CN113556770A - Data verification method, device, terminal and readable storage medium - Google Patents
Data verification method, device, terminal and readable storage medium Download PDFInfo
- Publication number
- CN113556770A CN113556770A CN202110853083.9A CN202110853083A CN113556770A CN 113556770 A CN113556770 A CN 113556770A CN 202110853083 A CN202110853083 A CN 202110853083A CN 113556770 A CN113556770 A CN 113556770A
- Authority
- CN
- China
- Prior art keywords
- data
- neural network
- value
- artificial neural
- acquiring
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/04—Arrangements for maintaining operational condition
-
- 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
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04Q—SELECTING
- H04Q9/00—Arrangements in telecontrol or telemetry systems for selectively calling a substation from a main station, in which substation desired apparatus is selected for applying a control signal thereto or for obtaining measured values therefrom
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W28/00—Network traffic management; Network resource management
- H04W28/02—Traffic management, e.g. flow control or congestion control
- H04W28/04—Error control
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04Q—SELECTING
- H04Q2209/00—Arrangements in telecontrol or telemetry systems
- H04Q2209/40—Arrangements in telecontrol or telemetry systems using a wireless architecture
Abstract
The invention discloses a data verification method, a device, a terminal and a readable storage medium, wherein the method comprises the steps of judging whether multi-channel collected data are consistent or not, and directly collecting a message without verifying if the multi-channel collected data are consistent; if not, judging whether the data packet format is wrong; if so, rejecting the error data and then acquiring the message; if not, judging whether the maximum number of the paths with the same acquisition value is more than half of the number of the acquisition paths; if so, acquiring the data corresponding to the maximum road number with the same acquisition value; and if not, acquiring the value closest to the output value of the improved BP interpolation artificial neural network in each path of acquired data. The invention adopts a communication mechanism of multiplexing of multiple channels on the monitoring station, deploys various wireless channels, establishes an effective multi-channel data verification mechanism based on the BP artificial neural network, strengthens the reliability and stability of data return of the monitoring station in remote areas, ensures continuous and uninterrupted monitoring, and reduces the requirement of manual maintenance of the monitoring station.
Description
Technical Field
The invention relates to the technical field of electric power data acquisition and verification, in particular to a data verification method, a data verification device, a terminal and a readable storage medium.
Background
At present, in the process of acquiring data by monitoring stations, a large amount of monitoring data needs to be acquired from equipment deployed in the field, and the monitoring stations usually do not have a wired transmission means and need to return data by means of wireless communication. The currently available wireless data transmission methods mainly include: mobile phone terminals, microwave transceiver stations, short-wave radio stations, troposphere scattering, satellites and the like. However, these wireless data transmission methods often have the following disadvantages:
firstly, the channel quality is not high, and the data transmission process is easy to be interfered, so that the transmission rate is reduced and the transmission content is wrong;
secondly, the channel is unstable and greatly influenced by the environment, and the data transmission is influenced by rain, snow and fog days;
thirdly, equipment maintenance is difficult, and maintenance personnel are difficult to timely repair faulty equipment due to the fact that the equipment is often deployed in an area which is difficult to reach.
Disclosure of Invention
The invention aims to provide a data verification method, a data verification device, a terminal and a readable storage medium, which are used for solving the problems of low channel quality, unstable data transmission, great environmental influence and difficult equipment maintenance in the existing wireless data transmission.
In order to overcome the defects in the prior art, the invention provides a data verification method, which comprises the following steps:
judging whether the data acquired by the multiple paths are consistent, if so, directly acquiring the message without checking; if not, judging whether the data packet format is wrong;
if so, rejecting the error data and then acquiring the message; if not, judging whether the maximum number of the paths with the same acquisition value is more than half of the number of the acquisition paths;
if so, acquiring the data corresponding to the maximum road number with the same acquisition value; and if not, acquiring the value closest to the output value of the improved BP interpolation artificial neural network in each path of acquired data.
Further, the data verification method further includes:
and inputting the value which is closest to the output value of the interpolation artificial neural network in each path of collected data into the improved BP interpolation artificial neural network for training so as to enable the error between the closest value and the output value of the interpolation artificial neural network to reach a preset error range.
Further, in the data verification method, a momentum method and a self-adaptive adjustment method are used for adjusting a standard BP algorithm to obtain an improved BP interpolation artificial neural network;
the momentum method is to superpose the last weight adjustment quantity with the current weight adjustment quantity to be used as the current actual weight adjustment quantity;
the self-adaptive adjustment method comprises the steps of increasing the learning rate if the algorithm converges; and if the algorithm is not converged, reducing the learning rate until the algorithm is converged.
Further, the multiplexed collected data comprises:
buoy monitoring station data returned by using a connected CDMA channel, shore-based monitoring station data returned by using a microwave transmission technology and short messages forwarded by a satellite.
The present invention also provides a data verification apparatus, comprising:
the first judgment unit is used for judging whether the data acquired by the multiple paths are consistent or not, and if so, direct letter acquisition is not needed to be checked;
the second judgment unit is used for judging whether the data packet format is wrong or not if the multi-path collected data are inconsistent; if so, rejecting the error data and then acquiring the message;
the third judging unit is used for judging whether the maximum number of the paths with the same acquisition value is more than half of the number of the acquired paths if the data packet format is correct; if so, acquiring the data corresponding to the maximum road number with the same acquisition value; and if not, acquiring the value closest to the output value of the improved BP interpolation artificial neural network in each path of acquired data.
Further, the data verification device further comprises a training unit, which is used for inputting the value closest to the output value of the interpolation artificial neural network in each path of collected data into the improved BP interpolation artificial neural network for training, so that the error between the closest value and the output value of the interpolation artificial neural network reaches a preset error range.
Further, the training unit is further adapted to,
adjusting a standard BP algorithm by using a momentum method and an adaptive adjustment method to obtain an improved BP interpolation artificial neural network;
the momentum method is to superpose the last weight adjustment quantity with the current weight adjustment quantity to be used as the current actual weight adjustment quantity;
the self-adaptive adjustment method comprises the steps of increasing the learning rate if the algorithm converges; and if the algorithm is not converged, reducing the learning rate until the algorithm is converged.
Further, the multiplexed collected data comprises:
buoy monitoring station data returned by using a connected CDMA channel, shore-based monitoring station data returned by using a microwave transmission technology and short messages forwarded by a satellite.
The present invention also provides a terminal device, including:
one or more processors;
a memory coupled to the processor for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement a data verification method as claimed in any preceding claim.
The present invention also provides a computer-readable storage medium having stored thereon a computer program for execution by a processor to implement the data verification method as defined in any one of the above.
Compared with the prior art, the invention has the beneficial effects that:
1) the data are transmitted in a multiplex mode of a plurality of wireless channels on monitoring, after the data are read by the acquisition server, the interfaces of various data transmitting devices are called to synchronously transmit the data to the data center, and a data transmission mechanism with mutual backup and mutual redundancy is realized.
2) An interpolation BP artificial neural network is adopted, and an estimated value of a certain monitoring value is calculated based on a plurality of related monitoring values and is used as a basis for verifying returned data. Based on the time correlation of the monitoring data indexes, the expected value of the target data is obtained by means of interpolation calculation of the BP artificial neural network and is used as a basis for multi-path returned data verification, so that an accurate monitoring value is selected when data errors occur due to a transmission channel, and the reliability of data returning of the monitoring station in remote areas is enhanced.
3) The multi-interface STM32 single board computer is used on the monitoring station to realize the multi-path parallel sending of data, establish a plurality of data transmission channels and construct a redundant data transmission system which is mutually backed up.
Drawings
In order to more clearly illustrate the technical solution of the present invention, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a data verification method according to an embodiment of the present invention;
fig. 2 is a schematic diagram of the operation of monitoring data transmission multi-channel multiplexing according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an artificial neural network for BP interpolation for verification according to an embodiment of the present invention;
FIG. 4 is a schematic flow chart of an adaptive method for adjusting learning rate of a standard BP interpolation artificial neural network according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a data verification apparatus according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be understood that the step numbers used herein are for convenience of description only and are not intended as limitations on the order in which the steps are performed.
It is to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
The terms "comprises" and "comprising" indicate the presence of the described features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
The term "and/or" refers to and includes any and all possible combinations of one or more of the associated listed items.
In a first aspect:
referring to fig. 1, an embodiment of the present invention provides a data verification method, including:
s10, judging whether the multi-path collected data are consistent; if yes, directly collecting the message without checking; if not, executing step S20, and determining whether the packet format is wrong;
in this embodiment, before data determination, data needs to be transmitted and received. In order to improve the reliability of data transmission, a plurality of wireless transmission means are used on a monitoring site in a channel multiplexing mode to improve the reliability of the transmission of real-time monitoring data.
In one embodiment, the principle of operation of monitoring the multiplexing of multiple channels of data transmission is provided, as shown in fig. 2. The specific method for channel multiplexing comprises the following steps: after a sensor of a monitoring station acquires real-time monitoring data, a control device STM32 single board computer is connected with the sensor to read data content and package the data content, the sending devices of various transmission channels are synchronously called through USART and SPI port communication, and the data are sent to a receiving station of a data center through different channels. And on the sea monitoring station, monitoring data are synchronously transmitted in a mode of a Unicom CDMA channel, microwave transmission and Beidou satellite short message multiplexing.
Further, after data transmission is performed through multiple channels, the data center needs to collect and summarize the data.
In one embodiment, the data center receives data returned by the buoy monitoring station through multiple receiving modes, and the data returned by the connected CDMA channel is transmitted to the data center server through a connected special line; microwave transmission is realized by deploying receiving equipment at a shore-based monitoring station at sea, and after receiving data, the data is transmitted back to a data center in a special line renting mode; and deploying a Beidou receiving terminal for the satellite short message in the data center, and receiving the short message forwarded by the satellite. The data returned by different channels are collected on the data center server and processed uniformly.
Further, after the data are collected, data check is required, that is, step S10 is executed, that is, whether the multiple paths of collected data are consistent is judged; if yes, the verification process is terminated without verifying the direct message collection.
If not, step S20 is executed to determine whether the packet format is wrong, i.e., to perform partition determination on the data.
Further, if the data packet format is wrong, step S30 is executed, the unreadable error data is eliminated, the content of the data packet without the format error is trusted, and then the verification process is terminated.
If the data packet format is correct, executing step S40, and determining whether the maximum number of the collected data is greater than half of the collected number of the collected data; for example, in multi-path collected data, m is the maximum number of paths with the same collection value, n is the total number of collected paths, and then the size relationship between m and n/2 is judged.
Further, if m is greater than n/2, step S50 is executed to collect the corresponding data of the maximum number of the collected values, that is, to collect the m collected values, and then the verification process is terminated.
If m is less than or equal to n/2, executing step S60, calculating the BP neural network interpolation result, and then executing step S70, selecting the value closest to the improved BP interpolation artificial neural network output value (interpolation result) in each path of collected data.
In one embodiment, after selecting a value closest to an output value (interpolation result) of the modified BP interpolation artificial neural network from the collected data, the method further includes: inputting the value into an improved BP interpolation artificial neural network for training, so that the error between the value and the output value of the interpolation artificial neural network reaches a preset error range, and the whole checking process is finished.
It should be noted that the reason for checking the BP interpolation artificial neural network is that one offshore buoy generally has a plurality of monitoring devices, and collects different hydrological and water quality monitoring data at the same time, and there is a certain correlation between these indexes, for example, the chlorophyll concentration in seawater and the water temperature, turbidity, total nitrogen and total phosphorus are in a significant positive correlation. Therefore, relevant monitoring parameters are selected as interpolation input, an interpolation output result of a certain index is calculated, and the method has rationality.
In one embodiment, a schematic structural diagram of an artificial neural network for verifying interpolation by BP is given, as shown in fig. 3. The following description is made on the BP interpolation artificial neural network with reference to fig. 3:
firstly, the check BP interpolation artificial neural network input layer is mainly divided into two types, one type is a time variable, and because the monitoring data is periodic variation data and has close correlation with time; one is other related monitoring value variables with obvious images for the check indexes, and the output layer is the calculation result of the check monitoring indexes. The data calculation process of the BP interpolation artificial neural network comprises two processes of forward calculation (forward propagation) of data flow and backward propagation of error signals. In forward propagation, the propagation direction is input layer → hidden layer → output layer, and the state of each layer of neurons only affects the next layer of neurons. If the desired output is not available at the output layer, the back propagation flow of the error signal is reversed. By alternately carrying out the two processes, an error function gradient descending strategy is executed in the weight vector space, a group of weight vectors are dynamically and iteratively searched, so that the network error function reaches the minimum value, and the training of the artificial neural network is completed.
Specifically, let the input layer of the BP network have n nodes, and the input variable of each node is xiThe hidden layer has q nodes, and the output layer has m nodesThe weight value between the node, the input layer and the hidden layer is vkiThe weight between the hidden layer and the output layer is wjkThe transfer function of the hidden layer is f1(. o) the transfer function of the output layer is f2(. o), then the output of the hidden layer node is (threshold written into the summation term):
the output of the output layer node is:
further, to obtain the back propagation function, the error function is defined as follows:
inputting P learning samples by X1,X2,...Xp,...XPTo indicate. Thus, the output obtained after obtaining the p-th sample input to the network is
Obtaining the error E of the p sample by adopting a square error functionp：
In the formula (I), the compound is shown in the specification,
is the desired output.
For P learning samples, the global error is:
w is adjusted by adopting an accumulative error BP algorithm through the weight of an output layerjkThe global error E is made smaller, and w is obtainedjkThe change of (A) is as follows:
where η is the learning rate of the error back propagation and the negative sign indicates the gradient decrease in the weight space. Through derivation, the weight value adjustment formula of each neuron of the hidden layer is as follows:
it should be noted that although the BP algorithm theory has the advantages of reliable basis, strict derivation process, high precision, good universality and the like, the standard BP algorithm has the following disadvantages: the convergence speed is slow; easily fall into local minimum values; it is difficult to determine the number of hidden layers and the number of hidden nodes. Therefore, what is employed in the embodiments of the present invention is an improved BP algorithm: the momentum-adaptive learning rate adjustment algorithm specifically comprises the following contents:
1) the improvement of the BP algorithm standard BP algorithm by using a momentum method is a simple steepest descent static optimization method, when correcting w (k), correction is carried out only according to the negative gradient direction of the k step, and the accumulated experience in the past, namely the gradient direction at the previous moment is not considered, so that the learning process is often oscillated and the convergence is slow. The specific method of the momentum method weight value adjusting algorithm is as follows: superposing a part of the previous weight adjustment quantity on the weight adjustment quantity calculated according to the current error to serve as the current actual weight adjustment quantity, namely:
wherein α is the coefficient of momentum, typically 0 < α < 0.9; eta is the learning rate and is in the range of 0.001-10. The momentum factor added by this method, which effectively acts as a damping term, reduces the tendency of oscillations during learning, thereby improving convergence. The momentum method reduces the sensitivity of the network to the local details of the error curved surface and effectively inhibits the network from falling into local minimum.
2) An important reason for the slow convergence speed of the self-adaptive adjustment learning rate standard BP algorithm is that the learning rate is selected improperly, the learning rate is selected too small, and the convergence is too slow; if the learning rate is selected too large, overshoot may be corrected, resulting in oscillations or even divergence. The learning rate may be adjusted using an adaptive approach as shown in fig. 4. The basic guiding idea of the adjustment is as follows: in the case of convergence of learning, η is increased to shorten the learning time; when η is too large to converge, η is decreased in time until convergence. Specifically, the method comprises the following steps:
judging whether the ratio of the global error to the last global error is greater than a k value:
if yes, the weight between the input layer and the hidden layer is maintained as vkiThe weight between the hidden layer and the output layer is wjkThe eta is timely reduced without change, and the eta is satisfiedn＝βηn-1Until convergence. If not, recalculating valid vki、wjkThen by ηn＝γηn-1Eta is increased to shorten the learning time.
According to the verification method provided by the embodiment of the invention, a multi-channel parallel sending of data is realized by adopting a multi-channel multiplexing communication mechanism on a monitoring site and utilizing a multi-interface STM32 single board computer, a plurality of data transmission channels are established, and a redundant data transmission system which is mutually backed up is constructed. Meanwhile, the method establishes an effective multi-channel data verification mechanism based on the BP artificial neural network, strengthens the reliability and stability of data return of the monitoring station in remote areas by various means, ensures the continuity and the continuity of monitoring, reduces the requirement of manual maintenance of the monitoring station, and can play an effective role in related scientific research and production projects.
In a second aspect:
referring to fig. 5, an embodiment of the present invention further provides a data verification apparatus, including:
the first judging unit 01 is used for judging whether the multi-path collected data are consistent, and if so, direct letter collection is not needed to be checked;
the second judging unit 02 is used for judging whether the data packet format is wrong or not if the multi-path collected data are inconsistent; if so, rejecting the error data and then acquiring the message;
a third determining unit 03, configured to determine whether the maximum number of the acquired data packets is greater than half of the maximum number of the acquired data packets if the data packet format is correct; if so, acquiring the data corresponding to the maximum road number with the same acquisition value; and if not, acquiring the value closest to the output value of the improved BP interpolation artificial neural network in each path of acquired data.
In one embodiment, the data verification apparatus further includes a training unit, configured to input a value closest to an output value of the interpolation artificial neural network in each path of collected data to the improved BP interpolation artificial neural network for training, so that an error between the closest value and the output value of the interpolation artificial neural network reaches a preset error range.
In a certain embodiment, the training unit is further adapted to,
adjusting a standard BP algorithm by using a momentum method and an adaptive adjustment method to obtain an improved BP interpolation artificial neural network;
the momentum method is to superpose the last weight adjustment quantity with the current weight adjustment quantity to be used as the current actual weight adjustment quantity;
the self-adaptive adjustment method comprises the steps of increasing the learning rate if the algorithm converges; and if the algorithm is not converged, reducing the learning rate until the algorithm is converged.
In one embodiment, the multi-channel collected data includes:
buoy monitoring station data returned by using a connected CDMA channel, shore-based monitoring station data returned by using a microwave transmission technology and short messages forwarded by a satellite.
When the method is executed, a multi-channel parallel sending of data is realized by adopting a multi-channel multiplexing communication mechanism on a monitoring site and utilizing a multi-interface STM32 single board computer, a plurality of data transmission channels are established, and a redundant data transmission system which is mutually backed up is constructed. Meanwhile, the method establishes an effective multi-channel data verification mechanism based on the BP artificial neural network, strengthens the reliability and stability of data return of the monitoring station in remote areas by various means, ensures the continuity and the continuity of monitoring, and reduces the requirement of manual maintenance of the monitoring station.
In a third aspect:
an embodiment of the present invention further provides a terminal device, including:
one or more processors;
a memory coupled to the processor for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the data verification method as described above.
The processor is used for controlling the overall operation of the terminal equipment so as to complete all or part of the steps of the data verification method. The memory is used to store various types of data to support operation at the terminal device, and these data may include, for example, instructions for any application or method operating on the terminal device, as well as application-related data. The Memory may be implemented by any type of volatile or non-volatile Memory device or combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic disk, or optical disk.
The terminal Device may be implemented by one or more Application Specific1 integrated circuits (AS 1C), a Digital Signal Processor (DSP), a Digital Signal Processing Device (DSPD), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a controller, a microcontroller, a microprocessor, or other electronic components, and is configured to perform the data verification method according to any of the embodiments described above, and achieve the technical effects consistent with the methods described above.
An embodiment of the invention also provides a computer readable storage medium comprising program instructions which, when executed by a processor, implement the steps of the data verification method as described in any one of the above embodiments. For example, the computer readable storage medium may be the above memory including program instructions, which are executable by the processor of the terminal device to perform the data verification method according to any one of the above embodiments, and achieve the technical effects consistent with the above method.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention.
Claims (10)
1. A method for data verification, comprising:
judging whether the data acquired by the multiple paths are consistent, if so, directly acquiring the message without checking; if not, judging whether the data packet format is wrong;
if so, rejecting the error data and then acquiring the message; if not, judging whether the maximum number of the paths with the same acquisition value is more than half of the number of the acquisition paths;
if so, acquiring the data corresponding to the maximum road number with the same acquisition value; and if not, acquiring the value closest to the output value of the improved BP interpolation artificial neural network in each path of acquired data.
2. The data verification method of claim 1, further comprising:
and inputting the value which is closest to the output value of the interpolation artificial neural network in each path of collected data into the improved BP interpolation artificial neural network for training so as to enable the error between the closest value and the output value of the interpolation artificial neural network to reach a preset error range.
3. The data verification method according to claim 2, wherein the standard BP algorithm is adjusted by using a momentum method and a self-adaptive adjustment method to obtain an improved BP interpolation artificial neural network;
the momentum method is to superpose the last weight adjustment quantity with the current weight adjustment quantity to be used as the current actual weight adjustment quantity;
the self-adaptive adjustment method comprises the steps of increasing the learning rate if the algorithm converges; and if the algorithm is not converged, reducing the learning rate until the algorithm is converged.
4. A data verification method as claimed in any one of claims 1 to 3, wherein the multiplexed data collected comprises:
buoy monitoring station data returned by using a connected CDMA channel, shore-based monitoring station data returned by using a microwave transmission technology and short messages forwarded by a satellite.
5. A data verification apparatus, comprising:
the first judgment unit is used for judging whether the data acquired by the multiple paths are consistent or not, and if so, direct letter acquisition is not needed to be checked;
the second judgment unit is used for judging whether the data packet format is wrong or not if the multi-path collected data are inconsistent; if so, rejecting the error data and then acquiring the message;
the third judging unit is used for judging whether the maximum number of the paths with the same acquisition value is more than half of the number of the acquired paths if the data packet format is correct; if so, acquiring the data corresponding to the maximum road number with the same acquisition value; and if not, acquiring the value closest to the output value of the improved BP interpolation artificial neural network in each path of acquired data.
6. The data verification device according to claim 5, further comprising a training unit, configured to input a value closest to an output value of the interpolated artificial neural network in each collected data path to the modified BP interpolated artificial neural network for training, so that an error between the closest value and the output value of the interpolated artificial neural network reaches a preset error range.
7. The data verification device of claim 6, wherein the training unit is further configured to,
adjusting a standard BP algorithm by using a momentum method and an adaptive adjustment method to obtain an improved BP interpolation artificial neural network;
the momentum method is to superpose the last weight adjustment quantity with the current weight adjustment quantity to be used as the current actual weight adjustment quantity;
the self-adaptive adjustment method comprises the steps of increasing the learning rate if the algorithm converges; and if the algorithm is not converged, reducing the learning rate until the algorithm is converged.
8. A data verification device according to any one of claims 5 to 7, wherein the multiplexed data collection comprises:
buoy monitoring station data returned by using a connected CDMA channel, shore-based monitoring station data returned by using a microwave transmission technology and short messages forwarded by a satellite.
9. A terminal device, comprising:
one or more processors;
a memory coupled to the processor for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement a data verification method as claimed in any one of claims 1 to 4.
10. A computer-readable storage medium, on which a computer program is stored, the computer program being executable by a processor to implement the data verification method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110853083.9A CN113556770A (en) | 2021-07-27 | 2021-07-27 | Data verification method, device, terminal and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110853083.9A CN113556770A (en) | 2021-07-27 | 2021-07-27 | Data verification method, device, terminal and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113556770A true CN113556770A (en) | 2021-10-26 |
Family
ID=78104621
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110853083.9A Pending CN113556770A (en) | 2021-07-27 | 2021-07-27 | Data verification method, device, terminal and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113556770A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114326371A (en) * | 2022-03-16 | 2022-04-12 | 天津德科智控股份有限公司 | Method for redundant communication between MCU (microprogrammed control Unit) chips of EPS (electric Power storage) system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102567276A (en) * | 2011-12-19 | 2012-07-11 | 华为技术有限公司 | Data transmission method based on multiple channels, related nodes and system |
| CN105791288A (en) * | 2016-03-02 | 2016-07-20 | 中国人民解放军信息工程大学 | Key virtual link protection method based on multiple parallel paths |
| CN107122477A (en) * | 2017-05-02 | 2017-09-01 | 成都中远信电子科技有限公司 | A kind of block chain storage system |
| WO2018126984A2 (en) * | 2017-01-06 | 2018-07-12 | 江南大学 | Mea-bp neural network-based wsn abnormality detection method |
| CN109117300A (en) * | 2018-07-03 | 2019-01-01 | 千寻位置网络有限公司 | Method of calibration and system, the positioning terminal of data |
| CN111885022A (en) * | 2020-07-09 | 2020-11-03 | 河南信大网御科技有限公司 | Mimicry communication method based on communication interface, communication architecture and terminal equipment |
-
2021
- 2021-07-27 CN CN202110853083.9A patent/CN113556770A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102567276A (en) * | 2011-12-19 | 2012-07-11 | 华为技术有限公司 | Data transmission method based on multiple channels, related nodes and system |
| CN105791288A (en) * | 2016-03-02 | 2016-07-20 | 中国人民解放军信息工程大学 | Key virtual link protection method based on multiple parallel paths |
| WO2018126984A2 (en) * | 2017-01-06 | 2018-07-12 | 江南大学 | Mea-bp neural network-based wsn abnormality detection method |
| CN107122477A (en) * | 2017-05-02 | 2017-09-01 | 成都中远信电子科技有限公司 | A kind of block chain storage system |
| CN109117300A (en) * | 2018-07-03 | 2019-01-01 | 千寻位置网络有限公司 | Method of calibration and system, the positioning terminal of data |
| CN111885022A (en) * | 2020-07-09 | 2020-11-03 | 河南信大网御科技有限公司 | Mimicry communication method based on communication interface, communication architecture and terminal equipment |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114326371A (en) * | 2022-03-16 | 2022-04-12 | 天津德科智控股份有限公司 | Method for redundant communication between MCU (microprogrammed control Unit) chips of EPS (electric Power storage) system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP2012161085A (en) | Apparatus and method for improving reliability of sensor data collected over network | |
| CN110602723B (en) | Two-stage bidirectional prediction data acquisition method based on underwater edge equipment | |
| JP2020532238A (en) | Systems and methods for predicting communication link quality | |
| CN103259696A (en) | Network bandwidth detecting method and device and network devices | |
| CN107040470B (en) | Low-orbit satellite link topology state data updating method and device | |
| CN113328784B (en) | Paging method, system, device and medium for low-orbit satellite based on 5G core network | |
| Jing et al. | Energy management and power allocation for underwater acoustic sensor network | |
| Jiang et al. | A space–time graph based multipath routing in disruption-tolerant earth-observing satellite networks | |
| CN113556770A (en) | Data verification method, device, terminal and readable storage medium | |
| KR101226012B1 (en) | System and method for transmiting/receiving data in satellite communication environments | |
| CN114978357B (en) | Instant circulation and interaction processing method for underwater sound data and computing equipment thereof | |
| EP4018571A1 (en) | Non-terrestrial network link adaptation | |
| CN112332903A (en) | Congestion control method, device, terminal and medium for satellite link | |
| CN116527565A (en) | Internet route optimization method and device based on graph convolution neural network | |
| CN113923743B (en) | Routing method, device, terminal and storage medium for electric power underground pipe gallery | |
| CN107561930B (en) | External ballistic networking test guidance control method | |
| CN116827846A (en) | Routing, routing path, multicast routing path decision method and electronic equipment | |
| CN108390764B (en) | Broadcast content repacking method and system for broadcast storage network | |
| Charalambous et al. | Average consensus in the presence of dynamically changing directed topologies and time delays | |
| CN115329990A (en) | Asynchronous federated learning acceleration method based on model segmentation under edge calculation scene | |
| Liu et al. | Fusion of state estimates over long-haul sensor networks under random delay and loss | |
| FR2844407A1 (en) | TRANSMISSION CHANNEL SELECTION METHOD AND ANTENNA DIVERSITY SIGNAL RECEIVER | |
| CN113746525A (en) | Link switching control method and control equipment | |
| CN112019443A (en) | Multi-path data transmission method and device | |
| CN115767417A (en) | Smart city water quality supervision method and system, electronic equipment and storage medium |
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: 20211026 |
|
| RJ01 | Rejection of invention patent application after publication |