CN117031277B - Intelligent monitoring method for motor running state - Google Patents

Intelligent monitoring method for motor running state Download PDF

Info

Publication number
CN117031277B
CN117031277B CN202311276133.7A CN202311276133A CN117031277B CN 117031277 B CN117031277 B CN 117031277B CN 202311276133 A CN202311276133 A CN 202311276133A CN 117031277 B CN117031277 B CN 117031277B
Authority
CN
China
Prior art keywords
motor
jump
abnormal
moment
vibration
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
Application number
CN202311276133.7A
Other languages
Chinese (zh)
Other versions
CN117031277A (en
Inventor
王华军
王春彦
尚栋
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Suzhou Baobang Electric Co ltd
Original Assignee
Suzhou Baobang Electric Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Suzhou Baobang Electric Co ltd filed Critical Suzhou Baobang Electric Co ltd
Priority to CN202311276133.7A priority Critical patent/CN117031277B/en
Publication of CN117031277A publication Critical patent/CN117031277A/en
Application granted granted Critical
Publication of CN117031277B publication Critical patent/CN117031277B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01RMEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/34Testing dynamo-electric machines
    • G01R31/343Testing dynamo-electric machines in operation
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01DMEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
    • G01D21/00Measuring or testing not otherwise provided for
    • G01D21/02Measuring two or more variables by means not covered by a single other subclass

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Control Of Electric Motors In General (AREA)

Abstract

The invention relates to the technical field of data processing, in particular to an intelligent monitoring method for the running state of a motor, which comprises the following steps: acquiring motor vibration speed data and a motor vibration displacement matrix; analyzing the vibration condition of the motor during operation, and constructing a follow-up association coefficient of the vibration jump point; acquiring a deflection direction included angle and a deflection direction vector value of the motor by combining displacement data of motor vibration; constructing a motor vibration deflection coefficient; constructing an abnormal evaluation index of each trip point; screening out abnormal jump points; constructing an abnormal operation index of the motor according to the time characteristics of the abnormal jump points; therefore, the detection of the running state of the motor is realized, the vibration error generated in the running environment of the motor is effectively reduced, and the accuracy of the detection result is improved.

Description

Intelligent monitoring method for motor running state
Technical Field
The application relates to the technical field of data processing, in particular to an intelligent monitoring method for the running state of a motor.
Background
Along with the development of industrial production, the motor is one of important power sources in industrial production, and the position in industrial production is gradually improved, and as industrial production often needs the motor to maintain stable operation of all equipment in the whole production flow so as to ensure production efficiency, the motor is used as a power source of industrial production, and the running state of the motor determines the efficiency of the production flow.
With the development of computer science and sensor devices, the method for monitoring the running state of a motor is gradually increased. At present, most of monitoring methods for the running state of a motor adopt a sensor to monitor the current and the voltage of the motor in an abnormal way. Conventional motor condition monitoring methods typically require the installation of sensors to obtain relevant parameters and signals, which may have a certain impact on the efficiency and reliability of the motor, while for older motors, implantation of invasive sensors may have an irreversible impact on the motor. To address this problem, some non-invasive or low-invasive motor condition monitoring methods have emerged in recent years to reduce interference with the motor itself and reduce the potential risk. At present, a temperature and vibration integrated sensor is mostly adopted to acquire external vibration speed and vibration displacement data when a motor operates, so that the operation state of the motor is estimated.
However, the running states of the motors are changeable, the practical application situation is complex, the running states of the motors are difficult to evaluate by the data of the vibration speeds independently, and the running states of the motors are possibly evaluated by the data of the vibration displacement of the motors due to single direction of the displacement data caused by the running environment of the motors and the direction of the motors.
Disclosure of Invention
In order to solve the technical problems, the invention provides an intelligent monitoring method for the running state of a motor, so as to solve the existing problems.
The intelligent monitoring method for the running state of the motor adopts the following technical scheme:
the embodiment of the invention provides an intelligent monitoring method for the running state of a motor, which comprises the following steps:
acquiring motor vibration speed data and motor vibration displacement data; acquiring a motor vibration displacement matrix according to motor vibration displacement data;
acquiring jump condition distinguishing indexes at each moment according to the change of the motor vibration speed data at each moment; acquiring a jump cluster point cluster according to jump condition discrimination indexes at each moment; acquiring the subsequent association coefficient of each jumping point according to each jumping point in the jumping cluster point cluster; acquiring motor vibration deflection coefficients at all moments according to a motor vibration displacement matrix; acquiring an abnormal evaluation index of each trip point according to the subsequent association coefficient of each trip point and the motor polarization coefficient at the corresponding moment; screening out abnormal jump points according to the abnormal evaluation indexes of the jump points; acquiring a time data set according to the time points corresponding to the abnormal jump points; constructing an abnormal operation index of the motor according to the data set at each moment;
and finishing the detection of the running state of the motor based on the abnormal running index of the motor.
Preferably, the jump condition identification index at each moment is obtained according to the change of the motor vibration speed data at each moment, specifically:
taking one half of the motor vibration speed data change value at each moment and the motor vibration speed difference value at the previous moment as the jump change rate at the moment; and taking the absolute value of the difference value of the jump change rate at each moment and the average value of the jump change rates at all moments as a jump condition distinguishing index at each moment.
Preferably, the method for acquiring the jump cluster point cluster according to the jump condition distinguishing index at each moment comprises the following steps:
obtaining the maximum value of jump condition discrimination indexes at all moments; taking the jump condition distinguishing indexes at all moments as the input of a clustering algorithm to obtain two clusters; and marking the cluster in which the maximum value of the jump condition distinguishing index is positioned as a jump cluster.
Preferably, the acquiring method acquires the subsequent association coefficient of each trip point according to each trip point in the trip cluster point cluster, and the acquiring method comprises the following steps:
forming a correlation sequence by corresponding data points of each jump point in a motor vibration speed data sequence and last M data points of the corresponding data points, wherein M is the number of preset data points; acquiring the mean value and standard deviation of the associated sequence; calculating the ratio of the standard deviation to the mean; taking the inverse number of the ratio as an index of an exponential function based on a natural constant; and taking the calculation result of the exponential function as a jump follow-up association coefficient of each jump point.
Preferably, the motor vibration deflection coefficient at each moment is obtained according to the motor vibration displacement matrix, and the obtaining method comprises the following steps:
taking the value of an inverse cosine function of the ratio of displacement data of a motor shaft in two vertical directions at each moment as an included angle of the vibration deflection direction of the motor at each moment; acquiring the average value of the included angles of the vibration deflection directions of the motor at all moments; the square of the absolute value of the difference between the included angle of the motor vibration deflection direction at each moment and the average value of the included angle is recorded as the difference value of the included angle;
taking Euclidean distance of displacement data of a motor shaft in two vertical directions at each moment as a vibration deflection direction displacement value at each moment; acquiring the mean value of the displacement values of the vibration deflection directions at all moments; the square of the absolute value of the difference between the motor vibration deflection direction displacement value at each moment and the average value of the displacement values is recorded as a displacement difference value;
and taking the product of the included angle difference value and the displacement difference value as a motor vibration deflection coefficient at each moment.
Preferably, the abnormality evaluation index is a product of a subsequent association coefficient of each trip point and a motor polarization coefficient corresponding to the trip point.
Preferably, the step of screening out the abnormal trip points according to the abnormal evaluation indexes of the trip points specifically includes:
acquiring an abnormal evaluation index threshold value according to the abnormal evaluation indexes of all the jumping points by adopting a cross validation algorithm; and marking the jump points with the abnormality evaluation indexes larger than the threshold value of the abnormality evaluation indexes as abnormal jump points.
Preferably, the method for acquiring the time data set according to the time points corresponding to the different jump points specifically includes:
acquiring corresponding moments of various abnormal jump points in motor operation vibration data; and adopting a region growing algorithm, taking the moment corresponding to any abnormal jump point as an initial point, and taking the adjacent moment corresponding to two abnormal jump points as a growing criterion to obtain each moment data set.
Preferably, the abnormal operation index of the motor is constructed according to the data set at each moment, and the specific expression is:
,
,
wherein QS is the abnormal operation index of the motor, R h For the weight of the h moment, p is the total number of the moment data sets of the abnormal jump points, D h 、D j Respectively, the h time data set and the j time data set, the Card () is a function for acquiring the number of the set elements, and the element () f To obtain a corresponding vibration velocity data value function for the f-th element of the set.
Preferably, the detection of the motor running state based on the abnormal running index of the motor is completed, and the specific method comprises the following steps:
acquiring an abnormal operation threshold value of the motor according to the abnormal operation index of the motor by adopting a cross validation algorithm; when the abnormal operation index of the motor is larger than the abnormal threshold value of the motor, the abnormal operation of the motor is indicated; and when the abnormal operation index of the motor is smaller than the abnormal threshold value of the motor, the motor is indicated to normally operate.
The invention has at least the following beneficial effects:
according to the invention, the temperature and vibration integrated transmitter is arranged according to the axial direction of the motor to detect the running state of the motor, so that the vibration data errors generated by the running environment of the motor or the setting position of the motor are reduced; meanwhile, vibration conditions during motor operation are analyzed, jump data are screened, direction synthesis is conducted on vibration displacement data corresponding to the jump time data, abnormal operation indexes of the motor are built by combining vibration speed and vibration displacement, further abnormal degrees of motor operation conditions are well estimated, motor operation states are detected, and robustness and accuracy of detection are effectively improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of an intelligent monitoring method for motor running state.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following is a detailed description of specific implementation, structure, characteristics and effects of an intelligent monitoring method for the running state of a motor according to the invention with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, 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 invention belongs.
The following specifically describes a specific scheme of the intelligent monitoring method for the running state of the motor provided by the invention with reference to the accompanying drawings.
The embodiment of the invention provides an intelligent monitoring method for the running state of a motor.
Specifically, the following method for intelligently monitoring the running state of a motor is provided, referring to fig. 1, and the method comprises the following steps:
step S001: and a temperature and vibration integrated transmitter is arranged outside the running motor, data acquisition is carried out on the running motor, and data pretreatment is carried out.
The outside of the motor takes the vertical direction of the motor as a Z axis, the horizontal direction of the motor as an X axis, and the motor axial direction is a Y axis, and an RS485 type temperature and vibration integrated transmitter is arranged. And after the time interval T, the temperature and vibration integrated transmitter is utilized to acquire data of the motor, the change conditions of parameters such as external temperature, vibration speed, vibration displacement and the like are acquired, and then the acquired data are preprocessed, so that the integrity of the data is ensured. It should be noted that, the method implementation of data preprocessing can be selected by the user according to the actual situation, in this embodiment, the collected data is preprocessed by using a mean filling method, which is a known technology in the prior art, and will not be described in detail in this embodiment.
The motor vibration speed data sequence is recorded as A 1 ,A 2 ,…,A n Wherein n is the total number of data acquired and the vibration displacement of the motor is due to the presence ofThe displacement in three directions was recorded as a vibration displacement matrix by dividing the data into three directions, and the expression was as follows:
,
wherein C represents a vibration displacement matrix,、/>、/>respectively representing vibration displacement values of the motor on the X axis at the 1 st, 2 nd and n th moments during operation, < >>、/>、/>Respectively representing vibration displacement values of the motor on the Y axis at the 1 st, 2 nd and n th moments during operation, < >>、/>、/>The vibration displacement values of the motor on the Z axis at the 1 st, 2 nd and n th moments in running are respectively shown.
It should be noted that, in the present embodiment, the time interval t=5 min, the total number of collected data n=500, and the practitioner can adjust according to the actual situation.
Step S002: and analyzing the vibration condition and displacement condition of the motor during operation, constructing an abnormal evaluation coefficient of the trip point, screening the abnormal trip point, and constructing an abnormal operation index of the motor in combination with the corresponding moment of the abnormal trip point.
When the motor is in normal operation, the vibration speed of the motor can fluctuate within a small range, and because the working requirements of the motor in industrial production are different, the output power of the motor needs to be adjusted occasionally according to the corresponding production requirements. During operation of the motor, an increase in output power generally results in an increase in the load inside the motor, thus producing more intense vibrations. As the load increases, the vibration frequency of the motor may rise due to a change in the vibration mode of the motor caused by the change in the load. As the load stabilizes, the vibration frequency may again stabilize after reaching the frequency corresponding to the motor output power. When the running state of the motor is abnormal, two conditions exist, wherein the first condition is that the motor equipment is old, accessories are abnormal and the like, so that the vibration frequency is greatly fluctuated when the motor runs, and the fluctuation is particularly increased in fluctuation amplitude and accelerated in fluctuation speed; the second situation is that the motor may fail, resulting in the motor not being able to continue to operate or operating at a power that does not meet the production requirements, resulting in the vibration frequency of the motor slipping down.
According to the characteristics of vibration data of abnormal motor operation, firstly, a motor vibration speed data sequence A is analyzed, and jump points of data change are found out. For normal operating conditions of the motor, the trip point is typically generated when the motor adjusts the output efficiency. When the motor output power increases, the load is generally increased, and a change in vibration characteristics such as a vibration frequency and an amplitude of the motor is caused. The larger load often causes the aggravation of the unbalance phenomenon in the motor, thereby inducing stronger vibration; when the motor output power decreases, the load decrease may cause the vibration characteristics inside the motor to also change. At lower vibration speeds, imbalance and resonance may be reduced, resulting in lower vibration levels. During operation of the motor, certain faults or anomalies may cause abrupt changes in the vibration characteristics of the motor. Such a change is typically manifested as a sudden jump in frequency, amplitude or phase of the vibration, the point of jump of which may be an indication of an abnormal change. For example, when a malfunction such as loosening of an internal structure, damage to bearings, unbalance, or the like occurs in the motor, a sudden change in vibration characteristics may occur at a certain point in time. Another situation is that the motor fails to operate properly and the vibration speed is extremely low. This may be due to motor failure, power supply problems, or other reasons. In this case, the trip point may appear as a significant drop or an abnormally low value of the vibration speed data.
According to the change of each data point in the motor vibration speed data sequence, a jump condition distinguishing index is constructed, and the specific expression is as follows:
,
,
wherein V is i For the jump change rate of the ith data point in the motor vibration speed data sequence, TBZ i A is a jump condition identification index of an ith data point in a motor vibration speed data sequence i-1 、A i Respectively the i-1 th data value and the i th data value in the motor vibration speed data sequence,the jump change rate average value of all data points of the motor vibration speed data sequence is obtained. The jump change rate of the first data point is the average value of the jump change rates of the two data points closest to the first data point.
Taking the jump condition identification index of each data point as the input of a K-means clustering algorithm, taking Euclidean distance between jump condition identification index data as the measurement distance during clustering, setting the number K of clustering clusters as 2, clustering the data points, finally outputting two classes to be marked as a clustering cluster X and a clustering cluster Y, obtaining the maximum jump condition identification indexes of the data points in the clustering cluster X and the clustering cluster Y, and marking the maximum jump condition identification indexes as the maximum jump condition identification indexes of the data points in the clustering cluster X and the maximum jump condition identification indexes in the clustering cluster Y respectively asAnd->When->If the number of the clusters is greater than 0, the cluster X is the cluster of jumping points in the motor vibration speed data sequence, and when +.>And if the number of the clusters is smaller than 0, the cluster Y is the cluster of the jumping points in the motor vibration speed data sequence.
In the clustering result, one class is a jump condition identification index cluster of the jump point, the other class is a jump condition identification index cluster of the common data point, and the jump change rate value of the jump point is necessarily larger than that of the common data point, so that the jump condition identification index of the jump point is necessarily larger than that of the common data point, and the jump condition identification index of the jump point is thereforeThere is no case equal to 0. On the other hand, the analysis method for the cluster of jumping points is consistent, so in the embodiment, the cluster X is assumed to be the cluster of the acquired jumping points of the motor vibration speed data sequence, and is analyzed.
The trip points in the motor vibration speed data sequence are distinguished based on the calculation, and the trip point cluster X is obtained.
The jump point cluster X comprises a change point of the motor vibration speed during normal motor power adjustment and an abnormal point when the motor is in an abnormal state, and in order to distinguish the normal change point and the abnormal point, the data points in the jump point cluster X are subjected to further association degree analysis.
Specifically, corresponding to each jump point, a corresponding data point in the motor vibration speed data sequence and the last M data points of the corresponding element are taken to form an association sequence, and the association sequence is used for judging the correlation between the jump point and the subsequent motor vibration speed. When it should be noted that, the number of data points can be set by the practitioner according to the actual situation, in this embodiment, m=10. The vibration conditions of the motor after the normal operation of the motor is jumped and before the normal operation of the motor is jumped are obviously different, namely the change condition occurs and ends in a short time, and the vibration of the motor is not greatly influenced. For each data point of the motor vibration speed data sequence, constructing a jump follow-up association coefficient of the jump point according to the distribution characteristics of the data points in the association sequence, wherein the specific expression is as follows:
,
in the formula, TBX i For the subsequent association coefficient of the hopping of the ith hopping point, G i For the average value of the associated sequences corresponding to the ith jump point, Z i For the standard deviation of the associated sequence corresponding to the ith trip point, exp () is an exponential function based on a natural constant.
The higher the association degree of the ith trip point with the data in the corresponding association sequence, the more likely the trip point is when the motor is operating normally,the smaller the value of TBX i The greater the value of (2); when the association degree of the ith trip point and the data in the corresponding association sequence is lower, the trip point is more likely to be the trip point when the motor generates abnormality, +.>The larger the value of TBX i The smaller the value of (2).
In order to further screen out abnormal jump points, analysis and calculation are carried out by combining the vibration displacement matrix C.
Specifically, when the Wen Zhen integrated transmitter is installed, the axial direction of the motor is set to be the Y axis, the vertical direction of the motor is set to be the Z axis, and the horizontal direction of the motor is set to be the X axis, so that when the motor operates normally, vibration of the motor hardly generates vibration displacement on the Y axis, vibration displacement is generated in the Z axis and the X axis, and the displacement generated on the X axis and the Z axis has a correlation. When the motor runs, a jump condition is generated, the vibration speed is changed, and the vibration displacement is also changed. And taking the X axis as a transverse axis and the Z axis as a longitudinal axis, and constructing a rectangular coordinate system XZ, wherein the X-axis vibration displacement data and the Z-axis vibration displacement data corresponding to the X-axis vibration displacement data and the Z-axis vibration displacement data exist at each moment, and the X-axis vibration displacement data and the Z-axis vibration displacement data are combined into a vibration deflection direction in the rectangular coordinate system, and an included angle theta is formed between the X-axis vibration displacement data and the Z-axis vibration displacement data and the transverse coordinate axis.
When the motor normally operates, the vibration condition of the motor is balanced at each moment, the formed vibration deflection direction is similar no matter in the normal operating state or after the output power of the motor is changed, the included angle theta is also similar, and only the values of the Z axis and the X axis are changed after the output power of the motor is changed; when the motor is abnormal, the vibration generated by the motor changes, and the deflection direction of the generated vibration changes.
Based on the X-axis data sequence and the Z-axis data sequence in the vibration displacement matrix C, a motor vibration deflection coefficient is constructed according to the vibration deflection direction characteristics at each moment, and the expression is as follows:
,
,
,
in θ i Is the included angle W of the vibration deflection direction of the motor at the ith moment i ZPL is the vibration deflection direction displacement value at the i-th time i Is the motor vibration deflection coefficient at the ith moment,、/>the vibration displacement values of the X axis and the Z axis at the ith moment are respectively +.>Is the mean value of the included angles of the vibration deflection directions of the motor, +.>Is the mean value of the displacement values of the vibration deflection vectors. Will->Recorded as the difference of included angles, will +.>Recorded as displacement difference values.
When the value of the motor vibration deflection coefficient is larger, the vibration deflection direction and the length of the vibration deflection vector of the motor are larger, the motor operation is possibly abnormal, and when the value of the motor vibration deflection coefficient is smaller, the vibration deflection direction and the length of the vibration deflection vector of the motor are both fluctuated within a reasonable range, and the motor operation is normal.
Combining the subsequent association coefficient of the jump of the ith jump point and the vibration deviation coefficient of the corresponding moment, and fusing to construct an jump point abnormality evaluation index, wherein the expression is as follows:
SDL i =norm(TBX i ×ZPL i )
in the formula, SDL i Abnormality evaluation index for ith trip point, TBX i ZPL for the subsequent association coefficient of the ith trip point i And (3) motor vibration bias coefficient of the ith jump point, wherein norm () is a normalization function.
Finally, using an abnormal evaluation index of each trip point as data input by a cross verification method, performing 10-fold cross verification, outputting a trip point abnormal evaluation index threshold, and when the value of the abnormal evaluation index is greater than or equal to the abnormal evaluation index threshold, indicating that the association degree of the trip point and the subsequent data is low, and the motor vibration deviation condition at the time of the trip point is serious, wherein the trip point is the abnormal trip point; when the value of the abnormal evaluation index is smaller than the threshold value of the abnormal evaluation index, the association degree of the jump point and the subsequent data is large, the vibration displacement of the motor is normal at the moment of the jump point, and the jump point is a change point of the normal operation of the motor. It should be noted that, the cross-validation method for obtaining the threshold is a known technology, and will not be described in detail in this embodiment.
So far, the abnormal jump point in the motor operation vibration speed data is obtained.
Acquiring corresponding time of an abnormal jump point in motor operation vibration speed data, using a region growing algorithm, taking time points corresponding to any abnormal jump point as an initial point, taking adjacent time points corresponding to two abnormal jump points as a growing criterion, growing the time points corresponding to the abnormal jump points which are in the vicinity of the initial point and meet the growing criterion, stopping growing when no data points which are in the vicinity of the initial point and meet the growing criterion exist, outputting a plurality of time data sets, and recording as D 1 ,D 2 ,…,D p And constructing an abnormal operation index of the motor by combining data elements in each set, wherein the expression is as follows:
wherein QS is the abnormal operation index of the motor, R h For the weight of the h moment, p is the total number of the moment data sets of the abnormal jump points, D h 、D j Respectively, the h time data set and the j time data set, the Card () is a function for acquiring the number of the set elements, and the element () f To obtain a corresponding vibration velocity data value function for the f-th element of the set.
So far, the abnormal operation index of the motor is obtained as an evaluation index of the operation state of the motor.
Step S003: and detecting the running state of the motor based on the abnormal running index of the motor.
Normalizing the abnormal motor operation index to be between (0 and 1), carrying out 10-fold cross validation by taking the normalized abnormal motor operation index as input by a cross validation method, outputting a motor abnormal operation threshold, indicating that the abnormal motor jump is more continuous when the value of the normalized abnormal motor operation index is more than or equal to the abnormal motor operation threshold, and sending out a relevant warning signal to relevant staff by a monitoring system when the value of the normalized abnormal motor operation index is less than the abnormal motor operation threshold.
Thus, intelligent detection of the running state of the target motor is completed.
In summary, the embodiment of the invention mainly aims at the situation that the vibration speed data is difficult to evaluate the running state of the motor independently and the vibration displacement data of the motor is easy to distinguish errors when the motor runs, and firstly, the temperature and vibration integrated transmitter is arranged according to the axial direction of the motor to detect the running state of the motor, so that the vibration data errors generated by the running environment of the motor or the setting position of the motor are reduced; meanwhile, vibration conditions during motor operation are analyzed, jump data are screened, direction synthesis is conducted on vibration displacement data corresponding to the jump time data, abnormal operation indexes of the motor are built by combining vibration speed and vibration displacement, further abnormal degrees of motor operation conditions are well estimated, motor operation states are detected, and robustness and accuracy of detection are effectively improved.
It should be noted that: the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this specification. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and the same or similar parts of each embodiment are referred to each other, and each embodiment mainly describes differences from other embodiments.
The above embodiments are only for illustrating the technical solution of the present application, and are not limiting; the technical solutions described in the foregoing embodiments are modified or some of the technical features are replaced equivalently, so that the essence of the corresponding technical solutions does not deviate from the scope of the technical solutions of the embodiments of the present application, and all the technical solutions are included in the protection scope of the present application.

Claims (6)

1. An intelligent monitoring method for the running state of a motor is characterized by comprising the following steps:
acquiring motor vibration speed data and motor vibration displacement data; acquiring a motor vibration displacement matrix according to motor vibration displacement data;
acquiring jump condition distinguishing indexes at each moment according to the change of the motor vibration speed data at each moment; acquiring a jump cluster point cluster according to jump condition discrimination indexes at each moment; acquiring the subsequent association coefficient of each jumping point according to each jumping point in the jumping cluster point cluster; acquiring motor vibration deflection coefficients at all moments according to a motor vibration displacement matrix; acquiring an abnormal evaluation index of each trip point according to the subsequent association coefficient of each trip point and the motor polarization coefficient at the corresponding moment; screening out abnormal jump points according to the abnormal evaluation indexes of the jump points; acquiring a time data set according to the time points corresponding to the abnormal jump points; constructing an abnormal operation index of the motor according to the data set at each moment;
finishing the detection of the running state of the motor based on the abnormal running index of the motor;
the subsequent association coefficient of each hopping point is obtained according to each hopping point in the hopping cluster point cluster, and the obtaining method comprises the following steps: forming a correlation sequence by corresponding data points of each jump point in a motor vibration speed data sequence and last M data points of the corresponding data points, wherein M is the number of preset data points; acquiring the mean value and standard deviation of the associated sequence; calculating the ratio of the standard deviation to the mean; taking the inverse number of the ratio as an index of an exponential function based on a natural constant; taking the calculation result of the exponential function as a jump follow-up association coefficient of each jump point;
the motor vibration deflection coefficients at all moments are obtained according to the motor vibration displacement matrix, and the obtaining method comprises the following steps: taking the value of an inverse cosine function of the ratio of displacement data of a motor shaft in two vertical directions at each moment as an included angle of the vibration deflection direction of the motor at each moment; acquiring the average value of the included angles of the vibration deflection directions of the motor at all moments; the square of the absolute value of the difference between the included angle of the motor vibration deflection direction at each moment and the average value of the included angle is recorded as the difference value of the included angle; taking Euclidean distance of displacement data of a motor shaft in two vertical directions at each moment as a vibration deflection direction displacement value at each moment; acquiring the mean value of the displacement values of the vibration deflection directions at all moments; the square of the absolute value of the difference between the motor vibration deflection direction displacement value at each moment and the average value of the displacement values is recorded as a displacement difference value; taking the product of the included angle difference value and the displacement difference value as a motor vibration deviation coefficient at each moment;
the abnormality evaluation index is the product of the subsequent association coefficient of each jump point and the motor polarization coefficient at the corresponding moment;
the abnormal operation index of the motor is constructed according to the data set at each moment, and the specific expression is as follows:
;
;
wherein QS is the abnormal operation index of the motor, R h For the weight of the h moment, p is the total number of the moment data sets of the abnormal jump points, D h 、D j Respectively, the h time data set and the j time data set, the Card () is a function for acquiring the number of the set elements, and the element () f To obtain a corresponding vibration velocity data value function for the f-th element of the set.
2. The intelligent monitoring method for motor operation state according to claim 1, wherein the jump condition discrimination index at each moment is obtained according to the motor vibration speed data change at each moment, specifically:
taking one half of the motor vibration speed data change value at each moment and the motor vibration speed difference value at the previous moment as the jump change rate at the moment; and taking the absolute value of the difference value of the jump change rate at each moment and the average value of the jump change rates at all moments as a jump condition distinguishing index at each moment.
3. The intelligent monitoring method for motor operation state according to claim 1, wherein the jump cluster point cluster is obtained according to jump condition distinguishing indexes at each moment, and the obtaining method comprises the following steps:
obtaining the maximum value of jump condition discrimination indexes at all moments; taking the jump condition distinguishing indexes at all moments as the input of a clustering algorithm to obtain two clusters; and marking the cluster in which the maximum value of the jump condition distinguishing index is positioned as a jump cluster.
4. The intelligent monitoring method for motor operation state according to claim 1, wherein the step of screening out abnormal trip points according to the abnormality evaluation index of each trip point comprises the following specific steps:
acquiring an abnormal evaluation index threshold value according to the abnormal evaluation indexes of all the jumping points by adopting a cross validation algorithm; and marking the jump points with the abnormality evaluation indexes larger than the threshold value of the abnormality evaluation indexes as abnormal jump points.
5. The intelligent monitoring method for motor operation state according to claim 1, wherein the acquiring the time data set according to the time point corresponding to each abnormal jump point comprises the following specific steps:
acquiring corresponding moments of various abnormal jump points in motor operation vibration data; and adopting a region growing algorithm, taking the moment corresponding to any abnormal jump point as an initial point, and taking the adjacent moment corresponding to two abnormal jump points as a growing criterion to obtain each moment data set.
6. The intelligent monitoring method for motor operation state according to claim 1, wherein the detection of motor operation state based on abnormal motor operation index is completed by the following steps:
acquiring an abnormal operation threshold value of the motor according to the abnormal operation index of the motor by adopting a cross validation algorithm; when the abnormal operation index of the motor is larger than the abnormal threshold value of the motor, the abnormal operation of the motor is indicated; and when the abnormal operation index of the motor is smaller than the abnormal threshold value of the motor, the motor is indicated to normally operate.
CN202311276133.7A 2023-09-29 2023-09-29 Intelligent monitoring method for motor running state Active CN117031277B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311276133.7A CN117031277B (en) 2023-09-29 2023-09-29 Intelligent monitoring method for motor running state

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311276133.7A CN117031277B (en) 2023-09-29 2023-09-29 Intelligent monitoring method for motor running state

Publications (2)

Publication Number Publication Date
CN117031277A CN117031277A (en) 2023-11-10
CN117031277B true CN117031277B (en) 2023-12-19

Family

ID=88630243

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311276133.7A Active CN117031277B (en) 2023-09-29 2023-09-29 Intelligent monitoring method for motor running state

Country Status (1)

Country Link
CN (1) CN117031277B (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117235615B (en) * 2023-11-14 2024-01-30 泰安维创游乐设备有限公司 Potential safety hazard risk early warning system for large amusement park equipment
CN117433591B (en) * 2023-12-21 2024-02-27 河北省农林科学院农业信息与经济研究所 Automatic equipment monitoring system based on multi-sensor data
CN117498735B (en) * 2024-01-02 2024-03-19 深圳市爱宝科技有限公司 Dynamic stable driving method and system for stepping motor
CN117743836B (en) * 2024-02-21 2024-05-03 聊城市产品质量监督检验所 Abnormal vibration monitoring method for bearing

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110458248A (en) * 2019-09-18 2019-11-15 华北电力大学(保定) Transformer exception condition detection method based on multi-measuring point vibration signal
CN111650514A (en) * 2020-06-15 2020-09-11 珠海万力达电气自动化有限公司 Multi-parameter joint diagnosis method for typical faults of asynchronous motor
CN112459971A (en) * 2020-11-30 2021-03-09 吉电(滁州)章广风力发电有限公司 Abnormal vibration detection method for tower of wind generating set
CN113780354A (en) * 2021-08-11 2021-12-10 国网上海市电力公司 Telemetry data anomaly identification method and device for dispatching automation master station system
WO2022252505A1 (en) * 2021-06-02 2022-12-08 杭州安脉盛智能技术有限公司 Device state monitoring method based on multi-index cluster analysis
CN116304766A (en) * 2023-05-25 2023-06-23 山东艾迈科思电气有限公司 Multi-sensor-based quick assessment method for state of switch cabinet
CN116701973A (en) * 2023-08-09 2023-09-05 无锡市明通动力工业有限公司 Motor abnormal vibration detection early warning method based on big data

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110458248A (en) * 2019-09-18 2019-11-15 华北电力大学(保定) Transformer exception condition detection method based on multi-measuring point vibration signal
CN111650514A (en) * 2020-06-15 2020-09-11 珠海万力达电气自动化有限公司 Multi-parameter joint diagnosis method for typical faults of asynchronous motor
CN112459971A (en) * 2020-11-30 2021-03-09 吉电(滁州)章广风力发电有限公司 Abnormal vibration detection method for tower of wind generating set
WO2022252505A1 (en) * 2021-06-02 2022-12-08 杭州安脉盛智能技术有限公司 Device state monitoring method based on multi-index cluster analysis
CN113780354A (en) * 2021-08-11 2021-12-10 国网上海市电力公司 Telemetry data anomaly identification method and device for dispatching automation master station system
CN116304766A (en) * 2023-05-25 2023-06-23 山东艾迈科思电气有限公司 Multi-sensor-based quick assessment method for state of switch cabinet
CN116701973A (en) * 2023-08-09 2023-09-05 无锡市明通动力工业有限公司 Motor abnormal vibration detection early warning method based on big data

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
基于滑动窗口和聚类算法的变压器状态异常检测;严英杰;盛戈;刘亚东;杜修明;王辉;江秀臣;;高电压技术;第42卷(第12期);第4020-4025页 *

Also Published As

Publication number Publication date
CN117031277A (en) 2023-11-10

Similar Documents

Publication Publication Date Title
CN117031277B (en) Intelligent monitoring method for motor running state
US11494618B2 (en) Anomaly detection using deep learning on time series data
CN110515351A (en) Anomaly detector
CN104915568B (en) Satellite telemetering data method for detecting abnormality based on DTW
CN111665066B (en) Equipment fault self-adaptive upper and lower early warning boundary generation method based on convolutional neural network
CN103792155B (en) Based on the bit wear Forecasting Methodology of inertia measurement parameter
KR20190025473A (en) Apparatus and Method for Predicting Plant Data
EP3441572A1 (en) Turbine blade maximum response prediction method, turbine blade maximum response prediction system and control program, and turbine equipped with turbine blade maximum response prediction system
US20180157249A1 (en) Abnormality Detecting Apparatus
JP2017129583A (en) Vibration monitoring systems
GB2507934A (en) Method, device and computer program for detecting occurrence of abnormality
US20200263669A1 (en) Operating state evaluation method and operating state evaluation device
EP2135144B1 (en) Machine condition monitoring using pattern rules
CN110472335A (en) Sensor fault diagnosis Threshold based on particle swarm optimization algorithm
CN115273791A (en) Industrial equipment fault detection method and device based on acoustic feature driving
CN103105292A (en) Stick-slip detecting device and detecting method
AU2021102131A4 (en) Fault diagnosis method of rolling bearing based on generalized composite multi-scale weighted permutation entropy and supervised isometric mapping
WO2022064038A1 (en) Method and system for wind speed determination using vibration data
JPWO2018051568A1 (en) Plant abnormality diagnosis device and plant abnormality diagnosis system
US20200410042A1 (en) Abnormality detection device, abnormality detection method, and non-transitory computer-readable medium
US10845792B2 (en) Failure diagnosis apparatus, monitoring apparatus, failure diagnosis method and recording medium
KR20210060520A (en) A method for monitoring the motion of a machine generating vibration and a device for implementing the method
CN114046816B (en) Sensor signal fault diagnosis method based on lightweight gradient lifting decision tree
CN112651078B (en) Arrow body structure state abnormality detection method based on symbol dynamics
CN114227701B (en) Robot fault prediction method based on production data

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
CP03 Change of name, title or address

Address after: No. 2-1 Wuhu Road, Fenghuang Town, Zhangjiagang City, Suzhou City, Jiangsu Province, 215600

Patentee after: SUZHOU BAOBANG ELECTRIC Co.,Ltd.

Country or region after: China

Address before: Building B, Building 1, Fenghuang Technology Entrepreneurship Park, No. 7 Fenghuang Avenue, Fenghuang Town, Zhangjiagang City, Suzhou City, Jiangsu Province, 215600

Patentee before: SUZHOU BAOBANG ELECTRIC Co.,Ltd.

Country or region before: China