CN110119339A - Appraisal procedure, system, equipment and the storage medium of the health status of industrial equipment - Google Patents
Appraisal procedure, system, equipment and the storage medium of the health status of industrial equipment Download PDFInfo
- Publication number
- CN110119339A CN110119339A CN201910376003.8A CN201910376003A CN110119339A CN 110119339 A CN110119339 A CN 110119339A CN 201910376003 A CN201910376003 A CN 201910376003A CN 110119339 A CN110119339 A CN 110119339A
- Authority
- CN
- China
- Prior art keywords
- data
- industrial equipment
- operation code
- historical
- sensor
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000003862 health status Effects 0.000 title claims abstract description 84
- 238000000034 method Methods 0.000 title claims abstract description 56
- 241001269238 Data Species 0.000 claims abstract 2
- 230000008569 process Effects 0.000 claims description 20
- 238000013480 data collection Methods 0.000 claims description 19
- 238000011156 evaluation Methods 0.000 claims description 13
- 241000208340 Araliaceae Species 0.000 claims description 11
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims description 11
- 235000003140 Panax quinquefolius Nutrition 0.000 claims description 11
- 235000008434 ginseng Nutrition 0.000 claims description 11
- 239000000203 mixture Substances 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 9
- 238000012417 linear regression Methods 0.000 claims description 8
- 230000006399 behavior Effects 0.000 claims description 4
- 230000000153 supplemental effect Effects 0.000 claims description 2
- 230000036541 health Effects 0.000 description 15
- 238000012549 training Methods 0.000 description 10
- 238000012544 monitoring process Methods 0.000 description 9
- 238000013210 evaluation model Methods 0.000 description 7
- 238000012360 testing method Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 230000007547 defect Effects 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3058—Monitoring arrangements for monitoring environmental properties or parameters of the computing system or of the computing system component, e.g. monitoring of power, currents, temperature, humidity, position, vibrations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3447—Performance evaluation by modeling
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Biology (AREA)
- Computer Hardware Design (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computing Systems (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses a kind of appraisal procedure of the health status of industrial equipment, system, equipment and storage medium, the appraisal procedure includes: to obtain the historical operating parameter data and operate corresponding historical operation code data that the sensor in industrial equipment acquires in history set period of time；Establish parametric prediction model；The corresponding parameter prediction value of sensor of interest is obtained according to parametric prediction model；According to target operating parameters data and parameter prediction value, health status of the industrial equipment within the goal-setting period is assessed.The present invention is based on the historical operation code datas of the historical operating parameter data of each sensor in industrial equipment and the corresponding discrete type of operation executed, establish the prediction model for predicting the parameter of either objective sensor output, then the health status of industrial equipment is assessed according to the residual error between the output parameter predicted value and real output value of model prediction, to improve the assessment accuracy of the health status of industrial equipment.
Description
Technical field
The present invention relates to device management techniques field, in particular to a kind of appraisal procedure of the health status of industrial equipment,
System, equipment and storage medium.
Background technique
Currently, as the intelligent level of equipment (such as industrial equipment) is constantly promoted, the remote condition monitoring of equipment with
Intelligent O&M is also gradually by the attention of enterprise.With the development of sensing technology and network technology, more and more data can be with
It realizes acquisition in real time and transmission, provides the foundation for the real-time status monitoring of equipment.Currently, being directed to different types of industrial equipment
Or different data characteristics, different health state evaluation methods is proposed, for example, some is directed to the vibration signal of gear-box,
The progress feature extraction such as (empirical mode decomposition) is decomposed based on EMD and constructs health state evaluation model；Some is passed through based on expert
It tests, by mechanism of giving a mark, constructs the overall assessment index to equipment；Some based on data and is specified based on fuzzy mathematics theory
Index etc., construct the subordinating degree function of health evaluating, obtain the health status of equipment.
I.e. in the prior art in the health state evaluation model for establishing industrial equipment, inertial thinking is exactly to use analog quantity
Characteristic parameter carry out training pattern；Or it only will recognize that further types of to acquire by using further types of sensor is added
The mode of the characteristic parameter of analog quantity obtains the assessment models of more high accuracy, and the above-mentioned feature ginseng for being based only on analog quantity
The health state evaluation model for the industrial equipment that number obtains haves the defects that Evaluation accuracy is not high.
Summary of the invention
The technical problem to be solved by the present invention is to equipment health state evaluation models in the prior art all only to consider analog quantity
Characteristic parameter, there are Evaluation accuracies the defects of not high, and it is an object of the present invention to provide a kind of assessment side of the health status of industrial equipment
Method, system, equipment and storage medium.
In order to solve the above-mentioned technical problem, specific inventive concept of the invention is as follows:
For a person skilled in the art, it is real-time all only to consider that the data of the continuous type obtained by sensor have
Property and continuity, can intuitively reflect these advantages of certain parameter situations of industrial equipment, thus just only will recognize that and be based only upon
The technical solution of the health state evaluation model for the industrial equipment that the characteristic parameter of continuous type obtains.Therefore, existing routine is answered
Also it cannot comprehensively reflect the healthy feelings of industrial equipment there is no defect existing for the data itself for considering continuous type in
Condition, thus the problem for causing the data training pattern for being based only upon continuous type to bring model prediction result precision not high.
For industrial equipment corresponding discrete type in the process of implementation data (such as in the operation of execution corresponding operation generation
Code data), and influence industrial equipment health state evaluation an important factor for.
And those skilled in the art, it is difficult to based on existing inertial thinking by the data of above-mentioned continuous type and discrete type
Data combine to establish the health state evaluation model of industrial equipment；It does not know how even if the two is combined based on this yet
Two kinds of data obtain the health state evaluation model of industrial equipment.
Specifically, the present invention is to solve above-mentioned technical problem by following technical proposals:
The present invention provides a kind of appraisal procedure of the health status of industrial equipment, and the appraisal procedure includes:
Obtain the corresponding historical operation code data of operation that executes in history set period of time of industrial equipment and described
All historical operating parameter data that sensor in industrial equipment acquires in the history set period of time；
Wherein, the historical operating parameter data are continuous data, and the historical operation code data is discrete type number
According to；The history set period of time includes multiple duty cycles；
A sensor is chosen as sensor of interest, respectively with the historical operation code in multiple duty cycles
Data and all historical operating parameter data are as input, with the sensor of interest in the corresponding duty cycle
The history target operating parameters data of interior acquisition establish parametric prediction model as output；
Obtain the first operational parameter data that the sensor in the industrial equipment acquires within the goal-setting period and
The corresponding first operation code data of the operation that the industrial equipment executes within the goal-setting period；
Wherein, first operational parameter data includes that the sensor of interest acquires within the goal-setting period
The first operational parameter data be target operating parameters data；
First operational parameter data and the first operation code data are input to the parametric prediction model, obtained
Take the corresponding parameter prediction value of the sensor of interest；
The industrial equipment according to the Bias of the target operating parameters data and the parameter prediction value is described
Health status in the goal-setting period.
Preferably, it is described respectively in multiple duty cycles the historical operation code data and it is all described in
Historical operating parameter data are as input, the history target acquired within the corresponding duty cycle with the sensor of interest
As output, the step of establishing parametric prediction model includes: operational parameter data
Coded treatment is carried out to the historical operation code data, obtains the corresponding operation of the historical operation code data
Code vector；
The historical operating parameter number all with the operation code vector sum in multiple duty cycles respectively
According to as input, made with the history target operating parameters data that the sensor of interest acquires within the corresponding duty cycle
For output, parametric prediction model is established.
Preferably, one state code sequence of each duty cycle corresponding historical operation code data composition
Column, the corresponding multiple state code Sequence composition state code sequence libraries of the history set period of time；
It is described that coded treatment is carried out to the historical operation code data, it is corresponding to obtain the historical operation code data
The step of operation code vector includes:
The operation code data corresponding to each of the state code sequence library duty cycle carry out only
Heat coding；
The operation code data after one-hot coding are input to Word2vec model (a kind of transformation model) to compile
Code processing, obtains the corresponding operation code vector of the operation code data.
Preferably, the industry according to the Bias of the target operating parameters data and the parameter prediction value
The step of health status of the equipment within the goal-setting period includes:
Calculate the residual error between the target operating parameters data and the parameter prediction value；
Judge whether the residual error is more than given threshold, if being more than, it is determined that the industrial equipment is in unhealthy status；
Otherwise, it determines the industrial equipment is in health status.
Preferably, the step of residual error calculated between the target operating parameters data and the parameter prediction value, wraps
It includes:
Residual error between the target operating parameters data and the parameter prediction value is calculated using Pauta criterion.
Preferably, it is described respectively in multiple duty cycles the historical operation code data and it is all described in
Historical operating parameter data are as input, the history target acquired within the corresponding duty cycle with the sensor of interest
As output, the step of establishing parametric prediction model includes: operational parameter data
Use linear regression algorithm or XGBoost algorithm (a kind of machine learning algorithm) respectively with multiple duty cycles
The interior historical operation code data and all historical operating parameter data are as input, with the sensor of interest
The history target operating parameters data acquired within the corresponding duty cycle establish parametric prediction model as output.
Preferably, the corresponding historical operation code of operation for obtaining industrial equipment and being executed in history set period of time
All historical operating parameter numbers that sensor in data and the industrial equipment acquires in the history set period of time
According to the step of after further include:
Remove the exceptional value in the historical operating parameter data and the historical operation code data.
Preferably, the corresponding historical operation code of operation for obtaining industrial equipment and being executed in history set period of time
All historical operating parameter numbers that sensor in data and the industrial equipment acquires in the history set period of time
According to the step of include:
The operation pair that industrial equipment executes in history set period of time is acquired respectively using different data collection systems
The sensor in historical operation code data and the industrial equipment answered acquires all in the history set period of time
Historical operating parameter data；
It is described obtain the corresponding historical operation code data of operation that is executed in history set period of time of industrial equipment and
The step for all historical operating parameter data that sensor in the industrial equipment acquires in the history set period of time
After rapid further include: the historical operating parameter data and the historical operation for acquiring the different data collection systems
Code data carries out registration process according to timestamp；
It is described respectively with the historical operation code data and all history fortune in multiple duty cycles
Row supplemental characteristic is as input, the history object run ginseng acquired within the corresponding duty cycle with the sensor of interest
Data, which are counted, as the step of exporting, establish parametric prediction model includes:
Respectively with after middle registration process in multiple duty cycles the historical operation code data and all institutes
It states historical operating parameter data and is used as input, the history mesh acquired within the corresponding duty cycle with the sensor of interest
Operational parameter data is marked as output, establishes parametric prediction model.
The present invention also provides a kind of assessment system of the health status of industrial equipment, the assessment system includes historical data
Obtain module, parametric prediction model establishes module, the first data acquisition module, parameter prediction value obtain module and evaluation module；
It is corresponding for obtaining the operation that industrial equipment executes in history set period of time that the historical data obtains module
Historical operation code data and the industrial equipment in sensor acquired in the history set period of time it is all
Historical operating parameter data；
Wherein, the historical operating parameter data are continuous data, and the historical operation code data is discrete type number
According to；The history set period of time includes multiple duty cycles；
The parametric prediction model establish module for choose a sensor as sensor of interest, respectively with multiple described
The historical operation code data and all historical operating parameter data in duty cycle is as input, with the mesh
The history target operating parameters data that mark sensor acquires within the corresponding duty cycle establish parameter prediction as output
Model；
First data acquisition module is used to obtain the sensor in the industrial equipment within the goal-setting period
The operation that is executed within the goal-setting period of the first operational parameter data and the industrial equipment of acquisition corresponding the
One operation code data；
Wherein, first operational parameter data includes that the sensor of interest acquires within the goal-setting period
The first operational parameter data be target operating parameters data；
The parameter prediction value obtains module and is used for first operational parameter data and the first operation code number
According to the parametric prediction model is input to, the corresponding parameter prediction value of the sensor of interest is obtained；
The evaluation module is used for the Bias institute according to the target operating parameters data and the parameter prediction value
State health status of the industrial equipment within the goal-setting period.
Preferably, it includes operation code vector acquiring unit and model foundation list that the parametric prediction model, which establishes module,
Member；
The operation code vector acquiring unit is used to carry out coded treatment to the historical operation code data, obtains institute
State the corresponding operation code vector of historical operation code data；
The model foundation unit is for all with the operation code vector sum in multiple duty cycles respectively
The historical operating parameter data as input, gone through with what the sensor of interest acquired within the corresponding duty cycle
History target operating parameters data establish parametric prediction model as output.
Preferably, one state code sequence of each duty cycle corresponding historical operation code data composition
Column, the corresponding multiple state code Sequence composition state code sequence libraries of the history set period of time；
The operation code vector acquiring unit includes that one-hot coding subelement and code vector obtain subelement；
The one-hot coding subelement is for corresponding to each of the state code sequence library duty cycle
The operation code data carry out one-hot coding；
The code vector obtains subelement for being input to the operation code data after one-hot coding
Word2vec model carries out coded treatment, obtains the corresponding operation code vector of the operation code data.
Preferably, the evaluation module includes residual computations unit, judging unit and determination unit；
The residual computations unit is residual between the target operating parameters data and the parameter prediction value for calculating
Difference；
The judging unit is for judging whether the residual error is more than given threshold, if being more than, calls described determining single
Member determines that the industrial equipment is in unhealthy status；Otherwise, the determination unit is called to determine that the industrial equipment is in strong
Health state.
Preferably, the residual computations unit is used to calculate the target operating parameters data and institute using Pauta criterion
State the residual error between parameter prediction value.
Preferably, the prediction model establishes module for using linear regression algorithm or XGBoost algorithm respectively with more
The historical operation code data and all historical operating parameter data in a duty cycle are used as input, with
The history target operating parameters data that the sensor of interest acquires within the corresponding duty cycle establish ginseng as output
Number prediction model.
Preferably, the assessment system further includes outlier processing module；
The outlier processing is for removing in the historical operating parameter data and the historical operation code data
Exceptional value.
Preferably, the assessment system further includes registration process module；
The historical data obtains module and is used to acquire industrial equipment respectively in history using different data collection systems
The sensor in operation corresponding historical operation code data and the industrial equipment executed in set period of time is gone through described
All historical operating parameter data acquired in history set period of time；
The registration process module is used for the historical operating parameter number for acquiring the different data collection systems
Registration process is carried out according to timestamp according to the historical operation code data；
The parametric prediction model establishes module for respectively with the institute after middle registration process in multiple duty cycles
Historical operation code data and all historical operating parameter data are stated as input, with the sensor of interest in correspondence
The duty cycle in acquire history target operating parameters data as output, establish parametric prediction model.
The present invention also provides a kind of electronic equipment, including memory, processor and storage on a memory and can handled
The computer program run on device, the processor realize the health status of above-mentioned industrial equipment when executing computer program
Appraisal procedure.
The present invention also provides a kind of computer readable storage mediums, are stored thereon with computer program, the computer journey
The step of appraisal procedure of the health status of above-mentioned industrial equipment is realized when sequence is executed by processor.
The positive effect of the present invention is that:
In the present invention, based on the historical operating parameter data that each sensor in industrial equipment is interior for a period of time in history
With the historical operation code data of the corresponding discrete type of operation of execution, the ginseng for predicting the output of either objective sensor is established
Several prediction model, then according between the output parameter predicted value of model prediction and the real output value of the sensor of interest
Residual error assesses the health status of industrial equipment, to improve the assessment accuracy of the health status of industrial equipment, and then promotes
Monitoring and management to industrial equipment.
Detailed description of the invention
Fig. 1 is the flow chart of the appraisal procedure of the health status of the industrial equipment of the embodiment of the present invention 1.
Fig. 2 is the flow chart of the appraisal procedure of the health status of the industrial equipment of the embodiment of the present invention 2.
Fig. 3 is the flow chart of the appraisal procedure of the health status of the industrial equipment of the embodiment of the present invention 3.
Fig. 4 is the module diagram of the assessment system of the health status of the industrial equipment of the embodiment of the present invention 4.
Fig. 5 is the module diagram of the assessment system of the health status of the industrial equipment of the embodiment of the present invention 5.
Fig. 6 is the module diagram of the assessment system of the health status of the industrial equipment of the embodiment of the present invention 6.
Fig. 7 is the knot of the electronic equipment of the appraisal procedure of the health status of the realization industrial equipment in the embodiment of the present invention 7
Structure schematic diagram.
Specific embodiment
The present invention is further illustrated below by the mode of embodiment, but does not therefore limit the present invention to the reality
It applies among a range.
Embodiment 1
As shown in Figure 1, the appraisal procedure of the health status of the industrial equipment of the present embodiment includes:
S101, obtain the corresponding historical operation code data of operation that is executed in history set period of time of industrial equipment and
All historical operating parameter data that sensor in industrial equipment acquires in history set period of time；
Wherein, historical operating parameter data are continuous data, and historical operation code data is discrete data；History is set
Section of fixing time includes multiple duty cycles；
Specified operation is completed in order to guarantee industrial equipment within each duty cycle, prior compilation operation code is needed and incites somebody to action
It is stored into corresponding storage equipment, and wherein historical operation code data is acquired from storage equipment by data collection system
It arrives.
S102, a sensor is chosen as sensor of interest, respectively with the historical operation code number in multiple duty cycles
Input, the history mesh acquired within the corresponding duty cycle with sensor of interest are used as according to all historical operating parameter data
Operational parameter data is marked as output, establishes parametric prediction model；
Specifically, use linear regression algorithm or XGBoost algorithm respectively with the historical operation generation in multiple duty cycles
Code data and all historical operating parameter data are gone through as input with what sensor of interest acquired within the corresponding duty cycle
History target operating parameters data establish parametric prediction model as output；But be also not necessarily limited to using linear regression algorithm,
XGBoost algorithm also may include other algorithms that other can be realized parametric prediction model foundation.
S103, obtain the first operational parameter data for being acquired within the goal-setting period of sensor in industrial equipment and
The corresponding first operation code data of the operation that industrial equipment executes within the goal-setting period；
Wherein, the first operational parameter data includes the first operation ginseng that sensor of interest acquires within the goal-setting period
Number data are target operating parameters data；
S104, the first operational parameter data and the first operation code data are input to parametric prediction model, obtain target
The corresponding parameter prediction value of sensor；
S105, according to the Bias industrial equipment of target operating parameters data and parameter prediction value in the goal-setting time
Health status in section.
In the present embodiment, based on the historical operating parameter number that each sensor in industrial equipment is interior for a period of time in history
According to the historical operation code data of the corresponding discrete type of operation with execution, establish for predicting the output of either objective sensor
Then the prediction model of parameter is commented according to the real output value of the output parameter predicted value of model prediction and the sensor of interest
Estimate the health status of industrial equipment, to improve the assessment accuracy of the health status of industrial equipment, and then promotes to set industry
Standby monitoring and management.
Embodiment 2
As shown in Fig. 2, the appraisal procedure of the health status of the industrial equipment of the present embodiment is further changing to embodiment 1
Into specifically:
After step S101, before step S103 further include:
S1030, historical operating parameter data and historical operation code data are pre-processed.
Wherein, pretreatment includes some abnormal numbers in removal historical operating parameter data and historical operation code data
According to, such as data obtained when sensor failure etc..
Historical operating parameter data and historical operation code data are obtained in the present embodiment using data collection system, this
The data collection system at place is the existing equipment that target data can be obtained from a certain equipment, concrete type, model
Deng not making particular/special requirement.
In addition, for the historical operating parameter data and historical operation code data that are acquired by same data collection system,
Historical operating parameter data and historical operation code data are acquired directly from data collection system；For being adopted by different data
The historical operating parameter data and historical operation code data that collecting system acquires respectively, need to pre-process it, specifically
Historical operating parameter data and historical operation code data are aligned and are integrated according to timestamp, for example, by A pairs of time point
The corresponding historical operation code data of historical operating parameter data and time point A answered is corresponded to.
For the step of establishing parametric prediction model, using the historical operation code data after registration process and all go through
History operational parameter data is as input to establish parametric prediction model.
Step S103 includes:
S1031, coded treatment is carried out to historical operation code data, obtains historical operation code data corresponding operation generation
Code vector；
S1032, respectively using all historical operating parameter data of the operation code vector sum in multiple duty cycles as
Input establishes ginseng using the history target operating parameters data that sensor of interest acquires within the corresponding duty cycle as output
Number prediction model.
In order to improve model prediction accuracy, while the case where prevent over-fitting, need to predict mould to the health status of building
Type is verified.Training set, verifying collection and test set are divided into the sample data that the building health status prediction model stage prepares,
After obtaining health status prediction model based on training set training, the health status prediction model obtained to training is collected using verifying
The tuning for carrying out verifying and hyper parameter, is then tested on test set again, the corresponding error of observation test set, according to the mistake
Difference judges whether that over-fitting occurs then to be needed to continue adjusting and optimizing hyper parameter if there is over-fitting, until the health status is pre-
Survey model accuracy with higher and Generalization Capability.
Step S105 includes:
Residual error between S1051, calculating target operating parameters data and parameter prediction value；
Specifically, the residual error between target operating parameters data and parameter prediction value is calculated using Pauta criterion.
S1052, judge whether residual error is more than given threshold, if being more than, it is determined that industrial equipment is in unhealthy status；It is no
Then, determine that industrial equipment is in health status.
In the present embodiment, based on the historical operating parameter number that each sensor in industrial equipment is interior for a period of time in history
According to, and coding is carried out to the historical operation code data of the corresponding discrete type of operation of execution and obtains operation code vector, it builds
The prediction model for predicting the parameter of either objective sensor output is found, then according to the output parameter predicted value of model prediction
Residual error between the real output value of the sensor of interest assesses the health status of industrial equipment, to improve industrial equipment
Health status assessment accuracy, and then promote monitoring and management to industrial equipment.
Embodiment 3
As shown in figure 3, the appraisal procedure of the health status of the industrial equipment of the present embodiment is further changing to embodiment 2
Into specifically:
One state code sequence of each duty cycle corresponding historical operation code data composition, history set period of time
Corresponding multiple state code Sequence composition state code sequence libraries.
For example, industrial equipment includes excavator, wind-driven generator etc..For excavator, can be used as from booting to shutdown
One duty cycle；For wind-driven generator, can each consecutive days as a duty cycle.
The industrial equipments such as excavator or wind-driven generator can execute a series of operation, Mei Gecao within each duty cycle
The historical operation code data of itself is all corresponded to, sequentially in time (duty cycle is from start to end), by each work
The historical operation code data of a series of operation in period constitutes a state code sequence.Specifically, it is assumed that excavator exists
Operation A (operation A corresponds to code " 001 "), operation B (operation B corresponds to code " 003 ") and behaviour are successively executed in one duty cycle
Make C (operation C corresponds to code " 012 "), then excavator corresponding state code sequence within a duty cycle is
"001003012".In addition, the case where there are causes different in size of corresponding state code sequence of different duty cycles.
Multiple duty cycles, corresponding multiple state code sequences generated the industrial equipments such as excavator or wind-driven generator
State code sequence library.
Step S1031 is specifically included:
S10311, solely heat volume is carried out to the corresponding operation code data of each duty cycle in state code sequence library
Code；
Such as: a state code sequence " 001003012 " in state code sequence library is encoded to " 010 ", i.e., will
The corresponding code " 001 " of operation A is encoded to " 0 ", will operate the corresponding code of B " 003 " and is encoded to " 1 ", the corresponding code of operation C
" 012 " is encoded to " 0 ", is converted to the corresponding operation code data of each duty cycle in state code sequence library with realizing
0 or 1, to guarantee that Word2vec model is capable of handling.
S10312, the operation code data after one-hot coding are input to Word2vec model progress coded treatment, obtained
The corresponding operation code vector of operation code data.
Wherein, digitalized data that the 0 of input or 1 indicates is encoded to corresponding with correlation by Word2vec model
Vector belongs to the prior art, therefore its specific coding process is not described in more detail here.
Each operation code vector in each duty cycle can measure difference between each operation code data with
Similarity degree.
It is illustrated below with reference to example:
1) for an excavator, the history that each sensor in the excavator acquires in for a period of time in history is obtained
The corresponding history of each operation (such as shovel is dug, bucket is dug) that operational parameter data and the excavator during this period of time execute
Operation code data；
2) the historical operating parameter data of acquisition and historical operation code data are pre-processed, such as deletes sensor event
Hinder data；
3) excavator is used as to a duty cycle from be switched on to shutting down, obtains each operation in each duty cycle
Corresponding historical operation code data forms operation code sequence, and then forms all working period corresponding operation code sequence
Library；One-hot coding is carried out to the historical operation code data in operation code sequence library, and by the historical operation after one-hot coding
Code data is input to Word2vec model and is encoded, obtain the corresponding operation code of each historical operation code data to
Amount；
4) select the temperature sensor for being used to acquire tank temperature in excavator as sensor of interest, using XGBoost
The historical operating parameter data that algorithm is acquired in for a period of time with all the sensors of the excavator in historical time section in history
It is input with operation code vector, acquires the history run ginseng that the temperature sensor of tank temperature acquires in for a period of time in history
Number data are output, establish parametric prediction model；
5) according to the oil temperature predicted value of the temperature sensor of parametric prediction model Prediction and Acquisition tank temperature, while oil is acquired
Then the oil temperature actual value of the temperature sensor actual acquisition of box temperature degree calculates oil using 3sigam method (i.e. Pauta criterion)
Residual error between warm predicted value and oil temperature reference value, when the residual error is more than given threshold, it is determined that excavator has exception, needs
It to arouse attention to it, continue to observe；If residual error is always maintained at more than given threshold, it is determined that excavator is overhauled, with
The normal use for guaranteeing excavator, extends its service life.
In the present embodiment, based on the historical operating parameter number that each sensor in industrial equipment is interior for a period of time in history
According to, and Word2vec model is used to carry out coding acquisition to the historical operation code data of the corresponding discrete type of operation of execution
Operation code vector establishes the prediction model for predicting the parameter of either objective sensor output, then according to model prediction
Output parameter predicted value and the sensor of interest real output value between residual error assess the health status of industrial equipment,
To improve the assessment accuracy of the health status of industrial equipment, and then promote the monitoring and management to industrial equipment.
Embodiment 4
As shown in figure 4, the assessment system of the health status of the industrial equipment of the present embodiment includes that historical data obtains module
1, parametric prediction model establishes module 2, the first data acquisition module 3, parameter prediction value and obtains module 4 and evaluation module 5.
Historical data obtains module 1 and is used to obtain that operation that industrial equipment executes in history set period of time to be corresponding goes through
All historical operating parameters that sensor in history operation code data and industrial equipment acquires in history set period of time
Data；
Wherein, historical operating parameter data are continuous data, and historical operation code data is discrete data；History is set
Section of fixing time includes multiple duty cycles；
Specified operation is completed in order to guarantee industrial equipment within each duty cycle, prior compilation operation code is needed and incites somebody to action
It is stored into corresponding storage equipment, and wherein historical operation code data is acquired from storage equipment by data collection system
It arrives.
Parametric prediction model establish module 2 for choose a sensor as sensor of interest, respectively with multiple work weeks
Historical operation code data and all historical operating parameter data in phase is as input, with sensor of interest in corresponding work
Make the history target operating parameters data acquired in the period as output, establishes parametric prediction model；
Specifically, use linear regression algorithm or XGBoost algorithm respectively with the historical operation generation in multiple duty cycles
Code data and all historical operating parameter data are gone through as input with what sensor of interest acquired within the corresponding duty cycle
History target operating parameters data establish parametric prediction model as output；But be also not necessarily limited to using linear regression algorithm,
XGBoost algorithm also may include other algorithms that other can be realized parametric prediction model foundation.
The sensor that first data acquisition module 3 is used to obtain in industrial equipment acquired within the goal-setting period the
The corresponding first operation code data of the operation that one operational parameter data and industrial equipment execute within the goal-setting period；
Wherein, the first operational parameter data includes the first operation ginseng that sensor of interest acquires within the goal-setting period
Number data are target operating parameters data；
Parameter prediction value obtains module 4 and is used to the first operational parameter data and the first operation code data being input to parameter
Prediction model obtains the corresponding parameter prediction value of sensor of interest；
Evaluation module 5 is used for according to the Bias industrial equipment of target operating parameters data and parameter prediction value in target
Health status in set period of time.
In the present embodiment, based on the historical operating parameter number that each sensor in industrial equipment is interior for a period of time in history
According to the historical operation code data of the corresponding discrete type of operation with execution, establish for predicting the output of either objective sensor
Then the prediction model of parameter is commented according to the real output value of the output parameter predicted value of model prediction and the sensor of interest
Estimate the health status of industrial equipment, to improve the assessment accuracy of the health status of industrial equipment, and then promotes to set industry
Standby monitoring and management.
Embodiment 5
As shown in figure 5, the assessment system of the health status of the industrial equipment of the present embodiment is further changing to embodiment 4
Into specifically:
Assessment system further includes outlier processing module 6 and registration process module 7.
Outlier processing module 6 is used to remove some exceptions in historical operating parameter data and historical operation code data
Data, such as the data obtained when sensor failure etc..
In addition, historical operating parameter data and historical operation code number are obtained in the present embodiment using data collection system
It is the existing equipment that target data can be obtained from a certain equipment according to, data collection system herein, concrete type,
Model etc. does not make particular/special requirement.
For the historical operating parameter data and historical operation code data acquired by same data collection system, directly from
Historical operating parameter data and historical operation code data are acquired in data collection system；For by different data collection systems
The historical operating parameter data and historical operation code data acquired respectively, need to pre-process it, specifically using pair
Historical operating parameter data and historical operation code data are aligned and are integrated according to timestamp by neat processing module 7, for example,
The corresponding historical operating parameter data of time point A and the corresponding historical operation code data of time point A are corresponded to.
When parametric prediction model establishes module 2 and establishes parametric prediction model, using the historical operation generation after registration process
Code data and all historical operating parameter data are used as input to establish parametric prediction model.
It includes operation code vector acquiring unit 8 and model foundation unit 9 that parametric prediction model, which establishes module 2,.
Operation code vector acquiring unit 8 is used to carry out coded treatment to historical operation code data, obtains historical operation
The corresponding operation code vector of code data；
Model foundation unit 9 is for history run ginsengs all with the operation code vector sum in multiple duty cycles respectively
Number data are as input, using the history target operating parameters data that sensor of interest acquires within the corresponding duty cycle as defeated
Out, parametric prediction model is established.
In order to improve model prediction accuracy, while the case where prevent over-fitting, need to predict mould to the health status of building
Type is verified.Training set, verifying collection and test set are divided into the sample data that the building health status prediction model stage prepares,
After obtaining health status prediction model based on training set training, the health status prediction model obtained to training is collected using verifying
The tuning for carrying out verifying and hyper parameter, is then tested on test set again, the corresponding error of observation test set, according to the mistake
Difference judges whether that over-fitting occurs then to be needed to continue adjusting and optimizing hyper parameter if there is over-fitting, until the health status is pre-
Survey model accuracy with higher and Generalization Capability.
Evaluation module 5 includes residual computations unit 10, judging unit 11 and determination unit 12；
Residual computations unit 10 is used to calculate health forecast value and with reference to the residual error between health value；Specifically, using drawing
According to the residual error calculated up to criterion between health forecast value and reference health value.
Judging unit 11 is for judging whether residual error is more than given threshold, if being more than, determination unit 12 is called to determine work
Industry equipment is in unhealthy status；Otherwise, determination unit 12 is called to determine that industrial equipment is in health status.
In the present embodiment, based on the historical operating parameter number that each sensor in industrial equipment is interior for a period of time in history
According to, and coding is carried out to the historical operation code data of the corresponding discrete type of operation of execution and obtains operation code vector, it builds
The prediction model for predicting the parameter of either objective sensor output is found, then according to the output parameter predicted value of model prediction
Residual error between the real output value of the sensor of interest assesses the health status of industrial equipment, to improve industrial equipment
Health status assessment accuracy, and then promote monitoring and management to industrial equipment.
Embodiment 6
As shown in fig. 6, the assessment system of the health status of the industrial equipment of the present embodiment is further changing to embodiment 5
Into specifically:
One state code sequence of each duty cycle corresponding historical operation code data composition, history set period of time
Corresponding multiple state code Sequence composition state code sequence libraries.
For example, industrial equipment includes excavator, wind-driven generator etc..For excavator, can be used as from booting to shutdown
One duty cycle；For wind-driven generator, can each consecutive days as a duty cycle.
The industrial equipments such as excavator or wind-driven generator can execute a series of operation, Mei Gecao within each duty cycle
The historical operation code data of itself is all corresponded to, sequentially in time (duty cycle is from start to end), by each work
The historical operation code data of a series of operation in period constitutes a state code sequence.Specifically, it is assumed that excavator exists
Operation A (operation A corresponds to code " 001 "), operation B (operation B corresponds to code " 003 ") and behaviour are successively executed in one duty cycle
Make C (operation C corresponds to code " 012 "), then excavator corresponding state code sequence within a duty cycle is
"001003012".In addition, the case where there are causes different in size of corresponding state code sequence of different duty cycles.
Multiple duty cycles, corresponding multiple state code sequences generated the industrial equipments such as excavator or wind-driven generator
State code sequence library.
Operation code vector acquiring unit 8 includes that one-hot coding subelement 13 and code vector obtain subelement 14.
One-hot coding subelement 13 is used for the corresponding operation code number of each duty cycle in state code sequence library
According to progress one-hot coding；
Such as: a state code sequence " 001003012 " in state code sequence library is encoded to " 010 ", i.e., will
The corresponding code " 001 " of operation A is encoded to " 0 ", will operate the corresponding code of B " 003 " and is encoded to " 1 ", the corresponding code of operation C
" 012 " is encoded to " 0 ", is converted to the corresponding operation code data of each duty cycle in state code sequence library with realizing
0 or 1, to guarantee that Word2vec model is capable of handling.
Code vector obtains subelement 14 and is used to the operation code data after one-hot coding being input to Word2vec model
Coded treatment is carried out, the corresponding operation code vector of operation code data is obtained.
Wherein, digitalized data that the 0 of input or 1 indicates is encoded to corresponding with correlation by Word2vec model
Vector belongs to the prior art, therefore its specific coding process is not described in more detail here.
Each operation code vector in each duty cycle can measure difference between each operation code data with
Similarity degree.
It is illustrated below with reference to example:
1) for an excavator, the history that each sensor in the excavator acquires in for a period of time in history is obtained
The corresponding history of each operation (such as shovel is dug, bucket is dug) that operational parameter data and the excavator during this period of time execute
Operation code data；
2) the historical operating parameter data of acquisition and historical operation code data are pre-processed, such as deletes sensor event
Hinder data；
3) excavator is used as to a duty cycle from be switched on to shutting down, obtains each operation in each duty cycle
Corresponding historical operation code data forms operation code sequence, and then forms all working period corresponding operation code sequence
Library；One-hot coding is carried out to the historical operation code data in operation code sequence library, and by the historical operation after one-hot coding
Code data is input to Word2vec model and is encoded, obtain the corresponding operation code of each historical operation code data to
Amount；
4) select the temperature sensor for being used to acquire tank temperature in excavator as sensor of interest, using XGBoost
The historical operating parameter data that algorithm is acquired in for a period of time with all the sensors of the excavator in historical time section in history
It is input with operation code vector, acquires the history run ginseng that the temperature sensor of tank temperature acquires in for a period of time in history
Number data are output, establish parametric prediction model；
5) according to the oil temperature predicted value of the temperature sensor of parametric prediction model Prediction and Acquisition tank temperature, while oil is acquired
Then the oil temperature actual value of the temperature sensor actual acquisition of box temperature degree calculates oil using 3sigam method (i.e. Pauta criterion)
Residual error between warm predicted value and oil temperature reference value, when the residual error is more than given threshold, it is determined that excavator has exception, needs
It to arouse attention to it, continue to observe；If residual error is always maintained at more than given threshold, it is determined that excavator is overhauled, with
The normal use for guaranteeing excavator, extends its service life.
In the present embodiment, based on the historical operating parameter number that each sensor in industrial equipment is interior for a period of time in history
According to, and Word2vec model is used to carry out coding acquisition to the historical operation code data of the corresponding discrete type of operation of execution
Operation code vector establishes the prediction model for predicting the parameter of either objective sensor output, then according to model prediction
Output parameter predicted value and the sensor of interest real output value between residual error assess the health status of industrial equipment,
To improve the assessment accuracy of the health status of industrial equipment, and then promote the monitoring and management to industrial equipment.
Embodiment 7
Fig. 7 is the structural schematic diagram for a kind of electronic equipment that the embodiment of the present invention 7 provides.Electronic equipment include memory,
Processor and storage are on a memory and the computer program that can run on a processor, processor realize implementation when executing program
The appraisal procedure of the health status of industrial equipment in example 1 to 3 in any one embodiment.The electronic equipment 30 that Fig. 7 is shown is only
An example, should not function to the embodiment of the present invention and use scope bring any restrictions.
As shown in fig. 7, electronic equipment 30 can be showed in the form of universal computing device, such as it can set for server
It is standby.The component of electronic equipment 30 can include but is not limited to: at least one above-mentioned processor 31, above-mentioned at least one processor
32, the bus 33 of different system components (including memory 32 and processor 31) is connected.
Bus 33 includes data/address bus, address bus and control bus.
Memory 32 may include volatile memory, such as random access memory (RAM) 321 and/or cache
Memory 322 can further include read-only memory (ROM) 323.
Memory 32 can also include program/utility 325 with one group of (at least one) program module 324, this
The program module 324 of sample includes but is not limited to: operating system, one or more application program, other program modules and journey
It may include the realization of network environment in ordinal number evidence, each of these examples or certain combination.
Processor 31 by operation storage computer program in memory 32, thereby executing various function application and
The appraisal procedure of the health status of industrial equipment in data processing, such as the embodiment of the present invention 1 to 3 in any one embodiment.
Electronic equipment 30 can also be communicated with one or more external equipments 34 (such as keyboard, sensing equipment etc.).It is this
Communication can be carried out by input/output (I/O) interface 35.Also, the equipment 30 that model generates can also pass through Network adaptation
Device 36 and one or more network (such as local area network (LAN), wide area network (WAN) and/or public network, such as internet) logical
Letter.As shown in fig. 7, the other modules for the equipment 30 that network adapter 36 is generated by bus 33 and model communicate.It should be understood that
Although not shown in the drawings, the equipment 30 that can be generated with binding model uses other hardware and/or software module, including but unlimited
In: microcode, device driver, redundant processor, external disk drive array, RAID (disk array) system, magnetic tape drive
Device and data backup storage system etc..
It should be noted that although being referred to several units/modules or subelement/mould of electronic equipment in the above detailed description
Block, but it is this division be only exemplary it is not enforceable.In fact, embodiment according to the present invention, is retouched above
The feature and function for two or more units/modules stated can embody in a units/modules.Conversely, above description
A units/modules feature and function can with further division be embodied by multiple units/modules.
Embodiment 8
A kind of computer readable storage medium is present embodiments provided, computer program is stored thereon with, program is processed
The step in the appraisal procedure of the health status of the industrial equipment in embodiment 1 to 3 in any one embodiment is realized when device executes.
Wherein, what readable storage medium storing program for executing can use more specifically can include but is not limited to: portable disc, hard disk, random
Access memory, read-only memory, erasable programmable read only memory, light storage device, magnetic memory device or above-mentioned times
The suitable combination of meaning.
In possible embodiment, the present invention is also implemented as a kind of form of program product comprising program generation
Code, when program product is run on the terminal device, program code is appointed for executing terminal device in realization embodiment 1 to 3
Step in the appraisal procedure of the health status of industrial equipment in an embodiment of anticipating.
Wherein it is possible to be write with any combination of one or more programming languages for executing program of the invention
Code, program code can be executed fully on a user device, partly execute on a user device, is independent as one
Software package executes, part executes on a remote device or executes on a remote device completely on a user device for part.
Although specific embodiments of the present invention have been described above, it will be appreciated by those of skill in the art that these
It is merely illustrative of, protection scope of the present invention is defined by the appended claims.Those skilled in the art is not carrying on the back
Under the premise of from the principle and substance of the present invention, various changes or modifications can be made to these embodiments, but these are changed
Protection scope of the present invention is each fallen with modification.
Claims (18)
1. a kind of appraisal procedure of the health status of industrial equipment, which is characterized in that the appraisal procedure includes:
Obtain the corresponding historical operation code data of operation and the industry that industrial equipment executes in history set period of time
All historical parameter datas of the industrial equipment that sensor in equipment acquires in the history set period of time；
Wherein, the history set period of time includes multiple duty cycles；
A sensor is chosen as sensor of interest, respectively with the historical operation code data in multiple duty cycles
With all historical operating parameter data as input, adopted within the corresponding duty cycle with the sensor of interest
The history target operating parameters data of collection establish parametric prediction model as output；
Obtain the first operational parameter data that the sensor in the industrial equipment acquires within the goal-setting period and described
The corresponding first operation code data of the operation that industrial equipment executes within the goal-setting period；
Wherein, first operational parameter data includes the mesh that the sensor of interest acquires within the goal-setting period
Mark operational parameter data；
First operational parameter data and the first operation code data are input to the parametric prediction model, obtain institute
State the corresponding parameter prediction value of sensor of interest；
The industrial equipment according to the Bias of the target operating parameters data and the parameter prediction value is in the target
Health status in set period of time.
2. the appraisal procedure of the health status of industrial equipment as described in claim 1, which is characterized in that described respectively with multiple
The historical operation code data and all historical operating parameter data in the duty cycle is as input, with institute
It states the history target operating parameters data that sensor of interest acquires within the corresponding duty cycle and is used as output, establish parameter
The step of prediction model includes:
Coded treatment is carried out to the historical operation code data, obtains the corresponding operation code of the historical operation code data
Vector；
Made respectively with all historical operating parameter data of the operation code vector sum in multiple duty cycles
For input, using the history target operating parameters data that the sensor of interest acquires within the corresponding duty cycle as defeated
Out, parametric prediction model is established.
3. the appraisal procedure of the health status of industrial equipment as claimed in claim 2, which is characterized in that each work week
Phase, the corresponding historical operation code data constituted a state code sequence, and the history set period of time is corresponding multiple
The state code Sequence composition state code sequence library；
It is described that coded treatment is carried out to the historical operation code data, obtain the corresponding operation of the historical operation code data
The step of code vector includes:
The operation code data corresponding to each of the state code sequence library duty cycle carry out solely heat and compile
Code；
The operation code data after one-hot coding are input to Word2vec model and carry out coded treatment, obtain the operation
The corresponding operation code vector of code data.
4. the appraisal procedure of the health status of industrial equipment as described in claim 1, which is characterized in that described according to the mesh
Industrial equipment described in operational parameter data and the Bias of the parameter prediction value is marked within the goal-setting period
The step of health status includes:
Calculate the residual error between the target operating parameters data and the parameter prediction value；
Judge whether the residual error is more than given threshold, if being more than, it is determined that the industrial equipment is in unhealthy status；It is no
Then, determine that the industrial equipment is in health status.
5. the appraisal procedure of the health status of industrial equipment as claimed in claim 4, which is characterized in that described to calculate the mesh
Mark operational parameter data and the parameter prediction value between residual error the step of include:
Residual error between the target operating parameters data and the parameter prediction value is calculated using Pauta criterion.
6. the appraisal procedure of the health status of industrial equipment as described in claim 1, which is characterized in that described respectively with multiple
The historical operation code data and all historical operating parameter data in the duty cycle is as input, with institute
It states the history target operating parameters data that sensor of interest acquires within the corresponding duty cycle and is used as output, establish parameter
The step of prediction model includes:
Use linear regression algorithm or XGBoost algorithm respectively with the historical operation code number in multiple duty cycles
It is used as input according to all historical operating parameter data, with the sensor of interest within the corresponding duty cycle
The history target operating parameters data of acquisition establish parametric prediction model as output.
7. the appraisal procedure of the health status of industrial equipment as described in claim 1, which is characterized in that the acquisition industry is set
The standby sensor operated in corresponding historical operation code data and the industrial equipment executed in history set period of time
After the step of all historical operating parameter data acquired in the history set period of time further include:
Remove the exceptional value in the historical operating parameter data and the historical operation code data.
8. the appraisal procedure of the health status of industrial equipment as described in claim 1, which is characterized in that the acquisition industry is set
The standby sensor operated in corresponding historical operation code data and the industrial equipment executed in history set period of time
The step of all historical operating parameter data acquired in the history set period of time includes:
It is corresponding that the operation that industrial equipment executes in history set period of time is acquired respectively using different data collection systems
What the sensor in historical operation code data and the industrial equipment acquired in the history set period of time all goes through
History operational parameter data；
The corresponding historical operation code data of operation that is executed in history set period of time of industrial equipment and described of obtaining
The step of all historical operating parameter data that sensor in industrial equipment acquires in the history set period of time it
Afterwards further include:
The historical operating parameter data and the historical operation code data that the different data collection systems is acquired
Registration process is carried out according to timestamp；
It is described respectively with the historical operation code data and all history runs ginseng in multiple duty cycles
Number data are as input, the history target operating parameters number acquired within the corresponding duty cycle with the sensor of interest
Include: according to the step of as output, establishing parametric prediction model
Respectively with after middle registration process in multiple duty cycles the historical operation code data and it is all described in go through
History operational parameter data is as input, the history target fortune acquired within the corresponding duty cycle with the sensor of interest
Row supplemental characteristic establishes parametric prediction model as output.
9. a kind of assessment system of the health status of industrial equipment, which is characterized in that the assessment system includes that historical data obtains
Modulus block, parametric prediction model establish module, the first data acquisition module, parameter prediction value and obtain module and evaluation module；
The historical data obtains module and is used to obtain that operation that industrial equipment executes in history set period of time to be corresponding goes through
All history that sensor in history operation code data and the industrial equipment acquires in the history set period of time
Operational parameter data；
Wherein, the history set period of time includes multiple duty cycles；
The parametric prediction model establish module for choose a sensor as sensor of interest, respectively with multiple work
The historical operation code data and all historical operating parameter data in period is as input, with target biography
The history target operating parameters data that sensor acquires within the corresponding duty cycle establish parameter prediction mould as output
Type；
The sensor that first data acquisition module is used to obtain in the industrial equipment acquires within the goal-setting period
The first operational parameter data and corresponding first behaviour of the operation that is executed within the goal-setting period of the industrial equipment
Make code data；
Wherein, first operational parameter data includes the mesh that the sensor of interest acquires within the goal-setting period
Mark operational parameter data；
The parameter prediction value obtains module for first operational parameter data and the first operation code data is defeated
Enter to the parametric prediction model, obtains the corresponding parameter prediction value of the sensor of interest；
The evaluation module is used for the work according to the Bias of the target operating parameters data and the parameter prediction value
Health status of the industry equipment within the goal-setting period.
10. the assessment system of the health status of industrial equipment as claimed in claim 9, which is characterized in that the parameter prediction
Model building module includes operation code vector acquiring unit and model foundation unit；
The operation code vector acquiring unit is used to carry out coded treatment to the historical operation code data, goes through described in acquisition
The corresponding operation code vector of history operation code data；
The model foundation unit is for institutes all with the operation code vector sum in multiple duty cycles respectively
It states historical operating parameter data and is used as input, the history mesh acquired within the corresponding duty cycle with the sensor of interest
Operational parameter data is marked as output, establishes parametric prediction model.
11. the assessment system of the health status of industrial equipment as claimed in claim 10, which is characterized in that each work
Period, the corresponding historical operation code data constituted a state code sequence, and the history set period of time is corresponding more
A state code Sequence composition state code sequence library；
The operation code vector acquiring unit includes that one-hot coding subelement and code vector obtain subelement；
The one-hot coding subelement is for corresponding to each of the state code sequence library duty cycle described
Operation code data carry out one-hot coding；
The code vector obtains subelement and is used to the operation code data after one-hot coding being input to Word2vec mould
Type carries out coded treatment, obtains the corresponding operation code vector of the operation code data.
12. the assessment system of the health status of industrial equipment as claimed in claim 9, which is characterized in that the evaluation module
Including residual computations unit, judging unit and determination unit；
The residual computations unit is used to calculate the residual error between the target operating parameters data and the parameter prediction value；
The judging unit, if being more than, calls the determination unit true for judging whether the residual error is more than given threshold
The fixed industrial equipment is in unhealthy status；Otherwise, the determination unit is called to determine that the industrial equipment is in healthy shape
State.
13. the assessment system of the health status of industrial equipment as claimed in claim 12, which is characterized in that the residual computations
Unit is used to calculate the residual error between the target operating parameters data and the parameter prediction value using Pauta criterion.
14. the assessment system of the health status of industrial equipment as claimed in claim 9, which is characterized in that the prediction model
Module is established for using linear regression algorithm or XGBoost algorithm respectively with the history behaviour in multiple duty cycles
Make code data and all historical operating parameter data as input, with the sensor of interest in the corresponding work
Make the history target operating parameters data acquired in the period as output, establishes parametric prediction model.
15. the assessment system of the health status of industrial equipment as claimed in claim 9, which is characterized in that the assessment system
It further include outlier processing module；
The outlier processing is used to remove the exception in the historical operating parameter data and the historical operation code data
Value.
16. the assessment system of the health status of industrial equipment as claimed in claim 9, which is characterized in that the assessment system
It further include registration process module；
The historical data is obtained module and is used to be acquired industrial equipment respectively using different data collection systems in history setting
The sensor in operation corresponding historical operation code data and the industrial equipment executed in period is set in the history
All historical operating parameter data acquired in section of fixing time；
Historical operating parameter data that the registration process module is used to acquire the different data collection system and
The historical operation code data carries out registration process according to timestamp；
The parametric prediction model establishes module for respectively to go through described in after middle registration process in multiple duty cycles
History operation code data and all historical operating parameter data are as input, with the sensor of interest in corresponding institute
The history target operating parameters data acquired in the duty cycle are stated as output, establish parametric prediction model.
17. a kind of electronic equipment including memory, processor and stores the calculating that can be run on a memory and on a processor
Machine program, which is characterized in that the processor realizes industry of any of claims 1-8 when executing computer program
The appraisal procedure of the health status of equipment.
18. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of the appraisal procedure of the health status of industrial equipment of any of claims 1-8 is realized when being executed by processor
Suddenly.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910376003.8A CN110119339A (en) | 2019-05-07 | 2019-05-07 | Appraisal procedure, system, equipment and the storage medium of the health status of industrial equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910376003.8A CN110119339A (en) | 2019-05-07 | 2019-05-07 | Appraisal procedure, system, equipment and the storage medium of the health status of industrial equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110119339A true CN110119339A (en) | 2019-08-13 |
Family
ID=67520409
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910376003.8A Pending CN110119339A (en) | 2019-05-07 | 2019-05-07 | Appraisal procedure, system, equipment and the storage medium of the health status of industrial equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110119339A (en) |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110398375A (en) * | 2019-07-16 | 2019-11-01 | 广州亚美信息科技有限公司 | Monitoring method, device, equipment and the medium of cooling system of vehicle working condition |
| CN110471401A (en) * | 2019-08-30 | 2019-11-19 | 盈盛智创科技(广州)有限公司 | A kind of prediction technique, device and the equipment of transmission equipment exception |
| CN110569278A (en) * | 2019-08-21 | 2019-12-13 | 广西电网有限责任公司电力科学研究院 | transformer defect assessment method based on big data analysis |
| CN110728041A (en) * | 2019-09-27 | 2020-01-24 | 联想(北京)有限公司 | Information processing method and electronic equipment |
| CN111241159A (en) * | 2020-01-08 | 2020-06-05 | 山东汇贸电子口岸有限公司 | Method and device for determining task execution time |
| CN111750925A (en) * | 2019-12-24 | 2020-10-09 | 广州极飞科技有限公司 | Equipment aging prediction system, method and device |
| CN111829425A (en) * | 2020-08-06 | 2020-10-27 | 厦门航空有限公司 | Health monitoring method and system for civil aircraft leading edge position sensor |
| CN112001622A (en) * | 2020-08-21 | 2020-11-27 | 中国建设银行股份有限公司 | Health degree evaluation method, system, equipment and storage medium of cloud virtual gateway |
| CN112198857A (en) * | 2020-12-08 | 2021-01-08 | 浙江中自庆安新能源技术有限公司 | Industrial equipment control optimization method and system based on monitoring data |
| CN112557793A (en) * | 2020-12-04 | 2021-03-26 | 广东电网有限责任公司 | Power plug-in health state detection method and device and storage medium |
| CN112766576A (en) * | 2021-01-22 | 2021-05-07 | 无锡市第五人民医院 | Parameter result prediction method and system based on database |
| CN113359623A (en) * | 2021-05-08 | 2021-09-07 | 深圳有象智联科技有限公司 | Method and device for monitoring working state and computer readable storage medium |
| CN113419930A (en) * | 2021-04-09 | 2021-09-21 | 南京苏宁软件技术有限公司 | System health state prediction method and device, computer equipment and storage medium |
| CN113486584A (en) * | 2021-07-06 | 2021-10-08 | 新智数字科技有限公司 | Equipment fault prediction method and device, computer equipment and computer readable storage medium |
| CN113554247A (en) * | 2020-04-23 | 2021-10-26 | 北京京东乾石科技有限公司 | Method, device and system for evaluating running condition of automatic guided vehicle |
| CN113612650A (en) * | 2021-06-07 | 2021-11-05 | 北京东方通科技股份有限公司 | Monitoring method for edge computing equipment |
| CN113704582A (en) * | 2020-05-20 | 2021-11-26 | 阿里巴巴集团控股有限公司 | Commissioning effect analysis method, commissioning effect data processing method, commissioning effect analysis device, commissioning effect data processing device, commissioning effect equipment and storage medium |
| CN114800036A (en) * | 2022-06-24 | 2022-07-29 | 成都飞机工业（集团）有限责任公司 | Equipment health state assessment method |
| CN115034094A (en) * | 2022-08-10 | 2022-09-09 | 南通恒强轧辊有限公司 | Prediction method and system for operation state of metal processing machine tool |
| CN116086537A (en) * | 2023-02-08 | 2023-05-09 | 杭州安脉盛智能技术有限公司 | Equipment state monitoring method, device, equipment and storage medium |
| CN118263984A (en) * | 2024-05-31 | 2024-06-28 | 广东中兴电器开关股份有限公司 | Intelligent monitoring system and method for operation state of switch cabinet based on IEC61850 communication |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105134510A (en) * | 2015-09-18 | 2015-12-09 | 北京中恒博瑞数字电力科技有限公司 | State monitoring and failure diagnosis method for wind generating set variable pitch system |
| CN106951984A (en) * | 2017-02-28 | 2017-07-14 | 深圳市华傲数据技术有限公司 | A kind of dynamic analyzing and predicting method of system health degree and device |
| CN108510280A (en) * | 2018-03-23 | 2018-09-07 | 上海氪信信息技术有限公司 | A kind of financial fraud behavior prediction method based on mobile device behavioral data |
| CN108680358A (en) * | 2018-03-23 | 2018-10-19 | 河海大学 | A kind of Wind turbines failure prediction method based on bearing temperature model |
| CN109118384A (en) * | 2018-07-16 | 2019-01-01 | 湖南优利泰克自动化系统有限公司 | A kind of Wind turbines healthy early warning method |
| CN109710505A (en) * | 2019-01-02 | 2019-05-03 | 郑州云海信息技术有限公司 | A kind of disk failure prediction technique, device, terminal and storage medium |
-
2019
- 2019-05-07 CN CN201910376003.8A patent/CN110119339A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105134510A (en) * | 2015-09-18 | 2015-12-09 | 北京中恒博瑞数字电力科技有限公司 | State monitoring and failure diagnosis method for wind generating set variable pitch system |
| CN106951984A (en) * | 2017-02-28 | 2017-07-14 | 深圳市华傲数据技术有限公司 | A kind of dynamic analyzing and predicting method of system health degree and device |
| CN108510280A (en) * | 2018-03-23 | 2018-09-07 | 上海氪信信息技术有限公司 | A kind of financial fraud behavior prediction method based on mobile device behavioral data |
| CN108680358A (en) * | 2018-03-23 | 2018-10-19 | 河海大学 | A kind of Wind turbines failure prediction method based on bearing temperature model |
| CN109118384A (en) * | 2018-07-16 | 2019-01-01 | 湖南优利泰克自动化系统有限公司 | A kind of Wind turbines healthy early warning method |
| CN109710505A (en) * | 2019-01-02 | 2019-05-03 | 郑州云海信息技术有限公司 | A kind of disk failure prediction technique, device, terminal and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 张小桃 等: "电力经济与信息化管理", 郑州：黄河水利出版社, pages: 117 - 118 * |
Cited By (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110398375A (en) * | 2019-07-16 | 2019-11-01 | 广州亚美信息科技有限公司 | Monitoring method, device, equipment and the medium of cooling system of vehicle working condition |
| CN110569278A (en) * | 2019-08-21 | 2019-12-13 | 广西电网有限责任公司电力科学研究院 | transformer defect assessment method based on big data analysis |
| CN110471401B (en) * | 2019-08-30 | 2021-08-17 | 盈盛智创科技(广州)有限公司 | Method, device and equipment for predicting abnormity of transmission equipment |
| CN110471401A (en) * | 2019-08-30 | 2019-11-19 | 盈盛智创科技(广州)有限公司 | A kind of prediction technique, device and the equipment of transmission equipment exception |
| CN110728041A (en) * | 2019-09-27 | 2020-01-24 | 联想(北京)有限公司 | Information processing method and electronic equipment |
| CN111750925A (en) * | 2019-12-24 | 2020-10-09 | 广州极飞科技有限公司 | Equipment aging prediction system, method and device |
| CN111241159A (en) * | 2020-01-08 | 2020-06-05 | 山东汇贸电子口岸有限公司 | Method and device for determining task execution time |
| CN111241159B (en) * | 2020-01-08 | 2023-07-07 | 山东汇贸电子口岸有限公司 | Method and device for determining task execution time |
| CN113554247A (en) * | 2020-04-23 | 2021-10-26 | 北京京东乾石科技有限公司 | Method, device and system for evaluating running condition of automatic guided vehicle |
| CN113704582A (en) * | 2020-05-20 | 2021-11-26 | 阿里巴巴集团控股有限公司 | Commissioning effect analysis method, commissioning effect data processing method, commissioning effect analysis device, commissioning effect data processing device, commissioning effect equipment and storage medium |
| CN111829425A (en) * | 2020-08-06 | 2020-10-27 | 厦门航空有限公司 | Health monitoring method and system for civil aircraft leading edge position sensor |
| CN111829425B (en) * | 2020-08-06 | 2022-05-24 | 厦门航空有限公司 | Health monitoring method and system for civil aircraft leading edge position sensor |
| CN112001622A (en) * | 2020-08-21 | 2020-11-27 | 中国建设银行股份有限公司 | Health degree evaluation method, system, equipment and storage medium of cloud virtual gateway |
| CN112557793A (en) * | 2020-12-04 | 2021-03-26 | 广东电网有限责任公司 | Power plug-in health state detection method and device and storage medium |
| CN112198857A (en) * | 2020-12-08 | 2021-01-08 | 浙江中自庆安新能源技术有限公司 | Industrial equipment control optimization method and system based on monitoring data |
| CN112198857B (en) * | 2020-12-08 | 2021-03-02 | 浙江中自庆安新能源技术有限公司 | Industrial equipment control optimization method and system based on monitoring data |
| CN112766576A (en) * | 2021-01-22 | 2021-05-07 | 无锡市第五人民医院 | Parameter result prediction method and system based on database |
| CN113419930A (en) * | 2021-04-09 | 2021-09-21 | 南京苏宁软件技术有限公司 | System health state prediction method and device, computer equipment and storage medium |
| CN113419930B (en) * | 2021-04-09 | 2023-01-06 | 南京苏宁软件技术有限公司 | System health state prediction method and device, computer equipment and storage medium |
| CN113359623B (en) * | 2021-05-08 | 2022-08-23 | 深圳有象智联科技有限公司 | Method and device for monitoring working state and computer readable storage medium |
| CN113359623A (en) * | 2021-05-08 | 2021-09-07 | 深圳有象智联科技有限公司 | Method and device for monitoring working state and computer readable storage medium |
| CN113612650A (en) * | 2021-06-07 | 2021-11-05 | 北京东方通科技股份有限公司 | Monitoring method for edge computing equipment |
| CN113612650B (en) * | 2021-06-07 | 2022-09-30 | 北京东方通科技股份有限公司 | Monitoring method for edge computing equipment |
| CN113486584A (en) * | 2021-07-06 | 2021-10-08 | 新智数字科技有限公司 | Equipment fault prediction method and device, computer equipment and computer readable storage medium |
| CN113486584B (en) * | 2021-07-06 | 2023-12-29 | 新奥新智科技有限公司 | Method and device for predicting equipment failure, computer equipment and computer readable storage medium |
| CN114800036A (en) * | 2022-06-24 | 2022-07-29 | 成都飞机工业（集团）有限责任公司 | Equipment health state assessment method |
| CN115034094A (en) * | 2022-08-10 | 2022-09-09 | 南通恒强轧辊有限公司 | Prediction method and system for operation state of metal processing machine tool |
| CN116086537A (en) * | 2023-02-08 | 2023-05-09 | 杭州安脉盛智能技术有限公司 | Equipment state monitoring method, device, equipment and storage medium |
| CN118263984A (en) * | 2024-05-31 | 2024-06-28 | 广东中兴电器开关股份有限公司 | Intelligent monitoring system and method for operation state of switch cabinet based on IEC61850 communication |
| CN118263984B (en) * | 2024-05-31 | 2024-08-09 | 广东中兴电器开关股份有限公司 | Intelligent monitoring system and method for operation state of switch cabinet based on IEC61850 communication |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110119339A (en) | Appraisal procedure, system, equipment and the storage medium of the health status of industrial equipment | |
| Alaswad et al. | A review on condition-based maintenance optimization models for stochastically deteriorating system | |
| US10809704B2 (en) | Process performance issues and alarm notification using data analytics | |
| Kwiatkowska et al. | Prism: Probabilistic model checking for performance and reliability analysis | |
| US10521490B2 (en) | Equipment maintenance management system and equipment maintenance management method | |
| Jouin et al. | Prognostics of PEM fuel cell in a particle filtering framework | |
| CN111563606A (en) | Equipment predictive maintenance method and device | |
| Safiyullah et al. | Prediction on performance degradation and maintenance of centrifugal gas compressors using genetic programming | |
| CN111459700A (en) | Method and apparatus for diagnosing device failure, diagnostic device, and storage medium | |
| KR20180108446A (en) | System and method for management of ict infra | |
| CN107835964A (en) | Control situation and the reasoning on control | |
| CN104102773A (en) | Equipment fault warning and state monitoring method | |
| CA2471013A1 (en) | Method and system for analyzing and predicting the behavior of systems | |
| CN101999101B (en) | The defining method of system cloud gray model prediction | |
| CN101413991A (en) | Method and system for remotely predicting the remaining life of an AC motor system | |
| CN112254972B (en) | Excavator oil temperature early warning method and device, server and excavator | |
| Chen et al. | Real-time forecasting and visualization toolkit for multi-seasonal time series | |
| CN115964907A (en) | Complex system health trend prediction method and system, electronic device and storage medium | |
| Zhang et al. | A review of fault prognostics in condition based maintenance | |
| US8359577B2 (en) | Software health management testbed | |
| CN101719091A (en) | Method and monitoring system for the rule-based monitoring of a service-oriented architecture | |
| Borissova et al. | A concept of intelligent e-maintenance decision making system | |
| KR0169808B1 (en) | Fault diagonistic expert system and diagonistic method | |
| CN113348473A (en) | Installation foundation for managing artificial intelligence module | |
| Hao et al. | A review on fault prognostics in integrated health management |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190813 |
|
| RJ01 | Rejection of invention patent application after publication |