CN112539828B - Pump unit equipment diagnosis method, system and equipment based on curve fitting contrast analysis - Google Patents
Pump unit equipment diagnosis method, system and equipment based on curve fitting contrast analysis Download PDFInfo
- Publication number
- CN112539828B CN112539828B CN202011422670.4A CN202011422670A CN112539828B CN 112539828 B CN112539828 B CN 112539828B CN 202011422670 A CN202011422670 A CN 202011422670A CN 112539828 B CN112539828 B CN 112539828B
- Authority
- CN
- China
- Prior art keywords
- vibration data
- pump set
- set equipment
- error limit
- period
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H17/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups
-
- 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
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
Abstract
The invention discloses a pump set equipment diagnosis method based on curve fitting contrastive analysis, which comprises the following steps: sampling pump set equipment to obtain vibration data; judging the period of the vibration data, and calculating the upper error limit and the lower error limit of the vibration data of each corresponding point position in different periods; establishing a rectangular coordinate system by taking time as a horizontal axis and numerical values of vibration data as a vertical axis, connecting the upper error limit of each point location as an upper limit curve, sequentially connecting the lower error limit of each point location as a lower limit curve, and setting the part between the upper limit curve and the lower limit curve as a vibration allowable domain; and judging the health state of the pump set equipment by comparing whether the real-time vibration data of the pump set equipment is in the vibration allowable domain.
Description
Technical Field
The invention relates to the field of equipment diagnosis, in particular to a pump set equipment diagnosis method, system and equipment based on curve fitting contrastive analysis.
Background
The main parts in the pump unit do rotary motion, so the vibration of the pump unit belongs to periodic vibration, and the period is kept relatively stable.
The existing stability state early warning method is a simple absolute value comparison method, namely, vibration, swing and pressure pulsation are obtained through field test or on-line monitoring and are compared with national and industrial standards, and the method has certain guiding significance for field operation. However, the simple absolute value comparison method has low precision and single limit value in practical application, and cannot adapt to complicated environments and different types of equipment on site.
Disclosure of Invention
In order to solve the technical problems, the invention provides a pump set equipment diagnosis method, system and equipment based on curve fitting contrast analysis.
In order to solve the technical problems, the invention adopts the following technical scheme:
a pump set equipment diagnosis method based on curve fitting contrast analysis comprises the following steps:
the method comprises the following steps: sampling pump set equipment to obtain vibration data;
step two: judging the period of the vibration data, and calculating the upper error limit and the lower error limit of the vibration data of each corresponding point position in different periods;
step three: establishing a rectangular coordinate system by taking time as a horizontal axis and numerical values of vibration data as a vertical axis, connecting the upper error limit of each point location as an upper limit curve, sequentially connecting the lower error limit of each point location as a lower limit curve, and setting the part between the upper limit curve and the lower limit curve as a vibration allowable domain;
step four: and judging the health state of the pump set equipment by comparing whether the real-time vibration data of the pump set equipment is in the vibration allowable domain.
In particular, the vibration data is the amplitude of the pump set equipment.
Specifically, when the period of the vibration data is determined in the step two, after the pump set device operates stably, the amplitude of the pump set device in a single direction changes periodically, and the time interval between two adjacent maximum amplitudes of the pump set device is used as the period of the vibration data.
Specifically, in the second step, when the upper error limit and the lower error limit of the vibration data of each corresponding point location in different periods are calculated, one period is selected, N point locations are selected at equal time intervals in the period, and the expected μ and standard deviation S of the corresponding amplitude of each point location in different periods are calculated, so that the upper error limit of the point location is μ -3S, and the lower error limit of the point location is μ +3S.
Specifically, in the third step, when the real-time vibration data of the pump set equipment is compared to determine whether the vibration data is in the vibration allowable domain, firstly, a time point is determined on the horizontal axis of the rectangular coordinate system according to the time of the vibration data, and whether the amplitude of the vibration data is in the range of the vibration allowable domain is judged.
A pump unit equipment diagnostic system based on curve fitting contrastive analysis, comprising:
the data acquisition module is used for sampling the pump set equipment to obtain vibration data;
the error calculation module judges the period of the vibration data and calculates the upper error limit and the lower error limit of the vibration data of each corresponding point in different periods;
the curve fitting module is used for establishing a rectangular coordinate system by taking time as a horizontal axis and numerical values of vibration data as a vertical axis, connecting the upper error limit of each point position as an upper limit curve, sequentially connecting the lower error limit of each point position as a lower limit curve, and setting the part between the upper limit curve and the lower limit curve as a vibration allowable domain;
and the health state judging module judges the health state of the pump set equipment by comparing whether the real-time vibration data of the pump set equipment is in the vibration allowable domain.
A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the pump group device diagnosis method when executing the computer program.
Compared with the prior art, the invention has the beneficial technical effects that:
according to the method, the expectation and the variance of each point position are obtained by carrying out statistical calculation on the amplitude values of corresponding point positions in different periods, the upper error limit and the lower error limit of the vibration of the pump set are obtained according to a normal distribution rule, and an upper limit curve, a lower limit curve and a vibration allowable domain are established; comparing the real-time amplitude of the pump set equipment with a vibration allowable domain in a rectangular coordinate system, and if the amplitude is in the vibration allowable domain, indicating that the pump set equipment is in a normal working state at the moment; otherwise, the pump unit equipment is in an abnormal working state.
Drawings
FIG. 1 is a schematic flow diagram of a pump unit apparatus diagnostic method according to the present invention;
FIG. 2 is a schematic view of the dot site of the present invention;
fig. 3 is a schematic view of the vibration allowable domain of the present invention.
Detailed Description
A preferred embodiment of the present invention will be described in detail below with reference to the accompanying drawings.
As shown in fig. 1, a pump unit equipment diagnosis method based on curve fitting contrast analysis includes the following steps:
s1: and sampling the pump set equipment to obtain vibration data.
In the embodiment, the vibration data is the amplitude of the pump set equipment; or may be a periodically varying physical quantity such as noise of the pump unit apparatus.
S2: and judging the period of the vibration data, and calculating the upper error limit and the lower error limit of the vibration data of each corresponding point in different periods.
Specifically, when the period of the vibration data is determined in the step two, after the pump set device operates stably, the amplitude of the pump set device in a single direction changes periodically, and the time interval between two adjacent maximum amplitudes of the pump set device is used as the period of the vibration data.
The periodic characteristics of the vibration data of the pump set equipment are determined by the structure of the pump set equipment; in this embodiment, only one maximum amplitude generally exists in one period of the pump set vibration data; according to the characteristics of the pump set equipment, the period of the vibration data can be judged.
Specifically, in the second step, when the upper error limit and the lower error limit of the vibration data of each corresponding point location in different periods are calculated, one period is selected, N point locations are selected at equal time intervals in the period, and the expected μ and standard deviation S of the corresponding amplitude of each point location in different periods are calculated, so that the upper error limit of the point location is μ -3S, and the lower error limit of the point location is μ +3S.
Although there are multiple operating cycles in FIG. 2, the images of each cycle are similar; in fact, if there are time points A1, A2,. AN in different periods, which have the same time interval x as the time point of the beginning of each period, the points have correlation, and their vibration directions, vibration trends, and amplitudes are approximately the same, and these points can be referred to as a point a. The relevance can be physically interpreted, when the pump set runs, each item of data naturally shows a periodic characteristic, and the physical data corresponding to two time points separated by a period or a plurality of periods are approximately the same.
The method utilizes the periodicity of vibration data of the pump set equipment to calculate the corresponding amplitude of a certain point location A, B, a.and H in each period to obtain an expectation and a standard deviation, and further obtain the upper error limit and the lower error limit of the point location; similarly, the upper error limit and the lower error limit of other point positions are obtained according to the method.
The time is inseparable, and even in a short period, numerous time points exist, so the selection number of the point positions is set according to the control precision.
Specifically, in the third step, when the real-time vibration data of the pump unit equipment is compared to determine whether the vibration data is in the vibration allowable domain, firstly, a time point is determined on the horizontal axis of the rectangular coordinate system according to the time of the vibration data, and whether the amplitude of the vibration data is in the vibration allowable domain range is judged.
S3: and establishing a rectangular coordinate system by taking time as a horizontal axis and numerical values of vibration data as a vertical axis, connecting the upper error limit of each point position as an upper limit curve, sequentially connecting the lower error limit of each point position as a lower limit curve, and setting the part between the upper limit curve and the lower limit curve as a vibration allowable domain.
If the random variable X obeys a mathematical expectation of mu and the variance of sigma 2 Normal distribution of (D), is denoted as N (μ, σ) 2 ) The expectation value μ determines the position of its probability density function, and the standard deviation σ determines the amplitude of the distribution.
By means of point location correspondence and expectation and variance calculation, amplitude characteristics in a plurality of periods are mapped into one period, so that the change of working conditions can be coped with, and the health state of pump set equipment can be reflected in time; because an average of the amplitudes of a plurality of cycles is desired, if the operating conditions change, the change can be reflected in the average; the invention also utilizes the 3 sigma principle to eliminate the gross error which is not within +/-3 sigma and carry out early warning on the unhealthy state of the pump set equipment.
According to the time sequence, the upper limit of the error of each point position is connected to generate an upper limit curve, the lower limit of the error of each point position is connected to generate a lower limit curve, and the connected curves can be straight-line segments or fitting curves.
Because the point location is selected in a limited way, the amplitude of all time points cannot be compared by the set of the upper error limit and the lower error limit, so that a relatively closed surface area can be generated in the rectangular coordinate system by curve fitting in a connection mode.
S4: and judging the health state of the pump set equipment by comparing whether the real-time vibration data of the pump set equipment is in the vibration allowable domain.
Since the vibration allowable domain in the rectangular coordinate system belongs to the vibration amplitude rationality which can only be judged in one period, after the amplitude of the pump set equipment is detected in real time by the sensor, the position of the horizontal axis on the rectangular coordinate system to which the time point of the amplitude should correspond needs to be judged according to the amplitude image of the amplitude, and whether the amplitude is in the vibration allowable domain or not is judged; if the time interval between the time point of the amplitude and the start time point of the period where the amplitude is located is y, the corresponding upper error limit and lower error limit can be searched for at the y time point of the horizontal axis of the rectangular coordinate system, and whether the amplitude is in the range of the upper error limit and the lower error limit is judged.
According to the invention, the target surface area is generated by adopting a point location plus fitting connection line mode, so that effective judgment can be still carried out even if the time point of real-time vibration data is not the point location used for establishing the rectangular coordinate system.
A pump unit equipment diagnostic system based on curve fitting contrastive analysis, comprising:
the data acquisition module is used for sampling the pump set equipment to obtain vibration data;
the error calculation module judges the period of the vibration data and calculates the upper error limit and the lower error limit of the vibration data of each corresponding point position in different periods;
the curve fitting module is used for establishing a rectangular coordinate system by taking time as a horizontal axis and numerical values of vibration data as a vertical axis, connecting the upper error limit of each point position as an upper limit curve, sequentially connecting the lower error limit of each point position as a lower limit curve, and setting the part between the upper limit curve and the lower limit curve as a vibration allowable domain;
and the health state judging module judges the health state of the pump set equipment by comparing whether the real-time vibration data of the pump set equipment is in the vibration allowable domain.
A computer arrangement comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the pump set arrangement diagnosis method when executing the computer program.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein, and any reference signs in the claims are not intended to be construed as limiting the claim concerned.
Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain only a single embodiment, and such description is for clarity only, and those skilled in the art should integrate the description, and the embodiments may be combined as appropriate to form other embodiments understood by those skilled in the art.
Claims (4)
1. A pump set equipment diagnosis method based on curve fitting contrast analysis comprises the following steps:
the method comprises the following steps: sampling pump set equipment to obtain vibration data;
step two: judging the period of the vibration data, and calculating the upper error limit and the lower error limit of the vibration data of each corresponding point position in different periods; the point location is a time point which has the same time interval with the starting time point of each period in different periods;
step three: establishing a rectangular coordinate system by taking time as a horizontal axis and numerical values of vibration data as a vertical axis, connecting the upper error limit of each point location as an upper limit curve, sequentially connecting the lower error limit of each point location as a lower limit curve, and setting the part between the upper limit curve and the lower limit curve as a vibration allowable domain;
step four: judging the health state of the pump set equipment by comparing whether the real-time vibration data of the pump set equipment is in a vibration allowable domain;
the vibration data is the amplitude of the pump set equipment;
when the period of the vibration data is judged in the second step, after the pump set equipment stably runs, the amplitude of the pump set equipment in a single direction is periodically changed, and the time interval between two adjacent maximum amplitudes of the pump set equipment is used as the period of the vibration data;
and step two, calculating the upper error limit and the lower error limit of the vibration data of each corresponding point location in different periods, selecting a period, selecting N point locations in the period at equal time intervals, and calculating the expected mu and standard deviation S of the corresponding amplitude of each point location in different periods, wherein the upper error limit of the point location is mu-3S, and the lower error limit of the point location is mu +3S.
2. The pump group facility diagnosis method based on curve fitting contrastive analysis according to claim 1, characterized in that, when the real-time vibration data of the pump group facility is compared in step three, firstly, the time point is determined on the horizontal axis of the rectangular coordinate system according to the time of the vibration data, and the amplitude is judged to be in the range of the vibration allowable domain.
3. A pump unit equipment diagnostic system based on curve fitting contrastive analysis, comprising:
the data acquisition module is used for sampling the pump set equipment to obtain vibration data;
the error calculation module judges the period of the vibration data and calculates the upper error limit and the lower error limit of the vibration data of each corresponding point position in different periods; the point location is a time point which has the same time interval with the starting time point of each period in different periods;
the curve fitting module is used for establishing a rectangular coordinate system by taking time as a horizontal axis and numerical values of vibration data as a vertical axis, connecting the upper error limit of each point position as an upper limit curve, sequentially connecting the lower error limit of each point position as a lower limit curve, and setting the part between the upper limit curve and the lower limit curve as a vibration allowable domain;
the health state judgment module judges the health state of the pump set equipment by comparing whether the real-time vibration data of the pump set equipment is in a vibration allowable domain;
the vibration data is the amplitude of the pump set equipment;
when the period of the vibration data is judged, after the pump set equipment stably runs, the amplitude of the pump set equipment in a single direction is periodically changed, and the time interval between two adjacent maximum amplitudes of the pump set equipment is taken as the period of the vibration data;
and calculating the upper error limit and the lower error limit of the vibration data of each corresponding point location in different periods, selecting a period, selecting N point locations at equal time intervals in the period, and calculating the expected mu and standard deviation S of the corresponding amplitude of each point location in different periods, wherein the upper error limit of the point location is mu-3S, and the lower error limit of the point location is mu +3S.
4. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the pump group device diagnostic method according to claim 1 or 2 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011422670.4A CN112539828B (en) | 2020-12-08 | 2020-12-08 | Pump unit equipment diagnosis method, system and equipment based on curve fitting contrast analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011422670.4A CN112539828B (en) | 2020-12-08 | 2020-12-08 | Pump unit equipment diagnosis method, system and equipment based on curve fitting contrast analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112539828A CN112539828A (en) | 2021-03-23 |
| CN112539828B true CN112539828B (en) | 2023-03-21 |
Family
ID=75019322
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011422670.4A Active CN112539828B (en) | 2020-12-08 | 2020-12-08 | Pump unit equipment diagnosis method, system and equipment based on curve fitting contrast analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112539828B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115438756B (en) * | 2022-11-10 | 2023-04-28 | 济宁中银电化有限公司 | Method for diagnosing and identifying fault source of rectifying tower |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2016075563A (en) * | 2014-10-06 | 2016-05-12 | 株式会社東芝 | Rotary apparatus vibration diagnosis device, method, and program |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7653512B2 (en) * | 2004-12-17 | 2010-01-26 | Korea Reserch Institute of Standards and Science | Precision diagnostic method for the failure protection and predictive maintenance of a vacuum pump and a precision diagnostic system therefor |
| CN106112697B (en) * | 2016-07-15 | 2018-07-17 | 西安交通大学 | A kind of milling parameter automatic alarm threshold setting method based on 3 σ criterion |
| CN106568557B (en) * | 2016-10-31 | 2018-08-21 | 东南大学 | A kind of safe early warning method of high-speed railway bridge vehicle-bridge vibration performance |
| CN108664710A (en) * | 2018-04-20 | 2018-10-16 | 江苏大学 | A kind of pump flow-induced vibration performance comprehensive evaluation method |
| CN109960780B (en) * | 2019-03-18 | 2022-11-15 | 湘潭大学 | System and method for judging economic performance and stable state of pump operation |
| CN110399986B (en) * | 2019-06-24 | 2023-04-07 | 中水三立数据技术股份有限公司 | Generating method of pump station unit fault diagnosis system |
| CN110243465A (en) * | 2019-07-19 | 2019-09-17 | 上海市建筑科学研究院 | Bridge vibration acceleration and intrinsic frequency on line real-time monitoring device, terminal and method |
| CN111609923A (en) * | 2020-04-27 | 2020-09-01 | 内蒙古电力(集团)有限责任公司内蒙古电力科学研究院分公司 | Steam turbine generator unit vibration early warning method based on DCS data |
-
2020
- 2020-12-08 CN CN202011422670.4A patent/CN112539828B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2016075563A (en) * | 2014-10-06 | 2016-05-12 | 株式会社東芝 | Rotary apparatus vibration diagnosis device, method, and program |
Non-Patent Citations (2)
| Title |
|---|
| Gong Shuai, et al.A Convenient and Extensible Offline Chinese Speech Recognition System Based on Convolutional CTC Networks.2019,第7606-7611页. * |
| 桂中华 ; 张浩 ; 孙慧芳 ; 张飞 ; .水电机组振动劣化预警模型研究及应用.2018,(02),第216-222页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112539828A (en) | 2021-03-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9092737B2 (en) | Systems, methods, and apparatus for 3-D surface mapping, compliance mapping, and spatial registration with an array of cantilevered tactile hair or whisker sensors | |
| US8504500B2 (en) | Systems, methods, and apparatus for reconstruction of 3-D object morphology, position, orientation and texture using an array of tactile sensors | |
| CN107766299A (en) | The abnormal monitoring method of data target and its system, storage medium, electronic equipment | |
| CN106323273A (en) | Robot relocation method and device | |
| CN112539828B (en) | Pump unit equipment diagnosis method, system and equipment based on curve fitting contrast analysis | |
| CN104699099A (en) | Method and apparatus for simultaneous localization and mapping of mobile robot environment | |
| CN1369068A (en) | Statistial determination of estimates of process control loop parameters | |
| CN113917851A (en) | Virtual test environment construction method based on digital twinning | |
| JP2013033459A (en) | Abnormality monitoring system and abnormality monitoring method | |
| CN113654899B (en) | Pressure analysis method, device, equipment and storage medium for conveying pipeline | |
| CN113283082B (en) | Centroid track generation method, centroid track generation device, computer readable storage medium and robot | |
| CN110363339A (en) | A kind of method and system carrying out predictive maintenance based on the parameter of electric machine | |
| CN116338608B (en) | Method, device, equipment and storage medium for adjusting detection angle of microwave radar | |
| CN114659621B (en) | Bridge vibration monitoring device | |
| CN111075794A (en) | Method and device for monitoring leakage of hydraulic system | |
| CN111506199A (en) | Kinect-based high-precision unmarked whole-body motion tracking system | |
| CN114663463A (en) | Method, system, device, electronic device and storage medium for measuring joint mobility | |
| WO2019121655A1 (en) | A probability-based detector and controller apparatus, method, computer program | |
| CN205138544U (en) | Intelligence is measured and is managed integration system based on internet | |
| JP6015881B2 (en) | Device that displays trends related to process variables | |
| CN115946120B (en) | Mechanical arm control method, device, equipment and medium | |
| CN113343458B (en) | Engine sensor selection method and device, electronic equipment and storage medium | |
| CN115507827A (en) | Net-shaped distributed landslide monitoring system based on ultra wide band and high-precision MEMS (micro-electromechanical systems) | |
| CN114298243A (en) | Data processing method, device and equipment | |
| CN114169104A (en) | Equipment mechanical parameter optimization method based on improved teaching and chicken flock algorithm |
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 |