Information processing device

Abstract

The present technology relates to an information processing device that makes it possible to more easily determine timing for maintenance, using event data. The information processing device comprises a state estimation unit that estimates a state of a grindstone, using event data from an event sensor, and outputs the estimation result, the event sensor outputting, as the event data, a temporal change of an electric signal obtained by photoelectric conversion of an optical signal. The present technology can be applied to, for example, an information processing system that notifies timing for maintenance of a grindstone of a machine tool.

Description

[Technical Field]

[0001] The present technology relates to an information processing device, and more particularly to an information processing device that uses event data to more easily determine the timing of maintenance. [Background technology]

[0002] Patent Document 1 discloses a maintenance support device that generates a learning model by performing machine learning using a learning data set in which the actual surface roughness measured by an off-machine measuring device is used as the objective variable and the measurement data from an on-machine measuring device is used as the explanatory variable, and that performs support processing for machine tool maintenance using measurement data obtained by an on-machine measuring device such as a non-contact displacement sensor. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2020-114615 Summary of the Invention [Problem to be solved by the invention]

[0004] It would be desirable to be able to more easily determine when machine tool maintenance is required.

[0005] The present technology has been developed in light of such circumstances, and makes it possible to more easily determine the timing of maintenance by using event data. [Means for solving the problem]

[0006] An information processing device according to one aspect of the present technology includes a state estimation unit that estimates the state of the grinding wheel using event data from an event sensor that outputs a temporal change in an electrical signal obtained by photoelectrically converting an optical signal, and outputs the estimation result.

[0007] In one aspect of the present technology, a change over time in an electrical signal obtained by photoelectrically converting an optical signal is output as event data, the state of the grinding wheel is estimated using the event data, and the estimation result is output.

[0008] The information processing device may be an independent device or a module incorporated into another device. [Brief explanation of the drawings]

[0009] [Figure 1] 1 is a block diagram showing a configuration example of a first embodiment of an information processing system to which the present technology is applied. [Figure 2] FIG. 10 is a diagram illustrating an example of event data. [Figure 3] 10A and 10B are diagrams illustrating an example of a method for generating frame data from event data. [Figure 4] FIG. 10 is a diagram illustrating an event image capturing falling sparks. [Figure 5] FIG. 2 is a block diagram illustrating a detailed configuration example of an information processing device. [Figure 6] FIG. 2 is a diagram illustrating the relationship between measurement parameters and physical quantities. [Figure 7] 1 is a table showing correlations between measurement parameters and physical quantities. [Figure 8] 10 is a flowchart illustrating a maintenance timing determination process performed by the information processing system. [Figure 9] 10 is a flowchart illustrating a threshold value update process. [Figure 10] FIG. 10 is a block diagram showing a configuration example of an EVS camera of a second embodiment of an information processing system to which the present technology is applied. [Figure 11] FIG. 2 is a block diagram showing an example of a schematic configuration of an imaging element. [Figure 12] FIG. 10 is a block diagram illustrating a configuration example of an address event detection circuit. [Figure 13] 1 is a circuit diagram showing detailed configurations of a current-voltage conversion circuit, a subtractor, and a quantizer. [Figure 14]FIG. 10 is a diagram illustrating a more detailed example of the circuit configuration of the address event detection circuit. [Figure 15] FIG. 10 is a circuit diagram showing another example of the configuration of the quantizer. [Figure 16] 16 is a diagram illustrating a more detailed example of the circuit configuration of an address event detection circuit when the quantizer of FIG. 15 is employed. [Figure 17] FIG. 2 is a block diagram illustrating an example of the hardware configuration of a computer. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, with reference to the accompanying drawings, a description will be given of an embodiment of the present technology. In this specification and the drawings, components having substantially the same functional configurations are designated by the same reference numerals, and redundant description will be omitted. The description will be given in the following order. 1. First embodiment of information processing system 2. Example of event data 3. Example of information processing device configuration 4. Relationship between measurement parameters and physical quantities 5. Flowchart of maintenance timing determination process 6. Flowchart of threshold update process 7. Second embodiment of information processing system 8. Summary 9. Computer configuration example

[0011] <1. First embodiment of information processing system> FIG. 1 shows a configuration example of a first embodiment of an information processing system to which the present technology is applied.

[0012] The information processing system 1 in FIG. 1 has an EVS camera 11, an information processing device 12, and a display 13, and is a system that estimates the state of a grinding wheel 22 of a machine tool 21 and notifies the user of the timing of maintenance.

[0013] The machine tool 21 is a so-called grinding machine that performs grinding processes such as cylindrical grinding, internal grinding, and surface grinding on the workpiece W. The machine tool 21 rotates a grinding wheel 22 at high speed to grind the workpiece W. A coolant 23 is supplied from an upper nozzle to the contact area between the grinding wheel 22 and the workpiece W. During grinding of the workpiece W by the grinding wheel 22, sparks 24 are generated from the contact area between the grinding wheel 22 and the workpiece W. In addition to the sparks 24, the coolant 23 also drips.

[0014] The EVS camera 11 is a camera equipped with an event sensor that outputs, as event data, temporal changes in an electrical signal obtained by photoelectrically converting an optical signal. Such an event sensor is also called an EVS (event-based vision sensor). A camera equipped with a general image sensor captures images in synchronization with a vertical synchronization signal and outputs frame data, which is image data for one frame (screen), at the period of the vertical synchronization signal. However, the EVS camera 11 outputs event data only when an event occurs, and can therefore be said to be an asynchronous or address-controlled camera.

[0015] The EVS camera 11 is installed so that the workpiece W and grinding wheel 22 during grinding are within its imaging range, and detects sparks 24 that occur during grinding and changes in light (brightness) caused by falling coolant liquid 23 as events, and outputs the event data to the information processing device 12.

[0016] The information processing device 12 estimates the state of the grinding wheel 22 based on the event data output from the EVS camera 11. For example, the information processing device 12 processes the event data to determine whether or not the grinding wheel 22 is clogged. If the information processing device 12 determines that the grinding wheel 22 is clogged, it outputs an alert that the grinding wheel 22 is clogged. Any method can be selected as the alert, such as audio output from a buzzer, lighting of a signal light, or display of an alert message. In this embodiment, the information processing device 12 displays a message (text) such as "Clogged. Maintenance required" on the display 13. The information processing device 12 also generates a display image using the event data from the EVS camera 11 and displays it on the display 13.

[0017] <2. Example of event data> FIG. 2 shows an example of event data output by the EVS camera 11.

[0018] For example, as shown in FIG. 2, the EVS camera 11 captures the image at the time t i , the coordinates (x i , y i ), and the polarity of the luminance change as an event p i Outputs event data including

[0019] Event time t i is a timestamp that indicates the time when an event occurred, and is expressed, for example, as the count value of a counter based on a predetermined clock signal in a sensor. A timestamp corresponding to the timing when an event occurred can be said to be time information that indicates the (relative) time when the event occurred, as long as the interval between events is maintained as it was when the events occurred.

[0020] polarity p irepresents the direction of the luminance change when a luminance change (change in light intensity) exceeding a predetermined threshold (hereinafter referred to as the event threshold) occurs as an event, and indicates whether the luminance change is a positive change (hereinafter also referred to as a positive change) or a negative change (hereinafter also referred to as a negative change). Event polarity p i is expressed as "1" when it is positive and as "0" when it is negative.

[0021] In the event data in Figure 2, the time t i and the time t of the event adjacent to that event i+1 The interval between the event time t i and t i+1 The time t may be the same or different. i and t i+1 For equation t i <=t i+1 There is a relationship expressed as:

[0022] The EVS camera 11 outputs only the position coordinates, polarity, and time information of pixels where a change in brightness is detected. Because the EVS camera 11 generates and outputs only the net change (difference) of the position coordinates, polarity, and time information, there is no redundancy in the amount of data and it has high time resolution on the order of μsec. This allows it to accurately capture sparks 24, coolant liquid 23, etc. that occur instantaneously.

[0023] Unlike frame-format image data (frame data) that is output at a frame cycle in synchronization with a vertical synchronization signal, event data is output each time an event occurs. Therefore, event data cannot be used as is to display images on the display 13 that displays images corresponding to frame data, nor can it be input to a classifier (classifier) ​​for image processing. To display event data on the display 13, it must be converted into frame data.

[0024] FIG. 3 is a diagram illustrating an example of a method for generating frame data from event data.

[0025] In Figure 3, in a three-dimensional (temporal) space consisting of the x-axis, y-axis, and time axis t, points representing event data are plotted at the time t of the event included in the event data and at the coordinates (x, y) of the pixel of the event.

[0026] That is, if the time t of an event included in the event data and the position (x, y, t) in three-dimensional space represented by the pixel (x, y) of the event are defined as the spatiotemporal position of the event, then in Figure 3, the event data is plotted as a point at the spatiotemporal position (x, y, t) of the event.

[0027] Using the event data output from the EVS camera 11 as pixel values, an event image can be generated at each predetermined frame interval using the event data within a predetermined frame width from the beginning of the predetermined frame interval.

[0028] The frame width and frame interval can be specified by time or by the number of event data. One of the frame width and frame interval can be specified by time, and the other can be specified by the number of event data.

[0029] Here, the frame width and frame interval are specified by time, and if the frame width and frame interval are the same, the frame volumes are adjacent with no gaps. If the frame interval is larger than the frame width, the frame volumes are arranged with gaps between them. If the frame width is larger than the frame interval, the frame volumes are arranged with some overlapping.

[0030] An event image can be generated, for example, by setting the pixel (pixel value) of the frame at the event position (x, y) to white, and pixels at other positions in the frame to a predetermined color such as gray.

[0031] In addition, when generating frame data, if the polarity of the change in light intensity as an event is to be distinguished for the event data, the pixel can be set to white if the polarity is positive, and set to black if the polarity is negative, and pixels at other positions in the frame can be set to a predetermined color such as gray.

[0032] FIG. 4 shows an example of an event image capturing a single spark 24 falling.

[0033] The spark 24 has a brighter light intensity than the surrounding background. Therefore, when the EVS camera 11 captures a single spark 24 falling from the dashed line position to the solid line position, as shown in Figure 4, a change in brightness (change in light intensity) from dark to bright occurs in the lower region in the direction of travel of the spark 24, and a positive event occurs. On the other hand, a change in brightness (change in light intensity) from bright to dark occurs in the upper region of the spark 24, opposite the direction of travel, and a negative event occurs.

[0034] If an image is generated for display on the display 13 by setting pixels with positive polarity to white, pixels with negative polarity to black, and pixels in other positions in the frame to gray, the image will look like the image on the far right of Figure 4.

[0035] <3. Configuration example of information processing device> FIG. 5 is a block diagram showing an example of a detailed configuration of the information processing device 12.

[0036] In addition to the EVS camera 11 and the display 13, FIG. 5 also illustrates an external sensor 14 that can be added as an option.

[0037] The information processing device 12 has a data acquisition unit 50, an event data processing unit 51, an event data storage unit 52, an image generation unit 53, an image storage unit 54, and an image data processing unit 55. The information processing device 12 also has a grindstone state estimation unit 56, a camera setting change unit 57, a feature storage unit 58, and an output unit 59.

[0038] The data acquisition unit 50 acquires event data output from the EVS camera 11 at any timing, and supplies the data to an event data processing unit 51 and an event data storage unit 52 .

[0039] The event data processing unit 51 executes predetermined event data processing using the event data supplied from the data acquisition unit 50, and supplies the processed data to the grinding wheel condition estimation unit 56. For example, the event data processing unit 51 calculates an event rate, which is the occurrence frequency of the event data, and supplies the event rate to the grinding wheel condition estimation unit 56.

[0040] The event data storage unit 52 stores the event data supplied from the data acquisition unit 50 for a certain period of time and supplies it to the image generation unit 53. The image generation unit 53 generates an event image using the event data stored in the event data storage unit 52. That is, the image generation unit 53 generates an event image using event data within a predetermined frame width from the beginning of a predetermined frame interval, out of the event data stored in the event data storage unit 52. The event images generated at each predetermined frame interval are supplied to the image storage unit 54. The image storage unit 54 stores the event images supplied from the image generation unit 53.

[0041] The image data processing unit 55 performs predetermined image data processing using the event images stored in the image storage unit 54. For example, the image data processing unit 55 calculates the number, size, speed, flight distance, and flight angle of the sparks 24 in the event image and supplies the calculation results to the grinding wheel state estimation unit 56. The number of sparks 24 represents, for example, the number of sparks 24 detected in the event image. The size of the sparks 24 represents, for example, the outer size (vertical and horizontal) of the sparks 24 detected in the event image. The speed of the sparks 24 represents the movement speed calculated from the positions of the same sparks 24 detected in multiple event images. The flight distance of the sparks 24 represents the distance from the position where the sparks 24 were first detected to the position just before they disappeared. The flight angle of the sparks 24 represents the angle between the vertical downward direction and the direction starting from the position where the sparks 24 were first detected and ending at the position just before they disappeared.

[0042] Depending on the setting value of the event threshold, the information processing device 12 can detect not only the sparks 24 but also the coolant 23 as an event. When the threshold is set to detect the coolant 23 as event data, the image data processing unit 55 also calculates the number, size, and velocity of the coolant 23 based on the event image, and supplies the calculation results to the grinding wheel state estimation unit 56.

[0043] In the following, in order to distinguish between the number, size, and velocity of the sparks 24 and the coolant liquid 23, the sparks 24 may be referred to as the number of sparks, spark size, and spark velocity, and the coolant liquid 23 may be referred to as the number of droplets, droplet size, and droplet velocity.

[0044] The grindstone state estimation unit 56 estimates the state of the grindstone 22 using the event processing data supplied from the event data processing unit 51 or the image data processing unit 55. Specifically, the grindstone state estimation unit 56 determines whether or not clogging has occurred in the grindstone 22 using at least one feature value from among the event rate, the number of sparks, the spark size, and the spark velocity.

[0045] For example, the grinding wheel condition estimation unit 56 determines whether the spark size is equal to or smaller than a predetermined first condition determination threshold VS1, and if it is determined that the spark size is equal to or smaller than the first condition determination threshold VS1, it determines that clogging has occurred in the grinding wheel 22.

[0046] Furthermore, for example, the grindstone condition estimation unit 56 compares the number of sparks and the spark size with predetermined condition determination thresholds. Specifically, the grindstone condition estimation unit 56 determines whether the number of sparks is equal to or less than a first condition determination threshold VS2 and the spark size is equal to or less than a second condition determination threshold VS3. If it is determined that the number of sparks is equal to or less than the first condition determination threshold VS2 and the spark size is equal to or less than the second condition determination threshold VS3, the grindstone condition estimation unit 56 determines that clogging has occurred in the grindstone 22.

[0047] When it is determined that clogging has occurred in the grinding wheel 22, the grinding wheel condition estimation unit 56 generates an alert image such as "Clogging has occurred. Maintenance is required," and outputs it to the display 13 via the output unit 59. Furthermore, when it is determined that the state of the grinding wheel 22 is normal, the grinding wheel condition estimation unit 56 may generate a display image at a predetermined frame rate and output it to the display 13 via the output unit 59.

[0048] Furthermore, the grindstone condition estimation unit 56 also has a function of adjusting the event threshold of the EVS camera 11 based on the event processing data supplied from the event data processing unit 51 or the image data processing unit 55. For example, the grindstone condition estimation unit 56 instructs the camera setting change unit 57 to increase or decrease the event threshold based on the event rate supplied from the event data processing unit 51. The camera setting change unit 57 changes the event threshold of the EVS camera 11 based on the instruction from the grindstone condition estimation unit 56 to increase or decrease the event threshold.

[0049] The feature amount storage unit 58 is a storage unit that stores the feature amount acquired by the grindstone state estimation unit 56 from the event data processing unit 51 or the image data processing unit 55.

[0050] The output unit 59 outputs the alert image supplied from the grindstone state estimation unit 56 to the display 13. The output unit 59 may also output an event image or a display image to the display 13.

[0051] The information processing device 12 is configured as described above and can estimate the state of the grinding wheel 22 based on the event data output from the EVS camera 11 and detect the occurrence of clogging of the grinding wheel 22. The information processing device 12 can prompt the worker to perform maintenance by displaying an alert image on the display 13.

[0052] Furthermore, the information processing device 12 can be connected to an external sensor 14 and estimate the state of the grinding wheel 22 using sensor data obtained by the external sensor 14 in addition to the event data output from the EVS camera 11. As the external sensor 14, for example, a microphone that detects sounds during grinding or a far-infrared sensor that measures temperature can be used. Of course, the external sensor 14 may be a sensor other than a microphone or a far-infrared sensor.

[0053] When the external sensor 14 is connected to the information processing device 12, the sensor data generated by the external sensor 14 is supplied to the grinding wheel state estimation unit 56. The grinding wheel state estimation unit 56 estimates the state of the grinding wheel 22 using the sensor data supplied from the external sensor 14 and the event processing data supplied from the event data processing unit 51 or the image data processing unit 55.

[0054] 4. Relationship between measurement parameters and physical quantities FIG. 6 is a diagram illustrating the relationship between parameters (measurement parameters) measurable by the EVS camera 11 (event sensor) and physical quantities related to the grinding process of the machine tool 21.

[0055] In FIG. 6, items that can be measured by the EVS camera 11 are shown surrounded by thick lines.

[0056] Examples of measuring devices for determining whether maintenance of machine tool 21 is required include a surface roughness meter, an RGB camera, a thermocouple, and a thermograph, as shown in the rightmost column of Fig. 6. In this embodiment, an EVS camera 11 (event sensor) is used instead of these measuring devices.

[0057] The EVS camera 11 can generate and output event data. The event data includes event data of sparks 24 and event data of coolant liquid 23. Events caused by ambient light or vibration of the device may also be detected. Events caused by ambient light or vibration of the device correspond to noise, and can be excluded by setting an appropriate event threshold.

[0058] In the event data of the sparks 24, the number of sparks, spark size, spark velocity, and spark explosion mode can be measured as measurement parameters. The spark explosion mode is a classification that indicates the characteristics of the explosion (how the sparks 24 break). The spark explosion mode differs depending on the material of the workpiece W. By detecting the spark explosion mode, the material of the workpiece W can be identified.

[0059] The number of sparks is related to the frequency of abrasive grains falling off, the grinding peripheral speed, and the feed rate, which is a processing condition. The spark size is related to the particle size of the abrasive grains in the grinding wheel 22, and the feed rate and depth of cut, which are processing conditions. The spark speed is related to the grinding peripheral speed. The frequency of abrasive grains falling off is related to the bonding strength of the bond in the grinding wheel 22 and the porosity of the pores, and the grinding peripheral speed is related to the processing conditions, the peripheral speed of the workpiece W and the peripheral speed of the grinding wheel 22.

[0060] The number of droplets, the size of droplets, and the velocity of droplets can be measured as measurement parameters in the event data of the coolant 23. The number of droplets, the size of droplets, and the velocity of droplets are related to the flow rate of the coolant 23.

[0061] When performing maintenance on the grinding wheel 22 of the machine tool 21, and particularly focusing on clogging of the grinding wheel 22, clogging of the grinding wheel 22 is closely related to the spark size that can be measured using event data of the spark 24. In terms of physical quantities, the spark size is closely related to the particle size of the abrasive grains.

[0062] FIG. 7 is a table showing the correlation between the measurement parameters that can be measured based on the event data and the physical quantities related thereto, which are indicated by the bold frame in FIG.

[0063] In Figure 7, if there is a positive correlation between the value of the physical quantity shown on the left side of the table and the measurement parameter shown on the top side of the table, it is represented by "+", if there is a negative correlation, it is represented by "-", and if there is a correlation other than positive or negative, it is represented by "◯".

[0064] For example, the particle size of the abrasive grains in the grinding wheel 22 and the size of the sparks are correlated such that the larger the abrasive grains, the larger the spark size. The degree of bonding of the binder and the number of sparks are correlated such that the higher the degree of bonding, the larger the number of sparks. The porosity of the pores and the number and size of the sparks are correlated such that the higher the porosity, the smaller the number and size of the sparks.

[0065] For example, the flow rate of the coolant liquid 23 and the number and speed of droplets have a correlation such that as the flow rate increases, the number and speed of droplets also increase.

[0066] According to the correlation between the measurement parameters measurable from the event data and the physical quantities as shown in FIG. 7, the grinding wheel condition estimation unit 56 can estimate the physical quantities from the data processing results of the event data and determine the timing of maintenance.

[0067] <5. Flowchart of Maintenance Timing Determination Process> Next, a maintenance timing determination process performed by the information processing system 1 will be described with reference to the flowchart of Fig. 8. This process is started, for example, when the EVS camera 11 and the information processing device 12 are started (powered on).

[0068] First, in step S11, the data acquisition unit 50 acquires event data output from the EVS camera 11 at any timing, and supplies the event data to the event data processing unit 51 and the event data storage unit 52.

[0069] In step S12, the event data processing unit 51 executes a predetermined event data processing using the event data supplied from the data acquisition unit 50, and supplies the processed data to the grinding wheel condition estimation unit 56. For example, the event data processing unit 51 calculates an event rate, which is the occurrence frequency of the event data, and supplies the event rate to the grinding wheel condition estimation unit 56.

[0070] In step S13, the event data storage unit 52 stores the event data supplied from the data acquisition unit 50 for a certain period of time and supplies the event data to the image generation unit 53. The image generation unit 53 generates an event image using the event data stored in the event data storage unit 52 and supplies the generated event image to the image storage unit 54.

[0071] In step S14, the image data processing unit 55 performs predetermined image data processing using the event image stored in the image storage unit 54. For example, the image data processing unit 55 calculates the number, size, speed, flying distance, and flying angle of the sparks 24 in the event image, and supplies the calculation results to the grinding wheel condition estimation unit 56.

[0072] In step S15, the grindstone condition estimation unit 56 executes a grindstone condition estimation process to estimate the condition of the grindstone 22 using the event processing data supplied from the event data processing unit 51 or the image data processing unit 55. For example, as the grindstone condition estimation process, the grindstone condition estimation unit 56 determines whether the spark size is equal to or smaller than a first condition determination threshold VS1. Alternatively, as the grindstone condition estimation process, the grindstone condition estimation unit 56 determines whether the number of sparks is equal to or smaller than a first condition determination threshold VS2 and the spark size is equal to or smaller than a second condition determination threshold VS3.

[0073] In step S16, the grindstone condition estimating unit 56 determines whether clogging has occurred in the grindstone 22 based on the result of the grindstone condition estimating process.

[0074] If it is determined in step S16 that no clogging has occurred in the grinding wheel 22, the process returns to step S11, and the processes of steps S11 to S16 described above are executed again. Note that, if the grinding wheel 22 is in a normal state where no clogging has occurred, a display image generated based on the event data, an event image generated by the image generation unit 53, etc. may be supplied to the display 13 via the output unit 59 and displayed.

[0075] On the other hand, if it is determined in step S16 that clogging has occurred in the grinding wheel 22, the process proceeds to step S17, where the grinding wheel condition estimation unit 56 issues an alert about clogging of the grinding wheel 22. For example, the grinding wheel condition estimation unit 56 generates an alert image such as "Clogging has occurred. Maintenance is required," and outputs it to the display 13 via the output unit 59. The display 13 displays the alert image supplied from the information processing device 12.

[0076] The above is the execution of the maintenance timing determination process by the information processing system 1. By the above process, the worker who has confirmed the alert image displayed on the display 13 knows that it is time for maintenance and performs dressing of the grinding wheel 22, etc.

[0077] <Grinding wheel condition estimation process using learning model> In the above-mentioned grinding wheel condition estimation process, the condition of the grinding wheel 22 was estimated by a threshold determination process that uses at least one of the number, size, speed, flight distance, and flight angle of the sparks 24 and the number, size, and speed of the coolant liquid 23 as feature quantities and determines the feature quantities against a predetermined threshold value.

[0078] Alternatively, the grinding wheel condition estimation process for estimating the condition of the grinding wheel 22 may use a learning model generated by machine learning to estimate the condition of the grinding wheel 22 and determine the timing of maintenance. For example, the grinding wheel condition estimation unit 56 generates a learning model by machine learning using event data obtained during grinding using the grinding wheel 22 when clogging or other issues occur and maintenance is required, and event data obtained during grinding when the grinding wheel 22 is in a normal state (a state in which maintenance is not required), with the necessity of maintenance as training data. The grinding wheel condition estimation unit 56 uses the generated learning model to estimate the necessity of maintenance of the grinding wheel 22 based on the input event data. Alternatively, instead of the event data itself, feature quantities such as the number, size, speed, flight distance, and flight angle of the sparks 24 may be used as training data when generating the learning model. The learning model may be trained to determine not only the necessity of maintenance but also the condition of the grinding wheel 22, such as clogging, glazing, and chipping.

[0079] <Grinding wheel condition estimation processing using external sensor data> Furthermore, if an external sensor 14 is connected to the information processing device 12, the state of the grinding wheel 22 may be estimated using sensor data obtained by the external sensor 14 in addition to the data processing results of the event data. The grinding wheel state estimation process using the data processing results of the event data and the sensor data may be a threshold judgment process or a judgment process using a learning model.

[0080] <6. Flowchart of threshold update process> Next, a threshold update process for dynamically changing the event threshold will be described with reference to the flowchart of Fig. 9. This process is started, for example, together with the maintenance timing determination process described with reference to Fig. 8, and is executed in parallel with the maintenance timing determination process.

[0081] First, in step S31, the grindstone condition estimating unit 56 acquires the data processing results of the event data or the event image. The processing of step S31 can be essentially omitted because it is included in the maintenance timing determination processing of Fig. 8 that is executed in parallel. In addition, the grindstone condition estimating unit 56 may also acquire the event data itself output from the EVS camera 11 via the event data processing unit 51.

[0082] In step S32, the grinding wheel condition estimation unit 56 calculates the influence of the coolant 23 using the acquired data processing results. For example, when the grinding wheel condition estimation unit 56 uses the event rate supplied from the event data processing unit 51, it can calculate the influence of the coolant 23 from the event rate in a state where no sparks 24 are emitted. Furthermore, when the data processing results of the event images are used, the grinding wheel condition estimation unit 56 can calculate the influence of the coolant 23 based on the ratio between the number of sparks and the number of droplets. The sparks 24 and the coolant 23 can be classified, for example, by size.

[0083] In step S33, the grinding wheel condition estimation unit 56 determines whether to change the event threshold. For example, when both the sparks 24 and the coolant liquid 23 are currently detected as events, and it is desired to detect only the sparks 24, the grinding wheel condition estimation unit 56 determines to change the event threshold. In this case, the event threshold is adjusted in a direction increasing the current value. Alternatively, when only the sparks 24 are currently detected, and it is desired to detect both the sparks 24 and the coolant liquid 23, it determines to change the event threshold. In this case, the event threshold is adjusted in a direction decreasing the current value.

[0084] If it is determined in step S33 that the event threshold is not to be changed, the process returns to step S31, and the processes of steps S31 to S33 described above are executed again.

[0085] On the other hand, in step S33, when it is determined that the event threshold value is to be changed, the process proceeds to step S34, and the grindstone state estimation unit 56 instructs the camera setting change unit 57 to increase or decrease the event threshold value. The camera setting change unit 57 sets a new event threshold value by supplying the new event threshold value to the EVS camera 11. The new event threshold value is, for example, a value changed by a predetermined change width in the indicated increase or decrease direction.

[0086] According to the above threshold update process, the event threshold value can be adjusted based on the detection status of the event in parallel with the grindstone state estimation process. Whether both the spark 24 and the coolant liquid 23 are detected as events or only the spark 24 is detected as an event can be specified in advance to the information processing apparatus 12, for example, by setting the operation mode.

[0087] <7. Second Embodiment of the Information Processing System> Next, a second embodiment of the information processing system to which the present technology is applied will be described.

[0088] In the first embodiment of the information processing system shown in FIG. 1, the EVS camera 11 detects a luminance change such as the spark 24 as an event, outputs event data to the information processing apparatus 12, and the information processing apparatus 12 executes a process of estimating the state of the grindstone 22 using the event data.

[0089] In contrast, in the information processing system 1 of the second embodiment described below, the process of estimating the state of the grindstone 22 using the event data is also performed within the EVS camera. In other words, the EVS camera 11 and the information processing apparatus 12 in the first embodiment are replaced by one EVS camera 300 shown in FIG. 10.

[0090] <Configuration Example of EVS Camera> The EVS camera 300 shown in FIG. 10 is an imaging device equipped with an event sensor and a processing unit that executes the functions of the information processing device 12 in the first embodiment. The EVS camera 300 is installed in the same position as the EVS camera 11 in FIG. 1 and detects events such as sparks 24 and changes in the brightness of the coolant 23, generating event data. The EVS camera 300 also executes a grinding wheel condition estimation process to estimate the condition of the grinding wheel 22 based on the event data and outputs a maintenance alert based on the results of the grinding wheel condition estimation process. For example, if it is determined that maintenance is required, the EVS camera 300 displays an alert image on the display 13, such as "Clogging has occurred. Maintenance is required." Furthermore, the EVS camera 300 can also generate a display image for monitoring by an operator based on the event data and display it on the display 13.

[0091] The EVS camera 300 includes an optical unit 311, an imaging element 312, a control unit 313, and a data processing unit 314.

[0092] The optical unit 311 collects light from a subject and makes it incident on the image sensor 312. The image sensor 312 photoelectrically converts the incident light that has entered through the optical unit 311 to generate event data, and supplies the event data to the data processing unit 314. The image sensor 312 is a light receiving element that regards a change in pixel brightness as an event and outputs event data that indicates the occurrence of an event.

[0093] The control unit 313 controls the imaging element 312. For example, the control unit 313 instructs the imaging element 312 to start and end imaging.

[0094] The data processing unit 314 is configured with, for example, an FPGA (Field Programmable Gate Array), a DSP (Digital Signal Processor), a microprocessor, etc., and executes the processing performed by the information processing device 12 in the first embodiment. The data processing unit 314 includes an event data processing unit 321 and a recording unit 322. For example, the event data processing unit 321 performs event data processing using event data supplied from the image sensor 312, image data processing using event images, grinding wheel state estimation processing for estimating the state of the grinding wheel 22, etc. The recording unit 322 corresponds to the event data storage unit 52, image storage unit 54, and feature amount storage unit 58 in the first embodiment, and records and accumulates predetermined data on a predetermined recording medium as needed.

[0095] <Example of imaging element configuration> FIG. 11 is a block diagram showing an example of a schematic configuration of the image sensor 312. As shown in FIG.

[0096] The imaging element 312 includes a pixel array section 341 , a driver section 342 , a Y arbiter 343 , an X arbiter 344 , and an output section 345 .

[0097] The pixel array unit 341 has a plurality of pixels 361 arranged in a two-dimensional lattice pattern. Each pixel 361 includes a photodiode 371 as a photoelectric conversion element and an address event detection circuit 372. When a change exceeding a predetermined threshold occurs in a photocurrent, which is an electrical signal generated by photoelectric conversion of the photodiode 371, the address event detection circuit 372 detects the change in photocurrent as an event. When an event is detected, the address event detection circuit 372 outputs a request to the Y arbiter 343 and the X arbiter 344, requesting the output of event data indicating the occurrence of the event.

[0098] The drive section 342 drives the pixel array section 341 by supplying a control signal to each pixel 361 of the pixel array section 341 .

[0099] The Y arbiter 343 arbitrates requests from pixels 361 in the same row within the pixel array unit 341, and returns a response indicating whether output of event data is permitted or not to the pixel 361 that sent the request. The X arbiter 344 arbitrates requests from pixels 361 in the same column within the pixel array unit 341, and returns a response indicating whether output of event data is permitted or not to the pixel 361 that sent the request. A pixel 361 that receives permission responses from both the Y arbiter 343 and the X arbiter 344 can output event data to the output unit 345.

[0100] The image sensor 312 may be configured to include only either the Y arbiter 343 or the X arbiter 344. For example, if the image sensor 312 is configured only with the X arbiter 344, data from all pixels 361 in the same column, including the pixel 361 that has sent the request, is transferred to the output unit 345. Then, in the output unit 345 or the data processing unit 314 (FIG. 10) at a subsequent stage, only the event data of the pixel 361 that actually issued the event is selected. If the image sensor 312 is configured only with the Y arbiter 343, pixel data is transferred to the output unit 345 on a row-by-row basis, and only the event data of the pixel 361 required at a subsequent stage is selected.

[0101] The output unit 345 performs necessary processing on the event data output by each pixel 361 that constitutes the pixel array unit 341, and supplies the data to the data processing unit 314 (FIG. 10).

[0102] <Example of address event detection circuit configuration> FIG. 12 is a block diagram showing an example of the configuration of the address event detection circuit 372.

[0103] The address event detection circuit 372 includes a current-voltage conversion circuit 381 , a buffer 382 , a subtractor 383 , a quantizer 384 , and a transfer circuit 385 .

[0104] The current-voltage conversion circuit 381 converts the photocurrent from the corresponding photodiode 371 into a voltage signal. The current-voltage conversion circuit 381 generates a voltage signal corresponding to the logarithmic value of the photocurrent and outputs it to the buffer 382.

[0105] The buffer 382 buffers the voltage signal from the current-voltage conversion circuit 381 and outputs it to the subtractor 383. The buffer 382 ensures isolation from noise caused by the switching operation of the subsequent stage and can improve the driving force for driving the subsequent stage. Note that the buffer 382 can also be omitted.

[0106] The subtractor 383 reduces the level of the voltage signal from the buffer 382 in accordance with the control signal from the driver 342. The subtractor 383 outputs the reduced voltage signal to the quantizer 384.

[0107] The quantizer 384 quantizes the voltage signal from the subtractor 383 into a digital signal and supplies it as event data to the transfer circuit 385. The transfer circuit 385 transfers (outputs) the event data to the output unit 345. That is, the transfer circuit 385 supplies a request for output of the event data to the Y arbiter 343 and the X arbiter 344. Then, when the transfer circuit 385 receives a response to the request from the Y arbiter 343 and the X arbiter 344 permitting the output of the event data, it transfers the event data to the output unit 345.

[0108] <Detailed configuration example of address event detection circuit> Fig. 13 is a circuit diagram showing detailed configurations of the current-voltage conversion circuit 381, the subtractor 383, and the quantizer 384. Fig. 13 also shows the photodiode 371 connected to the current-voltage conversion circuit 381.

[0109] The current-voltage conversion circuit 381 is made up of FETs 411 to 413. For example, N-type MOS (NMOS) FETs can be used as the FETs 411 and 413, and for example, a P-type MOS (PMOS) FET can be used as the FET 412.

[0110] The photodiode 371 receives incident light, performs photoelectric conversion, and generates and outputs a photocurrent as an electrical signal. The current-voltage conversion circuit 381 converts the photocurrent from the photodiode 371 into a voltage VLOG (hereinafter also referred to as photovoltage) corresponding to the logarithm of the photocurrent, and outputs it to the buffer 382.

[0111] The source of the FET 411 is connected to the gate of the FET 413, and a photocurrent generated by the photodiode 371 flows at the connection point between the source of the FET 411 and the gate of the FET 413. The drain of the FET 411 is connected to the power supply VDD, and the gate of the FET 411 is connected to the drain of the FET 413.

[0112] The source of the FET 412 is connected to a power supply VDD, and the drain thereof is connected to the connection point between the gate of the FET 411 and the drain of the FET 413. A predetermined bias voltage Vbias is applied to the gate of the FET 412. The source of the FET 413 is grounded.

[0113] The drain of the FET 411 is connected to the power supply VDD side, and the FET 411 functions as a source follower. The photodiode 371 is connected to the source of the source follower FET 411, so that a photocurrent caused by charges generated by photoelectric conversion of the photodiode 371 flows through the FET 411 (from the drain to the source). The FET 411 operates in the subthreshold region, and a photovoltage VLOG corresponding to the logarithm of the photocurrent flowing through the FET 411 appears at the gate of the FET 411. As described above, in the photodiode 371, the FET 411 converts the photocurrent from the photodiode 371 into a photovoltage VLOG corresponding to the logarithm of the photocurrent.

[0114] The photovoltage VLOG is output from the connection point between the gate of the FET 411 and the drain of the FET 413 via a buffer 382 to a subtractor 383 .

[0115] The subtractor 383 calculates the difference between the current photovoltage VLOG from the current-voltage conversion circuit 381 and the photovoltage at a timing that differs from the current by a small time, and outputs a difference signal Vdiff corresponding to this difference.

[0116] The subtractor 383 includes a capacitor 431, an operational amplifier 432, a capacitor 433, and a switch 434. The quantizer 384 includes comparators 451 and 452.

[0117] One end of the capacitor 431 is connected to the output of the buffer 382, ​​and the other end is connected to the input terminal of the operational amplifier 432. Therefore, the photovoltage VLOG is input to the (inverting) input terminal of the operational amplifier 432 via the capacitor 431.

[0118] The output terminal of the operational amplifier 432 is connected to the non-inverting input terminals (+) of the comparators 451 and 452 of the quantizer 384 .

[0119] One end of the capacitor 433 is connected to the input terminal of the operational amplifier 432 , and the other end is connected to the output terminal of the operational amplifier 432 .

[0120] The switch 434 is connected to the capacitor 433 so as to turn on / off the connection between both ends of the capacitor 433. The switch 434 turns on / off in accordance with a control signal from the drive unit 342, thereby turning on / off the connection between both ends of the capacitor 433.

[0121] The capacitor 433 and the switch 434 constitute a switched capacitor. When the switch 434, which is off, is temporarily turned on and then turned off again, the capacitor 433 is discharged and reset to a state where it can store new charge.

[0122] The photovoltage VLOG of the capacitor 431 on the photodiode 371 side when the switch 434 is turned on is represented as Vinit, and the capacitance (electrostatic capacitance) of the capacitor 431 is represented as C1. The input terminal of the operational amplifier 432 is virtually grounded, and the charge Qinit accumulated in the capacitor 431 when the switch 434 is on is represented by equation (1). Qinit = C1 × Vinit (1)

[0123] Furthermore, when switch 434 is on, both ends of capacitor 433 are shorted, so the charge stored in capacitor 433 becomes zero.

[0124] Thereafter, when the switch 434 is turned off, the photovoltage VLOG on the photodiode 371 side of the capacitor 431 is expressed as Vafter. Then, the charge Qafter accumulated in the capacitor 431 when the switch 434 is turned off is expressed by equation (2). Qafter = C1 × Vafter (2)

[0125] If the capacitance of the capacitor 433 is represented as C2, the charge Q2 stored in the capacitor 433 is expressed by the following equation (3) using the difference signal Vdiff, which is the output voltage of the operational amplifier 432. Q2 = -C2 × Vdiff (3)

[0126] The total charge amount, which is the sum of the charge on capacitor 431 and the charge on capacitor 433, does not change before and after switch 434 is turned off, and therefore equation (4) holds. Qinit = Qafter + Q2 (4)

[0127] Substituting equations (1) to (3) into equation (4) gives equation (5). Vdiff = -(C1 / C2)×(Vafter - Vinit) ···(5)

[0128] According to equation (5), the subtractor 383 subtracts the photovoltages Vafter and Vinit, i.e., calculates a difference signal Vdiff corresponding to the difference between the photovoltages Vafter and Vinit (Vafter - Vinit). According to equation (5), the subtraction gain of the subtractor 383 is C1 / C2. Therefore, the subtractor 383 outputs a voltage obtained by multiplying the change in the photovoltage VLOG after the capacitor 433 is reset by C1 / C2 as the difference signal Vdiff.

[0129] The switch 434 is turned on and off by the control signal output from the drive unit 342, and the subtractor 383 outputs the difference signal Vdiff.

[0130] The difference signal Vdiff output from the subtractor 383 is supplied to the non-inverting input terminals (+) of the comparators 451 and 452 of the quantizer 384 .

[0131] The comparator 451 compares the difference signal Vdiff from the subtractor 383 with a positive threshold Vrefp input to its inverting input terminal (-). The comparator 451 outputs a detection signal DET(+) of H (High) level or L (Low) level, which indicates whether the difference signal Vdiff has exceeded the positive threshold Vrefp, to the transfer circuit 385 as a quantized value of the difference signal Vdiff.

[0132] The comparator 452 compares the difference signal Vdiff from the subtractor 383 with a negative threshold Vrefn input to its inverting input terminal (-). The comparator 452 outputs a detection signal DET(-) of H (High) level or L (Low) level, which indicates whether the negative threshold Vrefn has been exceeded, to the transfer circuit 385 as a quantized value of the difference signal Vdiff.

[0133] FIG. 14 shows a more detailed example of the circuit configuration of the current-voltage conversion circuit 381, the buffer 382, ​​the subtractor 383, and the quantizer 384 shown in FIG.

[0134] FIG. 15 is a circuit diagram showing another example of the configuration of the quantizer 384. In FIG.

[0135] The quantizer 384 shown in FIG. 14 always compared the difference signal Vdiff from the subtractor 383 with both the + side threshold (voltage) Vrefp and the - side threshold (voltage) Vrefn, and output the comparison result.

[0136] In contrast, the quantizer 384 in FIG. 15 includes one comparator 453 and a switch 454, and outputs the comparison result obtained by comparing with either one of two thresholds (voltages) VthON or VthOFF switched by the switch 454.

[0137] The switch 454 is connected to the inverting input terminal (-) of the comparator 453, and selects terminal a or b according to the control signal from the drive unit 342. The voltage VthON as a threshold is supplied to terminal a, and the voltage VthOFF (<VthON) as a threshold is supplied to terminal b. Therefore, the voltage VthON or VthOFF is supplied to the inverting input terminal of the comparator 453.

[0138] The comparator 453 compares the difference signal Vdiff from the subtractor 383 with the voltage VthON or VthOFF, and outputs a detection signal DET of H level or L level representing the comparison result to the transfer circuit 385 as the quantized value of the difference signal Vdiff.

[0139] FIG. 16 shows a more detailed circuit configuration example of the current-voltage conversion circuit 381, buffer 382, subtractor 383, and quantizer 384 when the quantizer 384 shown in FIG. 15 is adopted.

[0140] 16, in addition to the voltages VthON and VthOFF, a terminal VAZ for initialization (AutoZero) is also added as a terminal of the switch 454. When an H (High) level initialization signal AZ is supplied to the gate of the FET 471, which is an N-type MOS (NMOS) FET, in the subtractor 383, the switch 454 of the quantizer 384 selects the terminal VAZ and performs an initialization operation. Thereafter, the switch 454 selects the terminal for the voltage VthON or the voltage VthOFF based on a control signal from the driver 342, and a detection signal DET indicating the comparison result with the selected threshold is output from the quantizer 384 to the transfer circuit 385.

[0141] The maintenance timing determination process and threshold value update process in the second embodiment are the same as those in the first embodiment described above, except that they are executed by the EVS camera 300 itself, rather than by the information processing device 12. This makes it possible to detect sparks 24 and coolant liquid 23 that occur during grinding as events, and to accurately notify the user of the timing of maintenance.

[0142] <8. Summary> According to each of the embodiments of the information processing system 1 described above, the timing of maintenance can be more easily determined by using an event sensor (EVS camera 11 or EVS camera 300) that detects a change in brightness of the spark 24 or the like as an event and outputs the detected event asynchronously. In addition, the event threshold can be dynamically changed depending on the event detection status.

[0143] In the above embodiment, an example has been described in which the machine tool 21 is a grinding machine, but the machine tool 21 may be a machine that performs any processing such as cutting, grinding, cutting, forging, bending, etc.

[0144] <9. Computer configuration example> The series of processes executed by the information processing device 12 described above can be executed by hardware or software. When the series of processes are executed by software, the programs constituting the software are installed in a computer. Here, the computer includes a microcomputer incorporated in dedicated hardware, and a general-purpose personal computer, for example, that can execute various functions by installing various programs.

[0145] FIG. 17 is a block diagram showing an example of the hardware configuration of a computer as an information processing device that executes the above-described series of processes by a program.

[0146] In the computer, a CPU (Central Processing Unit) 501, a ROM (Read Only Memory) 502, and a RAM (Random Access Memory) 503 are interconnected by a bus 504.

[0147] An input / output interface 505 is further connected to the bus 504. An input unit 506, an output unit 507, a storage unit 508, a communication unit 509, and a drive 510 are connected to the input / output interface 505.

[0148] The input unit 506 includes a keyboard, mouse, microphone, touch panel, input terminal, etc. The output unit 507 includes a display, speaker, output terminal, etc. The storage unit 508 includes a hard disk, RAM disk, non-volatile memory, etc. The communication unit 509 includes a network interface, etc. The drive 510 drives a removable recording medium 511 such as a magnetic disk, optical disk, magneto-optical disk, or semiconductor memory.

[0149] In the computer configured as above, the CPU 501 performs the above-described series of processes by, for example, loading a program stored in the storage unit 508 into the RAM 503 via the input / output interface 505 and the bus 504 and executing the program. The RAM 503 also stores data necessary for the CPU 501 to execute various processes as needed.

[0150] The program executed by the computer (CPU 501) can be provided by being recorded on a removable recording medium 511 such as a package medium, for example. The program can also be provided via a wired or wireless transmission medium such as a local area network, the Internet, or digital satellite broadcasting.

[0151] In a computer, the program can be installed in the storage unit 508 via the input / output interface 505 by inserting the removable recording medium 511 into the drive 510. The program can also be received by the communication unit 509 via a wired or wireless transmission medium and installed in the storage unit 508. Alternatively, the program can be installed in the ROM 502 or the storage unit 508 in advance.

[0152] The program executed by the computer may be a program that processes in chronological order according to the order described in this specification, or may be a program that processes in parallel or at the required timing, such as when called.

[0153] The embodiments of the present technology are not limited to the above-described embodiments, and various modifications are possible without departing from the spirit of the present technology.

[0154] For example, it is possible to adopt a form in which all or part of the above-described embodiments are combined as appropriate.

[0155] Furthermore, each step described in the above flowchart can be executed by one device, or can be shared and executed by multiple devices.

[0156] Furthermore, when one step includes multiple processes, the multiple processes included in that one step can be executed by one device or can be shared and executed by multiple devices.

[0157] The effects described in this specification are merely examples and are not limiting, and there may be effects other than those described in this specification.

[0158] The present technology can have the following configurations. (1) a state estimation unit that estimates the state of the grinding wheel using event data from an event sensor that outputs a temporal change in an electrical signal obtained by photoelectrically converting an optical signal, and outputs the estimated result; An information processing device comprising: (2) The state estimation unit estimates the state of the grinding wheel using the event data capturing sparks generated between the grinding wheel and the workpiece, and outputs the estimation result. The information processing device according to (1) above. (3) The state estimation unit estimates a state of the grindstone based on a feature amount of the event data and outputs an estimation result. The information processing device according to (1) or (2). (4) The feature amount of the event data is an event rate The information processing device according to (3) above. (5) further comprising an image generation unit that generates an event image from the event data; The feature amount of the event data is a feature amount detected from the event image. The information processing device according to (3) above. (6) The feature amount of the event data includes at least one of the number, size, speed, flying distance, and flying angle of the sparks. The information processing device according to (5) above. (7) The feature amount of the event data includes at least one of the number, size, and speed of the coolant liquid. The information processing device according to (5) or (6). (8) The state estimation unit outputs an alert based on the estimation result. The information processing device according to any one of (1) to (7). (9) The state estimation unit adjusts an event threshold based on the event data in parallel with an estimation process for estimating the state of the grindstone. The information processing device according to any one of (1) to (8). (10) The state estimation unit estimates the state of the grinding wheel using a learning model generated by machine learning using the event data, and outputs an estimation result. The information processing device according to any one of (1) to (9). (11) The state estimation unit estimates the state of the grinding wheel using sensor data acquired by an external sensor and the event data, and outputs the estimation result. The information processing device according to any one of (1) to (10). [Explanation of symbols]

[0159] 1: Information processing system, 11: EVS camera, 12: Information processing device, 13: Display, 14: External sensor, 21: Machine tool, 22: Grinding wheel, 23: Coolant liquid, 24: Spark, 50: Data acquisition unit, 51: Event data processing unit, 52: Event data storage unit, 53: Image generation unit, 54: Image storage unit, 55: Image data processing unit, 56: Grinding wheel state estimation unit, 57: Camera setting change unit, 58: Feature storage unit, 59: Output unit, 300: EVS camera, 311: Optical unit, 312: Image sensor, 313: Control unit, 314: Data processing unit, 321: Event data processing unit, 322: Recording unit, 501: CPU, 502: ROM, 503: RAM, 508: Storage unit

Claims

1. an event sensor that outputs, as event data, temporal changes in an electrical signal obtained by photoelectrically converting an optical signal; and a state estimation unit that estimates a state of the grinding wheel using the event data that detects, as events, sparks that occur while grinding a workpiece with the grinding wheel and changes in light caused by coolant liquid supplied to a contact portion between the workpiece and the grinding wheel, and outputs an estimation result. An information processing device comprising:

2. The state estimation unit estimates a state of the grindstone based on a feature amount of the event data and outputs an estimation result. The information processing device according to claim 1 .

3. The feature amount of the event data is an event rate. The information processing device according to claim 2 .

4. further comprising an image generation unit that generates an event image from the event data; The feature amount of the event data is a feature amount detected from the event image. The information processing device according to claim 2 .

5. The feature amount of the event data includes at least one of the number, size, speed, flying distance, and flying angle of the sparks. The information processing device according to claim 4 .

6. The feature amount of the event data includes at least one of the number, size, and speed of the coolant liquid. The information processing device according to claim 4 .

7. The state estimation unit outputs an alert based on the estimation result. The information processing device according to claim 1 .

8. The state estimation unit adjusts an event threshold based on the event data in parallel with an estimation process for estimating the state of the grindstone. The information processing device according to claim 1 .

9. The state estimation unit estimates the state of the grinding wheel using a learning model generated by machine learning using the event data, and outputs an estimation result. The information processing device according to claim 1 .

10. The state estimation unit estimates the state of the grinding wheel using sensor data acquired by an external sensor and the event data, and outputs the estimation result. The information processing device according to claim 1 .

Images