CN116878886B - Method for monitoring abrasion of water pump bearing of cooling tower - Google Patents
Method for monitoring abrasion of water pump bearing of cooling tower Download PDFInfo
- Publication number
- CN116878886B CN116878886B CN202311133444.8A CN202311133444A CN116878886B CN 116878886 B CN116878886 B CN 116878886B CN 202311133444 A CN202311133444 A CN 202311133444A CN 116878886 B CN116878886 B CN 116878886B
- Authority
- CN
- China
- Prior art keywords
- bearing
- sequence
- vibration acceleration
- set time
- time period
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 167
- 238000001816 cooling Methods 0.000 title claims abstract description 61
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000012544 monitoring process Methods 0.000 title claims abstract description 18
- 238000005299 abrasion Methods 0.000 title abstract description 15
- 230000001133 acceleration Effects 0.000 claims abstract description 125
- 230000008859 change Effects 0.000 claims abstract description 93
- 239000013598 vector Substances 0.000 claims abstract description 36
- 238000013145 classification model Methods 0.000 claims abstract description 34
- 238000012706 support-vector machine Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 6
- 230000006378 damage Effects 0.000 description 27
- 230000006870 function Effects 0.000 description 12
- 230000000694 effects Effects 0.000 description 7
- 239000012530 fluid Substances 0.000 description 6
- 239000007788 liquid Substances 0.000 description 4
- 238000005096 rolling process Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 238000009434 installation Methods 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 238000007789 sealing Methods 0.000 description 2
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 239000000945 filler Substances 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F04—POSITIVE - DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS FOR LIQUIDS OR ELASTIC FLUIDS
- F04D—NON-POSITIVE-DISPLACEMENT PUMPS
- F04D15/00—Control, e.g. regulation, of pumps, pumping installations or systems
- F04D15/0088—Testing machines
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING 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
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
- G01M13/04—Bearings
- G01M13/045—Acoustic or vibration analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2123/00—Data types
- G06F2123/02—Data types in the time domain, e.g. time-series data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Computation (AREA)
- Acoustics & Sound (AREA)
- Mechanical Engineering (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
- Structures Of Non-Positive Displacement Pumps (AREA)
Abstract
The invention relates to the technical field of bearing wear, in particular to a method for monitoring bearing wear of a water pump of a cooling tower, which comprises the following steps: acquiring a bearing vibration acceleration sequence, a water pump working power sequence and a return water end temperature sequence, and calculating a vibration acceleration change degree index based on each vibration acceleration in the bearing vibration acceleration sequence; obtaining a working power change degree index according to the working power in the water pump working power sequence; calculating a temperature change degree index based on the difference of temperatures of all backwater ends in the backwater end temperature sequence; forming a characteristic parameter vector corresponding to the set time period by using the vibration acceleration change degree index, the working power change degree index and the temperature change degree index of the set time period; and constructing a classification model according to the characteristic parameter vectors corresponding to the set time periods, acquiring the characteristic parameter vector corresponding to the current time period, and acquiring the wear grade corresponding to the bearing of the current time period by using the classification model. The invention can obtain accurate bearing abrasion condition.
Description
Technical Field
The invention relates to the technical field of bearing wear, in particular to a method for monitoring bearing wear of a water pump of a cooling tower.
Background
Fluid machinery is widely used in petrochemical industry, agriculture, electric power and other fields. Rolling bearings are an important component for supporting the rotor system of a fluid machine, and their normal operation plays an important role in the normal operation of the fluid machine. The bearing can have faults such as fatigue, abrasion, corrosion and the like in different forms or different degrees in complex and changeable mechanical systems and working environments, so that the condition of failure or scrapping is caused, and the normal operation of the whole machine is further influenced. Therefore, the diagnosis of bearing faults is particularly important to the detection and early warning of fluid mechanical faults.
The impact of the wear condition of the bearing is greatest when analyzing the fault condition of the bearing. A water pump is used as one of fluid machines and is applied to many scenes. The cooling tower heat exchange water pump is large in size, technicians in the installation position are not easy to contact, the environment is complex, and the abrasion monitoring of the bearings of the cooling tower is greatly hindered. In the prior art, the bearing carrier state can be monitored through data fed back by the sensor, but when the abrasion condition of the bearing is detected, only the condition of the bearing is considered, and the abnormal condition of the fluid machinery where the bearing is positioned is not combined for analysis, so that the analysis result is relatively inaccurate.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide a method for monitoring the abrasion of a water pump bearing of a cooling tower, which adopts the following technical scheme:
acquiring a fixed number of set time periods, acquiring vibration acceleration of a bearing at different moments in the set time periods, and respectively forming a bearing vibration acceleration sequence, a water pump working power sequence and a water return end temperature sequence by the working power of a water pump and the temperature of a water return end of a cooling tower;
calculating a vibration acceleration change degree index based on each vibration acceleration and the range of the vibration acceleration in the bearing vibration acceleration sequence; obtaining a working power change degree index according to the maximum value, the minimum value and the average value of the working power in the water pump working power sequence; calculating a temperature change degree index based on the difference of temperatures of all backwater ends in the backwater end temperature sequence;
forming a characteristic parameter vector corresponding to the set time period by using the vibration acceleration change degree index, the working power change degree index and the temperature change degree index corresponding to the set time period; and constructing a classification model according to the characteristic parameter vectors corresponding to the set time periods, acquiring the characteristic parameter vector corresponding to the current time period, and acquiring the wear grade corresponding to the bearing of the current time period by using the classification model.
Preferably, the acquiring the fixed number of set time periods is specifically: and acquiring a fixed number of set time periods according to the fixed time interval, wherein the time lengths of the set time periods are equal.
Preferably, the method for acquiring the vibration acceleration change degree index specifically comprises the following steps:
performing straight line fitting according to each moment in the bearing vibration acceleration sequence corresponding to any one set time period and the vibration acceleration corresponding to the moment, and obtaining the slope of the straight line obtained by fitting; and calculating the difference between the vibration acceleration corresponding to each moment in the bearing vibration acceleration sequence and the vibration acceleration corresponding to the same moment on the fitted straight line, and obtaining the vibration acceleration change degree index according to the slope of the straight line, the difference and the range.
Preferably, the method for acquiring the working power change degree index specifically comprises the following steps:
wherein,indicating the degree of change of the operating power corresponding to the nth set time period, < >>Representing the extreme difference of the working power in the water pump working power sequence corresponding to the set time period>Indicating the working power corresponding to the t-th moment in the working power sequence of the water pump, < >>The average value of all the operating powers in the water pump operating power sequence is represented, T represents the total number of times included in the set period, ln () represents a logarithmic function based on a natural constant e, exp () represents an exponential function based on a natural constant e.
Preferably, the method for obtaining the temperature change degree index specifically includes:
calculating the variance of the backwater end temperature in the backwater end temperature sequence corresponding to any set time period, obtaining the median value of the backwater end temperature in the backwater end temperature sequence, counting the number of moments corresponding to the backwater end temperature greater than the median value in the backwater end temperature sequence, calculating the average value of the differences of the backwater end temperatures corresponding to all adjacent two moments, obtaining a temperature change degree index according to the variance, the number and the average value, and expressing the temperature change degree index as follows by a formula:
wherein,index indicating the degree of temperature change corresponding to the nth set period of time,/->Indicating the number of times corresponding to the time when the temperature of the backwater end is greater than the median value in the backwater end temperature sequence, +.>Indicating the variance of the return water end temperature in the return water end temperature sequence,/->Representing the temperature of the backwater end corresponding to the t-th moment in the backwater end temperature sequence,/for>The temperature of the backwater end corresponding to the T-1 time in the backwater end temperature sequence is represented, T represents the total number of times contained in the backwater end temperature sequence, and mean () represents a function for averaging.
Preferably, the constructing the classification model according to the feature parameter vector corresponding to each set time period specifically includes:
Obtaining the correlation distance between the set time periods according to the cosine similarity between the feature parameter vectors corresponding to any two set time periods, and classifying the set time periods according to the correlation distance to obtain at least two wear degree class grades; and inputting the characteristic parameter vector corresponding to the classified set time period as a data set into a classification model, outputting the characteristic parameter vector as a wear degree class grade corresponding to the set time period, and training the classification model to obtain a trained classification model.
Preferably, after obtaining the wear level corresponding to the bearing for the current time period, the method further comprises:
after the bearing is put into use for a fixed time period, acquiring a bearing vibration acceleration sequence corresponding to a set time period and marking the bearing vibration acceleration sequence as a reference sequence, acquiring a bearing vibration acceleration sequence corresponding to a current time period, and acquiring a life index according to the similarity between the bearing vibration acceleration sequence corresponding to the current time period and the reference sequence; setting a service life threshold, and stopping the running work of the bearing when the service life index is larger than the service life threshold.
Preferably, the lifetime threshold is set to 0.8.
Preferably, the classification model is an SVM support vector machine.
Preferably, the classifying the set time period according to the related distance includes: and classifying different set time periods by adopting a K-medoids clustering algorithm.
The embodiment of the invention has at least the following beneficial effects:
according to the invention, by acquiring the vibration acceleration sequence of the bearing, the working power sequence of the water pump and the temperature sequence of the backwater end of the cooling tower, the vibration acceleration information of the bearing is considered, and the influence of bearing abrasion on the environment where the bearing is positioned is also considered; according to the sequences corresponding to the three characteristic factors, vibration acceleration change degree indexes, working power change degree indexes and temperature change degree indexes are calculated respectively, the abrasion degree of the bearing is analyzed from three different aspects, the consideration factors are more comprehensive, the characteristic parameter vector is obtained according to the three characteristic factors, and then an accurate analysis result of the abrasion degree of the bearing can be obtained. Meanwhile, a classification model is built by acquiring a fixed amount of data, and then the current characteristic parameter vector can be acquired in real time, so that the real-time monitoring of the abrasion condition of the bearing is realized.
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 method flow diagram of a method of the present invention for monitoring bearing wear of a cooling tower water pump.
Detailed Description
In order to further describe the technical means and effects adopted by the present invention to achieve the preset purposes, the following detailed description refers to specific embodiments, structures, features and effects of a method for monitoring bearing wear of a water pump of a cooling tower according to the present 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 a method for monitoring bearing wear of a water pump of a cooling tower, which is provided by the invention, with reference to the accompanying drawings.
Examples:
the specific scene aimed by the invention is as follows: under the condition that the environmental factors of the cooling tower are kept unchanged, the parameters of the large water pump for heat exchange of the cooling tower and the parameters of the rolling bearing of the water pump are collected, and then the collected data are processed to obtain the bearing abrasion condition of the large water pump for heat exchange of the cooling tower.
Referring to fig. 1, a method for monitoring wear of a water pump bearing of a cooling tower according to an embodiment of the present invention is shown, the method includes the following steps:
step one, a fixed number of set time periods are obtained, vibration acceleration of a bearing is obtained at different moments in the set time periods, and the working power of a water pump and the temperature of a water return end of a cooling tower respectively form a bearing vibration acceleration sequence, a water pump working power sequence and a water return end temperature sequence.
First, vibration is generated when the rolling bearing is operated, and vibration can be classified into three types, i.e., natural vibration, impact vibration, and stress vibration, according to the principle of vibration generation, and in this embodiment, impact vibration generated by the rolling bearing is taken as an example. In general, vibration is associated with the operation of the bearing, and when the bearing is damaged, the vibration speed is changed with the operation of the bearing, that is, the damaged bearing is different from the vibration speed generated by the bearing in normal operation.
The vibration acceleration of the bearing refers to the change degree of the vibration speed of the bearing in unit time, the vibration acceleration of the bearing is an important index for measuring the manufacturing level of the bearing, the running quality of the bearing is comprehensively reflected, and meanwhile, the vibration acceleration of the bearing is more visual vibration detection quantity than the vibration amplitude and the vibration speed. In this embodiment, the wear condition of the bearing is analyzed by acquiring vibration information of the bearing in the large water pump in which the cooling tower exchanges heat.
Specifically, a fixed number of set time periods are acquired according to fixed time intervals, the time lengths of the set time periods are equal, and vibration accelerations of the bearing at different moments are acquired in the set time periods to form a bearing vibration acceleration sequence. Each set time period corresponds to a bearing vibration acceleration sequence.
In this embodiment, the vibration acceleration sensor is used to collect the vibration acceleration of the bearing, the fixed number of values is set to 100, the fixed time interval is set to 1 day, the time length of the set time period is set to 10 minutes, and the practitioner can set according to the actual situation. The vibration acceleration of the bearing is collected at different moments within 10 minutes every one day, the vibration acceleration of the bearing collected at different moments within 10 minutes forms a bearing vibration acceleration sequence, and 100 bearing vibration acceleration sequences are obtained in total.
Then, when the bearing of the water pump is worn, a larger friction force is generated between the shaft and the bearing, so that the load of the water pump is increased, and when the load is increased, the working power of the water pump motor needs to be increased to ensure the normal working of the water pump. Based on this, when there is a damage condition of the bearing of the water pump, the operation power of the water pump may be changed.
Meanwhile, it should be noted that, because the working power of the water pump may be too large due to factors such as the too large size of the impeller of the water pump or improper axial sealing installation of the water pump, in this embodiment, it is necessary to ensure that the impeller of the water pump is properly sized and the sealing installation of the water pump bearing is correct. Meanwhile, other factors in the working environment of the water pump are kept unchanged. The change of the working power of the water pump is caused by objective factors, and the water pump has no other faults, so that the change of the working power of the water pump can be caused by damage to the bearing of the water pump.
Based on the method, a fixed number of set time periods are acquired according to fixed time intervals, the time lengths of the set time periods are equal, and the working powers of the water pumps at different moments are acquired in the set time periods to form a water pump working power sequence. Each set time period corresponds to a water pump working power sequence.
In the embodiment, a power meter is used for collecting the power of the motor when the water pump works and recording the power as the working power of the water pump. Meanwhile, the fixed number of values is set to 100, the fixed time interval is set to 1 day, the time length of the set time period is set to 10 minutes, and the implementer can set according to actual conditions. The working power of the water pump is collected at different moments within 10 minutes every one day, the working power of the water pump collected at different moments within 10 minutes forms a water pump working power sequence, and 100 bearing water pump working power sequences are obtained in total.
Finally, when the bearing is worn, the impeller of the water pump is unstable in rotation, and the blades of the impeller of the water pump transmit mechanical energy to the liquid, so that the pressure of the liquid is increased, and the purpose of conveying the liquid is achieved. At this time, if the bearing of the large water pump for heat exchange of the cooling tower is damaged, the pressure of the water supplied from the blades of the water pump to the liquid becomes unstable, and the flow rate of the water changes. The change of the flow of the water can lead to the cooling effect of the cooling tower on the filler, namely, when the flow of the water is large, the cooling effect is good, the temperature of the backwater end of the cooling tower is low, when the flow of the water is small, the cooling effect is poor, and at the moment, the temperature of the backwater end of the final cooling tower is high because only a small amount of water passes through.
Meanwhile, it should be noted that too much water circulation of the cooling tower or too high water temperature may affect the temperature of the water return end of the cooling tower, so that the temperature of the water return end changes, and therefore, in this embodiment, the water circulation is fixed and suitable, and the outdoor humidity temperature is fixed. At the same time, other factors in the operating environment of the cooling tower remain unchanged. The temperature change of the backwater end of the cooling tower is caused by objective factors, and the cooling tower does not have other faults, so that the temperature change of the backwater end of the cooling tower is likely to be caused by damage to the bearing of the large water pump for heat exchange of the cooling tower.
Based on the method, a fixed number of set time periods are acquired according to fixed time intervals, the time lengths of the set time periods are equal, and temperatures of the water return ends of the cooling towers at different moments are acquired in the set time periods to form a water return end temperature sequence. Each set time period corresponds to a backwater end temperature sequence.
In this embodiment, adopt temperature sensor to gather the temperature of return water end when the cooling tower cools off, place temperature sensor in the return water end of bottom just can gather temperature information in the tower. Meanwhile, the fixed number of values is set to 100, the fixed time interval is set to 1 day, the time length of the set time period is set to 10 minutes, and the implementer can set according to actual conditions. The temperature of the water return end of the cooling tower is collected at different moments within 10 minutes every day, the temperature of the water return end of the cooling tower collected at different moments within 10 minutes forms a water return end temperature sequence, and 100 water return end temperature sequences are obtained in total.
Step two, calculating a vibration acceleration change degree index based on each vibration acceleration and the extreme difference of the vibration acceleration in the bearing vibration acceleration sequence; obtaining a working power change degree index according to the maximum value, the minimum value and the average value of the working power in the water pump working power sequence; and calculating a temperature change degree index based on the difference of temperatures of all the backwater ends in the backwater end temperature sequence.
First, when there is damage to the bearing, the vibration acceleration of the bearing changes from that of a normal bearing. And performing straight line fitting according to each moment in the bearing vibration acceleration sequence corresponding to any set time period and the vibration acceleration corresponding to the moment, wherein the abscissa of the point on the straight line obtained by fitting is the moment, and the ordinate is the vibration acceleration corresponding to the moment. The fitted straight line represents the linear change of the vibration acceleration corresponding to most of the time. In this embodiment, a regression equation corresponding to the bearing vibration acceleration sequence is fitted, so as to obtain the slope of the fitted straight line, and the practitioner may select a method for fitting the straight line according to the actual situation, which is a known technique and will not be described herein too much.
When the bearing is not damaged in a set time period, the vibration acceleration of the bearing cannot change in the set time period or the change degree is small, the fitted straight line is approximate to a horizontal straight line, and the slope of the straight line is small or is close to 0. When the bearing is damaged in a set time period, the vibration acceleration of the bearing can change in the set time period, and the fitted straight line has a certain inclination angle, so that the slope of the straight line is larger.
Further, by comparing the differences between the vibration acceleration corresponding to each moment in the vibration acceleration sequence of the bearing and the vibration acceleration corresponding to the same moment on the straight line obtained by fitting, the differences represent the differences between the true values and the fitting values of the vibration acceleration corresponding to each moment, and the larger the differences are, the fact that certain deviation exists in the data corresponding to the moment is indicated, so that the bearing may be damaged at the moment.
Meanwhile, considering the situation that the bearing is damaged in most of time in a set time period, namely, the situation that the vibration acceleration corresponding to most of time in the set time period is an abnormal value, the change situation of the vibration acceleration in the set time period is reflected by acquiring the difference between the maximum value and the minimum value of the vibration acceleration of the bearing, if the bearing is damaged in the set time period, the difference between the maximum value and the minimum value is large, and if the bearing is not damaged, the difference between the maximum value and the minimum value is small, or the difference between the maximum value and the minimum value is almost not generated.
Based on this, the vibration acceleration variation degree index is calculated based on the differences between the vibration accelerations in the bearing vibration acceleration sequence and the range of all the vibration accelerations, and expressed as:
Wherein,indicating the vibration acceleration change degree index corresponding to the nth set time period,/for>Indicating the vibration acceleration corresponding to the nth set time periodFitting the slope of the resulting line, +.>Representing the vibration acceleration corresponding to the t-th moment in the vibration acceleration sequence of the bearing,/for>The vibration acceleration corresponding to the t-th moment on the straight line obtained by fitting is shown,the extreme difference of all vibration accelerations in the bearing vibration acceleration sequence, that is, the difference between the maximum value and the minimum value of the vibration acceleration, T represents the total number of times included in the set period, exp () represents an exponential function based on the natural constant e.
The larger the value of the vibration acceleration change degree index is, the larger the inclination angle of the straight line obtained by fitting is, the unstable the value of the vibration acceleration in the sequence is, the larger the value of the vibration acceleration change degree index is, the more damage to the bearing is likely to exist,the smaller the value of the vibration acceleration change degree index is, the closer the inclination angle of the straight line obtained by fitting is to the horizontal, the more stable the vibration acceleration in the sequence is, and the smaller the value of the vibration acceleration change degree index is, the less damage to the bearing is possible. The slope of the fitting straight line is increased by 1 to prevent the change degree index of the vibration acceleration from being affected when the slope is 0.
The larger the value of (a) is, the larger the difference between the true value and the fitting value of the vibration acceleration is, the larger the deviation between the value of the vibration acceleration at the moment and other moments in the set time period is, the larger the value of the vibration acceleration change degree index is, the more likely the bearing isIn case of injury, the patient is at risk of being injured>The smaller the value of the vibration acceleration is, the smaller the difference between the true value and the fitting value of the vibration acceleration is, the larger the deviation between the value of the vibration acceleration at the moment and other moments in the set time period is not generated, and the smaller the value of the vibration acceleration change degree index is, the less damage to the bearing is possible.
The larger the value is, the larger the fluctuation of the vibration acceleration in the vibration acceleration sequence of the bearing is, the larger the value of the vibration acceleration change degree index is, the more likely damage is caused to the bearing, and the more damage is caused to the bearing>The smaller the value is, the smaller the fluctuation of the vibration acceleration in the vibration acceleration sequence of the bearing is, the larger the value of the vibration acceleration change degree index is, and the less damage to the bearing is possible.
Then, if there is damage to the bearings of the water pump, the operating power of the water pump may be changed. For any set time period, the value of the working power in the water pump working power sequence corresponding to the set time period may have fluctuation, so that the difference between the maximum value and the minimum value of the working power of the water pump in the sequence is larger. The average value of all the working powers in the water pump working power sequence can represent the balanced condition of the numerical values of the elements in the sequence, so that the difference between the corresponding working powers and the average value at each moment is larger.
If the bearing of the water pump is not damaged, the working power of the water pump is not changed greatly or is hardly changed, the numerical value of the working power in the water pump working power sequence is not greatly or hardly fluctuated, the difference between the maximum value and the minimum value of the working power of the water pump in the sequence is small, and the difference between the corresponding working power and the average value at each moment is small.
Based on the difference value between the maximum value and the minimum value of the working power in the water pump working power sequence corresponding to any set time period is calculated, the difference value between the working power of the water pump corresponding to each moment and the average value of the working power corresponding to all moments is calculated, and the working power change degree index is obtained according to the difference value between the maximum value and the minimum value and the difference value between the average values, and is expressed as follows by a formula:
wherein,indicating the degree of change of the operating power corresponding to the nth set time period, < >>Representing the extreme difference of the working power in the working power sequence of the water pump corresponding to the set time period, namely the difference value of the maximum value and the minimum value of the working power, < >>Indicating the working power corresponding to the t-th moment in the working power sequence of the water pump, < > >The average value of all the operating powers in the water pump operating power sequence is represented, T represents the total number of times included in the set period, ln () represents a logarithmic function based on a natural constant e, exp () represents an exponential function based on a natural constant e.
The larger the value of the working power in the working power sequence of the water pump is, the larger the value of the working power change degree index corresponding to the set time period is, the more the value of the working power change degree index is, the change of the working power of the water pump is caused by objective factors, the water pump does not have other faults, the change of the working power of the water pump is possibly caused by damage to the bearing of the water pump, and thereforeThe more likely damage to the bearings of the water pump is present during the set period of time.
The larger the value of the (b) is, the larger the change of the working power of the water pump at the t moment is compared with the balance condition of all other moments, the more the value of the change degree of the working power is, and the more the bearing of the water pump is likely to be damaged in the set time period.
Because the bearing of the water pump is damaged, tangential swing can occur to the shaft when the bearing rotates, the friction force of the bearing can be high and low, the working power of the water pump can be fluctuated accordingly, the minimum value of the working power of the water pump is relatively similar or almost equal to the normal condition in the running process of the bearing of the water pump, and the maximum value of the working power of the water pump can be increased along with the increase of the loss degree of the bearing of the water pump. Therefore, the greater the value of the change degree of the working power is, the more serious the damage degree of the bearing of the water pump is. Under the condition that the bearing of the water pump is normal, the working power of the water pump is almost maintained in a relatively stable state, so that the smaller the value of the working power change degree index is, the lighter the damage degree of the bearing of the water pump is or the damage is hardly caused.
And finally, acquiring the median value of the temperatures of the backwater ends in the backwater end temperature sequence corresponding to any set time period, and counting the number of times when the temperatures of the backwater ends in the backwater end temperature sequence are greater than the median value. If the bearing of the water pump for heat exchange of the cooling tower is damaged, the temperature of the water return end of the cooling tower can change, namely the cooling effect of the cooling tower is poor, and the temperature of the water return end of the cooling tower is high. Based on this, the more the bearing is damaged, the greater the number of times the return water end temperature is greater than the median.
And then calculate the difference of return water end temperature that the adjacent moment corresponds in the return water end temperature sequence, if the bearing of the water pump that the cooling tower carries out the heat exchange has the damage, then the temperature of the return water end of cold and hot tower can change, and then there is the difference between the return water end temperature that the moment that the damage corresponds and the return water end temperature of adjacent moment great. If the bearing of the water pump for heat exchange of the cooling tower is not damaged, the temperature of the water return end of the cooling tower is not changed greatly or is hardly changed, and then the difference between the temperature of the water return end corresponding to the damaged moment and the temperature of the water return end at the adjacent moment is small or is hardly different.
Based on the method, the variance of the backwater end temperature in the backwater end temperature sequence corresponding to any set time period is calculated, the median value of the backwater end temperature in the backwater end temperature sequence is obtained, the number of times that the backwater end temperature in the backwater end temperature sequence is larger than the median value is counted, the average value of the differences of the backwater end temperatures corresponding to all two adjacent times is calculated, and the temperature change degree index is obtained according to the variance, the number and the average value and is expressed as follows by a formula:
wherein,index indicating the degree of temperature change corresponding to the nth set period of time,/->Indicating the number of times corresponding to the time when the temperature of the backwater end is greater than the median value in the backwater end temperature sequence, +.>Indicating the variance of the return water end temperature in the return water end temperature sequence,/->Representing the temperature of the backwater end corresponding to the t-th moment in the backwater end temperature sequence,/for>The temperature of the backwater end corresponding to the T-1 time in the backwater end temperature sequence is represented, T represents the total number of times contained in the backwater end temperature sequence, and mean () represents a function for averaging.
The larger the value of the water return end temperature sequence, the more the time when the temperature is higher exists in the water return end temperature sequence, and the temperature change of the water return end of the cooling tower is caused by objective factors, but the cooling tower does not have other faults, so that the temperature change of the water return end of the cooling tower is likely to be caused by damage to the bearing of the large water pump for heat exchange of the cooling tower. Therefore, the greater the temperature change degree index, the more likely the damage is to the bearing of the large water pump for heat exchange in the cooling tower. / >The smaller the value of the water return end temperature sequence, the closer the value of each water return end temperature in the water return end temperature sequence is, the smaller the temperature change degree index is, and the less damage is likely to exist on the bearing of the large water pump for heat exchange of the cooling tower.
The fluctuation condition of the temperature of the backwater end in the sequence can be reflected, the variance is taken as an index, and the difference caused by abnormal time of the temperature of the backwater end can be amplified, so that the time with damage can be more directly distinguished. The larger the value of the variance is, the larger the fluctuation of the temperature of the backwater end in the sequence is, and the larger the temperature of the backwater end is possibly changed at different moments, the larger the value of the index of the degree of temperature change is, and the more the damage to the bearing of the large water pump for heat exchange of the cooling tower is likely. The smaller the value of the variance, the closer the value of each backwater end temperature in the backwater end temperature sequence is, the smaller the temperature change degree index is, and the less likely damage exists on the bearing of the large water pump for heat exchange of the cooling tower.
Representing the difference value between the return water end temperature corresponding to the t time and the return water end temperature corresponding to the t-1 time in the return water end temperature sequence, further calculating the average value of all the difference values, wherein the average value isThe larger the temperature of the water return end is, the larger the overall change degree of the temperature of the water return end is in the set time period, the larger the value of the temperature change degree index is, the more serious the loss condition of the bearing is, the larger the water flow is, and the temperature of the water return end is changed along with the water flow in the running process of the bearing.
In this embodiment, the vibration acceleration of the bearing is analyzed, and the influence of the damage of the bearing on the environment where the bearing is located is considered, so that the damage condition of the bearing can be determined under the condition that other factors remain unchanged and no fault exists. By combining a plurality of characteristic information to analyze the loss degree of the bearing, the method has higher accuracy and higher reliability compared with the method for analyzing by using single characteristic information, and greatly reduces errors of data acquisition and errors of final results caused by extreme conditions.
Thirdly, forming a characteristic parameter vector corresponding to the set time period by using the vibration acceleration change degree index, the working power change degree index and the temperature change degree index corresponding to the set time period; and constructing a classification model according to the characteristic parameter vectors corresponding to the set time periods, acquiring the characteristic parameter vector corresponding to the current time period, and acquiring the wear grade corresponding to the bearing of the current time period by using the classification model.
Firstly, it should be noted that during operation of the bearing, the wear state does not occur suddenly, but rather exhibits a slower trend. By collecting the working data of the bearing for a certain time period and analyzing different time periods, the wear degree of the bearing corresponding to different set time periods can be obtained.
Specifically, the vibration acceleration change degree index, the working power change degree index and the temperature change degree index corresponding to the set time period form a characteristic parameter vector corresponding to the set time period, and the characteristic parameter vector is recorded asWherein->Indicating that the nth set time period corresponds toCharacteristic parameter vector,/, of (2)>Indicating the vibration acceleration change degree index corresponding to the nth set time period,/for>Indicating the degree of change of the operating power corresponding to the nth set time period, < >>A temperature change degree index corresponding to the nth set time period is represented; and constructing a classification model according to the characteristic parameter vectors corresponding to the set time periods.
In this embodiment, an SVM support vector machine is adopted to evaluate and analyze the wear degree of the bearing, the SVM support vector machine is trained by using the characteristic parameter vectors corresponding to the fixed number of set time periods, and the trained SVM support vector machine is recorded as a classification model. The classification model is used for classifying each set time period according to the characteristic parameter vector, and the classification model is various, and an implementer can select according to actual conditions.
The characteristic parameter vector corresponding to the set time period is input into a trained classification model, namely an SVM support vector machine, and the abrasion degree type corresponding to the set time period of the bearing is output. The SVM support vector machine is a generalized linear classification model for binary classification of data in a supervised learning mode. The decision boundary is the maximum margin hyperplane for solving the learning sample. The vector input by the classification model needs to be marked to the category to which the vector belongs, and the marked result can influence the accuracy of the output of the classification model, so that the data set of the classification model needs to be classified before the SVM support vector machine is trained.
Then, the relevant distance between the set time periods is obtained according to the cosine similarity between the characteristic parameter vectors corresponding to any two set time periods and is recorded asD represents a phaseAnd the off distance, R, represents cosine similarity between the feature parameter vectors corresponding to the two set time periods. The larger the cosine similarity value is, the more similar the data corresponding to the two set time periods are, and the smaller the correlation distance between the two set time periods is.
And classifying the set time period according to the related distance to obtain at least two wear degree class grades. In this embodiment, according to the specific scenario in which the bearing is located and the requirements on the device, the wear degrees of the bearing are set to 4 class levels, and are recorded as a first wear degree class level, a second wear degree class level, a third wear degree class level and a fourth wear degree class level. The first wear level class level indicates that the wear level of the bearing is minimum or almost not worn, the second wear level class level indicates that the wear level of the bearing is first-level wear, that is, the bearing is slightly damaged, the third wear level class level indicates that the wear level of the bearing is second-level wear, that is, the bearing is severely damaged, and the fourth wear level class level indicates that the wear level of the bearing is third-level wear, that is, the bearing is most severely lost, and the possibility of faults possibly exists at any time.
In this embodiment, the K-means clustering algorithm is used to classify different set time periods, and the classification method is various, and the practitioner can select according to the actual situation.
In this embodiment, 90 marked set time periods are selected as training sets, 10 marked set time periods are selected as test sets, and characteristic parameter vectors corresponding to the marked set time periods are input into a classification model as data sets and output as wear degree class levels corresponding to the set time periods. The number of the set time periods contained in the training set data set can be set by the implementers according to actual situations.
Training the classification model by using the training set, testing the trained classification model by using the testing set to obtain the classification effect, and judging whether the classification is correct or not and whether the accuracy meets the use requirement or not. If the accuracy is lower, the parameters of the classifier are continuously modified until the accuracy meets the use requirement. And further obtaining a trained classification model. Wherein, standard practitioners for testing the classification model need to be set according to requirements. The SVM support vector machine has the advantages that the linear or nonlinear classification can be performed by using a hyperplane and a kernel function mode, and the result is accurate.
Finally, the time period with the same time length as the set time period is obtained from the current moment and is recorded as the current time period, the characteristic parameter vector corresponding to the current time period is obtained according to the method, the characteristic parameter vector is input into a trained classification model, and the class grade of the abrasion degree corresponding to the current time period of the bearing of the large water pump for heat exchange of the cooling tower is output. The function of obtaining the current time period is to analyze the wear condition of the bearing in the current period, and the embodiment of the method for obtaining the current time period can also select according to the actual condition, which only needs to ensure that the time length of the current time period is equal to the time length of the set time period.
When the class level of the wear degree corresponding to the current time period is the first class level of the wear degree or the second class level of the wear degree, the wear degree of the bearing is slight or almost no wear exists, the bearing can normally operate, and the residual life of the bearing can be not required to be predicted. And when the class grade of the wear degree corresponding to the current time period of the bearing is the class grade of the third wear degree or the class grade of the fourth wear degree, the wear degree of the bearing is larger, and the normal operation of the bearing can be possibly influenced, so that the residual service life of the bearing needs to be predicted, and related staff can reasonably arrange the maintenance time of the bearing.
When the class level of the wear degree corresponding to the current time period is the class level of the third wear degree or the class level of the fourth wear degree, the related staff is required to be prompted to repair the bearing, if the related staff does not repair the bearing in time, the bearing continues to work in a certain period, and larger loss can be caused to the specific environment where the bearing is located, so that the residual service life of the bearing is required to be analyzed.
The vibration acceleration of the bearing is an important index for measuring the manufacturing level of the bearing, comprehensively reflects the running quality of the bearing, measures the quality of the bearing through the vibration acceleration value, and can simply reflect the fatigue life of the bearing. Based on the above, when the class level of the wear degree corresponding to the current time period is the third class level of the wear degree or the fourth class level of the wear degree, after the bearing is put into use for a fixed time period, the vibration acceleration sequence of the bearing corresponding to a set time period is acquired and recorded as a reference sequence. The time length of the fixed time period can be set by an operator according to actual conditions, and only the data related to the bearing in the initial stage of bearing use is ensured to be acquired as far as possible. The function of the reference sequence is to analyze the wear degree of the current bearing by taking the initial state corresponding to the initial stage of the bearing in use as a standard.
Obtaining a life index according to the similarity between the bearing vibration acceleration sequence corresponding to the current time period and the reference sequence, and expressing the life index as follows by a formula:
wherein M represents a life index corresponding to the current time period of the bearing, Z represents a vibration acceleration sequence of the bearing corresponding to the current time period,the reference sequence is represented, exp () represents an exponential function based on a natural constant e, and DTW () represents a function for obtaining a DTW distance. In the present embodiment, the similarity between the bearing vibration acceleration sequence corresponding to the current period and the reference sequence is obtained by calculating the DTW distance of the two.
The larger the value of (a) is, the description is between two sequencesThe larger the difference of the bearing is, the more serious the abrasion condition of the bearing exists in the current time period compared with the initial state, the larger the value of the life index of the bearing in the current time period is, and the closer the bearing is to the end stage in the current time period is. And setting a service life threshold value, and when the service life index is larger than the service life threshold value, forcibly stopping the running work of the bearing. In this embodiment, the lifetime threshold has a value of 0.8, and the practitioner can set the lifetime threshold according to the actual situation.
The above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the application and are intended to be included within the scope of the application.
Claims (7)
1. A method for monitoring wear of a cooling tower water pump bearing, the method comprising the steps of:
acquiring a fixed number of set time periods, and acquiring vibration acceleration of a bearing, working power of a water pump and temperature of a water return end of a cooling tower at different moments in the set time periods to respectively form a bearing vibration acceleration sequence, a water pump working power sequence and a water return end temperature sequence;
calculating a vibration acceleration change degree index based on each vibration acceleration and the range of the vibration acceleration in the bearing vibration acceleration sequence; obtaining a working power change degree index according to the maximum value, the minimum value and the average value of the working power in the water pump working power sequence; calculating a temperature change degree index based on the difference of temperatures of all backwater ends in the backwater end temperature sequence;
calculating a vibration acceleration change degree index based on the difference between each vibration acceleration and the range of all vibration accelerations in the bearing vibration acceleration sequence, and expressing the vibration acceleration change degree index as follows by a formula:
wherein,indicating the vibration acceleration change degree index corresponding to the nth set time period,/for>Indicating the slope of the straight line obtained by fitting the vibration acceleration corresponding to the nth set period of time, ++ >Representing the vibration acceleration corresponding to the t-th moment in the vibration acceleration sequence of the bearing,/for>Representing the vibration acceleration corresponding to the t-th moment on the straight line obtained by fitting, < >>Representing the extreme differences of all vibration accelerations in the bearing vibration acceleration sequence, namely the difference between the maximum value and the minimum value of the vibration acceleration, T representing the total number of moments contained in a set time period, exp () representing an exponential function based on a natural constant e;
the method for acquiring the working power change degree index specifically comprises the following steps:
wherein,indicating the degree of change of the operating power corresponding to the nth set time period, < >>Representing the extreme difference of the working power in the water pump working power sequence corresponding to the set time period>Indicating the working power corresponding to the t-th moment in the working power sequence of the water pump, < >>Representing the average value of all the working powers in the water pump working power sequence, T representing the total number of moments contained in a set time period, ln () representing a logarithmic function based on a natural constant e, exp () representing an exponential function based on the natural constant e;
the method for acquiring the temperature change degree index comprises the following steps:
calculating the variance of the backwater end temperature in the backwater end temperature sequence corresponding to any set time period, obtaining the median value of the backwater end temperature in the backwater end temperature sequence, counting the number of moments corresponding to the backwater end temperature greater than the median value in the backwater end temperature sequence, calculating the average value of the differences of the backwater end temperatures corresponding to all adjacent two moments, obtaining a temperature change degree index according to the variance, the number and the average value, and expressing the temperature change degree index as follows by a formula:
Wherein,index indicating the degree of temperature change corresponding to the nth set period of time,/->Indicating the number of times corresponding to the time when the temperature of the backwater end is greater than the median value in the backwater end temperature sequence, +.>Representing the variance of the temperature of the backwater end in the backwater end temperature sequence,representing the temperature of the backwater end corresponding to the t-th moment in the backwater end temperature sequence,/for>Representing the temperature of the backwater end corresponding to the T-1 time in the backwater end temperature sequence, wherein T represents the total number of times contained in the backwater end temperature sequence, and mean () represents a function for solving the average;
forming a characteristic parameter vector corresponding to the set time period by using the vibration acceleration change degree index, the working power change degree index and the temperature change degree index corresponding to the set time period; and constructing a classification model according to the characteristic parameter vectors corresponding to the set time periods, acquiring the characteristic parameter vector corresponding to the current time period, and acquiring the wear grade corresponding to the bearing of the current time period by using the classification model.
2. The method for monitoring bearing wear of a cooling tower water pump according to claim 1, wherein the acquiring a fixed number of set time periods is specifically: and acquiring a fixed number of set time periods according to the fixed time interval, wherein the time lengths of the set time periods are equal.
3. The method for monitoring bearing wear of a cooling tower water pump according to claim 1, wherein the constructing a classification model according to the feature parameter vector corresponding to each set time period specifically comprises:
obtaining the correlation distance between the set time periods according to the cosine similarity between the feature parameter vectors corresponding to any two set time periods, and classifying the set time periods according to the correlation distance to obtain at least two wear degree class grades; and inputting the characteristic parameter vector corresponding to the classified set time period as a data set into a classification model, outputting the characteristic parameter vector as a wear degree class grade corresponding to the set time period, and training the classification model to obtain a trained classification model.
4. A method for monitoring wear of a cooling tower water pump bearing according to claim 1, wherein after obtaining a wear level corresponding to the bearing for a current time period, the method further comprises:
after the bearing is put into use for a fixed time period, acquiring a bearing vibration acceleration sequence corresponding to a set time period and marking the bearing vibration acceleration sequence as a reference sequence, acquiring a bearing vibration acceleration sequence corresponding to a current time period, and acquiring a life index according to the similarity between the bearing vibration acceleration sequence corresponding to the current time period and the reference sequence; setting a service life threshold, and stopping the running work of the bearing when the service life index is larger than the service life threshold.
5. A method for monitoring bearing wear of a cooling tower water pump according to claim 4, wherein the lifetime threshold is set to 0.8.
6. The method for monitoring bearing wear of a cooling tower water pump according to claim 1, wherein the classification model is an SVM support vector machine.
7. A method for monitoring bearing wear of a cooling tower water pump according to claim 3, wherein said classifying a set period of time according to said associated distance comprises: and classifying different set time periods by adopting a K-medoids clustering algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311133444.8A CN116878886B (en) | 2023-09-05 | 2023-09-05 | Method for monitoring abrasion of water pump bearing of cooling tower |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311133444.8A CN116878886B (en) | 2023-09-05 | 2023-09-05 | Method for monitoring abrasion of water pump bearing of cooling tower |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116878886A CN116878886A (en) | 2023-10-13 |
| CN116878886B true CN116878886B (en) | 2023-12-15 |
Family
ID=88259041
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311133444.8A Active CN116878886B (en) | 2023-09-05 | 2023-09-05 | Method for monitoring abrasion of water pump bearing of cooling tower |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116878886B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117272192B (en) * | 2023-11-22 | 2024-03-08 | 青岛洛克环保科技有限公司 | Sewage treatment system of magnetic coagulation efficient sedimentation tank based on sewage detection |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004108177A (en) * | 2002-09-13 | 2004-04-08 | Toshiba Corp | Method and device for monitoring and diagnosing vertical pump |
| JP2006009581A (en) * | 2004-06-22 | 2006-01-12 | Ebara Corp | Damage detecting method and device for impeller |
| CN110647943A (en) * | 2019-09-26 | 2020-01-03 | 西北工业大学 | Cutting tool wear monitoring method based on evolutionary data cluster analysis |
| CN112343810A (en) * | 2020-11-04 | 2021-02-09 | 广州高澜节能技术股份有限公司 | Water pump health monitoring and diagnosing method for circulating water cooling system |
| CN112347641A (en) * | 2020-11-05 | 2021-02-09 | 华润电力技术研究院有限公司 | Water supply pump fault prediction and diagnosis method and system based on real-time data |
| CN113109051A (en) * | 2021-04-14 | 2021-07-13 | 中国人民解放军海军航空大学岸防兵学院 | Fault early warning method and system based on vibration data range sequence |
| CN214464967U (en) * | 2021-03-31 | 2021-10-22 | 山东微纳电子科技有限公司 | Gap monitor of axial force balancing device of multistage centrifugal pump |
| CN115062553A (en) * | 2022-08-17 | 2022-09-16 | 浪潮通用软件有限公司 | Water pump working condition degradation detection method, equipment and medium based on multi-model fusion |
| CN115238829A (en) * | 2022-09-21 | 2022-10-25 | 南通佳晟宏机械配件有限公司 | Method for analyzing wear degree of roller of hot rolling mill |
| CN115931354A (en) * | 2022-10-20 | 2023-04-07 | 国网江西省电力有限公司超高压分公司 | Valve cooling system main circulation pump bearing fault identification method based on multi-stage decision fusion |
| CN116296365A (en) * | 2023-03-21 | 2023-06-23 | 华能酒泉风电有限责任公司 | Automatic early warning method and system for abrasion of gear box of wind generating set |
-
2023
- 2023-09-05 CN CN202311133444.8A patent/CN116878886B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004108177A (en) * | 2002-09-13 | 2004-04-08 | Toshiba Corp | Method and device for monitoring and diagnosing vertical pump |
| JP2006009581A (en) * | 2004-06-22 | 2006-01-12 | Ebara Corp | Damage detecting method and device for impeller |
| CN110647943A (en) * | 2019-09-26 | 2020-01-03 | 西北工业大学 | Cutting tool wear monitoring method based on evolutionary data cluster analysis |
| CN112343810A (en) * | 2020-11-04 | 2021-02-09 | 广州高澜节能技术股份有限公司 | Water pump health monitoring and diagnosing method for circulating water cooling system |
| CN112347641A (en) * | 2020-11-05 | 2021-02-09 | 华润电力技术研究院有限公司 | Water supply pump fault prediction and diagnosis method and system based on real-time data |
| CN214464967U (en) * | 2021-03-31 | 2021-10-22 | 山东微纳电子科技有限公司 | Gap monitor of axial force balancing device of multistage centrifugal pump |
| CN113109051A (en) * | 2021-04-14 | 2021-07-13 | 中国人民解放军海军航空大学岸防兵学院 | Fault early warning method and system based on vibration data range sequence |
| CN115062553A (en) * | 2022-08-17 | 2022-09-16 | 浪潮通用软件有限公司 | Water pump working condition degradation detection method, equipment and medium based on multi-model fusion |
| CN115238829A (en) * | 2022-09-21 | 2022-10-25 | 南通佳晟宏机械配件有限公司 | Method for analyzing wear degree of roller of hot rolling mill |
| CN115931354A (en) * | 2022-10-20 | 2023-04-07 | 国网江西省电力有限公司超高压分公司 | Valve cooling system main circulation pump bearing fault identification method based on multi-stage decision fusion |
| CN116296365A (en) * | 2023-03-21 | 2023-06-23 | 华能酒泉风电有限责任公司 | Automatic early warning method and system for abrasion of gear box of wind generating set |
Non-Patent Citations (1)
| Title |
|---|
| 基于支持向量自回归的水泵运行状态预测研究;吴兴伟;《沈阳工程学院学报( 自然科学版)》;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116878886A (en) | 2023-10-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yang et al. | Real-time condition monitoring and fault detection of components based on machine-learning reconstruction model | |
| Leahy et al. | Diagnosing and predictingwind turbine faults from scada data using support vector machines | |
| Zeng et al. | Gearbox oil temperature anomaly detection for wind turbine based on sparse Bayesian probability estimation | |
| CN116878886B (en) | Method for monitoring abrasion of water pump bearing of cooling tower | |
| CN112067335A (en) | Power plant blower fault early warning method based on multivariate state estimation | |
| Zhu et al. | Anomaly detection and condition monitoring of wind turbine gearbox based on LSTM-FS and transfer learning | |
| CN110398384A (en) | The machine health monitoring of rotating machinery | |
| US20200263669A1 (en) | Operating state evaluation method and operating state evaluation device | |
| CN112329357B (en) | Simple diagnosis method and system for vibration fault of clean water centrifugal pump | |
| US11852294B2 (en) | Diagnosis system of lubricating oil and diagnosis method of lubricating oil | |
| CN115238829B (en) | Method for analyzing wear degree of roller of hot rolling mill | |
| CN112418306A (en) | Gas turbine compressor fault early warning method based on LSTM-SVM | |
| CN116771610A (en) | Method for adjusting fault evaluation value of variable pitch system of wind turbine | |
| Zhu et al. | Operational state assessment of wind turbine gearbox based on long short-term memory networks and fuzzy synthesis | |
| CN108416386A (en) | A kind of method and system judged extremely for Hydropower Unit bearing temperature | |
| CN114004059B (en) | Health portrait method for hydroelectric generating set | |
| CN115018178A (en) | Power station fan fault early warning method based on deep learning | |
| Bianchini et al. | Maintenance scheduling optimization for industrial centrifugal pumps | |
| Insuasty et al. | Scada data-driven wind turbine main bearing fault prognosis based on one-class support vector machines | |
| CN111192163B (en) | Generator reliability medium-short term prediction method based on wind turbine generator operating data | |
| JP7288794B2 (en) | Operating state evaluation method and operating state evaluation device | |
| CN116557230A (en) | Wind power plant unit power abnormality online assessment method and system | |
| CN112576454A (en) | Wind turbine generator main shaft temperature early warning method and device based on multi-dimensional early warning strategy | |
| CN112326246A (en) | Bearing safety state online monitoring method based on periodic data and nuclear density estimation | |
| CN115326393A (en) | Wind turbine generator bearing pair fault diagnosis method based on temperature information |
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 |