JP6975679B2 - Rotating machine diagnostic system, information processing device and rotating machine diagnostic method - Google Patents

Description

The present invention relates to a rotary machine diagnostic system, an information processing device, and a rotary machine diagnostic method.

There is a technology that automatically diagnoses the operating status of various mechanical devices and detects abnormal conditions such as failures and signs.

For example, Patent Document 1 collects diagnostic operation control means for performing diagnostic operation in a plurality of modes after the occurrence of an earthquake is detected, and sounds in the hoistway when the car is running in each mode of the diagnostic operation. Sound collecting means for sound, abnormal sound reference value storage means for storing a plurality of abnormal sound reference values set for each mode of diagnostic operation, and abnormal sound reference for each mode stored in the abnormal sound reference value storage means. Based on the value, the abnormal sound is determined by the abnormal sound determining means for determining whether or not the sound collected by the sound collecting means is an abnormal sound, and the abnormal sound is generated in the hoistway when the car is run multiple times in the same mode of the diagnostic operation. By providing an abnormal sound information determining means for determining whether or not the sound is detected at the same position, the abnormal sound suitable for each mode is detected and the accidental false detection of the sound is prevented. Is described.

Further, in Patent Document 2, as a method of diagnosing an abnormality of a rotating part such as a bearing and improving its reliability, an abnormality of a rotating part such as a bearing is diagnosed in an actual operation state without disassembling the device, and a rotation driving means is provided. A method for preventing a false diagnosis due to the influence of electrical disturbance noise generated in the bearing is described. Specifically, when the rotary drive means is de-energized and the rotating component is inertially rotated within a predetermined rotational speed region, an abnormality of the rotating component is diagnosed based on a vibration detected by a sensor or a temperature detection signal.

Japanese Unexamined Patent Publication No. 2007-223750 Japanese Unexamined Patent Publication No. 2006-105956

It is required to monitor the operating status of various machines, devices, systems, etc. (hereinafter referred to as "diagnosis targets") at low cost and with high accuracy. Therefore, it has been studied to automatically monitor the status of the diagnosis target by attaching various sensors to the diagnosis target and analyzing the signals obtained from the sensors.

When the object of diagnosis is an industrial device such as an air compressor, the life of the sensing means such as a sensor is shorter than the life of the industrial device, and a method for ensuring the reliability of the sensor data is required. Therefore, it is conceivable to prepare an operation mode (diagnosis mode) for sensor diagnosis as in Patent Document 1 and Patent Document 2, but it is necessary to stop normal operation and perform diagnostic operation, and the actual operating time Will be shortened. It is also conceivable to use multiple sensors of the same type and determine the status of equipment abnormality, sensor abnormality, etc. by majority voting processing, averaging processing, etc., but the sensor installation cost increases.

Diagnosis of industrial equipment is desired without a decrease in operating rate due to the diagnostic mode and an increase in cost due to the installation of multiple sensors.

A rotary machine diagnostic system for an industrial device including a plurality of rotary machines, which is an embodiment of the present invention, includes a first rotary machine, a first vibration sensor attached to the first rotary machine, and an industrial device. A sensor data database that stores normal data of the first vibration sensor and sensor data of the first vibration sensor acquired during normal operation of the industrial equipment for each of the plurality of operation modes of the above, and a rotating machine included in the industrial equipment. It has an abnormality diagnosis unit that diagnoses bearing abnormalities, and the abnormality diagnosis unit includes sensor data in the first mode in which the first rotating machine is rotating among a plurality of operation modes, and normal data in the first mode. When the sensor data of the first mode is increased compared to the normal data of the first mode, the sensor data of the second mode in which the first rotating machine is stopped in the operation mode is compared with the sensor data of the second mode. Comparing with the normal data of the second mode, if the sensor data of the second mode is increased compared to the normal data of the second mode, the first rotating machine is normal and the first If it is determined that there is an abnormality in the vibration sensor and the sensor data in the second mode does not increase compared to the normal data in the second mode, there is an abnormality in the first rotating machine and the first vibration sensor. Is determined to be normal.

It is possible to diagnose industrial equipment without a decrease in operating rate due to the diagnostic mode and an increase in cost due to the installation of multiple sensors.

Other issues and novel features will become apparent from the description and accompanying drawings herein.

A conceptual diagram showing the situation where a sensor is mounted on a pneumatic machine. The figure which shows the operation mode pattern. The graph which shows the example of the detection signal of a vibration sensor. A block diagram showing the overall configuration of a rotary machine diagnostic system. A flow chart showing the flow of diagnostic processing performed by the edge calculation unit. A flow chart showing the flow of abnormality cause estimation performed by the edge calculation unit. A conceptual diagram showing the situation where a sensor is mounted on a pneumatic machine. A conceptual diagram showing the situation where a database is stored in a storage device. The figure which shows the operation mode pattern. A conceptual diagram showing an arrangement example of a pneumatic machine. A conceptual diagram showing an arrangement example of a pneumatic machine. A conceptual diagram showing an arrangement example of a pneumatic machine. A conceptual diagram showing an arrangement example of a pneumatic machine. A flow chart showing the flow of abnormality cause estimation performed by the edge calculation unit. A conceptual diagram showing the situation where a sensor is mounted on a cutting machine. A conceptual diagram showing a situation in which a sensor is mounted on a semiconductor manufacturing device. A layout diagram showing an example of a maintenance monitor displayed on a terminal.

Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. However, the present invention is not limited to the description of the embodiments shown below. It is easily understood by those skilled in the art that a specific configuration thereof can be changed without departing from the spirit of the present invention.

In the configurations of the examples described below, the same reference numerals may be used in common for parts having the same or similar functions, and duplicate description may be omitted. Further, when there are a plurality of elements having the same or similar functions, they may be described by adding different subscripts to the same reference numerals. At this time, if it is not necessary to distinguish between a plurality of elements, the description may be omitted by omitting the subscript. In addition, the position, size, shape, range, etc. of each configuration shown in the drawings may not necessarily reflect the actual position, size, shape, range, etc. in order to facilitate understanding of the invention. ..

In this embodiment, an example is a rotating machine that constitutes an air compressor (hereinafter referred to as "pneumatic machine") as a diagnosis target, and an example is a system in which a vibration sensor is attached to this rotating machine to remotely monitor an abnormality in the bearing of the rotating machine. Explain to. A specific example of a rotating machine is a motor, and a specific example of a vibration sensor is a MEMS (Micro Electro Mechanical Systems) sensor. The types of devices to be diagnosed and the types of sensors used are not limited to these.

<1. Diagnosis target (pneumatic machine)>
FIG. 1 is a conceptual diagram showing a situation in which a sensor is mounted on a pneumatic machine. Generally, the pneumatic machine includes a plurality of rotary machines, but for the sake of simplification of the explanation, the pneumatic machine 100 is provided with one rotary machine 102, and the rotary machine 102 is described here. It is assumed that the air in the air tank 106 is compressed through the air compression valve 104. The vibration sensor 108 may be retrofitted to the pneumatic machine 100. In the example of FIG. 1, the vibration sensor 108 is attached to the rotating machine 102. As long as the vibration caused by the rotation of the shaft of the rotating machine can be detected, the mounting location is not particularly limited. Further, the vibration sensor 108 may be composed of a plurality of sensors.

The pneumatic machine 100 has an operation mode determined based on the rotation / stop of the rotary machine 102. As described above, the pneumatic machine generally includes a plurality of rotary machines, and each rotary machine has two states of rotation and stop. Therefore, the operation mode of the pneumatic machine is (rotation). The number of aircraft x 2) will exist.

FIG. 2 is a diagram showing an operation mode in the pneumatic machine of FIG. In the example of FIG. 1, since there is only one rotating machine, the operation mode "operating" corresponds to the state in which the rotating machine 102 is rotating, and the operation mode "stop" corresponds to the state in which the rotating machine 102 is stopped. In this embodiment, the sensor data of the vibration sensor 108 detected in the operation modes “operation” and “stop” is used as a test pattern for determining the bearing abnormality of the rotating machine 102.

<2. Sensor data>
FIG. 3 is a graph showing an example of sensor data of the vibration sensor 108 in each of the two operation modes of the pneumatic machine of FIG. The pneumatic machine operates in two operation modes, start and stop, and there is a significant difference in the size of the acquired sensor data between the two operation modes. Time is displayed on the horizontal axis and acceleration is displayed on the vertical axis in FIG. As can be judged from the graph of FIG. 3, the magnitude of the acceleration differs by one digit or more between the operation mode and the stop mode. It can also be seen that the waveform patterns are also different.

<3. Diagnostic system configuration>
FIG. 4 is a block diagram showing a configuration of a rotary machine diagnostic system. The vibration sensor 108 is attached to the pneumatic machine 100, and the sensor data of the vibration sensor 108 is transmitted to the edge calculation unit 300 placed near the pneumatic machine 100. Further, the pneumatic machine 100 includes a control device 110 thereof, and control information such as an operation mode is also transmitted to the edge calculation unit 300. For example, an interface that outputs a control signal is used to output a control signal and transmit an operation mode.

The edge calculation unit 300 is a general information processing device including a storage device 301, an input device 302, a processing device (processor or CPU (Central Processing Unit) 303, an output device 305, and a bus 306 connecting them, for example. It can be configured with a microcomputer or a server. Functions such as calculation and control in the edge calculation unit are realized by the processing device 303 executing the program stored in the storage device 301 in cooperation with other hardware. NS. The processing device 303 includes an abnormality diagnosis unit 304 as a function, and is realized by the processing device 303 executing the program stored in the storage device 301. The diagnosis result by the abnormality diagnosis unit 304 is transmitted from the output device 305 to the central calculation unit 320 via the network 310.

The central arithmetic unit 320 can also be configured by a general microcomputer or server including a storage device 321, an input device 322, a processing device 323, an output device 325, and a bus 326 connecting them. The processing device 323 includes an operation screen display unit 324 as a function, and displays the operation screen on the terminal 330 via the output device 325.

The communication between the vibration sensor 108 and the edge calculation unit 300 may be either wireless communication or wired communication. For ^{example, I 2 C (Inter-Integrated} Circuit) wired communication using a serial bus can be used. It may be wireless communication such as WiFi, Bluetooth (registered trademark), ZigBee (registered trademark) and the like. The interface required for communication is such that the vibration sensor 108 and the input device 302 each have a known configuration.

In this embodiment, the abnormality diagnosis unit 304 is included in the edge calculation unit 300, but may be included in the central calculation unit 320. In that case, the edge calculation unit 300 will transmit the sensor data to the central calculation unit 320 instead of the abnormality diagnosis result. Further, the edge calculation unit 300 and the central calculation unit 320 may be configured by a single computer, or any part of the input device, the output device, the processing device, and the storage device may be connected by a network. It may be composed of the computer of.

Further, the number of vibration sensors 108 is not limited to one, and a plurality of vibration sensors may be installed, for example, one for the bearing on the load side and one for the bearing on the non-load side. There may be a plurality of types of sensors such as a temperature sensor depending on the target of sensing. When having a plurality of sensors, the plurality of sensors may transmit the sensor data to one edge calculation unit 300, or may transmit the sensor data to another edge calculation unit (not shown).

Further, there may be a plurality of terminals 330. Further, the communication between the central calculation unit 320 and the terminal 330 may be either wireless communication or wired communication. In this embodiment, the operation screen display unit 324 assumes an HTML server, and outputs codes written in languages such as Javascript (registered trademark), CSS (Cascading Style Sheets), PHP, Ruby, and Java (registered trademark). do. The terminal 330 is supposed to be a tablet device which is a small computer, and is supposed to display an operation screen on a web browser.

A known general device can be appropriately applied to the storage device, the input device, the processing device, and the output device of this embodiment. For example, a magnetic disk device or various semiconductor memories can be applied as the storage device. As an input device, a keyboard, a mouse, or various input interfaces can be applied. As the output device, a display, a printer, or various output interfaces can be applied.

In the above description, the same functions as those configured by software can be realized by hardware such as FPGA (Field Programmable Gate Array) and ASIC (Application Specific Integrated Circuit).

<4. Diagnostic process flow>
FIG. 5 is a flow chart showing the flow of diagnostic processing performed by the edge calculation unit 300.
In the process S501, the vibration is measured by the vibration sensor 108 attached to the rotating machine 102 constituting the pneumatic machine 100, and the sensor data is acquired via the input device 302. Further, the operation mode information from the control device 110 is acquired via the input device 302. The acquired sensor data and operation mode information are stored in the storage device 301 for later processing. For the purpose of diagnosing bearing abnormality of a rotating machine, it is sufficient to periodically acquire sensor data for several seconds (for example, sensor data for 1 to 2 seconds every hour).

In the process S502, the operation mode of the sensor data is determined. As shown in FIG. 1, the compressed air generated by the pneumatic machine 100 is stored in the air tank 106, sent into equipment such as a factory, and used in another mechanical device. The pneumatic machine 100 performs on / off control so that the compressed air stored in the air tank 106 maintains a constant pressure level. This operation time is referred to as normal operation time. In general, normal operation refers to an operating state in which a device or equipment operates to achieve its original purpose, and is distinguished from other operating conditions in which, for example, operation is performed solely for diagnosis, inspection, repair, or maintenance. .. During this normal operation, the pneumatic machine 100 has two operation modes as shown in FIG. These two operation modes are distinguished and collected as a sensor data database (DB) 3011 for each operation mode. The sensor data database (DB) 3011 may be an independent database for each operation mode.

In the process S503, an abnormality is diagnosed for each rotating machine. As a method for determining an abnormality based on sensor data, various known methods can be adopted. For example, threshold determination, deep learning, reinforcement learning, or Bayesian networks can be used. The details will be described later with reference to FIG.

In the process S504, the abnormality diagnosis result performed in the process S503 is transmitted from the output device 305 to the central calculation unit 320 via the network 310. The central calculation unit 320 causes the terminal 330 to display the abnormality diagnosis result.

<5. Abnormal diagnosis>
The abnormality diagnosis method executed by the abnormality diagnosis unit 304 in the process S503 will be described. A monitoring function may be installed in the diagnosis target such as a pneumatic machine, but a sensor may be retrofitted. According to the abnormality diagnosis method of this embodiment, it is possible to diagnose the abnormality and estimate the cause of the abnormality even with a sensor attached later. FIG. 6 shows a flow chart showing a flow of bearing abnormality diagnosis of a rotating machine executed by the edge calculation unit 300 in the process S503. The bearing abnormality diagnosis is periodically executed based on the data accumulated in the sensor data DB 3011. For example, it is executed once a day or once a week.

In the process S601, the sensor data when the operation mode of the pneumatic machine is in operation is acquired from the sensor data DB 3011. In the process S602, it is determined whether or not the sensor data is increased, decreased, or disappeared as compared with the normal data (operation). Normal data is data that serves as a reference for determining whether or not there is an abnormality in the sensor data. Sensor data acquired when the normal operation of both the rotating machine and the sensor is confirmed, for example, when installing or maintaining the rotating machine. Is. This normal data is also held for each operation mode of the pneumatic machine. Since it is desirable to use the sensor data at the newest time as a reference for the abnormality diagnosis, it is desirable to update the data in normal times at the timing of maintenance of the pneumatic machine, for example. In the process S602, if the sensor data acquired in the process S601 has a certain deviation from the normal data (operation mode: operation), the sensor data is determined to be equivalent to the normal data, and the rotating machine (bearing) and the sensor are determined. Both are determined to be normal (S603). If it is not equivalent to normal data, the diagnosis depends on whether the sensor data is increasing, decreasing or disappearing.

When the operation mode of the pneumatic machine is operating, the sensor data is higher than normal, the vibration generated in the rotating machine is large due to the failure of the bearing of the rotating machine, and the rotating machine itself. Is normal and the vibration generated in the rotating machine is not different from that in normal times, but there are two possible cases where the sensor is abnormal and the sensor data is higher than in normal times. For this determination, the process proceeds to process S604, and the sensor data when the operation mode of the pneumatic machine is stopped is acquired from the sensor data DB 3011. Even when the rotating machine 102 to which the sensor 108 is attached is stopped, the sensor 108 detects vibration from surrounding devices (see FIG. 3). In the process S605, it is determined whether or not the sensor data is increased as compared with the normal data (stop). When the sensor data is increasing, in this case, since the rotating machine 102 is stopped, it is determined that the rotating machine is normal and the sensor is abnormal (S606). It is presumed that the causes of the sensor abnormality include mechanical deterioration of the sensor element, noise generation due to insufficient shield of the cable, noise generation in communication, looseness of sensor mounting, peeling and the like. If the process S605 is negative, it can be considered that the sensor has correctly detected the stop of the rotating machine, so that the rotating machine has an abnormality and the sensor is determined to be normal (S607).

On the other hand, when the sensor data is reduced or disappears in the process S602 as compared with the normal data (operation), it is determined that the rotating machine is normal and that the sensor has an abnormality (S608). This is because if an abnormality occurs in the bearing of the rotating machine, it always works in the direction of increasing the vibration. Causes of sensor abnormalities include mechanical and electrical deterioration of sensor elements, deterioration of capacitors and semiconductors on the board, corrosion of the board, noise generation due to insufficient cable shield, looseness, disconnection, gateway failure, battery exhaustion, etc. It is estimated that there is a power failure such as a power outage, noise is generated during communication, the sensor is loosely attached, and the sensor is peeled off. The increase, decrease, and disappearance of the sensor data are determined based on the increase, decrease, and disappearance of one or both of the amplitude component and the frequency component of the vibration.

In the above example, the example in which the pneumatic machine 100 has one rotary machine has been described, but as described above, the pneumatic machine 100 usually has a plurality of rotary machines. This embodiment can be easily extended even in such a case.

FIG. 7 shows an example of a pneumatic machine 100 composed of a motor (rotating machine a) 102a, a one-stage side screw (rotating machine b) 102b, and a two-stage side screw (rotating machine c) 102c. As shown in FIG. 7, a vibration sensor 108a is installed on the motor 102a, a vibration sensor 108b is installed on the first-stage screw 102b, and a vibration sensor 108c is installed on the second-stage screw 102c, each of which outputs sensor data. In this way, the vibrations of the plurality of rotating machines included in one pneumatic machine 100 are measured by different vibration sensors, and the sensor data is stored for each sensor.

As shown in FIG. 8, each sensor data is determined by the same method as described above, and the operation mode of the pneumatic machine 100 is determined, and the sensor data is stored in the storage device 301 as a sensor data database 3011 for each operation mode. NS.

As shown in FIG. 9, when the pneumatic shown in FIG. 7, on the basis of the rotation / stop of the rotating machine, the operation mode is present 2 ^{3 =} 8 pattern. The operation mode in which all the rotating machines are stopped is referred to as a stop mode, and the operation mode in which any of the rotating machines is rotated is referred to as an operation 1 to an operation 7 mode, respectively. In this case as well, the bearing abnormality of each rotating machine can be diagnosed according to the flowchart of FIG. Normal time data is also acquired and held for each operation mode (stop, operation 1 to operation 7) as described above.

First, in order to diagnose the bearing abnormality of the motor (rotating machine a) 102a, the sensor data of the operation mode "operation 4" in the process S601 is used as a test pattern, and the sensor data of the operation mode "operation 5" in the process S604 is used as a test pattern. Is desirable. This is because in the process S601, it is more preferable that only the rotating machine of interest is in operation because the influence from other rotating machines can be minimized. Further, in the process S604, it is more preferable that only the rotating machine of interest is stopped because the influence of vibration from other rotating machines can be as large as possible. However, it is possible to use any of the sensor data of the operation modes of the operation mode 1 to the operation 4 in which the rotary machine a is rotating in the process S601 as a test pattern, and similarly, the rotary machine a is stopped in the process S604. It is possible to use the sensor data of the operating modes 5 to 7 and stopped operating as a test pattern.

Similarly, in order to diagnose the bearing abnormality of the one-stage screw (rotating machine b) 102b, the sensor data of the operation mode "operation 6" is tested in the process S601, and the sensor data of the operation mode "operation 3" is tested in the process S604. It is desirable to use it as a pattern. Further, in order to diagnose the bearing abnormality of the two-stage screw (rotating machine c) 102c, the sensor data of the operation mode "operation 7" is tested in the process S601, and the sensor data of the operation mode "operation 2" is tested in the process S604. It is desirable to use it as a pattern.

Furthermore, the pneumatic system is generally operated by controlling the number of multiple units. Therefore, in the above description, an example of defining the operation mode based on the rotation / stop of the rotating machine is shown, but it is also possible to define the operation mode based on the state of the number control.

FIG. 10 is a diagram showing a configuration example of a system operated by controlling the number of a plurality of units. For example, constant speed base load machine two and (100-1, 100-2), if the number control by variable speed of the load absorbing unit two (100-3,100-4), operation mode ² 4 = There are 16 ways. Although FIG. 10 shows an example in which four pneumatic machines are arranged linearly, the arrangement may be two stages × two rows as shown in FIG. 11 or an L-shaped arrangement as shown in FIG. , The G-shaped arrangement may be used as shown in FIG. There are various variations in the arrangement method depending on the number of units, but from the pneumatic machine or motor adjacent to the vibration sensors 108-1, 108-2, 108-3, 108-4, ..., 108-N. An arrangement in which vibration is easily transmitted is preferable.

In the flow of FIG. 6, the presence / absence of an abnormality and the cause of the abnormality were diagnosed based on the sensor data from the sensor attached to the rotating machine, but the abnormality was made based on the sensor data from the sensor attached to the rotating machine other than the rotating machine of interest. It is also possible to diagnose the presence or absence of the abnormality and the cause of the abnormality. As a result, even if it is difficult to determine the presence or absence of an abnormality and the cause of the abnormality only from the output of a certain sensor, or if an abnormality occurs in a sensor attached to a certain rotating machine, the sensor of another rotating machine can be used. , The presence or absence of abnormality in the rotating machine and the sensor itself, and the cause of the abnormality can be determined. When this method is adopted, it is better that the vibration transmission between the sensor of the rotating machine to be diagnosed and the sensor of another rotating machine is as good as possible. As an example, the physical distance between the two should be as close as possible. FIG. 14 is a flow chart showing a flow of bearing abnormality diagnosis of the rotating machine executed by the edge calculation unit 300 in the process S503 (FIG. 5), based on sensor data from sensors attached to the rotating machine other than the rotating machine of interest. An example of diagnosing the presence or absence of an abnormality and the cause of the abnormality is shown. The rotating machine to be diagnosed is called a rotating machine of interest, and a rotating machine equipped with a sensor that uses sensor data is called a sensor-mounted rotating machine. For example, in the example of FIG. 10, when the diagnosis is made by the combination of the pneumatic machine 100-1 and the vibration sensor 108-2, the rotating machine of interest is the rotating machine of the pneumatic machine 100-1 and the sensor-mounted rotating machine is the vibration sensor 108-2. Is a rotating machine attached.

The flow diagram of FIG. 14 has the same concept as the flow diagram of FIG. Hereinafter, the feature portion will be described. In the process S1401, the sensor data of the operation mode (here, referred to as the first operation mode) in which the rotating machine of interest is rotating and the sensor-mounted rotating machine is stopped is acquired, and this is compared with the normal data of the first operation mode. (S1402). When selecting the first operation mode, it is important to select the operation mode in which the other rotating machines (pneumatic machine 100-3, pneumatic machine 100-4) are stopped, which is the rotating machine of interest (pneumatic machine 100-1). It can be said that it is more preferable because it is easier to judge the state of) more accurately. Similarly, in the process S1404, the sensor data of the operation mode (here, referred to as the second operation mode) in which the rotating machine of interest is stopped and the sensor-mounted rotating machine is stopped is acquired, and this is used in normal times in the second operation mode. Compare with the data (S1405). When selecting the second operation mode, selecting the operation mode in which the other rotating machines (pneumatic machine 100-3, pneumatic machine 100-4) are operating causes greater vibration from surrounding devices. It can be said that it is more preferable because it is considered to be.

In the flow chart of FIG. 14, the presence / absence of abnormality and the presence / absence of abnormality not only from the sensor data from the sensor mounted on one sensor-mounted rotary machine but also from the sensor data of the plurality of sensors mounted on the plurality of rotary machines. It is also possible to determine the cause of the abnormality. For example, in the configuration of FIG. 10, the presence / absence of an abnormality and the cause of the abnormality are determined by the combination of the pneumatic machine 100-1 and the vibration sensors 108-2, 108-3, 108-4. In the first operation mode in this case, the rotating machine of interest (pneumatic machine 100-1) is rotating, and the sensor-mounted rotating machine (pneumatic machine 100-2, 100-3, pneumatic machine 100-4) is stopped. It becomes the operation mode. Further, the second operation mode is an operation mode in which all the rotating machines (pneumatic machine 100-1, pneumatic machine 100-2, 100-3, pneumatic machine 100-4) are stopped.

Although the embodiment has been described above using the pneumatic machine as an example, it is possible to diagnose the abnormality of the bearing even for a device having a rotating machine other than the pneumatic machine. As another example, an example of bearing abnormality diagnosis of a cutting machine will be described. A cutting machine is a device that cuts or grinds a workpiece using a cutting tool, and includes, for example, a drilling machine, a milling machine, a machining center, and an NC (Numerically Control) lathe.

FIG. 15 shows an example (part) of a cutting machine equipped with a drill 161 as a cutting tool. The drill 161 is held by the drill holding portion 162. The drill holding portion 162 descends while rotating the drill 161 so that the drill 161 and the work 163 come into contact with each other to perform drilling. A vibration sensor 108v is attached to the drill holding portion 162 in order to monitor the abnormality of the cutting machine. This device also has two operation modes, operation and stop, and it is possible to detect a bearing abnormality and diagnose the cause of the abnormality based on the sensor signal obtained from the sensor 108v.

As yet another example, an example of application to a semiconductor manufacturing apparatus or a semiconductor inspection apparatus will be described. Here, the semiconductor manufacturing apparatus is an apparatus provided with a vacuum chamber, for example, a metal vapor deposition apparatus, a sputtering apparatus, a plasma CVD (Chemical Vapor Deposition) apparatus, and an ICP (Inductively Coupled Plasma). There are etching equipment, RIE (Reactive Ion Etching) equipment, ashing equipment, electron beam drawing equipment, FIB (Focused Ion Beam) equipment, and the like. Further, the semiconductor inspection device is also a device provided with a vacuum chamber, and examples thereof include an SEM (Scanning Electron Microscope) and a TEM (Transmission Electron Microscope).

FIG. 16 shows an example of the configuration of a semiconductor manufacturing apparatus / semiconductor inspection apparatus provided with a rough pulling pump and a main pulling pump. The rough pulling scroll pump 171 and the main pulling turbo molecular pump 172 are connected to the vacuum chamber 175 through the rough pulling valve 173 and the main pulling valve 174, respectively, as shown in the figure. In order to reduce the back pressure of the turbo molecular pump 172, the scroll pump 171 is connected to the turbo molecular pump 172 through a back pressure valve 176. A vibration sensor 108v is attached to the scroll pump 171 in order to monitor the abnormality of the rotary bearing included in the scroll pump 171. This device also has two operation modes, operation and stop, and it is possible to detect a bearing abnormality and diagnose the cause of the abnormality based on the sensor signal obtained from the sensor 108v.

An example of an interface in which an equipment observer (hereinafter referred to as a vendor) of a maintenance company monitors the equipment of each factory and displays the maintenance status by using the rotary machine diagnostic system described above is shown. Vendors monitor one or more factories at the same time and can provide users with timely repairs (or maintenance) depending on equipment status.

FIG. 17 is an example of a maintenance management monitor displayed on the terminal 330. The vendor can grasp the device status and the maintenance status through the maintenance management monitor 191 displayed on the terminal 330 shown in FIG. The device status window 192 displays the device error status and the probable cause. The assumed abnormality cause is estimated by the process S503 of FIG. 5, and the estimation result is sent to the terminal 330.

The repair proposal status is displayed in the maintenance status window 193. When the vendor presses an email, phone, fax, or mail button, each contact method is used to send a repair proposal to the user. In addition, the name of the maintenance staff in charge and the schedule of the maintenance staff in charge are displayed in the maintenance status window 193. The vendor can confirm the maintenance staff's schedule and contact the user for repair proposals, which enables quick decision on the repair schedule. In addition, the number of repair parts in stock is displayed in the maintenance status window. When the vendor presses the order button 194, the order information is transmitted to each component manufacturer. Since the vendor can manage the inventory of parts required for repair after checking the equipment status, the efficiency of inventory management can be improved. For example, when the occurrence of a device failure is detected, the delivery time of repair can be shortened by securing the inventory of necessary members in advance. In addition, it is possible to reduce the assets owned by the maintenance company by keeping a small inventory of materials necessary for failures that occur infrequently (for example, failures that occur once every 10 years). , ROE (return on equity) will be improved.

By using the configuration of this implementation and diagnosing bearing abnormalities of rotating machines in consideration of the operation mode, it is possible to suppress the decrease in operating rate due to the diagnostic mode and the cost increase due to the installation of multiple sensors, and to diagnose equipment abnormalities and sensor abnormalities. become.

The present invention is not limited to the above-described embodiment, and includes various modifications. For example, it is possible to replace a part of the configuration of one embodiment with the configuration of another embodiment, and it is possible to add the configuration of another embodiment to the configuration of one embodiment. Further, it is possible to add / delete / replace the configurations of other embodiments with respect to a part of the configurations of each embodiment.

100: Pneumatic machine, 102: Rotating machine, 104: Air compression valve, 106: Air tank, 108: Vibration sensor, 110: Control device, 300: Edge calculation unit, 301, 321: Storage device, 302, 322: Input device , 303, 323: processing device, 304: abnormality diagnosis unit, 324: operation screen display unit, 305, 325: output device, 306, 326: bus, 310: network, 320: central calculation unit, 330: terminal.

Claims (18)

A rotating machine diagnostic system for industrial equipment including multiple rotating machines.
With the first rotating machine,
The first vibration sensor attached to the first rotating machine and
A sensor data database that stores normal data of the first vibration sensor and sensor data of the first vibration sensor acquired during normal operation of the industrial equipment for each of a plurality of operation modes of the industrial equipment.
It has an abnormality diagnosis unit for diagnosing bearing abnormalities of rotating machines included in the industrial equipment.
The abnormality diagnosis unit compares the sensor data of the first mode in which the first rotating machine is rotating among the plurality of operation modes with the normal data of the first mode.
When the sensor data of the first mode is increased as compared with the normal data of the first mode, the sensor of the second mode in which the first rotating machine is stopped among the plurality of operation modes. Comparing the data with the normal data of the second mode,
When the sensor data of the second mode is increased as compared with the normal data of the second mode, it is determined that the first rotating machine is normal and the first vibration sensor has an abnormality. death,
When the sensor data of the second mode is not increased as compared with the normal data of the second mode, it is determined that the first rotating machine has an abnormality and the first vibration sensor is normal. Rotating machine diagnostic system. In claim 1,
When the sensor data of the first mode is equivalent to the normal data of the first mode, it is determined that both the first rotating machine and the first vibration sensor are normal.
When the sensor data of the first mode is reduced or disappears as compared with the normal data of the first mode, the first rotating machine is normal and the first vibration sensor is abnormal. Rotating machine diagnostic system that determines. In claim 1,
The first mode is an operation mode in which the first rotating machine is rotated and other rotating machines other than the first rotating machine are stopped.
The second mode is a rotary machine diagnostic system, which is an operation mode in which the first rotary machine is stopped and other rotary machines other than the first rotary machine are rotating. In claim 1,
Has a second rotating machine,
In the abnormality diagnosis unit, the sensor data of the third mode in which the second rotating machine is rotating and the first rotating machine is stopped among the plurality of operation modes and the normal time of the third mode. Compare with the data,
When the sensor data of the third mode is increased as compared with the normal data of the third mode, both the second rotating machine and the first rotating machine of the plurality of operation modes are stopped. The sensor data of the 4th mode is compared with the normal data of the 4th mode.
When the sensor data of the fourth mode is increased as compared with the normal data of the fourth mode, it is determined that the second rotating machine is normal and that the first vibration sensor has an abnormality. death,
When the sensor data of the fourth mode is not increased as compared with the normal data of the fourth mode, it is determined that the second rotating machine has an abnormality and the first vibration sensor is normal. Rotating machine diagnostic system. In claim 4,
When the sensor data of the third mode is equivalent to the normal data of the third mode, it is determined that both the second rotating machine and the first vibration sensor are normal.
When the sensor data of the third mode is reduced or disappears as compared with the normal data of the third mode, the second rotating machine is normal and the first vibration sensor is abnormal. Rotating machine diagnostic system that determines. In any one of claims 1 to 5,
A rotary machine diagnostic system in which a plurality of operation modes of the industrial equipment are determined based on a combination of rotation or stop for each of the plurality of rotary machines. In any one of claims 1 to 5,
The plurality of operation modes of the industrial equipment is a rotary machine diagnostic system defined based on the number control of the industrial equipment. In any one of claims 1 to 5,
The normal data is a sensor data acquired at the time of installation or maintenance of the rotary machine, which is a rotary machine diagnostic system. An information processing device for diagnosing an abnormality of a rotating machine in an industrial device having a plurality of rotating machines including a first rotating machine to which a first vibration sensor is attached.
A sensor data database that stores normal data of the first vibration sensor and sensor data of the first vibration sensor acquired during normal operation of the industrial equipment for each of a plurality of operation modes of the industrial equipment.
It has an abnormality diagnosis unit for diagnosing bearing abnormalities of rotating machines included in the industrial equipment.
The abnormality diagnosis unit compares the sensor data of the first mode in which the first rotating machine is rotating among the plurality of operation modes with the normal data of the first mode.
When the sensor data of the first mode is increased as compared with the normal data of the first mode, the sensor of the second mode in which the first rotating machine is stopped among the plurality of operation modes. Comparing the data with the normal data of the second mode,
When the sensor data of the second mode is increased as compared with the normal data of the second mode, it is determined that the first rotating machine is normal and the first vibration sensor has an abnormality. death,
When the sensor data of the second mode is not increased as compared with the normal data of the second mode, it is determined that the first rotating machine has an abnormality and the first vibration sensor is normal. Information processing device. In claim 9.
When the sensor data of the first mode is equivalent to the normal data of the first mode, it is determined that both the first rotating machine and the first vibration sensor are normal.
When the sensor data of the first mode is reduced or disappears as compared with the normal data of the first mode, the first rotating machine is normal and the first vibration sensor is abnormal. Information processing device that determines. In claim 9.
The first mode is an operation mode in which the first rotating machine is rotated and other rotating machines other than the first rotating machine are stopped.
The second mode is an information processing device which is an operation mode in which the first rotating machine is stopped and other rotating machines other than the first rotating machine are rotating. In claim 9.
The industrial equipment has a second rotating machine.
In the abnormality diagnosis unit, the sensor data of the third mode in which the second rotating machine is rotating and the first rotating machine is stopped among the plurality of operation modes and the normal time of the third mode. Compare with the data,
When the sensor data of the third mode is increased as compared with the normal data of the third mode, both the second rotating machine and the first rotating machine of the plurality of operation modes are stopped. The sensor data of the 4th mode is compared with the normal data of the 4th mode.
When the sensor data of the fourth mode is increased as compared with the normal data of the fourth mode, it is determined that the second rotating machine is normal and that the first vibration sensor has an abnormality. death,
When the sensor data of the fourth mode is not increased as compared with the normal data of the fourth mode, it is determined that the second rotating machine has an abnormality and the first vibration sensor is normal. Information processing device. In claim 12,
When the sensor data of the third mode is equivalent to the normal data of the third mode, it is determined that both the second rotating machine and the first vibration sensor are normal.
When the sensor data of the third mode is reduced or disappears as compared with the normal data of the third mode, the second rotating machine is normal and the first vibration sensor is abnormal. Information processing device that determines. It is a rotary machine diagnostic method for diagnosing an abnormality of a rotary machine for an industrial device having a plurality of rotary machines including a first rotary machine to which a first vibration sensor is attached.
The normal data of the first vibration sensor is stored in advance for each of the plurality of operation modes of the industrial equipment.
For each of the plurality of operation modes of the industrial equipment, the sensor data of the first vibration sensor is acquired during the normal operation of the industrial equipment.
Among the plurality of operation modes, the sensor data of the first mode in which the first rotating machine is rotating is compared with the normal data of the first mode.
When the sensor data of the first mode is increased as compared with the normal data of the first mode, the sensor of the second mode in which the first rotating machine is stopped among the plurality of operation modes. Comparing the data with the normal data of the second mode,
When the sensor data of the second mode is increased as compared with the normal data of the second mode, it is determined that the first rotating machine is normal and the first vibration sensor has an abnormality. death,
When the sensor data of the second mode is not increased as compared with the normal data of the second mode, it is determined that the first rotating machine has an abnormality and the first vibration sensor is normal. Rotating machine diagnostic method. In claim 14,
When the sensor data of the first mode is equivalent to the normal data of the first mode, it is determined that both the first rotating machine and the first vibration sensor are normal.
When the sensor data of the first mode is reduced or disappears as compared with the normal data of the first mode, the first rotating machine is normal and the first vibration sensor is abnormal. Rotating machine diagnostic method to determine. In claim 14,
The first mode is an operation mode in which the first rotating machine is rotated and other rotating machines other than the first rotating machine are stopped.
The second mode is a rotary machine diagnostic method, which is an operation mode in which the first rotary machine is stopped and other rotary machines other than the first rotary machine are rotating. In claim 14,
The industrial equipment has a second rotating machine.
Among the plurality of operation modes, the sensor data of the third mode in which the second rotating machine is rotating and the first rotating machine is stopped is compared with the normal data of the third mode.
When the sensor data of the third mode is increased as compared with the normal data of the third mode, both the second rotating machine and the first rotating machine of the plurality of operation modes are stopped. The sensor data of the 4th mode is compared with the normal data of the 4th mode.
When the sensor data of the fourth mode is increased as compared with the normal data of the fourth mode, it is determined that the second rotating machine is normal and that the first vibration sensor has an abnormality. death,
When the sensor data of the fourth mode is not increased as compared with the normal data of the fourth mode, it is determined that the second rotating machine has an abnormality and the first vibration sensor is normal. Rotating machine diagnostic method. In claim 17,
When the sensor data of the third mode is equivalent to the normal data of the third mode, it is determined that both the second rotating machine and the first vibration sensor are normal.
When the sensor data of the third mode is reduced or disappears as compared with the normal data of the third mode, the second rotating machine is normal and the first vibration sensor is abnormal. Rotating machine diagnostic method to determine.

Images