CN117668498B - Pump health assessment method based on reliability distribution and anomaly detection - Google Patents
Pump health assessment method based on reliability distribution and anomaly detection Download PDFInfo
- Publication number
- CN117668498B CN117668498B CN202410132805.5A CN202410132805A CN117668498B CN 117668498 B CN117668498 B CN 117668498B CN 202410132805 A CN202410132805 A CN 202410132805A CN 117668498 B CN117668498 B CN 117668498B
- Authority
- CN
- China
- Prior art keywords
- pump equipment
- pump
- reliability
- distribution
- component
- 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.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 27
- 238000000034 method Methods 0.000 title claims abstract description 25
- 230000005856 abnormality Effects 0.000 claims abstract description 25
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 14
- 238000012423 maintenance Methods 0.000 claims abstract description 9
- 238000007476 Maximum Likelihood Methods 0.000 claims abstract description 7
- 238000012545 processing Methods 0.000 claims abstract description 7
- 230000002159 abnormal effect Effects 0.000 claims description 9
- 238000012544 monitoring process Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 7
- 230000004927 fusion Effects 0.000 claims description 3
- 238000011478 gradient descent method Methods 0.000 claims description 3
- 230000015556 catabolic process Effects 0.000 abstract description 4
- 238000006731 degradation reaction Methods 0.000 abstract description 4
- 230000007774 longterm Effects 0.000 abstract description 4
- 239000000446 fuel Substances 0.000 description 7
- 238000011156 evaluation Methods 0.000 description 6
- 238000003745 diagnosis Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000004171 remote diagnosis Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
-
- 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
- F04B51/00—Testing machines, pumps, or pumping installations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Mechanical Engineering (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
- Control Of Positive-Displacement Pumps (AREA)
Abstract
The invention discloses a pump health assessment method based on reliability distribution and anomaly detection, which comprises the following steps: acquiring maintenance and replacement records of key components in pump equipment, and performing data processing on the records to obtain a life sample; calculating life distribution of the life samples based on a maximum likelihood estimation algorithm; calculating the operation reliability of each key component in the pump equipment according to the service life distribution; collecting real-time data of the current operation of the pump equipment; calculating an abnormality index of the pump equipment running in real time by using a clustering abnormality detection algorithm; calculating the operation health degree of the pump equipment according to the abnormality index and the operation reliability degree: if the value of the operation health degree is close to 1, the operation state of the pump equipment is healthy; if the value of the operational health is closer to 0, the pump equipment components are operating abnormally. On the basis of abnormality detection of the real-time running state of the equipment, the method increases the long-term degradation influence of the equipment based on reliability distribution, reduces the fault risk of key parts of the pump equipment, and reduces the potential running risk and maintenance cost.
Description
Technical Field
The invention relates to the technical field of pump equipment health monitoring, in particular to a pump health assessment method based on reliability distribution and anomaly detection.
Background
At present, the health monitoring of pump equipment is mainly divided into two types, one type is statistical analysis based on reliability life distribution, the method is obtained based on a statistical result of a large sample, and the reliability of the pump equipment can be estimated to be gradually reduced along with the increase of the running time, but the applicability of the pump equipment to single equipment is poor; the other type is an abnormality detection method based on the operation parameters of the equipment, which can evaluate whether the real-time operation state of the pump equipment is abnormal or not, but cannot effectively consider the long-term degradation trend of the equipment.
U.S. patent application publication No. 2019/0040812 (812 publication) describes a method of diagnosing a high-pressure fuel delivery system that includes sensing a starting fuel pressure in a fuel rail to establish or increase fuel pressure within the fuel rail upon engine start-up and misfire; the method determines a start leak rate based on the start fuel pressure, and when the start leak rate is greater than a start leak threshold, the method may identify a leak or inefficiency in the high pressure fuel pump, however, the method disclosed at 812 may not adequately determine the health of the pump and/or may falsely diagnose a leak or inefficiency of the pump.
CN111314463A discloses a method based on pump station unit health assessment, which establishes a network system overall architecture of a data acquisition front end combined with a monitoring network and remote diagnosis according to the requirements of the pump station unit health assessment, and comprises a sensing layer, a network layer and an application layer, wherein a data acquisition device according to the sensing layer acquires corresponding data of the pump station unit, the network layer sends the acquired data to a server of the application layer, and judges whether data analysis and fault diagnosis are required or not after comparing the acquired data with a preset alarm threshold value, and finally issues a diagnosis result; however, the method cannot effectively consider the long-term degradation trend of the equipment, and has poor applicability to single equipment.
Disclosure of Invention
This section is intended to outline some aspects of embodiments of the application and to briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section as well as in the description of the application and in the title of the application, which may not be used to limit the scope of the application.
In order to solve the technical problems, the invention provides the following technical scheme: collecting maintenance and replacement records of key components in pump equipment, and performing data processing on the records to obtain life samples;
Calculating life distribution of the life samples based on a maximum likelihood estimation algorithm;
calculating the operation reliability of each key component in the pump equipment according to the service life distribution;
collecting real-time data of the current operation of the pump equipment;
Calculating an abnormality index of the pump equipment running in real time by using a clustering abnormality detection algorithm;
Calculating the operation health degree of the pump equipment according to the abnormality index and the operation reliability degree:
if the value of the operation health degree is close to 1, the operation state of the pump equipment is healthy;
if the value of the operational health is closer to 0, the pump apparatus component is operating abnormally.
As a preferable mode of the pump health evaluation method based on reliability distribution and abnormality detection according to the present invention, the maintenance replacement record includes a damage time of the critical component and a replacement component type;
The key components comprise a pump body, a motor and a bearing;
The data processing is to record and sort the service time of each component to obtain the life sample { x 1,x2,...xn }.
As a preferable mode of the pump health evaluation method based on reliability distribution and abnormality detection according to the present invention, calculating the life distribution includes:
fitting life distribution of each key component according to the maximum likelihood estimation algorithm, and defining life distribution compliance Weibull distribution of the key component of the pump equipment, wherein probability density functions are as follows:
;
wherein, Is a scale parameter, k is a shape parameter, and t is a run time.
As a preferable scheme of the pump health evaluation method based on reliability distribution and anomaly detection, the mathematical expression formula of the log likelihood function corresponding to the key component is as follows:
;
where n is the number of life samples, Is the i-th life sample;
estimating parameters lambda and k of the Weibull distribution by maximizing a log-likelihood function;
Finding parameter values maximizing a log-likelihood function by using a gradient descent method to obtain a life distribution of the key component 。
As a preferable scheme of the pump health evaluation method based on reliability distribution and abnormality detection, after the life distribution calculation of each key component is completed, the variation of the reliability of each component along with the running time of a single component can be obtained, and the reliability of the ith component is defined as follows:
;
Wherein T is the current time, and T i is the length of time the component has been operated since the last replacement.
As a preferable scheme of the pump health evaluation method based on reliability distribution and anomaly detection, according to the reliability of the serial system, the mathematical expression formula of the reliability of the whole pump equipment of m key components is as follows:
;
Wherein R (t) is a value between 0 and 1, and a value closer to 1 indicates a higher reliability and a value closer to 0 indicates a lower reliability.
As a preferable scheme of the pump health assessment method based on reliability distribution and anomaly detection, the method acquires real-time data of the current operation of the pump equipment, including flow, pressure, vibration, temperature, current and rotating speed;
The data samples defining the p collected monitoring parameters are y= { Y 1,y2,...yp }.
As a preferable scheme of the pump health assessment method based on reliability distribution and anomaly detection, the definition of the normal running state of the pump equipment is completed based on a clustering anomaly detection algorithm, the real-time running state of the pump equipment is compared with the defined normal running state, deviation between the real-time running state and the defined normal running state is quantified, and the real-time running anomaly index of the pump equipment is formed.
As a preferable scheme of the pump health evaluation method based on reliability distribution and anomaly detection, the calculation formula of the health degree is a fusion index of the operation reliability and the anomaly index, and the method comprises the following steps:
;
wherein HI (t) is a value between 0 and 1, and a value closer to 1 indicates that the operation state of the pump equipment component is healthy, and a value closer to 0 indicates that the pump equipment component is abnormal;
When HI (t) is less than 0.6, triggering an alarm threshold to start, and sending out a pump equipment health alarm.
The invention has the beneficial effects that:
1. according to the method, two monitoring methods are combined, on the basis of abnormality detection of the real-time running state of the equipment, the long-term degradation influence of the equipment based on reliability distribution is increased, the running health of the pump equipment is estimated more comprehensively, the fault risk of key parts of the pump equipment is reduced, the problems can be reacted and treated early, and the potential running risk and the maintenance cost are reduced.
2. The method is used for identifying whether the pump equipment has abnormal parts or not, and giving corresponding alarm when the abnormality occurs, so as to serve as a reference basis for operation and maintenance.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. Wherein:
FIG. 1 is a flow chart of a pump health assessment method based on reliability distribution and anomaly detection according to the present invention.
Detailed Description
So that the manner in which the above recited objects, features and advantages of the present invention can be understood in detail, a more particular description of the invention, briefly summarized above, may be had by reference to the embodiments, some of which are illustrated in the appended drawings.
All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways other than those described herein, and persons skilled in the art will readily appreciate that the present invention is not limited to the specific embodiments disclosed below.
Referring to fig. 1, a pump health assessment method based on reliability distribution and anomaly detection according to an embodiment of the present invention specifically includes the following steps:
S1: and acquiring maintenance and replacement records of key components in the pump equipment, and performing data processing on the records to obtain a life sample. The step needs to be described as follows:
the maintenance replacement record includes the time of damage to the critical component and the type of the replacement component;
The key components comprise a pump body, a motor and a bearing.
In an alternative embodiment, the data processing is to record and sort the age of each component to obtain a life sample.
As an example, the aggregate form of lifetime samples is { x 1,x2,...xn }.
S2: the lifetime distribution of the lifetime samples is calculated based on a maximum likelihood estimation algorithm. The step of calculating the lifetime distribution includes:
fitting the life distribution of each key component according to a maximum likelihood estimation algorithm, and defining the life distribution obeying Weibull distribution of the key component of the pump equipment, wherein the probability density function is as follows:
;
wherein, Is a scale parameter, k is a shape parameter, and t is a run time.
Further, the mathematical expression formula of the log likelihood function corresponding to the key component is as follows:
;
where n is the number of life samples, Is the i-th life sample;
estimating parameters lambda and k of the Weibull distribution by maximizing a log-likelihood function;
Finding out the parameter value maximizing the log likelihood function by using the gradient descent method to obtain the life distribution of the key component 。
S3: based on the life distribution, operational reliability of each critical component in the pump apparatus is calculated. The step also needs to be described, after the life distribution calculation of each key component is completed, the reliability of each component can be obtained along with the change of the running time of the single component, and the reliability of the ith component is defined as follows:
;
Wherein T is the current time, and T i is the length of time the component has been operated since the last replacement.
Specifically, according to the reliability of the serial system, the mathematical expression formula of the reliability of the pump apparatus as a whole of m key components is as follows:
;
Wherein R (t) is a value between 0 and 1, and a value closer to 1 indicates a higher reliability and a value closer to 0 indicates a lower reliability.
S4: real-time data of the current operation of the pump device is collected. The step is to collect real-time data of the current operation of the pump equipment, including flow, pressure, vibration, temperature, current and rotation speed.
In an alternative embodiment, the data samples defining the p collected monitoring parameters are y= { Y 1,y2,...yp }.
S5: and calculating an abnormality index of the pump equipment running in real time by using a clustering abnormality detection algorithm. The step also needs to be described, namely, the definition of the normal running state of the pump equipment is completed based on the clustering abnormality detection algorithm, the real-time running state of the pump equipment is compared with the defined normal running state, the deviation between the real-time running state and the defined normal running state is quantized, and the real-time running abnormality index of the pump equipment is formed. Wherein:
(1) The monitored data sample y= { Y 1,y2,...yp } was normalized, and its mathematical expression was as follows:
;
wherein, Is normalized data, y is raw data,/>As the minimum value in the data sample set,Maximum value in the data sample set;
setting a neighborhood radius And a minimum number of neighbors minPts.
As an example of this, the number of devices,=0.1,minPts=10。
It should be noted that, the neighborhood radius specifies that the distance between two adjacent points is less than a certain number and can be classified into one class, and the minimum number of adjacent points defines the minimum number of points in one class.
(2) C clustering centers are formed through randomly set condition iteration core points;
Wherein C i is a P-dimensional variable, each monitoring record data point is a P-dimensional variable, and the attribution of the data point clustering category is judged to be the closest clustering center category of the data point.
(3) Calculate the average distance L 1 of the data points to the cluster center for each category;
The distance from the data point at a certain moment to the clustering center is recorded as Lt.
(4) The real-time operation abnormality index of the pump equipment is as follows:
;
wherein H (t) is a value between 0 and 1, and the closer to 1 is that the pump equipment operation parameter is normal, and the closer to 0 is that the pump equipment operation parameter is abnormal.
S6: calculating the operation health degree of the pump equipment according to the abnormality index and the operation reliability degree:
a: if the value of the operation health degree is close to 1, the operation state of the pump equipment is healthy;
b: if the value of the operational health is closer to 0, the pump equipment components are operating abnormally.
As an example, the calculation formula of the health degree is a fusion index of the operation reliability and the abnormality index, as follows:
;
Wherein HI (t) is a value between 0 and 1, and a value closer to 1 indicates that the operation state of the pump equipment component is healthy, and a value closer to 0 indicates that the pump equipment component is abnormal.
In an alternative embodiment, when HI (t) < 0.6, an alarm threshold is triggered to activate, and a pump device health alarm is issued.
It should be noted that, the alarm threshold may be set according to the actual operating situation of the field device, for example, the threshold may be set between (0.5,0.6), which is not limited by the embodiment of the present invention.
In an alternative embodiment, the bearer form of the pump device health alert may be pushed through the system platform or a cell phone SMS notification.
It should be noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention may be modified or substituted without departing from the spirit and scope of the technical solution of the present invention, which is intended to be covered in the scope of the claims of the present invention.
Claims (3)
1. A pump health assessment method based on reliability distribution and anomaly detection, comprising:
collecting maintenance and replacement records of key components in pump equipment, and performing data processing on the records to obtain life samples;
Calculating life distribution of the life samples based on a maximum likelihood estimation algorithm;
fitting life distribution of each key component according to the maximum likelihood estimation algorithm, and defining life distribution compliance Weibull distribution of the key component of the pump equipment, wherein probability density functions are as follows:
;
wherein, K is a shape parameter, and t is a running time;
the mathematical expression formula of the log likelihood function corresponding to the key component is as follows:
;
Wherein n is the number of life samples, and X i is the ith life sample;
estimating parameters lambda and k of the Weibull distribution by maximizing a log-likelihood function;
Finding parameter values maximizing a log-likelihood function by using a gradient descent method to obtain a life distribution of the key component ;
Calculating the operation reliability of each key component in the pump equipment according to the service life distribution;
After the life distribution calculation of each key component is completed, the change of the reliability of each component along with the running time of the single component can be obtained, and the reliability of the ith component is defined as follows:
;
Wherein T is the current time, and T i is the running time of the component from the last replacement to the present;
according to the reliability of the series system, the mathematical expression formula of the reliability of the pump equipment of m key components is as follows:
;
Wherein R (t) is a value between 0 and 1, and a value closer to 1 indicates a higher reliability and a value closer to 0 indicates a lower reliability;
collecting real-time data of the current operation of the pump equipment;
Calculating an abnormality index of the pump equipment running in real time by using a clustering abnormality detection algorithm;
The method comprises the steps of completing the definition of the normal running state of the pump equipment based on a clustering abnormality detection algorithm, comparing the real-time running state of the pump equipment with the defined normal running state, quantifying the deviation between the real-time running state and the defined normal running state, and forming a real-time running abnormality index of the pump equipment, wherein:
The monitored data sample y= { Y 1,y2,...yp } was normalized, and its mathematical expression was as follows:
;
wherein Y' is standardized data, Y is original data, min (Y) is a minimum value in a data sample set, and max (Y) is a maximum value in the data sample set;
setting a neighborhood radius And a minimum number of neighbors minPts =10;
C clustering centers are formed through randomly set condition iteration core points ;
Wherein, C i is a P-dimensional variable, each monitoring record data point is a P-dimensional variable, and the attribution of the data point clustering category is judged as the closest clustering center category of the data point;
calculate the average distance L 1 of the data points to the cluster center for each category ;
Recording the distance of a data point at a certain moment from the clustering center as Lt;
The real-time operation abnormality index of the pump equipment is as follows:
;
Wherein H (t) is a numerical value between 0 and 1, and the closer to 1 is that the operation parameter of the pump equipment is normal, and the closer to 0 is that the operation parameter of the pump equipment is abnormal;
calculating the operation health degree of the pump equipment according to the abnormal index and the operation reliability, wherein a calculation formula of the health degree is a fusion index of the operation reliability and the abnormal index, and the calculation formula is as follows:
;
wherein HI (t) is a value between 0 and 1, and a value closer to 1 indicates that the operation state of the pump equipment component is healthy, and a value closer to 0 indicates that the pump equipment component is abnormal;
if the value of the operation health degree is close to 1, the operation state of the pump equipment is healthy;
if the value of the operational health is closer to 0, the pump apparatus component is operating abnormally.
2. The pump health assessment method based on reliability distribution and anomaly detection of claim 1, wherein the service replacement record includes a time of failure of the critical component and a replacement component type;
The key components comprise a pump body, a motor and a bearing;
The data processing is to record and sort the service time of each component to obtain the life sample { x 1,x2,...xn }.
3. The pump health assessment method based on reliability distribution and anomaly detection of claim 1, wherein real-time data of the current operation of the pump device is collected, including flow, pressure, vibration, temperature, current, rotational speed;
The data samples defining the p collected monitoring parameters are y= { Y 1,y2,...yp }.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410132805.5A CN117668498B (en) | 2024-01-31 | 2024-01-31 | Pump health assessment method based on reliability distribution and anomaly detection |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410132805.5A CN117668498B (en) | 2024-01-31 | 2024-01-31 | Pump health assessment method based on reliability distribution and anomaly detection |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117668498A CN117668498A (en) | 2024-03-08 |
CN117668498B true CN117668498B (en) | 2024-04-26 |
Family
ID=90082840
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410132805.5A Active CN117668498B (en) | 2024-01-31 | 2024-01-31 | Pump health assessment method based on reliability distribution and anomaly detection |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117668498B (en) |
Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0269619A (en) * | 1988-09-05 | 1990-03-08 | Nippon Atom Ind Group Co Ltd | Device for supporting maintenance and management of plant apparatus |
CN105910806A (en) * | 2016-05-30 | 2016-08-31 | 重庆大学 | Filling pump early health status monitoring method |
CN112032034A (en) * | 2020-05-21 | 2020-12-04 | 和尘自仪(嘉兴)科技有限公司 | Sea water pump health state assessment method, model, device and storage medium |
CN112115417A (en) * | 2020-08-10 | 2020-12-22 | 贵州电网有限责任公司 | Transformer real-time fault probability calculation method based on probability density clustering |
CN112345261A (en) * | 2020-10-29 | 2021-02-09 | 南京航空航天大学 | Aero-engine pumping system abnormity detection method based on improved DBSCAN algorithm |
CN113849774A (en) * | 2021-09-30 | 2021-12-28 | 上海应用技术大学 | Intelligent equipment maintenance platform based on life analysis and health monitoring |
KR102407773B1 (en) * | 2021-10-18 | 2022-06-10 | 가온플랫폼 주식회사 | Facility reliablility calculation system and method reflecting real-time health of facilities |
CN114861827A (en) * | 2022-05-27 | 2022-08-05 | 太原理工大学 | Coal mining machine prediction diagnosis and health management method based on multi-source data fusion |
CN115034248A (en) * | 2021-03-03 | 2022-09-09 | 斯凯孚公司 | Automatic diagnostic method, system and storage medium for equipment |
KR20220132824A (en) * | 2021-03-24 | 2022-10-04 | 한국전력공사 | Distribution facility condition monitoring system and method |
CN115143129A (en) * | 2022-07-28 | 2022-10-04 | 常州机电职业技术学院 | Desulfurization pump fault prediction and health management device |
CN115774652A (en) * | 2023-02-13 | 2023-03-10 | 浪潮通用软件有限公司 | Cluster control equipment health monitoring method, equipment and medium based on clustering algorithm |
CN117114446A (en) * | 2023-08-29 | 2023-11-24 | 珠海英慕科技有限公司 | Device health assessment method based on data driving |
CN117195730A (en) * | 2023-09-14 | 2023-12-08 | 江西睿构科技有限公司 | Method and system for analyzing service life of electromechanical equipment of expressway |
-
2024
- 2024-01-31 CN CN202410132805.5A patent/CN117668498B/en active Active
Patent Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0269619A (en) * | 1988-09-05 | 1990-03-08 | Nippon Atom Ind Group Co Ltd | Device for supporting maintenance and management of plant apparatus |
CN105910806A (en) * | 2016-05-30 | 2016-08-31 | 重庆大学 | Filling pump early health status monitoring method |
CN112032034A (en) * | 2020-05-21 | 2020-12-04 | 和尘自仪(嘉兴)科技有限公司 | Sea water pump health state assessment method, model, device and storage medium |
CN112115417A (en) * | 2020-08-10 | 2020-12-22 | 贵州电网有限责任公司 | Transformer real-time fault probability calculation method based on probability density clustering |
CN112345261A (en) * | 2020-10-29 | 2021-02-09 | 南京航空航天大学 | Aero-engine pumping system abnormity detection method based on improved DBSCAN algorithm |
CN115034248A (en) * | 2021-03-03 | 2022-09-09 | 斯凯孚公司 | Automatic diagnostic method, system and storage medium for equipment |
KR20220132824A (en) * | 2021-03-24 | 2022-10-04 | 한국전력공사 | Distribution facility condition monitoring system and method |
CN113849774A (en) * | 2021-09-30 | 2021-12-28 | 上海应用技术大学 | Intelligent equipment maintenance platform based on life analysis and health monitoring |
KR102407773B1 (en) * | 2021-10-18 | 2022-06-10 | 가온플랫폼 주식회사 | Facility reliablility calculation system and method reflecting real-time health of facilities |
CN114861827A (en) * | 2022-05-27 | 2022-08-05 | 太原理工大学 | Coal mining machine prediction diagnosis and health management method based on multi-source data fusion |
CN115143129A (en) * | 2022-07-28 | 2022-10-04 | 常州机电职业技术学院 | Desulfurization pump fault prediction and health management device |
CN115774652A (en) * | 2023-02-13 | 2023-03-10 | 浪潮通用软件有限公司 | Cluster control equipment health monitoring method, equipment and medium based on clustering algorithm |
CN117114446A (en) * | 2023-08-29 | 2023-11-24 | 珠海英慕科技有限公司 | Device health assessment method based on data driving |
CN117195730A (en) * | 2023-09-14 | 2023-12-08 | 江西睿构科技有限公司 | Method and system for analyzing service life of electromechanical equipment of expressway |
Non-Patent Citations (4)
Title |
---|
Detection of inception of preload loss and remaining life prediction for ball screw considering change in dynamics due to worktable position;Kundu, Pradeep et.al;《MECHANICAL SYSTEMS AND SIGNAL PROCESSING》;20230602;第1-5页 * |
基于健康度分析的电网单元设备集可靠性评估研究;李军;李向阳;刘昭阁;;中国安全生产科学技术;20160630(06);第138-143页 * |
基于运行状态与绝缘寿命的电力变压器可靠性评估研究;刘亚婕;《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》;20200315;第C042-525页 * |
液压泵寿命的在线预测与健康管理;王向周;闫贺龙;郑戍华;;北京理工大学学报;20171015(10);第38-44页 * |
Also Published As
Publication number | Publication date |
---|---|
CN117668498A (en) | 2024-03-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR102092185B1 (en) | Platform for analyzing electric motor health and analysis method using the same | |
CN113190421B (en) | Method for detecting and analyzing health state of equipment in data center | |
CN113568774B (en) | Multi-dimensional time sequence data real-time abnormality detection method using unsupervised deep neural network | |
CN110703214B (en) | Weather radar state evaluation and fault monitoring method | |
CA2508008A1 (en) | A method for developing a unified quality assessment and providing an automated fault diagnostic tool for turbine machine systems and the like | |
CN117235557B (en) | Electrical equipment fault rapid diagnosis method based on big data analysis | |
CN113562562A (en) | Elevator safety early warning monitoring system and judgment method thereof | |
CN117131110B (en) | Method and system for monitoring dielectric loss of capacitive equipment based on correlation analysis | |
CN113982850B (en) | Fan comprehensive health analysis method and system integrating high-low frequency signals | |
CN112633614B (en) | Real-time fault degree diagnosis system and method based on feature extraction | |
CN113757093A (en) | Fault diagnosis method for flash steam compressor unit | |
CN116244765A (en) | Equipment maintenance management method based on industrial Internet | |
CN118051863B (en) | Health data acquisition system and method based on digital metering technology | |
CN117148045A (en) | Fault studying and judging management system for running state of power distribution network | |
CN117668498B (en) | Pump health assessment method based on reliability distribution and anomaly detection | |
CN118035904A (en) | Runout monitoring fault diagnosis method and system based on multi-band data fusion | |
CN117331790A (en) | Machine room fault detection method and device for data center | |
CN116071053B (en) | Reciprocating compressor state early warning system based on digital twinning | |
CN117435883A (en) | Method and system for predicting equipment faults based on digital twinning | |
CN117150313A (en) | Power information communication method and system based on abnormal state identification | |
CN115169650B (en) | Equipment health prediction method for big data analysis | |
CN115856613A (en) | Circuit breaker state evaluation method | |
US11047833B2 (en) | Method for automatic determination of trend in graphic analysis of turbomachines | |
CN118157327B (en) | Cable sheath circulation monitoring device based on NB-IOT technology | |
KR101967629B1 (en) | Signal Data Processing Apparatus For Prediction And Diagnosis Of Nuclear Power Plant |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |