CN117170249B - Self-adaptive optimal control method and system for networked control system - Google Patents
Self-adaptive optimal control method and system for networked control system Download PDFInfo
- Publication number
- CN117170249B CN117170249B CN202311414732.0A CN202311414732A CN117170249B CN 117170249 B CN117170249 B CN 117170249B CN 202311414732 A CN202311414732 A CN 202311414732A CN 117170249 B CN117170249 B CN 117170249B
- Authority
- CN
- China
- Prior art keywords
- control system
- network delay
- networked control
- time
- 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
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000012549 training Methods 0.000 claims abstract description 17
- 230000007246 mechanism Effects 0.000 claims abstract description 5
- 230000003044 adaptive effect Effects 0.000 claims description 34
- 230000002159 abnormal effect Effects 0.000 claims description 27
- 238000005457 optimization Methods 0.000 claims description 27
- 238000004364 calculation method Methods 0.000 claims description 11
- 230000009471 action Effects 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 2
- 239000004973 liquid crystal related substance Substances 0.000 claims 2
- 230000006978 adaptation Effects 0.000 claims 1
- 238000004458 analytical method Methods 0.000 abstract description 11
- 230000006870 function Effects 0.000 description 46
- 238000012706 support-vector machine Methods 0.000 description 11
- 230000008901 benefit Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000001105 regulatory effect Effects 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 231100001261 hazardous Toxicity 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000004171 remote diagnosis Methods 0.000 description 2
- 238000013024 troubleshooting Methods 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000006798 recombination Effects 0.000 description 1
- 238000005215 recombination Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Abstract
The application relates to a self-adaptive optimal control method and a self-adaptive optimal control system for a networked control system, wherein the method comprises the following steps: extracting a historical data set of network delay generated by the networked control system in the historical time from a data packet transmitted by the networked control system in the historical time; building a network delay prediction model based on a support vector mechanism; training a network delay prediction model by using a historical data set; collecting a network delay data set generated by a networked control system at time t and inputting the network delay data set into a network delay prediction model; according to the output result of the network delay prediction model, determining the network delay of the networked control system at the next time t+1 of the time t; and adjusting the control signal sent by the networked control system according to the network delay of the networked control system at the next time t+1. The invention can realize accurate description and analysis pre-judgment of the network delay data trend, and can utilize accurate network delay prediction data to regulate a networked control system.
Description
Technical Field
The present invention relates to the field of networked control, and more particularly, to an adaptive optimal control method and system for a networked control system.
Background
The networked control system is a fully distributed closed-loop real-time control system formed by transmitting data through a communication network, and the main difference between the networked control system and the traditional control system is that the communication network is used for replacing a point-to-point structure of the traditional control system to realize data transmission among components such as a sensor, a controller, an actuator and the like. The communication network is introduced into the control system, so that remote control and resource sharing are conveniently realized, the modularization degree of the system is higher, the installation and maintenance are more convenient and flexible, the expansion is easy, and the cost is lower.
Network delay is one of the common problems of a networked control system, and due to the limitation of factors such as network communication modes, irregular network load changes, limited network bandwidth and the like, the phenomena such as multipath transmission, data packet collision, data packet retransmission and even connection interruption often occur when data is transmitted in a network, so that the network delay is difficult to avoid. Therefore, a technical scheme suitable for a networked control system is needed, network delay in the networked control system can be predicted, targeted countermeasures can be made, and the networked control system is ensured to normally complete control.
Disclosure of Invention
In order to solve the technical problems, the application is provided to provide the self-adaptive optimization control method and the self-adaptive optimization control system for the networked control system, which can predict the network delay in the networked system and make targeted countermeasures and ensure that the networked control system normally completes control.
In a first aspect, the present invention provides an adaptive optimization control method for a networked control system, including: extracting a historical data set of network delay generated by a networked control system at historical time from data packets transmitted by the networked control system at the historical timeWherein oN, m is an integer; network delay prediction model is built based on support vector mechanism, and the function model of the network delay prediction model is as followsWherein, the method comprises the steps of, wherein,for the function modelIs used as a reference to the weight of the model,for the function modelIs used to determine the deviation value of the first component,for the function modelA kernel function of (a); using the historical datasetTraining the network delay prediction model, and determining a function model of the network delay prediction modelThe weight of (a)And the deviation valueThe method comprises the steps of carrying out a first treatment on the surface of the Collecting a data set of network delay generated by the networked control system at time tInputting the network delay prediction model to obtain a function model of the network delay prediction modelOutput result of (2)The method comprises the steps of carrying out a first treatment on the surface of the Function model according to the network delay prediction modelOutput result of (2)Determining network delay of the networked control system at a time t+1 next to the time tThe method comprises the steps of carrying out a first treatment on the surface of the According to the network delay of the networked control system at the next time t+1And adjusting the control signal sent by the networked control system.
Preferably, the function model is the adaptive optimization control method for the networked control systemKernel function of (a)Wherein H is a preset constant as the function modelKernel function of (a)Is set, is set as a preset parameter of the system.
Preferably, in the foregoing adaptive optimization control method for a networked control system, a historical data set of a network delay generated by the networked control system at a historical time is extracted from a data packet transmitted by the networked control system at the historical timeBefore the step of "further comprises: acquiring a minimum time interval when the networked control system continuously sends out control signalsThe method comprises the steps of carrying out a first treatment on the surface of the According to the minimum time intervalDetermining a maximum computation time consumption allowed by the network delay predictive model from receiving an input to generating an outputThe method comprises the steps of carrying out a first treatment on the surface of the Time consuming according to the maximum calculationCalculating the historical data set received by the network delay prediction modelM value ofWherein, the method comprises the steps of, wherein,is a preset constant.
Preferably, in the foregoing adaptive optimization control method for a networked control system, a historical data set of a network delay generated by the networked control system at a historical time is extracted from a data packet transmitted by the networked control system at the historical timeBefore the step of "further comprises: extracting an abnormal data packet transmitted when the networked control system is abnormal; identifying data content causing an anomaly from the anomaly data packet; and retrieving and filtering out data packets containing the abnormal data content from the data packets transmitted by the networked control system in the historical time.
Preferably, the step of "identifying the data content causing the anomaly from the anomaly data packet" of the adaptive optimization control method for the networked control system includes: identifying a plurality of separators present in the abnormal data packet; splitting all data contents in the abnormal data packet into a plurality of independent execution paragraphs according to the plurality of separators; respectively executing the plurality of independent execution paragraphs in a preset virtual environment; screening independent execution paragraphs with abnormal execution results from the plurality of independent execution paragraphs; and taking the independent execution paragraph with the abnormal execution result as the abnormal data content.
Preferably, the step of adjusting the control signal sent by the networked control system according to the network delay d (t+1) of the networked control system at the next time t+1 according to the foregoing adaptive optimization control method for the networked control system includes: according to the network delay d (t+1) of the networked control system at the next time t+1, adjusting the sending time of the control signal sent by the networked control system at the next time t+1, wherein the sending time after adjustment。
Preferably, the step of adjusting the control signal sent by the networked control system according to the network delay d (t+1) of the networked control system at the next time t+1 according to the foregoing adaptive optimization control method for the networked control system includes: according to the network delay d (t+1) of the networked control system at the next time t+1, presetting the signal acting time carried in the control signal sent by the networked control system at the next time t+1Adjusting the signal action time after adjustment。
Preferably, the foregoing adaptive optimization control method for a networked control system further includes: according to the network delay of the networked control system at the next time t+1Generating a network delay prompt notice, and sending the network delay prompt notice to other systems which have control relation with the networked control system.
In a second aspect, the present invention provides an adaptive optimal control system for a networked control system, comprising: a historical data set extraction module for extracting a historical data set of network delay generated by a networked control system at a historical time from data packets transmitted by the networked control system at the historical timeWherein oN, m is an integer; the network delay prediction model building module is used for building a network delay prediction model based on the support vector mechanism, and the function model of the network delay prediction model is as followsWherein, the method comprises the steps of, wherein,for the function modelIs used as a reference to the weight of the model,for the function modelIs used to determine the deviation value of the first component,for the function modelA kernel function of (a); a network delay prediction model training module, which uses the historical data setTraining the network delay prediction model, and determining a function model of the network delay prediction modelThe weight of (a)And the deviation valueThe method comprises the steps of carrying out a first treatment on the surface of the The network delay prediction model output module is used for collecting a network delay data set generated by the networked control system at time tInputting the network delay prediction model to obtain a function model of the network delay prediction modelOutput result of (2)The method comprises the steps of carrying out a first treatment on the surface of the Network delay determinationThe determining module is used for determining a function model according to the network delay prediction modelOutput result of (2)Determining network delay of the networked control system at a time t+1 next to the time tThe method comprises the steps of carrying out a first treatment on the surface of the The control signal adjusting module is used for adjusting the network delay of the networked control system at the next time t+1And adjusting the control signal sent by the networked control system.
The technical scheme provided by the invention has at least one or more of the following beneficial effects:
according to the technical scheme, a network delay prediction model is built based on a support vector machine, meanwhile, historical network delay information is extracted from historical data packets of a networked control system and used as training data of the network delay prediction model to train the network delay prediction model, the network delay prediction model uses a function model designed according to sequence characteristics of historical network delay, and accurate description and analysis pre-judgment of network delay data trend are achieved through calculation and analysis of known network delay data, so that control signals of the networked control system can be regulated by using accurate network delay prediction data, and the networked control system can be guaranteed to normally complete control.
Drawings
The foregoing and other objects, features and advantages of the present application will become more apparent from the following more particular description of embodiments of the present application, as illustrated in the accompanying drawings. The accompanying drawings are included to provide a further understanding of embodiments of the application and are incorporated in and constitute a part of this specification, illustrate the application and not constitute a limitation to the application. In the drawings, like reference numerals generally refer to like parts or steps.
FIG. 1 is a flow chart of an adaptive optimization control method for a networked control system according to an embodiment of the present application;
FIG. 2 is a partial flow chart of an adaptive optimization control method for a networked control system according to an embodiment of the present application;
FIG. 3 is another partial flow chart of an adaptive optimization control method for a networked control system according to an embodiment of the present application;
FIG. 4 is yet another partial flow chart of an adaptive optimization control method for a networked control system according to an embodiment of the present application;
fig. 5 is a block diagram of an adaptive optimal control system for a networked control system according to an embodiment of the present application.
Detailed Description
Some embodiments of the invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are merely for explaining the technical principles of the present invention, and are not intended to limit the scope of the present invention.
As shown in fig. 1, in one embodiment of the present invention, there is provided an adaptive optimization control method for a networked control system, including:
step S110, extracting a historical data set of network delay generated by the networked control system at the historical time from the data packets transmitted by the networked control system at the historical timeWherein oN, m is an integer.
In this embodiment, the type and use of the networked control system are not limited, and may be used for space and land exploration, access to hazardous areas and related operations, factory automation, remote diagnosis and troubleshooting, laboratory equipment, home robots, aircraft, vehicles, factory monitoring, care centers, remote operations, and the like.
Step S120, constructing a network delay prediction model based on the support vector machine, wherein the function model of the network delay prediction model is as followsWherein, the method comprises the steps of, wherein,is a function modelIs used as a reference to the weight of the model,is a function modelIs used to determine the deviation value of the first component,is a function modelIs a kernel function of (a).
In the embodiment, the support vector machine (Support Vector Machine, SVM) is a generalized linear classifier for binary classification of data according to a supervised learning mode, the decision boundary is the maximum margin hyperplane for solving a learning sample, and compared with other classifiers for machine learning, the support vector machine has relatively high efficiency when being applied to network delay prediction analysis, and meanwhile, the accuracy of analysis results can be ensured.
Step S130, using the historical datasetTraining a network delay prediction model, and determining a function model of the network delay prediction modelWeights in (3)And deviation value。
Step S140, collecting a data set of network delay generated by the networked control system at time tInputting the network delay prediction model to obtain a function model of the network delay prediction modelOutput result of (2)。
In this embodiment, after the training of the network delay prediction model is completed, the network delay prediction model can be used to analyze the network delay of the networked control system in real time.
Step S150, according to the function model of the network delay prediction modelOutput result of (2)Determining network delay of a networked control system at time t+1 next to time t。
Step S160, according to the network delay of the networked control system at the next time t+1And adjusting the control signal sent by the networked control system.
In this embodiment, the manner of adjusting the control signal sent by the networked control system is not limited, so as to eliminate the influence of the network delay on the control behavior of the networked control system.
According to the technical scheme of the embodiment, a network delay prediction model is built based on a support vector machine, meanwhile, historical network delay information is extracted from historical data packets of a networked control system and used as training data of the network delay prediction model to train the network delay prediction model, the network delay prediction model uses a function model designed according to sequence characteristics of historical network delay, and accurate description and analysis pre-judgment of network delay data trend are achieved through calculation and analysis of known network delay data, so that control signals of the networked control system can be regulated by using accurate network delay prediction data, and the networked control system can be guaranteed to complete control normally.
In one embodiment of the present invention, another adaptive optimization control method for a networked control system is provided, and compared to the previous embodiment, the adaptive optimization control method for a networked control system of the present embodiment, a function modelThe kernel function of (a) isWherein H is a preset constant as a function modelKernel function of (a)Is set, is set as a preset parameter of the system.
According to the technical scheme of the embodiment, the adopted function model is a radial basis function, the complexity of the radial basis function is relatively low, so that the network delay prediction model keeps relatively high calculation efficiency, and the method is suitable for rapidly analyzing and predicting the network delay of the networked control system.
As shown in fig. 2, in one embodiment of the present invention, another adaptive optimization control method for a networked control system is provided, and compared to the foregoing embodiment, the adaptive optimization control method for a networked control system of the present embodiment further includes, before step S110:
step S210, obtaining the minimum time interval when the networked control system continuously sends out the control signal。
In this embodiment, the minimum time interval when the networked control system continuously sends out the control signalThe control accuracy of the networked control system is actually reflected.
Step S220, according to the minimum time intervalDetermining a maximum computational time consumption allowed by a network delay prediction model from receiving an input to generating an output。
In this embodiment, when the control accuracy of the networked control system is high, the network delay prediction model is required to have high calculation efficiency, so as to quickly calculate the network delay and make corresponding adjustment to the control signal.
Step S230, according to the maximum calculation time consumptionCalculating a historical dataset received by a network delay prediction modelM value ofWherein, the method comprises the steps of, wherein,is a preset constant.
In this embodiment, when the network delay prediction model has higher calculation efficiency, it is necessarily required that the input dimension of the network delay prediction model is lower, that is, the input dimension is equivalent to the historical data set received by the network delay prediction modelThe value of m is lower, and according to the technical scheme of the embodiment, the network delay is reasonably controlledThe input dimension of the time prediction model is high and low, so that the network delay prediction model is ensured to have higher calculation efficiency.
As shown in fig. 3, in one embodiment of the present invention, another adaptive optimization control method for a networked control system is provided, and compared to the foregoing embodiment, the adaptive optimization control method for a networked control system of the present embodiment further includes, before step S110:
step S310, extracting an abnormal data packet transmitted when the networked control system is abnormal.
In this embodiment, when the networked control system is abnormal, there is an error in data in an abnormal data packet transmitted, and the error is used for negative effects when the network delay prediction model is trained.
In step S320, the data content causing the anomaly is identified from the anomaly data packet.
Step S330, retrieving and filtering the data packet containing the abnormal data content from the data packets transmitted by the networked control system in the historical time.
According to the technical scheme of the embodiment, after the data packets containing abnormal data contents are filtered from the data packets transmitted by the networked control system in the historical time, the data quality of training data of the network delay prediction model is effectively improved, and the high-performance network delay prediction model is obtained through training.
As shown in fig. 4, in one embodiment of the present invention, another adaptive optimization control method for a networked control system is provided, and, with respect to the foregoing embodiment, step S320 includes:
in step S410, a plurality of separators present in the abnormal data packet are identified.
In this embodiment, it is easily understood by those skilled in the art that the data packet has a separator in the format of a semicolon, a space, etc., and separates the data content in the data packet into segments that can be executed independently.
In step S420, all data contents in the abnormal data packet are split into a plurality of independent execution paragraphs according to the plurality of separators.
Step S430, executing a plurality of independent execution paragraphs in the preset virtual environment respectively.
In this embodiment, a virtual machine may be used to build an execution environment for executing multiple independent execution paragraphs, and execution results of the multiple independent execution paragraphs are obtained through a virtual machine technology.
Step S440, the independent execution paragraphs with abnormal execution result are screened from the plurality of independent execution paragraphs.
In step S450, the independent execution segment with abnormal execution result is taken as the data content causing the abnormality.
According to the technical scheme of the embodiment, the data content in the data packet is split into sections which can be executed independently, the execution result of each section is obtained through the virtual machine execution, and the independent execution section with abnormal execution result is screened out and used as the data content causing the abnormality.
In one embodiment of the present invention, another adaptive optimization control method for a networked control system is provided, and, relative to the foregoing embodiment, step S160 includes:
according to the network delay d (t+1) of the networked control system at the next time t+1, the sending time of the control signal sent by the networked control system at the next time t+1 is adjusted, and the adjusted sending time is adjusted。
According to the technical scheme of the embodiment, the sending time of the control signal sent by the networked control system is adjusted, the influence of network delay on the sending time of the control signal is overcome, and the control signal is sent to the target system according to the expected time.
In one embodiment of the present invention, another adaptive optimization control method for a networked control system is provided, and, relative to the foregoing embodiment, step S160 includes:
according to the network delay d (t+1) of the networked control system at the next time t+1, presetting the signal acting time carried in the control signal sent out by the networked control system at the next time t+1Adjusting the signal action time after adjustment。
According to the technical scheme of the embodiment, the signal acting time carried by the control signal sent by the networked control system is adjusted, the influence of network delay on the acting time of the control signal is overcome, and the control signal acts on control according to the expected time.
In one embodiment of the present invention, another adaptive optimization control method for a networked control system is provided, and compared to the foregoing embodiment, the adaptive optimization control method for a networked control system of the present embodiment further includes:
according to the network delay of the networked control system at the next time t+1Generating a network delay prompt notice, and sending the network delay prompt notice to other systems which have control relation with the networked control system.
According to the technical scheme of the embodiment, the network delay prompt notification is utilized to notify the network delay of the networked control system to other systems, so that the other systems are beneficial to reasonably processing the received control signals of the networked control system based on the network delay of the networked control system.
As shown in fig. 5, in one embodiment of the present invention, there is provided an adaptive optimal control system for a networked control system, including:
a historical data set extraction module 510 for extracting a historical data set of a network delay generated by the networked control system at a historical time from data packets transmitted by the networked control system at the historical timeWherein oN, m is an integer.
In this embodiment, the type and use of the networked control system are not limited, and may be used for space and land exploration, access to hazardous areas and related operations, factory automation, remote diagnosis and troubleshooting, laboratory equipment, home robots, aircraft, vehicles, factory monitoring, care centers, remote operations, and the like.
The network delay prediction model building module 520 builds a network delay prediction model based on the support vector machine, where the function model of the network delay prediction model isWherein, the method comprises the steps of, wherein,is a function modelIs used as a reference to the weight of the model,is a function modelIs used to determine the deviation value of the first component,is a function modelIs a kernel function of (a).
In the embodiment, the support vector machine (Support Vector Machine, SVM) is a generalized linear classifier for binary classification of data according to a supervised learning mode, the decision boundary is the maximum margin hyperplane for solving a learning sample, and compared with other classifiers for machine learning, the support vector machine has relatively high efficiency when being applied to network delay prediction analysis, and meanwhile, the accuracy of analysis results can be ensured.
Network delay prediction model training module 530 uses historical data setsTraining a network delay prediction model, and determining a function model of the network delay prediction modelWeights in (3)And deviation value。
The network delay prediction model output module 540 collects a data set of network delay generated by the networked control system at time tInputting the network delay prediction model to obtain a function model of the network delay prediction modelOutput result of (2)。
In this embodiment, after the training of the network delay prediction model is completed, the network delay prediction model can be used to analyze the network delay of the networked control system in real time.
The network delay determination module 550 predicts a function model of the model based on the network delayOutput result of (2)Determining network delay of a networked control system at time t+1 next to time t。
The control signal adjusting module 560 is used for adjusting the network delay of the next time t+1 according to the networked control systemAnd adjusting the control signal sent by the networked control system.
In this embodiment, the manner of adjusting the control signal sent by the networked control system is not limited, so as to eliminate the influence of the network delay on the control behavior of the networked control system.
According to the technical scheme of the embodiment, a network delay prediction model is built based on a support vector machine, meanwhile, historical network delay information is extracted from historical data packets of a networked control system and used as training data of the network delay prediction model to train the network delay prediction model, the network delay prediction model uses a function model designed according to sequence characteristics of historical network delay, and accurate description and analysis pre-judgment of network delay data trend are achieved through calculation and analysis of known network delay data, so that control signals of the networked control system can be regulated by using accurate network delay prediction data, and the networked control system can be guaranteed to complete control normally.
The basic principles of the present application have been described above in connection with specific embodiments, however, it should be noted that the advantages, benefits, effects, etc. mentioned in the present application are merely examples and not limiting, and these advantages, benefits, effects, etc. are not to be considered as necessarily possessed by the various embodiments of the present application. Furthermore, the specific details disclosed herein are for purposes of illustration and understanding only, and are not intended to be limiting, as the application is not intended to be limited to the details disclosed herein as such.
The block diagrams of the devices, apparatuses, devices, systems referred to in this application are only illustrative examples and are not intended to require or imply that the connections, arrangements, configurations must be made in the manner shown in the block diagrams. As will be appreciated by one of skill in the art, the devices, apparatuses, devices, systems may be connected, arranged, configured in any manner. Words such as "including," "comprising," "having," and the like are words of openness and mean "including but not limited to," and are used interchangeably therewith. The terms "or" and "as used herein refer to and are used interchangeably with the term" and/or "unless the context clearly indicates otherwise. The term "such as" as used herein refers to, and is used interchangeably with, the phrase "such as, but not limited to.
It is also noted that in the apparatus, devices and methods of the present application, the components or steps may be disassembled and/or assembled. Such decomposition and/or recombination should be considered as equivalent to the present application.
The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the application. Thus, the present application is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
The foregoing description has been presented for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of the application to the form disclosed herein. Although a number of example aspects and embodiments have been discussed above, a person of ordinary skill in the art will recognize certain variations, modifications, alterations, additions, and subcombinations thereof.
Claims (7)
1. An adaptive optimization control method for a networked control system, comprising:
extracting a historical data set of network delay generated by a networked control system at historical time from data packets transmitted by the networked control system at the historical timeWherein o->N, m is an integer;
network delay prediction model is built based on support vector mechanism, and the function model of the network delay prediction model is as followsWherein->For the function model->Weights of->For the function model->Deviation value of>For the function model->A kernel function of (a);
using the historical datasetTraining the network delay prediction model, and determining a function model of the network delay prediction model>The weight of +.>And the deviation value +.>；
Collecting network delay generated by the networked control system at time tIs a data set of (2)And inputting the network delay prediction model to obtain a function model of the network delay prediction model>Output result of +.>；
Function model according to the network delay prediction modelOutput result of +.>Determining a network delay of the networked control system at a time t+1 next to the time t>；
According to the network delay of the networked control system at the next time t+1Adjusting the control signal sent by the networked control system,
wherein the function modelThe kernel function of (a) is->Wherein H is a preset constant as the function model +.>Kernel function->Is used for the control of the temperature of the liquid crystal display device,
wherein, extracting the historical data set of the network delay generated by the networked control system at the historical time from the data packet transmitted by the networked control system at the historical timeBefore the step of "further comprises:
acquiring a minimum time interval when the networked control system continuously sends out control signals；
According to the minimum time intervalDetermining the maximum computational time allowed by said network delay prediction model from receiving input to generating output>；
Time consuming according to the maximum calculationCalculating said historical dataset received by said network delay prediction model +.>M value of
Wherein->Is a preset constant.
2. The adaptation for a networked control system of claim 1The optimized control method is characterized in that a historical data set of network delay generated by a networked control system at historical time is extracted from data packets transmitted by the networked control system at the historical timeBefore the step of "further comprises:
extracting an abnormal data packet transmitted when the networked control system is abnormal;
identifying data content causing an anomaly from the anomaly data packet;
and retrieving and filtering out data packets containing the abnormal data content from the data packets transmitted by the networked control system in the historical time.
3. The adaptive optimal control method for a networked control system according to claim 2, wherein the step of identifying the data content causing the anomaly from the anomaly data packet includes:
identifying a plurality of separators present in the abnormal data packet;
splitting all data contents in the abnormal data packet into a plurality of independent execution paragraphs according to the plurality of separators;
respectively executing the plurality of independent execution paragraphs in a preset virtual environment;
screening independent execution paragraphs with abnormal execution results from the plurality of independent execution paragraphs;
and taking the independent execution paragraph with the abnormal execution result as the abnormal data content.
4. The adaptive optimal control method for a networked control system according to claim 1, wherein the step of adjusting the control signal sent by the networked control system according to the network delay d (t+1) of the networked control system at the next time t+1 includes:
according to the networked control systemThe network delay d (t+1) of the next time t+1 adjusts the sending time of the control signal sent by the networked control system at the next time t+1, and the adjusted sending time。
5. The adaptive optimal control method for a networked control system according to claim 1, wherein the step of adjusting the control signal sent by the networked control system according to the network delay d (t+1) of the networked control system at the next time t+1 includes:
according to the network delay d (t+1) of the networked control system at the next time t+1, presetting the signal acting time carried in the control signal sent by the networked control system at the next time t+1Adjusting, the signal action time after adjustment>。
6. The adaptive optimal control method for a networked control system according to claim 1, further comprising:
according to the network delay of the networked control system at the next time t+1Generating a network delay prompt notice, and sending the network delay prompt notice to other systems which have control relation with the networked control system.
7. An adaptive optimal control system for a networked control system, comprising:
historical dataset extraction modelA block for extracting a historical data set of network delay generated by the networked control system at the historical time from data packets transmitted by the networked control system at the historical timeWherein o->N, m is an integer;
the network delay prediction model building module is used for building a network delay prediction model based on the support vector mechanism, and the function model of the network delay prediction model is as followsWherein->For the function model->Weights of->For the function model->Deviation value of>For the function model->A kernel function of (a);
a network delay prediction model training module, which uses the historical data setTraining the network delay prediction model, and determining a function model of the network delay prediction model>The weight of +.>And the deviation value𝑏/>；
The network delay prediction model output module is used for collecting a network delay data set generated by the networked control system at time tAnd inputting the network delay prediction model to obtain a function model of the network delay prediction model>Output result of +.>；
The network delay determining module is used for determining a function model according to the network delay prediction modelOutput result of +.>Determining a network delay of the networked control system at a time t+1 next to the time t>；
The control signal adjusting module is used for adjusting the network delay of the networked control system at the next time t+1Adjusting the control signal sent by the networked control system,
wherein the function modelThe kernel function of (a) is->Wherein H is a preset constant as the function model +.>Kernel function->Is used for the control of the temperature of the liquid crystal display device,
wherein, extracting the historical data set of the network delay generated by the networked control system at the historical time from the data packet transmitted by the networked control system at the historical timeBefore the step of "further comprises:
acquiring a minimum time interval when the networked control system continuously sends out control signals；
According to the minimum time intervalDetermining the maximum computational time allowed by said network delay prediction model from receiving input to generating output>；
Time consuming according to the maximum calculationCalculating said historical dataset received by said network delay prediction model +.>M value of
Wherein->Is a preset constant.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311414732.0A CN117170249B (en) | 2023-10-30 | 2023-10-30 | Self-adaptive optimal control method and system for networked control system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311414732.0A CN117170249B (en) | 2023-10-30 | 2023-10-30 | Self-adaptive optimal control method and system for networked control system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117170249A CN117170249A (en) | 2023-12-05 |
| CN117170249B true CN117170249B (en) | 2024-01-16 |
Family
ID=88945293
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311414732.0A Active CN117170249B (en) | 2023-10-30 | 2023-10-30 | Self-adaptive optimal control method and system for networked control system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117170249B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117518838B (en) * | 2024-01-05 | 2024-03-29 | 铵泰克（北京）科技有限公司 | Control method and system for output stability of networked control system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104503229A (en) * | 2014-11-24 | 2015-04-08 | 北京邮电大学 | Wave integral bilateral teleoperation control method based on LS-SVM (least square support vector machine) delay predication |
| EP3112960A1 (en) * | 2015-06-29 | 2017-01-04 | SUEZ Groupe | Combined method for detecting anomalies in a water distribution system |
| CN111367908A (en) * | 2020-02-27 | 2020-07-03 | 铵泰克（北京）科技有限公司 | Incremental intrusion detection method and system based on security assessment mechanism |
| CN113134828A (en) * | 2020-01-17 | 2021-07-20 | 中国科学院长春光学精密机械与物理研究所 | Positioning tracking system and time delay compensation method based on linear trend prediction |
| CN116894469A (en) * | 2023-09-11 | 2023-10-17 | 西南林业大学 | DNN collaborative reasoning acceleration method, device and medium in end-edge cloud computing environment |
-
2023
- 2023-10-30 CN CN202311414732.0A patent/CN117170249B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104503229A (en) * | 2014-11-24 | 2015-04-08 | 北京邮电大学 | Wave integral bilateral teleoperation control method based on LS-SVM (least square support vector machine) delay predication |
| EP3112960A1 (en) * | 2015-06-29 | 2017-01-04 | SUEZ Groupe | Combined method for detecting anomalies in a water distribution system |
| CN113134828A (en) * | 2020-01-17 | 2021-07-20 | 中国科学院长春光学精密机械与物理研究所 | Positioning tracking system and time delay compensation method based on linear trend prediction |
| CN111367908A (en) * | 2020-02-27 | 2020-07-03 | 铵泰克（北京）科技有限公司 | Incremental intrusion detection method and system based on security assessment mechanism |
| CN116894469A (en) * | 2023-09-11 | 2023-10-17 | 西南林业大学 | DNN collaborative reasoning acceleration method, device and medium in end-edge cloud computing environment |
Non-Patent Citations (1)
| Title |
|---|
| 基于LS-SVM的网络化控制系统自适应预测控制;李春茂 等;系统仿真学报;第19卷(第15期);3494-3498、3502 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117170249A (en) | 2023-12-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117170249B (en) | Self-adaptive optimal control method and system for networked control system | |
| US11275345B2 (en) | Machine learning Method and machine learning device for learning fault conditions, and fault prediction device and fault prediction system including the machine learning device | |
| US10884383B2 (en) | Advanced control systems for machines | |
| Liu et al. | A survey of event-based strategies on control and estimation | |
| CN110023850B (en) | Method and control device for controlling a technical system | |
| EP1672535A1 (en) | Distributed intelligent diagnostic scheme | |
| US11270218B2 (en) | Mapper component for a neuro-linguistic behavior recognition system | |
| WO2018157951A1 (en) | A method and apparatus for key performance indicator forecasting using artificial life | |
| JP2019012555A (en) | Artificial intelligence module development system and artificial intelligence module development integration system | |
| WO2015138706A1 (en) | Distributed big data in a process control system | |
| EP3312695B1 (en) | Information processing system, information processing method, information processing program, and recording medium | |
| US20210166083A1 (en) | Methods, devices, and computer program products for model adaptation | |
| US20220156574A1 (en) | Methods and systems for remote training of a machine learning model | |
| CN112202783A (en) | 5G network anomaly detection method and system based on adaptive deep learning | |
| CN116628633A (en) | IGBT real-time monitoring and service life prediction evaluation method | |
| CN115136080A (en) | Method, system and apparatus for intelligently simulating plant control systems and simulating response data | |
| Tham et al. | Active learning for IoT data prioritization in edge nodes over wireless networks | |
| JP2023106444A (en) | Information processing system, information processing method, and information processing device | |
| CN113379135A (en) | Intelligent production line product quality low-delay integrated prediction method and system based on cloud edge collaborative computing | |
| Wang et al. | Model predictive control with input disturbance and guaranteed Lyapunov stability for controller approximation | |
| EP3905642A1 (en) | Communicating parameters based on a change | |
| JP2021144415A (en) | Information processing method, information processing apparatus, failure determination system, failure determination apparatus, failure determination method, and program | |
| Dorneanu et al. | Towards fault detection and self-healing of chemical processes over wireless sensor networks | |
| Dorneanu et al. | Monitoring of smart chemical processes: A Sixth Sense approach | |
| Dorneau et al. | Stepping towards the industrial Sixth Sense |
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 |