JP6820771B2 - Condition monitoring system and wind power generator - Google Patents

Description

The present invention relates to a condition monitoring system for monitoring the state of mechanical elements constituting the apparatus, and more particularly to a condition monitoring system for monitoring the condition of mechanical elements constituting the wind power generator.

In a wind power generator, power is generated by rotating a spindle connected to a blade that receives wind power, accelerating the rotation of the spindle by a speed increaser, and then rotating a rotor of a generator. Each of the spindle and the rotary shaft of the speed increaser and the generator is rotatably supported by rolling bearings, and a condition monitoring system (CMS) for diagnosing abnormalities in such bearings is known. .. In such a condition monitoring system, it is diagnosed whether or not the bearing is damaged by using the vibration waveform data measured by the vibration sensor fixed to the bearing.

As a condition monitoring system for monitoring the state of the internal device of a general device having a built-in arithmetic unit or the like, for example, Japanese Patent Application Laid-Open No. 7-159469 (Patent Document 1) describes a circuit for measuring the internal state of the device to be measured. When an abnormality of the device under test is detected based on the signal output from, a configuration is shown in which the detection signal is received and a trigger for starting measurement and recording is generated for each measurement element circuit and recording unit. ing.

Japanese Unexamined Patent Publication No. 7-159469

However, in the condition monitoring system disclosed in Patent Document 1, when noise is superimposed on the signal output from the circuit that measures the internal state of the device under test, it is detected as an abnormality of the device under test and a trigger is generated. May occur. In such a case, since the trigger is frequently generated due to the influence of noise, the measurement and recording of the internal state of the device under test are started each time the trigger is generated. As a result, a huge amount of data is accumulated in the recording unit in a state where the data when the device to be measured is normal and the data when the device to be measured is abnormal are mixed. As a result, accurate abnormality diagnosis based on the data accumulated in the recording unit may not be possible.

Therefore, the present invention has been made to solve such a problem, and an object of the present invention is to provide a condition monitoring system and a wind power generation device that realize accurate abnormality diagnosis.

The condition monitoring system according to the present invention is a condition monitoring system that monitors the condition of a machine element constituting the device, and is a vibration sensor for measuring a vibration waveform of the machine element and a vibration sensor for diagnosing an abnormality of the machine element. It is equipped with a processing device. The processing device includes an evaluation value calculation unit and a diagnostic unit. The evaluation value calculation unit is configured to continuously calculate the evaluation value that characterizes the vibration waveform data output from the vibration sensor within a fixed time. The diagnostic unit diagnoses the abnormality of the machine element using the vibration waveform data by starting the measurement of the vibration waveform data triggered by the change in the tendency of the evaluation value calculated by the evaluation value calculation unit over time. It is configured to do.

According to the present invention, it is possible to reliably and appropriately acquire vibration waveform data when an abnormality occurs in a mechanical element constituting the device, so that an accurate abnormality diagnosis can be realized.

It is a figure which showed schematic the structure of the wind power generation apparatus to which the condition monitoring system which concerns on Embodiment 1 of this invention was applied. It is a functional block diagram which functionally shows the structure of the data processing apparatus shown in FIG. It is a figure explaining the operation of the vibration waveform data storage unit and the evaluation value calculation unit shown in FIG. It is a figure explaining the operation of the evaluation value trend storage part shown in FIG. It is a figure explaining the operation of the measurement trigger generation part and the vibration waveform data output part shown in FIG. It is a flowchart explaining the control process for storing the vibration waveform data of a bearing in the condition monitoring system which concerns on Embodiment 1. FIG. It is a flowchart explaining the control process for generating the measurement trigger of the vibration waveform data of a bearing in the condition monitoring system which concerns on Embodiment 1. FIG. It is a flowchart explaining the control process for generating the measurement trigger of the vibration waveform data of a bearing in the condition monitoring system which concerns on Embodiment 2. It is a flowchart explaining the control process for generating the measurement trigger of the vibration waveform data of a bearing in the state monitoring system which concerns on Embodiment 3. It is a functional block diagram which functionally shows the structure of the data processing apparatus in the state monitoring system which concerns on Embodiment 4. FIG. It is a conceptual diagram which shows the relationship between the vibration waveform data of a bearing and a segment within a certain time. It is a figure for demonstrating the feature quantity vector. It is a figure for demonstrating the basic concept of OC-SVM.

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.

[Embodiment 1]
FIG. 1 is a diagram schematically showing a configuration of a wind power generation device to which a condition monitoring system according to a first embodiment of the present invention is applied. With reference to FIG. 1, the wind power generator 10 includes a spindle 20, a blade 30, a speed increaser 40, a generator 50, a spindle bearing (hereinafter, simply referred to as “bearing”) 60, and vibration. It includes a sensor 70 and a data processing device 80. The speed increaser 40, the generator 50, the bearing 60, the vibration sensor 70 and the data processing device 80 are housed in the nacelle 90, and the nacelle 90 is supported by the tower 100.

The spindle 20 enters the nacelle 90, is connected to the input shaft of the speed increaser 40, and is rotatably supported by the bearing 60. Then, the spindle 20 transmits the rotational torque generated by the blade 30 that has received the wind power to the input shaft of the speed increaser 40. The blade 30 is provided at the tip of the spindle 20, converts wind power into rotational torque, and transmits the wind power to the spindle 20.

The bearing 60 is fixed in the nacelle 90 and rotatably supports the spindle 20. The bearing 60 is composed of rolling bearings, for example, self-aligning roller bearings, tapered roller bearings, cylindrical roller bearings, ball bearings and the like. These bearings may be of single row or double row.

The vibration sensor 70 is fixedly attached to the bearing 60. The vibration sensor 70 measures the vibration waveform of the bearing 60 and outputs the measured vibration waveform data to the data processing device 80. The vibration sensor 70 is composed of, for example, an acceleration sensor using a piezoelectric element.

The speed increaser 40 is provided between the spindle 20 and the generator 50, and increases the rotational speed of the spindle 20 to output to the generator 50. As an example, the speed increaser 40 is composed of a gear speed increase mechanism including a planetary gear, an intermediate shaft, a high speed shaft, and the like. Although not particularly shown, a plurality of bearings for rotatably supporting a plurality of shafts are also provided in the speed increaser 40.

The generator 50 is connected to the output shaft of the speed increaser 40 and generates electricity by the rotational torque received from the speed increaser 40. The generator 50 is composed of, for example, an induction generator. A bearing that rotatably supports the rotor is also provided in the generator 50.

The data processing device 80 is provided in the nacelle 90 and receives the vibration waveform data of the bearing 60 from the vibration sensor 70. The data processing device 80 diagnoses the abnormality of the bearing 60 by using the vibration waveform data of the bearing 60 according to a preset program.

FIG. 2 is a functional block diagram functionally showing the configuration of the data processing device 80 shown in FIG. With reference to FIG. 2, the data processing device 80 includes a band pass filter (hereinafter referred to as “BPF (Band Pass Filter)”) 110, an effective value calculation unit 120, a storage unit 130, and a vibration waveform data output. A unit 140, a diagnosis unit 150, an evaluation value calculation unit 160, and a measurement trigger generation unit 170 are included.

The BPF 110 receives the vibration waveform data of the bearing 60 from the vibration sensor 70. The BPF 110 includes, for example, a high pass filter (HPF (High Pass Filter)). The HPF passes a signal component higher than a predetermined frequency through the received vibration waveform data and blocks the low frequency component. The HPF is provided to remove the DC component included in the vibration waveform data of the bearing 60. If the output of the vibration sensor 70 does not include a DC component, the HPF may be omitted.

The BPF 110 may include a low pass filter (LPF (Low Pass Filter)) in addition to or in place of the HPF. The LPF passes a signal component lower than a predetermined frequency through the received vibration waveform data.

Further, an envelope processing unit may be provided between the vibration sensor 70 and the BPF 110. When the envelope processing unit receives the vibration waveform data of the bearing 60 from the vibration sensor 70, the envelope processing unit performs envelope processing on the received vibration waveform data to generate an envelope waveform of the vibration waveform data of the bearing 60. Various known methods can be applied to the envelope processing calculated in the envelope processing unit. As an example, the vibration waveform data of the bearing 60 received from the vibration sensor 70 is rectified to an absolute value and passed through the LPF. Generates an envelope waveform of vibration waveform data of the bearing 60.

In this case, in the BPF 110, when the HPF receives the envelope waveform of the vibration waveform data of the bearing 60 from the envelope processing unit, the received envelope waveform passes a signal component higher than a predetermined frequency and a low frequency component. To shut off. That is, the HPF is configured to remove the DC component contained in the envelope waveform and extract the AC component of the envelope waveform.

The effective value calculation unit 120 receives the vibration waveform data of the filtered bearing 60 from the BPF 110. The effective value calculation unit 120 calculates the effective value of the vibration waveform data of the bearing 60 (also referred to as “RMS (Root Mean Square) value”), and stores the calculated effective value of the vibration waveform data in the storage unit 130. Output to.

Since the effective value of the vibration waveform of the bearing 60 calculated by the effective value calculation unit 120 is the effective value of the raw vibration waveform without the envelope processing, for example, a part of the raceway ring of the bearing 60 is peeled off. However, the increase in vibration increases only when the rolling element passes through the peeled part. Although the increase in value is small for impulse-like vibration, it occurs when the surface of the contact part between the raceway ring and the rolling element is rough or poorly lubricated. The increase in value is large for continuous vibration.

On the other hand, as described above, when the envelope processing unit is provided, the effective value of the AC component of the envelope waveform calculated by the effective value calculation unit 120 is a continuous value that occurs when the surface of the raceway ring is rough or poor lubrication. The increase in value is small for vibration, and the increase in value is large for impulse-like vibration.

The storage unit 130 includes a vibration waveform data storage unit 132 and an evaluation value trend storage unit 134. The vibration waveform data storage unit 132 and the evaluation value trend storage unit 134 are composed of, for example, a readable and writable non-volatile memory.

The vibration waveform data storage unit 132 stores the effective value of the vibration waveform data of the bearing 60 calculated by the effective value calculation unit 120 every moment. The vibration waveform data storage unit 132 is configured to store the effective value of the vibration waveform data of the bearing 60 within a certain period of time. As will be described later, the effective value of the vibration waveform data of the bearing 60 stored in the vibration waveform data storage unit 132 is read out, and the abnormality of the bearing 60 is diagnosed using the read out effective value. In the following description, the effective value of the vibration waveform data is simply referred to as "vibration waveform data".

When the evaluation value calculation unit 160 reads the vibration waveform data of the bearing 60 within a fixed time from the vibration waveform data storage unit 132, the evaluation value calculation unit 160 calculates an evaluation value that characterizes the vibration waveform data of the bearing 60 within the read fixed time. The evaluation value calculation unit 160 is configured to calculate the evaluation value continuously in time.

The evaluation value trend storage unit 134 receives the evaluation value calculated by the evaluation value calculation unit 160. The evaluation value trend storage unit 134 stores the evaluation value given from the evaluation value calculation unit 160 every moment. In other words, the evaluation value trend storage unit 134 is configured to store the evaluation value trend indicating the tendency of the evaluation value to change with time.

FIG. 3 is a diagram illustrating the operation of the vibration waveform data storage unit 132 and the evaluation value calculation unit 160 shown in FIG.

With reference to FIG. 3, the vibration waveform data storage unit 132 receives the vibration waveform data of the bearing 60 from the effective value calculation unit 120 at predetermined time intervals. In the example of FIG. 3, a predetermined time interval is set to 1 second interval. D0 to D11 in FIG. 3 represent vibration waveform data given to the vibration waveform data storage unit 132 at 1-second intervals.

The vibration waveform data storage unit 132 stores the vibration waveform data of the bearing 60 within a certain period of time. The fixed time can be set according to the rotation speed of the spindle 20. In the example of FIG. 3, a fixed time is set to 10 seconds. For example, at time t0, the vibration waveform data storage unit 132 stores a total of 10 vibration waveform data D0 to D9 that are continuous in time (that is, for 10 seconds).

When the vibration waveform data storage unit 132 receives the vibration waveform data D10 from the effective value calculation unit 120 at the time t1 when 1 second has passed from the time t0, the oldest vibration waveform among the vibration waveform data D0 to D9 for 10 seconds. By erasing the data D0 and adding the newly input vibration waveform data D10, the vibration waveform data within a certain period of time is updated.

Further, at time t2 when 1 second has passed from time t1, the vibration waveform data storage unit 132 erases the oldest vibration waveform data D1 among the vibration waveform data D1 to D10 for 10 seconds and newly inputs the vibration waveform data D1. By adding the vibration waveform data D11, the vibration waveform data of the bearing 60 within a certain period of time is updated.

In this way, the vibration waveform data storage unit 132 updates the vibration waveform data of the bearing 60 within a fixed time at predetermined time intervals. The evaluation value calculation unit 160 reads out the vibration waveform data of the bearing 60 within a fixed time, which is updated at a predetermined time interval, from the vibration waveform data storage unit 132. The evaluation value calculation unit 160 calculates the evaluation value by statistically processing the vibration waveform data of the bearing 60 within a fixed time read out.

In the example of FIG. 3, when the evaluation value calculation unit 160 reads the vibration waveform data D0 to D9 for 10 seconds from the vibration waveform data storage unit 132 at time t0, the read vibration waveform data D0 to D9 are statistically processed. The evaluation value E0 is calculated by doing so. The evaluation value E0 is a value (representative value) that characterizes the vibration waveform data D0 to D9 for 10 seconds immediately before the time t0. Therefore, in the statistical processing, for example, the average value of the vibration waveform data D0 to D9 can be calculated as the evaluation value E0. Alternatively, as the evaluation value E0, the median value, mode value, minimum value, etc. of the vibration waveform data D0 to D9 can be calculated.

At time t1, the evaluation value calculation unit 160 calculates the evaluation value E1 by statistically processing the vibration waveform data D1 to D10 for 10 seconds. At time t2, the evaluation value calculation unit 160 calculates the evaluation value E2 by statistically processing the vibration waveform data D2 to D11 for 10 seconds.

In this way, the evaluation value calculation unit 160 calculates the evaluation value of the vibration waveform data of the bearing 60 within a fixed time at predetermined time intervals. The evaluation value calculation unit 160 outputs the calculated evaluation value to the evaluation value trend storage unit 134.

FIG. 4 is a diagram illustrating the operation of the evaluation value trend storage unit 134 shown in FIG.
With reference to FIG. 4, the evaluation value trend storage unit 134 receives the evaluation value from the evaluation value calculation unit 160 at a predetermined time interval. In the example of FIG. 4, a predetermined time interval is set to 1 second interval. E0 to E6 in FIG. 4 represent evaluation values given to the evaluation value trend storage unit 134 by the evaluation value calculation unit 160 at 1-second intervals.

The evaluation value trend storage unit 134 stores a predetermined number of evaluation values that are continuous in time. This temporally continuous predetermined number of evaluation values corresponds to an "evaluation value trend" showing the tendency of the evaluation value to change with time.

In the example of FIG. 4, the predetermined number is 5. For example, the evaluation value trend storage unit 134 stores the evaluation value E0 at the time t0, stores the evaluation value E1 at the time t1 1 second after the time t0, and at the time t2 1 second after the time t1. The evaluation value E2 is stored, the evaluation value E3 is stored at the time t3 when 1 second has passed from the time t2, and the evaluation value E4 is stored at the time t4 when 1 second has passed from the time t3. The evaluation value E3 is calculated by statistically processing the vibration waveform data D3 to D12 for 10 seconds immediately before the time t3. The evaluation value E4 is calculated by statistically processing the vibration waveform data D4 to D13 for 10 seconds immediately before the time t4.

In the example of FIG. 4, the evaluation value trend storage unit 134 stores a total of five evaluation values E0 to E4 at time t5, for example. At time t6, which is 1 second after time t5, the evaluation value trend storage unit 134 receives the evaluation value E5 of the vibration waveform data D5 to D14 for 10 seconds immediately before the time t5 from the evaluation value calculation unit 160, for a total of 5 A predetermined number of evaluation values are updated by deleting the oldest evaluation value E0 out of the evaluation values E0 to E4 and adding a newly input evaluation value E5.

Further, at time t6, which is one second after time t5, the evaluation value trend storage unit 134 receives the evaluation values E6 of the vibration waveform data D6 to D15 for 10 seconds immediately before the time t6 from the evaluation value calculation unit 160. A predetermined number of evaluation values are updated by deleting the oldest evaluation value E1 out of a total of five evaluation values E1 to E5 and adding a newly input evaluation value E6.

In this way, the evaluation value trend storage unit 134 updates a predetermined number of evaluation values (evaluation value trends) that are continuous in time at predetermined time intervals.

Returning to FIG. 2, when the measurement trigger generation unit 170 reads out a predetermined number of evaluation values (evaluation value trends) that are continuous in time from the evaluation value trend storage unit 134, the vibration waveform is based on the read evaluation value trend. A trigger for starting data measurement (hereinafter, also referred to as “measurement trigger”) is generated. The measurement trigger generation unit 170 outputs the generated measurement trigger to the vibration waveform data output unit 140.

FIG. 5 is a diagram illustrating the operation of the measurement trigger generation unit 170 and the vibration waveform data output unit 140 shown in FIG. FIG. 5 shows an evaluation value trend stored in the evaluation value trend storage unit 134, a measurement trigger generated from the measurement trigger generation unit 170 based on the evaluation value trend, and a bearing 60 output from the vibration waveform data output unit 140. An example of vibration waveform data is shown.

Ei-4, Ei-3, ... Ei, Ei + 1 in FIG. 5 represent evaluation values given to the evaluation value trend storage unit 134 at predetermined time intervals. In the example of FIG. 5, the predetermined time interval is set to 1 second interval. Ei indicates the evaluation value given to the evaluation value trend storage unit 134 at time ti-1, Ei-1 indicates the evaluation value given to the evaluation value trend storage unit 134 at time ti-1, and Ei + 1 indicates the evaluation value trend at time ti + 1. The evaluation value given to the storage unit 134 is shown.

The measurement trigger generation unit 170 determines whether or not the evaluation value trend, which represents the tendency of the evaluation value to change with time, has changed. When it is determined that the evaluation value trend has changed, the measurement trigger generation unit 170 generates a measurement trigger. Specifically, the measurement trigger generation unit 170 determines whether or not the evaluation value trend has changed based on the temporal change rate of the evaluation value, that is, the amount of change within a unit time.

In the example of FIG. 5, when the evaluation value Ei is stored in the evaluation value trend storage unit 134 at the time ti, the measurement trigger generation unit 170 has the evaluation value Ei at the time ti and the evaluation value Ei-1 at the time ti + 1. The rate of change of the evaluation value over time is calculated based on the difference. Assuming that the rate of change of the evaluation value at time ti is dEi, dEi is represented by the equation (1).

dEi = (Ei-Ei + 1) / (ti-ti + 1) ... (1)
The measurement trigger generation unit 170 compares the calculated temporal change rate dEi with the predetermined threshold value α. When the temporal change rate dEi is equal to or higher than the threshold value α, the measurement trigger generation unit 170 sets the measurement trigger to ON. On the other hand, when the temporal change rate dEi is smaller than the threshold value α, the measurement trigger generation unit 170 sets the measurement trigger to off. FIG. 5 shows a case where the temporal change rate dEi + 1 at the time ti + 1 is equal to or greater than the threshold value α. In this case, at time ti + 1, the measurement trigger generator 170 switches the measurement trigger from off to on. The measurement trigger generation unit 170 outputs the measurement trigger to the vibration waveform data output unit 140.

When the vibration waveform data output unit 140 receives the measurement trigger from the measurement trigger generation unit 170, the vibration waveform data output unit 140 reads out the vibration waveform data of the bearing 60 stored in the vibration waveform data storage unit 132 within a certain period of time. The vibration waveform data of the bearing 60 within the fixed time corresponds to the vibration waveform data of the bearing 60 within the fixed time immediately before the time when the measurement trigger is generated. In the example of FIG. 5, the vibration waveform data Di-9 to Di for 10 seconds immediately before the time ti + 1 are read from the vibration waveform data storage unit 132.

The vibration waveform data output unit 140 further receives the vibration waveform data of the bearing 60 after the time ti + 1 from the effective value calculation unit 120. In the example of FIG. 5, the vibration waveform data output unit 140 receives the vibration waveform data Di + 1 to Di + 10 for 10 seconds after the time ti + 1 from the effective value calculation unit 120.

The vibration waveform data output unit 140 sets the vibration waveform data Di-9 to Di of the bearing 60 within a certain time immediately before the time ti + 1 when the measurement trigger is generated, and the time ti + 1 or later when the measurement trigger is generated. The vibration waveform data Di + 1 to Di + 10 of the bearing 60 are collectively output to the diagnostic unit 150.

Upon receiving the vibration waveform data Di-9 to Di + 10 of the bearing 60, the diagnosis unit 150 diagnoses the abnormality of the bearing 60 based on the vibration waveform data Di-9 to Di + 10. That is, the diagnosis unit 150 is configured to start measuring the vibration waveform data when the measurement trigger is generated due to the change in the tendency of the evaluation value to change with time.

As described above, according to the state monitoring system according to the first embodiment, the evaluation value that characterizes the vibration waveform data within a certain period of time is calculated, and the evaluation value shows the tendency of the temporal change of the evaluation value. When the rate of change changes, a trigger is generated to start the measurement of the vibration waveform data. In this way, the trigger can be generated based on the evaluation value in which the influence of the noise superimposed on the vibration waveform data is appropriately eliminated, so that the trigger is prevented from being frequently generated due to the influence of the noise. can do. As a result, the vibration waveform data when a failure occurs in the bearing 60 can be measured reliably and efficiently, so that an accurate abnormality diagnosis can be realized.

Here, the grouped vibration waveform data Di-9 to Di + 10 of the bearing 60 given to the diagnostic unit 150 are before and after the time when the measurement trigger occurs, that is, the time when the tendency of the temporal change of the evaluation value changes. It corresponds to the vibration waveform data of the bearing 60 acquired over. Therefore, the diagnostic unit 150 can investigate the state of the bearing 60 before and after the time when the tendency of the temporal change of the evaluation value changes by analyzing these vibration waveform data.

The vibration waveform data storage unit 132 stores the vibration waveform data of the bearing 60 within a certain period of time immediately before the time when the measurement trigger is generated, and erases the vibration waveform data of the bearing 60 when the measurement trigger is not generated. It is configured to do. According to this, since the vibration waveform data storage unit 132 may have a storage capacity capable of storing only data useful for the subsequent investigation, the storage capacity of the memory built in the data processing device 80 is large. It is possible to avoid becoming too much.

Further, in the data processing device 80, the vibration waveform data storage unit 132 and the evaluation value trend storage unit 134 are stored in a memory independent of the storage unit for storing the vibration waveform data output from the effective value calculation unit 120 every moment. Can be configured by. In this way, the vibration waveform data storage unit 132 and the evaluation value trend storage unit 134 can be easily added or removed depending on the application and situation of the wind power generation device 10.

Next, the control process for diagnosing the abnormality of the bearing 60 in the condition monitoring system according to the first embodiment will be described with reference to FIGS. 6 and 7.

FIG. 6 is a flowchart illustrating a control process for storing vibration waveform data of the bearing 60 in the condition monitoring system according to the first embodiment. The control process shown in FIG. 6 is repeatedly executed by the vibration waveform data storage unit 132 at predetermined time intervals. For example, in the example of FIG. 3, the control process shown in FIG. 6 is repeatedly executed at 1-second intervals.

With reference to FIG. 6, the vibration waveform data storage unit 132 receives the vibration waveform data of the bearing 60 from the effective value calculation unit 120 in step S01. In step S02, the vibration waveform data storage unit 132 determines whether or not the number of vibration waveform data of the stored bearing 60 is a predetermined number X or more. This predetermined number X is worthy of the number of vibration waveform data of the bearing 60 acquired within a certain period of time. In the example of FIG. 3, since the fixed time is set to 10 seconds, the predetermined number X is set to "10" which is a value obtained by dividing the fixed time by a predetermined time interval.

When the number of the stored vibration waveform data of the bearing 60 is a predetermined number X or more (when YES is determined in S02), the vibration waveform data storage unit 132 proceeds to step S03 and out of the vibration waveform data of the predetermined number X. Erase the oldest vibration waveform data. Then, the vibration waveform data storage unit 132 adds the vibration waveform data acquired in step S01 in step S04.

On the other hand, when the number of the stored vibration waveform data of the bearing 60 is less than the predetermined number X (at the time of NO determination in S02), the vibration waveform data storage unit 132 proceeds to step S04 and the vibration acquired in step S01. Add waveform data. In this way, the vibration waveform data storage unit 132 updates the vibration waveform data within a fixed time at predetermined time intervals.

FIG. 7 is a flowchart illustrating a control process for generating a measurement trigger of vibration waveform data of the bearing 60 in the condition monitoring system according to the first embodiment. The control process shown in FIG. 7 is repeatedly executed by the evaluation value calculation unit 160, the evaluation value trend storage unit 134, the measurement trigger generation unit 170, and the vibration waveform data output unit 140 at predetermined time intervals.

With reference to FIG. 7, the evaluation value calculation unit 160 reads out the vibration waveform data of the bearing 60 within a certain period of time from the vibration waveform data storage unit 132 in step S11.

In step S12, the evaluation value calculation unit 160 calculates the evaluation value of the vibration waveform data of the bearing 60 within a certain time by statistically processing the vibration waveform data of the bearing 60 within a certain time read in step S11. The evaluation value calculation unit 160 outputs the calculated evaluation value to the evaluation value trend storage unit 134.

In step S13, the evaluation value trend storage unit 134 determines whether or not the number of stored evaluation value data is a predetermined number Y or more. The predetermined number Y corresponds to the number of data required to acquire the evaluation value trend representing the tendency of the evaluation value to change with time. The predetermined number Y is set to a number of 2 or more. In the example of FIG. 4, the predetermined number Y is set to 5.

When the number of stored evaluation value data is equal to or greater than the predetermined number Y (when YES is determined in S13), the evaluation value trend storage unit 134 proceeds to step S14 and proceeds to step S14, and the oldest evaluation value among the evaluation values of the predetermined number Y Clear the value. Then, the evaluation value trend storage unit 134 adds the evaluation value calculated in step S12 in step S15.

On the other hand, when the number of stored evaluation value data is less than the predetermined number Y (when NO is determined in S13), the evaluation value trend storage unit 134 proceeds to step S15 and adds the evaluation value calculated in step S12. .. In this way, the evaluation value trend storage unit 134 updates the evaluation value of a predetermined number Y at a predetermined time interval.

When the measurement trigger generation unit 170 reads out the evaluation value (evaluation value trend) of a predetermined number Y that is continuous in time from the evaluation value trend storage unit 134 in step S16, the evaluation value changes with time in the read evaluation value trend. Calculate the rate. In step S16, the measurement trigger generation unit 170 reads out the evaluation value added in step S15 and the evaluation value added immediately before the evaluation value from the evaluation value trend storage unit 134. Then, the measurement trigger generation unit 170 calculates the temporal change rate of the evaluation value based on the difference between the two read evaluation values by using the above equation (1).

In step S17, the measurement trigger generation unit 170 compares the temporal change rate of the evaluation value calculated in step S16 with the threshold value α. When the temporal change rate of the evaluation value is smaller than the threshold value α (when NO is determined in S17), the subsequent processes S18 to S21 are skipped. On the other hand, when the temporal change rate of the evaluation value is equal to or higher than the threshold value α (when YES is determined in S17), the measurement trigger generation unit 170 generates a measurement trigger in step S18 and outputs the generated measurement trigger as vibration waveform data. Output to unit 140.

When the vibration waveform data output unit 140 receives the measurement trigger from the measurement trigger generation unit 170, the vibration waveform data output unit 140 is stored in the vibration waveform data storage unit 132 every moment in step S19, and the vibration of the bearing 60 after the time when the measurement trigger is generated. Read the waveform data.

Further, in step S20, the vibration waveform data output unit 140 reads out the vibration waveform data of the bearing 60 stored in the vibration waveform data storage unit 132 within a certain period of time. As described with reference to FIG. 5, the vibration waveform data of the bearing 60 within a fixed time corresponds to the vibration waveform data of the bearing 60 within a fixed time immediately before the time when the measurement trigger is generated.

The vibration waveform data output unit 140 includes the vibration waveform data of the bearing 60 read in step S20 in step S20 within a certain period of time immediately before the time when the measurement trigger occurs, and the measurement trigger acquired in step S19. The vibration waveform data of the bearing 60 after the time when the above occurs is collected and output to the diagnosis unit 150. As a result, the diagnosis unit 150 diagnoses the abnormality of the bearing 60 by using the vibration waveform data of the bearing 60 collected together.

(Modified Example of Embodiment 1)
In the first embodiment described above, the rate of change over time (for example, dEi in FIG. 5) between two time-consecutive evaluation values (for example, the evaluation values Ei-1 and Ei in FIG. 5) is calculated. The configuration for generating the measurement trigger was described based on the result of comparing the calculated temporal change rate and the threshold value α. However, in this configuration, when noise is superimposed on one of the two evaluation values, the temporal change rate of the evaluation value may temporarily exceed the threshold value α due to the influence of the noise. In such a case, the measurement trigger generation unit 170 may erroneously generate the measurement trigger.

Therefore, in order to prevent the measurement trigger from being erroneously generated due to the influence of such noise, the measurement trigger generation unit 170 continuously determines that the temporal change rate of the evaluation value is the threshold value α or more. When obtained, it can be configured to generate a measurement trigger. For example, in the example of FIG. 5, when it is determined that both the temporal change rate dEi + 1 at the time ti + 1 and the temporal change rate dEi + 2 at the time ti + 2 are equal to or greater than the threshold value α, the measurement trigger generator 170 generates a measurement trigger. Can be configured to be

In this way, when the temporal change rate dEi + 1 at the time ti + 1 is equal to or greater than the threshold value α, while the temporal change rate dEi + 2 at the time ti + 2 is smaller than the threshold value α, the measurement trigger generator 170 causes the measurement trigger. Does not occur. Since the increase in the temporal change rate dEi + 1 is considered to be temporary due to the influence of noise, it is possible to prevent the measurement trigger from being erroneously generated.

[Embodiment 2]
In the first embodiment described above, it is determined based on the temporal change rate of the evaluation value that the tendency of the evaluation value of the vibration waveform data of the bearing 60 has changed within a certain period of time, and a measurement trigger is generated. The configuration to be performed was explained. In the second embodiment, a configuration for generating a measurement trigger by determining that the tendency of the evaluation value to change with time has changed based on the magnitude of the evaluation value will be described.

FIG. 8 is a flowchart illustrating a control process for generating a measurement trigger of vibration waveform data of the bearing 60 in the condition monitoring system according to the second embodiment. The control process shown in FIG. 8 is repeatedly executed by the evaluation value calculation unit 160, the evaluation value trend storage unit 134, the measurement trigger generation unit 170, and the vibration waveform data output unit 140 at predetermined time intervals.

Comparing FIG. 8 with FIG. 7, in the condition monitoring system according to the second embodiment, after the same processing of steps S11 to S15 as in FIG. 7, step S17A is executed instead of steps S16 and S17.

That is, when the evaluation value trend storage unit 134 adds the evaluation value calculated in step S12 in step S15, the measurement trigger generation unit 170 compares the evaluation value added in step S15 with the threshold value β in step S17A. .. When the evaluation value is smaller than the threshold value β (when NO is determined in S17A), the subsequent processes S18 to S21 are skipped. On the other hand, when the evaluation value is equal to or higher than the threshold value β (when YES is determined in S17A), the measurement trigger generation unit 170 generates the measurement trigger by the same process in step S18 as in FIG.

By performing the same processing in steps S19 to S21 as in FIG. 7, the vibration waveform data output unit 140 generated the vibration waveform data of the bearing 60 and the measurement trigger within a certain period of time immediately before the time when the measurement trigger was generated. The vibration waveform data of the bearing 60 after the time point is collected and output to the diagnosis unit 150.

As described above, according to the second embodiment, the evaluation value that characterizes the vibration waveform data within a certain period of time is calculated, and when the magnitude of this evaluation value becomes the threshold β or more, the evaluation value changes with time. It is determined that the tendency has changed, and a trigger for starting the measurement of the vibration waveform data is generated. In this way, the trigger can be generated based on the evaluation value in which the influence of noise superimposed on the vibration waveform data is appropriately eliminated. Therefore, even in the second embodiment, the same effect as that of the first embodiment can be obtained.

(Modified Example of Embodiment 2)
In the second embodiment described above, a configuration for generating a measurement trigger has been described based on the result of comparing the evaluation value and the threshold value β. However, in this configuration, when the evaluation value temporarily exceeds the threshold value β due to the superimposition of noise on the evaluation value, the measurement trigger generation unit 170 may erroneously generate the measurement trigger.

In order to prevent the measurement trigger from being erroneously generated due to the influence of such noise, the measurement trigger generator 170 measures when the determination result that the evaluation value is equal to or higher than the threshold value β is obtained a plurality of times in succession. It can be configured to trigger. For example, in the example of FIG. 5, when it is determined that the evaluation value Ei + 1 at the time ti + 1 and the evaluation value Ei + 2 at the time ti + 2 are both equal to or higher than the threshold value β, the measurement trigger generator 170 is configured to generate the measurement trigger. be able to.

In this way, when the evaluation value Ei + 1 at the time ti + 1 is equal to or higher than the threshold value β, while the evaluation value Ei + 2 at the time ti + 2 is smaller than the threshold value β, the measurement trigger generation unit 170 does not generate the measurement trigger. Since the increase in the evaluation value Ei + 1 is considered to be temporary due to the influence of noise, it is possible to prevent the measurement trigger from being erroneously generated.

[Embodiment 3]
In the third embodiment, the configuration in which the change in the tendency of the temporal change of the evaluation value is determined based on the temporal change rate and the magnitude of the evaluation value and the measurement trigger is generated will be described.

FIG. 9 is a flowchart illustrating a control process for generating a measurement trigger of vibration waveform data of the bearing 60 in the condition monitoring system according to the third embodiment. The control process shown in FIG. 9 is repeatedly executed by the evaluation value calculation unit 160, the evaluation value trend storage unit 134, the measurement trigger generation unit 170, and the vibration waveform data output unit 140 at predetermined time intervals.

Comparing FIG. 9 with FIG. 7, in the condition monitoring system according to the third embodiment, after the processing of steps S11 to S16 similar to FIG. 7, step S17A is executed in addition to step S17.

That is, when the evaluation value trend storage unit 134 adds the evaluation value calculated in step S12 in step S15, the measurement trigger generation unit 170 increases the temporal change rate and the threshold value α of the evaluation value calculated in step S16 in step S17. Compare with (first threshold). When the temporal change rate of the evaluation value is smaller than the threshold value α (when NO is determined in S17), the subsequent processes S17A to S21 are skipped. On the other hand, when the temporal change rate of the evaluation value is equal to or higher than the threshold value α (when YES is determined in S17), the measurement trigger generation unit 170 proceeds to step S17A, and proceeds to step S17A, and the evaluation value and the threshold value β added in step S15 (second). Threshold) and compare. When the evaluation value is smaller than the threshold value β (when NO is determined in S17A), the subsequent processes S18 to S21 are skipped.

On the other hand, when the evaluation value is equal to or higher than the threshold value β (when YES is determined in S17A), the measurement trigger generation unit 170 generates the measurement trigger by the same process in step S18 as in FIG.

By performing the same processing in steps S19 to S21 as in FIG. 7, the vibration waveform data output unit 140 generated the vibration waveform data of the bearing 60 and the measurement trigger within a certain period of time immediately before the time when the measurement trigger was generated. The vibration waveform data of the bearing 60 after the time point is collected and output to the diagnosis unit 150.

As described above, according to the third embodiment, the evaluation value that characterizes the vibration waveform data within a certain time is calculated, the temporal change rate of this evaluation value is equal to or more than the threshold value α, and the magnitude of the evaluation value is large. When the threshold value β or more is reached, it is determined that the tendency of the evaluation value to change with time has changed, and a trigger for starting the measurement of the vibration waveform data is generated. Even when the temporal change rate of the evaluation value is equal to or higher than the threshold value α, when the magnitude of the evaluation value is smaller than the threshold value β, the vibration degree, which is the magnitude of the vibration of the bearing 60, is small, so that noise It can be determined that the degree of influence is large. In such a case, by configuring the configuration so that the trigger is not generated, the trigger can be generated based on the evaluation value in which the influence of the noise superimposed on the vibration waveform data is appropriately excluded. Therefore, even in the third embodiment, the same effect as that of the first embodiment can be obtained.

(Modified Example of Embodiment 3)
As described above, when noise is superimposed on the evaluation value, the temporal change rate of the evaluation value temporarily becomes the threshold value α or more, or the evaluation value temporarily becomes the threshold value β or more, so that the measurement trigger generator The 170 may erroneously generate a measurement trigger.

Therefore, in the measurement trigger generation unit 170, the determination result that the temporal change rate of the evaluation value is the threshold value α or more is obtained a plurality of times in succession, and the determination result that the evaluation value is the threshold value β or more is obtained a plurality of times. It can be configured to generate a measurement trigger when it is obtained continuously. According to this, since the increase in the evaluation value is considered to be temporary due to the influence of noise, it is possible to prevent the measurement trigger from being erroneously generated.

[Embodiment 4]
In the fourth embodiment, a configuration for calculating the degree of abnormality of the vibration waveform data within the fixed time will be described as an evaluation value that characterizes the vibration waveform data within the fixed time.

FIG. 10 is a functional block diagram functionally showing the configuration of the data processing device 80 in the condition monitoring system according to the fourth embodiment of the present invention. With reference to FIG. 10, the data processing device 80 includes a BPF 110, an effective value calculation unit 120, a storage unit 130, a vibration waveform data output unit 140, an evaluation value calculation unit 160, and a measurement trigger generation unit 170. Includes diagnostic unit 150.

The storage unit 130 includes a vibration waveform data storage unit 132, an evaluation value trend storage unit 134, and a normal data storage unit 136. The vibration waveform data storage unit 132, the evaluation value trend storage unit 134, and the normal data storage unit 136 are composed of, for example, a readable and writable non-volatile memory.

As described with reference to FIG. 3, the vibration waveform data storage unit 132 is configured to store an effective value (vibration waveform data) of the vibration waveform data of the bearing 60 within a certain period of time.

The normal data storage unit 136 is an effective value (vibration waveform data) of the vibration waveform data of the bearing 60 measured when the normal operation of the wind power generator 10 (see FIG. 1) is guaranteed (for example, the initial state). Is configured to store. The vibration waveform data stored in the normal data storage unit 136 is used for setting the classification boundary in the learning unit 162, which will be described later. In the following description, the vibration waveform data stored in the normal data storage unit 136 is also referred to as “learning data”.

When the evaluation value calculation unit 160 reads the vibration waveform data of the bearing 60 within a fixed time from the vibration waveform data storage unit 132, the evaluation value calculation unit 160 calculates an evaluation value that characterizes the vibration waveform data of the bearing 60 within the read fixed time. In the present embodiment, the evaluation value calculation unit 160 includes a learning unit 162 and an abnormality degree calculation unit 164.

When the learning data is read from the normal data storage unit 136, the learning unit 162 sets a classification boundary for classifying normal and abnormal based on the read learning data.

The abnormality degree calculation unit 164 calculates the abnormality degree of the vibration waveform data by applying the classification boundary to the vibration waveform data of the bearing 60 within a certain period of time read from the vibration waveform data storage unit 132. The degree of anomaly corresponds to the distance from the classification boundary. The calculated degree of abnormality is an evaluation value that characterizes the vibration waveform data of the bearing 60 within the fixed time. The abnormality degree calculation unit 164 is configured to calculate the abnormality degree continuously in time.

In the present embodiment, when the evaluation value calculation unit 160 processes the vibration waveform data of the bearing 60 within a fixed time, the evaluation value calculation unit 160 divides the vibration waveform data into a plurality of segments and processes each segment. The segments will be described below.

FIG. 11 is a conceptual diagram showing the relationship between the vibration waveform data of the bearing 60 and the segment within a certain period of time. In the example of FIG. 11, the vibration waveform data within a certain period of time is the vibration waveform data D0 to D9 for 10 seconds, as in the example of FIG. The vibration waveform data D0 to D9 for 10 seconds are divided into 10 segments.

The anomaly degree calculation unit 164 generates a feature amount vector for each segment for the vibration waveform data D0 to D9 for 10 seconds. Similarly, the learning unit 162 also generates a feature amount vector for each segment of the learning data read from the normal data storage unit 136.

FIG. 12 is a diagram for explaining the feature quantity vector. FIG. 12 shows an example in which the vibration waveform data D0 to D9 for 10 seconds are divided into 10 segments and the feature amount is n.

The features are, for example, the effective value (OA), maximum value (Max), crest value (Crest factor), kurtosis, skewness, and the value after these signal processing (FFT processing, kefrency processing) of the vibration waveform data. Can be. The feature quantity vector treats n feature quantities as a set of vectors. The feature vector is used for abnormality determination. In the example of FIG. 12, 10 feature amount vectors are generated for the vibration waveform data D0 to D9 for 10 seconds.

If the feature amount is extracted and the feature amount vector is generated by collecting the entire vibration waveform data within a certain period of time, the entire data may not be usable for diagnosis when a sudden abnormality occurs. Therefore, in the present embodiment, the vibration waveform data within a certain period of time is divided into a plurality of segments, and the feature amount is extracted and the feature amount vector is generated in units of the segment data. For example, when the wind power generation device 10 is being monitored by the vibration sensor 70, sudden vibration may be temporarily detected by the vibration sensor 70. Even in such a case, the correct feature amount can be extracted at a time other than the sudden abnormality. Therefore, it is also possible to exclude the segment data corresponding to the sudden abnormality and compare and evaluate the feature amount for each segment data.

As shown in FIG. 12, the anomaly degree 0 to 9 is calculated for the feature quantities vectors 0 to 9 based on the classification boundary. The classification boundary is an index for performing anomaly discrimination used in a known anomaly detection method (One Class Support Vector Machine: OC-SVM).

FIG. 13 is a diagram for explaining the basic concept of OC-SVM. The vertical axis and the horizontal axis of FIG. 13 are feature quantities different from each other. In FIG. 13, the circle “◯” is the learning data, and the square mark “□” and the triangle mark “Δ” are the vibration waveform data. Of the vibration waveform data, "□" is data indicating an abnormality, and "Δ" is data indicating normality.

For example, as shown in FIG. 13 (A), on a two-dimensional scatter plot when there are two features, it is not possible to draw a boundary line that can classify normal / abnormal in the training data and vibration waveform data. Think.

On the other hand, useful features differ depending on the diagnosis target and operating conditions. Therefore, an appropriate feature amount is selected based on the diagnosis target and the operating conditions. By mapping each learning data and vibration waveform data to a multidimensional feature space containing appropriate features, it becomes possible to generate a classification interface that can classify normal / abnormal as shown in FIG. 13 (B). ..

For each learning data and vibration waveform data, the degree of abnormality, which is the distance from the classification boundary, can be calculated. The degree of abnormality is zero on the classification boundary, the degree of abnormality is a negative (-) value on the normal side of the classification boundary, and the degree of abnormality is a positive (+) value on the abnormal side of the classification boundary.

Such a method is called machine learning by OC-SVM, and it is possible to convert many features into one index (abnormality) and evaluate it.

Returning to FIG. 10, the learning unit 162 sets the above-mentioned classification boundary using the learning data. The anomaly degree calculation unit 164 calculates the anomaly degree 0 to 9, which is the distance from the classification boundary in the feature section, for each of the feature vectors 0 to 9.

The abnormality degree calculation unit 164 calculates the evaluation value E0 by subjecting the calculated abnormality degrees 0 to 9 to statistical processing. The calculation of the evaluation value corresponds to the process of step S12 in the control process shown in FIGS. 7, 8 and 9. The evaluation value E0 is a value (representative value) that characterizes the abnormalities 0 to 9 of the vibration waveform data for 10 seconds. Therefore, in the statistical processing, the average value of the abnormalities 0 to 9 can be calculated as the evaluation value E0. Alternatively, as the evaluation value E0, the median value, the mode value, the minimum value, etc. of the degree of abnormality 0 to 9 can be calculated.

Alternatively, in step S12 of FIGS. 7, 8 and 9, the abnormality rate can be calculated by comparing the abnormality determination threshold value set based on the learning data with each abnormality degree as the evaluation value E0. it can. The abnormality rate is obtained by dividing the number of abnormality degrees 0 to 9 in which the abnormality degree exceeds a predetermined abnormality determination threshold value by the total number of segments (10).

In this way, the evaluation value calculation unit 160 calculates the evaluation value (abnormality) of the vibration waveform data of the bearing 60 within a fixed time at predetermined time intervals. The evaluation value calculation unit 160 outputs the calculated evaluation value to the evaluation value trend storage unit 134.

As described with reference to FIG. 4, the evaluation value trend storage unit 134 stores the evaluation value (abnormality degree) given from the evaluation value calculation unit 160 every moment. In the present embodiment, a predetermined number of abnormalities that are continuous in time correspond to an "evaluation value trend" that represents a tendency of the degree of abnormality to change over time. The evaluation value trend storage unit 134 updates the evaluation value trend at predetermined time intervals.

Returning to FIG. 10, when the measurement trigger generation unit 170 reads out a predetermined number of abnormalities (evaluation values) that are continuous in time from the evaluation value trend storage unit 134, the measurement trigger generation unit 170 generates a measurement trigger based on the read evaluation value trend. To do. As described with reference to FIG. 5, the measurement trigger generation unit 170 generates a measurement trigger when it is determined that the evaluation value trend has changed. The generated measurement trigger is given to the vibration waveform data output unit 140.

As described with reference to FIG. 5, when the vibration waveform data output unit 140 receives the measurement trigger from the measurement trigger generation unit 170, the vibration waveform data output unit 140 is stored in the vibration waveform data storage unit 132 and is constant immediately before the measurement trigger is generated. The vibration waveform data of the bearing 60 in time is read out. The vibration waveform data output unit 140 further receives vibration waveform data of the bearing 60 from the time when the measurement trigger is generated from the effective value calculation unit 120. The vibration waveform data output unit 140 collectively outputs these vibration waveform data to the diagnosis unit 150.

The diagnosis unit 150 diagnoses the abnormality of the bearing 60 based on the vibration waveform data of the bearing 60 collected together.

As described above, according to the condition monitoring system according to the fourth embodiment, as an evaluation value for characterizing the vibration waveform data within a certain period of time, one index generated from a plurality of feature quantities extracted from the vibration waveform data. By using (abnormality), even if a plurality of feature quantities are individually changed, when the change occurs in a combination different from the usual one, the change can be captured. According to this, the vibration waveform data can be recorded even in a state where it is not possible to clearly define what kind of change is used as the measurement trigger.

Further, even if the vibration waveform data in the normal state has variation, it is recognized as a normal state by the machine learning by OC-SVM, so that it is possible to prevent the measurement trigger from being erroneously generated. .. Then, since the measurement trigger is generated when the tendency of the temporal change of the degree of abnormality is different from that in the normal state, a huge amount of data is accumulated, and the vibration waveform data when the abnormality occurs is surely and efficiently. Since it can be measured in an accurate manner, an accurate abnormality diagnosis can be realized.

In each of the above embodiments, the vibration sensor 70 is installed on the bearing 60, which is one of the mechanical elements constituting the wind power generator 10, to diagnose the abnormality of the bearing 60. It is confirmed that the mechanical element to be used is not limited to the bearing 60. For example, the vibration sensor is installed in the bearing 60 provided in the speed increaser 40 or the generator 50 together with the bearing 60 or in place of the bearing 60, and the speed increaser 40 is carried out by the same method as in each of the above embodiments. It is possible to diagnose an abnormality of the bearing provided inside or inside the generator 50.

Further, in each of the above embodiments, the configuration in which the evaluation value that characterizes the vibration waveform data within a certain period of time is calculated by statistically processing the effective value of the vibration waveform data within the certain time period has been described. The evaluation value may be calculated by statistically processing the peak value of the vibration waveform data within a certain period of time. In this configuration, the peak value of the vibration waveform data corresponds to the absolute value of the maximum value or the minimum value of the vibration waveform. Alternatively, the evaluation value may be calculated by statistically processing the crest rate of the vibration waveform data within the fixed time. In this configuration, the crest factor of the vibration waveform data corresponds to the ratio of the effective value to the maximum value of the vibration waveform.

Further, in each of the above embodiments, the evaluation value that characterizes the vibration waveform data within a certain period of time is set to one, and the measurement of the vibration waveform data is triggered by the change in the tendency of the temporal change of this one evaluation value. Although the configuration for starting the above has been described, the configuration may be triggered by a change in the tendency of a plurality of evaluation values to change over time.

Further, in each of the above embodiments, the data processing device 80 corresponds to one embodiment of the "processing device" in the present invention, and the storage unit 130, the evaluation value calculation unit 160, and the diagnosis unit 150 correspond to the "processing device" in the present invention. Corresponds to one embodiment of the "storage unit", the "evaluation value calculation unit", and the "diagnosis unit".

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

10 Wind power generator, 20 spindle, 30 blades, 40 speed increaser, 50 generator, 60 bearing, 70 vibration sensor, 80 data processor, 90 nacelle, 100 tower, 110 HPF, 120 effective value calculation unit, 130 storage unit , 132 Vibration waveform data storage unit, 134 Evaluation value trend storage unit, 136 Normal data storage unit, 140 Vibration waveform data output unit, 150 Diagnosis unit, 160 Evaluation value calculation unit, 162 Learning unit, 164 Abnormality calculation unit, 170 Measurement Trigger generator.

Claims (8)

A condition monitoring system that monitors the status of machine elements that make up a device.
A vibration sensor for measuring the vibration waveform of the machine element and
It is equipped with a processing device for diagnosing an abnormality of the mechanical element.
The processing device
An evaluation value calculation unit configured to continuously calculate evaluation values that characterize the vibration waveform data output from the vibration sensor within a certain period of time.
By starting the measurement of the vibration waveform data triggered by a change in the tendency of the temporal change of the evaluation value calculated by the evaluation value calculation unit, the abnormality of the machine element can be detected by using the vibration waveform data. A condition monitoring system that includes a diagnostic unit configured to make a diagnosis. The processing device further includes a storage unit for storing the vibration waveform data within the fixed time period.
The condition monitoring system according to claim 1, wherein the diagnostic unit acquires the vibration waveform data within the fixed time immediately before the time when the tendency of the temporal change of the evaluation value changes from the storage unit. The condition monitoring system according to claim 1 or 2, wherein the diagnostic unit detects that the temporal change rate of the evaluation value exceeds a threshold value and starts measuring the vibration waveform data. The diagnostic unit detects that the temporal change rate of the evaluation value is equal to or greater than the first threshold value and the magnitude of the evaluation value is equal to or greater than the second threshold value. The condition monitoring system according to claim 1 or 2, wherein the measurement of the vibration waveform data is started. The condition monitoring system according to any one of claims 1 to 4, wherein the evaluation value calculation unit calculates the evaluation value by statistically processing the vibration waveform data within a certain period of time. The evaluation value calculation unit
The vibration waveform data within the fixed time is divided into a plurality of segment data, and a feature quantity vector including a plurality of feature quantities is generated for each segment data.
Using the feature amount vector generated for the vibration waveform data when the device is normal, a classification boundary for classifying normal and abnormal is set.
For each of the plurality of feature quantity vectors generated for the vibration waveform data within the fixed time, the degree of abnormality, which is the distance from the classification boundary, is calculated.
The condition monitoring system according to any one of claims 1 to 4, wherein the evaluation value is generated by statistically processing a plurality of the abnormalities. The storage unit stores the vibration waveform data given by the vibration sensor at predetermined time intervals, and erases the oldest vibration waveform data among the stored vibration waveform data within the fixed time. , The condition monitoring system according to claim 2. A wind power generator comprising the condition monitoring system according to any one of claims 1 to 7.