CN111596629A - Cloud-edge-collaborative industrial data fusion method and security controller - Google Patents
Cloud-edge-collaborative industrial data fusion method and security controller Download PDFInfo
- Publication number
- CN111596629A CN111596629A CN202010490966.3A CN202010490966A CN111596629A CN 111596629 A CN111596629 A CN 111596629A CN 202010490966 A CN202010490966 A CN 202010490966A CN 111596629 A CN111596629 A CN 111596629A
- Authority
- CN
- China
- Prior art keywords
- data
- cloud
- module
- edge
- industrial
- 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.)
- Granted
Links
- 238000007500 overflow downdraw method Methods 0.000 title claims abstract description 17
- 238000012545 processing Methods 0.000 claims abstract description 41
- 238000004364 calculation method Methods 0.000 claims abstract description 36
- 238000000034 method Methods 0.000 claims abstract description 24
- 238000004891 communication Methods 0.000 claims abstract description 18
- 238000003745 diagnosis Methods 0.000 claims abstract description 11
- 230000002159 abnormal effect Effects 0.000 claims description 28
- 238000011156 evaluation Methods 0.000 claims description 22
- 230000004927 fusion Effects 0.000 claims description 22
- 230000007613 environmental effect Effects 0.000 claims description 12
- 238000001914 filtration Methods 0.000 claims description 10
- 238000003860 storage Methods 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 8
- 230000007123 defense Effects 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000007689 inspection Methods 0.000 claims description 3
- 238000011084 recovery Methods 0.000 claims description 3
- 230000004044 response Effects 0.000 claims description 3
- 238000013461 design Methods 0.000 abstract description 4
- 230000036039 immunity Effects 0.000 abstract description 2
- 230000006855 networking Effects 0.000 abstract description 2
- 230000000875 corresponding effect Effects 0.000 description 16
- 230000005540 biological transmission Effects 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000013499 data model Methods 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000013021 overheating Methods 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 239000003245 coal Substances 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
-
- 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]
- G05B19/4183—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 data acquisition, e.g. workpiece identification
-
- 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]
- G05B19/41845—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 system universality, reconfigurability, modularity
-
- 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
- G05B19/41855—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 by local area network [LAN], network structure
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/41885—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by modeling, simulation of the manufacturing system
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Manufacturing & Machinery (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Quality & Reliability (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
A cloud-edge collaborative industrial data fusion method comprises the following steps: the method for fusing the industrial data by utilizing the cloud-edge collaborative architecture comprises the following steps: the system comprises a data acquisition layer, a control layer and a cloud platform layer. The invention changes the traditional 'cloud-end' mode into the 'cloud-edge-end' mode, thereby reducing the cloud computing pressure and the problem of broadband congestion. The safety controller abandons the original data processing unit and replaces the original data processing unit with an edge computing module with stronger function, so that the whole safety controller has strong data processing capacity; an active immunity and fault diagnosis unit is added in the edge calculation module, so that the safety performance of the whole safety controller is improved; the whole safety controller adopts an industrial Ethernet module to carry out data communication media, so that networking is more convenient and faster; the safety controller is used as an operation carrier of the data fusion method, adopts a modular design, is easy to transplant and update, and has flexible use experience for users.
Description
Technical Field
The invention discloses a cloud-edge collaborative industrial data fusion method and a safety controller, and belongs to the technical field of edge computing and intelligent control.
Background
In industrial production, data is generated at all times. The rotating speed and energy consumption of a production machine tool, the temperature and humidity of food processing, the combustion and coal consumption of a thermal generator set, equipment data of an automobile, the position and speed of a logistics fleet and the like are data in the production process.
The collection and transmission of industrial data are basically in an end-tube-cloud mode. In the application field, the 'end' is responsible for collecting data and executing instructions, the 'pipe' is responsible for opening up a transmission path of the data, and the 'cloud' is responsible for all data analysis and control logic functions. The whole process can be successfully communicated, and the data acquisition, analysis and application capabilities are very important.
However, with the development of the internet of things, the amount of data generated by industrial manufacturing equipment will be more and more. If all the data are put in the cloud for processing, infinite spectrum resources, transmission bandwidth and data processing capacity are needed, and the cloud is inevitably burdened.
In a plurality of key problem researches on high-efficiency processing of big data under cloud computing published in Jilin university in Chinese document 2018, targeted preprocessing of data before data analysis is proposed for the problem of high-efficiency processing of big data, but the method is still carried out in the cloud and still occupies cloud resources; the form of interconnection and intercommunication of a plurality of data centers is cloud computing burden reduction, all software and hardware resources are still regarded as uniform resources for management and scheduling, and the centralized cloud cannot meet the resource requirements of large connection, low time delay and large bandwidth on the terminal side. Therefore, edge computing is required to share the pressure of cloud computing. In the aspect of data processing and application, data fusion needs to be carried out on the industrial data at the edge side because the data of the industrial field faces the problems that the 'freshness date' is short and a large amount of 'garbage' data does not need to be transmitted to the cloud.
Although the idea of 'cloud edge collaboration' is more researchers in the industry at the hot stage of application, there are no mature and standard processing schemes, and there are no explicit documents describing the specific implementation scheme especially for the industrial big data.
Disclosure of Invention
The invention provides a cloud-edge cooperative industrial data fusion method aiming at the characteristics of large industrial data amount, multiple data types, high commercial value, high processing speed, high accuracy requirement and strong real-time property.
The data fusion method provided by the invention is based on JDL data model architecture, the JDL is a data fusion model provided from the military application perspective, and comprises 5 layers: level zero, preprocessing the data to correct the deviation, and aligning in space and time; level one, correlating data to obtain the location or attributes of the target, the results that can be obtained at this level include target discrimination (classification and recognition) and target tracking (state and orientation of the target); level two, carrying out correlation analysis on the object or event and estimating the context of the object or event in the working environment, wherein the evaluation is mainly carried out on the importance of the target in a specific environment; level three, predicting the current situation to predict the event and estimate the threat intention, namely further evaluating the target of level two, such as the threat level; and level four, evaluating the ongoing fusion process and providing suggestions for the user, such as the priority of tasks and the allocation of available resources. The invention specifically expounds a JDL model-based data fusion method by utilizing a cloud-side cooperative architecture and combining the characteristics of industrial data, and solves the problems that invalid industrial big data occupies cloud-side spectrum resources, broadband and processing capacity; and a distributed lightweight edge calculation acquisition mode is introduced, so that communication and calculation overhead is saved for edge calculation at the side of the safety controller.
The invention also discloses a safety controller based on the industrial data fusion.
The technical scheme of the invention is as follows:
a cloud-edge collaborative industrial data fusion method is characterized by comprising the following steps: the method for fusing the industrial data by utilizing the cloud-edge collaborative architecture comprises the following steps: the system comprises a data acquisition layer, a control layer and a cloud platform layer;
the data acquisition layer adopts a distributed architecture, and an acquisition node in an industrial scene is provided with a sensor for acquiring original industrial data; for the requirement of later data modeling, adding lightweight edge calculation on each acquisition node for filtering environmental noise in original industrial data or abnormal data caused by the environmental noise, and then sending the filtered data to a control layer in a wired or wireless mode; the reasons for this design are: firstly, eliminating environmental noise of original industrial data, wherein the acquired data contains a large amount of environmental noise due to severe industrial field environment, and a plurality of abnormal data conditions occur, and common filtering methods comprise an amplitude limiting filtering method, a median filtering method, an arithmetic mean filtering method and the like; secondly, a distributed lightweight edge calculation acquisition mode is introduced, so that communication and calculation overhead is saved for edge calculation at the side of the safety controller; the lightweight edge calculation means that the edge calculation capability is weak, and the edge calculation method is only suitable for performing simple operations such as logic operation, arithmetic operation and sequencing on data, but cannot perform advanced operation functions such as data storage, data modeling and matrix on the data;
the control layer comprises an edge computing module which is additionally arranged on the safety controller, a JDL-based data fusion model which is suitable for industrial data is embedded in the edge computing module and used for extracting data characteristics uploaded to data of the control layer, the data fusion model simplifies the steps of the JDL original model, and each layer of the data model is subjected to division and cooperation by virtue of a cloud platform, so that the working efficiency is improved, and the control layer is easy to understand and convenient to operate for a user;
the cloud platform layer is used for building a data fusion model data feature library and an event evaluation scheme; the data characteristic library is used for storing the extracted data characteristics and taking the event evaluation as a data basis; the event evaluation scheme is characterized in that corresponding event prejudgment is carried out on extracted data characteristics according to professional knowledge and experience and based on the data characteristic library, wherein the corresponding events refer to processing means for dealing with abnormal conditions in an industrial scene, therefore, for different industrial scenes or industrial equipment, the processing means for dealing with the abnormal conditions are different when the data are abnormal.
Preferably, in the event evaluation scenario, the expertise and experience are determined by a "smart contract":
different abnormal data correspond to different operating conditions;
different running conditions correspond to different trigger events, and the trigger events are pre-judged for the corresponding events.
According to the invention, when the same abnormal data corresponds to multiple trigger events, the execution is performed in sequence according to the priority order of the events.
According to a preferred embodiment of the present invention, the JDL-based data fusion model suitable for industrial data specifically includes:
s0) the data acquisition layer calculates the original industrial data of the acquisition nodes by using the lightweight edges:
preprocessing the acquired analog quantity data to filter out burr values generated due to environmental noise, and uploading the processed data to a control layer;
directly uploading the collected switching value signals to a control layer;
preferably, the preprocessing method is an amplitude limiting filtering method, and because the abnormal data of the industrial data affected by noise has more burrs, the burrs can be easily filtered out by adopting simple amplitude limiting, the calculation amount of the method is extremely small, and the processing efficiency is improved;
s1) registering, correlating and estimating the uploaded analog quantity data by using an edge calculation module of the control layer to obtain data characteristics, and feeding the data characteristics back to the cloud platform layer;
after time alignment processing is carried out on the switching value signals, the switching value signals are directly verified and then transferred to a control layer for control execution;
s2) calling a data feature library by the cloud platform for comparison:
if the extracted data features exist in the cloud platform, directly performing step S3);
if the extracted data features are not in the cloud platform feature library, updating the cloud platform data feature library, constructing a new event evaluation scheme, and then performing step S3);
s3) the cloud platform directly calls the latest corresponding event evaluation scheme according to the extracted data characteristics, and feeds back the event result, namely the decision, processed according to the event evaluation scheme to the control layer;
s4) the control layer executes control immediately upon receiving the decision of the cloud platform.
A safety controller based on industrial data fusion, comprising: the device comprises a data acquisition module, an edge calculation module, an Ethernet communication module and a safety control module;
the data acquisition module comprises: the system comprises a local IO acquisition unit and an intelligent storage unit;
the local IO acquisition unit is used for: receiving a locally read switching value;
the intelligent storage unit is used for: the uploaded data are classified and stored for the edge computing module to call, and meanwhile, data related to safety and privacy in industry are stored locally;
the edge calculation module includes: the system comprises a data processing unit, an active immune unit and a fault diagnosis unit;
the data processing unit is embedded with the JDL-based data fusion model suitable for industrial data and is used for processing data of the data acquisition and storage module;
the active immune unit utilizes the stored relevant data for analysis:
the active depth defense is realized, that is, key information and key marks are preset in an active immune unit to serve as defense conditions, and once threat information exists outside and enters an edge calculation module, the threat information is actively deleted;
the early warning interruption in the process is realized, namely, if the active immune unit analyzes the threat situation, an alarm is given out, and the system operation is interrupted;
and realizing the recovery of the after-the-fact response: the safety controller is preset with a backup system, and the backup system is immediately awakened at any time and is handed to continue to execute so as to reduce loss;
the fault diagnosis unit detects and alarms data abnormity, sound abnormity, display abnormity and motor abnormity on the edge side; the data abnormity comprises an alarm of an abnormal result of the processing unit and a judgment alarm of failure of inspection of the switching value data acquired by the acquisition layer; the sound abnormity, the display abnormity and the motor abnormity refer to that when the field data of the equipment is abnormal, the diagnosis module gives an alarm in time according to the abnormal information;
the Ethernet communication module is used for data communication among the edge computing module, the safety control module, the data acquisition module and the cloud platform;
and the safety control module is used for analyzing the control instruction signals sent by the edge computing module, the cloud platform and the data acquisition module through the Ethernet communication module and carrying out corresponding control actions.
The technical advantages of the invention are as follows:
1. the invention changes the traditional 'cloud-end' mode into the 'cloud-edge-end' mode, thereby reducing the cloud computing pressure and the problem of broadband congestion.
2. Aiming at the problems of severe industrial field environment, large influence of noise on data and more abnormal points of the data, the invention provides the acquisition layer with a distributed architecture, adds light-weight edge calculation on the acquisition nodes of the acquisition layer, has small function and large use, saves communication cost, saves calculation cost for the edge calculation side of the control layer, and plays a vital role in data modeling in the edge calculation module of the control layer.
3. The invention carries out overall classification aiming at industrial process data, and carries out different modes of operation processing on the switching value and the analog value respectively at the acquisition layer and the control layer, thereby improving the operation efficiency and increasing the real-time property under the condition of ensuring the accuracy.
4. The invention divides the whole data fusion model and the fusion method into five steps, and simultaneously distributes the data fusion model and the fusion method in different levels:
step S0) at the acquisition layer, step S1), step S4) at the control layer, step S2) and step S3) at the cloud platform layer, time sharing and labor division are carried out, cloud edge cooperation is carried out, and application efficiency of the whole data model is improved.
5. The processes of supplementing and optimizing the feature library and creating the prediction model in the step S3) of the invention further improve the precision of data fusion and the decision validity.
6. The safety controller abandons the original data processing unit and replaces the original data processing unit by the edge calculation module with stronger function, so that the whole safety controller has strong data processing capacity; an active immunity and fault diagnosis unit is added in the edge calculation module, so that the safety performance of the whole safety controller is improved; the whole safety controller adopts an industrial Ethernet module to carry out data communication media, so that networking is more convenient and faster; the safety controller is used as an operation carrier of the data fusion method, adopts a modular design, is easy to transplant and update, and has flexible use experience for users.
Drawings
FIG. 1 is a cloud-edge collaboration architecture diagram according to the present invention;
fig. 2 is a block diagram of the design of the safety controller of the present invention.
Detailed Description
The invention is described in detail below with reference to the following examples and the accompanying drawings of the specification, but is not limited thereto.
Examples 1,
A cloud-edge collaborative industrial data fusion method comprises the following steps: the method for fusing the industrial data by utilizing the cloud-edge collaborative architecture comprises the following steps: the system comprises a data acquisition layer, a control layer and a cloud platform layer;
the data acquisition layer adopts a distributed architecture to install a sensor on an acquisition node in an industrial scene for acquiring original industrial data; for the requirement of later data modeling, adding lightweight edge calculation on each acquisition node for filtering environmental noise in original industrial data or abnormal data caused by the environmental noise, and then sending the filtered data to a control layer in a wired or wireless mode;
the control layer comprises an edge calculation module which is additionally arranged on the safety controller, wherein a JDL-based data fusion model which is suitable for industrial data is embedded in the edge calculation module and is used for extracting data characteristics uploaded to the data of the control layer;
the cloud platform layer is used for building a data fusion model data feature library and an event evaluation scheme; the data characteristic library is used for storing the extracted data characteristics and taking the event evaluation as a data basis; the event evaluation scheme is characterized in that corresponding event prejudgment is carried out on extracted data characteristics according to professional knowledge and experience and based on the data characteristic library, wherein the corresponding events refer to processing means for dealing with abnormal conditions in an industrial scene, therefore, for different industrial scenes or industrial equipment, the processing means for dealing with the abnormal conditions are different when the data are abnormal.
In the event evaluation scenario, the expertise and experience are determined by "smart contracts":
different abnormal data correspond to different operating conditions;
different running conditions correspond to different trigger events, and the trigger events are pre-judged for the corresponding events.
And when the same abnormal data corresponds to various trigger events, sequentially executing the events according to the priority order of the events. For example, data characteristics of overheating at multiple positions around a certain motor of the machine tool are collected and extracted, whether the fan needs to be started or the machine needs to be stopped emergently is judged according to the comprehensive judgment, and the process is pre-judged in an intelligent contract mode: and if the priority sequence of the corresponding events is carried out, for example, the events are judged to be a fan starting event and a fan stopping event, wherein the priority of the fan stopping event is higher than that of the fan starting event, the fan stopping event is preferentially executed.
The JDL-based data fusion model applicable to industrial data specifically comprises:
s0) the data acquisition layer calculates the original industrial data of the acquisition nodes by using the lightweight edges:
preprocessing the acquired analog quantity data to filter out burr values generated due to environmental noise, and uploading the processed data to a control layer;
directly uploading the collected switching value signals to a control layer;
the preprocessing method is an amplitude limiting filtering method, and because the abnormal data of the industrial data affected by noise has more burrs, the burrs can be easily filtered by adopting simple amplitude limiting, the calculated amount of the method is extremely small, and the processing efficiency is improved;
s1) registering, correlating and estimating the uploaded analog quantity data by using an edge calculation module of the control layer to obtain data characteristics, and feeding the data characteristics back to the cloud platform layer;
the registration refers to: unifying analog quantity data into the same reference time and space;
the association means: comparing the flight paths from different sensors with the measurement data by using a certain measurement scale to determine candidate pairs for relevant processing, wherein the step is a conventional technology for a person skilled in the art and can carry out pairing according to conditions such as various scenes or data attributes;
the correlation means that: processing the correlated flight path and report to determine whether the flight path and the report belong to the same target, wherein the target is as follows: processing event attributes corresponding to the associated data, for example, data characteristics of overheating at multiple positions around a certain motor of the machine tool are collected and extracted, wherein temperature data collected by multiple temperature sensors are data characteristics, wherein some temperature data are higher than normal working temperature but do not exceed a safety threshold value, a fan starting event is corresponding, and the temperature data and the fan starting event belong to the same target, namely the working temperature of the motor is reduced to the normal working temperature; if some temperature data exceed the safety threshold value, a shutdown event is corresponding to the temperature data, and the temperature data and the shutdown event belong to the same target, namely, the motor is forcibly shut down and cooled;
the estimation refers to: updating the state variable and the estimation error variance of the target according to the data result after the relevant processing, so as to realize the prediction of the target;
the data fed back to the cloud platform are characterized by being in a coding form, and can include but not limited to "motor 1 temperature X1", "motor 2 temperature X2", "machine tool 1 bearing 1 overrun limit X1", "machine tool 1 bearing 2 overrun limit X2", and the like, and the names are coded to improve the transmission efficiency;
after time alignment processing is carried out on the switching value signals, the switching value signals are directly verified and then transferred to a control layer for control execution; the check is to compare the switching value data transmitted by different acquisition nodes of the same variable: if the two values are the same, the two values are valid, and if the two values are different, the two values are discarded, and the purpose of verification is to increase the safety performance of the safety controller and prevent misoperation caused by environmental interference;
s2) calling a data feature library by the cloud platform for comparison:
if the extracted data features exist in the cloud platform, directly performing step S3);
if the extracted data features are not in the cloud platform feature library, updating the cloud platform data feature library, constructing a new event evaluation scheme, and then performing step S3);
s3) the cloud platform directly calls the latest corresponding event evaluation scheme according to the extracted data characteristics, and feeds back the event result, namely the decision, processed according to the event evaluation scheme to the control layer;
s4) the control layer executes control immediately upon receiving the decision of the cloud platform.
Examples 2,
A safety controller based on industrial data fusion, comprising: the device comprises a data acquisition module, an edge calculation module, an Ethernet communication module and a safety control module;
the data acquisition module comprises: the system comprises a local IO acquisition unit and an intelligent storage unit;
the local IO acquisition unit is used for: receiving locally read switching values, such as a soft start instruction (corresponding to a mechanical instruction), a soft emergency stop instruction (corresponding to a mechanical emergency stop), a steering instruction and the like;
the intelligent storage unit is used for: the uploaded data are classified and stored for the edge computing module to call, and meanwhile, data related to safety and privacy in industry are stored locally;
the edge calculation module includes: the system comprises a data processing unit, an active immune unit and a fault diagnosis unit;
the data processing unit is embedded with the JDL-based data fusion model suitable for industrial data and is used for processing data of the data acquisition and storage module;
the active immune unit utilizes the stored relevant data for analysis:
the active depth defense is realized, that is, key information and key marks are preset in an active immune unit to serve as defense conditions, and once threat information exists outside and enters an edge calculation module, the threat information is actively deleted;
the early warning interruption in the process is realized, namely, if the active immune unit analyzes the threat situation, an alarm is given out, and the system operation is interrupted;
and realizing the recovery of the after-the-fact response: the safety controller is preset with a backup system, and the backup system is immediately awakened at any time and is handed to continue to execute so as to reduce loss;
the fault diagnosis unit detects and alarms data abnormity, sound abnormity, display abnormity and motor abnormity on the edge side; the data abnormity comprises an alarm of an abnormal result of the processing unit and a judgment alarm of failure of inspection of the switching value data acquired by the acquisition layer; the sound abnormity, the display abnormity and the motor abnormity refer to that when the field data of the equipment is abnormal, the diagnosis module gives an alarm in time according to the abnormal information;
the ethernet communication module is used for data communication between the edge computing module, the security control module, the data acquisition module and the cloud platform, and is generally used between the data acquisition module and the security control module, between the edge computing module and the cloud platform, and between the cloud platform and the security control module.
The safety control module is used for analyzing control instruction signals sent by the edge computing module, the cloud platform and the data acquisition module through the Ethernet communication module and carrying out corresponding control actions, and comprises a main control module and an input/output submodule, wherein industrial Ethernet communication is adopted between the main control module and the input/output submodule.
Claims (5)
1. A cloud-edge collaborative industrial data fusion method is characterized by comprising the following steps: the method for fusing the industrial data by utilizing the cloud-edge collaborative architecture comprises the following steps: the system comprises a data acquisition layer, a control layer and a cloud platform layer;
the data acquisition layer adopts a distributed architecture to install sensors on acquisition nodes in an industrial scene for acquiring original industrial data, adds light-weight edge calculation on each acquisition node for filtering environmental noise in the original industrial data or abnormal data caused by the environmental noise, and then sends the filtered data to a control layer in a wired or wireless mode;
the control layer comprises an edge calculation module which is additionally arranged on the safety controller, wherein a JDL-based data fusion model which is suitable for industrial data is embedded in the edge calculation module and is used for extracting data characteristics uploaded to the data of the control layer;
the cloud platform layer is used for building a data fusion model data feature library and an event evaluation scheme; the data characteristic library is used for storing the extracted data characteristics and taking the event evaluation as a data basis; the event evaluation scheme is to pre-judge the corresponding event according to the extracted data characteristics based on the data characteristic library according to professional knowledge and experience.
2. The cloud-edge collaborative industrial data fusion method according to claim 1, wherein the expertise and experience in the event evaluation scenario are determined by "smart contracts":
different abnormal data correspond to different operating conditions;
different running conditions correspond to different trigger events, and the trigger events are pre-judged for the corresponding events.
3. The cloud-edge collaborative industrial data fusion method according to claim 2, characterized in that when the same abnormal data corresponds to a plurality of trigger events, the execution is performed in sequence according to the priority order of the events.
4. The cloud-edge collaborative industrial data fusion method according to claim 1, wherein the JDL-based data fusion model applicable to industrial data specifically includes:
s0) the data acquisition layer calculates the original industrial data of the acquisition nodes by using the lightweight edges:
preprocessing the acquired analog quantity data to filter out burr values generated due to environmental noise, and uploading the processed data to a control layer;
directly uploading the collected switching value signals to a control layer;
preferably, the preprocessing method is a limiting filtering method;
s1) registering, correlating and estimating the uploaded analog quantity data by using an edge calculation module of the control layer to obtain data characteristics, and feeding the data characteristics back to the cloud platform layer;
after time alignment processing is carried out on the switching value signals, the switching value signals are directly verified and then transferred to a control layer for control execution;
s2) calling a data feature library by the cloud platform for comparison:
if the extracted data features exist in the cloud platform, directly performing step S3);
if the extracted data features are not in the cloud platform feature library, updating the cloud platform data feature library, constructing a new event evaluation scheme, and then performing step S3);
s3) the cloud platform directly calls the latest corresponding event evaluation scheme according to the extracted data characteristics, and feeds back the event result, namely the decision, processed according to the event evaluation scheme to the control layer;
s4) the control layer executes control immediately upon receiving the decision of the cloud platform.
5. A safety controller based on industrial data fusion, comprising: the device comprises a data acquisition module, an edge calculation module, an Ethernet communication module and a safety control module;
the data acquisition module comprises: the system comprises a local IO acquisition unit and an intelligent storage unit;
the local IO acquisition unit is used for: receiving a locally read switching value;
the intelligent storage unit is used for: the uploaded data are classified and stored for the edge computing module to call, and meanwhile, data related to safety and privacy in industry are stored locally;
the edge calculation module includes: the system comprises a data processing unit, an active immune unit and a fault diagnosis unit;
the data processing unit is embedded with the JDL-based data fusion model suitable for industrial data and is used for processing data of the data acquisition and storage module;
the active immune unit utilizes the stored relevant data for analysis:
the active depth defense is realized, that is, key information and key marks are preset in an active immune unit to serve as defense conditions, and once threat information exists outside and enters an edge calculation module, the threat information is actively deleted;
the early warning interruption in the process is realized, namely, if the active immune unit analyzes the threat situation, an alarm is given out, and the system operation is interrupted;
and realizing the recovery of the after-the-fact response: the method includes that a backup system is preset in a safety controller, and the backup system is immediately awakened at any time and is handed to continue to execute;
the fault diagnosis unit detects and alarms data abnormity, sound abnormity, display abnormity and motor abnormity on the edge side; the data abnormity comprises an alarm of an abnormal result of the processing unit and a judgment alarm of failure of inspection of the switching value data acquired by the acquisition layer; the sound abnormity, the display abnormity and the motor abnormity refer to that when the field data of the equipment is abnormal, the diagnosis module gives an alarm in time according to the abnormal information;
the Ethernet communication module is used for data communication among the edge computing module, the safety control module, the data acquisition module and the cloud platform;
and the safety control module is used for analyzing the control instruction signals sent by the edge computing module, the cloud platform and the data acquisition module through the Ethernet communication module and carrying out corresponding control actions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010490966.3A CN111596629B (en) | 2020-06-02 | 2020-06-02 | Cloud-edge-collaborative industrial data fusion method and security controller |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010490966.3A CN111596629B (en) | 2020-06-02 | 2020-06-02 | Cloud-edge-collaborative industrial data fusion method and security controller |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111596629A true CN111596629A (en) | 2020-08-28 |
| CN111596629B CN111596629B (en) | 2021-08-03 |
Family
ID=72185843
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010490966.3A Active CN111596629B (en) | 2020-06-02 | 2020-06-02 | Cloud-edge-collaborative industrial data fusion method and security controller |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111596629B (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112118303A (en) * | 2020-09-08 | 2020-12-22 | 湖南建工集团有限公司 | Edge computing Internet of things middleware for multiple communication protocols |
| CN112257807A (en) * | 2020-11-02 | 2021-01-22 | 曲阜师范大学 | Dimension reduction method and system based on self-adaptive optimization linear neighborhood set selection |
| CN112738179A (en) * | 2020-12-23 | 2021-04-30 | 万申科技股份有限公司 | Edge calculation control equipment based on heterogeneous network |
| CN112988392A (en) * | 2021-04-09 | 2021-06-18 | 江苏安岚特智能科技有限公司 | Intelligent lamp pole data analysis method based on edge lightweight computing |
| CN113655764A (en) * | 2021-08-16 | 2021-11-16 | 珠海格力电器股份有限公司 | Cloud edge cooperative control system and control method |
| CN113867285A (en) * | 2021-09-24 | 2021-12-31 | 大唐互联科技(武汉)有限公司 | Edge cloud platform-based edge side equipment fault diagnosis method and system |
| CN113887749A (en) * | 2021-08-23 | 2022-01-04 | 国网江苏省电力有限公司信息通信分公司 | Cloud edge cooperation-based multi-dimensional monitoring and disposal method, device and platform for power internet of things |
| CN114253242A (en) * | 2021-12-21 | 2022-03-29 | 上海纽酷信息科技有限公司 | VPN-based Internet of things cloud equipment data acquisition system |
| CN114466029A (en) * | 2022-03-10 | 2022-05-10 | 浪潮云信息技术股份公司 | Cloud edge coordination system and method in edge cloud computing scene |
| WO2022111444A1 (en) * | 2020-11-25 | 2022-06-02 | 摩赛恩科技(苏州)有限公司 | Mass spectrum data processing system and method |
| CN114844724A (en) * | 2022-06-28 | 2022-08-02 | 杭州安恒信息技术股份有限公司 | Port anomaly detection method, device, equipment and medium based on end cloud linkage |
| CN116224879A (en) * | 2023-03-22 | 2023-06-06 | 佛山市众合科技有限公司 | Industrial data processing system based on cloud computing |
| CN117251825A (en) * | 2023-11-20 | 2023-12-19 | 浙江大学 | Multi-sensor data fusion platform for new energy power station |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3156944A1 (en) * | 2015-10-16 | 2017-04-19 | Thomson Licensing | Scene labeling of rgb-d data with interactive option |
| CN108011948A (en) * | 2017-11-30 | 2018-05-08 | 成都航天科工大数据研究院有限公司 | A kind of industrial equipment integrated monitoring system based on edge calculations |
| WO2018213108A1 (en) * | 2017-05-15 | 2018-11-22 | Siemens Aktiengesellschaft | Domain adaptation and fusion using weakly supervised target irrelevant data |
| CN109118732A (en) * | 2018-08-27 | 2019-01-01 | 中国科学院上海微***与信息技术研究所 | Sensor perception event judgement and alarm system and method based on marginal information |
| CN109933004A (en) * | 2019-03-27 | 2019-06-25 | 苏芯物联技术(南京)有限公司 | The machine failure diagnosis and prediction method and system cooperateed with based on edge calculations and cloud |
| CN109947079A (en) * | 2019-03-20 | 2019-06-28 | 阿里巴巴集团控股有限公司 | Region method for detecting abnormality and edge calculations equipment based on edge calculations |
| CN110336703A (en) * | 2019-07-12 | 2019-10-15 | 河海大学常州校区 | Industrial big data based on edge calculations monitors system |
| CN110719210A (en) * | 2019-12-05 | 2020-01-21 | 赣江新区智慧物联研究院有限公司 | Industrial equipment predictive maintenance method based on cloud edge cooperation |
-
2020
- 2020-06-02 CN CN202010490966.3A patent/CN111596629B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3156944A1 (en) * | 2015-10-16 | 2017-04-19 | Thomson Licensing | Scene labeling of rgb-d data with interactive option |
| WO2018213108A1 (en) * | 2017-05-15 | 2018-11-22 | Siemens Aktiengesellschaft | Domain adaptation and fusion using weakly supervised target irrelevant data |
| CN108011948A (en) * | 2017-11-30 | 2018-05-08 | 成都航天科工大数据研究院有限公司 | A kind of industrial equipment integrated monitoring system based on edge calculations |
| CN109118732A (en) * | 2018-08-27 | 2019-01-01 | 中国科学院上海微***与信息技术研究所 | Sensor perception event judgement and alarm system and method based on marginal information |
| CN109947079A (en) * | 2019-03-20 | 2019-06-28 | 阿里巴巴集团控股有限公司 | Region method for detecting abnormality and edge calculations equipment based on edge calculations |
| CN109933004A (en) * | 2019-03-27 | 2019-06-25 | 苏芯物联技术(南京)有限公司 | The machine failure diagnosis and prediction method and system cooperateed with based on edge calculations and cloud |
| CN110336703A (en) * | 2019-07-12 | 2019-10-15 | 河海大学常州校区 | Industrial big data based on edge calculations monitors system |
| CN110719210A (en) * | 2019-12-05 | 2020-01-21 | 赣江新区智慧物联研究院有限公司 | Industrial equipment predictive maintenance method based on cloud edge cooperation |
Non-Patent Citations (1)
| Title |
|---|
| 黄智国 等: ""一种云边协同的工业应用云化方案"", 《电信科学》 * |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112118303A (en) * | 2020-09-08 | 2020-12-22 | 湖南建工集团有限公司 | Edge computing Internet of things middleware for multiple communication protocols |
| CN112257807A (en) * | 2020-11-02 | 2021-01-22 | 曲阜师范大学 | Dimension reduction method and system based on self-adaptive optimization linear neighborhood set selection |
| CN112257807B (en) * | 2020-11-02 | 2022-05-27 | 曲阜师范大学 | Dimension reduction method and system based on self-adaptive optimization linear neighborhood set selection |
| WO2022111444A1 (en) * | 2020-11-25 | 2022-06-02 | 摩赛恩科技(苏州)有限公司 | Mass spectrum data processing system and method |
| CN112738179A (en) * | 2020-12-23 | 2021-04-30 | 万申科技股份有限公司 | Edge calculation control equipment based on heterogeneous network |
| CN112988392A (en) * | 2021-04-09 | 2021-06-18 | 江苏安岚特智能科技有限公司 | Intelligent lamp pole data analysis method based on edge lightweight computing |
| CN113655764A (en) * | 2021-08-16 | 2021-11-16 | 珠海格力电器股份有限公司 | Cloud edge cooperative control system and control method |
| CN113887749A (en) * | 2021-08-23 | 2022-01-04 | 国网江苏省电力有限公司信息通信分公司 | Cloud edge cooperation-based multi-dimensional monitoring and disposal method, device and platform for power internet of things |
| CN113867285A (en) * | 2021-09-24 | 2021-12-31 | 大唐互联科技(武汉)有限公司 | Edge cloud platform-based edge side equipment fault diagnosis method and system |
| CN113867285B (en) * | 2021-09-24 | 2024-06-04 | 大唐互联科技(武汉)有限公司 | Edge cloud platform-based edge side equipment fault diagnosis method and system |
| CN114253242B (en) * | 2021-12-21 | 2023-12-26 | 上海纽酷信息科技有限公司 | VPN-based cloud equipment data acquisition system for Internet of things |
| CN114253242A (en) * | 2021-12-21 | 2022-03-29 | 上海纽酷信息科技有限公司 | VPN-based Internet of things cloud equipment data acquisition system |
| CN114466029A (en) * | 2022-03-10 | 2022-05-10 | 浪潮云信息技术股份公司 | Cloud edge coordination system and method in edge cloud computing scene |
| CN114844724A (en) * | 2022-06-28 | 2022-08-02 | 杭州安恒信息技术股份有限公司 | Port anomaly detection method, device, equipment and medium based on end cloud linkage |
| CN116224879A (en) * | 2023-03-22 | 2023-06-06 | 佛山市众合科技有限公司 | Industrial data processing system based on cloud computing |
| CN117251825A (en) * | 2023-11-20 | 2023-12-19 | 浙江大学 | Multi-sensor data fusion platform for new energy power station |
| CN117251825B (en) * | 2023-11-20 | 2024-02-09 | 浙江大学 | Multi-sensor data fusion platform for new energy power station |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111596629B (en) | 2021-08-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111596629B (en) | Cloud-edge-collaborative industrial data fusion method and security controller | |
| Hafeez et al. | Edge intelligence for data handling and predictive maintenance in IIOT | |
| KR101814108B1 (en) | Remote server | |
| CN114715139A (en) | Automatic parking abnormal data acquisition method and device, storage medium and product | |
| Kim et al. | Server-Edge dualized closed-loop data analytics system for cyber-physical system application | |
| CN115098278B (en) | Digital twin workshop multi-scene interaction method based on microservice | |
| CN115453356A (en) | Power equipment running state monitoring and analyzing method, system, terminal and medium | |
| CN116248674A (en) | Data transmission method, device and system | |
| CN116520806A (en) | Intelligent fault diagnosis system and method for industrial system | |
| CN117251825B (en) | Multi-sensor data fusion platform for new energy power station | |
| CN111770133B (en) | Multi-body intelligent-connection cloud control platform | |
| JP7348103B2 (en) | Driving state classification system and driving state classification method | |
| CN117092918A (en) | Cloud edge cooperation-based intelligent gas sensing control method | |
| CN111380687A (en) | Industrial motor bearing fault diagnosis method based on multi-local model decision fusion | |
| Zhao et al. | On-board artificial intelligence based on edge computing in optical transport networks | |
| CN116224791A (en) | Collaborative training control method for intelligent manufacturing collaborative robot edge system | |
| Wotawa et al. | On classification and modeling issues in distributed model-based diagnosis | |
| CN115081585B (en) | Man-machine object cooperative abnormal state detection method for reinforced heterographic neural network | |
| JP2013246654A (en) | Log management device, log management method and log management program | |
| Butylin | Predictive maintenance framework for a vehicular iot gateway node using active database rules | |
| CN117217715B (en) | Construction progress monitoring method and system based on engineering electronic map | |
| Aihua | A method for condition evaluation based on DSmT | |
| CN116523429B (en) | Intelligent logistics monitoring system and method based on Internet of things | |
| CN113295963B (en) | Cross-domain cascading failure source node judgment method for CPS system of active power distribution network | |
| Noack et al. | Monitoring mobile cyber-physical systems by means of a knowledge discovery cycle |
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 |