Rotating machine vibration monitoring system and rotating machine vibration monitoring method

Abstract

To provide a rotating machine vibration monitoring system capable of detecting abnormal signs of a rotating machine with high sensitivity and greater accuracy, while using relatively inexpensive vibration sensors.SOLUTION: A rotating machine vibration monitoring system 100 comprises: vibration sensors 10 which are attached to one or more locations of each rotating machine to intermittently measure vibration at the attachment locations; an information processing device 30; and a data aggregation device 20 which aggregates measurement data from each vibration sensor 10, calculates vibration values at the attachment locations of the respective vibration sensors 10, and uploads them to the information processing device 30. The information processing device 30 has a function to receive and store vibration values uploaded from the data aggregation device 20, a function to calculate a variance of vibration values for a predetermined period at the attachment location of each vibration sensor 10 from the stored vibration values, a function to detect abnormal signs of a rotating machine when the variance exceeds a threshold, and a function to notify an alert related to the rotating machine in which abnormal signs are detected via an electric communication line.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to vibration monitoring of a moving machine, and more particularly to a monitoring method and system for detecting signs of abnormality in the moving machine from the vibration of the moving machine and issuing an alert. [Background technology]

[0002] Manufacturing lines and other industrial facilities use a large amount of moving machinery, including rotating and reciprocating equipment. Bearings are one of the most important components of these machines, and their health directly affects the operation of the entire facility. Bearings gradually deteriorate due to friction, metal fatigue, environmental conditions, and other factors, and can eventually fail. Bearing failure can result in production line shutdowns, reduced productivity, and expensive repair costs.

[0003] To prevent such incidents, it is important to continuously monitor vibrations, especially in bearings. Vibration analysis can provide valuable information about the condition of bearings and make it possible to detect early signs of abnormal wear or damage in advance. This allows for planned maintenance and part replacement to prevent production line stoppages due to mechanical failures and maintain equipment availability and productivity.

[0004] Furthermore, data collection and analysis through vibration monitoring contributes to maintaining the long-term health of moving machinery. The collected data can be used to predict bearing life and optimize maintenance schedules, ultimately reducing operating costs and improving production efficiency. In this way, vibration monitoring of moving machinery is an important means of detecting moving machinery failures before they occur and improving the reliability and sustainability of manufacturing lines and industrial facilities.

[0005] Regarding vibration monitoring of rotating equipment, a technique is known that predicts the presence or absence of signs of abnormality in the rotating equipment based on vibration data of the rotating equipment acquired at a predetermined timing and stored vibration data acquired in advance in a normal state of the rotating equipment corresponding to the operating data of the rotating equipment at the predetermined timing (see, for example, Patent Document 1).In addition, a technique is known that improves the accuracy of prediction of abnormalities in equipment by using a trained model trained by machine learning such as deep learning, so-called AI (see, for example, Patent Document 2). [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Japanese Patent Application Publication No. 2019-203788 [Patent Document 2] Japanese Patent Publication No. 2022-181896 Summary of the Invention [Problem to be solved by the invention]

[0007] The predictive accuracy of AI depends on the amount of training data, and if the amount of training data is small, it is difficult to achieve high accuracy. In this regard, with regard to vibration monitoring of moving machinery, there are challenges in preparing sufficient training data for the following reasons: 1) the high cost of continuous monitoring of moving machinery makes it difficult to monitor large numbers of moving machinery, and as a result, it is difficult to collect large amounts of data; 2) the low probability of machine failure makes it difficult to obtain data on abnormal events; and 3) the in-house training data must be prepared because data from other companies cannot be referenced. Furthermore, with AI, such as deep learning, the process from input to conclusion is a black box, and the criteria for judgment are unclear. Therefore, a trained model built for one moving machine cannot basically be used for another moving machine. As a result, a trained model must be built for each moving machine, which increases costs.

[0008] As mentioned above, instead of relying on AI, which has many challenges, we can consider an alternative approach: instead, we have the system detect signs of abnormalities in moving machinery using a simple method with clear criteria, such as issuing an alert when sensor values ​​exceed a threshold. Then, humans can use their experience and knowledge to determine the need for action by examining the vibration data of the machinery where abnormal signs were detected, particularly graphs showing daily trends in vibration values. This approach is not a precise diagnosis of moving machinery, but is specialized in anomaly screening. Therefore, expensive vibration sensors capable of detecting high-frequency vibrations or performing FFT analysis are not necessarily required, and inexpensive vibration sensors with limited functionality can be used. It is said that a factory of a certain size uses tens of thousands of bearings, so a system can be built by deploying a large number of inexpensive vibration sensors within the factory. The significance of deploying many vibration sensors throughout the facility to monitor moving machinery in this way is considered to be extremely great.

[0009] Even when using inexpensive vibration sensors, they need to be able to detect abnormal signs in moving machinery with high sensitivity. However, if you try to increase sensitivity carelessly by lowering the threshold, for example, there is a risk that the sensor will react to vibration noise and falsely detect abnormal signs due to simple judgment criteria. The more vibration sensors you use, the more false detections there will be, which will ultimately cause trouble for the equipment manager who is trying to determine abnormalities in the equipment.

[0010] SUMMARY OF THE INVENTION It is therefore an object of the present invention to provide a dynamic machine vibration monitoring system and method that can detect abnormal signs in dynamic machines with high sensitivity and accuracy using relatively inexpensive vibration sensors. [Means for solving the problem]

[0011] According to one aspect of the present invention, there is provided a dynamic machine vibration monitoring system for monitoring vibrations of one or more dynamic machines, comprising: vibration sensors attached to one or more locations on each dynamic machine and intermittently measuring the vibrations at those locations; an information processing device; and a data aggregation device that aggregates the measurement data of each vibration sensor, calculates vibration values ​​for the locations where each vibration sensor is attached, and uploads the calculated vibration values ​​to the information processing device, wherein the information processing device has the following functions: receiving and storing the vibration values ​​uploaded from the data aggregation device; calculating the variance of vibration values ​​for a predetermined period of time at the locations where each vibration sensor is attached from the stored vibration values; detecting abnormal signs in the dynamic machine when the variance exceeds a threshold; and notifying an alert regarding the dynamic machine in which an abnormal sign has been detected via a telecommunications line.

[0012] According to another aspect of the present invention, there is provided a dynamic machine vibration monitoring method for monitoring vibrations of one or more dynamic machines, the method comprising: a first step of automatically and intermittently measuring vibrations at one or more locations of each dynamic machine using vibration sensors attached to the respective locations; a second step of automatically aggregating the measurement data of each vibration sensor, automatically calculating vibration values ​​at the locations where each vibration sensor is attached, and automatically uploading the calculated vibration values ​​to an information processing device; a third step of having the information processing device receive and store the uploaded vibration values; a fourth step of having the information processing device calculate a variance of vibration values ​​for a predetermined period of time at the locations where each vibration sensor is attached from the stored vibration values; a fifth step of having the information processing device detect an abnormal sign in the dynamic machine if the variance exceeds a threshold; and a sixth step of having the information processing device issue an alert regarding the dynamic machine for which an abnormal sign has been detected, via a telecommunications line. [Effects of the Invention]

[0013] According to the present invention, it is possible to detect abnormal signs in moving machinery with high sensitivity and accuracy using a relatively inexpensive vibration sensor, which allows measures to be taken before the moving machinery breaks down, thereby improving the reliability of production lines and industrial facilities. [Brief explanation of the drawings]

[0014] [Figure 1] 1 is a schematic diagram of a dynamic mechanical vibration monitoring system according to an embodiment of the present invention; [Figure 2] 1 is a flowchart of a dynamic mechanical vibration monitoring method according to an embodiment of the present invention. [Figure 3] 10 is a graph comparing the detection sensitivity when abnormality indication detection is performed based on the maximum vibration value and when it is performed based on the variance of the vibration value. [Figure 4] FIG. 10 is a diagram illustrating the contents of an alert email according to an example. [Figure 5] FIG. 10 is a diagram illustrating an example of a vibration value graph displayed on a user terminal. DETAILED DESCRIPTION OF THE INVENTION

[0015] Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings as appropriate. However, more detailed description than necessary may be omitted. For example, detailed description of well-known matters or redundant description of substantially identical configurations may be omitted. This is to avoid unnecessary redundancy in the following description and to facilitate understanding by those skilled in the art. Note that the inventors provide the accompanying drawings and the following description to enable those skilled in the art to fully understand the present invention, and do not intend for them to limit the subject matter described in the claims.

[0016] <Embodiment> Fig. 1 is a schematic diagram of a dynamic mechanical vibration monitoring system according to one embodiment of the present invention. Fig. 2 is a flowchart of a dynamic mechanical vibration monitoring method according to one embodiment of the present invention. The dynamic mechanical vibration monitoring system 100 according to this embodiment monitors vibrations of dynamic machinery such as rotating machinery and reciprocating machinery, and if it detects signs of abnormality in the dynamic machinery, it notifies an equipment manager or the like by issuing an alert. Specifically, the dynamic mechanical vibration monitoring system 100 includes a vibration sensor 10, a data aggregating device 20, and an information processing device 30.

[0017] The vibration sensor 10 is a compact device incorporating a three-axis MEMS accelerometer and a magnetic sensor. Unlike piezoelectric or photoelectric sensors, the MEMS accelerometer is inexpensive because it neither precisely measures high-frequency vibrations nor performs FFT analysis. The vibration sensor 10 can be firmly attached by screws, adhesives, or other methods to the moving machinery whose vibration is to be monitored, such as rotating equipment such as pumps, blowers, and compressors (not shown) or reciprocating equipment such as reciprocating pumps and piston-type machines in production lines or industrial facilities, to measure the acceleration occurring at the installation location. The vibration at the installation location of the vibration sensor 10 can be determined from the difference between the maximum and minimum acceleration values ​​measured by the vibration sensor 10.

[0018] The vibration sensor 10 is preferably attached near the bearings of the moving machine. This is because bearing malfunctions can cause the moving machine to stop, and it is therefore important to detect signs of bearing malfunctions as early as possible in order to prevent equipment shutdowns. Multiple vibration sensors 10 may be attached to a single moving machine. For example, in the case of a cooling water pump, vibration sensors 10 may be attached to four locations: the fan section of the motor, the motor and pump sides of the motor-pump coupling device, and the pump impeller side. Furthermore, the number of moving machines to which the vibration sensor 10 can be attached is not limited to one. The vibration sensor 10 may be attached to multiple moving machines within the same factory or multiple factories, or even multiple factories of multiple companies.

[0019] The vibration sensor 10 is powered by a button battery and has a low-power short-range wireless communication function such as ZigBee (registered trademark). This allows it to be placed in places where power lines and communication lines cannot reach. The measurement data of the vibration sensor 10 is transmitted to the data aggregating device 20 via wireless communication.

[0020] Because the vibration sensor 10 is powered by a button battery, it is preferable to operate it intermittently so that it can continue to function for a long period of time without battery replacement. In other words, based on the idea that it is sufficient to detect signs of abnormalities in the moving machine, it is not necessary to monitor vibrations continuously for 24 hours. Instead, the vibration sensor 10 can be operated intermittently, such as every minute, every five minutes, or every hour, to measure the vibration of the moving machine at that time. Specifically, the vibration sensor 10 starts operation after a certain period of time has passed (YES in S11), performs measurements, for example, 480 times (approximately 2.23 seconds) at a sampling rate of 210 Hz, and transmits the obtained measurement data, including the maximum, minimum, and average acceleration values, to the data aggregating device 20 (S12). After the intermittent measurement is completed, the vibration sensor 10 goes into sleep mode until the next measurement to conserve battery power (NO in S13, S11). This allows the vibration sensor 10 to continue functioning for a long period of time, such as several years, without battery replacement.

[0021] The data aggregating device 20 aggregates measurement data from one or more vibration sensors 10, calculates vibration values ​​at the locations where each vibration sensor 10 is attached, and uploads the calculated vibration values ​​to the information processing device 30. Specifically, the data aggregating device 20 includes a short-range wireless communication device 21, a counting module 22, and an access point 23. The short-range wireless communication device 21 is a USB device that communicates with one or more vibration sensors 10 via short-range wireless communication to receive measurement data from each vibration sensor 10. The counting module 22 is connectable to one or more short-range wireless communication devices 21. Each time the counting module 22 receives measurement data from each vibration sensor 10 via the short-range wireless communication device 21 (YES in S21), the counting module 22 calculates the difference between the maximum and minimum acceleration values ​​included in the measurement data and uploads the calculated difference as a vibration value to the information processing device 30 (S22). The access point 23 is a relay device for communication between the counting module 22 and the information processing device 30. The access point 23 is connected to the counting module 22 on the downstream side via Wi-Fi (registered trademark) and to a telecommunications line 200, such as the Internet, on the upstream side. If the counting module 22 is directly connected to the telecommunications line 200, the access point 23 is not required.

[0022] The information processing device 30 is a computer device that collects, stores, and analyzes vibration values ​​uploaded from the data aggregating device 20 to detect signs of abnormalities in moving machinery. Specifically, the information processing device 30 is composed of a single computer device or a group of multiple computers, and is composed of, by role, a front-end server (not shown) that receives vibration values ​​uploaded from the aggregation module 22, accepts requests from user terminals (not shown), and provides information to the user terminals, a storage or database that accumulates the received vibration values, and a back-end server that performs various calculations on the accumulated vibration values. Note that it is not necessary to provide an individual information processing device 30 for each factory or company; a single information processing device 30 can receive measurement results from many vibration sensors 10 and perform vibration monitoring across factories and even companies.

[0023] The information processing device 30 receives and stores vibration values ​​uploaded from the data aggregating device 20 (S31). When vibration values ​​for a sufficiently long period have been stored, the information processing device 30 calculates the variance of vibration values ​​for a predetermined period from the stored vibration values ​​(S32). The predetermined period can be any period, but since moving machines are usually operated regularly every day, it is appropriate to set the predetermined period to, for example, one day to match such an operating cycle. In the following description, the variance is assumed to be the variance of vibration values ​​for one day.

[0024] Once the variance has been calculated, the information processing device 30 detects an abnormality sign of the moving machine if the variance exceeds a threshold value (S33). For example, a threshold value may be set that is four times the average variance of the vibration values ​​of a healthy moving machine, and if the variance exceeds the threshold value, the information processing device 30 detects that there is an abnormality sign in the moving machine to which the vibration sensor 10 is attached. If an abnormality sign is detected (YES in S34), the information processing device 30 notifies an administrator or the like of an alert regarding the moving machine in which an abnormality sign has been detected via the telecommunications line 200 (S35).

[0025] Figure 3 is a graph comparing the detection sensitivity of abnormality signs based on maximum vibration values ​​and vibration value variance. The graph shows the vibration trends measured by vibration sensor 10 over a one-year period from January 31 to January 30 for an actual rotating machine that operates 24 hours a day except on Sundays and also undergoes rotational speed control. The graph shows the maximum vibration value and the variance of the vibration values. The horizontal axis of the graph represents the date, the vertical axis represents the vibration value or variance, and the graph granularity is the day. The maximum vibration value is the maximum value of the vibration values ​​measured multiple times in a day, and the variance is the variance of the vibration values ​​for one day. The maximum vibration value and its 99th percentile value are represented by a line graph, and the variance is represented by a bar graph. In fact, this machine had scratches on the motor bearing balls. In other words, the graph shows an example of vibration trends when a malfunction occurs in the machine.

[0026] Focusing on the maximum vibration value in the same graph, it remains stable at a relatively low value below the warning level until late March, but begins to occasionally exceed the warning level from early April, frequently exceeding the warning level from mid-May to mid-December, and then settles back below the warning level from mid-December onwards. The vibration warning level is set at 2000 mG, twice the average normal vibration value of the machinery in question, which is 1000 mG. Meanwhile, focusing on the variance of daily vibration values, it remains stable at a relatively low value below the warning level until early March, but frequently exceeds the warning level on all days except Sundays from mid-March onwards. The variance warning level is set at 12000, four times the average variance of the machinery's normal vibration values, which is 3000.

[0027] In abnormal sign detection based on maximum vibration values, an abnormal sign is detected when the vibration values ​​obtained from the intermittently operating vibration sensor 10 exceed the alarm level (threshold) two consecutive times. For example, if the vibration sensor 10 operates at five-minute intervals, an abnormal sign is detected if the vibration value in one measurement exceeds the alarm level and then again in the next measurement five minutes later. In the example graph, an abnormal sign is first detected on April 7th, and is frequently detected thereafter until mid-December, but is no longer detected after mid-December. On the other hand, in abnormal sign detection based on the variance of daily vibration values, an abnormal sign is detected when the variance exceeds the alarm level (threshold). In the example graph, an abnormal sign is first detected on March 8th (see the enlarged view in the figure), and is frequently detected thereafter until the following day, January 30th, except on Sundays.

[0028] When comparing abnormal sign detection based on maximum vibration values ​​with abnormal sign detection based on the variance of one-day vibration values, the latter was able to detect abnormal signs approximately one month earlier than the former, and while the former did not detect any abnormal signs after mid-December, the latter continued to detect abnormal signs even after mid-December. From this, it can be said that by using the variance of one-day vibration values ​​as a measure of abnormal sign detection, it is possible to detect abnormal signs in moving machinery earlier, i.e. with higher sensitivity.

[0029] The threshold used as the basis for detecting abnormal signs may vary for each moving machine, and even for each location where the vibration sensor 10 is attached, even within the same moving machine. While thresholds may be set manually for all vibration sensors 10, appropriate thresholds can be automatically set by the information processing device 30. Specifically, the information processing device 30 can calculate the average of vibration values ​​measured by each vibration sensor 10 over several days when the moving machine is in a normal state, and set the threshold value to a value doubled or quadrupled. However, some moving machines are shut down overnight or change their rotation speed or reciprocating speed in response to load fluctuations during operation. In such moving machines, temporary large vibrations (shock vibrations) at startup or when the reciprocating speed is changed may act as noise, preventing the average vibration value in a normal state from being calculated appropriately. Therefore, the information processing device 30 may calculate the average of a predetermined percentile value, such as the 80th percentile value, of vibration values ​​measured by each vibration sensor 10 over several days when the moving machine is in a normal state, and set the threshold value to a value doubled or quadrupled. This makes it possible to more accurately determine the average vibration value in a normal state for a moving machine that is stopped periodically or irregularly and / or whose number of movements is changed, and to set an appropriate threshold value.

[0030] <Alert Notification> The alert from the information processing device 30 can be sent as a push notification to a dedicated app or by email to a pre-registered email address. Figure 4 shows the contents of an example alert email. The alert email contains a digest of the dynamic machines whose vibration values ​​and / or variances exceed the warning value and the dynamic machines whose vibration values ​​and / or variances exceed the danger value. An alert can be sent every time an abnormal sign is detected, or a daily alert can be sent by summarizing all abnormal sign detections for one day.

[0031] <Vibration data display> A user such as a facility manager can operate a user terminal (not shown) to request the information processing device 30 to display vibration data for any moving machine that is of concern among those for which an alert has been notified, or for any moving machine regardless of the alert. When the information processing device 30 receives the request from the user terminal, it can display the vibration data of the specified moving machine in graph or table format on the user terminal.

[0032] Figure 5 shows an example of a vibration graph displayed on a user terminal. The horizontal axis of the graph represents the date, the vertical axis represents the vibration value, and the graph granularity is days. Looking at the vibration status of a moving machine solely based on the maximum vibration value, one might suspect that the maximum vibration value frequently exceeds the warning level, indicating a sign of an abnormality in the equipment. However, in reality, the maximum vibration value may exceed the warning level due to the inclusion of vibration values ​​such as shock vibrations. Therefore, the information processing device 30 can display a predetermined percentile value of the vibration value, such as the 99th percentile value, on the user terminal along with the maximum vibration value. The 99th percentile value removes factors such as startup shocks, revealing the true vibration status of the moving machine. For example, in the example of Figure 5, the maximum vibration value frequently exceeds the warning level, suggesting an equipment abnormality. However, the 99th percentile value does not exceed the warning level, so it can be determined that there is no equipment abnormality.

[0033] Effect The dynamic machine vibration monitoring system 100 according to this embodiment uses a relatively inexpensive vibration sensor 10 and can detect signs of abnormality in a dynamic machine with higher sensitivity and accuracy than when detecting signs of abnormality using the maximum vibration value as a measure. For dynamic machines that are started and stopped and / or have their number of movements changed at least once a day, either regularly or irregularly, it is particularly effective to detect signs of abnormality using the variance of vibration values ​​as a measure.

[0034] <<Variations>> The vibration sensor 10 may be connected to the data aggregating device 20 by wire.

[0035] The vibration values ​​for a predetermined period used as the basis for calculating the variance are not limited to a single day's worth of vibration values. If the machine operates only during specific time periods, such as daytime or nighttime, the vibration values ​​may be those for several hours. Conversely, the vibration values ​​may be those for several days or even a week, which are longer than a single day. In this case, the automatic calculation of the threshold value used as the basis for detecting abnormal signs may be appropriately changed depending on the predetermined period used as the basis for calculating the variance. For example, when calculating the variance based on vibration values ​​for one week, the threshold value may be calculated based on vibration values ​​for one month, for example.

[0036] The information processing device 30 may be placed in a factory, that is, on the edge side, instead of being placed on the so-called cloud side on the Internet.

[0037] The vibration value calculated by the data aggregating device 10 is not limited to the difference between the maximum and minimum values ​​of acceleration included in the measurement data of the vibration sensor 10, i.e., the so-called Peak-to-Peak, but may be the root mean square (RMS) of the deviation of the maximum and minimum values ​​from a certain reference point (for example, the zero level). Alternatively, the absolute value of the deviation of the maximum and minimum values ​​from the reference point, i.e., Zero-to-Peak, may be used as the vibration value.

[0038] The vibration sensor 10 is not limited to an acceleration sensor; a speed sensor or a displacement sensor can also be used. For example, if a speed sensor or a displacement sensor is used as the vibration sensor 10, acceleration can be obtained by differentiating the measured speed or displacement. Alternatively, if a speed sensor or a displacement sensor is used as the vibration sensor 10, the peak-to-peak, RMS, zero-to-peak, etc. of the measured speed or displacement itself can be treated as vibration values ​​without obtaining acceleration, and signs of abnormality in the moving machine can be detected based on the variance of such vibration values.

[0039] Furthermore, the vibration sensor 10 may be an acceleration sensor, a velocity sensor, or a displacement sensor other than a MEMS sensor.

[0040] As described above, the embodiments have been described as examples of the technology of the present invention. For this purpose, the accompanying drawings and detailed description have been provided. Therefore, the components described in the accompanying drawings and detailed description may include not only components essential for solving the problem, but also components that are not essential for solving the problem in order to exemplify the above technology. Therefore, the fact that these non-essential components are described in the accompanying drawings or detailed description should not be interpreted as immediately indicating that these non-essential components are essential. Furthermore, because the above-described embodiments are intended to exemplify the technology of the present invention, various modifications, substitutions, additions, omissions, etc. may be made within the scope of the claims or their equivalents. [Explanation of symbols]

[0041] 100 Dynamic Mechanical Vibration Monitoring System 10 Vibration Sensor 20 Data Aggregation Device 30 Information processing equipment 200 Telecommunications Lines

Claims

1. A dynamic machine vibration monitoring system for monitoring vibrations of one or more dynamic machines, comprising: a vibration sensor attached to one or more locations of each of the moving machines and configured to intermittently measure vibrations at the respective locations; an information processing device; a data aggregating device that aggregates the measurement data of each vibration sensor, calculates vibration values ​​at the attachment points of each vibration sensor, and uploads the calculated vibration values ​​to the information processing device; The information processing device includes: a function of receiving and storing vibration values ​​uploaded from the data aggregating device; a function of calculating the variance of vibration values ​​for a predetermined period of time at the attachment points of each vibration sensor from the accumulated vibration values; a function of detecting an abnormal sign of the moving machine when the variance exceeds a threshold value; and a function to notify an alert regarding the moving machine that detects an abnormality sign via a telecommunications line. A dynamic mechanical vibration monitoring system.

2. The dynamic mechanical vibration monitoring system according to claim 1 , wherein the information processing device has a function of calculating the threshold value based on a predetermined percentile value of the vibration value.

3. 3. The dynamic machine vibration monitoring system according to claim 2, wherein the dynamic machine is a machine that is started and stopped and / or its number of movements is changed at least once during the predetermined period, either regularly or irregularly.

4. 1. A dynamic machine vibration monitoring method for monitoring vibrations of one or more dynamic machines, comprising: a first step of automatically and intermittently measuring vibrations at one or more locations of each of the moving machines using vibration sensors attached to the locations; a second step of automatically aggregating the measurement data of each vibration sensor, automatically calculating vibration values ​​at the attachment points of each vibration sensor, and automatically uploading the calculated vibration values ​​to an information processing device; a third step of causing the information processing device to receive and store the uploaded vibration values; a fourth step of causing the information processing device to calculate a variance of vibration values ​​for a predetermined period of time at the attachment points of each vibration sensor from the accumulated vibration values; a fifth step of causing the information processing device to detect an abnormality sign of the moving machine when the variance exceeds a threshold; a sixth step of causing the information processing device to issue an alert regarding the moving machine in which an abnormality symptom has been detected, via an electric communication line. A dynamic mechanical vibration monitoring method comprising:

5. 5. The dynamic mechanical vibration monitoring method according to claim 4, further comprising a seventh step of causing the information processing device to calculate the threshold value based on an average value of predetermined percentile values ​​of the vibration values.

6. 6. The dynamic machine vibration monitoring method according to claim 5, wherein the dynamic machine is a machine that is started and stopped and / or its number of movements is changed at least once during the predetermined period, either regularly or irregularly.

Images