JP6997051B2 - Rolling bearing condition monitoring method and condition monitoring device - Google Patents

Description

The present invention relates to a method for monitoring the condition of rolling bearings and a condition monitoring device.

Conventionally, a method for monitoring the condition of rolling bearings has been known. For example, Japanese Patent Application Laid-Open No. 2004-347401 (Patent Document 1) uses a background noise component that does not have a peak such as a rotation speed proportional component in the frequency spectrum, so that the rolling bearing can be efficiently and accurately configured with a simple configuration. A method for diagnosing a rolling bearing that can determine the presence or absence of an abnormality is disclosed.

Japanese Unexamined Patent Publication No. 2004-347401

Japanese Unexamined Patent Publication No. 2004-347401 (Patent Document 1) discloses a configuration in which it is determined that the grease enclosed in the rolling bearing has deteriorated when the frequency spectrum of the vibration data of the rolling bearing exceeds the threshold value. ..

In order to properly determine when to replace the grease, it is necessary to estimate the remaining life of the grease according to the degree of deterioration. However, Japanese Patent Application Laid-Open No. 2004-347401 (Patent Document 1) does not consider the estimation of the remaining life of grease according to the degree of deterioration.

The present invention has been made to solve the above problems, and an object of the present invention is to estimate the remaining life of grease enclosed in a rolling bearing.

The method for monitoring the state of a rolling bearing according to the present invention includes a step of creating a classifier by machine learning and a step of monitoring the state of the rolling bearing. The step of creating a classifier includes a step of calculating the feature amount of the first to third vibration data and a step of machine learning the feature amount of the first to third vibration data to create a classifier. The first vibration data is vibration data of a rolling bearing filled with grease having a first oil separation rate. The second vibration data is vibration data of a rolling bearing filled with grease having a second oil separation rate smaller than that of the first oil separation rate. The third vibration data is vibration data of a rolling bearing filled with normal grease. The operating time of the rolling bearing until the oil separation rate of the normal grease becomes the first oil separation rate is the first operating time. The operating time of the rolling bearing until the oil separation rate of the normal grease becomes the second oil separation rate is the second operating time, which is shorter than the first operating time. The step of monitoring the state includes a step of calculating the feature amount of the fourth vibration data, a step of calculating the first to third conformance ratios, and a step of calculating the remaining life of the grease enclosed in the rolling bearing. .. The fourth vibration data is the vibration data of the rolling bearing measured during monitoring. The first to third conformance rates are calculated by a classifier. The first to third conformance ratios are the conformance ratios between the feature amount of the fourth vibration data and the feature amount of the first to third vibration data. The remaining life of the grease sealed in the rolling bearing is calculated using the first and second operation times and the first to third conformance rates. The remaining life is the operating time of the rolling bearing until the oil separation rate of the grease enclosed in the rolling bearing becomes the first oil separation rate.

According to the rolling bearing condition monitoring method according to the present invention, the remaining life of the grease enclosed in the rolling bearing can be estimated by using the classifier created by machine learning of the feature amount of the vibration data.

It is a figure which also shows the cross-sectional view of the rolling bearing which is monitored by the condition monitoring apparatus and the condition monitoring apparatus which concerns on embodiment. It is a functional block diagram of the state monitoring apparatus of FIG. It is a flowchart which shows the outline of the estimation process of the residual life of grease performed by a control unit. It is a flowchart which shows concretely the flow of the process performed in a learning period. It is a figure which also shows (a) vibration data (acceleration data) and (b) STFT image of oil separation level 2 (oil separation rate 70%). It is a figure which also shows (a) the time chart of vibration data (acceleration data) of oil separation level 1 (oil separation rate 30%), and (b) STFT image. It is a figure which also shows (a) the time chart of the normal vibration data (acceleration data), and (b) the SFT image. It is a flowchart which shows concretely the flow of the process performed in a monitoring period. It is a time chart of the conformance rate between the RST image of the vibration data measured during monitoring and the RST image of each oil separation level. It is a figure which shows the relationship between the operation time of a rolling bearing, and the remaining life estimated by the condition monitoring apparatus which concerns on embodiment.

Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. The same or corresponding parts in the drawings are designated by the same reference numerals and the description thereof will not be repeated.

FIG. 1 is a diagram showing a cross-sectional view of a state monitoring device 1 and a rolling bearing 10 monitored by the state monitoring device 1 according to the embodiment. As shown in FIG. 1, the rolling bearing 10 includes an inner ring 12, an outer ring 14, a cage 16, and a plurality of rolling elements 18. Rolling bearings 10 include, for example, self-aligning roller bearings, tapered roller bearings, cylindrical roller bearings, ball bearings and the like. The rolling bearing 10 may be a single row bearing 10 or a double row bearing 10.

The inner ring 12 is a rotating wheel that is fitted and fixed to the main shaft 11 and that is integrated with the main shaft 11 and rotates in the direction of the arrow D. The outer ring 14 is a stationary ring arranged on the outer peripheral side of the inner ring 12.

The cage 16 is provided with a plurality of pockets for holding the plurality of rolling elements 18 at equal intervals. The cage 16 is arranged between the outer peripheral surface of the inner ring 12 and the inner peripheral surface of the outer ring 14 while holding the plurality of rolling elements 18. When the rolling element 18 rotates along the inner peripheral surface (orbital plane) of the outer ring 14 with the rotation of the inner ring 12, the cage 16 together with the plurality of rolling elements 18 includes the outer peripheral surface of the inner ring 12 and the inner peripheral surface of the outer ring 14. Rotate between.

Grease is formed inside the rolling bearing 10 to form an oil film around metal components (for example, inner ring 12, outer ring 14, cage 16, and rolling element 18) to suppress contact between metals. Grc is enclosed.

The condition monitoring device 1 measures the physical quantity of the rolling bearing 10 by a vibration sensor and monitors the state of the rolling bearing. Examples of the physical quantity of the rolling bearing 10 measured by the vibration sensor include acceleration, velocity, displacement, sound, AE (Acoustic Emission), and power.

As the operating time of the rolling bearing 10 increases, the grease Grc deteriorates and the oil separation rate of the grease Grc increases. When the oil separation rate of the grease Grc increases, it becomes difficult to form a sufficient oil film around the rolling element 18, and the metals tend to come into contact with each other inside the rolling bearing 10. When the metals are welded together due to the frictional heat generated by the contact between the metals, it becomes difficult to rotate the rolling bearing 10.

The life of the rolling bearing 10 due to deterioration of the grease Grc (lubrication life) is shorter than the life of the rolling bearing 10 due to damage (rolling fatigue) formed on the raceway surface by the plurality of rolling elements 18. In order to use the rolling bearing 10 for as long as possible, it is necessary to estimate how long the remaining lubrication life (remaining life) is and replace the grease Grc at an appropriate time.

Therefore, in the embodiment, the matching ratio between a certain feature amount and a plurality of machine-learned feature amounts is obtained by machine learning the feature amount of the vibration data of the rolling bearing filled with grease having different oil separation rates. Create a classifier that calculates each. By using the classifier, the remaining life of the grease sealed in the rolling bearing can be estimated.

FIG. 2 is a functional block diagram of the condition monitoring device 1 of FIG. As shown in FIG. 2, the condition monitoring device 1 includes a vibration sensor 20, a control unit 40, and a storage unit 50. The vibration sensor 20 measures the vibration data of the rolling bearing 10 and outputs it to the control unit 40.

During the learning period, the control unit 40 machine-learns the feature amount of the vibration data of the rolling bearing 10 filled with grease having different oil separation ratios, and creates a classifier. The classifier calculates the matching rate between a certain feature amount and each machine-learned feature amount. Classifiers include, for example, support vector machines, neural networks, naive Bayes, and decision trees. In the embodiment, a neural network is used as a classifier. The control unit 40 calculates the feature amount of the vibration data measured at the sampling time in the monitoring period, and calculates the remaining life of the grease Grc using the classifier created in the learning period. The control unit 40 includes a computer such as a CPU (Central Processing Unit).

The storage unit 50 stores, for example, vibration data, a feature amount calculated from the vibration data, and a classifier created by machine learning.

FIG. 3 is a flowchart showing an outline of the grease remaining life estimation process performed by the control unit 40. In the following, the step is simply referred to as S. As shown in FIG. 3, the control unit 40 creates a classifier in S1. S1 is a process performed during the learning period. The control unit 40 calculates the remaining life of the grease using a classifier in S2. S2 is a process performed during the monitoring period. The classifier created by machine learning may be created at the beginning of the monitoring period, and the learning period and the monitoring period do not have to be continuous.

FIG. 4 is a flowchart specifically showing the flow of the process (S1 in FIG. 3) performed during the learning period. The behavior of the rolling bearing 10 is not stable for a while after the rolling bearing 10 starts operation. Therefore, in the learning period, the running-in operation period (for example, 5 days) has elapsed since the operation of the rolling bearing 10 was started, and the measurement was performed for a certain period (for example, 1 month) in a state where the behavior of the rolling bearing 10 was stable. It is desirable that vibration data be used.

As shown in FIG. 4, the control unit 40 displays a short-time Fourier transform (STFT) image of vibration data of a rolling bearing filled with grease having an oil separation rate of oil separation level 2 in S11. It is calculated as a feature amount corresponding to the oil separation level 2, and the process proceeds to S12. The oil separation rate of the oil separation level 2 is set as the oil separation rate of the grease whose lubrication life has almost expired and which needs to be replaced. The oil separation rate of the oil separation level 2 is, for example, a value of 50% or more and 80% or less, and is 70% in the embodiment.

In S12, the control unit 40 calculates the STFT image of the vibration data of the rolling bearing filled with grease whose oil separation rate is oil separation level 1 as a measure corresponding to the oil separation level 1, and processes the process to S13. Proceed. The oil separation rate of the oil separation level 1 is set as the oil separation rate of the grease, which is less necessary to be replaced because the grease has deteriorated but the lubrication life is left to some extent. The ratio of the oil separation rate of the oil separation level 1 to the oil separation rate of the oil separation level 2 is, for example, a value of 40% or more and 60% or less. In the embodiment, the oil separation rate of oil separation level 1 is 30%.

In S13, the control unit 40 calculates the STFT image of the vibration data of the rolling bearing filled with the grease of the oil separation level 0 as the feature amount corresponding to the oil separation level 0, and proceeds to the process of S14. The grease having an oil separation level of 0 is a normal grease. Normal grease is grease that has hardly deteriorated. For example, unused grease, grease with an oil separation rate of less than the standard value, or rolling bearings filled with unused grease have been put into operation. Grease within the threshold time. In the embodiment, the grease having an oil separation level of 0 is the grease within 5 hours after the start of operation of the rolling bearing filled with the unused grease.

In S14, the control unit 40 machine-learns the FTFT images of the greases having oil separation levels 0 to 2 to create a classifier, and advances the process to S15. The classifier calculates the matching ratio between a certain SFT image and the STFT image of each oil isolation level.

In S15, the control unit 40 associates the SFT image of the oil separation level 0 to 2 with the operation times L0 to L2, stores them in the storage unit 50, and ends the process. Since the grease having an oil separation level of 0 is a normal grease, the operating time L0 is set to 0 in the embodiment. The operating time L1 is the operating time of the rolling bearing until the oil separation rate of the normal grease becomes the oil separation rate of the oil separation level 1. The operating time L2 is the operating time of the rolling bearing until the oil separation rate of the normal grease reaches the oil separation rate of the oil separation level 2. The operating time L1 may be the operating time when the rolling bearing is actually operated until the oil separation rate of the unused grease reaches the oil separation rate of the oil separation level 1, or the relational expression between the operating time and the oil separation rate. The operating time obtained from may be used. The same applies to the operating time L2. In the embodiment, the operation time L1 is 1000 hours and the operation time L2 is 2000 hours.

S11 to S13 may be executed before S14, and need not be performed in the order shown in FIG. Further, S11 to S13 may be performed in parallel rather than sequentially.

FIG. 5 is a diagram showing (a) vibration data (acceleration data) and (b) RST image of oil separation level 2 (oil separation rate 70%) together. FIG. 6 is a diagram showing (a) a time chart of vibration data (acceleration data) at an oil separation level of 1 (oil separation rate of 30%) and (b) an STFT image. FIG. 7 is a diagram showing (a) a time chart of normal vibration data (acceleration data) and (b) an STFT image. The vibration data shown in FIGS. 5 to 7 is data obtained by measuring the vibration acceleration of an angular contact ball bearing 7216 manufactured by NTN Corporation operating at a rotation speed of 1500 min-1 at a sampling speed of 50 kHz. In the measurement of the vibration data shown in FIGS. 5 to 7, the radial load and the axial load are both 1.3 kN, and the temperature is 150 ° C.

In S11 of FIG. 4, FIGS. 5 (a) to 5 (b) are calculated. In S12 of FIG. 4, FIGS. 6 (a) to 6 (b) are calculated. In S13 of FIG. 4, FIGS. 7 (a) to 7 (b) are calculated. In S14 of FIG. 4, FIGS. 5 (b), 6 (b), and 7 (b) are machine-learned.

The greases of the oil separation levels 1 and 2 may be greases obtained by actually operating the rolling bearing to be monitored, or may be greases whose oil separation rate OS has been artificially adjusted. As a method of artificially adjusting the oil separation rate OS of grease, for example, a method of removing oil separated by a centrifuge from grease using the following formula (1), or heating grease in a constant temperature bath or the like is used. The method of evaporating the oil or separating the oil can be mentioned. In the formula (1), T0 is the thickener amount (%) of the unused grease, and T1 is the thickener amount (%) of the grease to be adjusted.

OS = (1-T0 / T1) x 100 ... (1)
As a method for measuring the amount of thickener, the grease whose weight has been measured is diluted with petroleum benzine, separated by a centrifuge, and the supernatant oil and petroleum benzine are removed by repeating the operation several times. A method of measuring the weight of the thickener and determining the ratio of the thickener weight to the grease weight can be mentioned.

In S11 and S12 of FIG. 4, vibration data of a rolling bearing filled with grease having an encapsulation amount G1 assuming a weight change due to oil separation at a set oil separation rate is referred to. The encapsulation amount G1 can be obtained, for example, from the following formula (2). In the formula (2), G0 is the filling amount (initial filling amount) of the grease to be filled at the start of operation of the rolling bearing. The filling amounts G0 and G1 in the formula (2) are the ratio of the volume of the sealed grease to the total volume inside the rolling bearing in which the grease is filled. In the embodiment, the initial encapsulation amount G0 is 27%.

G1 = G0 × (100-OS) / 100 ... (2)
FIG. 8 is a flowchart specifically showing the flow of the process (S2 in FIG. 3) performed during the monitoring period. The process shown in FIG. 8 is performed at each sampling time by a main routine (not shown).

As shown in FIG. 8, the control unit 40 calculates the FTFT image of the vibration data (measurement data) measured at the sampling time in S21, and advances the processing to S22. In S22, the control unit 40 calculates the matching ratios P0 to P2 between the STFT image of the measurement data and each of the three machine-learned STFT images using the classifier created during the learning period, and advances the processing to S23. .. The matching ratio P0 is the matching ratio between the RST image of the measurement data and the RST image of the oil separation level 0. The precision ratio P1 is the precision ratio between the STFT image of the measurement data and the STFT image of the oil separation level 1. The conformance rate P2 is the conformance rate between the STFT image of the measurement data and the STFT image of the oil separation level 2. The sum of the conformance rates P0 to P2 is 1.

In S23, the control unit 40 calculates the remaining life ΔL until the oil separation rate of the grease becomes the oil separation rate of the oil separation level 2 using the following equation (3), and returns the process to the main routine.

ΔL = L2- (L0 × P0 + L1 × P1 + L2 × P2)… (3)
When the remaining life ΔL is smaller than the threshold value, the control unit 40 notifies the user, for example, a message prompting the replacement of grease.

The following shows the results of an experiment in which the remaining life of grease in a rolling bearing was estimated using the condition monitoring device according to the embodiment. In this experiment, an angular contact ball bearing 7216 manufactured by NTN Corporation was operated at a rotation speed of 1500 min-1, and the vibration acceleration of the angular contact ball bearing 7216 was measured every 2 hours for 20 seconds at a sampling speed of 50 kHz. Both the radial load and the axial load were set to 1.3 kN, and the temperature was set to 150 ° C. by heating with a heater. The oil separation rate of the grease sealed inside the angular contact ball bearing 7216 was 70% when the operating time reached 2000 hours.

FIG. 9 is a time chart of the conformance rate between the SFT image of the vibration data measured during monitoring and the SFT image of each oil separation level. In FIG. 9, the curve C0 shows the time change of the conformance rate P0 between the SFT image of the vibration data measured during monitoring and the SFT image of the oil separation level 0. The curve C1 shows the time change of the conformance rate P1 between the SFT image of the vibration data measured during monitoring and the SFT image of the oil separation level 1. The curve C2 shows the time change of the conformance rate P2 between the SFT image of the vibration data measured during monitoring and the SFT image of the oil separation level 2.

As shown in FIG. 9, the operating time L10 (0 <L10 <500) is closest to the operating time L0 (0) associated with the oil separation level 0, followed by the oil separation level 1. The operating time is close to L1 (1000). The actual state of the grease at the operating time L10 is closest to the state of the grease having the oil separation level 0, and then the state of the grease having the oil separation level 1. The values of the precision ratios P0 to P2 at the operation time L10 are 0.9, 0.1, and 0, respectively. From the magnitude relationship P0> P1> P2 of the conformance ratios P0 to P2, the state of the grease at the operating time L10 is closest to the state of the grease having the oil separation level 0, and then the state of the grease having the oil separation level 1. Can be estimated. The conformance rates P0 to P2 of the operation time L10 reflect the actual state of grease in the operation time L10.

The operating time L20 (1000 <L20 <1500) is closest to the operating time L1 and then to the operating time L2 (2000) associated with the oil isolation level 2. The actual state of the grease at the operating time L20 is closest to the state of the grease of the oil separation level 1, and then the state of the grease of the oil separation level 2. The values of the precision ratios P0 to P2 at the operation time L20 are 0, 0.9, and 0.1, respectively. From the magnitude relationship P1> P2> P0 of the conformance ratios P0 to P2, the state of the grease at the operating time L20 is closest to the state of the grease of the oil separation level 1, and then the state of the grease of the oil separation level 2. Can be estimated. The conformance rates P0 to P2 of the operating time L20 reflect the actual state of grease during the operating time L20.

The operating time L30 (1500 <L30 <2000) is closest to the operating time L2, followed by the operating time L1. The actual state of the grease at the operating time L30 is closest to the state of the grease of the oil separation level 2, and then the state of the grease of the oil separation level 1. The values of the precision ratios P0 to P2 at the operation time L30 are 0, 0.1, and 0.9, respectively. From the magnitude relationship P2> P1> P0 of the conformance ratios P0 to P2, the state of the grease at the operating time L30 is closest to the state of the grease of the oil separation level 2, and then the state of the grease of the oil separation level 1. Can be estimated. The conformance rates P0 to P2 of the operating time L30 reflect the actual state of grease during the operating time L30.

FIG. 10 is a diagram showing the relationship between the operating time of the rolling bearing and the remaining life estimated by the condition monitoring device according to the embodiment. As shown in FIG. 10, the remaining life corresponding to the state of grease that deteriorates with an increase in operating time is estimated.

In the embodiment, the case where the inner ring is a rotating wheel and the outer ring is a stationary ring has been described. In the rolling bearing to be monitored by the condition monitoring device according to the embodiment, the inner ring may be a stationary wheel and the outer ring may be a rotating wheel.

In the embodiment, the oil separation rate is divided into three levels, and the case where the STFT images of each level are machine-learned during the learning period has been described. The oil separation rate may be divided into 4 levels or more. Further, the feature amount of the vibration data may be other than the SFT image, and may be, for example, an effective value, a maximum value, a crest factor, a kurtosis, and a skewness.

As described above, according to the condition monitoring device according to the embodiment, the remaining life of the grease sealed in the rolling bearing can be estimated by using the classifier created by machine learning of the feature amount of the vibration data.

It should be considered that the embodiments disclosed this time are exemplary in all respects and not restrictive. The scope of the present invention is shown by the scope of claims rather than the above description, and is intended to include all modifications within the meaning and scope equivalent to the scope of claims.

1 Condition monitoring device, 10 Rolling bearing, 11 Spindle, 12 Inner ring, 14 Outer ring, 16 Cage, 18 Rolling element, 20 Vibration sensor, 40 Control unit, 50 Storage unit, Grc grease.

Claims (7)

Steps to create a classifier by machine learning,
Including steps to monitor the condition of rolling bearings
The step of creating the classifier is
A step of calculating the feature amount of the first vibration data of the rolling bearing filled with grease of the first oil separation rate, and
A step of calculating the feature amount of the second vibration data of the rolling bearing in which grease having a second oil separation rate smaller than that of the first oil separation rate is filled, and
A step of calculating the feature amount of the third vibration data of the rolling bearing filled with normal grease, and
It includes a step of machine learning the features of the first to third vibration data to create the classifier.
The operating time of the rolling bearing until the oil separation rate of the normal grease becomes the first oil separation rate is the first operating time.
The operating time of the rolling bearing until the oil separation rate of the normal grease becomes the second oil separation rate is the second operating time shorter than the first operating time.
The step of monitoring the above state is
A step of calculating the feature amount of the fourth vibration data of the rolling bearing measured during monitoring, and
Using the classifier, a step of calculating the first to third conformance ratios of the feature amount of the fourth vibration data and the feature amount of the first to third vibration data, respectively.
Using the first and second operation times and the first to third conformance rates, the remaining life until the oil separation rate of the grease sealed in the rolling bearing becomes the first oil separation rate is calculated. How to monitor the condition of rolling bearings, including steps to do. The total of the first to third conformance rates is 1.
In the step of calculating the remaining life, the total of the values obtained by multiplying the first and second conformance rates and the first and second operating hours is subtracted from the first operating time, and the remaining life is calculated. The method for monitoring the state of the rolling bearing according to claim 1, which is calculated as. The method for monitoring the condition of a rolling bearing according to claim 1 or 2, wherein the grease having a first oil separation rate and the grease having a second oil separation rate are artificially adjusted greases. The grease having the first oil separation rate is grease obtained by operating the rolling bearing filled with the normal grease for the first operating time.
The grease according to claim 1 or 2, wherein the grease having a second oil separation rate is grease obtained by operating the rolling bearing filled with the normal grease for the second operating time. Condition monitoring method. The condition monitoring of the rolling bearing according to any one of claims 1 to 4, wherein the feature amount of the first to fourth vibration data includes data obtained by short-time Fourier transform of the first to fourth vibration data. Method. The state of the rolling bearing according to any one of claims 1 to 5, wherein the first to third vibration data are vibration data measured after the running-in operation period has elapsed since the operation of the rolling bearing was started. Monitoring method. A condition monitoring device for monitoring the condition of the rolling bearing by using the method for monitoring the condition of the rolling bearing according to any one of claims 1 to 6.

Images