CN118114081A - Method and system for predicting residual life of plunger pump - Google Patents
Method and system for predicting residual life of plunger pump Download PDFInfo
- Publication number
- CN118114081A CN118114081A CN202410541568.8A CN202410541568A CN118114081A CN 118114081 A CN118114081 A CN 118114081A CN 202410541568 A CN202410541568 A CN 202410541568A CN 118114081 A CN118114081 A CN 118114081A
- Authority
- CN
- China
- Prior art keywords
- real
- time
- plunger pump
- life
- record
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000004458 analytical method Methods 0.000 claims abstract description 35
- 238000012545 processing Methods 0.000 claims abstract description 16
- 238000012544 monitoring process Methods 0.000 claims abstract description 13
- 238000010606 normalization Methods 0.000 claims abstract description 9
- 238000012423 maintenance Methods 0.000 claims description 64
- 239000013598 vector Substances 0.000 claims description 53
- 238000007689 inspection Methods 0.000 claims description 48
- 238000004140 cleaning Methods 0.000 claims description 25
- 238000005461 lubrication Methods 0.000 claims description 21
- 230000008569 process Effects 0.000 claims description 17
- 238000001514 detection method Methods 0.000 claims description 16
- 238000012549 training Methods 0.000 claims description 8
- 230000000694 effects Effects 0.000 abstract description 7
- 230000015556 catabolic process Effects 0.000 abstract description 5
- 238000006731 degradation reaction Methods 0.000 abstract description 5
- 238000003745 diagnosis Methods 0.000 abstract description 2
- 238000004364 calculation method Methods 0.000 description 8
- 230000007613 environmental effect Effects 0.000 description 8
- 230000009467 reduction Effects 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000003749 cleanliness Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000003921 oil Substances 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000000306 component Substances 0.000 description 1
- 239000000356 contaminant Substances 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 239000010779 crude oil Substances 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000003344 environmental pollutant Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 239000010687 lubricating oil Substances 0.000 description 1
- 239000003129 oil well Substances 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 231100000719 pollutant Toxicity 0.000 description 1
- 238000007789 sealing Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Control Of Positive-Displacement Pumps (AREA)
Abstract
The invention discloses a method and a system for predicting the residual life of a plunger pump, and relates to the technical field of pump diagnosis management, wherein the method comprises the following steps: analyzing the real-time running state information of the plunger pump obtained by multi-dimensional monitoring through a residual life prediction model to obtain a predicted real-time residual life; reading a predetermined life loss analysis function, and analyzing the predetermined service life of the plunger pump based on the predetermined life loss analysis function to obtain a predetermined real-time residual life; and weighting the predicted real-time residual life and the preset real-time residual life after normalization processing to obtain the target residual life of the plunger pump. The technical problems that the real-time operation data of the pump cannot be accurately obtained, the performance degradation trend analysis result of the pump is inaccurate in the existing plunger pump residual life prediction are solved, the residual life prediction of the plunger pump is inaccurate are further solved, and the technical effects of improving the accuracy and reliability of the residual life prediction result of the plunger pump are achieved.
Description
Technical Field
The application relates to the technical field of pump diagnosis management, in particular to a method and a system for predicting the residual life of a plunger pump.
Background
Along with the rapid development of automation and intellectualization of modern industrial technology, higher requirements are put forward on the stability and reliability of equipment performance, the stability of the running state and the service life of a plunger pump serving as a core component of a hydraulic system in an industrial process directly influence the efficiency and safety of the whole production line, in the actual running process, the performance of the plunger pump is gradually reduced due to the fact that the plunger pump bears the influence of severe working environments such as high pressure, high speed, high temperature and the like for a long time, faults finally occur, the accurate prediction of the residual service life of the plunger pump is particularly important, but the traditional prediction method of the residual service life of the plunger pump is not accurate enough when data of the running process are collected and analyzed, so that the prediction result deviation of a residual service life prediction model is larger, and further the production efficiency of enterprises and the use management of equipment are influenced.
Therefore, in the prior art of time noise reduction convergence, the technical problems of inaccurate prediction of the residual life of the plunger pump caused by inaccurate analysis results of real-time operation data of the pump and performance degradation trend of the pump cannot be accurately obtained.
Disclosure of Invention
By providing the method and the system for predicting the residual life of the plunger pump, the technical problems that the existing method and the system for predicting the residual life of the plunger pump cannot accurately acquire real-time operation data of the pump and the analysis result of the performance degradation trend of the pump is inaccurate due to the adoption of the technical means of constructing a prediction model, establishing a loss analysis function and the like, and further the residual life of the plunger pump is inaccurate are solved, and the technical effects of improving the accuracy and the reliability of the residual life prediction result of the plunger pump are achieved.
The application provides a method for predicting the residual life of a plunger pump, which comprises the following steps: analyzing real-time running state information of the plunger pump obtained through multi-dimensional monitoring through a residual life prediction model to obtain predicted real-time residual life, wherein the residual life prediction model is an intelligent model obtained by training data in a use database of the same type of plunger pump product of the plunger pump; reading a predetermined life loss analysis function, and analyzing the predetermined service life of the plunger pump based on the predetermined life loss analysis function to obtain a predetermined real-time residual life; and weighting the predicted real-time residual life and the preset real-time residual life after normalization processing to obtain the target residual life of the plunger pump.
In a possible implementation, the predicted real-time remaining lifetime is obtained, and the following is performed: randomly extracting a first usage record in the usage database, wherein the first usage record comprises first record running state information and first record residual life of a first plunger pump; acquiring a first state similarity, wherein the first state similarity refers to the similarity degree of the real-time running state information and the first recorded running state information; if the first state similarity reaches a preset similarity threshold, adding the residual life of the first record to a primary prediction result set; and the residual life prediction model takes the mode residual life value of each recorded residual life in the preliminary prediction result set as the predicted real-time residual life.
In a possible implementation, the first state similarity is obtained, and the following processing is performed: acquiring a first operation characteristic, wherein the first operation characteristic corresponds to a first preset label scheme; extracting a first real-time characteristic parameter in the real-time running state information and a first record characteristic parameter in the first record running state information based on the first running characteristic respectively; sequentially acquiring a first real-time tag of the first real-time characteristic parameter and a first record tag of the first record characteristic parameter according to the first preset tag scheme; obtaining a real-time tag vector of the real-time running state information based on the first real-time tag, and obtaining a first record tag vector of the first record running state information based on the first record tag; and calling a predetermined similarity function to analyze the real-time tag vector and the first record tag vector, so as to obtain the first state similarity.
In a possible implementation manner, the real-time tag vector and the first record tag vector are analyzed by calling a predetermined similarity function, and the following processing is further performed: the expression of the predetermined similarity function is as follows:
T（，/>）/>；
Wherein, T is% ，/>) Means the real-time running state information/>With the first recorded running state information/>The first state similarity between/>Means the real-time running state information/>Corresponding real-time tag vector and first recorded tag vector/>The number of matching pairs of corresponding said first record label vectors being identical,Means the real-time running state information/>Corresponding real-time tag vector and first recorded tag vector/>And the total number of matched pairs of the corresponding first record label vector.
In a possible implementation, a predetermined real-time remaining lifetime is obtained, and the following is also performed: acquiring a target usage record of the plunger pump, wherein the target usage record comprises a plurality of usage records; randomly extracting a first use record in the multiple use records, and obtaining a first use index according to the first use record; acquiring a target maintenance record of the plunger pump, wherein the target maintenance record comprises a plurality of maintenance records; randomly extracting a first dimension check record in the plurality of dimension check records, and obtaining a first dimension check index according to the first dimension check record; and according to the predetermined life loss analysis function, calculating and analyzing the predetermined service life by combining a target use index obtained based on the first use index and a target dimension index obtained based on the first dimension index to obtain the predetermined real-time residual life of the plunger pump.
In a possible implementation, the target usage index is obtained, and the following processing is also performed: the first use record comprises first use operation information, first use condition information and first use environment information; determining a first operation index according to a first operation deviation obtained by comparing the first usage operation information with the preset operation information, and generating a target operation index; weighting a first operation state characteristic parameter in the first using operation state information to determine a first operation state index, and generating a target operation state index; weighting a first environment characteristic parameter in the first using environment information to determine a first environment index, and generating a target environment index; and weighting the target operation index, the target working condition index and the target environment index to obtain the target use index.
In a possible implementation, a first dimension index is obtained, and the following processing is further performed: the first dimension check record comprises first dimension check time and first dimension check information; the method comprises the steps of weighting and analyzing a first lubrication dimension inspection index obtained by first lubrication system dimension inspection information in the first dimension inspection information and a first cleaning dimension inspection index obtained by analyzing first cleaning dimension inspection information in the first dimension inspection information to obtain a first initial dimension inspection index; analyzing the first dimension detection time to obtain a first dimension detection frequency, and weighting the first initial dimension detection index to obtain the first dimension detection index.
The application also provides a residual life prediction system of the plunger pump, which comprises the following steps:
The system comprises a predicted real-time residual life obtaining module, a real-time monitoring module and a real-time monitoring module, wherein the predicted real-time residual life obtaining module is used for analyzing real-time running state information of a plunger pump obtained through multi-dimensional monitoring through a residual life predicting model to obtain a predicted real-time residual life, and the residual life predicting model is an intelligent model obtained through training data in a use database of the same type of plunger pump product of the plunger pump;
The system comprises a preset real-time residual life acquisition module, a preset real-time residual life analysis module and a control module, wherein the preset real-time residual life acquisition module is used for reading a preset life loss analysis function and analyzing the preset service life of the plunger pump based on the preset life loss analysis function to obtain the preset real-time residual life;
the target remaining life obtaining module is used for weighting the predicted real-time remaining life and the preset real-time remaining life after normalization processing to obtain the target remaining life of the plunger pump.
The method and the system for predicting the residual life of the plunger pump are used for collecting historical event load data and extracting a key feature word list by adopting a noise reduction convergence model; after noise reduction treatment, a clustering algorithm is adopted to obtain a clustering output result; generating an event baseline; collecting real-time event load data, and matching by combining an event baseline with a feature matching model; if the two risk marks are not matched, outputting an abnormal risk mark; based on the normal event behavior recognition module, carrying out validity analysis on the security triage result; generating a parameter adjustment instruction; iterative correction is performed through a URL baseline filtering model. The technical problems that the load data characteristics existing in the existing event noise reduction convergence are not accurate in acquisition, and further the residual life prediction of the plunger pump is inaccurate are solved, and the technical effects of improving the accuracy and reliability of the residual life prediction result of the plunger pump are achieved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following will briefly describe the drawings of the embodiments of the present disclosure, in which flowcharts are used to illustrate operations performed by a system according to embodiments of the present disclosure. It should be understood that the preceding or following operations are not necessarily performed in order precisely. Rather, the various steps may be processed in reverse order or simultaneously, as desired. Also, other operations may be added to or removed from these processes.
Fig. 1 is a flow chart of a method for predicting the residual life of a plunger pump according to an embodiment of the present application;
Fig. 2 is a schematic structural diagram of a residual life prediction system of a plunger pump according to an embodiment of the present application.
Reference numerals illustrate: the predicted real-time remaining life obtaining module 10, the predetermined real-time remaining life obtaining module 20, the target remaining life obtaining module 30.
Detailed Description
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be described in further detail with reference to the accompanying drawings, and the described embodiments should not be construed as limiting the present application, and all other embodiments obtained by those skilled in the art without making any inventive effort are within the scope of the present application.
In the following description, reference is made to "some embodiments" which describe a subset of all possible embodiments, but it is to be understood that "some embodiments" may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict, the term "first\second" being referred to merely as distinguishing between similar objects and not representing a particular ordering for the objects. The terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements that are expressly listed or inherent to such process, method, article, or apparatus, but may include other steps or modules that may not be expressly listed or inherent to such process, method, article, or apparatus, and unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. The terminology used herein is for the purpose of describing embodiments of the application only.
The embodiment of the application provides a method for predicting the residual life of a plunger pump, as shown in fig. 1, comprising the following steps:
And step S100, analyzing real-time running state information of the plunger pump obtained through multi-dimensional monitoring through a residual life prediction model to obtain predicted real-time residual life, wherein the residual life prediction model is an intelligent model obtained through training data in a use database of the same type of plunger pump product of the plunger pump. The residual life prediction model is an intelligent model and is based on training data in a use database of the same type of plunger pump product of the plunger pump, real-time operation state information obtained through multi-dimensional monitoring is analyzed, and further the real-time residual life of the plunger pump is predicted, specifically, the same type of plunger pump refers to a pump with the same grade and the same product model, the use database refers to a database storing multiple types of plunger pump use information, the use information of each type of plunger pump is recorded in detail and used for subsequent data analysis and model training, the data in the use database possibly comprises operation time, work load, environmental conditions, fault information, maintenance records and the like of the plunger pump, and through analysis of the data, the residual life prediction model can learn key factors of performance degradation rules, residual life and residual life influence of the plunger pump. When the monitored multidimensional real-time running state information is input into the model, the residual life prediction model processes and analyzes the information and predicts the residual life of the plunger pump, wherein the residual life prediction result of the plunger pump is a dynamic real-time numerical value, and the residual life prediction result is updated continuously along with the running state and environmental condition change of the plunger pump.
In a possible implementation, step S100 further includes step S110 of randomly extracting a first usage record in the usage database, where the first usage record includes first record running status information and a first record remaining life of the first plunger pump. Randomly extracting a first usage record in a usage database, wherein the first usage record is used for randomly selecting a record from the database as sample data, and comprises the operation state information of a first plunger pump (namely, the selected plunger pump) at a certain moment or within a certain period of time and the corresponding residual service life, and specifically, the first recorded operation state information is used for monitoring and recording various state data of the first plunger pump in the operation process, including but not limited to parameters such as pressure, flow, temperature, vibration and the like; the first recorded remaining life refers to the estimated remaining life of the first plunger pump in the current state calculated or inferred from the data in the usage record, typically a relative value indicating the duration or period of time that the pump may be able to continue to operate for a future period of time. The method further comprises step S120, wherein a first state similarity is obtained, and the first state similarity refers to the similarity degree between the real-time running state information and the first recorded running state information. Specifically, the first state similarity refers to the similarity degree between the real-time running state information and the first recorded running state information, and is generally based on the feature between the two state information for matching comparison, and the calculation of the state similarity is helpful to evaluate the proximity degree between the current real-time running state and a certain past state, so as to infer the residual life possibly corresponding to the current state. Step S130 is further included, if the first state similarity reaches a predetermined similarity threshold, adding the remaining life of the first record to a preliminary prediction result set. If the first state similarity reaches a predetermined similarity threshold, indicating that the real-time operating state is very similar to the first record operating state, the remaining life information in the first record may have an important reference value for the remaining life prediction of the current state, and the first record remaining life is added to a preliminary prediction result set, wherein the preliminary prediction result set is a set for storing all remaining life values satisfying the similarity threshold condition. And step S140, the residual life prediction model takes the mode residual life value of each recorded residual life in the preliminary prediction result set as the predicted real-time residual life. In the process of predicting the residual life, after a preliminary predicting result set is obtained, namely the set contains a plurality of recorded residual life values which are screened based on state similarity, the mode of the residual life values is needed to be determined from the set to serve as the final predicted real-time residual life, specifically, the model can count the residual life value with the largest occurrence number in the preliminary predicting result set, namely the mode residual life value, and the residual life value is used as a predicting result of the current real-time residual life of the plunger pump to obtain the predicted real-time residual life.
In a possible implementation manner, step S120 further includes step S121, where a first operation feature is obtained, where the first operation feature corresponds to a first predetermined label scheme. Specific operation characteristics corresponding to a first preset label scheme are extracted from the real-time operation state information, and in particular, the first preset label scheme is used for classifying and identifying the operation state characteristics of the plunger pump, and the first operation characteristics reflect certain key aspects of the plunger pump in the current operation state, such as load conditions, working environments, performance performances and the like. And step S122, extracting a first real-time characteristic parameter in the real-time running state information and a first record characteristic parameter in the first record running state information based on the first running characteristic respectively. According to the determined first operation characteristics, corresponding recording characteristic parameters are respectively extracted from the real-time operation state information and the first recording operation state information, specifically, parameter values corresponding to the first operation characteristics are found out from the currently collected sensor data, and the specific performance of the plunger pump in the real-time operation process is reflected; and (3) finding out a parameter value corresponding to the first operation characteristic from the historical database, and recording the operation state of the plunger pump at a certain time or within a certain period of time in the past for comparison and matching with the real-time state. And step S123, sequentially obtaining the first real-time tag of the first real-time characteristic parameter and the first record tag of the first record characteristic parameter according to the first predetermined tag scheme. And according to the determined first preset label scheme, labeling the extracted first real-time characteristic parameters and the first recording characteristic parameters to obtain corresponding first real-time labels and first recording labels. The method further comprises step S124, wherein a real-time label vector of the real-time running state information is obtained based on the first real-time label, and a first record label vector of the first record running state information is obtained based on the first record label. The first real-time tag and the first record tag are converted into vector forms so as to facilitate subsequent mathematical calculation and comparison, wherein the tag vector is a data structure and is used for representing a series of tag sets, the real-time tag vector comprises tags of all relevant characteristic parameters in real-time running state information, and the first record tag vector comprises tags of corresponding characteristic parameters in the first record running state information. The method further includes step S125, retrieving a predetermined similarity function to analyze the real-time tag vector and the first record tag vector, so as to obtain the first state similarity. Calculating the similarity degree between the real-time tag vector and the first record tag vector by using a similarity function so as to obtain first state similarity, wherein the predetermined similarity function is used for measuring the similarity or difference between the two vectors, specifically, the real-time tag vector and the first record tag vector are taken as input parameters to be transmitted into the function, the similarity function compares and analyzes the two vectors according to an internal algorithm of the similarity function, and calculates a similarity score between the two vectors, namely the first state similarity, reflecting the similarity degree of the real-time running state information and the first record running state information on a tag layer, and the higher the similarity score is, the closer the two states are; the lower the score, the greater the difference between states is explained.
In a possible implementation manner, step S125 further includes the following expression of the predetermined similarity function:
T（，/>）/>；
Wherein, T is% ，/>) Means the real-time running state information/>With the first recorded running state information/>The first state similarity between/>Means the real-time running state information/>Corresponding real-time tag vector and first recorded tag vector/>The number of matching pairs of corresponding said first record label vectors being identical,Means the real-time running state information/>Corresponding real-time tag vector and first recorded tag vector/>And the total number of matched pairs of the corresponding first record label vector.
And step 200, reading a predetermined life loss analysis function, and analyzing the predetermined service life of the plunger pump based on the predetermined life loss analysis function to obtain a predetermined real-time residual life. The predetermined life loss analysis function is used for analyzing and predicting the life loss condition of the plunger pump, accurately reflecting the life decay law of the plunger pump, wherein the predetermined service life refers to the total life expected or the effective working time of the plunger pump when the plunger pump is designed to leave the factory, is generally estimated based on materials, structures, performances and the like of equipment, specifically, the predetermined service life of the plunger pump is analyzed based on the predetermined life loss analysis function, and comprises the steps of considering the current working state, the running environment, the load condition and the like of the plunger pump, quantitatively calculating the life loss in combination with the predetermined service life of the plunger pump, and obtaining the result of analysis is the predetermined real-time residual life, namely the residual time expected to be capable of continuously working by the plunger pump under the current condition.
In a possible implementation manner, step S200 further includes step S210, where a target usage record of the plunger pump is obtained, where the target usage record includes multiple usage records. A series of usage records of the plunger pump in actual use are collected and tidied, and the records reflect usage conditions and historical data of the plunger pump under different conditions at different times, wherein the target usage record is an integrated data set and contains detailed information of multiple usage of the plunger pump, specifically, the target usage record may include usage time (working time of the plunger pump), working load (load condition to evaluate working strength and condition of equipment), environmental condition (environmental parameters such as environmental temperature, humidity and the like at the time of use), fault record (related fault information, processing measures and results), maintenance information (maintenance condition, such as replacement of parts, lubrication, maintenance), etc. The method also comprises a step S220 of randomly extracting a first usage record in the multiple usage records and obtaining a first usage index according to the first usage record. Randomly selecting one record from multiple use records as a first use record, and calculating a first use index based on information in the record, wherein the first use index refers to use factors including use working conditions, use modes and environmental conditions, and particularly, working conditions include pressure, temperature, viscosity and corrosiveness of a medium, and working frequency and load period of a plunger pump; whether or not the operation manual is used correctly, such as start, stop, cleaning, and maintenance procedures; the position and action of the plunger pump throughout the system, e.g., piping design, valve configuration, etc.; extreme temperatures and humidity can affect the performance, material properties, and corrosion of plunger pumps and failure of electronic components; corrosive gases and chemicals accelerate wear and damage of the plunger pump. The method further comprises step S230, wherein the target maintenance record of the plunger pump is obtained, and the target maintenance record comprises a plurality of maintenance records. The method comprises the steps of collecting and collating multiple maintenance and inspection records of the plunger pump during the service life of the plunger pump, wherein the records are important data about the maintenance history of the plunger pump and reflect the maintenance condition, inspection result and possible problems of the equipment at different time points, and the target maintenance record is a comprehensive data set and comprises detailed information of multiple maintenance and inspection of the plunger pump, and can be from maintenance logs, maintenance reports, periodic inspection records and the like of the equipment. And step S240, randomly extracting a first dimension check record in the plurality of dimension check records, and obtaining a first dimension check index according to the first dimension check record. The maintenance condition or health state of the plunger pump in the first maintenance record is reflected by randomly selecting one record from the multiple maintenance records, calculating a first maintenance index based on the content of the record, and by comparing the maintenance indexes recorded by different maintenance records, the performance difference and health condition of the plunger pump under different maintenance conditions can be evaluated, wherein the first maintenance index can be calculated based on various factors, such as maintenance frequency, maintenance content, condition of replacement parts, and advantages and disadvantages of the inspection result. And step S250, according to the predetermined life loss analysis function, calculating and analyzing the predetermined service life by combining a target use index obtained based on the first use index and a target dimension index obtained based on the first dimension index to obtain the predetermined real-time residual life of the plunger pump. The target use index and the target maintenance index are further calculated or comprehensively obtained values based on the first use index and the first maintenance index, so that the overall condition of the plunger pump in use and maintenance can be more comprehensively reflected, the preset service life of the plunger pump can be calculated and analyzed by combining a preset service life loss analysis function, the target use index and the target maintenance index, and the target maintenance index comprises lubrication (the lubrication oil is replaced regularly and the oil quality is checked regularly, so that the normal operation of a lubrication system is ensured); cleaning (periodic cleaning of the pump interior, removal of deposits and impurities, protection against wear and clogging); checking and replacing, periodically checking the state of vulnerable parts (such as sealing elements, valves, filter screens and the like) and replacing the vulnerable parts in time, specifically, taking a target index as an input parameter of a function, predicting the life loss condition of equipment in the current state and under the condition through calculation of the function, wherein accidents or quality fluctuation possibly occur in the process of calculation and analysis of the service life, such as operation errors, external force impact, power interruption and other unpredictable events or quality fluctuation of parts provided by suppliers influence the service life of the plunger pump, the preset real-time residual life of the plunger pump can be obtained according to the result of calculation and analysis, which shows that under the current use and maintenance condition, the plunger pump is expected to be able to continue to operate for a remaining time or life.
In a possible implementation manner, step S250 further includes step S251, where the first usage record includes first usage operation information, first usage condition information, and first usage environment information. The first usage operation information describes the specific operation condition of the plunger pump when in use, and may include the start-up and stop time of the device, the change condition of parameters such as speed, pressure, flow rate and the like in the running process, and any special operation instruction or mode; the first usage condition information describes specific working conditions and task requirements of the plunger pump when in use, and may include factors such as workload, operation period, task type, working strength, etc., for example, if the plunger pump is used for petroleum exploitation, the condition information may include depth of an oil well, viscosity of crude oil, exploitation rate, etc.; the first usage environment information describes the external environmental conditions of the plunger pump when in use, which may include environmental factors such as temperature, humidity, pressure, vibration, dust, etc. The method also comprises a step S252 of determining a first operation index according to a first operation deviation obtained by comparing the first usage operation information with the preset operation information and generating a target operation index. The predetermined operating information is typically a set of standard or expected operating parameters and patterns representing the operating requirements of the device in an ideal or standard operating state, comparing the first usage operating information with the predetermined operating information means that the actual operating parameters (such as start time, stop time, running speed, pressure control, etc.) are compared item by item with the predetermined standard or expected values, a difference or deviation between the two is identified, i.e. a first operating deviation, reflecting the degree of deviation between the actual usage operation and the standard or expected operation, the first operating index is further determined based on the first operating deviation for evaluating the compliance and quality of the operation, e.g. for a behaviour deviating seriously from the predetermined operating information, the operating index may be lower, indicating poor quality of operation; and for the behavior close to or conforming to the preset operation information, the operation index is higher, and the obtained operation indexes are weighted and averaged to finally generate the target operation index. The method further includes step S253, wherein the first operating condition index is determined by weighting the first operating condition characteristic parameter in the first usage operating condition information, and the target operating condition index is generated. And carrying out weighted processing on the first operation state characteristic parameters in the first using operation state information to determine a first operation state index, wherein the first operation state index is used for quantitatively evaluating the operation state of the equipment under a specific operation state, and finally generating a target operation state index which may be a comprehensive result based on a plurality of using records or operation state indexes under a plurality of operation states. Further comprising step S254, determining a first environment index by weighting a first environment characteristic parameter in the first usage environment information, and generating a target environment index. And carrying out weighting processing on the first environment characteristic parameters in the first using environment information to determine a first environment index, wherein the first environment index is used for quantitatively evaluating the running state of the equipment in a specific environment, and finally generating a target environment index which may be a comprehensive result based on the environment index in the multi-use environment. And step S255, weighting the target operation index, the target working condition index and the target environment index to obtain the target use index. The three indexes of different dimensions, namely the target operation index, the target working condition index and the target environment index, are combined through a certain weight distribution mode to form a comprehensive target use index capable of comprehensively reflecting the use condition of the plunger pump.
In a possible implementation manner, step S240 further includes step S241, where the first dimension record includes a first dimension time and first dimension information. The first dimension time refers to a specific point in time or period of time at which a maintenance inspection is performed, including a start time, an end time, and possibly a duration of the dimension; the first inspection information refers to specific data collected during maintenance inspection, including lubrication cycle, leakage, cleaning condition, plunger pump cleanliness, presence of contaminants, and the like. And step S242, the first lubrication dimension inspection index obtained by weighting and analyzing the first lubrication system dimension inspection information in the first dimension inspection information and the first cleaning dimension inspection index obtained by analyzing the first cleaning dimension inspection information in the first dimension inspection information are weighted and analyzed to obtain a first initial dimension inspection index. Extracting maintenance information related to a lubrication system and cleaning from the first maintenance information, wherein the maintenance information comprises concrete data such as the replacement condition of lubricating oil, the running condition of the lubrication system, the execution condition of cleaning operation, the effect after cleaning and the like, and respectively analyzing and calculating corresponding first lubrication maintenance indexes based on the extracted lubrication system maintenance information and the extracted cleaning maintenance information to quantitatively reflect the maintenance condition and the performance of the lubrication system; for the cleaning maintenance information, the cleaning effect can be evaluated according to the execution condition of the cleaning operation, the cleanliness of the device after cleaning, whether residues or pollutants exist or not and the like, and a first cleaning maintenance index is calculated, so that the quality and effect of the cleaning maintenance work are quantitatively reflected; and carrying out weighted analysis on the first lubrication maintenance index and the first cleaning maintenance index, and combining the first lubrication maintenance index and the first cleaning maintenance index into a comprehensive maintenance index according to the importance of the lubrication system and the cleaning in equipment maintenance to obtain a first initial maintenance index. And step S243, analyzing the first dimension detection time to obtain a first dimension detection frequency, and weighting the first initial dimension detection index to obtain the first dimension detection index. The first dimension inspection time is analyzed to obtain a first dimension inspection frequency, the dimension inspection time is analyzed to calculate the dimension inspection times of the plunger pump in a specific time period, namely the dimension inspection frequency, the dimension inspection of high frequency possibly means that the equipment needs more attention and maintenance, the dimension inspection of low frequency possibly means that the equipment state is relatively stable or the maintenance plan is not reasonable enough, the first initial dimension inspection index and the first dimension inspection frequency are subjected to weighted analysis, namely the first initial dimension inspection index and the first dimension inspection frequency are allocated with proper weights to calculate the first dimension inspection index, and the maintenance quality of the equipment and the timeliness and regularity of the maintenance are comprehensively considered.
And step S300, weighting the predicted real-time residual life and the preset real-time residual life after normalization processing to obtain the target residual life of the plunger pump. According to the respective reliability and precision of the predicted real-time residual life and the predicted real-time residual life, different weights are distributed, weighting processing is carried out, the predicted real-time residual life and the predicted real-time residual life possibly differ due to calculation modes, units or other factors, normalization can ensure that the predicted real-time residual life and the predicted real-time residual life can be directly used in subsequent calculation, after weighting and normalization processing are completed, two processed residual life values are combined, the target residual life of the plunger pump is obtained through calculation, the finally obtained target residual life is a numerical value integrating the predicted real-time residual life and the predicted real-time residual life, and the relative importance and dimensional difference of the two data are considered, so that more accurate life prediction is provided for the use and maintenance of the plunger pump.
Hereinabove, the method of predicting the remaining life of the plunger pump according to the embodiment of the present invention is described in detail with reference to fig. 1. Next, a residual life prediction system of a plunger pump according to an embodiment of the present invention will be described with reference to fig. 2.
The system for predicting the residual life of the plunger pump is used for solving the technical problems that the existing system for predicting the residual life of the plunger pump cannot accurately acquire real-time operation data of the pump and the analysis result of the performance degradation trend of the pump is inaccurate, so that the residual life of the plunger pump is inaccurate, and the technical effects of improving the accuracy and the reliability of the residual life prediction result of the plunger pump are achieved. The plunger pump remaining life prediction system includes: the predicted real-time remaining life obtaining module 10, the predetermined real-time remaining life obtaining module 20, the target remaining life obtaining module 30.
The predicted real-time residual life obtaining module 10 is used for analyzing the real-time running state information of the plunger pump obtained through multi-dimensional monitoring through a residual life predicting model to obtain the predicted real-time residual life, wherein the residual life predicting model is an intelligent model obtained through training data in a use database of the same type of plunger pump product of the plunger pump;
The device comprises a preset real-time residual life acquisition module 20, wherein the preset real-time residual life acquisition module 20 is used for reading a preset life loss analysis function and analyzing the preset service life of the plunger pump based on the preset life loss analysis function to obtain the preset real-time residual life;
The target remaining life obtaining module 30 is configured to weight the predicted real-time remaining life and the predetermined real-time remaining life after normalization processing, to obtain the target remaining life of the plunger pump.
Next, the specific configuration of the predicted real-time remaining life obtaining module 10 will be described in detail. The predicted real-time remaining life obtaining module 10 further includes: randomly extracting a first usage record in the usage database, wherein the first usage record comprises first record running state information and first record residual life of a first plunger pump; acquiring a first state similarity, wherein the first state similarity refers to the similarity degree of the real-time running state information and the first recorded running state information; if the first state similarity reaches a preset similarity threshold, adding the residual life of the first record to a primary prediction result set; and the residual life prediction model takes the mode residual life value of each recorded residual life in the preliminary prediction result set as the predicted real-time residual life.
Next, the specific configuration of the predicted real-time remaining life obtaining module 10 will be described in further detail. The predicted real-time remaining life obtaining module 10 may further include: acquiring a first operation characteristic, wherein the first operation characteristic corresponds to a first preset label scheme; extracting a first real-time characteristic parameter in the real-time running state information and a first record characteristic parameter in the first record running state information based on the first running characteristic respectively; sequentially acquiring a first real-time tag of the first real-time characteristic parameter and a first record tag of the first record characteristic parameter according to the first preset tag scheme; obtaining a real-time tag vector of the real-time running state information based on the first real-time tag, and obtaining a first record tag vector of the first record running state information based on the first record tag; and calling a predetermined similarity function to analyze the real-time tag vector and the first record tag vector, so as to obtain the first state similarity.
Next, the specific configuration of the predicted real-time remaining life obtaining module 10 will be described in further detail. The predicted real-time remaining life obtaining module 10 may further include: the expression of the predetermined similarity function is as follows:
T（，/>）/>；
Wherein, T is% ，/>) Means the real-time running state information/>With the first recorded running state information/>The first state similarity between/>Means the real-time running state information/>Corresponding real-time tag vector and first recorded tag vector/>The number of matching pairs of corresponding said first record label vectors being identical,Means the real-time running state information/>Corresponding real-time tag vector and first recorded tag vector/>And the total number of matched pairs of the corresponding first record label vector.
Next, the specific configuration of the predetermined real-time remaining life acquisition module 20 will be described in detail. The predetermined real-time remaining life acquisition module 20 further includes: acquiring a target usage record of the plunger pump, wherein the target usage record comprises a plurality of usage records; randomly extracting a first use record in the multiple use records, and obtaining a first use index according to the first use record; acquiring a target maintenance record of the plunger pump, wherein the target maintenance record comprises a plurality of maintenance records; randomly extracting a first dimension check record in the plurality of dimension check records, and obtaining a first dimension check index according to the first dimension check record; and according to the predetermined life loss analysis function, calculating and analyzing the predetermined service life by combining a target use index obtained based on the first use index and a target dimension index obtained based on the first dimension index to obtain the predetermined real-time residual life of the plunger pump.
Next, the specific configuration of the predetermined real-time remaining life acquisition module 20 will be described in further detail. The predetermined real-time remaining life acquisition module 20 further includes: the first use record comprises first use operation information, first use condition information and first use environment information; determining a first operation index according to a first operation deviation obtained by comparing the first usage operation information with the preset operation information, and generating a target operation index; weighting a first operation state characteristic parameter in the first using operation state information to determine a first operation state index, and generating a target operation state index; weighting a first environment characteristic parameter in the first using environment information to determine a first environment index, and generating a target environment index; and weighting the target operation index, the target working condition index and the target environment index to obtain the target use index.
Next, the specific configuration of the predetermined real-time remaining life acquisition module 20 will be described in further detail. The predetermined real-time remaining life acquisition module 20 may further include: the first dimension check record comprises first dimension check time and first dimension check information; the method comprises the steps of weighting and analyzing a first lubrication dimension inspection index obtained by first lubrication system dimension inspection information in the first dimension inspection information and a first cleaning dimension inspection index obtained by analyzing first cleaning dimension inspection information in the first dimension inspection information to obtain a first initial dimension inspection index; analyzing the first dimension detection time to obtain a first dimension detection frequency, and weighting the first initial dimension detection index to obtain the first dimension detection index.
The residual life prediction system of the plunger pump provided by the embodiment of the invention can execute the residual life prediction method of the plunger pump provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
Although the present application makes various references to certain modules in a system according to embodiments of the present application, any number of different modules may be used and run on a user terminal and/or server, including units and modules that are merely partitioned by functional logic, but are not limited to the above-described partitioning, so long as the corresponding functionality is enabled; in addition, the specific names of the functional units are also only for distinguishing from each other, and are not used to limit the protection scope of the present application.
The above embodiments do not limit the scope of the present application. It will be apparent to those skilled in the art that various modifications, combinations, and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the scope of the present application.
Claims (8)
1. The method for predicting the residual life of the plunger pump is characterized by comprising the following steps:
Analyzing real-time running state information of the plunger pump obtained through multi-dimensional monitoring through a residual life prediction model to obtain predicted real-time residual life, wherein the residual life prediction model is an intelligent model obtained by training data in a use database of the same type of plunger pump product of the plunger pump;
Reading a predetermined life loss analysis function, and analyzing the predetermined service life of the plunger pump based on the predetermined life loss analysis function to obtain a predetermined real-time residual life;
And weighting the predicted real-time residual life and the preset real-time residual life after normalization processing to obtain the target residual life of the plunger pump.
2. The method of predicting remaining life of a plunger pump as set forth in claim 1, wherein the process of obtaining the predicted real-time remaining life comprises:
Randomly extracting a first usage record in the usage database, wherein the first usage record comprises first record running state information and first record residual life of a first plunger pump;
acquiring a first state similarity, wherein the first state similarity refers to the similarity degree of the real-time running state information and the first recorded running state information;
If the first state similarity reaches a preset similarity threshold, adding the residual life of the first record to a primary prediction result set;
And the residual life prediction model takes the mode residual life value of each recorded residual life in the preliminary prediction result set as the predicted real-time residual life.
3. The method of predicting remaining life of a plunger pump of claim 2, wherein the process of obtaining the first state similarity comprises:
acquiring a first operation characteristic, wherein the first operation characteristic corresponds to a first preset label scheme;
Extracting a first real-time characteristic parameter in the real-time running state information and a first record characteristic parameter in the first record running state information based on the first running characteristic respectively;
Sequentially acquiring a first real-time tag of the first real-time characteristic parameter and a first record tag of the first record characteristic parameter according to the first preset tag scheme;
Obtaining a real-time tag vector of the real-time running state information based on the first real-time tag, and obtaining a first record tag vector of the first record running state information based on the first record tag;
And calling a predetermined similarity function to analyze the real-time tag vector and the first record tag vector, so as to obtain the first state similarity.
4. A method of predicting remaining life of a plunger pump as set forth in claim 3, wherein the expression of the predetermined similarity function is as follows:
T（，/>）/>；
Wherein, T is% ，/>) Means the real-time running state information/>With the first recorded running state information/>The first state similarity between/>Means the real-time running state information/>Corresponding real-time tag vector and first recorded tag vector/>The number of matching pairs of corresponding said first record label vectors being identical,Means the real-time running state information/>Corresponding real-time tag vector and first recorded tag vector/>And the total number of matched pairs of the corresponding first record label vector.
5. The method of predicting remaining life of a plunger pump as set forth in claim 1, wherein the process of obtaining a predetermined real-time remaining life comprises:
Acquiring a target usage record of the plunger pump, wherein the target usage record comprises a plurality of usage records;
Randomly extracting a first use record in the multiple use records, and obtaining a first use index according to the first use record;
acquiring a target maintenance record of the plunger pump, wherein the target maintenance record comprises a plurality of maintenance records;
randomly extracting a first dimension check record in the plurality of dimension check records, and obtaining a first dimension check index according to the first dimension check record;
And according to the predetermined life loss analysis function, calculating and analyzing the predetermined service life by combining a target use index obtained based on the first use index and a target dimension index obtained based on the first dimension index to obtain the predetermined real-time residual life of the plunger pump.
6. The method of predicting remaining life of a plunger pump as set forth in claim 5, wherein the process of obtaining the target usage index comprises:
The first use record comprises first use operation information, first use condition information and first use environment information;
Determining a first operation index according to a first operation deviation obtained by comparing the first usage operation information with the preset operation information, and generating a target operation index;
weighting a first operation state characteristic parameter in the first using operation state information to determine a first operation state index, and generating a target operation state index;
Weighting a first environment characteristic parameter in the first using environment information to determine a first environment index, and generating a target environment index;
and weighting the target operation index, the target working condition index and the target environment index to obtain the target use index.
7. The method of predicting remaining life of a plunger pump of claim 5, wherein the process of obtaining a first dimension index comprises:
the first dimension check record comprises first dimension check time and first dimension check information;
The method comprises the steps of weighting and analyzing a first lubrication dimension inspection index obtained by first lubrication system dimension inspection information in the first dimension inspection information and a first cleaning dimension inspection index obtained by analyzing first cleaning dimension inspection information in the first dimension inspection information to obtain a first initial dimension inspection index;
analyzing the first dimension detection time to obtain a first dimension detection frequency, and weighting the first initial dimension detection index to obtain the first dimension detection index.
8. A plunger pump remaining life prediction system for implementing the plunger pump remaining life prediction method according to any one of claims 1 to 7, comprising:
The system comprises a predicted real-time residual life obtaining module, a real-time monitoring module and a real-time monitoring module, wherein the predicted real-time residual life obtaining module is used for analyzing real-time running state information of a plunger pump obtained through multi-dimensional monitoring through a residual life predicting model to obtain a predicted real-time residual life, and the residual life predicting model is an intelligent model obtained through training data in a use database of the same type of plunger pump product of the plunger pump;
The system comprises a preset real-time residual life acquisition module, a preset real-time residual life analysis module and a control module, wherein the preset real-time residual life acquisition module is used for reading a preset life loss analysis function and analyzing the preset service life of the plunger pump based on the preset life loss analysis function to obtain the preset real-time residual life;
the target remaining life obtaining module is used for weighting the predicted real-time remaining life and the preset real-time remaining life after normalization processing to obtain the target remaining life of the plunger pump.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410541568.8A CN118114081B (en) | 2024-04-30 | 2024-04-30 | Method and system for predicting residual life of plunger pump |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410541568.8A CN118114081B (en) | 2024-04-30 | 2024-04-30 | Method and system for predicting residual life of plunger pump |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118114081A true CN118114081A (en) | 2024-05-31 |
| CN118114081B CN118114081B (en) | 2024-08-30 |
Family
ID=91221284
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410541568.8A Active CN118114081B (en) | 2024-04-30 | 2024-04-30 | Method and system for predicting residual life of plunger pump |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118114081B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115640652A (en) * | 2022-10-10 | 2023-01-24 | 武汉科技大学 | Method for predicting residual life of axial plunger pump |
| CN115935622A (en) * | 2022-11-25 | 2023-04-07 | 武汉科技大学 | Axial plunger pump residual life prediction method based on joint model identification |
| CN116878839A (en) * | 2023-07-11 | 2023-10-13 | 北京唐智科技发展有限公司 | Method, device, equipment and storage medium for predicting service life of mechanical equipment |
| WO2023216015A1 (en) * | 2022-05-07 | 2023-11-16 | 潍柴动力股份有限公司 | Method for predicting remaining service life of urea pump and related apparatus |
| WO2024077685A1 (en) * | 2022-10-11 | 2024-04-18 | 烟台杰瑞石油装备技术有限公司 | Service life prediction method and apparatus for oil and gas fracturing pump device, and non-volatile storage medium |
-
2024
- 2024-04-30 CN CN202410541568.8A patent/CN118114081B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023216015A1 (en) * | 2022-05-07 | 2023-11-16 | 潍柴动力股份有限公司 | Method for predicting remaining service life of urea pump and related apparatus |
| CN115640652A (en) * | 2022-10-10 | 2023-01-24 | 武汉科技大学 | Method for predicting residual life of axial plunger pump |
| WO2024077685A1 (en) * | 2022-10-11 | 2024-04-18 | 烟台杰瑞石油装备技术有限公司 | Service life prediction method and apparatus for oil and gas fracturing pump device, and non-volatile storage medium |
| CN115935622A (en) * | 2022-11-25 | 2023-04-07 | 武汉科技大学 | Axial plunger pump residual life prediction method based on joint model identification |
| CN116878839A (en) * | 2023-07-11 | 2023-10-13 | 北京唐智科技发展有限公司 | Method, device, equipment and storage medium for predicting service life of mechanical equipment |
Non-Patent Citations (1)
| Title |
|---|
| 刘杨成;: "混凝土泵车砼活塞剩余寿命预测方法研究", 现代制造工程, no. 08, 18 August 2020 (2020-08-18) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118114081B (en) | 2024-08-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Baur et al. | A review of prognostics and health management of machine tools | |
| CN109524139B (en) | Real-time equipment performance monitoring method based on equipment working condition change | |
| Heng et al. | Rotating machinery prognostics: State of the art, challenges and opportunities | |
| US7496798B2 (en) | Data-centric monitoring method | |
| CN101770219B (en) | Knowledge acquisition method of fault diagnosis knowledge library of turn-milling combined machine tool | |
| CN105930963B (en) | Electromechanical system equipment health assessment method | |
| Goodall et al. | Concepts and techniques for railway condition monitoring | |
| Li et al. | Preventive maintenance decision model of urban transportation system equipment based on multi-control units | |
| Zschech et al. | Prognostic model development with missing labels: a condition-based maintenance approach using machine learning | |
| CN116292241A (en) | Fault diagnosis early warning method and system for oil delivery pump unit | |
| Becherer et al. | Intelligent choice of machine learning methods for predictive maintenance of intelligent machines | |
| Saranya et al. | Data-driven prognostics for run-to-failure data employing machine learning models | |
| CN116235148A (en) | Early warning method and device for downtime of dry pump, electronic equipment, storage medium and program | |
| Calabrese et al. | An event based machine learning framework for predictive maintenance in industry 4.0 | |
| CN117782580B (en) | Defect detection method and system for automobile parts | |
| Montgomery et al. | Minor maintenance actions and their impact on diagnostic and prognostic CBM models | |
| Guo et al. | Manufacturing process monitoring with nonparametric change-point detection in automotive industry | |
| CN118114081B (en) | Method and system for predicting residual life of plunger pump | |
| Kobbacy et al. | Condition monitoring of diesel engines | |
| Srivyas et al. | Study of various maintenance approaches types of failure and failure detection techniques used in hydraulic pumps: a review | |
| Seo et al. | Gearbox Condition Monitoring and Diagnosis of Unlabeled Vibration Signals Using a Supervised Learning Classifier | |
| Morgan et al. | Predicting future states with $ n $-dimensional Markov chains for fault diagnosis | |
| Joelian | Engine replacement scheduling optimization using Data Mining | |
| Helge Nystad et al. | Remaining useful life of natural gas export compressors | |
| CN117972989B (en) | Service life prediction method and system for coal machine equipment |
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 |