CN108549343B - Motion control system and control method based on big data - Google Patents
Motion control system and control method based on big data Download PDFInfo
- Publication number
- CN108549343B CN108549343B CN201810389904.6A CN201810389904A CN108549343B CN 108549343 B CN108549343 B CN 108549343B CN 201810389904 A CN201810389904 A CN 201810389904A CN 108549343 B CN108549343 B CN 108549343B
- Authority
- CN
- China
- Prior art keywords
- data
- module
- cluster
- dimension
- motion control
- 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 57
- 238000012544 monitoring process Methods 0.000 claims abstract description 27
- 238000013500 data storage Methods 0.000 claims abstract description 12
- 238000001514 detection method Methods 0.000 claims description 48
- 230000002159 abnormal effect Effects 0.000 claims description 25
- 230000004323 axial length Effects 0.000 claims description 24
- 230000008569 process Effects 0.000 claims description 21
- 238000012545 processing Methods 0.000 claims description 19
- 238000012360 testing method Methods 0.000 claims description 17
- 230000009467 reduction Effects 0.000 claims description 15
- 230000000875 corresponding effect Effects 0.000 claims description 12
- 230000001276 controlling effect Effects 0.000 claims description 10
- 230000009471 action Effects 0.000 claims description 9
- 238000003672 processing method Methods 0.000 claims description 9
- 230000009466 transformation Effects 0.000 claims description 8
- 238000012549 training Methods 0.000 claims description 7
- 238000003860 storage Methods 0.000 claims description 6
- 239000000126 substance Substances 0.000 claims description 6
- 238000007493 shaping process Methods 0.000 claims description 4
- 230000003044 adaptive effect Effects 0.000 claims description 3
- 238000004590 computer program Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 abstract description 5
- 238000007405 data analysis Methods 0.000 abstract description 2
- 238000004891 communication Methods 0.000 description 8
- 238000005265 energy consumption Methods 0.000 description 5
- 238000013459 approach Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000013450 outlier detection Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000002123 temporal effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- KRTSDMXIXPKRQR-AATRIKPKSA-N monocrotophos Chemical compound CNC(=O)\C=C(/C)OP(=O)(OC)OC KRTSDMXIXPKRQR-AATRIKPKSA-N 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000007639 printing Methods 0.000 description 1
- 230000035484 reaction time Effects 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 239000004753 textile Substances 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]
- G05B19/4185—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 the network communication
-
- 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
- G05B2219/31—From computer integrated manufacturing till monitoring
- G05B2219/31088—Network communication between supervisor and cell, machine group
-
- 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)
- General Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to the technical field of motion control, and discloses a motion control system and a control method based on big data, wherein the motion control system based on the big data comprises the following components: the system comprises a solar power supply module, a switch control module, a monitoring module, a single-chip microcomputer control module, an execution module, a speed control module, a cloud service module, a data storage module and a display module; a control method is also disclosed. The solar energy power supply module can obtain continuous solar energy, and the solar energy is clean and efficient, saves energy, and is economic and environment-friendly; meanwhile, the cloud service module can greatly improve the data analysis and calculation speed and improve the motion control efficiency.
Description
Technical Field
The invention belongs to the technical field of motion control, and particularly relates to a motion control system and a motion control method based on big data.
Background
Currently, the current state of the art commonly used in the industry is such that:
motion Control (MC) is a branch of automation that uses devices known as servos, such as hydraulic pumps, linear actuators, or electric motors, to control the position or speed of a machine. The application of motion control in the field of robotics and numerically controlled machines is more complex than in special machines, since the latter forms of motion are simpler, commonly referred to as universal motion control (GMC). Motion control is widely used in the packaging, printing, textile and assembly industries. However, the conventional motion control system consumes electric energy due to the conventional power supply mode, and is not beneficial to environmental protection; meanwhile, the processing speed of the motion control data is low, and the control efficiency is influenced.
Currently, there are multiple outlier detection methods: a neighbor-based approach, a statistical-based approach, a clustering-based approach, and a spectral analysis-based approach. However, some of the sensor network's own features make not all existing detection methods well suited for direct use therein. For this reason, in order to better design an efficient and feasible outlier detection method for WSNs, the following characteristics need to be considered:
(1) the node capabilities are limited. The inexpensive miniature nature of the sensor nodes results in a rather limited amount of energy being carried by the sensor nodes. The amount of energy affects the processing, storage and communication transceiving capabilities of the sensor node to a certain extent. Therefore, in practical applications, various energy and capacity limitations of the sensor nodes should be fully considered, while most of the traditional detection methods rarely consider the performance of the algorithm under the condition that the capacity of the nodes is limited.
(2) Distributed self-organization. In the WSNs, all nodes are in the same position, no node is a 'dominator' in a strict sense, and the equal direct influence among the network nodes is that the normal operation of the network can be ensured through distributed cooperation. Meanwhile, the nodes of the WSNs have strong self-organizing capability, the network can be configured in any severe or dynamic environment, and monitoring data are transmitted to a remote observer through a specific way, so that the function of the network is realized. The super-strong self-organizing capability of the network is considered, so that the network overhead can be well reduced, and a more effective abnormal value detection algorithm is designed
(3) High energy consumption and high load. Wireless communication of wireless sensor network nodes consumes a large portion of the node's energy, which is many times the computational consumption of the node. However, most of the conventional abnormal value detection methods adopt a method of centrally processing collected data, thereby greatly increasing node energy consumption and communication load and reducing network life. Therefore, how to reduce communication power consumption to extend the lifetime of WSNs is an important consideration in designing methods for detecting abnormal values of WSNs.
(4) And (4) real-time performance. The comprehensive analysis of the application field of the WSNs can be realized, and the detection of abnormal values needs to be on-line and in real time. The reaction time of the network to an event is proportional to the performance of the system. Therefore, it is extremely necessary to design a real-time abnormal value detection method.
In summary, the abnormal value detection method which is real-time and distributed and can keep lower communication energy consumption and communication load can be realized, and the abnormal value detection method which is higher in detection rate and lower in false alarm rate is the abnormal value detection algorithm which is suitable for the wireless sensor network.
In the literature, Statistics-based outputter detection on for wiseslseeensor networks, several methods for detecting abnormal data of WSNs based on statistical models are given by the authors. Including methods that consider only temporal correlations, methods that consider only spatial correlations, and methods in which colleagues consider spatio-temporal correlations. However, as for multidimensional data, a time series model and geographic statistics are still adopted in the article, and the dimension reduction of the data is not considered, so that the calculation consumption is greatly increased.
In the document, object-based multi-dimensional output detection in wireless sensor networks using high Markov Models, authors use fourier transforms to reduce the dimensions of multidimensional data collected by sensor nodes. Meanwhile, the time correlation among data is also utilized in the application process of the hidden Markov model. However, the spatial correlation existing between nodes is not considered herein.
In the document Distributed online detection in wireless sensor networks using an ellipsometric supported vector machine, an author classifies data by using an ultra-ellipsoid support vector machine so as to achieve the purpose of finding out abnormal data. The norm is used herein to define the distance between multidimensional data. The method has the advantages that the higher detection rate is achieved, and meanwhile, the low false detection rate is guaranteed. Meanwhile, the method is also an online and real-time detection method. However, the process of training the ellipsoid SVM requires a distribution of data to be specified in advance, which requires a large energy consumption.
In the document An Energy-Efficient output Detection Based on Data Clustering in WSNs, nodes are clustered by analyzing spatial correlation among the nodes, so that communication exchange is reduced, and Energy consumption is further reduced. However, for multi-dimensional data, the one-dimensional data is processed and then integrated, so that the calculation amount is increased.
In summary, the problems of the prior art are as follows:
the existing motion control system is powered by a traditional mode, consumes electric energy and is not beneficial to environmental protection; meanwhile, the processing speed of the motion control data is low, and the control efficiency is influenced.
In the wireless sensor network, the data of nodes in adjacent areas have spatial correlation theoretically, and the data of the same node in continuous time periods have time correlation theoretically. However, only a few anomaly detection methods in the existing literature consider both temporal and spatial correlation, which inevitably leads to a reduction in detection accuracy or an increase in detection cost.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a motion control system and a motion control method based on big data.
The present invention is achieved by a big data based motion control system, including:
the monitoring module is connected with the single chip microcomputer control module and is used for monitoring the motion control process through the camera;
the single chip microcomputer control module is connected with the monitoring module, the execution module, the speed control module and the cloud service module and used for scheduling each module to work normally;
the execution module is connected with the single chip microcomputer control module and is used for controlling the mechanical structure to complete corresponding actions through the motor;
the speed control module is connected with the single chip microcomputer control module and used for controlling the movement speed of the execution module; the control method of the speed control module comprises the following steps:
performing nonlinear transformation on the received signal s (t) according to the following formula:
whereinA represents the amplitude of the signal, a (m) represents the symbol sign of the signal, p (t) represents the shaping function, fcWhich is indicative of the carrier frequency of the signal,representing the phase of the signal, resulting from the nonlinear transformation:
the multipath space for constructing n signals is:
wherein the content of the first and second substances,q is the number of sampling points, K is the maximum time delay, and the maximum detection distance RmaxC is obtained in which xreci(t) is a reference signal, RmaxC is the maximum detection distance, and c is the speed of light;
then utilizing least square method principle to inhibit direct wave and its multipath, and calculating min | | | Ssur-Xref·α2Is converted into a solutionTo obtain:
wherein S issurFor echo channel signals, alpha is an adaptive weight, alphaestimIs an estimated value of a and is,is XrefIs transposed, SotherThe final echo and noise in the echo channel are obtained;
the cloud service module is connected with the single-chip microcomputer control module and used for processing the control data through the cloud server centralized big data computing resources; the data processing method of the cloud service module comprises the following steps:
firstly, clustering sensor nodes according to sensor node data at a certain same moment, respectively training a hyperellipsoid for each clustered cluster, correspondingly calculating each axial length of the hyperellipsoid, linearly reducing the dimension of multidimensional data by taking an axial length proportionality coefficient as a coefficient, and fitting the data after dimension reduction into a data curve as a test curve. And performing same dimension reduction and curve fitting treatment on the data in the same time period on the next day, wherein the fitted curve is used as a detection curve. And comparing the trends and the curve similarity of the test curve and the detection curve so as to detect whether abnormal data exist in the multi-dimensional data collected by the nodes.
Further, the big data based motion control system further comprises:
the solar power supply module is connected with the singlechip control module and used for converting solar energy into electric energy through the solar cell panel to supply power to the motion control system;
the switch control module is connected with the single chip microcomputer control module and used for starting and closing the control system through a switch key;
the data storage module is connected with the single chip microcomputer control module and used for storing the operating data of the control system;
the display module is connected with the singlechip control module and is used for displaying the monitoring data of motion control;
the control signal receiving module is used for receiving a mechanical control signal;
the program driving loading module is used for loading a driving program controlled by the machine;
and the action execution module is used for finishing mechanical operation actions.
Further, the data processing method of the cloud service module comprises the following steps:
d-dimensional sensor data setWherein r isi d=<ri[1],...,ri[d]>,ri d[k]Data of the k-th dimension representing an ith node; the k-dimension permission radius is defined as:
if there isThen call data ridAndare contiguous in the k dimension; if r isi dAndadjacent to the k-th dimension, the adjacent to the k-th dimension belongs to a cluster in the k-th dimension; for node i, j, only if its d-dimensional data ri dAndwhen all the kth dimensions (k is more than or equal to 1 and less than or equal to d) belong to a cluster, the nodes i and j are called to belong to the same cluster;
cluster CjCluster interval of (A) is noted asWherein for k is more than or equal to 1 and less than or equal to d
Wherein the content of the first and second substances,is a cluster CiA cluster interval in the k-th dimension;
when cluster intervalAndwhen the k-th dimension overlaps, the cluster C is callediAnd cluster CjIn the k-dimension, can be merged and the cluster radius of the newly formed cluster is CR ═ MIN ({ MIN })i,minj}),MAX({maxi,maxj})](ii) a When cluster CiAnd CjWhen all the k-th (1. ltoreq. k. ltoreq. d) dimensions overlap, cluster CiAnd CjCan be merged into a new cluster;
the functions g (X) and f (X) defined on X are similar if, after g (X) and f (X) have translated to the same starting point, there is: for any X ∈ X, | f (X) -g (X) | < c;
or the following steps:
in the above formula, c is a parameter greater than 0, but not too large, and should be much smaller than 1; in practical applications this value is determined by the actual situation.
Further, the data processing method of the cloud service module comprises the following steps:
1): selecting test data;
2): performing node clustering on the selected test data;
3): training the divided clusters to include the hyperellipsoids of all nodes in the clusters, and calculating the axial lengths of the corresponding hyperellipsoids;
4): performing data dimension reduction according to the axial length of each hyper ellipsoid;
5): carrying out corresponding curve fitting on the data subjected to dimension reduction according to the axial length of each hyper-ellipsoid;
6): selecting detection data;
7): processing the detection data;
8): comparing the similarity of the test curve and the detection curve to determine whether the data has abnormal data;
9): repeating the steps 4) to 8) until all the node data are detected;
the specific process of the step 2) is as follows:
clustering nodes according to the data of the same time point of each node, calculating the permitted radius of the data in each dimension through the selected node data,
judgment of ri dAndwhether or not they are adjacent; if the nodes are adjacent, the nodes i and j belong to the same cluster in the first dimension direction. And only when the nodes belong to the same cluster in all the k dimensions, the nodes i and j are called as the same cluster. At the same time, if two clusters CiAnd CjCluster interval ofAndsatisfy the requirement of
When all k are true, cluster C is formediAnd CjCan be combined into a cluster with a cluster radius of
CR=[MIN({mini,minj}),MAX({maxi,maxj})];
The specific process of the step 3) is as follows:
the relationship between the data attributes is described by the proportional relation among the axial lengths of the hyperellipsoids, wherein the axial lengths of the hyperellipsoids are sigmapl≥σp-1l≥σp-2l≥…≥σ1l; wherein σi(1. ltoreq. i.ltoreq.p) represents the square root of the eigenvalue of the covariance matrix Σ of the data set D, and when μ represents the mean value of the data set D, it corresponds to the axial length of the hyper-ellipsoid
The step 8) needs to determine an abnormal value by judging the similarity degree of the two curves, and the specific process is as follows:
let f (X) be the fitted test curve, g (X) be the fitted curve to be tested, and for the preset threshold value c (0 < c < 1), when the curve f (X) and the curve g (X) satisfy, for any X ∈ X, there is
|f(x)-g(x)|<c
Or satisfy
Then the node is said to have no abnormal value, otherwise, the abnormal value is considered to exist.
Another object of the present invention is to provide an information data processing terminal equipped with the motion control system based on big data
Another object of the present invention is to provide a motion control method based on big data, comprising the steps of:
converting solar energy into electric energy through a solar energy power supply module to supply power to a motion control system;
secondly, starting and closing the control system through the switch control module; monitoring the motion control process through a monitoring module;
thirdly, the single chip microcomputer control module scheduling execution module controls the mechanical structure to complete corresponding actions through the motor; controlling the movement speed of the execution module through a speed control module;
processing the control data by using the cloud service module to centralize big data computing resources; storing control system operation data through a data storage module;
and fifthly, displaying the monitoring data of the motion control through a display module.
Another object of the present invention is to provide a computer program for implementing the big data based motion control method.
Another object of the present invention is to provide an information data processing terminal implementing the big data based motion control method.
Another object of the present invention is to provide a computer-readable storage medium, comprising instructions, which when run on a computer, cause the computer to execute the big data based motion control method.
The invention has the advantages and positive effects that:
the solar energy power supply module can obtain continuous solar energy, and the solar energy is clean and efficient, saves energy, and is economic and environment-friendly; meanwhile, the cloud service module can greatly improve the data analysis and calculation speed and improve the motion control efficiency.
The clustering process of the invention considers the spatial correlation among the network nodes, thus leading the data dimension reduction process to be more accurate and targeted.
The invention carries out linear dimensionality reduction on the data by utilizing the ellipse, thereby avoiding the defect of overlarge calculated amount caused by directly using multidimensional data.
The method utilizes the time correlation among the node data in the process of abnormal value detection, and realizes the detection process by comparing the fitting curves of the data for two consecutive days.
The invention can realize the detection requirements in different monitoring environments by properly adjusting the size of the ratio parameter c.
The invention has no extra communication consumption in the whole detection process, so the invention is also suitable for the wireless sensor network with dynamic change.
The invention fully utilizes the spatial correlation between the data of adjacent nodes of the network and the time correlation of the data of the same node in the detection process; the dimension of the data is reduced through clustering, so that the defect of high calculation complexity of directly processing multidimensional data is avoided; the abnormal value detection method can accurately detect the condition that the abnormal value continuously appears at the network node, and has high detection rate and low false detection rate.
The control method of the speed control module comprises the following steps:
performing nonlinear transformation on the received signal s (t) according to the following formula:
whereinA represents the amplitude of the signal, a (m) represents the symbol sign of the signal, p (t) represents the shaping function, fcWhich is indicative of the carrier frequency of the signal,representing the phase of the signal, resulting from the nonlinear transformation:
Drawings
FIG. 1 is a flow chart of a big data based motion control method provided by the implementation of the present invention.
FIG. 2 is a block diagram of a big data based motion control system provided by an implementation of the present invention.
In fig. 2: 1. a solar power supply module; 2. a switch control module; 3. a monitoring module; 4. a single chip microcomputer control module; 5. an execution module; 6. a speed control module; 7. a cloud service module; 8. a data storage module; 9. and a display module.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
As shown in fig. 1, the motion control method based on big data provided by the present invention includes the following steps:
s101, converting solar energy into electric energy through a solar power supply module to supply power to a motion control system;
s102, starting and closing the control system through the switch control module; monitoring the motion control process through a monitoring module;
s103, the single chip microcomputer control module dispatches the execution module to complete corresponding actions by controlling a mechanical structure through a motor; controlling the movement speed of the execution module through a speed control module;
s104, processing control data by using a cloud service module to centralize big data computing resources; storing control system operation data through a data storage module;
and S105, displaying the monitoring data of the motion control through a display module.
As shown in fig. 2, the big data based motion control system provided by the present invention comprises: the system comprises a solar power supply module 1, a switch control module 2, a monitoring module 3, a single-chip microcomputer control module 4, an execution module 5, a speed control module 6, a cloud service module 7, a data storage module 8 and a display module 9.
The solar power supply module 1 is connected with the singlechip control module 4 and used for converting solar energy into electric energy through a solar panel to supply power to the motion control system;
the switch control module 2 is connected with the singlechip control module 4 and is used for starting and closing the control system through a switch key;
the monitoring module 3 is connected with the single chip microcomputer control module 4 and is used for monitoring the motion control process through a camera;
the single-chip microcomputer control module 4 is connected with the solar power supply module 1, the switch control module 2, the monitoring module 3, the execution module 5, the speed control module 6, the cloud service module 7, the data storage module 8 and the display module 9 and is used for scheduling each module to normally work;
the execution module 5 is connected with the single chip microcomputer control module 4 and is used for controlling the mechanical structure to complete corresponding actions through the motor;
the speed control module 6 is connected with the singlechip control module 4 and is used for controlling the movement speed of the execution module;
the cloud service module 7 is connected with the single chip microcomputer control module 4 and used for processing the control data through the cloud server centralized big data computing resources;
the data storage module 8 is connected with the single chip microcomputer control module 4 and used for storing the operation data of the control system;
and the display module 9 is connected with the single-chip microcomputer control module 4 and is used for displaying the monitoring data of the motion control.
The execution module 5 provided by the invention comprises a control signal receiving module, a program drive loading module and an action execution module;
the control signal receiving module is used for receiving a mechanical control signal;
the program driving loading module is used for loading a driving program controlled by the machine;
and the action execution module is used for finishing mechanical operation actions.
The control method of the speed control module comprises the following steps:
performing nonlinear transformation on the received signal s (t) according to the following formula:
whereinA represents the amplitude of the signal, a (m) represents the symbol sign of the signal, p (t) represents the shaping function, fcWhich is indicative of the carrier frequency of the signal,representing the phase of the signal, resulting from the nonlinear transformation:
the multipath space for constructing n signals is:
wherein the content of the first and second substances,q is the number of sampling points, K is the maximum time delay, and the maximum detection distance RmaxC is obtained in which xreci(t) is a reference signal, RmaxC is the maximum detection distance, and c is the speed of light;
then utilizing least square method principle to inhibit direct wave and its multipath, and calculating min | | | Ssur-Xref·α||2Is converted into a solutionTo obtain:
wherein S issurFor echo channel signals, alpha is an adaptive weight, alphaestimIs an estimated value of a and is,is XrefIs transposed, SotherThe final echo and noise in the echo channel are obtained;
the cloud service module is connected with the single-chip microcomputer control module and used for processing the control data through the cloud server centralized big data computing resources; the data processing method of the cloud service module comprises the following steps:
firstly, clustering sensor nodes according to sensor node data at a certain same moment, respectively training a hyperellipsoid for each clustered cluster, correspondingly calculating each axial length of the hyperellipsoid, linearly reducing the dimension of multidimensional data by taking an axial length proportionality coefficient as a coefficient, and fitting the data after dimension reduction into a data curve as a test curve. And performing same dimension reduction and curve fitting treatment on the data in the same time period on the next day, wherein the fitted curve is used as a detection curve. And comparing the trends and the curve similarity of the test curve and the detection curve so as to detect whether abnormal data exist in the multi-dimensional data collected by the nodes.
Further, the big data based motion control system further comprises:
the solar power supply module is connected with the singlechip control module and used for converting solar energy into electric energy through the solar cell panel to supply power to the motion control system;
the switch control module is connected with the single chip microcomputer control module and used for starting and closing the control system through a switch key;
the data storage module is connected with the single chip microcomputer control module and used for storing the operating data of the control system;
the display module is connected with the singlechip control module and is used for displaying the monitoring data of motion control;
the control signal receiving module is used for receiving a mechanical control signal;
the program driving loading module is used for loading a driving program controlled by the machine;
and the action execution module is used for finishing mechanical operation actions.
Further, the data processing method of the cloud service module comprises the following steps:
d-dimensional sensor data setWherein r isi d=<ri[1],...,ri[d]>,ri d[k]Data of the k-th dimension representing an ith node; the k-dimension permission radius is defined as:
if there isThen call the data ri dAndare contiguous in the k dimension; if r isi dAndadjacent to the k-th dimension, the adjacent to the k-th dimension belongs to a cluster in the k-th dimension; for node i, j, only if its d-dimensional data ri dAndwhen all the kth dimensions (k is more than or equal to 1 and less than or equal to d) belong to a cluster, the nodes i and j are called to belong to the same cluster;
cluster CjCluster interval of (A) is noted asWherein for k is more than or equal to 1 and less than or equal to d
Wherein the content of the first and second substances,is a cluster CiA cluster interval in the k-th dimension;
when cluster intervalAndwhen the k-th dimension overlaps, the cluster C is callediAnd cluster CjIn the k-dimension, can be merged and the cluster radius of the newly formed cluster is CR ═ MIN ({ MIN })i,minj}),MAX({maxi,maxj})](ii) a When cluster CiAnd CjWhen all the k-th (1. ltoreq. k. ltoreq. d) dimensions overlap, cluster CiAnd CjCan be merged into a new cluster;
the functions g (X) and f (X) defined on X are similar if, after g (X) and f (X) have translated to the same starting point, there is: for any X ∈ X, | f (X) -g (X) | < c;
or the following steps:
in the above formula, c is a parameter greater than 0, but not too large, and should be much smaller than 1; in practical applications this value is determined by the actual situation.
The data processing method of the cloud service module comprises the following steps:
1): selecting test data;
2): performing node clustering on the selected test data;
3): training the divided clusters to include the hyperellipsoids of all nodes in the clusters, and calculating the axial lengths of the corresponding hyperellipsoids;
4): performing data dimension reduction according to the axial length of each hyper ellipsoid;
5): carrying out corresponding curve fitting on the data subjected to dimension reduction according to the axial length of each hyper-ellipsoid;
6): selecting detection data;
7): processing the detection data;
8): comparing the similarity of the test curve and the detection curve to determine whether the data has abnormal data;
9): repeating the steps 4) to 8) until all the node data are detected;
the specific process of the step 2) is as follows:
clustering nodes according to the data of the same time point of each node, calculating the permitted radius of the data in each dimension through the selected node data,
judgment of ri dAndwhether or not they are adjacent; if the nodes are adjacent, the nodes i and j belong to the same cluster in the first dimension direction. And only when the nodes belong to the same cluster in all the k dimensions, the nodes i and j are called as the same cluster. At the same time, if two clusters CiAnd CjCluster interval ofAndsatisfy the requirement of
When all k are true, cluster C is formediAnd CjCan be combined into a cluster with a cluster radius of
CR=[MIN({mini,minj}),MAX({maxi,maxj})];
The specific process of the step 3) is as follows:
the relationship between the data attributes is described by the proportional relation among the axial lengths of the hyperellipsoids, wherein the axial lengths of the hyperellipsoids are sigmapl≥σp-1l≥σp-2l≥…≥σ1l; wherein σi(1. ltoreq. i.ltoreq.p) represents the square root of the eigenvalue of the covariance matrix Σ of the data set D, and when μ represents the mean value of the data set D, it corresponds to the axial length of the hyper-ellipsoid
The step 8) needs to determine an abnormal value by judging the similarity degree of the two curves, and the specific process is as follows:
let f (X) be the fitted test curve, g (X) be the fitted curve to be tested, and for the preset threshold value c (0 < c < 1), when the curve f (X) and the curve g (X) satisfy, for any X ∈ X, there is
|f(x)-g(x)|<c
Or satisfy
Then the node is said to have no abnormal value, otherwise, the abnormal value is considered to exist.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When used in whole or in part, can be implemented in a computer program product that includes one or more computer instructions. When loaded or executed on a computer, cause the flow or functions according to embodiments of the invention to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, the computer instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center via wire (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL), or wireless (e.g., infrared, wireless, microwave, etc.)). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that includes one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (9)
1. A big-data based motion control system, comprising:
the monitoring module is connected with the single chip microcomputer control module and is used for monitoring the motion control process through the camera;
the single chip microcomputer control module is connected with the monitoring module, the execution module, the speed control module and the cloud service module and used for scheduling each module to work normally;
the execution module is connected with the single chip microcomputer control module and is used for controlling the mechanical structure to complete corresponding actions through the motor;
the speed control module is connected with the single chip microcomputer control module and used for controlling the movement speed of the execution module; the control method of the speed control module comprises the following steps:
performing nonlinear transformation on the received signal s (t) according to the following formula:
whereinA represents the amplitude of the signal, a (m) represents the symbol sign of the signal, p (t) represents the shaping function, fcWhich is indicative of the carrier frequency of the signal,representing the phase of the signal, resulting from the nonlinear transformation:
the multipath space for constructing n signals is:
wherein the content of the first and second substances,q is the number of sampling points, K is the maximum time delay, and the maximum detection distance RmaxC is obtained in which xreci(t) is a reference signal, RmaxC is the maximum detection distance, and c is the speed of light;
then utilizing least square method principle to inhibit direct wave and its multipath, and calculating min | | | Ssur-Xref·α||2Is converted into a solutionTo obtain:
wherein S issurFor echo channel signals, alpha is an adaptive weight, alphaestimIs an estimated value of a and is,is XrefIs transposed, SotherThe final echo and noise in the echo channel are obtained;
the cloud service module is connected with the single-chip microcomputer control module and used for processing the control data through the cloud server centralized big data computing resources; the data processing method of the cloud service module comprises the following steps:
firstly, clustering sensor nodes according to sensor node data at a certain same moment, respectively training a hyperellipsoid for each clustered cluster, correspondingly calculating each axial length of the hyperellipsoid, linearly reducing the dimension of multidimensional data by taking an axial length proportionality coefficient as a coefficient, and fitting the data after dimension reduction into a data curve as a test curve; performing same dimension reduction and curve fitting treatment on the data in the same time period on the next day, wherein the fitted curve is used as a detection curve; and comparing the trends and the curve similarity of the test curve and the detection curve so as to detect whether abnormal data exist in the multi-dimensional data collected by the nodes.
2. The big-data based motion control system as claimed in claim 1, wherein the big-data based motion control system further comprises:
the solar power supply module is connected with the singlechip control module and used for converting solar energy into electric energy through the solar cell panel to supply power to the motion control system;
the switch control module is connected with the single chip microcomputer control module and used for starting and closing the control system through a switch key;
the data storage module is connected with the single chip microcomputer control module and used for storing the operating data of the control system;
the display module is connected with the singlechip control module and is used for displaying the monitoring data of motion control;
the control signal receiving module is used for receiving a mechanical control signal;
the program driving loading module is used for loading a driving program controlled by the machine;
and the action execution module is used for finishing mechanical operation actions.
3. The big data-based motion control system according to claim 1, wherein the data processing method of the cloud service module comprises:
d-dimensional sensor data setWherein r isi d=〈ri[1],...,ri[d]>,ri d[k]Data of the k-th dimension representing an ith node; the k-dimension permission radius is defined as:
if there isThen call the data ri dIn thatAre contiguous in the k dimension; if r isi dAndadjacent to the k-th dimension, the adjacent to the k-th dimension belongs to a cluster in the k-th dimension;for node i, j, only if its d-dimensional data ri dAndwhen all the kth dimensions (k is more than or equal to 1 and less than or equal to d) belong to a cluster, the nodes i and j are called to belong to the same cluster;
cluster CjCluster interval of (A) is noted asWherein for k is more than or equal to 1 and less than or equal to d
Wherein the content of the first and second substances,is a cluster CiA cluster interval in the k-th dimension;
when cluster intervalAndwhen the k-th dimension overlaps, the cluster C is callediAnd cluster CjIn the k-dimension, can be merged and the cluster radius of the newly formed cluster is CR ═ MIN ({ MIN })i,minj}),MAX({maxi,maxj})](ii) a When cluster CiAnd CjWhen all the k-th (1. ltoreq. k. ltoreq. d) dimensions overlap, cluster CiAnd CjCan be merged into a new cluster;
the functions g (X) and f (X) defined on X are similar if, after g (X) and f (X) have translated to the same starting point, there is: for any X ∈ X, | f (X) -g (X) | < c;
or the following steps:
in the above formula, c is a parameter greater than 0, but not too large, and should be much smaller than 1; in practical applications this value is determined by the actual situation.
4. The big data-based motion control system according to claim 1, wherein the data processing method of the cloud service module comprises:
1): selecting test data;
2): performing node clustering on the selected test data;
3): training the divided clusters to include the hyperellipsoids of all nodes in the clusters, and calculating the axial lengths of the corresponding hyperellipsoids;
4): performing data dimension reduction according to the axial length of each hyper ellipsoid;
5): carrying out corresponding curve fitting on the data subjected to dimension reduction according to the axial length of each hyper-ellipsoid;
6): selecting detection data;
7): processing the detection data;
8): comparing the similarity of the test curve and the detection curve to determine whether the data has abnormal data;
9): repeating the steps 4) to 8) until all the node data are detected;
the specific process of the step 2) is as follows:
clustering nodes according to the data of the same time point of each node, calculating the permitted radius of the data in each dimension through the selected node data,
judgment of ri dAndwhether or not they are adjacent; if the nodes are adjacent, the nodes i and j belong to a cluster in the first dimension direction; only when the nodes belong to the same cluster in all the k dimensions, the nodes i and j are called the same cluster; at the same time, if two clusters CiAnd CjCluster interval ofAndsatisfy the requirement of
When all k are true, cluster C is formediAnd CjCan be combined into a cluster with a cluster radius of
CR=[MIN({mini,minj}),MAX({maxi,maxj})];
The specific process of the step 3) is as follows:
the relationship between the data attributes is described by the proportional relation among the axial lengths of the hyperellipsoids, wherein the axial lengths of the hyperellipsoids are sigmapl≥σp-1l≥σp-2l≥…≥σ1l; wherein σi(1. ltoreq. i.ltoreq.p) represents the square root of the eigenvalue of the covariance matrix Σ of the data set D, and when μ represents the mean value of the data set D, it corresponds to the axial length of the hyper-ellipsoid
5. An information data processing terminal equipped with the big data based motion control system according to any one of claims 1 to 4.
6. A big data-based motion control method of a big data-based motion control system according to claim 1, wherein the big data-based motion control method comprises the steps of:
converting solar energy into electric energy through a solar energy power supply module to supply power to a motion control system;
secondly, starting and closing the control system through the switch control module; monitoring the motion control process through a monitoring module;
thirdly, the single chip microcomputer control module scheduling execution module controls the mechanical structure to complete corresponding actions through the motor; controlling the movement speed of the execution module through a speed control module;
processing the control data by using the cloud service module to centralize big data computing resources; storing control system operation data through a data storage module;
and fifthly, displaying the monitoring data of the motion control through a display module.
7. A computer program implementing the big-data based motion control method of claim 6.
8. An information data processing terminal implementing the big data based motion control method of claim 6.
9. A computer-readable storage medium comprising instructions that, when executed on a computer, cause the computer to perform the big-data based motion control method of claim 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810389904.6A CN108549343B (en) | 2018-04-27 | 2018-04-27 | Motion control system and control method based on big data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810389904.6A CN108549343B (en) | 2018-04-27 | 2018-04-27 | Motion control system and control method based on big data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108549343A CN108549343A (en) | 2018-09-18 |
CN108549343B true CN108549343B (en) | 2020-11-27 |
Family
ID=63512730
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810389904.6A Active CN108549343B (en) | 2018-04-27 | 2018-04-27 | Motion control system and control method based on big data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108549343B (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103543735A (en) * | 2013-10-30 | 2014-01-29 | 北京理工大学 | Distributed type low-speed high-precision device and method for controlling astronomical telescope |
CN104898573A (en) * | 2015-04-06 | 2015-09-09 | 华中科技大学 | Numerical control system data acquiring and processing method based on cloud computing |
CN105205563A (en) * | 2015-09-28 | 2015-12-30 | 国网山东省电力公司菏泽供电公司 | Short-term load predication platform based on large data |
CN105307200A (en) * | 2015-09-30 | 2016-02-03 | 西安电子科技大学 | Method for detecting abnormal value of multidimensional data of wireless sensor network based on trajectory |
CN105550374A (en) * | 2016-01-29 | 2016-05-04 | 湖南大学 | Random forest parallelization machine studying method for big data in Spark cloud service environment |
CN106216843A (en) * | 2016-08-25 | 2016-12-14 | 广东工业大学 | A kind of self adaptation laser peening corrector based on big data platform and method |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9026864B2 (en) * | 2012-02-29 | 2015-05-05 | Red Hat, Inc. | Offloading health-checking policy |
-
2018
- 2018-04-27 CN CN201810389904.6A patent/CN108549343B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103543735A (en) * | 2013-10-30 | 2014-01-29 | 北京理工大学 | Distributed type low-speed high-precision device and method for controlling astronomical telescope |
CN104898573A (en) * | 2015-04-06 | 2015-09-09 | 华中科技大学 | Numerical control system data acquiring and processing method based on cloud computing |
CN105205563A (en) * | 2015-09-28 | 2015-12-30 | 国网山东省电力公司菏泽供电公司 | Short-term load predication platform based on large data |
CN105307200A (en) * | 2015-09-30 | 2016-02-03 | 西安电子科技大学 | Method for detecting abnormal value of multidimensional data of wireless sensor network based on trajectory |
CN105550374A (en) * | 2016-01-29 | 2016-05-04 | 湖南大学 | Random forest parallelization machine studying method for big data in Spark cloud service environment |
CN106216843A (en) * | 2016-08-25 | 2016-12-14 | 广东工业大学 | A kind of self adaptation laser peening corrector based on big data platform and method |
Also Published As
Publication number | Publication date |
---|---|
CN108549343A (en) | 2018-09-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Harb et al. | Energy-efficient sensor data collection approach for industrial process monitoring | |
Jiang et al. | Outlier detection approaches based on machine learning in the internet-of-things | |
CN113051830B (en) | Intelligent production line dynamic error prediction system, control method and digital twin system | |
Alzghoul et al. | Data stream forecasting for system fault prediction | |
CN115469627B (en) | Intelligent factory operation management system based on Internet of things | |
Long et al. | Motor fault diagnosis using image visual information and bag of words model | |
CN108549343B (en) | Motion control system and control method based on big data | |
Fan et al. | Research and applications of data mining techniques for improving building operational performance | |
Gao et al. | An Approach to Intelligent Fault Diagnosis of Cryocooler Using Time‐Frequency Image and CNN | |
CN117688362A (en) | Photovoltaic power interval prediction method and device based on multivariate data feature enhancement | |
CN110887652B (en) | Interactive multi-model detection method for vibration detection and displacement extraction of accelerometer | |
Ding et al. | Health assessment and fault classification for hydraulic pump based on LR and softmax regression | |
US10635992B2 (en) | Reducing bandwidth requirements for telemetry data using a cross-imputability analysis technique | |
CN113554149B (en) | Neural network processing unit NPU, neural network processing method and device | |
CN114330875A (en) | Environment information determination method and device, electronic equipment and storage medium | |
Zhang et al. | Intelligent fault diagnosis system based on vibration signal edge computing | |
Zhu et al. | Research on indoor positioning algorithm based on BP neural network | |
CN110161459B (en) | Rapid positioning method for amplitude modulation sound source | |
CN112466322A (en) | Electromechanical device noise signal feature extraction method | |
Huang et al. | MicroT: Low-Energy and Adaptive Models for MCUs | |
CN116450592B (en) | Working condition self-adaptive compression method and system based on industrial big data characteristics | |
Vulfin | Detection of Network Attacks in a Heterogeneous Industrial Network Based on Machine Learning | |
CN116935608B (en) | Remote intelligent monitoring method and system for air energy equipment | |
Chen et al. | A Novel Big Data Cleaning Algorithm Based On Edge Computing In Industrial Internet of Things | |
Wang et al. | A non-intrusive load decomposition method for residents |
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 | ||
CB03 | Change of inventor or designer information | ||
CB03 | Change of inventor or designer information |
Inventor after: Cai Mingshan Inventor after: Li Jianqi Inventor after: Pan Xianggao Inventor before: Cai Mingshan |
|
GR01 | Patent grant | ||
GR01 | Patent grant |