CN117033143B - Intelligent monitoring data transmission system and method based on running state of big data - Google Patents

Intelligent monitoring data transmission system and method based on running state of big data Download PDF

Info

Publication number
CN117033143B
CN117033143B CN202311288622.4A CN202311288622A CN117033143B CN 117033143 B CN117033143 B CN 117033143B CN 202311288622 A CN202311288622 A CN 202311288622A CN 117033143 B CN117033143 B CN 117033143B
Authority
CN
China
Prior art keywords
behavior
assimilation
abnormal
operation state
state
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
Application number
CN202311288622.4A
Other languages
Chinese (zh)
Other versions
CN117033143A (en
Inventor
徐才红
汪强
丁单进
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Changzhou Ruiyang Hydraulic Equipment Co ltd
Original Assignee
Changzhou Ruiyang Hydraulic Equipment Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Changzhou Ruiyang Hydraulic Equipment Co ltd filed Critical Changzhou Ruiyang Hydraulic Equipment Co ltd
Priority to CN202311288622.4A priority Critical patent/CN117033143B/en
Publication of CN117033143A publication Critical patent/CN117033143A/en
Application granted granted Critical
Publication of CN117033143B publication Critical patent/CN117033143B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/3003—Monitoring arrangements specially adapted to the computing system or computing system component being monitored
    • G06F11/3006—Monitoring arrangements specially adapted to the computing system or computing system component being monitored where the computing system is distributed, e.g. networked systems, clusters, multiprocessor systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/3065—Monitoring arrangements determined by the means or processing involved in reporting the monitored data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
    • G06F11/3452—Performance evaluation by statistical analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
    • G06F11/3466—Performance evaluation by tracing or monitoring
    • G06F11/3495—Performance evaluation by tracing or monitoring for systems
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/06—Management of faults, events, alarms or notifications
    • H04L41/0631—Management of faults, events, alarms or notifications using root cause analysis; using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis
    • H04L41/064—Management of faults, events, alarms or notifications using root cause analysis; using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis involving time analysis
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Quality & Reliability (AREA)
  • General Physics & Mathematics (AREA)
  • Computing Systems (AREA)
  • Signal Processing (AREA)
  • Computer Hardware Design (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Probability & Statistics with Applications (AREA)
  • Mathematical Physics (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Testing Or Calibration Of Command Recording Devices (AREA)

Abstract

The invention discloses an intelligent monitoring data transmission system and method based on the running state of big data, and belongs to the technical field of data transmission. The architecture operation data base is used for storing feedback data of the sensor in a uniformly divided storage space, constructing an abnormal operation state behavior perception model, and combining an abnormal feedback set to form different abnormal operation state behavior characteristics; aiming at the running state characteristics of cluster equipment in a control system, carrying out assimilation analysis to correlate abnormal running state behaviors to form an assimilation data sample library; constructing an assimilation relation iteration model, and finding out the association relation between abnormal operation state behaviors to form an assimilation relation behavior pair; analyzing and predicting the occurrence time of an assimilation target by analyzing and predicting the interval studying and judging time, and mining a time distribution rule in the data synchronous transmission process based on the synchronous sensing behavior of the sensor as a guide; therefore, the decision balance of the data transmission channel is ensured, and the data transmission efficiency is improved.

Description

Intelligent monitoring data transmission system and method based on running state of big data
Technical Field
The invention relates to the technical field of data transmission, in particular to an intelligent monitoring data transmission system and method based on the running state of big data.
Background
Sensing technology and various applications thereof are continuously developed along with the development of technology and business requirements, and the sensor can be used for detecting various actual properties from distance to heat to pressure; the industrial system industry has a large number of machines or systems or clusters of interconnected devices which rely on sensors to normally operate, and the sensors networked in the process flow can continuously detect, measure and transmit any changed electric signals in the physical environment, and the electric signals are transmitted to a computer, process data and further guide a control system;
in reality, for each sensor in cluster equipment operation monitoring in a control system, data transmission is generally performed through a direct transmission model and a network-based transmission model; the direct transmission model is to directly send data to a receiver, so that a large amount of data is transmitted, and the energy consumption is increased; the network-based transmission model is used for transmitting data through links in the sensor network, and a data compression mechanism is used for reducing the data transmission quantity, so that energy sources are saved; however, in reality, in the data transmission process, a transmission interface channel is often required to plan, decide or allocate a data transmission task, and especially for the existence of different operation features of cluster devices in an actual control system, it is often difficult to ensure the decision balance of the data transmission channel, and it is difficult to improve the data transmission efficiency.
Disclosure of Invention
The invention aims to provide an intelligent monitoring data transmission system and method based on the running state of big data so as to solve the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme:
the system for intelligently monitoring the data transmission based on the running state of big data comprises: the system comprises a state intelligent sensing module, a data overall planning module, a behavior relation analysis module and a transmission prompting module;
the state intelligent sensing module is used for dividing storage space according to the number of the sensors, respectively storing state data generated in the running process of the multiple sensors, and generating an abnormal feedback set; and each abnormal feedback set stored in the operation and maintenance database is called to form an abnormal operation state behavior set;
the data overall planning module is used for storing the abnormal feedback sets generated by the sensors in the abnormal operation state behavior sets when the sensors synchronously sense different abnormal operation state behaviors, and carrying out overall planning and unified numbering on the abnormal operation state behavior sets; according to the abnormal operation state behavior set, an assimilation data sample library is established for analyzing assimilation conditions among the abnormal operation state behaviors, and all abnormal operation state behavior sets are stored;
The behavior relation analysis module is used for constructing an assimilation relation iteration model, randomly selecting one abnormal behavior state set as an assimilation medium in each iteration process, randomly selecting the other abnormal behavior state set as an assimilation target, and analyzing the assimilation relation between abnormal operation state behaviors; generating an assimilation relation behavior pair according to an assimilation relation iteration result, recording the time when each abnormal operation state behavior occurs, and generating a synchronous time set;
the transmission prompting module is used for establishing a one-dimensional coordinate time line, mapping the synchronous time set in the one-dimensional coordinate time line and dividing a continuous time interval; and analyzing a predicted time range of abnormal running state behaviors under a continuous time interval range, and keeping the data transmission channels of the sensors in the time range smooth.
Further, the state intelligent sensing module further comprises a state data acquisition unit and a state behavior sensing unit;
the state data acquisition unit is used for constructing a running data base, receiving and storing state data generated in the multi-sensor monitoring process, wherein the state data is feedback information parameters perceived by a sensor when an abnormal condition occurs to a monitored object; dividing a storage space for a transport database, uniformly numbering a plurality of sensors, and adding a unique code identifier to the storage space according to the number of the sensors, wherein one storage space correspondingly stores state data generated by one sensor, generates an abnormal feedback set, and marks as G (I) i )={FP 1 ，FP 2 ，...，FP n }, wherein I i Representing the unique coded identifier attached to the storage space, i is the number of the sensor, and FP 1 ，FP 2 ，...，FP n Respectively representing the 1 st, 2 nd, n state data perceived by the sensor;
the state behavior sensing unit is used for constructing an abnormal operation state behavior sensing model, the abnormal operation state behavior sensing model is used for modulating each abnormal feedback set stored in the operation data base to form an abnormal operation state behavior set, the abnormal operation state behavior set comprises a plurality of sub-item sets, when the abnormal condition of a monitored object occurs, each sub-item set takes the synchronous sensing behavior of a sensor as a guide, and each synchronous sensing sensor of the abnormal operation state behavior sensing model is used for generating an abnormal feedback set correspondingly.
Further, the data overall module further comprises a data set overall unit and a data sample library overall unit;
the data set overall unit is used for overall planning and numbering the abnormal operation state behavior sets, one abnormal operation state behavior set corresponds to one abnormal operation state behavior, and any abnormal operation state behavior set is marked as SB j ={G j (I 1 )，G j (I 2 )，...，G j (I m ) }, where SB j Represents the behavior set of the abnormal operation state corresponding to the j-th abnormal operation state behavior, G j (I 1 )，G j (I 2 )，...，G j (I m ) Respectively representing abnormal feedback sets generated by the sensors when the j-th abnormal running state acts and the 1,2, m sensors synchronously sense;
the data sample library overall unit establishes an assimilation data sample library for analyzing assimilation conditions among abnormal operation state behaviors according to the abnormal operation state behavior set, stores the assimilation data sample library into all abnormal operation state behavior sets, and marks the assimilation data sample library as R.
Further, the behavior relation analysis module further comprises an assimilation relation iteration model unit and a time recording unit;
the assimilation relation iteration model unit is used for constructing an assimilation relation iteration model, and the L-th iteration sample set is R L Then the first iteration sample set is R 1 And R is 1 =r; at the L th iteration sample set R L Any one of the abnormal behavior state sets SB x As an assimilation medium, denoted as L: SB (SB) x At the L-th iteration sample set R L Status set SB of exception behavior x Arbitrarily selecting an abnormal behavior state set SB y As an assimilation target, denoted as L: SB (SB) y Wherein x and y are numbers of the behaviors of the x and y abnormal operation states respectively, and x is not equal to y;
Then the sample set for iteration number L +1Let the L-th iteration output set be SR L (SB x ) The assimilation condition between abnormal operation state behaviors is analyzed, and the process of carrying out the L-th assimilation relation iteration is as follows:
，
wherein, AP (SB) x →SB y ) Representing the probability of matching assimilation between assimilation mediator and assimilation target, NUM [ G ] x (I i )∩G y (I i )]Representing an abnormal behavior state set SB x And abnormal behavior state set SB y In the same memory space I i Corresponding generated abnormal feedback set G x (I i ) And G y (I i ) The amount of state data contained in the intersection between NUM [ G ] x (I i )∪G y (I i )]Representing an abnormal behavior state set SB x And abnormal behavior state set SB y In the same memory space I i Corresponding generated abnormal feedback set G x (I i ) And G y (I i ) The amount of state data contained in the union of the two;
presetting an assimilation probability threshold, if AP (SB) x →SB y ) Greater than or equal to the assimilation probability threshold, the abnormal behavior state set SB is collected y Store to the L-th iteration output set SR L (SB x ) If not, the data is not stored; at the L th iteration sample set R L The next assimilation target is selected to continue to assimilate the medium L: SB (SB) x Performing matching assimilation until the L-th iteration sample set R L All assimilation targets in the sequence are matched and assimilated, and the L-th iteration output set SR is output L (SB x ) And carrying out the L+1st assimilation relation iteration;
Until all abnormal operation state behavior sets in the assimilation data sample library R complete matching assimilation, the assimilation relation iteration stops;
the saidThe time recording unit is used for comprehensively planning each iteration output set according to the iteration result of the assimilation relation; taking the abnormal operation state behaviors corresponding to the abnormal operation state behavior sets in each iteration output set range as clustering judgment objects, generating assimilation relation behavior pairs, and marking the assimilation relation behavior pairs as Q x →{Q 1 ，Q 2 ，...，Q y ，...，Q w }, wherein Q x ，Q 1 ，Q 2 ，...，Q y ，...，Q w Respectively, represents the x,1,2, the term y, w abnormal running state behaviors; recording the time when each abnormal operation state behavior occurs, and generating a synchronous time set, wherein the assimilation medium L: SB (SB) x Corresponding abnormal operation state behavior Q x The generated set of synchronization times is denoted as T (Q x )={T 1 ，T 2 ，...，T a Based on the assimilation relation behavior pair, { Q } 1 ，Q 2 ，...，Q y ，...，Q w Any one of assimilation targets L: SB (SB) y Corresponding abnormal operation state behavior Q y The generated set of synchronization times is noted as t (Q y )={t 1 ，t 2 ，...，t b }, wherein T is 1 ，T 2 ，...，T a Respectively represent abnormal operation state behaviors Q x Time of a occurrence, t 1 ，t 2 ，...，t b Respectively represent abnormal operation state behaviors Q y Time of b occurrences.
Further, the transmission prompting module further comprises a time interval mapping unit and a transmission analysis prompting unit;
The time interval mapping unit is used for establishing a one-dimensional coordinate time line and synchronizing a time set t (Q y ) Mapping on a one-dimensional coordinate time line, dividing continuous time intervals to obtain b-1 continuous time intervals, intercepting any continuous time interval, and marking as tt u ：t u-1 ～t u The method comprises the steps of carrying out a first treatment on the surface of the At the same time synchronize the time set T (Q x ) Mapping on a one-dimensional coordinate time line, and acquiring a synchronous time set T (Q) x ) Generates a subset of interval timesSet, denoted as T [ tt ] u ]={T 1 ，T 2 ，...，T c }；
The transmission analysis prompting unit is used for researching and judging abnormal operation state behaviors Q according to the interval time set y Calculating interval judging time V { T [ tt ] u ]}=c -1 Σ d=1 c (T d -t u ) The method comprises the steps of carrying out a first treatment on the surface of the Respectively selecting the maximum and minimum values in all interval studying and judging time, and marking as V max And V min ；
Behavior Q if current abnormal running state x Time of occurrence of T 0 Outputting abnormal operation state behavior Q according to the assimilation relation behavior pair y The time range of occurrence is [ T ] 0 +V min ，T 0 +V max ]And prompt the staff to make the abnormal operation state behavior set SB y The sensors corresponding to the different feedback sets in the time range [ T ] 0 +V min ，T 0 +V max ]The transmission channel in the inner part is kept smooth.
The intelligent monitoring data transmission method based on the running state of big data comprises the following steps:
Step S100: dividing storage spaces according to the number of the sensors, respectively storing state data generated in the running process of the multiple sensors, and generating an abnormal feedback set; and each abnormal feedback set stored in the operation and maintenance database is called to form an abnormal operation state behavior set;
step S200: when synchronously sensing the sensors under different abnormal running state behaviors, storing an abnormal feedback set generated by each sensor into the abnormal running state behavior set, and carrying out overall and unified numbering on the abnormal running state behavior set; according to the abnormal operation state behavior set, an assimilation data sample library is established for analyzing assimilation conditions among the abnormal operation state behaviors, and all abnormal operation state behavior sets are stored;
step S300: constructing an assimilation relation iteration model, randomly selecting one abnormal behavior state set as an assimilation medium in each iteration process, randomly selecting the other abnormal behavior state set as an assimilation target, and analyzing the assimilation relation between abnormal operation state behaviors; generating an assimilation relation behavior pair according to an assimilation relation iteration result, recording the time when each abnormal operation state behavior occurs, and generating a synchronous time set;
Step S400: establishing a one-dimensional coordinate time line, mapping the synchronous time set in the one-dimensional coordinate time line, and dividing a continuous time interval; and analyzing a predicted time range of abnormal running state behaviors under a continuous time interval range, and keeping the data transmission channels of the sensors in the time range smooth.
Further, the specific implementation process of the step S100 includes:
step S101: the method comprises the steps of constructing a database of operation data, receiving and storing state data generated in the process of monitoring a plurality of sensors, wherein the state data are feedback information parameters perceived by the sensors when an abnormal condition occurs to a monitored object; dividing a storage space for a transport database, uniformly numbering a plurality of sensors, and adding a unique code identifier to the storage space according to the number of the sensors, wherein one storage space correspondingly stores state data generated by one sensor, generates an abnormal feedback set, and marks as G (I) i )={FP 1 ，FP 2 ，...，FP n }, wherein I i Representing the unique coded identifier attached to the storage space, i is the number of the sensor, and FP 1 ，FP 2 ，...，FP n Respectively representing the 1 st, 2 nd, n state data perceived by the sensor;
step S102: constructing an abnormal running state behavior perception model, wherein the abnormal running state behavior perception model invokes each abnormal feedback set stored in the running data database to form an abnormal running state behavior set, each abnormal running state behavior set comprises a plurality of sub-item sets, when an abnormal condition occurs to a monitored object, the abnormal running state behavior perception model takes the synchronous perception behavior of a sensor as a guide, and each synchronous perceived sensor of the abnormal running state behavior perception model is integrated to generate an abnormal feedback set correspondingly;
According to the method, the industrial system industry has a large number of clusters of machines or systems or interconnection devices which can normally run only by relying on sensors, and the networked sensors in the process flow need to continuously sense and control feedback information parameters in the clusters and transmit data through a transmission channel; in the prior art, the protocol architecture of a transmission channel is always fixedly limited, so that the transmission efficiency of feedback data of each sensor is limited in the process of executing a large number of data transmission tasks, meanwhile, in the prior art, data transmission is generally carried out through a direct transmission model and a network-based transmission model, however, cluster equipment in an actual control system has different operation characteristics, and then data transmission is accompanied by a certain synchronization phenomenon, and the frequency of sensing feedback abnormal data of the sensor is also different, so that the occupation condition of the transmission channel of the data in the transmission process is often changed along with different operation characteristics of cluster equipment in the actual control system, and then the decision balance of the data transmission channel is often difficult to ensure; in the invention, the operation database is constructed, so that feedback information parameters sensed by the sensors can be stored in a uniformly divided storage space, and meanwhile, an abnormal operation state behavior sensing model is constructed, and different abnormal operation state behavior characteristics are comprehensively combined with an abnormal feedback set, because the information parameters fed back by each sensor can be regularly expressed under different abnormal operation state behavior characteristics, particularly under different operation state characteristics of cluster equipment in an actual control system, different abnormal operation state behavior characteristics are displayed through synchronous sensing of the sensors.
Further, the specific implementation process of the step S200 includes:
step S201: the abnormal operation state behavior sets are comprehensively and uniformly numbered, one abnormal operation state behavior set corresponds to one abnormal operation state behavior, and any abnormal operation state behavior set is marked as SB j ={G j (I 1 )，G j (I 2 )，...，G j (I m ) }, where SB j Representing abnormal operation corresponding to j-th abnormal operation state behaviorLine state behavior set, G j (I 1 )，G j (I 2 )，...，G j (I m ) Respectively representing abnormal feedback sets generated by the sensors when the j-th abnormal running state acts and the 1,2, m sensors synchronously sense;
step S202: according to the abnormal operation state behavior set, an assimilation data sample library is established for analyzing assimilation conditions among the abnormal operation state behaviors, all abnormal operation state behavior sets are stored, and the assimilation data sample library is marked as R;
according to the method, assimilation means that dissimilar or dissimilar things gradually become similar or identical, then the assimilation process can be expressed as all actions of incorporating other things under own rule system, and actions of methods and tools used in the processes, then, in the invention of the application, different operation state characteristics, namely abnormal operation state actions, are related by assimilation analysis aiming at different operation state characteristics of cluster equipment in an actual control system.
Further, the implementation process of the step S300 includes:
step S301: constructing an assimilation relation iteration model to enable an L-th iteration sample set to be R L Then the first iteration sample set is R 1 And R is 1 =r; at the L th iteration sample set R L Any one of the abnormal behavior state sets SB x As an assimilation medium, denoted as L: SB (SB) x At the L-th iteration sample set R L Status set SB of exception behavior x Arbitrarily selecting an abnormal behavior state set SB y As an assimilation target, denoted as L: SB (SB) y Wherein x and y are numbers of the behaviors of the x and y abnormal operation states respectively, and x is not equal to y;
then the sample set for iteration number L +1Let the L-th iteration output set be SR L (SB x ) Analysis of assimilation between abnormal behavior and L-th assimilation relationship iteration processThe following steps:
，
wherein, AP (SB) x →SB y ) Representing the probability of matching assimilation between assimilation mediator and assimilation target, NUM [ G ] x (I i )∩G y (I i )]Representing an abnormal behavior state set SB x And abnormal behavior state set SB y In the same memory space I i Corresponding generated abnormal feedback set G x (I i ) And G y (I i ) The amount of state data contained in the intersection between NUM [ G ] x (I i )∪G y (I i )]Representing an abnormal behavior state set SB x And abnormal behavior state set SB y In the same memory space I i Corresponding generated abnormal feedback set G x (I i ) And G y (I i ) The amount of state data contained in the union of the two;
presetting an assimilation probability threshold, if AP (SB) x →SB y ) Greater than or equal to the assimilation probability threshold, the abnormal behavior state set SB is collected y Store to the L-th iteration output set SR L (SB x ) If not, the data is not stored; at the L th iteration sample set R L The next assimilation target is selected to continue to assimilate the medium L: SB (SB) x Performing matching assimilation until the L-th iteration sample set R L All assimilation targets in the sequence are matched and assimilated, and the L-th iteration output set SR is output L (SB x ) And carrying out the L+1st assimilation relation iteration;
until all abnormal operation state behavior sets in the assimilation data sample library R complete matching assimilation, the assimilation relation iteration stops;
step S302: according to the assimilation relation iteration result, comprehensively planning each iteration output set; taking the abnormal operation state behaviors corresponding to the abnormal operation state behavior sets in each iteration output set range as clustering judgment objects, generating assimilation relation behavior pairs, and marking the assimilation relation behavior pairs as Q x →{Q 1 ，Q 2 ，...，Q y ，...，Q w }, wherein Q x ，Q 1 ，Q 2 ，...，Q y ，...，Q w Respectively, represents the x,1,2, the term y, w abnormal running state behaviors; recording the time when each abnormal operation state behavior occurs, and generating a synchronous time set, wherein the assimilation medium L: SB (SB) x Corresponding abnormal operation state behavior Q x The generated set of synchronization times is denoted as T (Q x )={T 1 ，T 2 ，...，T a Based on the assimilation relation behavior pair, { Q } 1 ，Q 2 ，...，Q y ，...，Q w Any one of assimilation targets L: SB (SB) y Corresponding abnormal operation state behavior Q y The generated set of synchronization times is noted as t (Q y )={t 1 ，t 2 ，...，t b }, wherein T is 1 ，T 2 ，...，T a Respectively represent abnormal operation state behaviors Q x Time of a occurrence, t 1 ，t 2 ，...，t b Respectively represent abnormal operation state behaviors Q y Time of b occurrences;
according to the method, the assimilation condition is analyzed, namely, searching among abnormal operation state behaviors, based on the time distribution rule in the synchronous transmission process of the data, which is guided by the synchronous sensing behavior of the sensor, then the assimilation relation iteration model is constructed, and in each iteration process, the association relation among the abnormal operation state behaviors is searched, namely, an iteration output set is output, and in one iteration output set SR L (SB x ) In when the abnormal behavior state is set SB x When the abnormal behavior state is generated, according to the matching assimilation probability, the abnormal behavior state set SB y It is also highly likely that the greater the match assimilation probability value, the abnormal behavior state set SB y The greater the probability of occurrence; at the same time, when an abnormal behavior state set SB is selected x As an assimilation medium, after matching assimilation analysis with different assimilation targets, an iterative output set SR is output L (SB x ) Then, in the next iteration, the abnormal behavior state set SB can not be used x As assimilation medium, followed by the L+1st iteration sample setWherein->The assimilation medium of the previous L+1 iterations is comprehensively prepared, and no association analysis is carried out by eliminating the previous L+1 iterations, so that the operation amount of data is reduced, and the comprehensiveness of assimilation relation analysis is improved.
Further, the specific implementation process of the step S400 includes:
step S401: establishing a one-dimensional coordinate time line, and synchronizing the time set t (Q y ) Mapping on a one-dimensional coordinate time line, dividing continuous time intervals to obtain b-1 continuous time intervals, intercepting any continuous time interval, and marking as tt u ：t u-1 ～t u The method comprises the steps of carrying out a first treatment on the surface of the At the same time synchronize the time set T (Q x ) Mapping on a one-dimensional coordinate time line, and acquiring a synchronous time set T (Q) x ) Generates a set of interval times, denoted T [ tt ] u ]={T 1 ，T 2 ，...，T c }；
Step S402: according to the interval time set, the abnormal running state behavior Q is researched and judged y Calculating interval judging time V { T [ tt ] u ]}=c -1 Σ d=1 c (T d -t u ) The method comprises the steps of carrying out a first treatment on the surface of the Respectively selecting the maximum and minimum values in all interval studying and judging time, and marking as V max And V min ；
Behavior Q if current abnormal running state x Time of occurrence of T 0 Outputting abnormal operation state behavior Q according to the assimilation relation behavior pair y The time range of occurrence is [ T ] 0 +V min ，T 0 +V max ]And prompt the staff to make the abnormal operation state behavior set SB y The sensors corresponding to the different feedback sets in the time range [ T ] 0 +V min ，T 0 +V max ]The transmission channel in the inner part is kept smooth;
according to the method, after determining the assimilation relation, that is, each iteration output set, an assimilation relation behavior pair is generated, according to the mapping condition of the time set, the abnormal operation state behaviors corresponding to the assimilation medium are analyzed in combination with the interval studying and judging time of the continuous time interval to deduce and predict the occurrence time of the abnormal operation state behaviors corresponding to the assimilation target, so that each synchronously perceived sensor existing in the abnormal operation state behaviors corresponding to the assimilation target is detected in the time range [ T ] 0 +V min ，T 0 +V max ]The transmission channel in the inner part needs to be kept clear.
Compared with the prior art, the invention has the following beneficial effects: in the intelligent monitoring data transmission system and method based on the running state of big data, the running data database is constructed, so that the feedback data of the sensor are stored in the uniformly divided storage space, and the abnormal running state behavior perception model is constructed, and different abnormal running state behavior characteristics are formed by combining an abnormal feedback set; aiming at the running state characteristics of cluster equipment in a control system, carrying out assimilation analysis to correlate abnormal running state behaviors to form an assimilation data sample library; constructing an assimilation relation iteration model, and finding out the association relation between abnormal operation state behaviors to form an assimilation relation behavior pair; analyzing and predicting the occurrence time of an assimilation target by analyzing and predicting the interval studying and judging time, and mining a time distribution rule in the data synchronous transmission process based on the synchronous sensing behavior of the sensor as a guide; therefore, the decision balance of the data transmission channel is ensured, and the data transmission efficiency is improved.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a schematic diagram of the intelligent monitoring data transmission system based on the running state of big data;
fig. 2 is a schematic diagram of steps of the intelligent monitoring data transmission method based on the running state of big data.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1-2, the present invention provides the following technical solutions:
referring to fig. 1, in a first embodiment: providing an intelligent monitoring data transmission system based on the running state of big data, the system comprises: the system comprises a state intelligent sensing module, a data overall planning module, a behavior relation analysis module and a transmission prompting module;
The state intelligent sensing module is used for dividing storage space according to the number of the sensors, respectively storing state data generated in the running process of the multiple sensors, and generating an abnormal feedback set; and each abnormal feedback set stored in the operation and maintenance database is called to form an abnormal operation state behavior set;
the state intelligent sensing module further comprises a state data acquisition unit and a state behavior sensing unit;
the state data acquisition unit is used for constructing a running data base, receiving and storing state data generated in the multi-sensor monitoring process, wherein the state data is feedback information parameters perceived by the sensor when an abnormal condition occurs to a monitored object; dividing a storage space for a transport database, uniformly numbering a plurality of sensors, and adding a unique code identifier to the storage space according to the number of the sensors, wherein one storage space correspondingly stores state data generated by one sensor, generates an abnormal feedback set, and marks as G (I) i )={FP 1 ，FP 2 ，...，FP n }, wherein I i Representing the unique coded identifier attached to the storage space, i is the number of the sensor, and FP 1 ，FP 2 ，...，FP n Respectively represent the transmissionSensor perceived 1, 2..n status data;
The state behavior sensing unit is used for constructing an abnormal operation state behavior sensing model, the abnormal operation state behavior sensing model is used for calling each abnormal feedback set stored in the operation data database to form an abnormal operation state behavior set, the abnormal operation state behavior set comprises a plurality of sub-item sets, when the abnormal condition of a monitored object occurs, each sub-item set takes the synchronous sensing behavior of a sensor as a guide, and each synchronous sensing sensor of the abnormal operation state behavior sensing model is used for generating an abnormal feedback set correspondingly;
the data overall planning module is used for storing the abnormal feedback sets generated by the sensors in the abnormal operation state behavior sets when synchronously sensing the sensors under different abnormal operation state behaviors, and carrying out overall planning and unified numbering on the abnormal operation state behavior sets; according to the abnormal operation state behavior set, an assimilation data sample library is established for analyzing assimilation conditions among the abnormal operation state behaviors, and all abnormal operation state behavior sets are stored;
the data overall module further comprises a data set overall unit and a data sample library overall unit;
the data set overall unit is used for overall and unified numbering of the abnormal operation state behavior sets, one abnormal operation state behavior set corresponds to one abnormal operation state behavior, and any abnormal operation state behavior set is marked as SB j ={G j (I 1 )，G j (I 2 )，...，G j (I m ) }, where SB j Represents the behavior set of the abnormal operation state corresponding to the j-th abnormal operation state behavior, G j (I 1 )，G j (I 2 )，...，G j (I m ) Respectively representing abnormal feedback sets generated by the sensors when the j-th abnormal running state acts and the 1,2, m sensors synchronously sense;
the data sample library overall unit is used for establishing an assimilation data sample library for analyzing assimilation conditions among abnormal operation state behaviors according to the abnormal operation state behavior set, storing the assimilation data sample library into all abnormal operation state behavior sets, and marking the assimilation data sample library as R;
the behavior relation analysis module is used for constructing an assimilation relation iteration model, randomly selecting one abnormal behavior state set as an assimilation medium in each iteration process, randomly selecting the other abnormal behavior state set as an assimilation target, and analyzing the assimilation relation between abnormal operation state behaviors; generating an assimilation relation behavior pair according to an assimilation relation iteration result, recording the time when each abnormal operation state behavior occurs, and generating a synchronous time set;
the behavior relation analysis module further comprises an assimilation relation iteration model unit and a time recording unit;
an assimilation relation iteration model unit for constructing an assimilation relation iteration model to make the L-th iteration sample set be R L Then the first iteration sample set is R 1 And R is 1 =r; at the L th iteration sample set R L Any one of the abnormal behavior state sets SB x As an assimilation medium, denoted as L: SB (SB) x At the L-th iteration sample set R L Status set SB of exception behavior x Arbitrarily selecting an abnormal behavior state set SB y As an assimilation target, denoted as L: SB (SB) y Wherein x and y are numbers of the behaviors of the x and y abnormal operation states respectively, and x is not equal to y;
then the sample set for iteration number L +1Let the L-th iteration output set be SR L (SB x ) The assimilation condition between abnormal operation state behaviors is analyzed, and the process of carrying out the L-th assimilation relation iteration is as follows:
，
wherein, AP (SB) x →SB y ) Representing the probability of matching assimilation between assimilation mediator and assimilation target, NUM [ G ] x (I i )∩G y (I i )]Representing an abnormal behavior state set SB x And abnormal behavior state set SB y In the same memory space I i Corresponding generated abnormal feedback set G x (I i ) And G y (I i ) The amount of state data contained in the intersection between NUM [ G ] x (I i )∪G y (I i )]Representing an abnormal behavior state set SB x And abnormal behavior state set SB y In the same memory space I i Corresponding generated abnormal feedback set G x (I i ) And G y (I i ) The amount of state data contained in the union of the two;
presetting an assimilation probability threshold, if AP (SB) x →SB y ) Greater than or equal to the assimilation probability threshold, the abnormal behavior state set SB is collected y Store to the L-th iteration output set SR L (SB x ) If not, the data is not stored; at the L th iteration sample set R L The next assimilation target is selected to continue to assimilate the medium L: SB (SB) x Performing matching assimilation until the L-th iteration sample set R L All assimilation targets in the sequence are matched and assimilated, and the L-th iteration output set SR is output L (SB x ) And carrying out the L+1st assimilation relation iteration;
until all abnormal operation state behavior sets in the assimilation data sample library R complete matching assimilation, the assimilation relation iteration stops;
the time recording unit is used for comprehensively planning each iteration output set according to the iteration result of the assimilation relation; taking the abnormal operation state behaviors corresponding to the abnormal operation state behavior sets in each iteration output set range as clustering judgment objects, generating assimilation relation behavior pairs, and marking the assimilation relation behavior pairs as Q x →{Q 1 ，Q 2 ，...，Q y ，...，Q w }, wherein Q x ，Q 1 ，Q 2 ，...，Q y ，...，Q w Respectively, represents the x,1,2, the term y, w abnormal running state behaviors; recording the time when each abnormal operation state behavior occurs, and generating a synchronous time set, wherein the assimilation medium L: SB (SB) x Corresponding abnormal operation state behavior Q x The generated set of synchronization times is denoted as T (Q x )={T 1 ，T 2 ，...，T a Based on the assimilation relation behavior pair, { Q } 1 ，Q 2 ，...，Q y ，...，Q w Any one of assimilation targets L: SB (SB) y Corresponding abnormal operation state behavior Q y The generated set of synchronization times is noted as t (Q y )={t 1 ，t 2 ，...，t b }, wherein T is 1 ，T 2 ，...，T a Respectively represent abnormal operation state behaviors Q x Time of a occurrence, t 1 ，t 2 ，...，t b Respectively represent abnormal operation state behaviors Q y Time of b occurrences;
the transmission prompting module is used for establishing a one-dimensional coordinate time line, mapping the synchronous time set in the one-dimensional coordinate time line and dividing a continuous time interval; analyzing a predicted time range of abnormal running state behaviors in a continuous time interval range, and keeping the data transmission channels of the sensors in the time range smooth;
the transmission prompting module further comprises a time interval mapping unit and a transmission analysis prompting unit;
a time interval mapping unit for establishing a one-dimensional coordinate time line and synchronizing the time set t (Q y ) Mapping on a one-dimensional coordinate time line, dividing continuous time intervals to obtain b-1 continuous time intervals, intercepting any continuous time interval, and marking as tt u ：t u-1 ～t u The method comprises the steps of carrying out a first treatment on the surface of the At the same time synchronize the time set T (Q x ) Mapping on a one-dimensional coordinate time line, and acquiring a synchronous time set T (Q) x ) Generates a set of interval times, denoted T [ tt ] u ]={T 1 ，T 2 ，...，T c }；
The transmission analysis prompting unit is used for researching and judging abnormal operation state behaviors Q according to the interval time set y Calculating interval judging time V { T [ tt ] u ]}=c -1 Σ d=1 c (T d -t u ) The method comprises the steps of carrying out a first treatment on the surface of the At allRespectively selecting the maximum and minimum values in the interval studying and judging time of (2) and marking as V max And V min ；
Behavior Q if current abnormal running state x Time of occurrence of T 0 Outputting abnormal operation state behavior Q according to the assimilation relation behavior pair y The time range of occurrence is [ T ] 0 +V min ，T 0 +V max ]And prompt the staff to make the abnormal operation state behavior set SB y The sensors corresponding to the different feedback sets in the time range [ T ] 0 +V min ，T 0 +V max ]The transmission channel in the inner part is kept smooth.
Referring to fig. 2, in the second embodiment: the method for intelligently monitoring the data transmission based on the running state of big data comprises the following steps:
dividing storage spaces according to the number of the sensors, respectively storing state data generated in the running process of the multiple sensors, and generating an abnormal feedback set; and each abnormal feedback set stored in the operation and maintenance database is called to form an abnormal operation state behavior set;
the system comprises a framework operation data base, a sensor and a control unit, wherein the framework operation data base receives and stores state data generated in the multi-sensor monitoring process, and the state data is feedback information parameters perceived by the sensor when an abnormal condition occurs to a monitored object; dividing a storage space for a transport database, uniformly numbering a plurality of sensors, and adding a unique code identifier to the storage space according to the number of the sensors, wherein one storage space correspondingly stores state data generated by one sensor, generates an abnormal feedback set, and marks as G (I) i )={FP 1 ，FP 2 ，...，FP n }, wherein I i Representing the unique coded identifier attached to the storage space, i is the number of the sensor, and FP 1 ，FP 2 ，...，FP n Respectively representing the 1 st, 2 nd, n state data perceived by the sensor;
when synchronously sensing the sensors under different abnormal running state behaviors, storing an abnormal feedback set generated by each sensor into the abnormal running state behavior set, and carrying out overall and unified numbering on the abnormal running state behavior set; according to the abnormal operation state behavior set, an assimilation data sample library is established for analyzing assimilation conditions among the abnormal operation state behaviors, and all abnormal operation state behavior sets are stored;
the abnormal operation state behavior sets are comprehensively and uniformly numbered, one abnormal operation state behavior set corresponds to one abnormal operation state behavior, and any abnormal operation state behavior set is marked as SB j ={G j (I 1 )，G j (I 2 )，...，G j (I m ) }, where SB j Represents the behavior set of the abnormal operation state corresponding to the j-th abnormal operation state behavior, G j (I 1 )，G j (I 2 )，...，G j (I m ) Respectively representing abnormal feedback sets generated by the sensors when the j-th abnormal running state acts and the 1,2, m sensors synchronously sense;
according to the abnormal operation state behavior set, an assimilation data sample library is established for analyzing assimilation conditions among the abnormal operation state behaviors, all the abnormal operation state behavior sets are stored, and the assimilation data sample library is marked as R;
Constructing an assimilation relation iteration model, randomly selecting one abnormal behavior state set as an assimilation medium in each iteration process, randomly selecting the other abnormal behavior state set as an assimilation target, and analyzing the assimilation relation between abnormal operation state behaviors; generating an assimilation relation behavior pair according to an assimilation relation iteration result, recording the time when each abnormal operation state behavior occurs, and generating a synchronous time set;
constructing an abnormal running state behavior sensing model, wherein the abnormal running state behavior sensing model is used for calling each abnormal feedback set stored in the running data database to form an abnormal running state behavior set, each abnormal running state behavior set comprises a plurality of sub-item sets, when an abnormal condition occurs to a monitored object, each sub-item set takes the synchronous sensing behavior of a sensor as a guide, and each synchronous sensing sensor of the abnormal running state behavior sensing model is used for generating an abnormal feedback set correspondingly;
constructing an assimilation relation iteration model to enable an L-th iteration sample set to be R L Then the first iteration sample set is R 1 And R is 1 =r; at the L th iteration sample set R L Any one of the abnormal behavior state sets SB x As an assimilation medium, denoted as L: SB (SB) x At the L-th iteration sample set R L Status set SB of exception behavior x Arbitrarily selecting an abnormal behavior state set SB y As an assimilation target, denoted as L: SB (SB) y Wherein x and y are numbers of the behaviors of the x and y abnormal operation states respectively, and x is not equal to y;
then the sample set for iteration number L +1Let the L-th iteration output set be SR L (SB x ) The assimilation condition between abnormal operation state behaviors is analyzed, and the process of carrying out the L-th assimilation relation iteration is as follows:
，
wherein, AP (SB) x →SB y ) Representing the probability of matching assimilation between assimilation mediator and assimilation target, NUM [ G ] x (I i )∩G y (I i )]Representing an abnormal behavior state set SB x And abnormal behavior state set SB y In the same memory space I i Corresponding generated abnormal feedback set G x (I i ) And G y (I i ) The amount of state data contained in the intersection between NUM [ G ] x (I i )∪G y (I i )]Representing an abnormal behavior state set SB x And abnormal behavior state set SB y In the same memory space I i Corresponding generated abnormal feedback set G x (I i ) And G y (I i ) The amount of state data contained in the union of the two;
presetting an assimilation probability threshold, if AP (SB) x →SB y ) Greater than or equal to assimilation probabilityRate threshold, abnormal behavior state set SB y Store to the L-th iteration output set SR L (SB x ) If not, the data is not stored; at the L th iteration sample set R L The next assimilation target is selected to continue to assimilate the medium L: SB (SB) x Performing matching assimilation until the L-th iteration sample set R L All assimilation targets in the sequence are matched and assimilated, and the L-th iteration output set SR is output L (SB x ) And carrying out the L+1st assimilation relation iteration;
until all abnormal operation state behavior sets in the assimilation data sample library R complete matching assimilation, the assimilation relation iteration stops;
according to the assimilation relation iteration result, comprehensively planning each iteration output set; taking the abnormal operation state behaviors corresponding to the abnormal operation state behavior sets in each iteration output set range as clustering judgment objects, generating assimilation relation behavior pairs, and marking the assimilation relation behavior pairs as Q x →{Q 1 ，Q 2 ，...，Q y ，...，Q w }, wherein Q x ，Q 1 ，Q 2 ，...，Q y ，...，Q w Respectively, represents the x,1,2, the term y, w abnormal running state behaviors; recording the time when each abnormal operation state behavior occurs, and generating a synchronous time set, wherein the assimilation medium L: SB (SB) x Corresponding abnormal operation state behavior Q x The generated set of synchronization times is denoted as T (Q x )={T 1 ，T 2 ，...，T a Based on the assimilation relation behavior pair, { Q } 1 ，Q 2 ，...，Q y ，...，Q w Any one of assimilation targets L: SB (SB) y Corresponding abnormal operation state behavior Q y The generated set of synchronization times is noted as t (Q y )={t 1 ，t 2 ，...，t b }, wherein T is 1 ，T 2 ，...，T a Respectively represent abnormal operation state behaviors Q x Time of a occurrence, t 1 ，t 2 ，...，t b Respectively represent abnormal operation state behaviors Q y Time of b occurrences;
for exampleIn iteration 2, the sample set is iterated={SB 1 ，SB 2 ，SB 3 ，SB 4 }-{SB 1 }={SB 2 ，SB 3 ，SB 4 Sample set R at iteration 2 2 Any one of the abnormal behavior state sets SB 2 As assimilation medium, at iteration 2, sample set R 2 Status set SB of exception behavior 2 Arbitrarily selecting an abnormal behavior state set SB 3 As an assimilation target, assimilation conditions between abnormal operation state behaviors were analyzed, and AP (SB 2 →SB 3 ) If AP (SB) 2 →SB 3 ) Greater than or equal to the assimilation probability threshold, the abnormal behavior state set SB is collected 3 Deposit into the 2 nd iteration output set SR 2 (SB 2 ) If not, the data is not stored; at iteration 2, sample set R 2 Selecting the next assimilation target, namely an abnormal behavior state set SB 4 Continuing and assimilating medium 2: SB (SB) 2 Matching assimilation was performed, and AP (SB) was calculated 2 →SB 4 ) Is a value of (2);
establishing a one-dimensional coordinate time line, mapping the synchronous time set in the one-dimensional coordinate time line, and dividing a continuous time interval; analyzing a predicted time range of abnormal running state behaviors in a continuous time interval range, and keeping the data transmission channels of the sensors in the time range smooth;
Establishing a one-dimensional coordinate time line, and synchronizing the time set t (Q y ) Mapping on a one-dimensional coordinate time line, dividing continuous time intervals to obtain b-1 continuous time intervals, intercepting any continuous time interval, and marking as tt u ：t u-1 ～t u The method comprises the steps of carrying out a first treatment on the surface of the At the same time synchronize the time set T (Q x ) Mapping on a one-dimensional coordinate time line, and acquiring a synchronous time set T (Q) x ) Generates a set of interval times, denoted T [ tt ] u ]={T 1 ，T 2 ，...，T c }；
According to the intervalTime set, study and judge abnormal running state behavior Q y Calculating interval judging time V { T [ tt ] u ]}=c -1 Σ d=1 c (T d -t u ) The method comprises the steps of carrying out a first treatment on the surface of the Respectively selecting the maximum and minimum values in all interval studying and judging time, and marking as V max And V min ；
Behavior Q if current abnormal running state x Time of occurrence of T 0 Outputting abnormal operation state behavior Q according to the assimilation relation behavior pair y The time range of occurrence is [ T ] 0 +V min ，T 0 +V max ]And prompt the staff to make the abnormal operation state behavior set SB y The sensors corresponding to the different feedback sets in the time range [ T ] 0 +V min ，T 0 +V max ]The transmission channel in the inner part is kept smooth.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: the foregoing description is only a preferred embodiment of the present invention and is not intended to limit the present invention, but although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the technical solutions described in the foregoing embodiments, or equivalents may be substituted for some of the technical features thereof. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (4)

1. The intelligent monitoring data transmission method based on the running state of big data is characterized by comprising the following steps:
step S100: dividing storage spaces according to the number of the sensors, respectively storing state data generated in the running process of the multiple sensors, and generating an abnormal feedback set; and each abnormal feedback set stored in the operation and maintenance database is called to form an abnormal operation state behavior set;
step S200: when synchronously sensing the sensors under different abnormal running state behaviors, storing an abnormal feedback set generated by each sensor into the abnormal running state behavior set, and carrying out overall and unified numbering on the abnormal running state behavior set; according to the abnormal operation state behavior set, an assimilation data sample library is established for analyzing assimilation conditions among the abnormal operation state behaviors, and all abnormal operation state behavior sets are stored;
Step S300: constructing an assimilation relation iteration model, randomly selecting one abnormal behavior state set as an assimilation medium in each iteration process, randomly selecting the other abnormal behavior state set as an assimilation target, and analyzing the assimilation relation between abnormal operation state behaviors; generating an assimilation relation behavior pair according to an assimilation relation iteration result, recording the time when each abnormal operation state behavior occurs, and generating a synchronous time set;
step S400: establishing a one-dimensional coordinate time line, mapping the synchronous time set in the one-dimensional coordinate time line, and dividing a continuous time interval; analyzing a predicted time range of abnormal running state behaviors in a continuous time interval range, and keeping the data transmission channels of the sensors in the time range smooth;
the specific implementation process of the step S100 includes:
step S101: the method comprises the steps of constructing a database of operation data, receiving and storing state data generated in the process of monitoring a plurality of sensors, wherein the state data are feedback information parameters perceived by the sensors when an abnormal condition occurs to a monitored object; dividing the storage space of the operation and maintenance data base, uniformly numbering the multiple sensors, and according to the operation and maintenance data base The number of the sensor, add the unique code label to the memory space, wherein, a memory space correspondingly stores the state data generated by a sensor, and generates an abnormal feedback set, which is marked as G (I) i )＝{FP 1 ，FP 2 ，...，FP n }, wherein I i Representing the unique coded identifier attached to the storage space, i is the number of the sensor, and FP 1 ，FP 2 ，...，FP n Respectively representing the 1 st, 2 nd, n state data perceived by the sensor;
step S102: constructing an abnormal running state behavior perception model, wherein the abnormal running state behavior perception model invokes each abnormal feedback set stored in the running data database to form an abnormal running state behavior set, each abnormal running state behavior set comprises a plurality of sub-item sets, when an abnormal condition occurs to a monitored object, the abnormal running state behavior perception model takes the synchronous perception behavior of a sensor as a guide, and each synchronous perceived sensor of the abnormal running state behavior perception model is integrated to generate an abnormal feedback set correspondingly;
the specific implementation process of the step S200 includes:
step S201: the abnormal operation state behavior sets are comprehensively and uniformly numbered, one abnormal operation state behavior set corresponds to one abnormal operation state behavior, and any abnormal operation state behavior set is marked as SB j ＝{G j (I 1 )，G j (I 2 )，...，G j (I m ) }, where SB j Represents the behavior set of the abnormal operation state corresponding to the j-th abnormal operation state behavior, G j (I 1 )，G j (I 2 )，...，G j (I m ) Respectively representing abnormal feedback sets generated by the sensors when the j-th abnormal running state acts and the 1,2, m sensors synchronously sense;
step S202: according to the abnormal operation state behavior set, an assimilation data sample library is established for analyzing assimilation conditions among the abnormal operation state behaviors, all abnormal operation state behavior sets are stored, and the assimilation data sample library is marked as R;
the specific implementation process of the step S300 includes:
step S301: constructing an assimilation relation iteration model to enable an L-th iteration sample set to be R L Then the first iteration sample set is R 1 And R is 1 =r; at the L th iteration sample set R L Any one of the abnormal behavior state sets SB x As an assimilation medium, denoted as L: SB (SB) x At the L-th iteration sample set R L Status set SB of exception behavior x Arbitrarily selecting an abnormal behavior state set SB y As an assimilation target, denoted as L: SB (SB) y Wherein x and y are numbers of the behaviors of the x and y abnormal operation states respectively, and x is not equal to y;
then the sample set for iteration number L +1Let the L-th iteration output set be SR L (SB x ) The assimilation condition between abnormal operation state behaviors is analyzed, and the process of carrying out the L-th assimilation relation iteration is as follows:
wherein, AP (SB) x →SB y ) Representing the probability of matching assimilation between assimilation mediator and assimilation target, NUM [ G ] x (I i )∩G y (I i )]Representing an abnormal behavior state set SB x And abnormal behavior state set SB y In the same memory space I i Corresponding generated abnormal feedback set G x (I i ) And G y (I i ) The amount of state data contained in the intersection between NUM [ G ] x (I i )∪G y (I i )]Representing an abnormal behavior state set SB x And abnormal behavior state set SB y In the same memory space I i Corresponding generated abnormal feedback set G x (I i ) And G y (I i ) The amount of state data contained in the union of the two;
presetting an assimilation probability threshold, if AP (SB) x →SB y ) Greater than or equal to the assimilation probability threshold, the abnormal behavior state set SB is collected y Store to the L-th iteration output set SR L (SB x ) If not, the data is not stored; at the L th iteration sample set R L The next assimilation target is selected to continue to assimilate the medium L: SB (SB) x Performing matching assimilation until the L-th iteration sample set R L All assimilation targets in the sequence are matched and assimilated, and the L-th iteration output set SR is output L (SB x ) And carrying out the L+1st assimilation relation iteration;
until all abnormal operation state behavior sets in the assimilation data sample library R complete matching assimilation, the assimilation relation iteration stops;
Step S302: according to the assimilation relation iteration result, comprehensively planning each iteration output set; taking the abnormal operation state behaviors corresponding to the abnormal operation state behavior sets in each iteration output set range as clustering judgment objects, generating assimilation relation behavior pairs, and marking the assimilation relation behavior pairs as Q x →{Q 1 ，Q 2 ，...，Q y ，...，Q w }, wherein Q x ，Q 1 ，Q 2 ，...，Q y ，...，Q w Respectively, represents the x,1,2, the term y, w abnormal running state behaviors; recording the time when each abnormal operation state behavior occurs, and generating a synchronous time set, wherein the assimilation medium L: SB (SB) x Corresponding abnormal operation state behavior Q x The generated set of synchronization times is denoted as T (Q x )＝{T 1 ，T 2 ，...，T a Based on the assimilation relation behavior pair, { Q } 1 ，Q 2 ，...，Q y ，...，Q w Any one of assimilation targets L: SB (SB) y Corresponding abnormal operation state behavior Q y The generated set of synchronization times is noted as t (Q y )＝{t 1 ，t 2 ，...，t b }, wherein T is 1 ，T 2 ，...，T a Respectively represent abnormal operation state behaviors Q x Time of a occurrence, t 1 ，t 2 ，...，t b Respectively represent abnormal operation state behaviors Q y Time of b occurrences.
2. The method for intelligently monitoring data transmission based on the operation state of big data according to claim 1, wherein the specific implementation process of step S400 includes:
step S401: establishing a one-dimensional coordinate time line, and synchronizing the time set t (Q y ) Mapping on a one-dimensional coordinate time line, dividing continuous time intervals to obtain b-1 continuous time intervals, intercepting any continuous time interval, and marking as tt u ：t u-1 ～t u The method comprises the steps of carrying out a first treatment on the surface of the At the same time synchronize the time set T (Q x ) Mapping on a one-dimensional coordinate time line, and acquiring a synchronous time set T (Q) x ) Generates a set of interval times, denoted T [ tt ] u ]＝{T 1 ，T 2 ，...，T c }；
Step S402: according to the interval time set, the abnormal running state behavior Q is researched and judged y Calculating interval judging time V { T [ tt ] u ]}＝c -1 Σ d＝1 c (T d -t u ) The method comprises the steps of carrying out a first treatment on the surface of the Respectively selecting the maximum and minimum values in all interval studying and judging time, and marking as V max And V min ；
Behavior Q if current abnormal running state x Time of occurrence of T 0 Outputting abnormal operation state behavior Q according to the assimilation relation behavior pair y The time range of occurrence is [ T ] 0 +V min ，T 0 +V max ]And prompt the staff to make the abnormal operation state behavior set SB y The sensors corresponding to the different feedback sets in the time range [ T ] 0 +V min ，T 0 +V max ]The transmission channel in the inner part is kept smooth.
3. The utility model provides an operation state intelligent monitoring data transmission system based on big data which characterized in that, the system includes: the system comprises a state intelligent sensing module, a data overall planning module, a behavior relation analysis module and a transmission prompting module;
The state intelligent sensing module is used for dividing storage space according to the number of the sensors, respectively storing state data generated in the running process of the multiple sensors, and generating an abnormal feedback set; and each abnormal feedback set stored in the operation and maintenance database is called to form an abnormal operation state behavior set;
the data overall planning module is used for storing the abnormal feedback sets generated by the sensors in the abnormal operation state behavior sets when the sensors synchronously sense different abnormal operation state behaviors, and carrying out overall planning and unified numbering on the abnormal operation state behavior sets; according to the abnormal operation state behavior set, an assimilation data sample library is established for analyzing assimilation conditions among the abnormal operation state behaviors, and all abnormal operation state behavior sets are stored;
the behavior relation analysis module is used for constructing an assimilation relation iteration model, randomly selecting one abnormal behavior state set as an assimilation medium in each iteration process, randomly selecting the other abnormal behavior state set as an assimilation target, and analyzing the assimilation relation between abnormal operation state behaviors; generating an assimilation relation behavior pair according to an assimilation relation iteration result, recording the time when each abnormal operation state behavior occurs, and generating a synchronous time set;
The transmission prompting module is used for establishing a one-dimensional coordinate time line, mapping the synchronous time set in the one-dimensional coordinate time line and dividing a continuous time interval; analyzing a predicted time range of abnormal running state behaviors in a continuous time interval range, and keeping the data transmission channels of the sensors in the time range smooth;
the state intelligent perception module further comprises a state data acquisition unit and a state behavior perception unit;
the state data acquisition unit is used for constructing a running data base, receiving and storing state data generated in the multi-sensor monitoring process, wherein the state data is feedback information parameters perceived by a sensor when an abnormal condition occurs to a monitored object; partitioning a database of operational dimensionsThe storage space is uniformly numbered for a plurality of sensors, and a unique code identifier is added to the storage space according to the number of the sensors, wherein one storage space correspondingly stores state data generated by one sensor, and an abnormal feedback set is generated and is marked as G (I) i )＝{FP 1 ，FP 2 ，...，FP n }, wherein I i Representing the unique coded identifier attached to the storage space, i is the number of the sensor, and FP 1 ，FP 2 ，...，FP n Respectively representing the 1 st, 2 nd, n state data perceived by the sensor;
The state behavior sensing unit is used for constructing an abnormal operation state behavior sensing model, the abnormal operation state behavior sensing model is used for calling each abnormal feedback set stored in the operation data base to form an abnormal operation state behavior set, the abnormal operation state behavior set comprises a plurality of sub-item sets, when the abnormal condition of a monitored object occurs, each sub-item set takes the synchronous sensing behavior of a sensor as a guide, and each synchronous sensing sensor of the abnormal operation state behavior sensing model is used for generating an abnormal feedback set correspondingly;
the data overall module further comprises a data set overall unit and a data sample library overall unit;
the data set overall unit is used for overall planning and numbering the abnormal operation state behavior sets, one abnormal operation state behavior set corresponds to one abnormal operation state behavior, and any abnormal operation state behavior set is marked as SB j ＝{G j (I 1 )，G j (I 2 )，...，G j (I m ) }, where SB j Represents the behavior set of the abnormal operation state corresponding to the j-th abnormal operation state behavior, G j (I 1 )，G j (I 2 )，...，G j (I m ) Respectively representing abnormal feedback sets generated by the sensors when the j-th abnormal running state acts and the 1,2, m sensors synchronously sense;
The data sample library overall unit establishes an assimilation data sample library according to the abnormal operation state behavior set for analyzing assimilation conditions among the abnormal operation state behaviors, stores the assimilation data sample library into all the abnormal operation state behavior sets, and marks the assimilation data sample library as R;
the behavior relation analysis module further comprises an assimilation relation iteration model unit and a time recording unit;
the assimilation relation iteration model unit is used for constructing an assimilation relation iteration model, and the L-th iteration sample set is R L Then the first iteration sample set is R 1 And R is 1 =r; at the L th iteration sample set R L Any one of the abnormal behavior state sets SB x As an assimilation medium, denoted as L: SB (SB) x At the L-th iteration sample set R L Status set SB of exception behavior x Arbitrarily selecting an abnormal behavior state set SB y As an assimilation target, denoted as L: SB (SB) y Wherein x and y are numbers of the behaviors of the x and y abnormal operation states respectively, and x is not equal to y;
then the sample set for iteration number L +1Let the L-th iteration output set be SR L (SB x ) The assimilation condition between abnormal operation state behaviors is analyzed, and the process of carrying out the L-th assimilation relation iteration is as follows:
wherein, AP (SB) x →SB y ) Representing the probability of matching assimilation between assimilation mediator and assimilation target, NUM [ G ] x (I i )∩G y (I i )]Representing an abnormal behavior state set SB x And abnormal behavior state set SB y In the same memory space I i Corresponding generated abnormal feedback set G x (I i ) And G y (I i ) The amount of state data contained in the intersection between NUM [ G ] x (I i )∪G y (I i )]Representing abnormal rowsIs a state set SB x And abnormal behavior state set SB y In the same memory space I i Corresponding generated abnormal feedback set G x (I i ) And G y (I i ) The amount of state data contained in the union of the two;
presetting an assimilation probability threshold, if AP (SB) x →SB y ) Greater than or equal to the assimilation probability threshold, the abnormal behavior state set SB is collected y Store to the L-th iteration output set SR L (SB x ) If not, the data is not stored; at the L th iteration sample set R L The next assimilation target is selected to continue to assimilate the medium L: SB (SB) x Performing matching assimilation until the L-th iteration sample set R L All assimilation targets in the sequence are matched and assimilated, and the L-th iteration output set SR is output L (SB x ) And carrying out the L+1st assimilation relation iteration;
until all abnormal operation state behavior sets in the assimilation data sample library R complete matching assimilation, the assimilation relation iteration stops;
the time recording unit is used for comprehensively planning each iteration output set according to the iteration result of the assimilation relation; taking the abnormal operation state behaviors corresponding to the abnormal operation state behavior sets in each iteration output set range as clustering judgment objects, generating assimilation relation behavior pairs, and marking the assimilation relation behavior pairs as Q x →{Q 1 ，Q 2 ，...，Q y ，...，Q w }, wherein Q x ，Q 1 ，Q 2 ，...，Q y ，...，Q w Respectively, represents the x,1,2, the term y, w abnormal running state behaviors; recording the time when each abnormal operation state behavior occurs, and generating a synchronous time set, wherein the assimilation medium L: SB (SB) x Corresponding abnormal operation state behavior Q x The generated set of synchronization times is denoted as T (Q x )＝{T 1 ，T 2 ，...，T a Based on the assimilation relation behavior pair, { Q } 1 ，Q 2 ，...，Q y ，...，Q w Any one of assimilation targets L: SB (SB) y Corresponding abnormal operation state behavior Q y The generated set of synchronization times is noted as t (Q y )＝{t 1 ，t 2 ，...，t b }, wherein T is 1 ，T 2 ，...，T a Respectively represent abnormal operation state behaviors Q x Time of a occurrence, t 1 ，t 2 ，...，t b Respectively represent abnormal operation state behaviors Q y Time of b occurrences.
4. The big data based operational status intelligent monitoring data transmission system of claim 3, wherein: the transmission prompting module also comprises a time interval mapping unit and a transmission analysis prompting unit;
the time interval mapping unit is used for establishing a one-dimensional coordinate time line and synchronizing a time set t (Q y ) Mapping on a one-dimensional coordinate time line, dividing continuous time intervals to obtain b-1 continuous time intervals, intercepting any continuous time interval, and marking as tt u ：t u-1 ～t u The method comprises the steps of carrying out a first treatment on the surface of the At the same time synchronize the time set T (Q x ) Mapping on a one-dimensional coordinate time line, and acquiring a synchronous time set T (Q) x ) Generates a set of interval times, denoted T [ tt ] u ]＝{T 1 ，T 2 ，...，T c }；
The transmission analysis prompting unit is used for researching and judging abnormal operation state behaviors Q according to the interval time set y Calculating interval judging time V { T [ tt ] u ]}＝c -1 Σ d＝1 c (T d -t u ) The method comprises the steps of carrying out a first treatment on the surface of the Respectively selecting the maximum and minimum values in all interval studying and judging time, and marking as V max And V min ；
Behavior Q if current abnormal running state x Time of occurrence of T 0 Outputting abnormal operation state behavior Q according to the assimilation relation behavior pair y The time range of occurrence is [ T ] 0 +V min ，T 0 +V max ]And prompt the staff to make the abnormal operation state behavior set SB y The sensors corresponding to the different feedback sets are in the time rangeT 0 +V min ，T 0 +V max ]The transmission channel in the inner part is kept smooth.
CN202311288622.4A 2023-10-08 2023-10-08 Intelligent monitoring data transmission system and method based on running state of big data Active CN117033143B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311288622.4A CN117033143B (en) 2023-10-08 2023-10-08 Intelligent monitoring data transmission system and method based on running state of big data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311288622.4A CN117033143B (en) 2023-10-08 2023-10-08 Intelligent monitoring data transmission system and method based on running state of big data

Publications (2)

Publication Number Publication Date
CN117033143A CN117033143A (en) 2023-11-10
CN117033143B true CN117033143B (en) 2024-01-26

Family

ID=88645181

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311288622.4A Active CN117033143B (en) 2023-10-08 2023-10-08 Intelligent monitoring data transmission system and method based on running state of big data

Country Status (1)

Country Link
CN (1) CN117033143B (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1526106A (en) * 2001-03-26 2004-09-01 Method and apparatus for intelligent data assimilation
WO2020198794A1 (en) * 2019-04-03 2020-10-08 Octavius Partners Pty Limited Process monitoring system
CN115081184A (en) * 2022-05-16 2022-09-20 华南理工大学 Multi-source data fusion dynamic system scenario behavior deduction and reliability prediction analysis method and system
CN115953731A (en) * 2022-12-14 2023-04-11 河南宝佳信息技术有限公司 Intelligent coal flow monitoring data analysis method for improving CNN algorithm model
CN116455930A (en) * 2023-03-21 2023-07-18 中国电子科技集团公司第二十八研究所 Intelligent Internet of things exploring type data analysis focus correlation technology application system
CN116614277A (en) * 2023-05-24 2023-08-18 中国电子科技集团公司第三十研究所 Network security supervision system and method based on machine learning and abnormal behavior analysis

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1526106A (en) * 2001-03-26 2004-09-01 Method and apparatus for intelligent data assimilation
WO2020198794A1 (en) * 2019-04-03 2020-10-08 Octavius Partners Pty Limited Process monitoring system
CN115081184A (en) * 2022-05-16 2022-09-20 华南理工大学 Multi-source data fusion dynamic system scenario behavior deduction and reliability prediction analysis method and system
CN115953731A (en) * 2022-12-14 2023-04-11 河南宝佳信息技术有限公司 Intelligent coal flow monitoring data analysis method for improving CNN algorithm model
CN116455930A (en) * 2023-03-21 2023-07-18 中国电子科技集团公司第二十八研究所 Intelligent Internet of things exploring type data analysis focus correlation technology application system
CN116614277A (en) * 2023-05-24 2023-08-18 中国电子科技集团公司第三十研究所 Network security supervision system and method based on machine learning and abnormal behavior analysis

Also Published As

Publication number Publication date
CN117033143A (en) 2023-11-10

Similar Documents

Publication Publication Date Title
EP1983437A1 (en) Determining of data quality in data streams
CN101110713B (en) Information anastomosing system performance test bed based on wireless sensor network system
US10417599B2 (en) Time and motion data fusion for high fidelity data sets
CN116866095B (en) Industrial router with touch panel and standby control method thereof
CN104731079A (en) Oil field data monitoring system and method
CN116993532B (en) Method and system for improving preparation efficiency of battery parts
CN115640860B (en) Electromechanical equipment remote maintenance method and system for industrial cloud service
CN116823227A (en) Intelligent equipment management system and method based on Internet of things
CN117111519A (en) Intelligent monitoring system and method for coal production safety
CN102354377A (en) Method and device for managing a manufacturing environment using tool operating data
CN117033143B (en) Intelligent monitoring data transmission system and method based on running state of big data
CN115936680A (en) Intelligent order dispatching method and system for equipment operation and maintenance
CN115796906A (en) Software cost estimation system
Lin et al. Reliability evaluation of a manufacturing network with reworking action
CN115327942A (en) Intelligent environment monitoring system
CN115935285A (en) Multi-element time series anomaly detection method and system based on mask map neural network model
WO2013143846A1 (en) Monitoring the progress of a scheduled activity in an industrial process
CN114205355A (en) Method and system for testing performance of auxiliary equipment of power transformation gateway
CN115906534B (en) Self-updating and automatic reverse control oil-gas field digital twin method and system
CN117041302B (en) Operation system and method for multi-equipment collaborative planning
Shiddiqi et al. GA-Sense: Sensor placement strategy for detecting leaks in water distribution networks based on time series flow and genetic algorithm
Talukder et al. Autonomous resource management and control algorithms for distributed wireless sensor networks
CN112929991B (en) Sensor management method, device, equipment and storage medium
CN108804636B (en) Data processing method of composite environmental manufacturing system
CN116306325B (en) Production supply chain monitoring management system and method based on industrial Internet

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant