CN111753396A - Desulfurization and denitrification circulating pump fault diagnosis method based on mechanism-data driving model - Google Patents
Desulfurization and denitrification circulating pump fault diagnosis method based on mechanism-data driving model Download PDFInfo
- Publication number
- CN111753396A CN111753396A CN202010443401.XA CN202010443401A CN111753396A CN 111753396 A CN111753396 A CN 111753396A CN 202010443401 A CN202010443401 A CN 202010443401A CN 111753396 A CN111753396 A CN 111753396A
- Authority
- CN
- China
- Prior art keywords
- data
- desulfurization
- circulating pump
- denitrification
- denitrification circulating
- 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
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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01D—SEPARATION
- B01D53/00—Separation of gases or vapours; Recovering vapours of volatile solvents from gases; Chemical or biological purification of waste gases, e.g. engine exhaust gases, smoke, fumes, flue gases, aerosols
- B01D53/34—Chemical or biological purification of waste gases
- B01D53/46—Removing components of defined structure
- B01D53/60—Simultaneously removing sulfur oxides and nitrogen oxides
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01D—SEPARATION
- B01D53/00—Separation of gases or vapours; Recovering vapours of volatile solvents from gases; Chemical or biological purification of waste gases, e.g. engine exhaust gases, smoke, fumes, flue gases, aerosols
- B01D53/34—Chemical or biological purification of waste gases
- B01D53/74—General processes for purification of waste gases; Apparatus or devices specially adapted therefor
- B01D53/80—Semi-solid phase processes, i.e. by using slurries
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01D—SEPARATION
- B01D2258/00—Sources of waste gases
- B01D2258/02—Other waste gases
- B01D2258/0283—Flue gases
Abstract
The invention discloses a desulfurization and denitrification circulating pump fault diagnosis method based on a mechanism-data driving model, which belongs to the technical field of desulfurization and denitrification fault analysis and comprises the following steps: s1: acquiring relevant data of single key part faults and state parameters of the desulfurization and denitrification circulating pump by an experimental method, and establishing a mechanism type model for the parallel data; s2: establishing a data driving model for a multi-part of the desulfurization and denitrification circulating pump by using a data driving machine learning algorithm; s3: and carrying out fault diagnosis on the desulfurization and denitrification circulating pump by utilizing the mechanism model and the data driving model. According to the mechanism type model and the data driving model, the health state of the desulfurization and denitrification circulating pump can be accurately predicted, and a worker can timely judge whether the desulfurization and denitrification circulating pump needs to be expanded for maintenance, so that the economic loss of the desulfurization and denitrification circulating pump when the desulfurization and denitrification circulating pump is failed is avoided.
Description
Technical Field
The invention relates to the technical field of desulfurization and denitrification fault analysis, in particular to a desulfurization and denitrification circulating pump fault diagnosis method based on a mechanism-data driving model.
Background
The pollution of sulfur and nitrate to the environment is large, and the method is the key point of the current environment protection work. A large amount of sulfur and nitrate can be generated in the production flow of a thermal power plant, and if the sulfur and nitrate is not treated, the environment is greatly damaged, so that the desulfurization and denitrification equipment is generally used in the current power industry.
The desulfurization and denitrification circulating pump can achieve the desulfurization and denitrification effect by repeatedly contacting the absorbent slurry in the absorption tower with the flue gas. The SOx/NOx control circulating pump trouble is a common problem, but, in the middle of the failure diagnosis of current SOx/NOx control circulating pump, can't carry out real-time supervision to the health condition of SOx/NOx control circulating pump, can only be through carrying out the regular maintenance to SOx/NOx control circulating pump, or when SOx/NOx control circulating pump breaks down, just maintains the SOx/NOx control circulating pump. Obviously, if the SOx/NOx control circulating pump breaks down, the maintenance is untimely and will cause very big economic loss for the SOx/NOx control circulating pump.
Therefore, the problem to be solved by the technical personnel in the field needs to be solved urgently, and how to provide a better fault diagnosis method for the desulfurization and denitrification circulating pump so as to reduce the economic loss of the desulfurization and denitrification circulating pump when the desulfurization and denitrification circulating pump fails.
Disclosure of Invention
The invention aims to provide a fault diagnosis method of a desulfurization and denitrification circulating pump based on a mechanism-data driving model, so as to solve the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme: the method for diagnosing the fault of the desulfurization and denitrification circulating pump based on the mechanism-data driving model comprises the following steps of:
s1: acquiring relevant data of single key part faults and state parameters of the desulfurization and denitrification circulating pump by an experimental method, and establishing a mechanism type model for the parallel data;
s2: establishing a data driving model for a multi-part of the desulfurization and denitrification circulating pump by using a data driving machine learning algorithm;
s3: and carrying out fault diagnosis on the desulfurization and denitrification circulating pump by utilizing the mechanism model and the data driving model.
Preferably, the process of diagnosing the fault of the desulfurization and denitrification circulating pump by using the mechanism model and the data-driven model includes:
and monitoring and analyzing the health state of the desulfurization and denitrification circulating pump by using the mechanism model and the data driving model, and recording monitoring information to a log.
Preferably, after the process of diagnosing the malfunction of the desulfurization and denitrification circulation pump by using the mechanistic model and the data-driven model, the method further includes:
preferably, the operation data of the desulfurization and denitrification circulating pump is acquired;
judging whether fault data with unknown reasons exist in the operation data;
if so, analyzing the fault data of the unknown reasons by using an expert system to obtain analysis data, and recording the analysis data to a preset database.
Preferably, if so, after the process of analyzing the fault data of the unknown cause by using an expert system to obtain analysis data and recording the analysis data to a preset database, the method further includes:
judging whether fault data with a clear reason exist in the analysis data;
if so, acquiring a fault diagnosis result corresponding to the fault data with the definite reason, and recording the fault diagnosis result to the log.
Preferably, the establishing of the data-driven model for the multi-part component of the desulfurization and denitrification circulating pump by using the data-driven machine learning algorithm includes:
respectively acquiring first data and second data of a multi-part component of the desulfurization and denitrification circulating pump in a standard operation state and a daily operation state;
comparing the first data with the second data to obtain comparison data;
based on the data-driven machine learning algorithm, establishing a data-driven model for the desulfurization and denitrification circulating pump by using the comparison data
Preferably, the step of comparing the first data with the second data to obtain comparison data includes:
respectively acquiring a first data curve and a second data curve corresponding to the first data and the second data;
determining the degree of correlation and the degree of deviation of the first data curve and the second data curve by using the correlation coefficient and the deviation coefficient to obtain the comparison data:
wherein the expression of the correlation coefficient is:
in the formula, ρxyIs the correlation coefficient, x is the first data curve, y is the second data curve, d (x) is the variance of the first data curve, d (y) is the variance of the second data curve;
the expression of the deviation coefficient is:
in the formula (d)xyIs the distance, Y, of the first data curve from the second data curvekIs the value of the first data curve at time point k, XkIs the value of the second data curve at time point k.
Preferably, the process of respectively acquiring a first data curve and a second data curve corresponding to the first data and the second data includes:
judging whether a vacancy value occurs in the first data and the second data or not;
if so, respectively acquiring the first data curve and the second data curve corresponding to the first data and the second data by using a difference algorithm.
Preferably, the process of acquiring the associated data of the fault and the state parameter of the single key part of the desulfurization and denitrification circulating pump by using the experimental method and establishing the mechanism type model for the parallel data comprises the following steps:
attaching data acquisition equipment to a single key part of the desulfurization and denitrification circulating pump, and numbering the equipment;
acquiring relevant data of the faults and state parameters of the single key parts of the desulfurization and denitrification circulating pump through data acquisition equipment;
and constructing the single key part mechanism model by using the associated data on an MATLAB platform, wherein the single key part comprises but is not limited to: a shaft and a mechanical bearing.
Compared with the prior art, the invention has the beneficial effects that: according to the method, firstly, a desulfurization and denitrification circulating pump is modeled according to the working mechanism of the desulfurization and denitrification circulating pump to obtain a mechanism model, then a data driving model is built for multi-part parts of the desulfurization and denitrification circulating pump by using a data-driven machine learning algorithm, and finally the created mechanism model and the data driving model are used for carrying out fault diagnosis on the desulfurization and denitrification circulating pump. Obviously, in the invention, because the health state of the desulfurization and denitrification circulating pump can be accurately predicted according to the mechanism model and the data driving model, the staff can timely judge whether the desulfurization and denitrification circulating pump needs to be expanded and maintained, thereby avoiding the economic loss of the desulfurization and denitrification circulating pump when the desulfurization and denitrification circulating pump is in failure.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of a method for diagnosing a malfunction of a SOx/NOx circulating pump based on a mechanism-data driven model according to an embodiment of the present invention;
FIG. 2 is a flowchart of a method for diagnosing a malfunction of a SOx/NOx control circulation pump based on a mechanism-data driven model according to an embodiment of the present invention;
fig. 3 is a flowchart of a method for diagnosing a malfunction of a denitration and desulfurization circulation pump based on a mechanism-data driven model according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-3, the present invention provides a technical solution: the method for diagnosing the fault of the desulfurization and denitrification circulating pump based on the mechanism-data driving model comprises the following steps of:
s1: acquiring relevant data of single key part faults and state parameters of the desulfurization and denitrification circulating pump by an experimental method, and establishing a mechanism type model for the parallel data;
it should be noted that, in this embodiment, the data acquisition device is attached to a single key part of the desulfurization and denitrification circulating pump, and the data acquisition device is numbered; acquiring relevant data of the faults and state parameters of the single key parts of the desulfurization and denitrification circulating pump through data acquisition equipment; and constructing a single key part mechanism model by using the associated data on an MATLAB platform, wherein the single key part comprises but is not limited to: a shaft and a mechanical bearing.
It can be thought that, when SOx/NOx control circulating pump was in normal operating condition, SOx/NOx control circulating pump's operating condition can be fixed unchangeable, but, when single part broke down in SOx/NOx control circulating pump, can lead to SOx/NOx control circulating pump to be in the fault state, at this moment, just can build single key part mechanism model with the associated data of gathering when breaking down on MATLAB platform. This can be achieved in part by the prior art.
S2: establishing a data driving model for a multi-part of the desulfurization and denitrification circulating pump by using a data-driven machine learning algorithm;
according to actual conditions, when the desulfurization and denitrification circulating pump is in a normal operation state, the multi-part component of the desulfurization and denitrification circulating pump can operate within a certain operation parameter range, but if the multi-part component in the desulfurization and denitrification circulating pump is damaged or the desulfurization and denitrification circulating pump is in a fault state due to some uncontrollable factors, the operation parameters of the multi-part component in the desulfurization and denitrification circulating pump are bound to be out of the preset operation parameter range.
Therefore, in the embodiment, data information of a large number of multi-part components of the desulfurization and denitrification circulating pump in normal operation state and fault state is collected and obtained by using a data-driven machine learning algorithm, and then a data-driven model of the desulfurization and denitrification circulating pump is created and obtained by using the collected data information. And then, the established data driving model is utilized to judge whether the desulfurization and denitrification circulating pump is in a failure state.
S3: and (4) utilizing a mechanism type model and a data driving model to carry out fault diagnosis on the desulfurization and denitrification circulating pump.
It can be understood that when the mechanism model and the data driving model of the desulfurization and denitrification circulating pump are obtained, the health state of the desulfurization and denitrification circulating pump is evaluated, and thus the desulfurization and denitrification circulating pump is subjected to health management.
If the desulfurization and denitrification circulating pump is in a fault state, the worker can also maintain the desulfurization and denitrification circulating pump according to fault information provided by the mechanism model and the data driving model; in addition, the staff can also utilize mechanism type model and data drive model to come to prejudge the health status of SOx/NOx control circulating pump to make the staff in time know SOx/NOx control circulating pump's trouble severity. Obviously, by the method, the probability of safety accidents sent by the desulfurization and denitrification circulating pump is reduced, and the safety performance of the desulfurization and denitrification circulating pump in the operation process can be greatly improved.
In this embodiment, firstly, a model is built for the desulfurization and denitrification circulating pump according to the working mechanism of the desulfurization and denitrification circulating pump to obtain a mechanism model; and finally, carrying out health management on the desulfurization and denitrification circulating pump by using the established mechanism model and the data driving model. Obviously, in this embodiment, because the health status of the desulfurization and denitrification circulating pump can be accurately predicted according to the mechanism type model and the data driving model, the staff can timely judge whether the desulfurization and denitrification circulating pump needs to be maintained, so that the economic loss of the desulfurization and denitrification circulating pump when the desulfurization and denitrification circulating pump breaks down is avoided.
Based on the above embodiments, this embodiment further describes and optimizes the technical solution, specifically the above steps
The process of utilizing the mechanism type model and the data driving model to carry out fault diagnosis on the desulfurization and denitrification circulating pump comprises the following steps:
and monitoring and analyzing the health state of the desulfurization and denitrification circulating pump by using a mechanism type model and a data driving model, and recording monitoring information to a log.
It can be understood that after the mechanism model and the data driving model of the desulfurization and denitrification circulating pump are created, the mechanism model and the data driving model can be used for carrying out health management on the desulfurization and denitrification circulating pump, that is, the created mechanism model and the created data driving model can be used for detecting the health state of the desulfurization and denitrification circulating pump, judging the fault state of the desulfurization and denitrification circulating pump, and determining the fault state information of the desulfurization and denitrification circulating pump by using the mechanism model and the data driving model.
In addition, when the monitoring information of the desulfurization and denitrification circulating pump is acquired by using the mechanism model and the data driving model, the monitoring information can be stored in the log, so that when the desulfurization and denitrification circulating pump fails or is abnormal, the reason why the desulfurization and denitrification circulating pump fails or is abnormal can be analyzed according to the monitoring information stored in the log, and the working efficiency of workers is further improved.
Based on the above embodiments, the present embodiment further describes and optimizes the technical solution, and as shown in fig. 2, the present embodiment is a flowchart of a method for diagnosing a fault of a desulfurization and denitrification circulating pump based on a mechanism-data driven model according to an embodiment of the present invention.
After the process of utilizing the mechanism type model and the data driving model to carry out fault diagnosis on the desulfurization and denitrification circulating pump, the method further comprises the following steps:
acquiring operation data of a desulfurization and denitrification circulating pump;
judging whether fault data with unknown reasons exist in the operation data;
if so, analyzing the fault data of unknown reasons by using an expert system to obtain analysis data, and recording the analysis data to a preset database.
In this embodiment, in order to analyze the operation state of the desulfurization and denitrification circulating pump more comprehensively and accurately, after the process of health management of the desulfurization and denitrification circulating pump can be performed by using the mechanism model and the data driving model, the operation data of the desulfurization and denitrification circulating pump is obtained, and whether fault data of unknown reasons of the desulfurization and denitrification circulating pump exists in the operation data is judged, if fault data of unknown reasons exists in the operation data of the desulfurization and denitrification circulating pump, the fault data of unknown reasons can be analyzed by using a pre-established expert system, that is, the reason why the desulfurization and denitrification circulating pump is abnormal is analyzed by using the expert system, so as to obtain analysis data. And then, the analysis data is recorded into a preset database, so that a worker can analyze the fault reason of the desulfurization and denitrification circulating pump according to the data information stored in the preset database.
It should be noted that the expert system is an expert in the field of the desulfurization and denitrification circulating pump, and the expert knowledge and experience are utilized to reason and judge the fault data of unknown reasons in the desulfurization and denitrification circulating pump so as to solve the practical problem.
Obviously, when the expert system is used for analyzing the fault data with unknown reasons and recording the analysis data to the preset database, the fault reasons of the desulfurization and denitrification circulating pump stored in the preset database can be more comprehensive and detailed, and in addition, the operating state of the desulfurization and denitrification circulating pump can be better predicted and analyzed by using the data in the preset database by a worker.
Correspondingly, if, utilize expert system to carry out the analysis to the fault data of unknown reason, obtain the analytic data to behind the process of will analyzing data record to predetermineeing the database, still include:
judging whether fault data with a clear reason exist in the analysis data;
if so, acquiring a fault diagnosis result corresponding to the fault data with the clear reason, and recording the fault diagnosis result to a log.
It is conceivable that, if there is failure data of a clear cause in the analysis data, at this time, the failure diagnosis result corresponding to the failure data of the clear cause is recorded into the log. Therefore, if the fault data occur again in the subsequent operation process of the desulfurization and denitrification circulating pump, the working personnel can more accurately and quickly analyze and predict the operation state of the desulfurization and denitrification circulating pump according to the data stored in the log.
Based on the above embodiments, the present embodiment further describes and optimizes the technical solution, and as shown in fig. 3, the present embodiment is a flowchart of a method for diagnosing a fault of a desulfurization and denitrification circulating pump based on a mechanism-data driven model according to an embodiment of the present invention.
The method for establishing the data driving model for the multi-part of the desulfurization and denitrification circulating pump by using the data-driven machine learning algorithm comprises the following steps:
respectively acquiring first data and second data of a multi-part component of the desulfurization and denitrification circulating pump in a standard operation state and a daily operation state;
comparing the first data with the second data to obtain comparison data;
and establishing a data driving model for the desulfurization and denitrification circulating pump by using the comparison data based on a data-driven machine learning algorithm.
It can be understood that, when SOx/NOx control circulating pump is in different running state, SOx/NOx control circulating pump's operating data can demonstrate different trend of change, in other words, SOx/NOx control circulating pump can demonstrate different trend of change under standard running state and the daily running state, so, can judge whether SOx/NOx control circulating pump is in the fault condition according to SOx/NOx control circulating pump trend of change under the running state.
In addition, in the machine learning theory, only sample data and a sample label corresponding to the sample data need to be input into the created machine model, and the data result of the sample to be detected can be inferred by using the machine learning theory. Therefore, in the present embodiment, a machine learning model is first created based on a machine learning theory, and then, the first data and the second data of the desulfurization and denitrification circulating pump in the standard operation state and the abnormal operation state are input into the machine learning model, that is, in the process, the first data corresponds to sample data, and the second data corresponds to a sample tag corresponding to the sample data.
And finally, modeling the desulfurization and denitrification circulating pump by using the comparison data based on a machine learning theory to obtain a data driving model. It is conceivable that, after the data-driven model is created, the health condition of the desulfurization and denitrification circulating pump in the operating state can be detected by using the data-driven model.
Therefore, based on a machine learning theory, the first data and the second data of the desulfurization and denitrification circulating pump in the standard running state and the daily running state are used for creating the data driving model, so that the created data driving model has higher reliability, and the judgment result is more accurate.
Based on the above embodiments, the present embodiment further describes and optimizes the technical solution,
a process for comparing first data with second data to obtain comparison data, comprising:
respectively acquiring a first data curve and a second data curve corresponding to the first data and the second data;
determining the degree of correlation and the degree of deviation of the first data curve and the second data curve by using the correlation coefficient and the deviation coefficient to obtain comparison data:
wherein, the expression of the correlation coefficient is:
in the formula, ρxyIs a correlation coefficient, x is a first data curve, y is a second data curve, D (x) is a variance of the first data curve, and D (y) is a variance of the second data curve;
the expression of the deviation factor is:
in the formula (d)xyIs the distance, Y, between the first data curve and the second data curvekIs the value of the first data curve at time point k, XkThe value of the second data curve at time point k.
It can be understood that the SOx/NOx control circulating pump can present different trend under the running state of difference, so, in this embodiment, compare SOx/NOx control circulating pump data curve under standard running state with SOx/NOx control circulating pump data curve under daily running state, judge the running state of SOx/NOx control circulating pump.
Specifically, in the present embodiment, first, a first data curve and a second data curve corresponding to first data and second data are acquired, respectively, and the correlation coefficient ρ is usedxyThe degree of correlation of the first data curve and the second data curve is calculated.
Note that, in the present embodiment, the correlation coefficient ρ isxyHas a value range of [ -1,1 [)]I.e. when the correlation coefficient pxyWhen the correlation coefficient is 1, the first data curve and the second data curve are completely correlated, and the correlation coefficient rho isxyAt-1, the representative first data curve and the second data curve are completely uncorrelated.
It is conceivable if only the correlation coefficient ρ is utilizedxyTo determine whether the operation state of the desulfurization and denitrification circulating pump is a normal operation state, and erroneous determination is likely to occur, therefore, in this embodiment, the deviation coefficient d may also be usedxyThe deviation degree between the first data curve and the second data curve is calculated to further judge whether the desulfurization and denitrification circulating pump is in a normal operation state.
Specifically, if the calculated correlation degree between the first data curve and the second data curve is low and the deviation degree between the first data curve and the second data curve is too large, or the correlation degree between the first data curve and the second data curve is high and the deviation degree between the first data curve and the second data curve is large, the second data curve is the data curve acquired when the desulfurization and denitrification circulating pump is in the fault state.
When the calculated correlation coefficient rhoxy< 0.9991 and/or a deviation factor dxyIf the running state of the desulfurization and denitrification circulating pump is more than 49, the running state of the desulfurization and denitrification circulating pump can be judged to be a fault state; when the first data curve and the second data are obtained by calculationPhase relation ρ of the curvexyNot less than 0.9991, and a coefficient of deviation dxyAnd when the temperature is less than or equal to 49 ℃, judging that the running state of the desulfurization and denitrification circulating pump is a normal running state.
It should be noted that the calculated values of the correlation coefficient and the deviation coefficient are related to the experimental environment and the amount of data, so that only one reference value is provided in this embodiment, and in actual application, the values of the correlation coefficient and the deviation coefficient may be adaptively adjusted according to the specific situation in the actual application, which is not described herein in detail.
Obviously, in the present embodiment, the correlation coefficient ρ is calculatedxyAnd coefficient of deviation dxyWhether the desulfurization and denitrification circulating pump is in a normal operation state or not is judged, so that the judgment result of the desulfurization and denitrification circulating pump is more accurate and reliable.
Based on the above embodiments, the present embodiment further describes and optimizes the technical solution,
a process for obtaining first and second data curves corresponding to first and second data, respectively, comprising:
judging whether the first data and the second data have vacancy values or not;
and if so, respectively acquiring a first data curve and a second data curve corresponding to the first data and the second data by using a difference algorithm.
It can be understood that when the first data and the second data of the desulfurization and denitrification circulating pump in the standard operation state and the daily operation state are obtained, the first data and/or the second data may be lost for some reasons, so that the reliability of the statistical result is poor.
In this embodiment, in order to avoid this situation, when it is determined that the null value occurs in the first data and the second data, the interpolation algorithm is used to fill the null value in the first data and/or the second data, so as to obtain the first data curve and the second data curve corresponding to the first data and the second data. It is conceivable that, in this way, not only the first data curve and the second data curve can be made smoother, but also the reliability of the first data curve and the second data curve can be made higher, thereby further improving the accuracy of the health management result of the desulfurization and denitrification circulating pump.
In the description herein, references to the description of "one embodiment," "an example," "a specific example" or the like are intended to mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The preferred embodiments of the invention disclosed above are intended to be illustrative only. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise forms disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best utilize the invention. The invention is limited only by the claims and their full scope and equivalents.
Claims (8)
1. The desulfurization and denitrification circulating pump fault diagnosis method based on the mechanism-data driving model is characterized by comprising the following steps of: the method comprises the following steps:
s1: acquiring relevant data of single key part faults and state parameters of the desulfurization and denitrification circulating pump by an experimental method, and establishing a mechanism type model for the parallel data;
s2: establishing a data driving model for a multi-part of the desulfurization and denitrification circulating pump by using a data driving machine learning algorithm;
s3: and carrying out fault diagnosis on the desulfurization and denitrification circulating pump by utilizing the mechanism model and the data driving model.
2. The desulfurization and denitrification circulating pump fault diagnosis method based on the mechanism-data driving model as claimed in claim 1, characterized in that: the process of performing fault diagnosis on the desulfurization and denitrification circulating pump by using the mechanism model and the data driving model comprises the following steps:
and monitoring and analyzing the health state of the desulfurization and denitrification circulating pump by using the mechanism model and the data driving model, and recording monitoring information to a log.
3. The desulfurization and denitrification circulating pump fault diagnosis method based on the mechanism-data driving model as claimed in claim 1, characterized in that: after the process of performing fault diagnosis on the desulfurization and denitrification circulating pump by using the mechanism model and the data driving model, the method further comprises the following steps:
acquiring operation data of the desulfurization and denitrification circulating pump;
judging whether fault data with unknown reasons exist in the operation data;
if so, analyzing the fault data of the unknown reasons by using an expert system to obtain analysis data, and recording the analysis data to a preset database.
4. The desulfurization and denitrification circulating pump fault diagnosis method based on the mechanism-data driving model as claimed in claim 3, characterized in that: if yes, analyzing the fault data of the unknown reasons by using an expert system to obtain analysis data, and recording the analysis data to a preset database, wherein the method further comprises the following steps:
judging whether fault data with a clear reason exist in the analysis data;
if so, acquiring a fault diagnosis result corresponding to the fault data with the definite reason, and recording the fault diagnosis result to the log.
5. The method for diagnosing the fault of the desulfurization and denitrification circulating pump based on the mechanism-data driving model according to any one of claims 1 to 4, characterized in that: the method for establishing the data driving model for the multi-part of the desulfurization and denitrification circulating pump by using the data-driven machine learning algorithm comprises the following steps:
respectively acquiring first data and second data of a multi-part component of the desulfurization and denitrification circulating pump in a standard operation state and a daily operation state;
comparing the first data with the second data to obtain comparison data;
and establishing a data driving model for the desulfurization and denitrification circulating pump by using the comparison data based on the data-driven machine learning algorithm.
6. The desulfurization and denitrification circulating pump fault diagnosis method based on the mechanism-data driving model as claimed in claim 5, characterized in that: the process of comparing the first data with the second data to obtain comparison data includes:
respectively acquiring a first data curve and a second data curve corresponding to the first data and the second data;
determining the degree of correlation and the degree of deviation of the first data curve and the second data curve by using the correlation coefficient and the deviation coefficient to obtain the comparison data:
wherein the expression of the correlation coefficient is:
in the formula, ρxyIs the correlation coefficient, x is the first data curve, y is the second data curve, d (x) is the variance of the first data curve, d (y) is the variance of the second data curve;
the expression of the deviation coefficient is:
in the formula (d)xyIs the first data curve and the second data curveDistance of two data curves, YkIs the value of the first data curve at time point k, XkIs the value of the second data curve at time point k.
7. The desulfurization and denitrification circulating pump fault diagnosis method based on the mechanism-data driving model as claimed in claim 6, characterized in that: the process of respectively acquiring a first data curve and a second data curve corresponding to the first data and the second data includes:
judging whether a vacancy value occurs in the first data and the second data or not;
if so, respectively acquiring the first data curve and the second data curve corresponding to the first data and the second data by using a difference algorithm.
8. The desulfurization and denitrification circulating pump fault diagnosis method based on the mechanism-data driving model as claimed in claim 1, characterized in that: the process of acquiring the associated data of the faults and the state parameters of the single key parts of the desulfurization and denitrification circulating pump by the experimental method and establishing a mechanism type model for the parallel data comprises the following steps:
attaching data acquisition equipment to a single key part of the desulfurization and denitrification circulating pump, and numbering the equipment;
acquiring relevant data of the faults and state parameters of the single key parts of the desulfurization and denitrification circulating pump through data acquisition equipment;
and constructing the single key part mechanism model by using the associated data on an MATLAB platform, wherein the single key part comprises but is not limited to: a shaft and a mechanical bearing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010443401.XA CN111753396A (en) | 2020-05-22 | 2020-05-22 | Desulfurization and denitrification circulating pump fault diagnosis method based on mechanism-data driving model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010443401.XA CN111753396A (en) | 2020-05-22 | 2020-05-22 | Desulfurization and denitrification circulating pump fault diagnosis method based on mechanism-data driving model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111753396A true CN111753396A (en) | 2020-10-09 |
Family
ID=72673614
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010443401.XA Pending CN111753396A (en) | 2020-05-22 | 2020-05-22 | Desulfurization and denitrification circulating pump fault diagnosis method based on mechanism-data driving model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111753396A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117434910A (en) * | 2023-12-20 | 2024-01-23 | 沧州中铁装备制造材料有限公司 | Intelligent operation control system of power plant denitration agent supply pump based on Internet of things |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003036321A (en) * | 2001-07-24 | 2003-02-07 | Nikkiso Co Ltd | Method and device for abnormality diagnosis of pump for liquefied gas |
| EP1298511A1 (en) * | 2001-09-27 | 2003-04-02 | Reliance Electric Technologies, LLC | Motorized system integrated control and diagnostics using vibration, pressure, temperature, speed, and/or current analysis |
| CN101807045A (en) * | 2010-04-02 | 2010-08-18 | 杭州电子科技大学 | Data-based urban sewage pumping station system modeling method |
| CN109033930A (en) * | 2018-05-07 | 2018-12-18 | 北京化工大学 | Mechanical equipment fault diagnosis method based on fault mechanism and statistical model online learning |
| CN109240244A (en) * | 2018-10-26 | 2019-01-18 | 云达世纪（北京）科技有限公司 | Equipment running status health degree analysis method and system based on data-driven |
| CN109754490A (en) * | 2019-01-15 | 2019-05-14 | 中车株洲电力机车有限公司 | Health control method, device, medium and the equipment of brake system of electric locomotive |
-
2020
- 2020-05-22 CN CN202010443401.XA patent/CN111753396A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003036321A (en) * | 2001-07-24 | 2003-02-07 | Nikkiso Co Ltd | Method and device for abnormality diagnosis of pump for liquefied gas |
| EP1298511A1 (en) * | 2001-09-27 | 2003-04-02 | Reliance Electric Technologies, LLC | Motorized system integrated control and diagnostics using vibration, pressure, temperature, speed, and/or current analysis |
| CN101807045A (en) * | 2010-04-02 | 2010-08-18 | 杭州电子科技大学 | Data-based urban sewage pumping station system modeling method |
| CN109033930A (en) * | 2018-05-07 | 2018-12-18 | 北京化工大学 | Mechanical equipment fault diagnosis method based on fault mechanism and statistical model online learning |
| CN109240244A (en) * | 2018-10-26 | 2019-01-18 | 云达世纪（北京）科技有限公司 | Equipment running status health degree analysis method and system based on data-driven |
| CN109754490A (en) * | 2019-01-15 | 2019-05-14 | 中车株洲电力机车有限公司 | Health control method, device, medium and the equipment of brake system of electric locomotive |
Non-Patent Citations (1)
| Title |
|---|
| 陈朝旭等: "基于数据的复杂工程系统故障预测", 《上海应用技术学院学报》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117434910A (en) * | 2023-12-20 | 2024-01-23 | 沧州中铁装备制造材料有限公司 | Intelligent operation control system of power plant denitration agent supply pump based on Internet of things |
| CN117434910B (en) * | 2023-12-20 | 2024-03-01 | 沧州中铁装备制造材料有限公司 | Intelligent operation control system of power plant denitration agent supply pump based on Internet of things |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101470426B (en) | Fault detection method and system | |
| EP3105644B1 (en) | Method of identifying anomalies | |
| CN104390657A (en) | Generator set operating parameter measuring sensor fault diagnosis method and system | |
| CN116645010B (en) | Chemical industry safety in production inspection system | |
| CN112801313A (en) | Fully mechanized mining face fault judgment method based on big data technology | |
| CN114862275B (en) | Storage logistics system reliability assessment method and system based on digital twin model | |
| CN111753396A (en) | Desulfurization and denitrification circulating pump fault diagnosis method based on mechanism-data driving model | |
| CN115407712A (en) | Intelligent maintenance system for hydraulic station of steel mill and working process | |
| CN114738132A (en) | Supercharger speed sensor fault diagnosis method and system based on real ship data | |
| Chesterman et al. | Condition monitoring of wind turbines and extraction of healthy training data using an ensemble of advanced statistical anomaly detection models | |
| CN117221145A (en) | Equipment fault predictive maintenance system based on Internet of things platform | |
| CN110262460B (en) | Concrete piston fault prediction method for extracting features by combining clustering idea | |
| CN116345690B (en) | Power monitoring false alarm identification method and system based on power supply system equipment list | |
| CN117215940A (en) | Intelligent operation and maintenance emergency processing system | |
| CN109754490A (en) | Health control method, device, medium and the equipment of brake system of electric locomotive | |
| CN113955149B (en) | Health diagnosis method and device for motor system | |
| CN115650006A (en) | Elevator safety monitoring and early warning method and system based on big data | |
| CN115009948A (en) | Elevator maintenance-on-demand intelligent management system and management method thereof | |
| CN116414086A (en) | Device for integrating safety control system based on FMEDA failure prediction technology | |
| CN112101758A (en) | Clothing factory production abnormity decision making system and method based on artificial intelligence | |
| CN117374976B (en) | Electrical safety management system based on automatic line fault identification | |
| CN117313019B (en) | Data anomaly detection method based on deep reinforcement learning | |
| CN117689214B (en) | Dynamic safety assessment method for energy router of flexible direct-current traction power supply system | |
| CN111175041B (en) | Valve monitoring method and system | |
| Li et al. | Enhancing anomaly diagnosis of automatic train supervision system based on operation log |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201009 |
|
| RJ01 | Rejection of invention patent application after publication |