CN113721565A - Industry internet controlgear with adjustable - Google Patents
Industry internet controlgear with adjustable Download PDFInfo
- Publication number
- CN113721565A CN113721565A CN202110876544.4A CN202110876544A CN113721565A CN 113721565 A CN113721565 A CN 113721565A CN 202110876544 A CN202110876544 A CN 202110876544A CN 113721565 A CN113721565 A CN 113721565A
- Authority
- CN
- China
- Prior art keywords
- particle
- data
- resource
- value
- equipment
- 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
- 239000002245 particle Substances 0.000 claims abstract description 82
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 25
- 238000000034 method Methods 0.000 claims abstract description 22
- 238000012544 monitoring process Methods 0.000 claims abstract description 6
- 238000012360 testing method Methods 0.000 claims description 39
- 238000007726 management method Methods 0.000 claims description 15
- 238000011161 development Methods 0.000 claims description 12
- 238000012546 transfer Methods 0.000 claims description 12
- 230000000007 visual effect Effects 0.000 claims description 12
- 238000005457 optimization Methods 0.000 claims description 11
- 238000005516 engineering process Methods 0.000 claims description 10
- 238000004891 communication Methods 0.000 claims description 7
- 238000001514 detection method Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000003745 diagnosis Methods 0.000 claims description 4
- 230000001133 acceleration Effects 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000002790 cross-validation Methods 0.000 claims description 3
- 238000013500 data storage Methods 0.000 claims description 3
- 238000009826 distribution Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000011176 pooling Methods 0.000 claims description 3
- 238000013468 resource allocation Methods 0.000 claims description 3
- 238000009827 uniform distribution Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract 1
- 230000002159 abnormal effect Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 239000003795 chemical substances by application Substances 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 238000011157 data evaluation Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 244000144992 flock Species 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000004148 unit process Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/41885—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by modeling, simulation of the manufacturing system
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/32—Operator till task planning
- G05B2219/32339—Object oriented modeling, design, analysis, implementation, simulation language
-
- 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]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Automation & Control Theory (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The utility model discloses an adjustable industrial internet control device, belongs to the technical field of industrial internet of things, and comprises an improved particle swarm algorithm integrated into the device, wherein a NET Framework + C # heterogeneous system is adopted in a control device system, and the NET Framework is used for rich display components, so that the reliability and stability of the device are improved. The method and the device have the effects of realizing real-time monitoring of the state of the industrial Internet of things equipment, real-time scanning of operation risks, diagnosing equipment faults, displaying the state of the equipment in real time, optimizing the operation of the equipment and automatically analyzing reports.
Description
Technical Field
The application relates to the technical field of industrial Internet of things, in particular to adjustable industrial Internet control equipment.
Background
The industrial Internet of things equipment refers to electronic equipment which can be remotely controlled and remotely operated by means of wireless or electric signals in a mode of accessing a network through the Internet and the like, and is mainly applied to the aspects of monitoring, service, diagnosis and the like. Industry thing networking equipment need be on the basis based on the internet, control, wherein, need control through controlgear, current controlgear utilizes information acquisition device to gather relevant construction information, and send information to main control unit through the wireless signal transmitter on, be used for through the computer to main control unit input user demand information, main control unit processes the information of acquireing and generates control instruction information after the analysis, send control instruction information for running gear through wireless signal transmitter, thereby realize the control to construction equipment.
For the related technologies, the inventor thinks that there is a command generation error in the industrial internet of things control device, and after the command is generated, both the correct command and the incorrect command are directly sent to the device side, so that the correctness of the control command information cannot be guaranteed, and the construction risk is high.
Disclosure of Invention
In order to overcome the defects in the prior art, the application provides adjustable industrial internet control equipment.
The application provides an industry internet control equipment with adjustable adopts following technical scheme: the method comprises the steps of integrating an improved particle swarm algorithm into control equipment, wherein a NET Framework + C # heterogeneous system is adopted in a system of the control equipment, applying NET Framework rich display components, improving the reliability and stability of a platform, dividing the control equipment into a service supporting layer, an application system layer, a basic platform layer and a data resource layer, building a resource system of the control equipment and a control system cloud basic Framework, carrying out related virtualization and data center network calculation, and achieving flexible management and distribution of system scheduling, safety and resources through a standardized interface.
According to the technical scheme, the NET Framework component is mainly used for realizing panoramic Visual display of a communication scheduling picture, Visual Studio 2010 is used for realizing development of a Visual system, and the application system layer provides a unified call interface agent service;
furthermore, the service support layer mainly provides interface service for service logic access between the application layer and the application system layer, the application system layer realizes development of middleware such as data acquisition, interface management, timing scheduling and the like based on a C # technology, and the application system layer realizes information transmission between the data resource layer and the service support layer through an interface by a NetBEUI protocol;
furthermore, the basic platform layer provides resources such as calculation, storage and the like required by the user, and realizes resource allocation and rapid deployment as required through resource pooling by technologies such as virtualization and the like;
furthermore, the data resource layer is a visual database and stores information of different application systems, including equipment detection test information, equipment operation and fault information.
According to the technical scheme, the cloud infrastructure pools server resources into a computing resource pool, a network resource pool, a storage resource pool and an application resource pool through a virtualization technology, meanwhile, a unified management network is built through a switch to achieve automatic scheduling and allocation of resources, and the cloud infrastructure receives an application instruction and issues a control command through an interface A; the data resource pool receives the control command through the interface B, executes the instrument operation and uploads the test result; the equipment to be tested receives the configuration command through the interface C and returns state information; the personal cloud desktop applies for testing instrument resources, storage resources and computing resources through an interface D, and control and operation of the data network automatic testing system are achieved; the SVN software version control system synchronizes the version codes of the data network automation test system in real time through the interface E, so that collaborative development is realized, and the backtracking can be effectively tracked in the software life cycle.
Through the technical scheme, the cloud infrastructure checks the personal resource application, if the current resource meets the application requirement, the resource is distributed according to the applied resource, otherwise, the related application is rejected; after the resource application of the detection personnel is approved, the execution of the automatic test system can be controlled by the management software of the test instrument; and after the test is finished, processing the test data and the test result and releasing the applied resources.
According to the technical scheme, the scheduling of the data of the Internet of things from a single target to multiple targets is completed by utilizing the improved particle swarm optimization, and a fitness function needs to be determined when the scheduling is performed from the multiple targets to the multiple targets:
further, wherein γR(D) For the classification error rate of the selected feature subset R relative to the decision D, | s | is the size of the selected feature subset, | D | represents the total number of features, α and β are two parameters corresponding to the classification accuracy and importance of the selected feature size, α [0,1 ]]And β ═ 1- α;
further, the error rate of the K-NN classifier is used in the fitness function, where each sample is divided into a class of labels to which most of its K neighbors belong. In the classification phase, the data set is typically divided into a training subset and a testing subset. To determine the class of each sample in the test data, the nearest K neighbors of each sample must be computed from the training data, using K-fold cross-validation with K10.
According to the technical scheme, the characteristic selection is carried out by utilizing the multi-population-based particle swarm optimization, each particle in the optimization has two solutions, one solution is randomly generated, and the other solution is generated by a Relieff characteristic sorting method;
the Relieff algorithm is a method for ranking features by calculating the distance from each feature to a target, in the method, each feature is assigned a weight, the range is 1 to +1, the related features are expected to have higher weights, the algorithm searches a solution space by using two solutions at the same time, and then the particles adjust the positions of the particles by using a gBest and pBest solution;
further, in the algorithm, the initial velocity value of the particles is set to zero, and each particle has two initialization solutions, an initial solution, xi,kWhere i is the index k of the particle is the initial type, xi,0Representing two initial solutions xi,kThe random selection selects a number from 0 to 1 based on a uniform distribution, if the value is greater than 0.5, the position is set to 1, otherwise to 0, the terrain ordering method assigns [1,1 ] to each feature]These correlation values are converted to [0,1 ]]An equation.
Further, where θ to U (0, 1), rw is a correlation weight matrix,
is the probability of occurrence of the ith feature, xi,2Initial position generated using Relieff. If the correlation value of any of the characteristics is negative, the global optimal solution of the cluster and the individual optimal solution of each particle are calculated based on the fitness value of the initialized particle assuming that the correlation value of the characteristic is 0.
By the technical scheme, for each particle, a time-varying mirror image sigmoid transfer function is utilized to adjust the next position of the particle,
further, in the formula, I represents the ith particle, k is the initial type, j is the dimension of the characteristic of the ith particle, and w is the inertia weight, which is used for adjusting the balance between the current position and the next position of the particle. c. C1And c2Is the coefficient of acceleration, r1And r2Is a random number between 0 and 1,
is pBestiThe jth position of (1), gBestjIs the jth position of the gBest,
further, the position of the particle is a continuous value, which cannot be directly used for feature selection due to its binary nature, and to solve this problem, the continuous value is converted into a binary value using a transfer function, which is shown below,
further, where σ is σ at the first iterationminσ as σ at the last iterationmaxLinearly increasing, switching smoothly from exploration to development, σ is given as,
further, the next binary position of each transfer function is obtained by using the equation, and the target function is
And
greedy selection is made between them. Then, the optimal position is selected as the particle
The next binary position. Will be provided with
Is given to
Further, if the new fitness value is better than the human best experience value for the particle, the pair
And assigning the value of pBesti, and if the value of pBesti is better than the current global best, assigning the value of pBesti to the gBest so as to update the gBest.
Through the technical scheme, the data of the industrial Internet of things come from different conveying systems, so that the data have different structures, and therefore, the data with different structures are processed during communication scheduling, the standards of the data are unified and normalized, and the data storage and access speed is further improved.
To sum up, the method and the device can realize real-time monitoring of the state of the equipment of the internet of things, real-time scanning of operation risks, diagnosis of equipment faults, real-time display of the state of the equipment, and operation optimization and automatic analysis reporting of the equipment. :
drawings
FIG. 1 is a system architecture diagram of the present invention;
FIG. 2 is a diagram of a cloud infrastructure architecture of the present invention;
fig. 3 is a flow chart of updating the particle swarm algorithm of the present invention.
Detailed Description
The technical solution in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application; it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all embodiments, and all other embodiments obtained by those of ordinary skill in the art without any inventive work based on the embodiments in the present application belong to the protection scope of the present application.
In the description of the present application, it should be noted that the terms "upper", "lower", "inner", "outer", "top/bottom", and the like indicate orientations or positional relationships based on those shown in the drawings, and are only for convenience of description and simplification of description, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation, and be operated, and thus should not be construed as limiting the present application. Furthermore, the terms "first" and "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the present application, it is to be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "disposed," "sleeved/connected," "connected," and the like are to be construed broadly, e.g., "connected," which may be fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meaning of the above terms in the present application can be understood in a specific case by those of ordinary skill in the art.
The present application is described in further detail below with reference to the attached drawings.
An adjustable industrial internet control device in an embodiment of the present application is, as shown in fig. 1, configured to integrate an improved particle swarm algorithm into a cloud infrastructure, where a NET Framework + C # heterogeneous system is adopted in a system, and a NET Framework rich presentation component is applied, so as to improve reliability and stability of a platform. The platform is divided into a service supporting layer, an application system layer, a basic platform layer and a data resource layer. And (4) building a cloud infrastructure of the resource system and the control system, and performing related virtualization and data center network computing. And the system scheduling, safety and flexible management and allocation of resources are realized through a standardized interface.
NET Framework components are used for realizing panoramic Visual display of a communication scheduling picture, Visual Studio 2010 is used for realizing development of a Visual system, and the application system layer provides uniform calling interface agent service;
the service support layer mainly provides interface service for service logic access between the application layer and the application system layer. The application system layer realizes the development of middleware such as data acquisition, interface management, timing scheduling and the like based on the C # technology, and mainly comprises a safety service support, a message service support, a form service support and a business service support;
the application system layer realizes information transmission between the application system layer and the data resource layer and between the application system layer and the service supporting layer through an interface by a NetBEUI protocol, and the application system layer mainly comprises a portal website, a cloud end, a comprehensive evaluation system, a data application system and human-computer interaction;
the basic platform layer provides resources such as calculation and storage required by a user, and realizes resource allocation and rapid deployment as required by pooling of the resources through technologies such as virtualization, and the basic platform layer mainly comprises a network and communication system, a large-screen display system, a video monitoring system, an information security system, a call center system, a host storage system and a data backup system;
the data resource layer is a visual database and stores information of different application systems, including equipment detection test information and equipment operation and fault information, and the data resource layer mainly comprises evaluation indexes, data acquisition, data management, data display, data maintenance, interface management and data evaluation.
As shown in fig. 2, further, the cloud infrastructure pools server resources into a computing, network, storage, and application resource pool through a virtualization technology. Meanwhile, a unified management network is built through the switch, and automatic scheduling and allocation of resources are achieved. The cloud infrastructure receives an application instruction and issues a control command through an interface A; the data resource pool receives the control command through the interface C, executes the instrument operation and uploads the test result; the equipment to be tested receives the configuration command through the interface B and returns state information; the personal cloud desktop applies for testing instrument resources, storage resources and computing resources through an interface D, and control and operation of the data network automatic testing system are achieved; the SVN software version control system synchronizes the version codes of the data network automation test system in real time through the interface E, so that collaborative development is realized, and the backtracking can be effectively tracked in the software life cycle.
The scheduling data network adopts a module cooperation mode, the script platform runs the user script and transmits an interface operation instruction to the scheduling management module; after receiving the instruction, the scheduling management module transmits the instruction to the driving platform, sets a waiting clock, and returns abnormal information after timeout; the driving platform analyzes the instruction transmitted by the scheduling management module after receiving the instruction, searches case parameters in the test case topological graph according to the name of the test case, positions interface elements on the tested system through the case parameters, performs related operations, analyzes and judges a return value of the tested system, generates an execution result, transmits the execution result to the scheduling management module, and returns abnormal information if the execution is abnormal; the scheduling management module receives the execution result and then transmits the execution result to the script platform, and waits for the clock to return to zero; and after receiving the returned result and information, the script platform carries out log recording and exception processing and executes the next instruction. Through the design of the cooperation of the distribution modules, the logic of the whole test project is clearer, the expandability is strong, and the maintenance is easy.
Further, the cloud infrastructure checks the personal resource application, if the current resource meets the application requirement, the resource is distributed according to the applied resource, otherwise, the related application is rejected; after the resource application of the detection personnel is approved, the execution of the automatic test system can be controlled by the management software of the test instrument; and after the test is finished, processing the test data and the test result and releasing the applied resources.
Particle Swarm Optimization (PSO) is a meta-heuristic search technique that mimics the motion of a flock of birds to find the food and location of each particle. In particle swarm optimization, each particle represents a population solution and is evaluated by a predefined fitness function. One group is a set of solutions containing N particles. Each particle is a form of a candidate solution having a vector,
d, i and j represent the quantitative characteristics, the population of the index, and the index of the property, respectively. Xi is a binary vector with a value of 1 or 0.
In BPSO, each particle is typically randomly initialized. In the present invention, two initialization techniques, z, are evaluated, namely random initialization and correlation value initialization based on the Relieff sorting method. Particle swarm optimization algorithms find the best solution by adjusting each particle with the personal best and global best information. gBest is the solution with the highest fitness value in the population, and pBest is the solution with the highest fitness value in the particle. The rate of change of position (velocity) of the ith particle is denoted Vi＝{vi1,vi2，vij，...,vid}。vijIs at a predefined value of VmaxAnd VminTo avoid local optimality.
The next velocity vector is calculated using the current velocity, the local best position and the best position of the population (as shown in equation (1)).
Inertia weighted value wmaxInitialization, gradually decreasing to w by equation (2)minWherein
For the position of the ith particle of the jth dimension solution, the invention will c1And c2Set to 2.
To perform feature selection using BPSO, the value of the velocity vector must be converted into a binary string by equation (6). r represents the shapes (s-type and v-type) of the transfer functions in the formulas (3) and (4), and the transfer functions are classified into v-type and s-type according to the shapes.
Tυ(φ)＝|tanh(φ)| (4)
The feature selection can be regarded as a multi-objective optimization problem, and the goal of the feature selection is to realize two mutually contradictory goals; higher classification accuracy and a smaller number of selected features. The goal is to achieve better accuracy with a minimum number of features, usually with classification error as the evaluation function. However, for feature selection, the number of selected features should also be considered in the merit function. To this end, the present invention employs the fitness function given in equation (7).
Wherein gamma isR(D) For the classification error rate of the selected feature subset R with respect to the decision D, | s | is the size of the selected feature subset. | d | represents the total number of characteristics. Alpha and beta are two parameters corresponding to the classification accuracy and importance of the selected feature size, alpha 0,1]And β ═ 1- α. In the present invention, the significant impact weight is assigned to the classification accuracy rather than the number of attributes.
In the present invention, the error rate of the K-NN classifier is used in the fitness function. In K-NN, each sample is divided into a class of labels to which its K neighbors mostly belong. In the classification phase, the data set is typically divided into a training subset and a testing subset. To determine the class of each sample in the test data, the nearest k neighbors of each sample must be computed from the training data. In the present invention, K-fold cross-validation with K-10 was used.
Conventional particle swarm algorithms typically start with a randomly generated population. However, particle swarm algorithms are sensitive to initialization and tend to fall into local optima, especially in high-dimensional feature spaces. In the present invention, in order to make the search space more diversified, we propose a particle swarm algorithm based on multiple clusters to perform feature selection. In the algorithm, each particle has two solutions, one solution is randomly generated, and the other solution is generated by a Relieff characteristic sorting method.
The Relieff algorithm is a method of sorting features by calculating the distance of each feature to a target. In this method, each feature is assigned a weight, ranging from 1 to + 1. It is desirable that the relevant features have a higher weight. The algorithm searches the solution space with both solutions simultaneously. The particle then adjusts its position using the gBest and pBest solutions. PiThe ith particle is shown. Xi,0And vi,0Current position and velocity, respectively, and Xi,1And Xi,2Are competing solutions initialized by different initialization techniques. Vi，1And Vi，2Is the speed of the solution, algorithm 3 also gives details of the algorithm.
In this algorithm, the initial velocity value of the particle is set to zero, with two initialization solutions per particle. Initial solution, xi,kWhere i is the index k of the particle is the initial type. x is the number ofi,0Representing two initial solutions xi,kThe best solution of (1). The random selection selects a number from 0 to 1 based on a uniform distribution. If the value is greater than 0.5, the position is set to 1, otherwise it is set to 0. The terrain ordering method assigns a value of [1,1 ] to each feature]. These correlation values are converted to [0,1 ]]Equations (8) and (9).
Wherein, theta to U (0, 1), rw is the correlation weight matrix,
is the probability of occurrence of the ith feature, xi,2Initial position generated using Relieff. Note that if the correlation value of any characteristic is negative, the correlation value of the characteristic is assumed to be 0.
And calculating a global optimal solution of the group and a personal optimal solution of each particle according to the fitness value of the initialized particle. The initial solution generation mechanism of the method is given.
For each particle, the new velocity is calculated according to equation (10). In order to adjust the next position of the particle, a time-varying mirror sigmoid transfer function is proposed, and good results are obtained for the binary problem. In the present invention, we modify the function to be able to handle the feature selection of multiple populations.
And
are obtained from the formulae (11) and (12), respectively. Passing through type(16) Selecting
And
the best position in between as the next position. The suboptimal solution (gBest) is updated based on these new particle fitness values.
In the formula, I represents the ith particle, k is the initial type, j is the dimension of the characteristic of the ith particle, and w is the inertia weight, and is used for adjusting the balance between the current position and the next position of the particle. c. C1And c2Is the coefficient of acceleration, r1And r2Is a random number between 0 and 1.
Is pBestiThe jth position of (1), gBestjIs the jth position of gBest.
The position of the particle is a continuous value that cannot be used directly for feature selection due to its binary nature. To solve this problem, a transfer function is used to convert successive values into binary values. The transfer function is shown in equations (13) and (14).
Wherein, sigma is sigma min in the first iteration, and sigma linearly increases along with sigma max in the last iteration, and the exploration and the development are smoothly switched. σ is given as
The next binary position of each transfer function is obtained using the equation. Respectively (11) and (12). Then, based on the objective function as shown in equation (16), in
And
greedy selection is made between them. Then, the optimal position is selected as the particle
The next binary position. Will be provided with
Is given to
If the new fitness value is better than the human best experience value for the particle, then the pair
The value is assigned pBesti. If pBesti is better than the current global best, pBesti is assigned to gBest, thereby updating gBest.
The step of finding the optimal solution is as follows, as shown in FIG. 3
Step 1: and randomly generating n particles, and initializing the initial positions of the n particles in the population, wherein the dimension of each particle is the same as that of the search space.
Step 2: and (4) carrying out constraint condition processing, calculating the fitness of each particle, forming an individual optimal value solution set and a global optimal value solution set according to the non-domination relation, and storing data.
And step 3: and determining an individual optimal value and a global optimal value of each particle through the dominance relation and the crowding distance.
And 4, step 4: and adjusting the position of each particle by combining a position updating formula of the improved particle swarm optimization. And judging whether the position meets the constraint condition, if not, the position needs to be adjusted.
And 5: and updating external storage data, storing the non-dominated solution set and deleting the dominated solution.
Step 6: and updating the global optimal solution and the individual optimal solution. And (3) stopping iteration after the algorithm reaches the maximum iteration times or meets the iteration requirement, and returning to the step 2 if the iteration ending condition is not met.
Because the data of the internet of things come from different conveying systems, the data have different structures, and therefore the data of the different structures are processed during communication scheduling, so that the standards are unified and normalized, and the data storage and access speed is further improved, thereby realizing real-time monitoring of the equipment state of the internet of things, real-time scanning of operation risks, equipment fault diagnosis, real-time equipment state display, operation optimization of equipment and automatic analysis reporting.
The above embodiments are preferred embodiments of the present application, and the protection scope of the present application is not limited by the above embodiments, so: all equivalent changes made according to the structure, shape and principle of the present application shall be covered by the protection scope of the present application.
Claims (8)
1. The utility model provides an industry internet controlgear with adjustable which characterized in that: the method comprises the steps of integrating an improved particle swarm algorithm into control equipment, wherein a NET Framework + C # heterogeneous system is adopted in a system of the control equipment, applying NET Framework rich display components, improving the reliability and stability of a platform, dividing the control equipment into a service supporting layer, an application system layer, a basic platform layer and a data resource layer, building a resource system of the control equipment and a control system cloud basic Framework, carrying out related virtualization and data center network calculation, and achieving flexible management and distribution of system scheduling, safety and resources through a standardized interface.
2. The adjustable industrial internet control device as claimed in claim 1, wherein: NET Framework components are used for realizing panoramic Visual display of frames of communication scheduling, Visual Studio 2010 is used for realizing development of a Visual system, and the layer provides uniform calling interface proxy service;
the service supporting layer mainly provides interface service for service logic access between the application layer and the application system layer, the application system layer realizes development of middleware such as data acquisition, interface management, timing scheduling and the like based on a C # technology, and the application system layer realizes information transmission between the data resource layer and the service supporting layer through an interface by a NetBEUI protocol;
the basic platform layer provides resources such as calculation, storage and the like required by the user for the user, and realizes resource allocation and rapid deployment as required through resource pooling by technologies such as virtualization and the like;
the data resource layer is a visual database and stores information of different application systems, including equipment detection test information, equipment operation and fault information.
3. The adjustable industrial internet control device as claimed in claim 1, wherein: the cloud infrastructure pools server resources into a computing resource pool, a network resource pool, a storage resource pool and an application resource pool through a virtualization technology, meanwhile, a unified management network is built through a switch to achieve automatic scheduling and allocation of resources, and the cloud infrastructure receives an application instruction and issues a control command through an interface A; the data resource pool receives the control command through the interface B, executes the instrument operation and uploads the test result; the equipment to be tested receives the configuration command through the interface C and returns state information; the personal cloud desktop applies for testing instrument resources, storage resources and computing resources through an interface D, and control and operation of the data network automatic testing system are achieved; the SVN software version control system synchronizes the version codes of the data network automation test system in real time through the interface E, so that collaborative development is realized, and the backtracking can be effectively tracked in the software life cycle.
4. The adjustable industrial internet control device as claimed in claim 1, wherein: the cloud infrastructure checks the personal resource application, if the current resource meets the application requirement, the resource is distributed according to the applied resource, otherwise, the relevant application is rejected; after the resource application of the detection personnel is approved, the execution of the automatic test system can be controlled by the management software of the test instrument; and after the test is finished, processing the test data and the test result and releasing the applied resources.
5. The adjustable industrial internet control device as claimed in claim 1, wherein: the method comprises the following steps of utilizing an improved particle swarm algorithm to complete scheduling of the data of the Internet of things from a single target to multiple targets, and determining a fitness function when scheduling is carried out from the multiple targets to the multiple targets:
wherein gamma isR(D) For the classification error rate of the selected feature subset R relative to the decision D, | s | is the size of the selected feature subset, | D | represents the total number of features, α and β are two parameters corresponding to the classification accuracy and importance of the selected feature size, α [0,1 ]]And β ═ 1- α;
the error rate of a K-NN classifier is used in the fitness function, where each sample is divided into a class of labels to which its K neighbors mostly belong, and in the classification phase, the data set is usually divided into a training subset and a testing subset, and in order to determine the class of each sample in the test data, the nearest K neighbors of each sample must be calculated from the training data, using K times cross-validation with K10.
6. The adjustable industrial internet control device as claimed in claim 1, wherein: the characteristic selection is carried out by utilizing a multi-population-based particle swarm algorithm, each particle in the algorithm has two solutions, one solution is randomly generated, and the other solution is generated by a Relieff characteristic sorting method;
the Relieff algorithm is a method for ranking features by calculating the distance from each feature to a target, in the method, each feature is assigned a weight, the range is 1 to +1, the related features are expected to have higher weights, the algorithm searches a solution space by using two solutions at the same time, and then the particles adjust the positions of the particles by using a gBest and pBest solution;
in this algorithm, the initial velocity value of a particle is set to zero, and there are two initial solutions for each particle, the initial solution, xi,kWhere i is the index k of the particle is the initial type, xi,0Representing two initial solutions xi,kThe random selection selects a number from 0 to 1 based on a uniform distribution, if the value is greater than 0.5, the position is set to 1, otherwise to 0, the terrain ordering method assigns [1,1 ] to each feature]These correlation values are converted to [0,1 ]]An equation.
Wherein, theta to U (0, 1), rw is the correlation weight matrix,
is the probability of occurrence of the ith feature, xi,2An initial position generated using the Relieff, assuming that the correlation value of any characteristic is 0 if the correlation value of the characteristic is negative, according to the initializationAnd calculating the global optimal solution of the cluster and the individual optimal solution of each particle according to the fitness value of the particle.
7. The adjustable industrial internet control device as claimed in claim 6, wherein: for each particle, using a time-varying mirror sigmoid transfer function, to adjust the next position of the particle,
wherein, I represents the I particle, k is the initial type, j is the dimension of the I particle characteristic, w is the inertia weight for adjusting the balance between the current position and the next position of the particle, c1And c2Is the coefficient of acceleration, r1And r2Is a random number between 0 and 1,
is pBestiThe jth position of (1), gBestjIs the jth position of the gBest,
the position of the particle is a continuous value, which cannot be used directly for feature selection due to its binary nature, and to solve this problem, the continuous value is converted into a binary value using a transfer function, which is shown below,
wherein σ is σ at the first iterationminσ as σ at the last iterationmaxLinearly increasing, switching smoothly from exploration to development, σ is given as,
the next binary position of each transfer function is obtained by using an equation, and the target function is
And
greedy selection is made between them, and then the best position is selected as the particle
Will be next binary position
Is given to
If the new fitness value is better than the human best experience value for the particle, then the pair
And assigning the value of pBesti, and if the value of pBesti is better than the current global best, assigning the value of pBesti to the gBest so as to update the gBest.
8. The adjustable industrial internet control device as claimed in claim 1, wherein: the data of the industrial Internet of things come from different conveying systems, so that the data have different structures, and therefore, the data of the different structures are processed during communication scheduling, the data are unified and normalized in standard, the data storage and access speed is further improved, and therefore real-time monitoring of the equipment state of the Internet of things, real-time scanning of operation risks, equipment fault diagnosis, real-time display of the equipment state, operation optimization of the equipment and automatic analysis reporting are achieved.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110876544.4A CN113721565A (en) | 2021-07-31 | 2021-07-31 | Industry internet controlgear with adjustable |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110876544.4A CN113721565A (en) | 2021-07-31 | 2021-07-31 | Industry internet controlgear with adjustable |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113721565A true CN113721565A (en) | 2021-11-30 |
Family
ID=78674528
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110876544.4A Pending CN113721565A (en) | 2021-07-31 | 2021-07-31 | Industry internet controlgear with adjustable |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113721565A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8018874B1 (en) * | 2009-05-06 | 2011-09-13 | Hrl Laboratories, Llc | Network optimization system implementing distributed particle swarm optimization |
| US20140277599A1 (en) * | 2013-03-13 | 2014-09-18 | Oracle International Corporation | Innovative Approach to Distributed Energy Resource Scheduling |
| CN106921702A (en) * | 2015-12-25 | 2017-07-04 | 中国电力科学研究院 | It is a kind of based on service-oriented power distribution network information physical system |
| CN108469983A (en) * | 2018-04-02 | 2018-08-31 | 西南交通大学 | A kind of virtual machine deployment method based on particle cluster algorithm under cloud environment |
| CN109766374A (en) * | 2018-12-26 | 2019-05-17 | 科大国创软件股份有限公司 | A kind of credit joint supervising platform |
| CN110991518A (en) * | 2019-11-28 | 2020-04-10 | 山东大学 | Two-stage feature selection method and system based on evolution multitask |
| CN111930469A (en) * | 2020-07-20 | 2020-11-13 | 湖北美和易思教育科技有限公司 | College big data competition management system and method based on cloud computing |
-
2021
- 2021-07-31 CN CN202110876544.4A patent/CN113721565A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8018874B1 (en) * | 2009-05-06 | 2011-09-13 | Hrl Laboratories, Llc | Network optimization system implementing distributed particle swarm optimization |
| US20140277599A1 (en) * | 2013-03-13 | 2014-09-18 | Oracle International Corporation | Innovative Approach to Distributed Energy Resource Scheduling |
| CN106921702A (en) * | 2015-12-25 | 2017-07-04 | 中国电力科学研究院 | It is a kind of based on service-oriented power distribution network information physical system |
| CN108469983A (en) * | 2018-04-02 | 2018-08-31 | 西南交通大学 | A kind of virtual machine deployment method based on particle cluster algorithm under cloud environment |
| CN109766374A (en) * | 2018-12-26 | 2019-05-17 | 科大国创软件股份有限公司 | A kind of credit joint supervising platform |
| CN110991518A (en) * | 2019-11-28 | 2020-04-10 | 山东大学 | Two-stage feature selection method and system based on evolution multitask |
| CN111930469A (en) * | 2020-07-20 | 2020-11-13 | 湖北美和易思教育科技有限公司 | College big data competition management system and method based on cloud computing |
Non-Patent Citations (4)
| Title |
|---|
| KE CHEN 等: "A hybrid particle swarm optimizer with sine cosine acceleration coefficients", 《INFORMATION SCIENCES》 * |
| KE CHEN 等: "Chaotic dynamic weight particle swarm optimization for numerical function optimization", 《KNOWLE DGE-BASE D SYSTEMS》 * |
| 党宏社 等: "基于ＲeliefF 特征加权和KNN 的自然图像分类方法", 《数字视频》 * |
| 姜洪辉: "《基于改进PSO优化FWSVM的燃烧稳定性判定研究》", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lai et al. | Fedscale: Benchmarking model and system performance of federated learning at scale | |
| JP6359716B1 (en) | Diagnosing slow tasks in distributed computing | |
| Liu et al. | Context-aware and adaptive QoS prediction for mobile edge computing services | |
| WO2019011015A1 (en) | Method and device for service scheduling | |
| CN111695695B (en) | Quantitative analysis method and device for user decision behaviors | |
| Irtija et al. | Energy efficient edge computing enabled by satisfaction games and approximate computing | |
| CN110362494A (en) | Method, model training method and the relevant apparatus that micro services status information is shown | |
| Lai et al. | Oort: Informed participant selection for scalable federated learning | |
| US11125655B2 (en) | Tool for optimal supersaturated designs | |
| US11593735B2 (en) | Automated and efficient personal transportation vehicle sharing | |
| CN115543577B (en) | Covariate-based Kubernetes resource scheduling optimization method, storage medium and device | |
| JP2024536241A (en) | Techniques for input classification and response using generative neural networks. | |
| CN113553160A (en) | Task scheduling method and system for edge computing node of artificial intelligence Internet of things | |
| CN115396335B (en) | Industrial wireless network equipment access IPv6 test system and method based on micro-service | |
| JP2019204507A (en) | AI Headline News | |
| Geng et al. | Interference-aware parallelization for deep learning workload in GPU cluster | |
| Chen et al. | Silhouette: Efficient cloud configuration exploration for large-scale analytics | |
| CN114546609A (en) | DNN inference task batch scheduling method facing heterogeneous cluster | |
| Tundo et al. | An energy-aware approach to design self-adaptive ai-based applications on the edge | |
| CN113721565A (en) | Industry internet controlgear with adjustable | |
| CN111709778A (en) | Travel flow prediction method and device, electronic equipment and storage medium | |
| CN112819152A (en) | Neural network training method and device | |
| CN114969209B (en) | Training method and device, and method and device for predicting resource consumption | |
| Saemi et al. | Solving task scheduling problem in mobile cloud computing using the hybrid multi-objective Harris Hawks optimization algorithm | |
| Saylam et al. | Federated Learning on Edge Sensing Devices: A Review |
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: 20211130 |
|
| RJ01 | Rejection of invention patent application after publication |