CN117540315A - Online diagnosis method for process industrial equipment system health degree - Google Patents
Online diagnosis method for process industrial equipment system health degree Download PDFInfo
- Publication number
- CN117540315A CN117540315A CN202311530634.3A CN202311530634A CN117540315A CN 117540315 A CN117540315 A CN 117540315A CN 202311530634 A CN202311530634 A CN 202311530634A CN 117540315 A CN117540315 A CN 117540315A
- Authority
- CN
- China
- Prior art keywords
- model
- data
- equipment
- evaluation
- analysis
- 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
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000003745 diagnosis Methods 0.000 title claims abstract description 34
- 230000008569 process Effects 0.000 title claims abstract description 21
- 230000036541 health Effects 0.000 title claims abstract description 18
- 230000005856 abnormality Effects 0.000 claims abstract description 22
- 238000011156 evaluation Methods 0.000 claims abstract description 18
- 230000002159 abnormal effect Effects 0.000 claims abstract description 16
- 238000013210 evaluation model Methods 0.000 claims abstract description 6
- 238000013135 deep learning Methods 0.000 claims abstract description 5
- 238000010219 correlation analysis Methods 0.000 claims abstract description 3
- 238000004458 analytical method Methods 0.000 claims description 13
- 238000007405 data analysis Methods 0.000 claims description 12
- 238000012417 linear regression Methods 0.000 claims description 10
- 238000002405 diagnostic procedure Methods 0.000 claims description 9
- 238000003062 neural network model Methods 0.000 claims description 7
- 230000007246 mechanism Effects 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 claims description 3
- 230000007547 defect Effects 0.000 abstract description 2
- 238000012544 monitoring process Methods 0.000 abstract description 2
- 238000012423 maintenance Methods 0.000 abstract 1
- 239000003921 oil Substances 0.000 description 8
- 229910052739 hydrogen Inorganic materials 0.000 description 6
- 239000001257 hydrogen Substances 0.000 description 6
- 239000003245 coal Substances 0.000 description 4
- UFHFLCQGNIYNRP-UHFFFAOYSA-N Hydrogen Chemical compound [H][H] UFHFLCQGNIYNRP-UHFFFAOYSA-N 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000012098 association analyses Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000011234 economic evaluation Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 239000010687 lubricating oil Substances 0.000 description 1
- 238000011418 maintenance treatment Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 239000010865 sewage Substances 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000011282 treatment Methods 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
- 239000002351 wastewater Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/27—Regression, e.g. linear or logistic regression
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C3/00—Registering or indicating the condition or the working of machines or other apparatus, other than vehicles
- G07C3/005—Registering or indicating the condition or the working of machines or other apparatus, other than vehicles during manufacturing process
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data
Abstract
The invention relates to the field of equipment monitoring methods, in particular to an online diagnosis method for the health degree of a process industrial equipment system, which comprises the steps of obtaining historical data of industrial equipment, wherein the historical data comprises equipment operation data; establishing a data identification prediction model based on the historical data, performing horizontal correlation analysis and longitudinal deep learning on the historical data based on the data identification prediction, and obtaining a predicted value of fault diagnosis; establishing an evaluation model, and performing evaluation scoring of fault diagnosis based on the predicted value and the acquired real-time operation parameters; the operating state of the device is determined based on the evaluation score, and the operating state with the abnormality is displayed. The invention avoids abnormal shutdown accidents, assists decision making and reminds maintenance personnel of actively eliminating defects.
Description
Technical Field
The invention relates to the field of equipment monitoring methods, in particular to an online diagnosis method for the health degree of a process industrial equipment system.
Background
The traditional thermal power plant mainly relies on people to monitor the state and parameters of equipment, operators monitor continuously-changed data for twenty-four hours, slow changes of parameters at the early period of equipment failure are difficult to discover, the slow changes can only be processed after an alarm appears, and the working pressure of the operators is high and the labor intensity is high; moreover, the thermal power generation operation work has extremely high requirements on professional skills of people, and only excellent operators can observe the abnormality of equipment in thousands of data, so that correct treatment can be performed in the early period of failure.
Based on the above problems, the prior literature discloses a power plant equipment abnormal state identification method based on intelligent deep learning, which comprises the steps of collecting power plant equipment data to obtain a total database; judging whether the grouping data of the total database is consistent with the characteristics of the normal state, if so, entering the normal state database, and if not, entering the abnormal state database; calculating the real-time data of the acquired equipment and two groups of data which are compared and compared with the normal state database and the abnormal state database by adopting Jaccard coefficients to compare and identify; and carrying out alarm reminding or inputting into a database according to the comparison result. The method solves the problems that the existing method is inconvenient to analyze in real time and broadcast and position the fault area according to the state data of the power plant equipment, and is low in accuracy and efficiency.
However, the method is based on real-time detection of the comparison and judgment of the data of the equipment and the normal data, and the data can be compared to the abnormality only when the equipment has generated the abnormality or the fault, so that the abnormality or the fault judgment of the equipment is delayed and untimely.
Disclosure of Invention
The invention aims to provide an online diagnosis method for the health degree of a process industrial equipment system, which aims to solve the problem of lagging fault diagnosis of the existing method.
The on-line diagnosis method for the health degree of the process industrial equipment system in the scheme comprises the following steps:
step 1, acquiring historical data of industrial equipment, wherein the historical data comprises equipment operation data;
step 2, establishing a data identification prediction model based on the historical data, performing horizontal correlation analysis and longitudinal deep learning on the historical data based on the data identification prediction, and obtaining a prediction value of fault diagnosis;
step 3, establishing an evaluation model, and performing evaluation scoring of fault diagnosis based on the predicted value and the acquired real-time operation parameters;
and 4, determining the operation state of the equipment based on the evaluation score, and displaying the abnormal operation state.
Further, in the step 2, the process of establishing the data identification prediction model includes a process analysis, a data analysis, an operation standard and an operation experience.
Further, the mechanism analysis is to calculate the characteristic value of the equipment, analyze the performance index of the equipment and select proper analysis variables according to the balance relation of the continuous series;
the data analysis is to establish a multi-dimensional, full-period and multi-angle data analysis principle, comprehensively and carefully analyze a large amount of data, analyze the data with relevance and select a proper data analysis model;
the operation standard is a standard for designing an abnormality diagnosis model, wherein the abnormality diagnosis model is supposed to have equipment operation specifications and operation regulations;
the operation experience can be used for intelligently debugging and maintaining the equipment according to the operation experience of the equipment in the model.
In step 2, the data identification prediction model includes a multiple linear regression model, a nonlinear state pre-estimated NXET model and a neural network model, and when on-line diagnosis is performed, any model is set according to the diagnosis requirement.
Further, the multiple linear regression model is used to form a relationship between a fault occurrence and a plurality of causes of the fault occurrence in the plant, assuming thatFor real-time prediction, x is an implementation-associated variable, and w is a weight vector, the multiple linear regression model can be expressed as:
。
further, the nonlinear state pre-estimated NXET model is configured to establish an evaluation index by using the similarity between each sample, and assuming that the vector of the prediction parameter is Y, the very easy matrix is D, and the weight vector is W, the model may be expressed as:
。
further, the neural network model is used for establishing the correlation which is originally existed between the variables and mainly based on the principle.
In step 3, an evaluation model is built by combining the real-time data, the predicted value and the HPI index, and evaluation scoring is performed.
Compared with the prior art, the beneficial effect of this scheme is:
according to the scheme, various models are built for the data of the power plant equipment, the relevance of faults and corresponding information is analyzed, fault diagnosis can be conducted through different models according to actual requirements, system faults which are not easy to find can be analyzed in advance, abnormal shutdown accidents are avoided, decision assistance and active defect elimination are achieved, and the management efficiency of the power plant is effectively improved.
Drawings
FIG. 1 is a block flow diagram of a first embodiment of an on-line diagnostic method for process plant system health of the present invention;
FIG. 2 is a diagram of a neural network model in a first embodiment of an on-line diagnostic method for process plant system health according to the present invention.
Detailed Description
Further details are provided below with reference to the specific embodiments.
Example 1
The on-line diagnosis method for the health degree of the process industrial equipment system is based on an Ovation system platform, reads real-time data in the power plant industry through Ovation PDS software, and comprises the following steps as shown in figure 1:
step 1, processing, classifying and cleaning the collected equipment operation data through existing deletion individual anomalies, and extracting to obtain equipment characteristic parameters to form corresponding historical data. Obtaining historical data of industrial equipment, wherein the historical data comprises equipment operation data, such as equipment operation data including temperature, pressure, displacement, vibration, circulating water temperature, active power of a generator, circulating water flow and the like, and the historical data is calculated according to 8: the scale of 2 is divided into a test set and a validation set for use by the subsequent model.
Step 2, respectively establishing a data identification prediction model based on a plurality of different parameters in historical data, for example, modeling exciting current-active power-hydrogen temperature-hydrogen pressure-hydrogen leakage quantity aiming at abnormal hydrogen pressure faults of a certain power plant, taking the hydrogen leakage rate with the unit of cubic meter as a prediction model, and representing as follows:
;
wherein V is the volume of the generator, per cubic meter, and is obtained by consulting the use instruction of the product;for local atmospheric pressure, continuously updating when calculating in real time; />The standard atmospheric pressure is adopted, and the value is 1MPa; />The initial pressure in the generator is expressed as MPa; />The internal termination pressure of the generator is expressed as MPa; />Taking the reference temperature as a reference temperature, and taking the value of 273.15K; />Stopping cold hydrogen temperature for the generator by a unit K; />The temperature is the ambient temperature, and is updated online in real time, and the unit is K.
The indexes of influencing machine equipment, such as coal mill equipment, are monitored, and data of motor current, lubricating oil temperature, inlet and outlet pressure of the coal mill, inlet and outlet temperature and the like are analyzed. And carrying out transverse association analysis on historical data based on data identification prediction, setting association analysis such as fan equipment, carrying out comprehensive analysis on fan current, inlet and outlet pressure, inlet and outlet flow, bearing temperature, oil station temperature and fan rotating speed to obtain whether the fan operates in an economic operation interval, setting characteristic influence coefficients according to operation experience and equipment mechanism analysis by using the established association data, and obtaining influence coefficients through longitudinal deep learning to obtain a model so as to obtain a predicted value of fault diagnosis. The data identification prediction model building process comprises a theory analysis, a data analysis, an operation standard and an operation experience.
The mechanism analysis is to confirm the characteristic value of the equipment according to the unit condition, such as calculation of pressure, temperature, performance and the like, analyze the performance index of the equipment, select proper analysis variables according to a continuous series of balance relations, for example, a certain characteristic reaches balance without abrupt change in a normal fluctuation range, namely, the balance relation, and take the balanced characteristic as the analysis variable.
The data analysis is to build a multi-dimensional, full-time-period and multi-angle data analysis principle, comprehensively and carefully analyze a large amount of data, analyze the data with relevance, and select a proper data analysis model, such as a neural network fitting model, a regression statistics model and the like.
The operation standard is a standard for designing an abnormality diagnosis model, wherein the abnormality diagnosis model is provided with equipment operation specifications and operation regulations, the equipment operation specifications and the operation regulations are set by a power plant for different equipment, for example, 1, the maximum oil level of a coal mill oil station cannot exceed 820mm, the minimum oil level cannot be lower than 450mm, and if the maximum oil level exceeds the range, the abnormality is judged. For example, 2, the temperature of the oil station cannot be suddenly changed, the temperature at the current time is T1, the temperature at the moment five seconds before is T2, and |T1-T2| <10 ℃ is required, and when the condition is not satisfied, the sudden change is indicated.
The running experience can intelligently debug and maintain the equipment according to the running experience of the equipment in the model, and the running experience is such as how the equipment is set in running conditions such as speed, temperature and the like under a certain public condition, so that the accuracy of fault early warning is improved, and the fault false alarm rate is reduced.
The data identification prediction model comprises a multiple linear regression model, a nonlinear state pre-estimated NXET model and a neural network model, and any model is set according to the diagnosis requirement to perform on-line diagnosis.
The multiple linear regression model is used to form a relationship between a fault current in the plant and a plurality of causes that cause the fault current, assumingFor real-time prediction, x is an implementation-associated variable, and w is a weight vector, the multiple linear regression model can be expressed as:
。
the polynomial fitting function is beneficial to analyzing the counted technology, is beneficial to better understanding, simulating and predicting data, is an effective way for fitting the statistical analysis technology into a mathematical model in the form of functions and the like, and is simple and practical, the current cause analysis of faults is carried out through a multiple linear regression model, most of diagnosis requirements can be solved, and the relationship among variables is convenient to understand.
The nonlinear state pre-estimated NXET model is used for establishing an evaluation index by utilizing the similarity among all samples, and assuming that the vector of the prediction parameter is Y, the extremely easy matrix is D and the weight vector is W, the model can be expressed as:
。
and the prediction based on the nonlinear state prediction NXET model has good universality and higher accuracy of a prediction result.
As shown in fig. 2, the neural network model is used for establishing the correlation originally existing between the variables, and the neural network has high prediction accuracy, and good stability and robustness.
And 3, establishing an evaluation model, performing evaluation scoring of fault diagnosis based on the predicted value and the acquired real-time operation parameters, wherein the unit scoring consists of safety evaluation, economic evaluation, deviation evaluation, fault early warning and reliability evaluation, and after the real-time data are combined and normalized according to the predicted model value, the data are 1 score according to 0.01, 100 score according to 1 and HPI index, and the evaluation scoring is performed. For example, 1, the normal operation range of the current blower bearing is 55-65 ℃, the current temperature is 68 ℃, the dangerous temperature of the blower bearing is more than 70 ℃, the bearing temperature is not directly affected, but a certain hidden danger exists, the safety score of the blower is reduced to 92 ℃, the safety score of a smoke system is affected, the health score of a unit is reduced, and an operator timely notifies maintenance treatment based on the score. After the model is iterated for a plurality of times, the prediction score is closer to the real situation of the equipment, and an operator can safely operate the equipment only by paying attention to the score.
And 4, determining the operation state of the equipment based on the evaluation score, and displaying the abnormal operation state.
According to the method, the fault diagnosis is carried out by establishing various prediction models according to actual demands and different models, faults of equipment operation can be diagnosed by combining the superiority of the various models, the advance and the accuracy of the fault diagnosis are greatly improved, the safety and the stability of the operation of the equipment of each unit are improved, the labor cost is reduced, the production efficiency of a power plant is improved, and the degree of stable and safe operation of the whole unit is improved.
Example two
The difference from the first embodiment is that in step 1, the maximum disturbance in the recent data of the unit may be prioritized, the history data further includes device management flow data, a single management flow in the device management flows is divided, and the single management flow and the possible abnormal operation of the devices are associated to form a comparison relationship, where the device management flow data is shown as a certain 14: and at the moment 10, performing power management operation of the wastewater lifting pump, opening management operation of a cold air adjusting door of the coal mill and the like, wherein the control relationship can cause blockage abnormality for the management operation of lifting pump flow increase of a sewage adding agent node.
And 5, when the evaluation scoring display equipment is abnormal in operation, acquiring corresponding equipment management flow data, judging the abnormal quantity of equipment operation abnormality corresponding to each single management flow, and when the abnormal quantity is greater than three, performing early warning sequencing by taking the single management flow with low direct action degree as the highest priority, and performing processing guidance by taking the early warning sequencing as an early warning prompt. For example, when the equipment operation abnormality is an OPC oil pressure abnormality, the equipment management flow data includes 1# high-pressure valve safety check adjustment, 2# high-pressure valve safety check adjustment, 5# high-pressure valve safety check adjustment, etc., wherein after the 2# high-pressure valve safety check adjustment is directly performed, the oil pressure is swayed between 122 bar and 134bar, and the 1# high-pressure valve safety check adjustment is used as an early warning prompt.
According to the embodiment, when the abnormality is marked, corresponding management flow data are obtained, equipment operation abnormality corresponding to a single management flow is corresponding, then a large number of abnormalities are used as trigger conditions, a target which can be processed preferentially can be intelligently discharged when more abnormalities occur in a short time, so that abnormal fault points caused by complex factors can be found out rapidly, abnormal diagnosis caused by other faults caused by linkage after the fault generation time is too long is prevented from being interfered and confused, the direct action degree of the equipment operation abnormality is judged according to the management flow, the equipment operation abnormality is ordered, early warning prompt is carried out according to the abnormal points, the fault can be rapidly detected and removed conveniently, and the safety operation degree of a unit is improved.
The foregoing is merely exemplary embodiments of the present invention, and specific structures and features that are well known in the art are not described in detail herein. It should be noted that modifications and improvements can be made by those skilled in the art without departing from the structure of the present invention, and these should also be considered as the scope of the present invention, which does not affect the effect of the implementation of the present invention and the utility of the patent. The protection scope of the present application shall be subject to the content of the claims, and the description of the specific embodiments and the like in the specification can be used for explaining the content of the claims.
Claims (8)
1. An on-line diagnosis method for the health degree of a process industrial equipment system is characterized by comprising the following steps:
step 1, acquiring historical data of industrial equipment, wherein the historical data comprises equipment operation data;
step 2, establishing a data identification prediction model based on the historical data, performing horizontal correlation analysis and longitudinal deep learning on the historical data based on the data identification prediction, and obtaining a prediction value of fault diagnosis;
step 3, establishing an evaluation model, and performing evaluation scoring of fault diagnosis based on the predicted value and the acquired real-time operation parameters;
and 4, determining the operation state of the equipment based on the evaluation score, and displaying the abnormal operation state.
2. The process industry equipment system health online diagnostic method of claim 1, wherein: in the step 2, the data identification prediction model building process comprises a theory analysis, a data analysis, an operation standard and an operation experience.
3. The process industry equipment system health online diagnostic method of claim 2, wherein: the mechanism analysis is to calculate the characteristic value of the equipment, analyze the performance index of the equipment and select proper analysis variables according to the balance relation of a continuous series;
the data analysis is to establish a multi-dimensional, full-period and multi-angle data analysis principle, comprehensively and carefully analyze a large amount of data, analyze the data with relevance and select a proper data analysis model;
the operation standard is a standard for designing an abnormality diagnosis model, wherein the abnormality diagnosis model is supposed to have equipment operation specifications and operation regulations;
the operation experience can be used for intelligently debugging and maintaining the equipment according to the operation experience of the equipment in the model.
4. A process industry equipment system health on-line diagnostic method as defined in claim 3, wherein: in the step 2, the data identification prediction model includes a multiple linear regression model, a nonlinear state pre-estimated NXET model and a neural network model, and any model is set according to the diagnosis requirement to perform on-line diagnosis.
5. The process industry equipment system health online diagnostic method of claim 4, wherein: the multiple linear regression model is used to form a relationship between a fault current in the plant and a plurality of causes that cause the fault current, assumingFor real-time prediction, x is the implementation-associated variable, and w is the weight vector, the multiple linear regression model can be expressed as:
。
6. the process industry equipment system health online diagnostic method of claim 5, wherein: the nonlinear state pre-estimated NXET model is used for establishing an evaluation index by utilizing the similarity among all samples, and assuming that the vector of the prediction parameter is Y, the extremely easy matrix is D and the weight vector is w, the model can be expressed as:
。
7. the process industry equipment system health online diagnostic method of claim 5, wherein: the neural network model is used for establishing the original relevance between the variables based on the main basis.
8. The process industry equipment system health online diagnostic method of claim 5, wherein: in the step 3, an evaluation model is established by combining the real-time data, the predicted value and the HPI index, and evaluation scoring is performed.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311530634.3A CN117540315A (en) | 2023-11-16 | 2023-11-16 | Online diagnosis method for process industrial equipment system health degree |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311530634.3A CN117540315A (en) | 2023-11-16 | 2023-11-16 | Online diagnosis method for process industrial equipment system health degree |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117540315A true CN117540315A (en) | 2024-02-09 |
Family
ID=89795241
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311530634.3A Pending CN117540315A (en) | 2023-11-16 | 2023-11-16 | Online diagnosis method for process industrial equipment system health degree |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117540315A (en) |
-
2023
- 2023-11-16 CN CN202311530634.3A patent/CN117540315A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104573850B (en) | A kind of Power Plant Equipment state evaluating method | |
CN109240244B (en) | Data-driven equipment running state health degree analysis method and system | |
CN110414155A (en) | A kind of detection of fan part temperature anomaly and alarm method with single measuring point | |
CN113705924B (en) | Intelligent diagnosis method and system for thermal control equipment | |
KR20140130540A (en) | Method and system for real-time performance recovery advisory for centrifugal compressors | |
WO2012149901A1 (en) | Similarity curve-based device malfunction early-warning and optimization method and system | |
GB2379752A (en) | Root cause analysis under conditions of uncertainty | |
CN114757380B (en) | Fault early warning system and method for thermal power plant, electronic equipment and storage medium | |
CN110469496B (en) | Intelligent early warning method and system for water pump | |
CN110209144B (en) | Two-layer real-time monitoring and alarm tracing method based on dynamic and static cooperative difference analysis | |
CH710737A2 (en) | System and method for detecting an anomaly in a combustion section of a gas turbine. | |
CN116184948A (en) | Intelligent monitoring disc for water plant and application system and method of early warning diagnosis technology | |
CN112685216A (en) | Equipment abnormity monitoring system and method based on trend analysis | |
CN112288298A (en) | Desulfurization system health condition evaluation method based on online data | |
CN116562739B (en) | Liquid chemical engineering wharf operation flow planning and dynamic monitoring system | |
CN110009126A (en) | The online alarm analysis method merged based on PLS model with PCA contribution degree | |
KR102108975B1 (en) | Apparatus and method for condition based maintenance support of naval ship equipment | |
CN116147878B (en) | Large-scale low-temperature wind tunnel safety interlocking method, device and storage medium | |
CN117540315A (en) | Online diagnosis method for process industrial equipment system health degree | |
CN116665401A (en) | Accident prevention alarm system for chemical production | |
CN116205622A (en) | Intelligent fault early warning and maintenance decision method for smoke machine equipment | |
CN113673600B (en) | Industrial signal abnormality early warning method, system, storage medium and computing device | |
CN103955182A (en) | Safe operation monitoring and instructing method | |
CN104731056B (en) | The method of the quick operation stability for judging chemical production device | |
CN116235121A (en) | Apparatus and method for identifying anomalies in industrial facilities for performing a production process |
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 |