CN116882973A - Motor prediction maintenance method and system - Google Patents
Motor prediction maintenance method and system Download PDFInfo
- Publication number
- CN116882973A CN116882973A CN202310831960.1A CN202310831960A CN116882973A CN 116882973 A CN116882973 A CN 116882973A CN 202310831960 A CN202310831960 A CN 202310831960A CN 116882973 A CN116882973 A CN 116882973A
- Authority
- CN
- China
- Prior art keywords
- curve
- viscosity
- oil viscosity
- motor
- negative
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012423 maintenance Methods 0.000 title claims abstract description 79
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000009499 grossing Methods 0.000 claims abstract description 68
- 239000003921 oil Substances 0.000 claims description 157
- 239000010687 lubricating oil Substances 0.000 claims description 37
- 239000000314 lubricant Substances 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 3
- 230000002035 prolonged effect Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 14
- 230000035699 permeability Effects 0.000 description 9
- 238000004891 communication Methods 0.000 description 7
- 239000002184 metal Substances 0.000 description 7
- 238000005299 abrasion Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 5
- 239000002245 particle Substances 0.000 description 5
- 230000004927 fusion Effects 0.000 description 4
- 238000007689 inspection Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 239000007787 solid Substances 0.000 description 4
- 239000007788 liquid Substances 0.000 description 3
- 230000004075 alteration Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000010355 oscillation Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Chemical compound O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000002238 attenuated effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000005674 electromagnetic induction Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 239000010419 fine particle Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000001050 lubricating effect Effects 0.000 description 1
- 229920006254 polymer film Polymers 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000003911 water pollution Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/27—Regression, e.g. linear or logistic regression
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Operations Research (AREA)
- Artificial Intelligence (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Strategic Management (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The application provides a motor predictive maintenance method and a system, which are characterized in that an oil viscosity fitting curve is obtained by firstly detecting an oil viscosity information sequence of a motor, then carrying out curve fitting on the oil viscosity information sequence, positive and negative normal distribution signals are respectively overlapped on the oil viscosity fitting curve, smoothing is carried out on the oil viscosity fitting curve, then a positive and negative viscosity smoothing curve is obtained, then a median oil viscosity curve is obtained after weighting and fusing the positive and negative viscosity smoothing curves, the wear quality characteristics of the motor are determined according to the median oil viscosity curve, finally, a historical wear quality characteristic sequence is obtained in a preset maintenance time period, the predicted wear quality is obtained by establishing a moving average autoregressive model of the historical wear quality characteristic sequence, and when the predicted wear quality is larger than a preset threshold value, the motor is maintained, so that the motor predictive maintenance method without stopping maintenance of the motor at regular time is realized, and the service life of the motor is prolonged.
Description
Technical Field
The application relates to the technical field of motor maintenance, in particular to a motor prediction maintenance method and system.
Background
The motor is a device for converting electric energy into mechanical energy, is a device capable of generating rotation force and power output through electromagnetic action, has extremely important significance in daily life and modern industrial development, wherein safe, economical and stable power supply is the most important target of device operation, particularly the operation condition of the device in power distribution operation has great influence on the safety of a power distribution system, and therefore, the understanding of maintenance operation of the power distribution device is very important.
In the prior art, if the running condition of the motor is to be known, and if the potential safety hazard exists in the motor, the motor must be subjected to timing inspection, for example, the motor is subjected to one-time shutdown maintenance inspection, the maintenance mode is too simple, the maintenance is not fine enough, the follow-up motor running state is not predicted according to the historical running state of the motor, the labor and physical cost is wasted due to multiple shutdown maintenance, and the motor is frequently subjected to shutdown inspection and restarting to cause additional stress and abrasion on electric elements and mechanical parts of the motor, so that the service life of the motor is reduced.
Disclosure of Invention
The application provides a motor predictive maintenance method and a motor predictive maintenance system, which aim to solve the technical problems that the shutdown maintenance of a motor is not fine enough, and the service life of the motor can be reduced when the motor is frequently stopped, checked and restarted.
In order to solve the technical problems, the application adopts the following technical scheme:
in a first aspect, the present application provides a motor predictive maintenance method, including:
detecting the viscosity of lubricating oil when the motor works at equal time intervals to obtain an oil viscosity information sequence of the motor;
performing curve fitting on the oil viscosity information sequence to obtain an oil viscosity fitting curve, and respectively superposing positive and negative normal distribution signals on the oil viscosity fitting curve to obtain a positive oil viscosity curve and a negative oil viscosity curve;
smoothing the positive oil viscosity curve and the negative oil viscosity curve to obtain a positive viscosity smoothing curve and a negative viscosity smoothing curve;
according to the smoothness corresponding to the positive viscosity smooth curve and the negative viscosity smooth curve, weighting and fusing the positive viscosity smooth curve and the negative viscosity smooth curve to obtain a median oil viscosity curve, and determining the wear quality characteristics of the motor according to the median oil viscosity curve;
presetting a maintenance time period, and recording the wear quality characteristics in any section of the maintenance time period to obtain a historical wear quality characteristic sequence;
and establishing a moving average autoregressive model of the historical wear quality characteristic sequence, predicting the wear quality characteristic at the end of the next maintenance time period through the moving average autoregressive model to obtain predicted wear quality, and maintaining the motor when the predicted wear quality is greater than a preset threshold.
In some embodiments, smoothing the positive oil viscosity curve and the negative oil viscosity curve includes:
acquiring a maximum value set and a minimum value set of the forward oil viscosity curve;
mapping the maximum value set and the minimum value set into a two-dimensional coordinate system with time as a bottom, connecting adjacent maximum values in the maximum value set to obtain a maximum value broken line, and connecting adjacent minimum values in the minimum value set to obtain a minimum value broken line;
obtaining an average value of the maximum curve and the minimum curve to obtain a filtering curve;
obtaining a forward viscosity smoothing curve according to the difference value between the forward oil viscosity curve and the filtering curve;
and obtaining a maximum value set and a minimum value set of the negative oil viscosity curve, and repeating the similar steps to obtain a negative viscosity smooth curve.
In some embodiments, the forward viscosity smoothing curve is determined according to the following equation, namely:
G z (t)＝ω(t)-0.5[ω max (t)+ω min (t)]
wherein G is z (t) is the forward viscosity smoothing curve, ω (t) is the forward oil viscosity curve, ω max (t)、ω min (t) maximum and minimum fold lines, respectively.
In some embodiments, detecting the viscosity of the lubricant when the motor is operating at equal time intervals, the obtaining a sequence of oil viscosity information for the motor includes:
collecting lubricating oil dropped by a motor in operation at equal time intervals, and detecting the viscosity of the lubricating oil through a viscosity sensor to obtain oil viscosity information of the motor at different collecting moments;
and arranging the oil viscosity information obtained at different acquisition moments according to a time sequence to obtain an oil viscosity information sequence of the motor.
In some embodiments, a polynomial function fitting method is adopted to perform curve fitting on the oil viscosity information sequence, so as to obtain an oil viscosity fitting curve.
In some embodiments, a lagrangian interpolation method is used to perform curve fitting on the oil viscosity information sequence to obtain an oil viscosity fitting curve.
In some embodiments, the positive and negative normal distribution curves have integral values over the domain of positive and negative 1, respectively.
In a second aspect, the present application provides a motor predictive maintenance system comprising:
the oil viscosity information acquisition module is used for detecting the viscosity of the lubricating oil when the motor works at equal time intervals to obtain an oil viscosity information sequence of the motor;
the positive and negative oil viscosity curve determining module is used for performing curve fitting on the oil viscosity information sequence to obtain an oil viscosity fitting curve, and respectively superposing positive and negative normal distribution signals on the oil viscosity fitting curve to obtain a positive oil viscosity curve and a negative oil viscosity curve;
the curve smoothing processing module is used for carrying out smoothing processing on the positive oil viscosity curve and the negative oil viscosity curve to obtain a positive viscosity smoothing curve and a negative viscosity smoothing curve;
the wear quality characteristic determining module is used for obtaining a median oil viscosity curve after weighting and fusing the positive viscosity smooth curve and the negative viscosity smooth curve according to the smoothness corresponding to the positive viscosity smooth curve and the negative viscosity smooth curve, and determining the wear quality characteristic of the motor according to the median oil viscosity curve;
the historical wear quality characteristic sequence determining module is used for presetting a maintenance time period, and recording the wear quality characteristics in any section of the maintenance time period to obtain a historical wear quality characteristic sequence;
and the motor prediction maintenance module is used for establishing a moving average autoregressive model of the historical wear quality characteristic sequence, predicting the wear quality characteristic at the end of the next maintenance time period through the moving average autoregressive model to obtain predicted wear quality, and maintaining the motor when the predicted wear quality is larger than a preset threshold value.
In a third aspect, the present application provides a computer device comprising a memory storing code and a processor configured to obtain the code and to perform the above-described motor predictive maintenance method.
In a fourth aspect, the present application provides a computer readable storage medium storing a computer program which when executed by a processor implements the above-described motor predictive maintenance method.
The technical scheme provided by the embodiment of the application has the following beneficial effects:
according to the motor predictive maintenance method and system, after an oil viscosity information sequence of a motor is detected, curve fitting is carried out on the oil viscosity information sequence to obtain an oil viscosity fitting curve, positive and negative normal distribution signals are respectively overlapped on the oil viscosity fitting curve and are subjected to smoothing treatment to obtain a positive viscosity smoothing curve and a negative viscosity smoothing curve, the positive viscosity smoothing curve and the negative viscosity smoothing curve are weighted and fused according to the smoothness corresponding to the positive viscosity smoothing curve and the negative viscosity smoothing curve to obtain a median oil viscosity curve, the wear quality characteristics of the motor are determined according to the median oil viscosity curve, a maintenance time period is preset, the wear quality characteristics in any maintenance time period are recorded to obtain a historical wear quality characteristic sequence, a moving average autoregressive model of the historical wear quality characteristic sequence is established, the wear quality is predicted when the maintenance time period is finished under prediction by the moving average autoregressive model, and the predicted wear quality is obtained.
Drawings
FIG. 1 is an exemplary flow chart of a motor predictive maintenance method according to some embodiments of the application;
FIG. 2 is a schematic diagram of exemplary hardware and/or software of a motor predictive maintenance method system according to some embodiments of the application;
fig. 3 is a schematic structural diagram of a computer device implementing a motor predictive maintenance method according to some embodiments of the application.
Detailed Description
According to the motor predictive maintenance method and system provided by the application, firstly, after an oil viscosity information sequence of a motor is detected, curve fitting is carried out on the oil viscosity information sequence to obtain an oil viscosity fitting curve, positive and negative normal distribution signals are respectively overlapped on the oil viscosity fitting curve and are subjected to smoothing treatment to obtain a positive viscosity smoothing curve and a negative viscosity smoothing curve, the positive viscosity smoothing curve and the negative viscosity smoothing curve are subjected to weighted fusion according to the smoothness corresponding to the positive viscosity smoothing curve and the negative viscosity smoothing curve to obtain a median oil viscosity curve, the wear quality characteristics of the motor are determined according to the median oil viscosity curve, a maintenance time period is preset, the wear quality characteristics in any maintenance time period are recorded to obtain a historical wear quality characteristic sequence, a moving average autoregressive model of the historical wear quality characteristic sequence is established, the wear quality characteristics at the end of the maintenance time period are predicted through the moving average autoregressive model to obtain predicted wear quality, and when the predicted wear quality is larger than a preset threshold value, the motor is maintained, the motor predictive maintenance method without time is realized, the service life of the motor is prolonged, and the service life of the motor is more fine.
In order to better understand the above technical solutions, the following detailed description will refer to the accompanying drawings and specific embodiments. Referring to fig. 1, which is an exemplary flowchart of a motor predictive maintenance method according to some embodiments of the application, the motor predictive maintenance method 100 generally includes the steps of:
in step S101, the viscosity of the lubricating oil when the motor works is detected at equal time intervals, and an oil viscosity information sequence of the motor is obtained.
In some embodiments, the lubricant that the motor droops during the working can be collected at equal time intervals, and then the viscosity of the lubricant is detected by the viscosity sensor, so as to obtain the lubricant viscosity information of the motor at different collection moments, for example, the viscosity sensor working based on the torque micro-oscillation principle can be adopted to send a tiny vibration signal to the lubricant, then the oscillation signal fed back in the lubricant is collected, a corresponding electrical signal is output according to the magnitude of the oscillation signal, and the electrical signal is amplified by a proportional amplifying unit preset in the viscosity sensor, so as to obtain the lubricant viscosity information finally displayed.
Reasonably, the oil viscosity information obtained at different acquisition moments is arranged according to a time sequence to obtain an oil viscosity information sequence of the motor.
And step S102, performing curve fitting on the oil viscosity information sequence to obtain an oil viscosity fitting curve, and respectively superposing positive and negative normal distribution signals on the oil viscosity fitting curve to obtain a positive oil viscosity curve and a negative oil viscosity curve.
Preferably, in some embodiments, a polynomial function fitting method may be used to perform curve fitting on the oil viscosity information sequence to obtain an oil viscosity fitting curve, for example, a proper polynomial order is selected, and a polynomial function with the same polynomial order is used to perform linear combination, so that the polynomial after combination approximates to a data value of oil viscosity information in the oil viscosity information sequence.
In other embodiments, a lagrangian interpolation method may also be used to perform curve fitting on the oil viscosity information sequence to obtain an oil viscosity fitting curve.
The normal distribution signal is a random signal which is subjected to Gaussian distribution and is used for eliminating error interference in the oil viscosity fitting curve, so that the robustness of the oil viscosity fitting curve is enhanced, wherein the integral value of the positive-negative normal distribution curve in a definition domain is positive and negative 1 respectively.
And step S103, performing smoothing treatment on the positive oil viscosity curve and the negative oil viscosity curve to obtain a positive viscosity smoothing curve and a negative viscosity smoothing curve.
Preferably, in some embodiments, the smoothing of the positive oil viscosity curve and the negative oil viscosity curve may be performed by:
acquiring a maximum value set and a minimum value set of the forward oil viscosity curve;
mapping the maximum value set and the minimum value set into a two-dimensional coordinate system with time as a bottom, connecting adjacent maximum values in the maximum value set to obtain a maximum value broken line, and connecting adjacent minimum values in the minimum value set to obtain a minimum value broken line;
obtaining an average value of the maximum curve and the minimum curve to obtain a filtering curve;
obtaining a forward viscosity smoothing curve according to the difference value between the forward oil viscosity curve and the filtering curve;
and obtaining a maximum value set and a minimum value set of the negative oil viscosity curve, and repeating the similar steps to obtain a negative viscosity smooth curve.
Preferably, in some embodiments, the value of the corresponding moment in the forward viscosity smoothing curve is the difference between the forward oil viscosity curve and the filtering curve at the moment, and in particular, the forward viscosity smoothing curve may also be determined according to the following formula, namely:
G z (t)＝ω(t)-0.5[ω max (t)+ω min (t)]
wherein G is z (t) is the forward viscosity smoothing curve, ω (t) is the forward oil viscosity curve, ω max (t)、ω min (t) maximum and minimum fold lines, respectively.
And step S104, according to the smoothness corresponding to the positive viscosity smooth curve and the negative viscosity smooth curve, weighting and fusing the positive viscosity smooth curve and the negative viscosity smooth curve to obtain a median oil viscosity curve, and determining the wear quality characteristics of the motor according to the median oil viscosity curve.
The positive viscosity smooth curve and the negative viscosity smooth curve are oil viscosity fitting curves after adding positive-negative normal distribution signals and performing smoothing treatment respectively, and in the detection process of the sensor, due to the zero drift phenomenon existing in the sensor, detection errors caused by zero drift are partially canceled with the positive normal distribution signals or the negative normal distribution signals, so that better stability exists in the curves after smoothing treatment, and therefore, in order to obtain more accurate curves reflecting oil viscosity information, weight coefficients can be determined according to the smoothness of the positive viscosity smooth curve and the negative viscosity smooth curve, and then the median oil viscosity curve is obtained after weighted fusion of the positive viscosity smooth curve and the negative viscosity smooth curve.
In some embodiments, the smoothness is used to reflect the magnitude of curve fluctuation of the positive viscosity smooth curve and the negative viscosity smooth curve, that is, the smooth performance of the curve, and in specific implementations, the smoothness of the positive viscosity smooth curve may also be determined according to the following formula:
wherein θ z For the smoothness of the forward viscosity smoothing curve, G z (t)' is the first derivative of the forward viscosity smoothing curve, t is the time argument, |G z (T)' is the absolute value of the first derivative of the forward viscosity smoothing curve, dt is the differential of the time independent variable, T is the current time value, k is the acquisition times of lubricating oil during motor operation, Q is the interval time between two adjacent acquisitions, D is the variance of the oil viscosity information sequence, alpha n And the nth oil viscosity information in the oil viscosity information sequence is obtained.
It should be noted that, the positive viscosity smooth curve in the above formula is replaced by the negative viscosity smooth curve, so that the smoothness of the negative viscosity smooth curve can be obtained, and then the median oil viscosity curve can be obtained after the positive viscosity smooth curve and the negative viscosity smooth curve are weighted and fused according to the smoothness corresponding to the positive viscosity smooth curve and the negative viscosity smooth curve, and the obtained median oil viscosity curve has stronger robustness to the zero drift interference of the sensor, so that the viscosity change information of the lubricating liquid in the working process of the motor can be reflected more accurately.
In specific implementation, the weight coefficient when the positive viscosity smooth curve and the negative viscosity smooth curve are weighted and fused is determined by the smoothness corresponding to the positive viscosity smooth curve and the negative viscosity smooth curve, for example, the median oil viscosity curve can be obtained by the following formula, namely:
wherein G (t) is the median oil viscosity curve, G z (t) is the forward viscosity smoothing curve, θ z G is the smoothness of the forward viscosity smoothing curve f (t) smoothing the negative viscosityCurve, θ f Is the smoothness of the negative viscosity smoothing curve.
It should be noted that, since the viscosity of the oil of the lubricating oil may drop off fine particles along with the wear of metal parts of the motor during the use of the lubricating oil, the concentration of the lubricating oil is increased, so that the lubricating oil becomes viscous, and the interaction between solid particles and lubricating oil molecules may also cause the relative movement between lubricating oil molecules to be limited, so that the internal friction of the lubricating oil is increased, so that the viscosity of the lubricating oil is increased, the content of solid particles in the motor may be determined according to the viscosity change condition of the lubricating oil dropped by the motor, so that the wear condition of the metal parts in the motor may be indirectly measured, in addition, the viscosity of the lubricating oil in the motor may be affected by other factors, for example, water pollution of water vapor in air to the motor lubricating oil may cause the viscosity to decrease, and the friction increase viscosity in the lubricating oil may also be increased by other solid particles in the air entering the lubricating oil, which needs to be comprehensively considered, so that in some embodiments, before determining the wear quality characteristics of the motor according to the median oil viscosity curve may further include: and detecting the moisture proportion and the relative magnetic permeability of the lubricating oil liquid when the motor works, wherein the moisture proportion and the relative magnetic permeability are used for correcting the abrasion quality characteristics of the motor.
Wherein in some embodiments, the capacitance sensor may be used to change the dielectric constant of its own polymer film by the moisture content in the lubricating oil, so as to change the capacitance value, and the output of the capacitance sensor may be changed, so as to measure the moisture content in the lubricating oil, and in other embodiments, other devices or apparatuses capable of detecting the moisture content in the lubricating oil may be used, which are not limited herein.
When the relative magnetic permeability of the lubricating oil is detected during the operation of the motor, the magnetic permeability of the lubricating oil can be detected by adopting a special magnetic permeability instrument through electromagnetic induction and then compared with the magnetic permeability before the lubricating oil is not used, so that the relative magnetic permeability of the lubricating oil during the operation is obtained, the relative magnetic permeability of the lubricating oil is detected, the proportion of metal part particles which cause the motor abrasion in solid particles with the viscosity rising in the lubricating oil can be determined, and further the more accurate abrasion quality characteristics of the motor are obtained.
Preferably, in some embodiments, the wear quality characteristic of the motor may be determined according to the proportion of the length of the curve with the derivative being negative in the median oil viscosity curve and the oil viscosity information sequence, where the wear quality characteristic is the ratio between the oil quality at the current time and the wear quality of the metal part of the motor, and the specific process of determining the oil viscosity characteristic value according to the median oil viscosity curve may be represented by the following formula, namely:
wherein E is the wear quality characteristic of the motor, alpha k Alpha is the kth oil viscosity information in the oil viscosity information sequence 1 The 1 st oil viscosity information in the oil viscosity information sequence is represented by T, dt, T, k, Q, G (T) 'and G (T)' respectively, wherein T, k are the number of times the motor is operated to collect lubricating oil, Q is the interval time between two adjacent collection, G (T) 'is the first derivative of the median oil viscosity curve, G (T)' is the absolute value of the first derivative of the median oil viscosity curve, sigma is the sensitivity coefficient, and p is the water proportion of the oil in the lubricating oil operation according to empirical calibration as a constant,is the relative permeability of oil liquid when the lubricating oil works.
In step S105, a maintenance time period is preset, and the wear quality characteristics in any section of the maintenance time period are recorded, so as to obtain a historical wear quality characteristic sequence.
In step S106, a moving average autoregressive model of the historical wear quality feature sequence is established, the wear quality feature at the end of the next maintenance time period is predicted by the moving average autoregressive model, the predicted wear quality is obtained, and when the predicted wear quality is greater than a preset threshold, the motor is maintained.
It should be noted that the wear quality characteristic is the ratio between the oil quality of the motor and the wear quality of the metal parts of the motor at the current moment, when the wear quality of the metal parts in the motor is too large, the energy consumption of the motor is easily increased, the power is easily reduced, equipment faults are easily caused, and even safety problems are caused, therefore, when the wear quality characteristic of the motor is too large, the motor in operation needs to be shut down and maintained, for example, the worn metal parts in the motor are replaced and the motor is subjected to adjustment and calibration again, axis inspection and bolts are fastened, and the like.
Preferably, in some embodiments, the moving average autoregressive model of the historical wear quality feature sequence may be established by a method that a preset maintenance time period is 7 days, at this time, the wear quality features of the motor for the past 168 hours may be recorded separately, so as to obtain a historical wear quality sequence containing 168 historical wear qualities, and in other embodiments, the maintenance time period may also be preset to other time lengths; furthermore, a time sequence diagram of the historical wear quality characteristic can be drawn, the abscissa of the time sequence diagram corresponds to different moments, and preferably, the abscissa of the time sequence diagram can also be the sequence of sequence elements in the historical wear quality sequence, for example, the abscissa of the time sequence diagram, which corresponds to the motor wear quality characteristic at the 7 th hour, is 7; and further, the time sequence diagram of the historical wear quality feature set can be subjected to exponential conversion, so that the trend of variance in the time sequence diagram along with time is eliminated.
And secondly, drawing an autocorrelation coefficient graph of the wear quality characteristic according to a time sequence graph of the historical wear quality characteristic, wherein the horizontal axis of the autocorrelation coefficient graph is a hysteresis period number, and the vertical axis of the autocorrelation coefficient graph is a value of the autocorrelation coefficient. And drawing a partial autocorrelation coefficient graph of the abrasion quality characteristic, wherein the horizontal axis of the partial autocorrelation coefficient graph is a hysteresis period number, and the vertical axis of the partial autocorrelation coefficient graph is a value of the partial autocorrelation coefficient.
According to the characteristics of the autocorrelation coefficient graphs and the partial autocorrelation coefficient graphs, the order of the model and the value range of the coefficients can be preliminarily determined, for example, the autocorrelation coefficient graphs can be drawn, whether the autocorrelation coefficients show tail-cutting characteristics after a certain order is observed, and if the autocorrelation coefficients drop sharply and remain near 0 after a certain order, the order of the autoregressive model can be preliminarily determined; drawing a partial autocorrelation coefficient graph, observing whether the partial autocorrelation coefficient shows the characteristic of tail cutting after a certain order, and if the partial autocorrelation coefficient drops sharply and remains near 0 after a certain order, determining the order of the moving average model preliminarily.
In particular, the last significant autocorrelation coefficient can be found according to the autocorrelation coefficient diagram, which is the order of the autocorrelation model, for example, if the last significant autocorrelation coefficient in the autocorrelation coefficient diagram is at 3 order, the order of the autocorrelation model is 3; further, according to the partial autocorrelation coefficient diagram, the last significant partial autocorrelation coefficient is found, which is the order of the moving average model, for example, if the last significant partial autocorrelation coefficient in the partial autocorrelation coefficient diagram is at the order of 2, the order of the moving average model is 2; finally, determining the order (p, q) of the autoregressive moving average model according to the autocorrelation coefficient graphs and the partial autocorrelation coefficient graphs, for example, if the autocorrelation coefficient graphs and the partial autocorrelation coefficient graphs are attenuated to zero after 3 steps, the order of the autoregressive moving average model is (3, 3); and selecting proper parameters to establish an autoregressive moving average model of the historical wear quality characteristics according to the order of the autoregressive moving average model, and bringing the historical wear quality characteristics into the autoregressive moving average model to predict the subsequent wear quality characteristics, wherein the wear quality characteristics at the end of the next maintenance time period are taken as the predicted wear quality.
In particular implementations, for example, the model autoregressive and moving average processes may be subjected to parameter estimation and saliency verification using a least squares method, and in some embodiments, the saliency verification is performed at a level of 0.05, and finally the best-fit autoregressive moving average model parameters are selected according to the schwarz bayesian criterion, thereby determining the final autoregressive moving average model of the wear quality features.
The autoregressive moving average model is a function of the change of the wear quality feature over a past maintenance period, and the historical wear quality feature is brought into the autoregressive moving average model to predict subsequent wear quality features, wherein in some embodiments, the wear quality feature at the end of the next maintenance period is taken as the predicted wear quality.
Additionally, in another aspect of the present application, in some embodiments, the present application provides a motor predictive maintenance system, referring to FIG. 2, which is a schematic diagram of exemplary hardware and/or software of a motor predictive maintenance system according to some embodiments of the present application, the motor predictive maintenance system 200 comprising: the oil viscosity information acquisition module 201, the positive and negative oil viscosity curve determination module 202, the curve smoothing module 203, the wear quality feature determination module 204, the historical wear quality feature sequence determination module 205 and the motor prediction maintenance module 206 are respectively described as follows:
the oil viscosity information acquisition module 201 is mainly used for detecting the viscosity of lubricating oil when the motor works at equal time intervals to obtain an oil viscosity information sequence of the motor.
The positive and negative oil viscosity curve determining module 202 is mainly used for performing curve fitting on the oil viscosity information sequence to obtain an oil viscosity fitting curve, and respectively superposing positive and negative normal distribution signals on the oil viscosity fitting curve to obtain a positive oil viscosity curve and a negative oil viscosity curve.
The curve smoothing module 203 in the present application, the curve smoothing module 203 is mainly used for smoothing the positive oil viscosity curve and the negative oil viscosity curve to obtain a positive viscosity smoothing curve and a negative viscosity smoothing curve.
The wear quality characteristic determining module 204 in the present application is mainly configured to obtain a median oil viscosity curve by performing weighted fusion on the positive viscosity smooth curve and the negative viscosity smooth curve according to the smoothness corresponding to the positive viscosity smooth curve and the negative viscosity smooth curve, and determine the wear quality characteristic of the motor according to the median oil viscosity curve.
The historical wear quality characteristic sequence determining module 205 is mainly used for presetting a maintenance time period, and recording wear quality characteristics in any maintenance time period to obtain a historical wear quality characteristic sequence.
The motor prediction maintenance module 206 in the present application is mainly configured to establish a moving average autoregressive model of the historical wear quality feature sequence, predict the wear quality feature at the end of the next maintenance time period through the moving average autoregressive model, obtain a predicted wear quality, and maintain the motor when the predicted wear quality is greater than a preset threshold.
In addition, the application also provides a computer device, which comprises a memory and a processor, wherein the memory stores codes, and the processor is configured to acquire the codes and execute the motor prediction maintenance method.
In some embodiments, reference is made to FIG. 3, which is a schematic structural diagram of a computer device employing a motor predictive maintenance method, according to some embodiments of the application. The motor predictive maintenance method in the above embodiment may be implemented by a computer device shown in fig. 3, which includes at least one processor 301, a communication bus 302, a memory 303, and at least one communication interface 304.
The processor 301 may be a general purpose central processing unit (central processing unit, CPU), application-specific integrated circuit (ASIC), or one or more of the methods for controlling the performance of the motor predictive maintenance method of the present application.
Communication bus 302 may include a path to transfer information between the above components.
The Memory 303 may be, but is not limited to, a read-only Memory (ROM) or other type of static storage device that can store static information and instructions, a random access Memory (random access Memory, RAM) or other type of dynamic storage device that can store information and instructions, an electrically erasable programmable read-only Memory (electrically erasable programmable read-only Memory, EEPROM), a compact disc (compact disc read-only Memory) or other optical disk storage, a compact disc storage (including compact disc, laser disc, optical disc, digital versatile disc, blu-ray disc, etc.), a magnetic disk or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and that can be accessed by a computer. The memory 303 may be stand alone and be coupled to the processor 301 via the communication bus 302. Memory 303 may also be integrated with processor 301.
The memory 303 is used for storing program codes for executing the scheme of the present application, and the processor 301 controls the execution. The processor 301 is configured to execute program code stored in the memory 303. One or more software modules may be included in the program code. The determination of the wear quality characteristics in the above-described embodiments may be implemented by one or more software modules in the processor 301 and in the program code in the memory 303.
Communication interface 304, using any transceiver-like device for communicating with other devices or communication networks, such as ethernet, radio access network (radio access network, RAN), wireless local area network (wireless local areanetworks, WLAN), etc.
In a specific implementation, as an embodiment, a computer device may include a plurality of processors, where each of the processors may be a single-core (single-CPU) processor or may be a multi-core (multi-CPU) processor. A processor herein may refer to one or more devices, circuits, and/or processing cores for processing data (e.g., computer program instructions).
The computer device may be a general purpose computer device or a special purpose computer device. In particular implementations, the computer device may be a desktop, laptop, web server, palmtop (personal digital assistant, PDA), mobile handset, tablet, wireless terminal device, communication device, or embedded device. Embodiments of the application are not limited to the type of computer device.
In addition, the application also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program realizes the motor prediction maintenance method when being executed by a processor.
In summary, in the motor prediction maintenance method and system disclosed by the embodiment of the application, firstly, after an oil viscosity information sequence of a motor is detected, curve fitting is performed on the oil viscosity information sequence to obtain an oil viscosity fitting curve, positive and negative normal distribution signals are respectively overlapped on the oil viscosity fitting curve and smoothed to obtain a positive viscosity smoothing curve and a negative viscosity smoothing curve, according to the smoothness corresponding to the positive viscosity smoothing curve and the negative viscosity smoothing curve, weighted fusion is performed on the positive viscosity smoothing curve and the negative viscosity smoothing curve to obtain a median oil viscosity curve, the wear quality characteristics of the motor are determined according to the median oil viscosity curve, the maintenance time period is preset, the wear quality characteristics in any maintenance time period are recorded to obtain a historical wear quality characteristic sequence, a moving average autoregressive model of the historical wear quality characteristic sequence is established, the wear quality characteristics at the end of the next maintenance time period are predicted through the moving average autoregressive model to obtain predicted wear quality, and when the predicted wear quality is greater than a preset threshold, the motor is maintained, the motor prediction maintenance method without stopping maintenance is realized, the motor is increased in service life, and the service life is finer.
While preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the application.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the spirit or scope of the application. Thus, it is intended that the present application also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (10)
1. The motor prediction maintenance method is characterized by comprising the following steps of:
detecting the viscosity of lubricating oil when the motor works at equal time intervals to obtain an oil viscosity information sequence of the motor;
performing curve fitting on the oil viscosity information sequence to obtain an oil viscosity fitting curve, and respectively superposing positive and negative normal distribution signals on the oil viscosity fitting curve to obtain a positive oil viscosity curve and a negative oil viscosity curve;
smoothing the positive oil viscosity curve and the negative oil viscosity curve to obtain a positive viscosity smoothing curve and a negative viscosity smoothing curve;
according to the smoothness corresponding to the positive viscosity smooth curve and the negative viscosity smooth curve, weighting and fusing the positive viscosity smooth curve and the negative viscosity smooth curve to obtain a median oil viscosity curve, and determining the wear quality characteristics of the motor according to the median oil viscosity curve;
presetting a maintenance time period, and recording the wear quality characteristics in any section of the maintenance time period to obtain a historical wear quality characteristic sequence;
and establishing a moving average autoregressive model of the historical wear quality characteristic sequence, predicting the wear quality characteristic at the end of the next maintenance time period through the moving average autoregressive model to obtain predicted wear quality, and maintaining the motor when the predicted wear quality is greater than a preset threshold.
2. The method of claim 1, wherein smoothing the positive oil viscosity curve and the negative oil viscosity curve comprises:
acquiring a maximum value set and a minimum value set of the forward oil viscosity curve;
mapping the maximum value set and the minimum value set into a two-dimensional coordinate system with time as a bottom, connecting adjacent maximum values in the maximum value set to obtain a maximum value broken line, and connecting adjacent minimum values in the minimum value set to obtain a minimum value broken line;
obtaining an average value of the maximum curve and the minimum curve to obtain a filtering curve;
obtaining a forward viscosity smoothing curve according to the difference value between the forward oil viscosity curve and the filtering curve;
and obtaining a maximum value set and a minimum value set of the negative oil viscosity curve, and repeating the similar steps to obtain a negative viscosity smooth curve.
3. The method of claim 2, wherein the forward viscosity smoothing curve is determined according to the following equation:
G z (t)＝ω(t)-0.5[ω max (t)+ω min (t)]
wherein G is z (t) is the forward viscosity smoothing curve, ω (t) is the forward oil viscosity curve, ω max (t)、ω min (t) maximum and minimum fold lines, respectively.
4. The method of claim 1, wherein detecting the viscosity of the lubricant during operation of the motor at equal time intervals, the obtaining a sequence of oil viscosity information for the motor, comprises:
collecting lubricating oil dropped by a motor in operation at equal time intervals, and detecting the viscosity of the lubricating oil through a viscosity sensor to obtain oil viscosity information of the motor at different collecting moments;
and arranging the oil viscosity information obtained at different acquisition moments according to a time sequence to obtain an oil viscosity information sequence of the motor.
5. The method of claim 1, wherein the oil viscosity information sequence is curve-fitted using a polynomial function fitting method to obtain an oil viscosity fitting curve.
6. The method of claim 1 wherein said curve fitting said sequence of oil viscosity information is performed using lagrangian interpolation to obtain an oil viscosity fit curve.
7. The method of claim 1, wherein the positive and negative normal distribution curves have integral values over a domain of positive and negative 1, respectively.
8. A motor predictive maintenance system, comprising:
the oil viscosity information acquisition module is used for detecting the viscosity of the lubricating oil when the motor works at equal time intervals to obtain an oil viscosity information sequence of the motor;
the positive and negative oil viscosity curve determining module is used for performing curve fitting on the oil viscosity information sequence to obtain an oil viscosity fitting curve, and respectively superposing positive and negative normal distribution signals on the oil viscosity fitting curve to obtain a positive oil viscosity curve and a negative oil viscosity curve;
the curve smoothing processing module is used for carrying out smoothing processing on the positive oil viscosity curve and the negative oil viscosity curve to obtain a positive viscosity smoothing curve and a negative viscosity smoothing curve;
the wear quality characteristic determining module is used for obtaining a median oil viscosity curve after weighting and fusing the positive viscosity smooth curve and the negative viscosity smooth curve according to the smoothness corresponding to the positive viscosity smooth curve and the negative viscosity smooth curve, and determining the wear quality characteristic of the motor according to the median oil viscosity curve;
the historical wear quality characteristic sequence determining module is used for presetting a maintenance time period, and recording the wear quality characteristics in any section of the maintenance time period to obtain a historical wear quality characteristic sequence;
and the motor prediction maintenance module is used for establishing a moving average autoregressive model of the historical wear quality characteristic sequence, predicting the wear quality characteristic at the end of the next maintenance time period through the moving average autoregressive model to obtain predicted wear quality, and maintaining the motor when the predicted wear quality is larger than a preset threshold value.
9. A computer device comprising a memory storing code and a processor configured to obtain the code and to perform the motor predictive maintenance method of any one of claims 1 to 7.
10. A computer readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the motor predictive maintenance method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310831960.1A CN116882973A (en) | 2023-07-07 | 2023-07-07 | Motor prediction maintenance method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310831960.1A CN116882973A (en) | 2023-07-07 | 2023-07-07 | Motor prediction maintenance method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116882973A true CN116882973A (en) | 2023-10-13 |
Family
ID=88257976
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310831960.1A Pending CN116882973A (en) | 2023-07-07 | 2023-07-07 | Motor prediction maintenance method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116882973A (en) |
-
2023
- 2023-07-07 CN CN202310831960.1A patent/CN116882973A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113748326B (en) | Method for estimating bearing fault severity for induction motor | |
| CN108573224B (en) | Bridge structure damage positioning method for mobile reconstruction of principal components by using single sensor information | |
| CN117196353B (en) | Environmental pollution assessment and monitoring method and system based on big data | |
| CN116434372B (en) | Intelligent data acquisition system and working condition identification system for variable working condition equipment | |
| CN115932586A (en) | Method, device, equipment and medium for estimating state of charge of battery on line | |
| CN114996654B (en) | Road surface flatness detection method and device, electronic equipment and medium | |
| CN110298765B (en) | Power distribution network power consumption abnormality detection method based on objective correlation factors | |
| CN113947017A (en) | Method for predicting residual service life of rolling bearing | |
| EP1418312A2 (en) | Turbine blade oxidation monitoring and life prediction using neural network based diagnostic techniques in conjunction with pyrometer signals | |
| CN113460122B (en) | State detection method, device, equipment and medium for electric turnout switch machine system | |
| CN112926636A (en) | Method and device for detecting abnormal temperature of traction converter cabinet body | |
| CN115586438A (en) | Dual-motor efficiency testing method, system, equipment and storage medium | |
| CN117610307B (en) | Digital twin construction method of simply supported beam under action of moving mass | |
| CN107918275A (en) | The climb displacement method and linear electric machine of linear electric machine | |
| CN114858250A (en) | Fault detection method and system of intelligent water meter and readable storage medium | |
| CN116882973A (en) | Motor prediction maintenance method and system | |
| CN117036732B (en) | Electromechanical equipment detection system, method and equipment based on fusion model | |
| CN108266364B (en) | Electric pump load over-low fault diagnosis method and device | |
| JP2018204952A (en) | Displacement amount calculation system, program and recording medium | |
| CN108223401B (en) | Electric pump overload fault diagnosis method and device | |
| CN116226719A (en) | Bearing fault diagnosis method based on multidimensional steady-state vibration characteristics and related components | |
| CN114739557A (en) | Tension sensor data processing method and device and terminal equipment | |
| CN116161551A (en) | Method for detecting height of lifting hook, crane, storage medium and controller | |
| CN115541112A (en) | Dynamic balance experiment method, device, equipment and medium for rigid rotor | |
| CN114742103A (en) | City monitoring data processing method and device based on Internet of things and storage medium |
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 |