the actual output is closer to the expected output through continuous correction of the weight.
The invention has the beneficial effects that: the method for judging the satellite substation fault based on the neural network is provided, and dangerous factors, the possibility of accidents, the loss and the injury degree in the satellite substation are investigated, analyzed and demonstrated, so that the overall safety of the system is evaluated, existing problems are solved, and effective safety measures are provided.
Drawings
Fig. 1 is a schematic flow chart of a method for determining a satellite substation fault based on a neural network according to the present invention.
FIG. 2 is a block diagram of a Radial Basis (RBF) neural network.
Detailed Description
The invention is further illustrated with reference to the following figures and examples.
The conception, the specific structure, and the technical effects produced by the present invention will be clearly and completely described below in conjunction with the embodiments and the accompanying drawings to fully understand the objects, the features, and the effects of the present invention. It is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments, and those skilled in the art can obtain other embodiments without inventive effort based on the embodiments of the present invention, and all embodiments are within the protection scope of the present invention. In addition, all the connection/connection relations referred to in the patent do not mean that the components are directly connected, but mean that a better connection structure can be formed by adding or reducing connection auxiliary components according to specific implementation conditions. All technical characteristics in the invention can be interactively combined on the premise of not conflicting with each other.
The invention discloses a satellite substation fault judgment method based on a neural network, which is used for investigating, analyzing and demonstrating dangerous factors, accident occurrence possibility, loss and injury degree in a satellite substation, so as to evaluate the overall safety of a system and provide effective safety measures aiming at existing problems. Specifically, referring to fig. 1, the method for determining a satellite substation fault based on a neural network according to the present invention includes the following steps:
s10, initializing parameters, establishing a three-layer radial basis function neural network fault judgment model consisting of an input layer, a hidden layer and an output layer, and initializing the neural network;
in the embodiment, the three-layer radial basis function neural network fault judgment model is established by analyzing and sorting original data of the satellite substation and combining an index system of the satellite substation;
s20, training the neural network by adopting 200 example samples, carrying out example verification by using the other 20 example samples, acting the samples on the input layer, and inputting the samples into the hidden layer by the input layer to realize result output of the hidden layer; each input node of the input layer corresponds to a feature of a sample;
in this embodiment, the training of the neural network is to adopt an error back propagation algorithm, which includes steps S201 to S202:
s201, in a forward propagation process, an input signal is transmitted from an input layer to an output layer through a hidden layer, an output signal is generated at an output end, in the signal transmission process, the weight value of a network is fixed and unchanged, the state of each layer of neuron only affects the state of the next layer of neuron, and if the expected output cannot be obtained at the output layer, the next step is carried out;
s202, back propagation of error signals, namely the difference between actual output and expected output of an output layer is an error, the error signals are propagated forward layer by layer from an output end, in the propagation process, the weight of the network is adjusted by error feedback, and the actual output is closer to the expected output through continuous correction of the weight;
in this embodiment, the sample characteristics corresponding to the input nodes of the input layer include: and (3) mapping the jitter, the delay, the throughput, the packet loss rate, the C/N dynamic range of a single carrier, the minimum efficiency, the beam number, the terminal antenna size, the information rate, the symbol rate, the modulation mode, the bandwidth, the allowance, the efficiency, the power amplifier and a fault system diagram of the satellite small station.
S30, inputting the output of each unit of the hidden layer to an output layer, and realizing the result output of the output layer; an output node of the output layer is equal to a corresponding security level; the number of hidden layer nodes of the hidden layer is one;
each output node of the output layer corresponds to one security level, eight nodes of the output layer correspond to the security levels, and the corresponding security levels are normal online, offline, warning, activated, inactivated, not synchronized with configuration, not accessed to the network after configuration, synchronized with configuration and accessed to the network;
s40, checking the output error of each unit of the output layer, correcting the weight according to the error, judging whether the error is less than a specified value, outputting a response fault result when the error is less than the specified value, and returning to the step S20 when the error is not less than the specified value;
and when the security level of the check sample is consistent with the actual security level, the network training is successful.
Because the artificial neural network tries to form a novel information processing system in a mode of simulating the organization of a human brain nervous system, the artificial neural network has the characteristics of adaptivity, self-learning, parallelism, nonlinearity, fault tolerance and knowledge processing intensification, and provides a new path with infinite potential for solving the non-structural problem.
Therefore, the evaluation method based on the artificial neural network model can avoid the limitation and subjectivity of the common method, solve the contradiction between the unsafe perceptibility of the satellite substation, improve the evaluation precision, and is an ideal evaluation model and evaluation method. The establishment of the evaluation index is the basis and key of the evaluation research content, and directly influences the correctness of the evaluation result. The evaluation index can reflect the main characteristics and basic conditions of the satellite small station and the dangerous state existing in the system as the target.
According to various dangerous hazard factors possibly existing in the satellite small station, the evaluation indexes of the satellite fault safety system are marked into a whole target, namely a satellite fault judgment index system by using hierarchical analysis.
The invention adopts a hierarchical standard quantization method to convert qualitative indexes into quantitative indexes. Dividing each index into 8 levels, namely level 1, level 2, level 3 and level 4 … … 8, and respectively representing normal online, offline, warning, activated and inactivated; the configuration is not synchronous, the configuration is completed without network access, and the configuration is synchronous and network access is realized. Each level defines a value standard and a numerical value, and when evaluation is carried out, the evaluation value of the corresponding index is obtained according to the actual situation of an evaluation object.
The neuron model is mainly based on the transfer characteristics of simulated biological neuron information, namely input and output relations. The neural network model is a feedforward multilayer neural network adopting an error back propagation algorithm, and the structure of the neural network model is a multilayer network structure. The neurons in each layer are completely interconnected, and the neurons in the same layer are not connected. Each input node of the network corresponds to a feature of the sample, and the number of input nodes is equal to a feature of the sample, which is: the method comprises the steps of drawing X1 satellite small station jitter, X2 delay, X3 throughput, X4 packet loss rate, C/N dynamic range of X5 single carrier, X6 minimum efficiency, X7 beam number, X8 terminal antenna size, X9 information rate, X10 symbol rate, X11 modulation mode, X12 bandwidth, X13 margin, X14 efficiency, X15 power amplifier and X16 fault system diagram. One output node corresponds to one security level, which is respectively: y1 normally online, Y2 offline, Y3 warning, Y4 activated, Y5 not activated; y6 configuration is not synchronized, Y7 configuration is not accessed to the network, Y8 configuration is synchronized and accessed to the network.
The selection of the number of nodes in each layer in the neural network based on the algorithm has a great influence on the performance of the network, and the number of nodes in each layer needs to be properly selected. The secondary index of the fault judgment of the satellite communication operation system is the influence factor of the fault judgment of the satellite small station, and can basically reflect various control factors of the fault judgment of the satellite communication operation system.
Therefore, the number of input nodes of the neural network is determined to be one. And the safety level of the satellite small station is classified into stages, so that the neural network is determined to have an output node. When each node adopts a type function, a hidden layer is used for realizing the random decision classification problem. Therefore, a three-layer neural network structure with a single hidden layer is adopted. For the number of hidden nodes, according to the research, the number of the hidden nodes of the single hidden neural network is 2 × 16+1, and the number of the hidden nodes in the text is determined to be 33. The number of outputs is 8, so the network structure is 16-33-8.
Referring to fig. 2, the structure of the RBF network is shown in fig. 2, and is characterized in that: the network is provided with N person input nodes, P hidden nodes and i output nodes; the number of hidden nodes of the network is equal to the number of human input samples, the activation function of the hidden nodes is a Gaussian radial basis function, all human input samples are set as the centers of the radial basis functions, and each radial basis function is provided with a uniform expansion constant.
Let any node of the input layer be denoted by i, any node of the hidden node be denoted by j, and any node of the output layer be denoted by k. The mathematical description of the layers is as follows:
inputting a vector:
X＝(x1,x2,...,xN)T；
activation function of any hidden node:
determining an output vector Y and a desired output vector O:
wherein q is the number of output layer units;
initializing the connection weight from the hidden layer to the output layer:
Wk＝[wk1,wk2,...,wkp]T,(k＝1,2,...,q)；
where p is the number of hidden layer elements and q is the number of output layer elements.
The method for initializing the reference center provides a method for initializing the weight from a hidden layer to an output layer, which comprises the following steps:
where mink is the minimum of all expected outputs in the kth output neuron in the training set; maxk is the maximum of all expected outputs in the kth output neuron in the training set.
After a neural network model is determined, a corresponding learning method must be matched with the neural network model in order to make the neural network have certain intelligent characteristics. The learning method is the adjusting method of the network connection right at the bottom. The neural network adopts an error back propagation algorithm, and the network connection weight is obtained by learning and continuously adjusting.
According to the analysis and the arrangement of the original data of the satellite small station and the combination of a certain index system, an example sample of a fault judgment model based on a neural network is established for training, and another sample is used for example verification. And the safety level of the check sample is consistent with the actual safety level, which indicates that the network training is successful.
Due to the characteristics of nonlinearity, fault tolerance, self-learning, real-time processing and the like of the artificial neural network, the method can be used for solving the problem of satellite substation fault judgment. A mathematical model of satellite substation fault judgment based on a neural network is established, a plurality of control factors of the satellite substation fault judgment are reflected on the number of input neurons, the safety level of the satellite substation fault judgment is reflected on the number of output neurons, the network is trained and corrected through an established typical training sample, and finally the training is successful.
And finally, expressing the output result by using a color identifier, and expressing the result by using the following method:
in the satellite field, a satellite small station has various states, and when the online state is checked, the situations of offline, online configuration not pushed, online error, offline configuration not pushed, online alarm and the like can occur. For such a situation, when the state of each cell is distinguished by color, the cell condition can be defined immediately according to the color definition. According to the color definition, troubleshooting of the small station can be realized. The checking time is greatly reduced, and the positioning error is accelerated.
The invention adopts a combination mode for the online condition of the small station and the colors and icons of the alarm types, not only adopts a double-icon representation method, but also can realize the random combination of the icon shapes, and the alarm icons and the colors can also be customized and combined, but the two combinations are best for convenient viewing in the using process.
While the preferred embodiments of the present invention have been illustrated and described, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (7)
1. A satellite small station fault judgment method based on a neural network is characterized by comprising the following steps:
s10, initializing parameters, establishing a three-layer radial basis function neural network fault judgment model consisting of an input layer, a hidden layer and an output layer, and initializing the neural network;
s20, training the neural network by adopting the example sample, and carrying out example verification by using another sample, wherein the sample acts on the input layer and is input into the hidden layer by the input layer, so that the result output of the hidden layer is realized; each input node of the input layer corresponds to a feature of a sample;
s30, inputting the output of each unit of the hidden layer to an output layer, and realizing the result output of the output layer; an output node of the output layer is equal to a corresponding security level;
s40, checking the output error of each unit of the output layer, correcting the weight according to the error, judging whether the error is less than a specified value, outputting a response fault result when the error is less than the specified value, and returning to the step S20 when the error is not less than the specified value;
and when the security level of the check sample is consistent with the actual security level, the network training is successful.
2. The method for judging the fault of the satellite small station based on the neural network as claimed in claim 1, wherein in step S10, the three-layer radial basis function neural network fault judgment model is established by analyzing and sorting the raw data of the satellite small station and combining an index system of the satellite small station.
3. The method for determining the satellite small station fault based on the neural network as claimed in claim 1, wherein in step S20, the sample characteristics corresponding to the input nodes of the input layer include: and (3) mapping the jitter, the delay, the throughput, the packet loss rate, the C/N dynamic range of a single carrier, the minimum efficiency, the beam number, the terminal antenna size, the information rate, the symbol rate, the modulation mode, the bandwidth, the allowance, the efficiency, the power amplifier and a fault system diagram of the satellite small station.
4. The method for determining the satellite small station fault based on the neural network as claimed in claim 1, wherein in step S30, the number of hidden layer nodes of the hidden layer is one.
5. The method for determining satellite small station fault based on neural network as claimed in claim 1, wherein in step S30, each output node of said output layer corresponds to a security level.
6. The method as claimed in claim 5, wherein the number of the nodes of the output layer is eight, and the security levels respectively correspond to normal online, offline, warning, active, inactive, unsynchronized configuration, synchronized configuration and networked.
7. The method for judging the satellite small station fault based on the neural network as claimed in claim 1, wherein in the step S20, the training of the neural network is to adopt an error back propagation algorithm, and the method comprises the following steps:
s201, in a forward propagation process, an input signal is transmitted from an input layer to an output layer through a hidden layer, an output signal is generated at an output end, in the signal transmission process, the weight value of a network is fixed and unchanged, the state of each layer of neuron only affects the state of the next layer of neuron, and if the expected output cannot be obtained at the output layer, the next step is carried out;
s202, back propagation of error signals is carried out, the difference value between the actual output and the expected output of an output layer is the error, the error signals are propagated forward layer by layer from the output end, in the propagation process, the weight of the network is adjusted through error feedback, and the actual output is closer to the expected output through continuous correction of the weight.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110936456.9A CN113705781A (en) | 2021-08-16 | 2021-08-16 | Satellite small station fault judgment method based on neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110936456.9A CN113705781A (en) | 2021-08-16 | 2021-08-16 | Satellite small station fault judgment method based on neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113705781A true CN113705781A (en) | 2021-11-26 |
Family
ID=78652767
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110936456.9A Pending CN113705781A (en) | 2021-08-16 | 2021-08-16 | Satellite small station fault judgment method based on neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113705781A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101894214A (en) * | 2010-07-09 | 2010-11-24 | 中冶北方工程技术有限公司 | Mine ventilation system fault judging method based on hereditary neural network |
| CN103995237A (en) * | 2014-05-09 | 2014-08-20 | 南京航空航天大学 | Satellite power supply system online fault diagnosis method |
| CN107798380A (en) * | 2017-09-12 | 2018-03-13 | 上海航天控制技术研究所 | Ephemeris computational methods and computing system on detector device |
| CN109617597A (en) * | 2019-02-19 | 2019-04-12 | 亚太卫星宽带通信（深圳）有限公司 | Multi-track satellite network interworking system and satellite communication method |
| CN110988927A (en) * | 2019-12-06 | 2020-04-10 | 上海航天控制技术研究所 | On-line detection method for correctness of Beidou satellite navigation positioning speed measurement result |
-
2021
- 2021-08-16 CN CN202110936456.9A patent/CN113705781A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101894214A (en) * | 2010-07-09 | 2010-11-24 | 中冶北方工程技术有限公司 | Mine ventilation system fault judging method based on hereditary neural network |
| CN103995237A (en) * | 2014-05-09 | 2014-08-20 | 南京航空航天大学 | Satellite power supply system online fault diagnosis method |
| CN107798380A (en) * | 2017-09-12 | 2018-03-13 | 上海航天控制技术研究所 | Ephemeris computational methods and computing system on detector device |
| CN109617597A (en) * | 2019-02-19 | 2019-04-12 | 亚太卫星宽带通信（深圳）有限公司 | Multi-track satellite network interworking system and satellite communication method |
| CN110988927A (en) * | 2019-12-06 | 2020-04-10 | 上海航天控制技术研究所 | On-line detection method for correctness of Beidou satellite navigation positioning speed measurement result |
Non-Patent Citations (2)
| Title |
|---|
| 孙世友等: "《大地图 测绘地理信息大数据理论与实践》", 30 September 2017, pages: 235 - 236 * |
| 王丽娜: "《现代通信技术》", 31 October 2016, pages: 292 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112784964A (en) | Image classification method based on bridging knowledge distillation convolution neural network | |
| CN110798227B (en) | Model prediction optimization method, device, equipment and readable storage medium | |
| CN107480787B (en) | Open-pit mine gyratory crusher fault diagnosis method based on BP neural network | |
| CN114781609A (en) | Traffic flow prediction method based on multi-mode dynamic residual image convolution network | |
| CN113392429B (en) | Block chain-based power distribution Internet of things data safety protection method and device | |
| CN106572494A (en) | Base station fault detection method and device | |
| CN108470251B (en) | Community division quality evaluation method and system based on average mutual information | |
| CN113705781A (en) | Satellite small station fault judgment method based on neural network | |
| Khan et al. | An Explainable Intelligent Framework for Anomaly Mitigation in Cyber-Physical Inverter-based Systems | |
| CN109784629B (en) | Transformer substation industrial control network fault positioning method based on neural network | |
| CN111538239A (en) | Multi-agent navigation following consistency control system and method | |
| CN115115131A (en) | Multi-center power system fault prediction method and system based on transfer learning | |
| CN108830382A (en) | A kind of DCS method for evaluating reliability based on dynamic evidence network | |
| CN111935171B (en) | Terminal security policy selection method based on machine learning under edge calculation | |
| Li et al. | Effects of measurement dependence on generalized Clauser-Horne-Shimony-Holt Bell test in the single-run and multiple-run scenarios | |
| Yasinzadeh et al. | Fake measurement identification in power substations based on correlation between data and distance of the evidence | |
| Wang et al. | Fault detection for complex systems with channel fadings, randomly occurring multiple delays and infinitely distributed delays | |
| CN110942150A (en) | Intelligent diagnosis method for forming failure of parts of selective laser melting equipment | |
| Zhang et al. | The Application of GABP Neural Network Algorithm in the Aspect of Security Assessment of Computer Network | |
| Shi et al. | Finite‐time control for discrete time‐varying systems with randomly occurring non‐linearity and missing measurements | |
| CN113965467B (en) | Power communication system reliability assessment method and system based on neural network | |
| CN114884827B (en) | Model construction and code generation method for industrial control network protocol | |
| CN114024669B (en) | System and method for detecting communication abnormal terminal of discrete modulation CVQKD | |
| CN113705075B (en) | Social relationship analysis method based on graph neural network | |
| Zhang et al. | Research on Traffic Situational Awareness System Based on Software-Defined Network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211126 |
|
| RJ01 | Rejection of invention patent application after publication |