CN116398414A - Monitoring alarm method and system for air compressor system - Google Patents
Monitoring alarm method and system for air compressor system Download PDFInfo
- Publication number
- CN116398414A CN116398414A CN202310181592.0A CN202310181592A CN116398414A CN 116398414 A CN116398414 A CN 116398414A CN 202310181592 A CN202310181592 A CN 202310181592A CN 116398414 A CN116398414 A CN 116398414A
- Authority
- CN
- China
- Prior art keywords
- variable
- monitoring
- variables
- air compressor
- alarm
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 188
- 238000000034 method Methods 0.000 title claims abstract description 69
- 238000012546 transfer Methods 0.000 claims abstract description 65
- 238000004458 analytical method Methods 0.000 claims abstract description 61
- 230000008569 process Effects 0.000 claims abstract description 35
- 238000000513 principal component analysis Methods 0.000 claims abstract description 30
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 26
- 239000011159 matrix material Substances 0.000 claims description 9
- 238000005070 sampling Methods 0.000 claims description 7
- 238000010219 correlation analysis Methods 0.000 claims description 6
- 230000001186 cumulative effect Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 6
- 238000005259 measurement Methods 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 2
- 239000003921 oil Substances 0.000 description 19
- 238000004519 manufacturing process Methods 0.000 description 18
- 238000010586 diagram Methods 0.000 description 13
- 230000008859 change Effects 0.000 description 7
- 238000007726 management method Methods 0.000 description 7
- 239000010725 compressor oil Substances 0.000 description 5
- 230000002159 abnormal effect Effects 0.000 description 4
- 230000001364 causal effect Effects 0.000 description 4
- 238000007906 compression Methods 0.000 description 4
- 230000006835 compression Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 239000007789 gas Substances 0.000 description 3
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 238000013329 compounding Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000011112 process operation Methods 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 230000001808 coupling effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013144 data compression Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 239000013067 intermediate product Substances 0.000 description 1
- 239000010687 lubricating oil Substances 0.000 description 1
- 229910052757 nitrogen Inorganic materials 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F04—POSITIVE - DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS FOR LIQUIDS OR ELASTIC FLUIDS
- F04B—POSITIVE-DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS
- F04B49/00—Control, e.g. of pump delivery, or pump pressure of, or safety measures for, machines, pumps, or pumping installations, not otherwise provided for, or of interest apart from, groups F04B1/00 - F04B47/00
- F04B49/06—Control using electricity
- F04B49/065—Control using electricity and making use of computers
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F04—POSITIVE - DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS FOR LIQUIDS OR ELASTIC FLUIDS
- F04B—POSITIVE-DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS
- F04B49/00—Control, e.g. of pump delivery, or pump pressure of, or safety measures for, machines, pumps, or pumping installations, not otherwise provided for, or of interest apart from, groups F04B1/00 - F04B47/00
- F04B49/10—Other safety measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Mechanical Engineering (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computing Systems (AREA)
- Evolutionary Biology (AREA)
- Operations Research (AREA)
- Probability & Statistics with Applications (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Geometry (AREA)
- Control Of Positive-Displacement Pumps (AREA)
Abstract
The invention relates to a monitoring alarm method and a system of an air compressor system, wherein the method comprises the following steps: acquiring historical data of a monitoring variable of an air compressor system, and dividing the monitoring variable into an oil system related variable, an electric system related variable and an air system related variable according to a subsystem to which the monitoring variable belongs; respectively carrying out process analysis on each subsystem to obtain an initial alarm propagation path of each subsystem monitoring variable; performing relevance analysis on historical data of the monitoring variable based on a transfer entropy analysis algorithm, and correcting the initial alarm path according to a relevance analysis result to obtain a final alarm propagation path; constructing a principal component analysis model according to the monitoring variable of the air compressor in normal state; and judging whether the current system has faults according to the principal component analysis model for the monitoring data at the current moment, if so, judging fault monitoring variables, and carrying out alarm prompt according to a final alarm propagation path.
Description
Technical Field
The invention relates to the technical field of air compressor monitoring and alarming, in particular to a monitoring and alarming method and a system of an air compressor system.
Background
The process monitoring achieves the goal of ensuring proper operation of the process by detecting, identifying and eliminating abnormal process features or behaviors. Therefore, process monitoring has become one of the key measures to effectively ensure safe and smooth operation of the flow industrial production process. For typical continuous flow industry, variable overrun caused by failure of an actuator and a sensor, failure of a control system component or abnormal equipment state is monitored by utilizing data of a distributed control system at present, and although the system has an abnormal alarm function, the instantaneous overrun disappears due to the action of the control system only according to whether input and output data exceeds a limit value, and the input and output are in causal relation due to the decision and control closed loop feedback action and the coupling action among units of the system, so that false alarm and abnormal tracing are easy to cause; for discrete industrial processes, the local operating state of critical process equipment is monitored primarily by single source feature parameters. The monitoring system ignores the related relation and causal relation of data, so that the monitoring result is unreliable and the whole process operation and the quality of intermediate products cannot be comprehensively monitored. The data-driven intelligent process monitoring scheme is based on the collection and analysis of process operation data, avoids a complex process reaction mechanism, has higher flexibility and universality, and is widely applied to the field of process monitoring in the process industry.
Alarm management is always the focus of operation attention of process devices, and many petrochemical accidents in the world are irrelevant to alarm management. Modern petrochemical production devices and auxiliary facilities alarm settings are numerous, alarm information frequently appears, pressure is caused for operators, important alarms are missed, unnecessary production loss is caused, and production safety is reduced. Therefore, an effective alarm strategy is formulated, and the setting of an alarm management system is a key measure for standardizing and improving the current state of alarm. The existing DCS control system is more important for alarm management, and a professional alarm management system is designed. The alarm management system collects, records, analyzes, manages and optimizes the alarm information of the process alarm and control system, and helps operators find problems occurring in the production process and the control system and process the problems in time. The alarm management system fully plays the functions of the alarm system and improves the production operation safety through the functions of alarm grouping, priority division, alarm adjustment, alarm filtering, alarm suppression, alarm information diagnosis and analysis and the like. In a complex and changeable working environment, the sudden fault treatment is solved in time, and the method is a primary condition for improving the working efficiency. In the actual factory production process, when a plurality of production lines work simultaneously, the whole production line and even the production process of the whole factory are affected due to the fact that a certain section of interval breaks down, so that the fault position cannot be accurately checked, the production period is delayed, the whole production line or the progress of the whole production is affected, the production efficiency is greatly reduced, and therefore, in order to accurately find the fault position, the waste of time is reduced, and the important problem of actual production is solved.
Disclosure of Invention
In view of the above analysis, the embodiment of the invention aims to provide a monitoring and alarming method and system of an air compressor system, which are used for solving the problems that the existing method and system can not accurately find the fault position and has low alarming efficiency.
In one aspect, an embodiment of the present invention provides a monitoring alarm method for an air compressor system, including the following steps:
acquiring historical data of a monitoring variable of an air compressor system, and dividing the monitoring variable into an oil system related variable, an electric system related variable and an air system related variable according to a subsystem to which the monitoring variable belongs;
respectively carrying out process analysis on each subsystem to obtain an initial alarm propagation path of each subsystem monitoring variable;
performing relevance analysis on historical data of the monitoring variable based on a transfer entropy analysis algorithm, and correcting the initial alarm path according to a relevance analysis result to obtain a final alarm propagation path;
constructing a principal component analysis model according to the monitoring variable of the air compressor in normal state; and judging whether the current system has faults according to the principal component analysis model for the monitoring data at the current moment, if so, judging fault monitoring variables, and carrying out alarm prompt according to a final alarm propagation path.
Based on the further improvement of the technical scheme, the relevance analysis of the monitoring variable based on the transfer entropy analysis algorithm comprises the following steps:
calculating the transfer relation of continuous variables in the monitoring variables in each subsystem based on a transfer entropy analysis algorithm to obtain the association relation of the monitoring variables in each subsystem;
and calculating the transfer relation of continuous variables in the monitoring variables among the subsystems based on a transfer entropy analysis algorithm to obtain the association relation of the monitoring variables among the subsystems.
Further, the transfer relationship is calculated for the monitored variables inside the subsystem in the following manner:
s301, sequencing the monitoring variables according to the sequence from the inlet to the outlet of the air compressor at the process position to obtain a monitoring variable sequence; taking the first monitoring variable in the monitoring variable sequence as a variable to be analyzed;
s302, sequentially taking the next monitored variable to the last monitored variable of the variables to be analyzed in the monitored variable sequence as a current variable, and calculating the transfer relationship between the variables to be analyzed and the current variable;
s303, if the variable to be analyzed is the last variable in the monitoring variable sequence, ending the analysis, otherwise, taking the next monitoring variable of the variable to be analyzed in the monitoring variable sequence as the variable to be analyzed, and returning to the step S302.
Further, the following formula is adopted to calculate the transfer relation t between the monitoring variables X→Y ：
t X→Y ＝t(x|y)-t(y|x)
Wherein x is i Representing the value of the variable x at the i-th moment, y i Representing the value of the variable y at the i-th moment, x i+1 Represents the value of the variable x, y at time i+1 i+1 Represents the value of the variable y at time i+1, P (x i+1 ,x i ,y i ) Represents x i+1 ,x i ,y i Is a joint probability of P (y) i+1 ,y i ,x i ) Representing y i+1 ,y i ,x i Is a joint probability of P (x) i+1 |x i ) Expressed under condition x i Lower x i+1 Probability of P (y) i+1 |y i ) Expressed under condition y i Lower y i+1 Probability of P (x) i ,y i ) Represents x i ,y i N represents the number of sampling points.
Further, the following method is adopted to construct a principal component analysis model according to the monitoring variable when the air compressor is normal:
carrying out standardization processing on the monitored variable sample data and calculating a covariance matrix;
calculating eigenvalues and corresponding eigenvectors of the covariance matrix;
and taking k eigenvalues and corresponding eigenvectors according to the cumulative variance percentage to construct a principal component analysis model.
Further, the monitoring data at the current moment judges whether the current system has faults according to the principal component analysis model, and the method comprises the following steps:
carrying out standardized processing on the monitoring data at the current moment;
according to
Calculating a square prediction error SPE, wherein X ij Measurement value representing the jth monitored variable at the ith moment,/->
A principal component model predicted value of a jth monitoring variable at an ith moment is represented;
if the square prediction error SPE is larger than a first threshold value, judging that the error exists in the current system.
On the other hand, the embodiment of the invention provides a monitoring alarm system of an air compressor system, which comprises the following modules:
the monitoring variable acquisition module is used for acquiring historical data of the monitoring variable of the air compressor system and dividing the monitoring variable into an oil system related variable, an electric system related variable and an air system related variable according to a subsystem to which the monitoring variable belongs;
the initial path determining module is used for respectively carrying out process analysis on each subsystem to obtain an initial alarm propagation path of each subsystem monitoring variable;
the final path determining module is used for carrying out relevance analysis on the historical data of the monitoring variable based on the transfer entropy analysis algorithm, and correcting the initial alarm path according to the relevance analysis result to obtain a final alarm propagation path;
the alarm module is used for constructing a principal component analysis model according to the monitoring variable when the air compressor is normal; and judging whether the current system has faults according to the principal component analysis model for the monitoring data at the current moment, if so, judging fault monitoring variables, and carrying out alarm prompt according to a final alarm propagation path.
Based on further improvement of the technical scheme, the final path determining module performs relevance analysis on the monitoring variable based on the transfer entropy analysis algorithm, and the method comprises the following steps:
calculating the transfer relation of continuous variables in the monitoring variables in each subsystem based on a transfer entropy analysis algorithm to obtain the association relation of the monitoring variables in each subsystem;
and calculating the transfer relation of continuous variables in the monitoring variables among the subsystems based on a transfer entropy analysis algorithm to obtain the association relation of the monitoring variables among the subsystems.
Further, the final path determination module calculates the transfer relationship for the monitored variables inside the subsystem in the following manner:
s301, sequencing the monitoring variables according to the sequence from the inlet to the outlet of the air compressor at the process position to obtain a monitoring variable sequence; taking the first monitoring variable in the monitoring variable sequence as a variable to be analyzed;
s302, sequentially taking the next monitored variable to the last monitored variable of the variables to be analyzed in the monitored variable sequence as a current variable, and calculating the transfer relationship between the variables to be analyzed and the current variable;
s303, if the variable to be analyzed is the last variable in the monitoring variable sequence, ending the analysis, otherwise, taking the next monitoring variable of the variable to be analyzed in the monitoring variable sequence as the variable to be analyzed, and returning to the step S302.
Further, the final path determination module calculates the transfer relationship t between the monitored variables using the following formula X→Y ：
t X→Y ＝t(x|y)-t(y|x)
Wherein x is i Representing the value of the variable x at the i-th moment, y i Indicating the ith time changeThe value of quantity y, x i+1 Represents the value of the variable x, y at time i+1 i+1 Represents the value of the variable y at time i+1, P (x i+1 ,x i ,y i ) Represents x i+1 ,x i ,y i Is a joint probability of P (y) i+1 ,y i ,x i ) Representing y i+1 ,y i ,x i Is a joint probability of P (x) i+1 |x i ) Expressed under condition x i Lower x i+1 Probability of P (y) i+1 |y i ) Expressed under condition y i Lower y i+1 Probability of P (x) i ,y i ) Represents x i ,y i N represents the number of sampling points.
Compared with the prior art, the method has the advantages that the initial alarm propagation path is constructed by analyzing the air compressor system, the alarm propagation path is corrected according to the correlation analysis result of the monitoring variable, the alarm propagation path in the process of more compounding actual operation can be obtained, the system can be timely alarmed through the principal component analysis model when faults exist, and the fault tracing prompt is carried out according to the alarm propagation path, so that an operator can conveniently and accurately find and locate the fault source in time, the fault repair is carried out in time, and the production efficiency is improved.
In the invention, the technical schemes can be mutually combined to realize more preferable combination schemes. Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention may be realized and attained by the structure particularly pointed out in the written description and drawings.
Drawings
The drawings are only for purposes of illustrating particular embodiments and are not to be construed as limiting the invention, like reference numerals being used to refer to like parts throughout the several views.
FIG. 1 is a flow chart of a monitoring alarm method of an air compressor system according to an embodiment of the present invention;
fig. 2 is a block diagram of a monitoring alarm system of the air compressor system according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of an air compressor mechanism according to an embodiment of the present invention;
fig. 4 is a schematic diagram of an alarm path of the 1# air compressor according to an embodiment of the present invention;
fig. 5 is a schematic diagram of an alarm path of the air compressor system according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of a transfer relationship according to an embodiment of the present invention.
Detailed Description
Preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings, which form a part hereof, and together with the description serve to explain the principles of the invention, and are not intended to limit the scope of the invention.
The invention discloses a monitoring alarm method of an air compressor system, which comprises the following steps as shown in fig. 1:
s1, acquiring historical data of a monitoring variable of an air compressor system, and dividing the monitoring variable into an oil system related variable, an electric system related variable and an air system related variable according to a subsystem to which the monitoring variable belongs;
s2, respectively carrying out process analysis on each subsystem to obtain an initial alarm propagation path of each subsystem monitoring variable;
s3, carrying out relevance analysis on historical data of the monitoring variable based on a transfer entropy analysis algorithm, and correcting the initial alarm path according to a relevance analysis result to obtain a final alarm propagation path;
s4, constructing a principal component analysis model according to the monitoring variable of the air compressor in normal state; and judging whether the current system has faults according to the principal component analysis model for the monitoring data at the current moment, if so, judging fault monitoring variables, and carrying out alarm prompt according to a final alarm propagation path.
According to the invention, an initial alarm propagation path is constructed by analyzing the air compressor system, and the alarm propagation path is corrected according to the correlation analysis result of the monitoring variable, so that the alarm propagation path in the process of more compounding actual operation can be obtained, and through the principal component analysis model, when the system has faults, the system can give an alarm in time, and the fault tracing prompt is carried out according to the alarm propagation path, so that an operator can conveniently and accurately find and locate the fault source in time, and carry out fault repair in time, and the production efficiency is improved.
When the method is implemented, the history and real-time data of the monitoring variables of the air compressor system can be obtained through the DCS.
In the implementation, the super HD-DCS system of three air compression stations of a certain oil refinery is taken as an example for explanation. The three air compression stations comprise 2 air compressors (1 # and 3# air compressors), 1 nitrogen compressor and 4 sets of drying systems. The invention is mainly used for monitoring, alarming and analyzing the air compressor.
The three-air compression system is formed by connecting a plurality of devices. The devices interact with each other and the internal variables of the devices are also related, as shown in fig. 3. The air compressor structure mainly comprises three parts, namely an oil system, a gas system and a motor system of the air compressor, which correspond to the oil machine equipment for storing and using lubricating oil in the air in the figure 3, and a three-stage impeller bearing is connected between the three sections of air compression pipelines and the sections of the air compressor. These are the basis for classifying and modeling of the variable subsystem in the air compressor. In order to facilitate accurate alarm path analysis, the air compressor subsystem is first divided into three subsystems, namely an oil system, an electric system and an air system. The monitored variables are divided into oil system related variables, electrical system related variables, and gas system related variables. The main monitoring variables of the air compressor are shown in table 1. Oil system related variables include 3, 4, 5, 7, 8, 21, electrical system related variables include 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, and gas system related variables include 1, 2, 6, 9, 10, 11, 12, 13, 22.
Table 1 partial monitoring variables for air compressor
| 1 | PT-101/1 | System pressure of No. 1 air compressor (Inlet) |
| 2 | PT-102/1 | Exhaust pressure (outlet) of No. 1 air compressor |
| 3 | PT-105/1 | 1# air compressor oil pressure (whether normal state at present) |
| 4 | PT-106/1 | Bearing oil pressure of No. 1 air compressor (whether normal state at present) |
| 5 | PT-108/1 | Front oil pressure of No. 1 air compressor filter (whether normal state at present) |
| 6 | PT-113/1 | Inlet air filter differential pressure of No. 1 air compressor (whether normal state at present) |
| 7 | PDI-108/1 | Differential pressure calculation of oil filter of No. 1 air compressor |
| 8 | TE-101/1 | 1# air compressor oil temperature (whether normal state at present) |
| 9 | TE-103/1 | Two-stage inlet temperature of 1# air compressor (whether normal state at present) |
| 10 | TE-104/1 | Three-section inlet temperature of 1# air compressor (whether normal state at present) |
| 11 | VT-110/1 | 1# air compressor one-section vibration (3 taking 2 judgment vibration) |
| 12 | VT-111/1 | Two-stage vibration of 1# air compressor (3 judgment vibration 2) |
| 13 | VT-112/1 | Three-section vibration of 1# air compressor (3 taking 2 judgment vibration) |
| 14 | YS-108/1 | Motor running signal (start and stop) 0-1 of No. 1 air compressor |
| 15 | IE-114/1 | Driving motor current of No. 1 air compressor |
| 16 | IY-114/1 | Surge control point of No. 1 air compressor (algorithm output point) |
| 17 | QY-114/1 | Surge count for 1# air compressor |
| 18 | UY-114/1 | Surge monitoring motor of No. 1 air compressor (Current) |
| 19 | HS-112/1 | Emergency stop (manual button) 0-1 of No. 1 air compressor |
| 20 | EI-100/1 | No. 1 air compressor voltage module 380v |
| 21 | LSL-102/1 | 1# air compressor oil level switch 0-1 |
| 22 | HV3011 | Filter outlet butterfly valve switch |
Variables related to the occurrence of air compressor surge faults include continuous variables 1, 2, 6, 11, 12, 13 and discrete variables 16 and 17; variables related to the temperature change of the air compressor include continuous variables 3, 4, 5, 8, 9, 10 and discrete variables 14 and 21;
the variables related to the pressure change inside the air compressor are continuous variables 1, 2, 6, 7 and discrete variables 19. The initial alarm propagation paths of the monitoring variables of the three subsystems in the air compressor based on the process experience knowledge analysis are as follows:
and an air compressor oil system: 21- & gt 3- & gt 8- & gt 5- & gt 7
Air compressor electromechanical system: 11-12-13-18-16-17; 19-20-14-15
Air compressor air system: 6- & gt 11- & gt 12- & gt 13; 6- & gt 1- & gt 2
After the initial alarm propagation path is established, the correlation analysis of the monitoring variable is carried out through the transfer entropy, and the initial alarm path is corrected.
Specifically, performing relevance analysis on the monitored variable based on the transfer entropy analysis algorithm includes:
calculating the transfer relation of continuous variables in the monitoring variables in each subsystem based on a transfer entropy analysis algorithm to obtain the association relation of the monitoring variables in each subsystem;
and calculating the transfer relation of continuous variables in the monitoring variables among the subsystems based on a transfer entropy analysis algorithm to obtain the association relation of the monitoring variables among the subsystems.
That is, the correlation analysis is performed inside the subsystem and between the subsystems, respectively.
Specifically, the monitored variables in the subsystem are calculated by the following ways:
s301, sequencing the monitoring variables according to the sequence from the inlet to the outlet of the air compressor at the process position to obtain a monitoring variable sequence; taking the first monitoring variable in the monitoring variable sequence as a variable to be analyzed;
s302, sequentially taking the next monitored variable to the last monitored variable of the variables to be analyzed in the monitored variable sequence as a current variable, and calculating the transfer relationship between the variables to be analyzed and the current variable;
s303, if the variable to be analyzed is the last variable in the monitoring variable sequence, ending the analysis, otherwise, taking the next monitoring variable of the variable to be analyzed in the monitoring variable sequence as the variable to be analyzed, and returning to the step S302.
And calculating the transfer relation of monitoring variables between all subsystems in pairs.
The transfer entropy is a method for obtaining causality between time sequences based on probability distribution and shannon entropy statistics. The transfer entropy indicates how much the amount of Y uncertainty is reduced for the present state by knowing the history of the source variable X and the history of the target variable Y, than from the history of Y alone. This information is asymmetric from Y to X and from X to Y, which gives rise to the establishment of a relation of drive and response.
Specifically, the following formula is used to calculate the transfer entropy between the monitored variables:
according to t X→Y Calculating the transfer relation between the monitored variables by using t (x|y) -t (y|x);
wherein x is i Representing the value of the variable x at the i-th moment, y i Represents the value of the variable y at the i-th moment, P (x i+1 ,x i ,y i ) Represents x i+1 ,x i ,y i Is a joint probability of P (x) i+1 |x i ) Represents conditional probability, P (x) i ,y i ) Represents x i ,y i N represents the number of sampling points.
Calculating the transfer relation between continuous variables in each monitored variable in and among the subsystems according to the calculation formula, if t X→Y And if the I is smaller than or equal to the second threshold value, considering that the variables x and y have no transmission relation, and if the direct connection between x and y exists in the initial alarm propagation path, deleting the connection. If |t X→Y I is greater than the second threshold, if t X→Y >0, the explanatory information is transferred from variable x to y, if t X→Y <0, the explanatory information is transmitted from the variable y to x, if there is no connection between the variable x and y in the initial alarm propagation path, the association relation is added, and if there is a connection with wrong direction, the connection direction is corrected.
When entropy relations are transferred among the computing variables, the transfer causal relations can be expressed in a chained propagation graph mode, for example, loop situations can exist for the multi-element time variables x, y and z, and paths with small transfer relations are removed according to the size of transfer relation values. For example, if t is the loop shown in FIG. 6 (a) X→Y And t Y→Z Are all greater than t X→Z The transfer relationship is corrected to fig. 6 (b).
On the basis of calculating the transfer entropy of the continuous variable, the influence of the discrete variable on the fault path propagation also needs to be considered, and in the actual industrial process, most of the discrete variable is used as a starting point or an end point of a process system. The discrete variables comprise alarm data such as switch variables, alarm points, alarm count statistics and the like which are acquired from a DCS system. The method specifically comprises the steps of including a plurality of switch variables in the air compressor process, evaluating the influence of the discrete variables on the continuous variables according to process knowledge, and adding the continuous variables into an alarm path diagram. For example, for discrete variable 22 (filter outlet butterfly valve switch), which has an effect on variable 6 (air compressor inlet air filter differential pressure) as assessed by process knowledge, it is added to the alarm path diagram.
The final alarm path propagation diagram of the whole 1# air compressor subsystem is shown in fig. 4, and as can be seen from fig. 4, the 1# air compressor alarm group consists of variables and alarm logic propagation relations among the variables. The oil level switch variable 21 controls signal transmission of the whole air compressor oil system and directly influences the oil pressure change 3 of the air compressor. On the basis, the oil temperature 8 of the air compressor, the oil pressure 5 before the air compressor is filtered, the differential pressure calculation 7 of the oil filter and the bearing oil pressure 4 are affected gradually. And the 4 variable can affect the second-stage inlet temperature 9 of the air compressor in the air system. The filter outlet butterfly valve from the air filter system regulates the air compressor inlet filter differential pressure 6, thereby affecting the air compressor system pressure 1, the air compressor outlet exhaust pressure 2. At the same time, the inlet differential pressure 6 of the air compressor also affects the second-section inlet temperature 9 and the third-section inlet temperature 10 of the air compressor, and further controls the inlet temperature and the outlet temperature of the air compressor cooler in the compressed air cooling system together with the outlet pressure of the air compressor. After the vibration influence is added, the inlet differential pressure 6 can also directly influence the first-stage vibration 11, the second-stage vibration 12 and the third-stage vibration 13 of the air compressor, and the vibration can trigger the influence of the system pressure 1. Finally, an additional surge detection motor unit of the air compressor is arranged, and a surge monitoring motor 18 and a surge control point 16 influence a surge count 17. The root variable of the surge counting monitoring is the outlet pressure 2 of the air compressor, and the change of the root variable directly reflects whether the air compressor has surge faults or not.
According to this method, the causal relationship propagation path diagram of other devices can be acquired as well. The propagation path subgraphs of the individual devices are linked according to process knowledge, which reflects the interrelationship between the devices. The fault propagation path diagram of the overall system is shown in fig. 5.
In practice, the fault propagation path diagram may be displayed on the DCS system.
After the fault propagation path diagram is obtained, judging whether the current system has faults according to the principal component analysis model, and carrying out estimation traceability reminding when the faults occur.
Principal component analysis, also called principal component analysis, is one of the methods commonly used in multivariate statistical analysis, and its basic method is to determine the dominant and subordinate positions of the change direction according to the variance of the data change, and obtain each principal element according to the dominant and subordinate sequence, where the principal elements are independent from each other. By means of the tool, change information can be refined, and complexity of data analysis is reduced. The method can project the high-dimensional data related to the multiple variables into the mutually independent low-dimensional data space, greatly reduces the difficulty of directly analyzing the multi-dimensional complex process variables, and can be used for realizing data simplification, data denoising, data compression, modeling, singular value detection and variable selection.
Specifically, the following method is adopted to construct a principal component analysis model according to the monitoring variable when the air compressor is normal:
s41, carrying out standardization processing on the monitored variable sample data and calculating a covariance matrix;
during implementation, the data of each monitoring variable stored in the DCS of the previous month of the No. 1 air compressor can be obtained, and standardized pretreatment is carried out on the data of the monitoring variable. In practice, invalid data may be removed, for example, if a variable has no data at a certain time, the variable is considered to be invalid data, and the data at the certain time is removed. For example, there are m monitoring variables in total, data of n sampling points are extracted, and the sample data is X n×m 。
Before calculating the covariance matrix, the data of each monitored variable is normalized, i.e. the value of each monitored variable is subtractedThe mean value of the monitored variable. The data thus processed all had a mean value of 0, and the normalized data were
Calculating normalized data
Covariance matrix>
S42, calculating eigenvalues and corresponding eigenvectors of the covariance matrix;
and calculating the eigenvalues and the corresponding eigenvectors of the covariance matrix, and sorting the eigenvalues and the corresponding eigenvectors according to the sizes of the eigenvalues.
S43, taking k eigenvalues and corresponding eigenvectors according to the cumulative variance percentage to construct a principal component analysis model.
The number of principal elements is determined from the cumulative variance percentage. Specifically, according to the formula
And calculating the cumulative variance percentage, and if the cumulative variance percentage of the first k eigenvalues is larger than a third threshold value, for example 90%, taking the first k eigenvalues and corresponding eigenvectors to construct a principal component analysis model. I.e. < ->
Wherein p is l Represents the ith feature vector, X i The monitoring data at the i-th time is indicated.
And after the principal component analysis model is established, judging whether the current system fails or not according to the monitoring variable value at the current moment.
Specifically, the monitoring data at the current moment judges whether the current system has faults according to the principal component analysis model, and the method comprises the following steps:
carrying out standardized processing on the monitoring data at the current moment; i.e. the value of each monitored variable at the current moment is subtracted by the mean value of that monitored variable.
According to
Calculating a square prediction error SPE, wherein X ij Measurement value representing the jth monitored variable at the ith moment,/->
A principal component model predicted value of a jth monitoring variable at an ith moment is represented;
wherein,,
according to the formula->
And (5) calculating to obtain the product.
If the square prediction error SPE is larger than a first threshold value, judging that the error exists in the current system.
In practice, the first threshold may be determined based on the accuracy of the system monitoring.
The SPE can judge whether the system has faults currently according to the square prediction error, and if the system has faults, the SPE needs to further judge which monitoring variable or monitoring variables have faults.
In practice, according to
And calculating the contribution degree of each monitoring variable as a fault, and regarding the contribution degree being larger than a fourth threshold value, treating the monitoring variable as a fault variable.
After the fault variable is obtained, fault tracing alarm reminding can be carried out according to the final alarm path diagram.
In one embodiment of the present invention, a monitoring alarm system of an air compressor system is disclosed, as shown in fig. 2, comprising the following modules:
the monitoring variable acquisition module is used for acquiring historical data of the monitoring variable of the air compressor system and dividing the monitoring variable into an oil system related variable, an electric system related variable and an air system related variable according to a subsystem to which the monitoring variable belongs;
the initial path determining module is used for respectively carrying out process analysis on each subsystem to obtain an initial alarm propagation path of each subsystem monitoring variable;
the final path determining module is used for carrying out relevance analysis on the historical data of the monitoring variable based on the transfer entropy analysis algorithm, and correcting the initial alarm path according to the relevance analysis result to obtain a final alarm propagation path;
the alarm module is used for constructing a principal component analysis model according to the monitoring variable when the air compressor is normal; and judging whether the current system has faults according to the principal component analysis model for the monitoring data at the current moment, if so, judging fault monitoring variables, and carrying out alarm prompt according to a final alarm propagation path.
Preferably, the final path determination module performs relevance analysis on the monitored variable based on a transfer entropy analysis algorithm, including:
calculating the transfer relation of continuous variables in the monitoring variables in each subsystem based on a transfer entropy analysis algorithm to obtain the association relation of the monitoring variables in each subsystem;
and calculating the transfer relation of continuous variables in the monitoring variables among the subsystems based on a transfer entropy analysis algorithm to obtain the association relation of the monitoring variables among the subsystems.
Preferably, the final path determination module calculates the transfer relationship for the monitored variables inside the subsystem in the following manner:
s301, sequencing the monitoring variables according to the sequence from the inlet to the outlet of the air compressor at the process position to obtain a monitoring variable sequence; taking the first monitoring variable in the monitoring variable sequence as a variable to be analyzed;
s302, sequentially taking the next monitored variable to the last monitored variable of the variables to be analyzed in the monitored variable sequence as a current variable, and calculating the transfer relationship between the variables to be analyzed and the current variable;
s303, if the variable to be analyzed is the last variable in the monitoring variable sequence, ending the analysis, otherwise, taking the next monitoring variable of the variable to be analyzed in the monitoring variable sequence as the variable to be analyzed, and returning to the step S302.
Preferably, the method comprises the steps of,the final path determination module calculates the transfer relationship t between the monitored variables using the following formula X→Y ：
t X→Y ＝t(x|y)-t(y|x)
Wherein x is i Representing the value of the variable x at the i-th moment, y i Representing the value of the variable y at the i-th moment, x i+1 Represents the value of the variable x, y at time i+1 i+1 Represents the value of the variable y at time i+1, P (x i+1 ,x i ,y i ) Represents x i+1 ,x i ,y i Is a joint probability of P (y) i+1 ,y i ,x i ) Representing y i+1 ,y i ,x i Is a joint probability of P (x) i+1 |x i ) Expressed under condition x i Lower x i+1 Probability of P (y) i+1 |y i ) Expressed under condition y i Lower y i+1 Probability of P (x) i ,y i ) Represents x i ,y i N represents the number of sampling points.
The method embodiment and the system embodiment are based on the same principle, and the related parts can be mutually referred to and can achieve the same technical effect. The specific implementation process refers to the foregoing embodiment, and will not be described herein.
Those skilled in the art will appreciate that all or part of the flow of the methods of the embodiments described above may be accomplished by way of a computer program to instruct associated hardware, where the program may be stored on a computer readable storage medium. Wherein the computer readable storage medium is a magnetic disk, an optical disk, a read-only memory or a random access memory, etc.
The present invention is not limited to the above-mentioned embodiments, and any changes or substitutions that can be easily understood by those skilled in the art within the technical scope of the present invention are intended to be included in the scope of the present invention.
Claims (10)
1. The monitoring and alarming method of the air compressor system is characterized by comprising the following steps of:
acquiring historical data of a monitoring variable of an air compressor system, and dividing the monitoring variable into an oil system related variable, an electric system related variable and an air system related variable according to a subsystem to which the monitoring variable belongs;
respectively carrying out process analysis on each subsystem to obtain an initial alarm propagation path of each subsystem monitoring variable;
performing relevance analysis on historical data of the monitoring variable based on a transfer entropy analysis algorithm, and correcting the initial alarm path according to a relevance analysis result to obtain a final alarm propagation path;
constructing a principal component analysis model according to the monitoring variable of the air compressor in normal state; and judging whether the current system has faults according to the principal component analysis model for the monitoring data at the current moment, if so, judging fault monitoring variables, and carrying out alarm prompt according to a final alarm propagation path.
2. The method of claim 1, wherein performing a correlation analysis on the monitored variable based on a transfer entropy analysis algorithm comprises:
calculating the transfer relation of continuous variables in the monitoring variables in each subsystem based on a transfer entropy analysis algorithm to obtain the association relation of the monitoring variables in each subsystem;
and calculating the transfer relation of continuous variables in the monitoring variables among the subsystems based on a transfer entropy analysis algorithm to obtain the association relation of the monitoring variables among the subsystems.
3. The monitoring alarm method of air compressor system according to claim 2, wherein the transmission relation is calculated by using the following method for monitoring variables in the subsystem:
s301, sequencing the monitoring variables according to the sequence from the inlet to the outlet of the air compressor at the process position to obtain a monitoring variable sequence; taking the first monitoring variable in the monitoring variable sequence as a variable to be analyzed;
s302, sequentially taking the next monitored variable to the last monitored variable of the variables to be analyzed in the monitored variable sequence as a current variable, and calculating the transfer relationship between the variables to be analyzed and the current variable;
s303, if the variable to be analyzed is the last variable in the monitoring variable sequence, ending the analysis, otherwise, taking the next monitoring variable of the variable to be analyzed in the monitoring variable sequence as the variable to be analyzed, and returning to the step S302.
4. The monitoring alarm method of air compressor system according to claim 2, wherein the following formula is adopted to calculate the transfer relation t between the monitored variables X→Y ：
t X→Y ＝t(x|y)-t(y|x)
Wherein x is i Representing the value of the variable x at the i-th moment, y i Representing the value of the variable y at the i-th moment, x i+1 Represents the value of the variable x, y at time i+1 i+1 Represents the value of the variable y at time i+1, P (x i+1 ,x i ,y i ) Represents x i+1 ,x i ,y i Is a joint probability of P (y) i+1 ,y i ,x i ) Representing y i+1 ,y i ,x i Is a joint probability of P (x) i+1 |x i ) Expressed under condition x i Lower x i+1 Probability of P (y) i+1 |y i ) Expressed under condition y i Lower y i+1 Probability of P (x) i ,y i ) Representation ofx i ,y i N represents the number of sampling points.
5. The monitoring alarm method of the air compressor system according to claim 1, wherein the principal component analysis model is constructed according to monitoring variables of the air compressor during normal conditions by adopting the following modes:
carrying out standardization processing on the monitored variable sample data and calculating a covariance matrix;
calculating eigenvalues and corresponding eigenvectors of the covariance matrix;
and taking k eigenvalues and corresponding eigenvectors according to the cumulative variance percentage to construct a principal component analysis model.
6. The monitoring alarm method of air compressor system according to claim 1, wherein the monitoring data at the current moment, according to the principal component analysis model, judges whether there is a fault in the current system, includes:
carrying out standardized processing on the monitoring data at the current moment;
according to
Calculating a square prediction error SPE, wherein X ij Measurement value representing the jth monitored variable at the ith moment,/->
A principal component model predicted value of a jth monitoring variable at an ith moment is represented;
if the square prediction error SPE is larger than a first threshold value, judging that the error exists in the current system.
7. The monitoring alarm system of the air compressor system is characterized by comprising the following modules:
the monitoring variable acquisition module is used for acquiring historical data of the monitoring variable of the air compressor system and dividing the monitoring variable into an oil system related variable, an electric system related variable and an air system related variable according to a subsystem to which the monitoring variable belongs;
the initial path determining module is used for respectively carrying out process analysis on each subsystem to obtain an initial alarm propagation path of each subsystem monitoring variable;
the final path determining module is used for carrying out relevance analysis on the historical data of the monitoring variable based on the transfer entropy analysis algorithm, and correcting the initial alarm path according to the relevance analysis result to obtain a final alarm propagation path;
the alarm module is used for constructing a principal component analysis model according to the monitoring variable when the air compressor is normal; and judging whether the current system has faults according to the principal component analysis model for the monitoring data at the current moment, if so, judging fault monitoring variables, and carrying out alarm prompt according to a final alarm propagation path.
8. The supervisory alarm system of claim 7, wherein the final path determination module performs a correlation analysis on the supervisory variables based on a transfer entropy analysis algorithm comprises:
calculating the transfer relation of continuous variables in the monitoring variables in each subsystem based on a transfer entropy analysis algorithm to obtain the association relation of the monitoring variables in each subsystem;
and calculating the transfer relation of continuous variables in the monitoring variables among the subsystems based on a transfer entropy analysis algorithm to obtain the association relation of the monitoring variables among the subsystems.
9. The supervisory alarm system of claim 8, wherein the final path determination module calculates the transfer relationship for the supervisory variables within the subsystem by:
s301, sequencing the monitoring variables according to the sequence from the inlet to the outlet of the air compressor at the process position to obtain a monitoring variable sequence; taking the first monitoring variable in the monitoring variable sequence as a variable to be analyzed;
s302, sequentially taking the next monitored variable to the last monitored variable of the variables to be analyzed in the monitored variable sequence as a current variable, and calculating the transfer relationship between the variables to be analyzed and the current variable;
s303, if the variable to be analyzed is the last variable in the monitoring variable sequence, ending the analysis, otherwise, taking the next monitoring variable of the variable to be analyzed in the monitoring variable sequence as the variable to be analyzed, and returning to the step S302.
10. The monitoring alarm system of claim 8 wherein the final path determination module calculates the transfer relationship t between the monitored variables using the formula X→Y ：
t X→Y ＝t(x|y)-t(y|x)
Wherein x is i Representing the value of the variable x at the i-th moment, y i Representing the value of the variable y at the i-th moment, x i+1 Represents the value of the variable x, y at time i+1 i+1 Represents the value of the variable y at time i+1, P (x i+1 ,x i ,y i ) Represents x i+1 ,x i ,y i Is a joint probability of P (y) i+1 ,y i ,x i ) Representing y i+1 ,y i ,x i Is a joint probability of P (x) i+1 |x i ) Expressed under condition x i Lower x i+1 Probability of P (y) i+1 |y i ) Expressed under condition y i Lower y i+1 Probability of P (x) i ,y i ) Represents x i ,y i N represents the number of sampling points.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310181592.0A CN116398414A (en) | 2023-02-20 | 2023-02-20 | Monitoring alarm method and system for air compressor system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310181592.0A CN116398414A (en) | 2023-02-20 | 2023-02-20 | Monitoring alarm method and system for air compressor system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116398414A true CN116398414A (en) | 2023-07-07 |
Family
ID=87016842
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310181592.0A Pending CN116398414A (en) | 2023-02-20 | 2023-02-20 | Monitoring alarm method and system for air compressor system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116398414A (en) |
-
2023
- 2023-02-20 CN CN202310181592.0A patent/CN116398414A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109240244B (en) | Data-driven equipment running state health degree analysis method and system | |
| US7702401B2 (en) | System for preserving and displaying process control data associated with an abnormal situation | |
| JP5364265B2 (en) | Apparatus and method for abnormal event detection in continuous industrial process operation | |
| JP4762088B2 (en) | Process abnormality diagnosis device | |
| EP2519895B1 (en) | Method and apparatus for monitoring performance and anticipate failures of plant instrumentation | |
| JP2010506331A (en) | Defect detection method and system in manufacturing plant | |
| JP5025776B2 (en) | Abnormality diagnosis filter generator | |
| EP3055747A1 (en) | Correlation and annotation of time series data sequences to extracted or existing discrete data | |
| US20160239755A1 (en) | Correlation and annotation of time series data sequences to extracted or existing discrete data | |
| CN110209144B (en) | Two-layer real-time monitoring and alarm tracing method based on dynamic and static cooperative difference analysis | |
| CN112306036B (en) | Method for diagnosing operation fault of chemical process | |
| CN112598144A (en) | CNN-LSTM burst fault early warning method based on correlation analysis | |
| EP4113539A1 (en) | Method and system for intelligent monitoring of state of nuclear power plant | |
| CN114237167A (en) | Anomaly monitoring system and method in industrial production process | |
| KR102140532B1 (en) | Method for Failure Detecting in Air Compressor based on big data | |
| CN115717590A (en) | Intelligent abnormity detection method for compressor and related device | |
| CN117662445B (en) | Nitrogen compressor operation control method and system | |
| TW202142815A (en) | Monitoring method of cool system and monitoring device thereof | |
| CN114519382A (en) | Nuclear power plant key operation parameter extraction and abnormity monitoring method | |
| TWI841756B (en) | Vacuum system with diagnostic circuitry and a method and computer program for monitoring the health of such a vacuum system | |
| CN116398414A (en) | Monitoring alarm method and system for air compressor system | |
| KR102108975B1 (en) | Apparatus and method for condition based maintenance support of naval ship equipment | |
| WO2018037541A1 (en) | Equipment malfunction diagnostic device and malfunction diagnostic method | |
| CN113919225B (en) | Environmental test box reliability assessment method and system | |
| CN112306035B (en) | Diagnostic system for operation fault of chemical 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 |