CN109613898A - A kind of enterprise's creation data monitoring method based on industrial Internet of Things - Google Patents
A kind of enterprise's creation data monitoring method based on industrial Internet of Things Download PDFInfo
- Publication number
- CN109613898A CN109613898A CN201811524263.7A CN201811524263A CN109613898A CN 109613898 A CN109613898 A CN 109613898A CN 201811524263 A CN201811524263 A CN 201811524263A CN 109613898 A CN109613898 A CN 109613898A
- Authority
- CN
- China
- Prior art keywords
- data
- enterprise
- creation data
- things
- creation
- 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
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000012544 monitoring process Methods 0.000 title claims abstract description 19
- 238000004519 manufacturing process Methods 0.000 claims abstract description 43
- 230000005540 biological transmission Effects 0.000 claims abstract description 19
- 238000013528 artificial neural network Methods 0.000 claims abstract description 17
- 238000005265 energy consumption Methods 0.000 claims abstract description 17
- 238000007405 data analysis Methods 0.000 claims abstract description 9
- 238000013480 data collection Methods 0.000 claims abstract description 7
- 238000003062 neural network model Methods 0.000 claims description 21
- 238000012549 training Methods 0.000 claims description 10
- 230000015572 biosynthetic process Effects 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 4
- 238000003786 synthesis reaction Methods 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 abstract description 11
- 230000008569 process Effects 0.000 abstract description 4
- 238000012546 transfer Methods 0.000 abstract description 2
- LELOWRISYMNNSU-UHFFFAOYSA-N hydrogen cyanide Chemical compound N#C LELOWRISYMNNSU-UHFFFAOYSA-N 0.000 description 20
- 238000006243 chemical reaction Methods 0.000 description 12
- QGZKDVFQNNGYKY-UHFFFAOYSA-N Ammonia Chemical compound N QGZKDVFQNNGYKY-UHFFFAOYSA-N 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 5
- 229910021529 ammonia Inorganic materials 0.000 description 4
- 238000011161 development Methods 0.000 description 4
- 230000018109 developmental process Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 4
- 238000001311 chemical methods and process Methods 0.000 description 3
- 238000009434 installation Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 230000000638 stimulation Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- XLJMAIOERFSOGZ-UHFFFAOYSA-N cyanic acid Chemical compound OC#N XLJMAIOERFSOGZ-UHFFFAOYSA-N 0.000 description 2
- 230000002401 inhibitory effect Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 239000003345 natural gas Substances 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000004445 quantitative analysis Methods 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 229910052739 hydrogen Inorganic materials 0.000 description 1
- 239000001257 hydrogen Substances 0.000 description 1
- 125000004435 hydrogen atom Chemical class [H]* 0.000 description 1
- 230000003116 impacting effect Effects 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000001558 permutation test Methods 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 230000008929 regeneration Effects 0.000 description 1
- 238000011069 regeneration method Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 238000009966 trimming Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/4183—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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provide one kind can safety-oriented data transfer, and analysis and intuitively enterprise's creation data monitoring method based on industrial Internet of Things for showing are carried out to data, included the following steps, S1 data collection steps.S2 data transmission step, the data transmission step include that creation data is transmitted to server by data encryption step；S3 data analysis step, the data analysis step include that creation data is stored in the database based on mathematical logic and is analyzed according to things logic creation data by middle tier server.S4 data show step.The present invention intuitively shows influence of each data to energy consumption in generating process to administrative staff by way of production energy consumption neural network paraphrase figure, and administrator is facilitated to make production decision, reduces energy consumption.
Description
Technical field
The present invention relates to industrial internet of things field, and in particular to the present invention relates to a kind of, and the enterprise based on industrial Internet of Things is raw
Produce data monitoring method.
Background technique
The enlargement and overall technology equipment of industrial production equipment are constantly promoted in recent years, as low-carbon economy develops
Theory is goed deep into, and requirement of the enterprise to production process Resource regeneration, safety and environmental protection is increasingly urgent to.Meanwhile industrial Internet of Things is fast
Speed development provides strong technical support for the monitoring of enterprise production process.In June, 2017, general office, Ministry of Industry and Information issue
The notice of " about mobile Internet of Things development is pushed forward comprehensively " is mentioned in notice, pushes forward wide covering, big connection, low function comprehensively
Consume mobile Internet of Things construction.Therefore industrial Internet of Things effect is given full play to, is believed domestic the intelligent of existing procedure industry is completed
Breathization manufacturing improvement has great importance.
Many scientific & technical corporation have applied being related to the patent of industrial internet of things data monitoring, but these existing methods, system
Have the following problems:
A. it is developed just for a certain special industry, limitation is larger, is unfavorable for being widely used for system.
B. data transmission is easy to distort and steal creation data without safety guarantee.
C. system function is single, does not adapt to the needs that modern enterprise is energy-saving, and completion informationization makes the transition.
D. cloud platform Cascade System seriously threatens enterprise safety operation in Modern Operations System.
Such as application No. is 201711277580.9, a kind of safety based on power generation control and monitoring data of denomination of invention
Encryption system, major function are the attack and infringement for taking precautions against hacker's machine malicious code etc. to electric power monitoring system, are only used for electricity
The safeguard protection of Force system, limitation is larger, and the Cascade System is in former industry control network, once system is controlled, direct shadow
Ring enterprise safety operation；Application No. is 201810501386.2, denomination of invention industrial platform of internet of things based on cloud, data are used
WIFI module and GPRS module carry out data transmission, and without any encryption measures, have very big safety hidden the creation data of enterprise
Suffer from.Its data application module web-based management backstage, carry out data by way of Android system APP or ioS system APP be in
It is now and interactive, need user installation client that could use, maintenance cost is high, and application scenarios are limited larger by equipment place；Application
Number be 201610757376.6, a kind of internet of things data monitoring processing system of denomination of invention, the system can treat prison in real time
Measurement equipment is monitored, and is triggered alarm unit according to Real-time Monitoring Data processing result and alarmed, and is mainly used for prison
Measurement equipment carries out the alarm of data exception, has a single function the demand for being unable to satisfy IT application in enterprise.
Summary of the invention
To solve the above-mentioned problems, the present invention provide one kind can safety-oriented data transfer, and analysis and straight is carried out to data
The enterprise's creation data monitoring method based on industrial Internet of Things shown is seen, is included the following steps,
S1 data collection steps, the data collection steps include acquiring or the data of industry spot measuring instrument to enterprise
Data acquisition in industry DCS control system；
S2 data transmission step, the data transmission step include that creation data is transmitted to clothes by data encryption step
Business device；
S3 data analysis step, the data analysis step include that creation data is stored in the number based on mathematical logic
Creation data is analyzed according to things logic according to library and by middle tier server.
S4 data show step, the real-time production including showing production equipment to user with graphics data by client
Data, accumulative creation data, produce abnormal alarm data, one of enterprise's production energy consumption data or a variety of.
Further, the data encryption step includes,
Collected creation data is transmitted to industry spot industry control by unidirectional introducing equipment by wire transmission by S21
Machine；
S22 industrial personal computer carries out collected data, and classification is packaged and stores；
S23 industrial personal computer to by classification, be packaged and the creation data of storage, using the system time factor as foundation, by the
One signature algorithm carries out signature and generates packet signature；
S24 server generates sample database signature using the system time factor as foundation, by the first signature algorithm；
Before S25 industrial personal computer sends data packet, packet signature and server end sample database are compared, if label
Name is consistent, then sends data packet.
S26 server is decrypted to obtain creation data to the data packet received.
Further, it is described by middle layer database be based on things logic to creation data carry out analysis include,
S31 constructs multiple neural network models, each neural network model according to the creation data sample after standardization
It is trained using the initial weight of small random number and the training method with momentum term and learning rate.
S32 selects the neural network model with optimum prediction performance in the multiple neural network model, and remembers
Record the initial weight of the lower model and terminate weight, according to terminate weight and connection weight method calculate neural network model C, OI,
RI, comprising the following steps:
S321 calculates input-hidden layer-output connection weight contribution degree C；
S322 calculates the synthesis connection weight contribution degree OI of each variable；
S323 calculates the relative contribution rate RI of each variable；
S33 changes the sequence of training sample output collection at random；
S34 with after change sequence sample and S32 step in the initial weight that records, re -training neural network model,
And the termination weight of record cast；
S33 and S34 step is repeated several times in S35, and to record number of repetition as COUNT, is weighed according to the termination recorded in S34
Weight executes C, OI, RI that S32 step is randomized.
S36 calculates separately input-hidden layer-output connection weight contribution degree C, comprehensive connection weight contribution degree OI, relative contribution rate
The significance degree P of RI, includes the following steps,
If S361 standard value is greater than 0, P=(N+1)/(COUNT+1), N is the number that randomization value is more than or equal to standard value；
If S362 standard value is the number that randomization value is less than or equal to standard value less than 0, P=(M+1)/(COUNT+1), M；
If S37 p is less than default level of signifiance value, retains the connection weight and otherwise reject the connection weight, and generate production energy
Consume neural network paraphrase figure.
Further, the data show that step includes,
Technical staff's permission of different stage is set, and can be checked in data according to the authority setting technical staff
Hold.
Further, the data show that step includes,
The graphics data includes by carrying out year-on-year ring than control, generation pair to the creation data stored in database
The histogram answered, cake chart, curve graph；
Enterprise's production energy consumption data include production energy consumption neural network paraphrase figure.
Further, the client and the server are isolated using B/S framework and with enterprise production information system.
The invention has the advantages that
1 server uses B/S (BrowSer/Server) mode development, client zero installation, zero dimension shield, and system easily expands
Exhibition.
2 Internet of things system are independently of enterprise's data system, and data transmission utilizes integrity verification technology, to original number
It according to signing, and also signs to sample database, the signature by initial data and sample database is needed before data transmission
It is verified, guarantees the safety of enterprise's creation data.
3 servers carry out comprehensive analysis to creation data, and will be analyzed in real time by client as a result, classification is other
It is sent to enterprise engineering technical staff, enterprise security is instructed efficiently to produce.
4 by being arranged different middleware servers for different enterprises, and the application of this system is not limited solely to certain all one's life
Enterprise is produced, different enterprise demands can be directed to, timely update adjustment, is suitble to promote the use of.
5 present invention are intuitively shown in production process by way of production energy consumption neural network paraphrase figure to administrative staff
Influence of each data to energy consumption facilitates administrator to make production decision, reduces energy consumption.
Detailed description of the invention
Fig. 1 is one embodiment of the invention flow chart.
Fig. 2 is neural network paraphrase figure before one embodiment of the invention is trimmed.
Fig. 3 is neural network paraphrase figure after one embodiment of the invention trimming.
Specific embodiment
The present invention solve the problems, such as the invention thinking that is described in background technique first is that, the present invention passes through acquisition production equipment
Data information, by production equipment Data Encryption Transmission to server；Server carries out analysis to enterprise's production big data and will divide
It analyses result to show to user, user is facilitated to make decision-making of production management.Data monitoring system of the present invention, using independently opening
Hair mode, can in the safety for completing to ensure that its data while creation data analysis except enterprise information system
Effectively enterprise security is instructed efficiently to produce.
The present invention as shown in Figure 1 provides a kind of enterprise's creation data monitoring method based on industrial Internet of Things, including following
Step,
S1 data collection steps, the data collection steps include acquiring or the data of industry spot measuring instrument to enterprise
Data acquisition in industry DCS control system；
S2 data transmission step, the data transmission step include that creation data is transmitted to clothes by data encryption step
Business device；
S3 data analysis step, the data analysis step include that creation data is stored in the number based on mathematical logic
Creation data is analyzed according to things logic according to library and by middle tier server.
S4 data show step, the real-time production including showing production equipment to user with graphics data by client
Data, accumulative creation data, produce abnormal alarm data, one of enterprise's production energy consumption data or a variety of.
Data encryption step includes,
Collected creation data is transmitted to industry spot industry control by unidirectional introducing equipment by wire transmission by S21
Machine；
Unidirectional introducing equipment is one kind of the safety equipment of enterprise's DCS control system, it may ensure that in data transmission,
It can only be transmitted from DCS system to outside, prevent external data from having an impact to enterprise's DCS system, cause damages, unidirectional import sets
The standby control information system independently of production equipment, prevents the data exception at Internet of Things end from impacting to Modern Operations System,
Further increase security of system.
S22 industrial personal computer carries out collected data, and classification is packaged and stores；
S23 industrial personal computer to by classification, be packaged and the creation data of storage, using the system time factor as foundation, by the
One signature algorithm carries out signature and generates packet signature；
S24 server generates sample database signature using the system time factor as foundation, by the first signature algorithm；
Before S25 industrial personal computer sends data packet, packet signature and server end sample database are compared, if label
Name is consistent, then sends data packet.
S26 server is decrypted to obtain creation data to the data packet received.
The above-mentioned dynamic encryption technology based on time synchronization signs to initial data using integrity verification technology,
And also sign to sample database, it needs to carry out the signature of initial data and sample database to verify before data transmission logical
It crosses, ensure that the safety of data transmission procedure.
Carrying out analysis to creation data based on things logic by middle layer database includes,
Things logic refers to creation data logic corresponding with production process in production process, such as chemical industry process of factory production
In, the logic of different creation datas is corresponded in chemical reaction process different step from raw material to product.
Client is based on things logic to user's present graphical creation data, and preferably administrative staff can be facilitated to life
Production process has an intuitive understanding.
By different production type enterprises being arranged different middle layer database servers, it is quick to can be convenient system
It is switched in different production type enterprises, improves the adaptability of system.
S31 constructs multiple neural network models, each neural network model according to the creation data sample after standardization
It is trained using the initial weight of small random number and the training method with momentum term and learning rate.
S32 selects the neural network model with optimum prediction performance in the multiple neural network model, and remembers
Record the initial weight of the lower model and terminate weight, according to terminate weight and connection weight method calculate neural network model C, OI,
RI, comprising the following steps:
S321 calculates input-hidden layer-output connection weight contribution degree C；
S322 calculates the synthesis connection weight contribution degree OI of each variable；
S323 calculates the relative contribution rate RI of each variable；
S33 changes the sequence of training sample output collection at random；
S34 with after change sequence sample and S32 step in the initial weight that records, re -training neural network model,
And the termination weight of record cast；
S33 and S34 step is repeated several times in S35, and to record number of repetition as COUNT, is weighed according to the termination recorded in S34
Weight executes C, OI, RI that S32 step is randomized.
S36 calculates separately input-hidden layer-output connection weight contribution degree C, comprehensive connection weight contribution degree OI, relative contribution rate
The significance degree P of RI, includes the following steps,
If S361 standard value is greater than 0, P=(N+1)/(COUNT+1), N is the number that randomization value is more than or equal to standard value；
If S362 standard value is the number that randomization value is less than or equal to standard value less than 0, P=(M+1)/(COUNT+1), M；
Standard value in the present invention refers to the value of OI, RI, and for a certain input, the sign of the two is consistent, even certain
The OI of one variable is positive value, then RI is also positive value, and the expression of '+' plays positive stimulation；The expression of '-' plays negative sense and inhibits to make
With.Absolute value is bigger to indicate bigger to the contribution degree of output.
If S37 p is less than default level of signifiance value, retains the connection weight and otherwise reject the connection weight, and generate production energy
Consume neural network paraphrase figure.
The data show that step includes,
Technical staff's permission of different stage is set, and can be checked in data according to the authority setting technical staff
Hold.
Client does not log in design using classification, and the technical staff of different stage can check that the permission of data is different,
Improve while data instruct benefit effective protection creation data safety.
The data show that step includes,
The graphics data includes by carrying out year-on-year ring than control, generation pair to the creation data stored in database
The histogram answered, cake chart, curve graph, technical staff can check arbitrary period, the creation data of arbitrary equipment, and root at any time
Preferably analysis and judgement, which are made, according to the graphics data that system provides improves production management efficiency.
Energy consumption analysis model based on neural network transparence, using neural network paraphrase figure, assigning connection weight " can be solved
Release " ability, realize the visualization of chemical process model；Using connection weight method, chemical process NN model decision parameter is realized
Quantitative analysis to target variable importance；It is test using improved randomization, has trimmed complicated chemical process NN model, picked
In addition to redundancy, the transparence degree of NN model is improved, improves the intelligence and information of enterprise energy consumption prediction and analysis
Change.
The client and the server are isolated using B/S framework and with enterprise production information system.Server uses
B/S (BrowSer/Server) mode development, client zero installation, zero dimension shield, system easily extend.
C, OI, RI of one embodiment of the invention neural network model are illustrated below
(1) record is input to hidden layer and hidden layer to the connection weight matrix exported；
1 connection weight matrix of table
Table 1 Connection weightS matrix
(2) input-hidden layer-output connection weight contribution degree C is calculated
It is big to the contribution of output by hidden neuron to characterize each variable for input-hidden layer-output connection weight contribution degree
It is small.Its value be input to hidden layer connection weight and hidden layer to output connection weight product, expression formula are as follows:
Cij=Wij×WYi, i=A, B；J=1,2,3； (1)
Example: CA1=WA1×WYA=0.8147 × (- 0.6557)=- 0.5342, shows decision variable X1Pass through hidden layer nerve
First A is -0.5342 to the contribution degree of output Y.Input-hidden layer-output contribution degree such as table 2.
Table 2 inputs hidden layer and exports contribution degree
Table 2 The contribution of input-hidden-output
(3) comprehensive connection weight contribution degree OI
OI characterizes each input variable to the contribution of output variable.The expression of '+' plays positive stimulation；'-'
Negative sense inhibiting effect is indicated.The bigger expression of absolute value, expression formula bigger to the contribution degree of output are as follows:
Example:Show X1To the comprehensive contribution degree of Y
It is -0.6001.
(4) relative contribution rate RI
RI shows that each input variable integrally to the significance level of output variable, is provided with percents.If it is greater than
0, indicate that the variable plays positive interaction to output variable；If it is less than the 0 expression variable to having exported negative interaction.If it is equal to 0, table
Show that the variable does not influence output variable.Its calculation formula is:
Synthesis connection weight contribution degree OI and relative contribution rate the RI such as table 3 of calculating.
Table 3 comprehensive contribution degree OI and relative contribution rate RI
Table 3 Overall contribution(OI)and relative contribution rate(RI)
According to table 3, it can be deduced that X1、X3To output Y rise negative sense inhibiting effect, relative contribution rate be respectively -60.43% and -
29.24%；X2Positive stimulation is played to Y, relative contribution rate is 10.33%.Therefore, connection weight method compensates for neural network and releases
First defect of adopted figure, realizes quantitative analysis of the input variable to target variable contribution rate.
Below by a specific embodiment, next the present invention will be described.
In enterprise's hydrogen cyanide production process in the present embodiment, the complication the Worker's Stadium system is built using neural network
Mould inputs the compensating flowrate (Nm of compensation temperature (DEG C) for ammonia, ammonia3·h-1), natural gas/ammonia volume ratio, air/ammonia gas
Product ratio, the compensation pressure (Mpa) of ammonia, the compensation pressure (Mpa) of natural gas and 9 decisions of big mixer outlet temperature (DEG C) are joined
Number, corresponding variable are TN, FN, CN, AN, PN, PC, PA, PP, TD, are exported as hydrogen cyanide conversion ratio η (HCN).In production process
Decision parameters, HCN conversion ratio (η (HCN)) and sample data such as table 4.Sample data is divided into training set and inspection set, through anti-
It is 9-7-1 that the final topological structure for determining network is practiced in refreshment, as shown in Figure 2.
4 HCN production process variable of table and data set
Table 4 ProceSS variableS and data SetS of HCN
However, specific physical message cannot be obtained in HCN production process using the model in the prior art to explain this
Chemical industry system, also without the relationship between 9 decision parameters of method interpretation and hydrogen cyanide conversion ratio.Therefore, it is utilized respectively connection weight method
The contribution rate for quantitatively calculating the model decision parameter is test using improved randomization to trim hydrogen cyanide conversion ratio η (HCN) mind
Through network paraphrase figure, the transparence degree of hydrogen cyanide conversion ratio η (HCN) neural network model is further increased.
To hydrogen cyanide conversion ratio η (HCN) neural network model application connection weight method, 9 input decision parameters pair have been obtained
The comprehensive contribution degree and relative contribution rate of hydrogen cyanide conversion ratio η (HCN), as shown in table 5.
The comprehensive contribution rate OI and relative contribution rate RI of 5 decision variable of table
Table5 Overall contribution and relative contribution rate of
deciSion variableS
By carrying out randomization test to hydrogen cyanide conversion ratio η (HCN) neural network paraphrase figure, input-hidden layer-has been obtained
The randomization P value of connection weight is exported, as shown in table 6 (both preset value is 0.05 for α=0.05).
The P value (α=0.05) that table 6 is randomized
Table 6P value of randomization
Inapparent connection weight in hydrogen cyanide conversion ratio η (HCN) model is removed according to the P value in table 6, has obtained new hydrogen
Cyanic acid conversion ratio η (HCN) neural network paraphrase figure, as shown in Figure 3.When α=0.1 both preset value is 0.01, it can be found that mould
Type does not still obtain satisfactory neural network paraphrase figure although removing the inapparent connection weight in part.α=
0.05 both preset value be 0.05 when neural network paraphrase figure, compared with Fig. 2, hydrogen cyanide conversion ratio η (HCN) neural network paraphrase
Pattern is more succinct, and transparence degree is high, it is easier to explain between decision parameters and decision parameters, decision parameters and response variable
Relationship.Compared with the existing technology model is greatly improved by obtaining the internal information of process variable compared with, the present invention
" being appreciated that " ability can provide for the energy consumption analysis of enterprise's creation data and effectively instruct foundation.
Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although
Present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: it is still
Technical solution documented by foregoing embodiments is modified, or is equally replaced to some or all of the technical features
It changes；And these are modified or replaceed, the model for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution
It encloses, should all cover within the scope of the claims and the description of the invention.
Claims (6)
1. a kind of enterprise's creation data monitoring method based on industrial Internet of Things, which is characterized in that include the following steps,
S1 data collection steps, the data collection steps include acquiring or the data of industry spot measuring instrument to enterprise
Data acquisition in DCS control system；
S2 data transmission step, the data transmission step include that creation data is transmitted to service by data encryption step
Device；
S3 data analysis step, the data analysis step include that creation data is stored in the database based on mathematical logic
And creation data is analyzed according to things logic by middle tier server；
S4 data show step, the real-time production number including showing production equipment to user with graphics data by client
According to, accumulative creation data, abnormal alarm data, one of enterprise's production energy consumption data or a variety of are produced.
2. a kind of enterprise's creation data monitoring method based on industrial Internet of Things as shown in claim 1, which is characterized in that institute
Stating data encryption step includes,
Collected creation data is transmitted to industry spot industrial personal computer by unidirectional introducing equipment by wire transmission by S21；
S22 industrial personal computer carries out collected data, and classification is packaged and stores；
S23 industrial personal computer, using the system time factor as foundation, passes through the first label to by classification, the creation data for being packaged and storing
Name algorithm carries out signature and generates packet signature；
S24 server generates sample database signature using the system time factor as foundation, by the first signature algorithm；
Before S25 industrial personal computer sends data packet, packet signature and server end sample database are compared, if signature one
It causes, then sends data packet；
S26 server is decrypted to obtain creation data to the data packet received.
3. a kind of enterprise's creation data monitoring method based on industrial Internet of Things as shown in claim 1, which is characterized in that institute
It states that creation data analyze based on things logic by middle layer database and includes,
S31 constructs multiple neural network models according to the creation data sample after standardization, and each neural network model uses
The initial weight of small random number and training method with momentum term and learning rate are trained；
S32 selects the neural network model with optimum prediction performance in the multiple neural network model, and records
The initial weight and termination weight of the model, according to C, OI, the RI for terminating weight and connection weight method calculating neural network model, packet
Include following steps:
S321 calculates input-hidden layer-output connection weight contribution degree C；
S322 calculates the synthesis connection weight contribution degree OI of each variable；
S323 calculates the relative contribution rate RI of each variable；
S33 changes the sequence of training sample output collection at random；
S34 with after change sequence sample and S32 step in the initial weight that records, re -training neural network model, and remembering
Record the termination weight of model；
S33 and S34 step is repeated several times in S35, and to record number of repetition as COUNT, according to the termination weight recorded in S34,
Execute C, OI, RI that S32 step is randomized；
S36 calculates separately input-hidden layer-output connection weight contribution degree C, comprehensive connection weight contribution degree OI, relative contribution rate RI
Significance degree P, includes the following steps,
If S361 standard value is greater than 0, P=(N+1)/(COUNT+1), N is the number that randomization value is more than or equal to standard value；
If S362 standard value is the number that randomization value is less than or equal to standard value less than 0, P=(M+1)/(COUNT+1), M；
If S37 p is less than default level of signifiance value, retains the connection weight and otherwise reject the connection weight, and generates production energy consumption mind
Through network paraphrase figure.
4. a kind of enterprise's creation data monitoring method based on industrial Internet of Things as shown in claim 1, which is characterized in that institute
It states data and shows that step includes,
Technical staff's permission of different stage is set, and can check the content of data according to the authority setting technical staff.
5. a kind of enterprise's creation data monitoring method based on industrial Internet of Things as described in claim 1, which is characterized in that institute
It states data and shows that step includes,
The graphics data includes being generated corresponding by carrying out year-on-year ring than control to the creation data stored in database
Histogram, cake chart, curve graph；
Enterprise's production energy consumption data include production energy consumption neural network paraphrase figure.
6. a kind of enterprise's creation data monitoring method based on industrial Internet of Things as shown in claim 1, which is characterized in that institute
Client and the server are stated using B/S framework and is isolated with enterprise production information system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811524263.7A CN109613898B (en) | 2018-12-13 | 2018-12-13 | Enterprise production data monitoring method based on industrial Internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811524263.7A CN109613898B (en) | 2018-12-13 | 2018-12-13 | Enterprise production data monitoring method based on industrial Internet of things |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109613898A true CN109613898A (en) | 2019-04-12 |
| CN109613898B CN109613898B (en) | 2020-09-11 |
Family
ID=66009233
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811524263.7A Expired - Fee Related CN109613898B (en) | 2018-12-13 | 2018-12-13 | Enterprise production data monitoring method based on industrial Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109613898B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110362050A (en) * | 2019-07-22 | 2019-10-22 | 上海舜师自动化科技有限公司 | A kind of operation monitoring system of the production system of wireless charging mould group |
| CN111027799A (en) * | 2019-10-24 | 2020-04-17 | 山西云时代技术有限公司 | National enterprise productivity analysis system |
| CN111866057A (en) * | 2019-04-26 | 2020-10-30 | 株式会社安川电机 | Communication system, communication method, and program |
| CN112099449A (en) * | 2020-09-10 | 2020-12-18 | 南京柏瑞斯特智能科技有限公司 | Equipment data acquisition system based on industrial Internet of things cloud platform |
| CN112307507A (en) * | 2020-09-23 | 2021-02-02 | 上海上实龙创智能科技股份有限公司 | AIOT integrated management method based on intelligent gateway factory production |
| CN113958369A (en) * | 2021-11-10 | 2022-01-21 | 重庆科技学院 | Tunnel lining structure health monitoring method and system based on digital twinning |
| CN116345676A (en) * | 2023-02-15 | 2023-06-27 | 西安宇翔电气工程有限公司 | Intelligent monitoring system for power distribution cabinet |
| CN117075549A (en) * | 2023-08-17 | 2023-11-17 | 湖南源达智能科技有限公司 | Plant control method and system based on artificial neural network |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5857030A (en) * | 1995-08-18 | 1999-01-05 | Eastman Kodak Company | Automated method and system for digital image processing of radiologic images utilizing artificial neural networks |
| CN103581173A (en) * | 2013-09-11 | 2014-02-12 | 北京东土科技股份有限公司 | Safe data transmission method, system and device based on industrial Ethernet |
| CN105956786A (en) * | 2016-05-13 | 2016-09-21 | 河南心连心化肥有限公司 | Energy management system used for fertilizer enterprise |
| CN106843125A (en) * | 2017-01-12 | 2017-06-13 | 佛山职业技术学院 | A kind of production line data exchange system |
| CN207135281U (en) * | 2017-08-15 | 2018-03-23 | 北京国电智深控制技术有限公司 | One kind production real-time information management system |
| CN108762210A (en) * | 2018-05-25 | 2018-11-06 | 银川华信智信息技术有限公司 | A kind of industrial intelligent manufaturing data harvester and method based on Internet of Things |
| US20180336468A1 (en) * | 2017-05-16 | 2018-11-22 | Nec Laboratories America, Inc. | Pruning filters for efficient convolutional neural networks for image recognition in surveillance applications |
-
2018
- 2018-12-13 CN CN201811524263.7A patent/CN109613898B/en not_active Expired - Fee Related
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5857030A (en) * | 1995-08-18 | 1999-01-05 | Eastman Kodak Company | Automated method and system for digital image processing of radiologic images utilizing artificial neural networks |
| CN103581173A (en) * | 2013-09-11 | 2014-02-12 | 北京东土科技股份有限公司 | Safe data transmission method, system and device based on industrial Ethernet |
| CN105956786A (en) * | 2016-05-13 | 2016-09-21 | 河南心连心化肥有限公司 | Energy management system used for fertilizer enterprise |
| CN106843125A (en) * | 2017-01-12 | 2017-06-13 | 佛山职业技术学院 | A kind of production line data exchange system |
| US20180336468A1 (en) * | 2017-05-16 | 2018-11-22 | Nec Laboratories America, Inc. | Pruning filters for efficient convolutional neural networks for image recognition in surveillance applications |
| CN207135281U (en) * | 2017-08-15 | 2018-03-23 | 北京国电智深控制技术有限公司 | One kind production real-time information management system |
| CN108762210A (en) * | 2018-05-25 | 2018-11-06 | 银川华信智信息技术有限公司 | A kind of industrial intelligent manufaturing data harvester and method based on Internet of Things |
Non-Patent Citations (2)
| Title |
|---|
| 李倩: "人工神经网络混合剪枝算法", 《清华大学学报(自然科学版)》 * |
| 杨扬: "基于统计分析的卷积神经网络模型压缩方法", 《计算机系统应用》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111866057A (en) * | 2019-04-26 | 2020-10-30 | 株式会社安川电机 | Communication system, communication method, and program |
| CN111866057B (en) * | 2019-04-26 | 2023-05-05 | 株式会社安川电机 | Communication system and communication method |
| CN110362050A (en) * | 2019-07-22 | 2019-10-22 | 上海舜师自动化科技有限公司 | A kind of operation monitoring system of the production system of wireless charging mould group |
| CN111027799A (en) * | 2019-10-24 | 2020-04-17 | 山西云时代技术有限公司 | National enterprise productivity analysis system |
| CN112099449A (en) * | 2020-09-10 | 2020-12-18 | 南京柏瑞斯特智能科技有限公司 | Equipment data acquisition system based on industrial Internet of things cloud platform |
| CN112307507A (en) * | 2020-09-23 | 2021-02-02 | 上海上实龙创智能科技股份有限公司 | AIOT integrated management method based on intelligent gateway factory production |
| CN113958369A (en) * | 2021-11-10 | 2022-01-21 | 重庆科技学院 | Tunnel lining structure health monitoring method and system based on digital twinning |
| CN116345676A (en) * | 2023-02-15 | 2023-06-27 | 西安宇翔电气工程有限公司 | Intelligent monitoring system for power distribution cabinet |
| CN116345676B (en) * | 2023-02-15 | 2024-02-06 | 西安宇翔电气工程有限公司 | Intelligent monitoring system for power distribution cabinet |
| CN117075549A (en) * | 2023-08-17 | 2023-11-17 | 湖南源达智能科技有限公司 | Plant control method and system based on artificial neural network |
| CN117075549B (en) * | 2023-08-17 | 2024-03-22 | 湖南源达智能科技有限公司 | Plant control method and system based on artificial neural network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109613898B (en) | 2020-09-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109613898A (en) | A kind of enterprise's creation data monitoring method based on industrial Internet of Things | |
| Du et al. | GAN-based anomaly detection for multivariate time series using polluted training set | |
| Ramos et al. | AI in power systems and energy markets | |
| CN113657661A (en) | Enterprise carbon emission prediction method and device, computer equipment and storage medium | |
| Liu et al. | Real-time corporate carbon footprint estimation methodology based on appliance identification | |
| CN106199174A (en) | Extruder energy consumption predicting abnormality method based on transfer learning | |
| Shi et al. | DANTD: A deep abnormal network traffic detection model for security of industrial internet of things using high-order features | |
| Yang et al. | Cloud model for security state recognition based on factor space | |
| CN115049095A (en) | Dynamic optimization system for improving energy efficiency and carbon emission of equipment and related device | |
| Kai et al. | Construction of network security perception system using elman neural network | |
| Zheng et al. | Direct position updating‐based trying‐mutation particle swarm optimization algorithm and its application on reliability optimization | |
| Zhang et al. | A novel wasserstein generative adversarial network for stochastic wind power output scenario generation | |
| Sun et al. | Short-Term Exhaust Gas Temperature Trend Prediction of a Marine Diesel Engine Based on an Improved Slime Mold Algorithm-Optimized Bidirectional Long Short-Term Memory—Temporal Pattern Attention Ensemble Model | |
| Liu et al. | Short-term power load forecasting in FGSM-Bi-LSTM networks based on empirical wavelet transform | |
| Wang et al. | Neural network applications in hybrid data-model driven dynamic frequency trajectory prediction for weak-damping power systems | |
| He et al. | Identifying vulnerable set of cascading failure in power grid using deep learning framework | |
| Zhou et al. | A Novel Rolling and Fractional-ordered Grey System Model and Its Application for Predicting Industrial Electricity Consumption | |
| Ma et al. | Digital-Twin-Based CPS Anomaly Diagnosis and Security Defense Countermeasure Recommendation | |
| Xu et al. | Carbon Neutrality Computational Cost Optimization for Economic Dispatch With Carbon Capture Power Plants in Smart Grid | |
| Xu et al. | EPFSTO-ARIMA: Electric Power Forced Stochastic Optimization Predicting Based on ARIMA | |
| Liu et al. | Sustainability indicator of renewable energy system based on fuzzy multi-criteria decision making methods | |
| Xia et al. | Research on hidden danger risk perception technology based on big data | |
| Yu et al. | FedDeepFM: Ad CTR Prediction Based on Federated Factorization Machine | |
| Qiu et al. | The Analysis of Environmental Cost Control of Manufacturing Enterprises Using Deep Learning Optimization Algorithm and Internet of Things | |
| Ling et al. | Application research of data mining technology in power dispatching management system |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200911 Termination date: 20211213 |