JP7225984B2 - System, Arithmetic Unit, and Program - Google Patents

Description

The present invention relates to systems, arithmetic devices, and programs.

Techniques for detecting an abnormality in a device by collecting data generated when the device operates and analyzing the data are being considered. The probability of an abnormality occurring in a factory or plant is extremely low, and it is difficult to collect data when an abnormality occurs.

There is a disclosure of a system for displaying and selecting data in order to efficiently detect outliers (see Patent Document 1).

However, as a basic idea of the outlier detection method, a discriminator generated by analyzing normal data is used to discriminate between normality and abnormality. Therefore, in order to generate a classifier with high accuracy, it is ideal for maintenance personnel to manually label all the data generated from the equipment with data for determining whether it is normal or abnormal. It is conceivable to introduce statistics to automate the labeling, but some of the data judged to be abnormal by statistical processing include cases judged to be normal by maintenance personnel. This is because there is a real problem that even if a minor failure occurs in a device, it can still be used as normal in the field. Therefore, in consideration of actual operation, human labeling is ultimately required. Since labeling a huge amount of data takes a long time and is unrealistic, there is a problem of how to improve the efficiency of this work by humans.

The present invention has been made in view of the above, and an object of the present invention is to provide a system, an arithmetic device, and a program capable of streamlining the work of labeling discrimination data.

In order to solve the above-described problems and achieve the object, the present invention provides a system having a device to be diagnosed and a diagnostic device for diagnosing the device, wherein the device to be diagnosed an output unit for outputting a signal indicating a change in a physical quantity, wherein the diagnostic device includes a frequency analysis processing unit for performing frequency analysis on the output signal indicating the change in the physical quantity to be diagnosed, which is output by the output unit; a low-dimensional data display unit for displaying the low-dimensional feature quantity obtained by the frequency analysis in the low-dimensional setting; and receiving selection of one data from the data displayed by the low-dimensional data display unit. A reception unit, a high-dimensional data output unit that outputs high-dimensional information of selected data, a discrimination data setting unit that sets discrimination data of the data received by the reception unit, and a change in the physical quantity of the diagnosis target. and a discriminating unit that discriminates the output signal indicating the signal based on the discriminating data set by the discriminating data setting unit.

ADVANTAGE OF THE INVENTION According to this invention, there exists an effect that it becomes possible to make the work which labels discrimination|determination data efficient.

FIG. 1 is a functional block diagram showing an example of a diagnostic system according to this embodiment. FIG. 2 is a block diagram showing an example of the hardware configuration of the processing machine. FIG. 3 is a block diagram showing an example of the hardware configuration of the diagnostic device. FIG. 4 is a block diagram showing an example of functions related to the abnormality detection unit of the diagnostic device. FIG. 5 is a diagram showing an example of the configuration of functional blocks related to labeling processing in the diagnostic device. FIG. 6 is an explanatory diagram of obtaining a frequency distribution from signal data by frequency analysis. FIG. 7 is a diagram illustrating a setting example of a low-dimensional feature quantity table. FIG. 8 is a diagram showing an example of distribution of feature quantities visualized in a three-dimensional feature quantity space. FIG. 9 is a diagram showing an example of basic information about data selected by the user. FIG. 10 is a diagram showing an example of a UI for sound operation. FIG. 11 is a diagram showing an example of a UI for labeling by the user. FIG. 12 is an explanatory diagram of processing for generating a discriminator. FIG. 13 is an explanatory diagram of abnormality detection of sound/vibration data using a discriminator and storage of detection results. FIG. 14 is a diagram showing an example of the overall configuration of a UI screen on which a user performs labeling processing. FIG. 15 is a diagram showing an example of a UI screen. FIG. 16 is a diagram illustrating an example of the flow of labeling processing performed by the control unit of the diagnostic device.

Embodiments of a system, an arithmetic device, and a program according to the present invention will be described in detail below with reference to the accompanying drawings. A diagnosis system for diagnosing a processing machine will be described as an example of a system for diagnosing equipment.

(Embodiment)
FIG. 1 is a functional block diagram showing an example of a diagnostic system according to this embodiment. As shown in FIG. 1, the diagnostic system includes a processing machine 200 and diagnostic device 100 . The processing machine 200 is an example of a device to be diagnosed by the diagnostic device 100 .

The processing machine 200 and the diagnostic device 100 may be connected in any connection form. For example, the processing machine 200 and the diagnostic device 100 are connected by a dedicated connection line, a wired network such as a wired LAN (Local Area Network), a wireless network, or the like.

The processing machine 200 includes a numerical controller 201 , a communication controller 202 and a machine tool 203 . The machine tool 203 has a sensor 211 , a drive section 212 and a tool 213 . Among them, the sensor 211 and the communication control unit 202 correspond to the "output unit".

The machine tool 203 is a machine that processes an object to be processed under the control of the numerical control unit 201 . The machine tool 203 includes a driving section 212 that operates under the control of the numerical control section 201 . The drive unit 212 is, for example, a motor. The tool 213 is an object to be actually driven by the drive unit 212, and may be any tool such as a drill and an end mill for machining an object, as long as it is used for machining and subject to numerical control. There may be. One or more driving units 212 may be provided.

The numerical control unit 201 executes machining by the machine tool 203 by numerical control. For example, the numerical control section 201 generates and outputs numerical control data for controlling the operation of the driving section 212 . Numerical control unit 201 also outputs context information to communication control unit 202 . The context information is a plurality of pieces of information defined for each type of operation of the processing machine 200 . The context information includes, for example, information identifying the tool 213 driven by the drive unit 212, the number of rotations of the drive unit 212, the rotation speed of the drive unit 212, movement information of the drive unit 212 and the tool 213, and the like.

Numerical control unit 201 transmits, for example, context information indicating the current operation to diagnostic apparatus 100 via communication control unit 202 . When machining a workpiece, the numerical control unit 201 changes the type of tool 213 driven by the drive unit 212 and the drive state (rotation speed, rotation speed, etc.) of the drive unit 212 according to the process of machining. do. The numerical control unit 201 sequentially transmits context information corresponding to the changed type of motion to the diagnostic apparatus 100 via the communication control unit 202 each time the type of motion is changed.

The sensor 211 is a detection unit that detects a physical quantity that changes according to the operation of the processing machine 200 and outputs detection information (sensor data). In this embodiment, a sensor (for example, a microphone) that detects sound during processing (operation sound, grinding sound, etc.), vibration, and the like is used. For example, when the blade of the tool 213 used for processing is broken or chipped, the sound during processing changes. Therefore, a sensor (such as a microphone) detects sound/vibration data. The type of the sensor 211 and the physical quantity to be detected may further include other items. For example, the sensor 211 may be an acceleration sensor or an AE (acoustic emission) sensor, and the detection information may be acceleration data or data indicating an AE wave. Moreover, the number of sensors 211 is arbitrary. A plurality of sensors 211 that detect the same physical quantity may be provided, or a plurality of sensors 211 that detect mutually different physical quantities may be provided.

A communication control unit 202 controls communication with an external device such as the diagnostic device 100 . For example, the communication control unit 202 transmits context information corresponding to the current action and detection information by the sensor 211 to the diagnostic device 100 .

The diagnostic device 100 includes a communication control section 101 and an abnormality detection section 102 . A communication control unit 101 controls communication with an external device such as the processing machine 200 . For example, the communication control unit 101 receives context information and detection information from the processing machine 200 . The abnormality detection unit 102 refers to the context information and the detection information, and determines whether or not the operation of the processing machine 200 is normal using a discriminator.

FIG. 2 is a block diagram showing an example of the hardware configuration of the processing machine 200. As shown in FIG. As shown in FIG. 2, the processing machine 200 includes a CPU (Central Processing Unit) 51, a ROM (Read Only Memory) 52, a RAM (Random Access Memory) 53, a communication I/F (interface) 54, a drive A control circuit 55 and a motor 56 are connected by a bus 58 .

The CPU 51 controls the processing machine 200 as a whole. The CPU 51 executes a program stored in the ROM 52 or the like using the RAM 53 as a work area, for example, thereby controlling the overall operation of the processing machine 200 and realizing the processing function.

Communication I/F 54 is an interface for communicating with an external device such as diagnostic device 100 . The drive control circuit 55 is a circuit that controls driving of the motor 56 . The motor 56 drives tools 213 used for processing, such as drills, cutters, and tables. The motor 56 corresponds to, for example, the driving section 212 in FIG. The sensor 57 is attached to the processing machine 200 , detects physical quantities that change according to the operation of the processing machine 200 , and outputs detection information to the diagnostic device 100 . Sensor 57 corresponds to sensor 211 in FIG. 1, for example.

Numerical control unit 201 and communication control unit 202 in FIG. 1 may be implemented by causing CPU 51 in FIG. 2 to execute programs, that is, by software, or by hardware such as an IC (Integrated Circuit). Alternatively, it may be implemented using both software and hardware.

FIG. 3 is a block diagram showing an example of the hardware configuration of the diagnostic device 100. As shown in FIG. As shown in FIG. 3 , diagnostic device 100 has a configuration in which CPU 61 , ROM 62 , RAM 63 , communication I/F 64 , storage 65 , and I/O 67 are connected via bus 66 .

The CPU 61 controls the diagnosis device 100 as a whole. The CPU 61 executes a program stored in the ROM 62 or the like using the RAM 63 as a work area, for example, thereby controlling the overall operation of the diagnostic apparatus 100 and realizing the diagnostic function. Communication I/F 64 is an interface for communicating with an external device such as processing machine 200 .

The storage 65 is non-volatile storage means such as a HDD (Hard Disk Drive), an EEPROM (Electrically Erasable Programmable Read-Only Memory), or an SSD (Solid State Drive). The storage 65 stores setting information, context information, detection information, and the like. Among these, the context information and detection information are transmitted from the communication control unit 202 of the processing machine 200 .

The I/O 67 connects I/O devices such as an input device 68 such as a mouse and a keyboard, a display 69 such as an LCD and an organic EL, and a speaker 70 for sound output, and exchanges data between the I/O device and the CPU 61 . Do input and output. Speaker 70 may be a headphone speaker or the like.

The numerical control unit 101 and the abnormality detection unit 102 in FIG. 1 may be implemented by causing the CPU 61 in FIG. and hardware may be used in combination.

FIG. 4 is a block diagram showing an example of functions related to the abnormality detection unit 102 of the diagnostic device 100. As shown in FIG.

The control unit 110 controls each unit to perform abnormality detection processing. The storage 120 stores detection information received from the processing machine 200, setting data used in abnormality detection processing, and the like. In the example shown in FIG. 4, the signal data a1 representing the acoustic/vibration waveform corresponds to the detection information. The frequency distribution spectrogram Data is data generated by analyzing the signal data a1. In addition, it stores tables T1 to T4 used for setting labeling of discrimination data (normal or abnormal), and one or more models (discriminator 2000) used for discriminating between normal and abnormal.

The input unit 130 receives operation input by the user from the input device 68 . Display unit 140 displays the display information output from control unit 110 on the screen of display 69 . The sound output unit 150 reproduces the sound/vibration data output from the control unit 110 and outputs it from the speaker 70 . Here, the input unit 130 and the display unit 140 correspond to the "reception unit".

The model (identifier 2000) is generated by learning, for example, using detection information detected when the processing machine 200 is operating normally. Alternatively, depending on the purpose of detection, the model is generated by attaching a new tool 213 and performing predetermined machining to obtain data until the tool 213 becomes abnormal (broken blade, chipping, etc.). The learning method and the format of the learning model may be any method. For example, models such as GMM (Gaussian Mixture Model) and HMM (Hidden Markov Model) and corresponding model learning methods can be applied.

Also, for example, a predetermined machining period after mounting a new tool 213 may be set as a learning period, and a normal state and an abnormal state may be ruled and stored as a model. For example, the first 10 times of machining after a new tool 213 is attached and the machining is started is set as a learning period for determining rules for diagnosis. Diagnosis rule determination may be performed in advance separately from actual processing, and the determined rule may be stored in the storage 120 as a model.

In this embodiment, a model is generated for each piece of context information. For example, context information and a model corresponding to the context information are associated and stored.

FIG. 5 is a diagram showing an example of the configuration of functional blocks related to labeling processing in the diagnostic apparatus 100. As shown in FIG. FIG. 5 shows, as functional blocks related to labeling processing, a frequency analysis processing unit 111, a multivariate analysis processing unit 112, a feature amount display unit 113, a basic information display unit 114, an acoustic data reproduction unit 115, and a labeling unit. It has a work processing unit 116 , a discriminator generation unit 117 , and an anomaly detection unit 118 . Each unit uses the storage 12 to generate the frequency distribution Data from the signal data a1, set tables T1 to T4 by UI display, and generate the discriminator 2000. FIG.

Here, the frequency analysis processing unit 111 and the multivariate analysis processing unit 112 correspond to the "frequency analysis processing unit". The feature amount display section 113 corresponds to the "low-dimensional data display section". The basic information display section 114 and the acoustic data reproduction section 115 correspond to the "high-dimensional data output section". The labeling work processing unit 116 corresponds to the "discrimination data setting unit". The discriminator generator 117 and the anomaly detector 118 correspond to the "discriminator".

The frequency analysis processing unit 111 performs frequency analysis such as Fourier transform on the acquired signal data a1 (sound/vibration data) to calculate frequency characteristics. For example, when one minute of signal data is subjected to Fourier transform with a window length of 20 ms and a shift of 10 ms and divided into 512-dimensional frequency characteristics, a frequency distribution of 5999 frames×512 dimensions is obtained. As an example is shown in FIG. 6, a frequency distribution (a spectrogram is shown in FIG. 6) Data is obtained from the signal data a1 by frequency analysis.

The multivariate analysis processing unit 112 performs multivariate analysis such as principal component analysis and autoencoder from the high-dimensional frequency distribution to calculate low-dimensional feature amounts. For example, the multivariate analysis processing unit 112 performs principal component analysis on the frequency distribution calculated by the frequency analysis processing unit 111 by inputting each frame (Data 1, Data 2, . to calculate a feature quantity (upper principal component) having a frequency distribution feature. FIG. 7 shows a setting example of a feature amount table T1 obtained by reducing the dimension of a high-dimensional frequency distribution by multivariate analysis. In the table T1, the distribution of the feature amount of each Data (Data 1, Data 2, . . . Data n) is reduced to three dimensions (FV1, FV2, FV3) and set.

The feature amount display unit 113 outputs to the display unit 140 information that visualizes the setting of the feature amount obtained by the multivariate analysis processing unit 112 . In other words, the distribution of the visualized feature quantity is displayed on the screen of the display 69 . FIG. 8 shows the distribution of feature quantities visualized in the three-dimensional feature quantity space Q based on the settings in the low-dimensional feature quantity table T1. The points shown in the three-dimensional feature amount space Q are the feature amounts (higher order principal components) of each Data (Data 1, Data 2, . . . Data n). It shows the distribution of feature quantities in a three-dimensional space that is easy for the user to visually grasp. As a result, the user can intuitively grasp the distribution of the feature amount, and can intuitively find a point of interest, such as a group of frequency distributions or an outlier, for example.

The basic information display unit 114 outputs basic information about data selected by the user from the feature amount space Q to the display unit 140 . FIG. 9 shows basic information q1 related to data selected by the user from the feature amount space Q. As shown in FIG. The feature amount space Q is extracted by multivariate analysis, and does not necessarily express all the information inherent in the data. It is also difficult to fully understand what each feature value means. Therefore, intuitive understanding is supported by presenting basic information such as signal data (waveform of sound/vibration data) a1 and frequency distribution Data as original information of data selected by the user.

The sound data reproduction unit 115 displays a UI (User Interface) for sound operation on the screen, and outputs the sound/vibration data of the data selected by the user from the feature quantity space Q to the sound output unit 150 for reproduction. . FIG. 10 shows an example of a UI for sound operation. When the user performs a reproduction operation on the UI 1000 for sound operation shown in FIG. 10, the sound/vibration data (for example, sound during processing) selected by the user from the feature amount space Q is reproduced by the sound data reproduction unit 115. do. Many items can be grasped visually by the processing up to the basic information display unit 114 . However, maintenance personnel perceive the site conditions with their ears, and hearing with their ears is important when judging whether it is normal or abnormal. Therefore, by directly listening to the sound/vibration data, the user can assist the labeling work in which the user's knowledge is reflected.

The labeling work processing unit 116 accepts labeling by the user and saves the result in the table T2. FIG. 11 shows an example of a UI 1100 for the user to label. The UI 1100 displays a list of setting information for setting whether each feature amount is normal or abnormal, and receives input of each setting. For example, when the user selects data from the feature amount space Q, the UI 1100 enables the user to input or change settings corresponding to the selected data. As an example, the UI 1100 shows "choice" as an acceptable setting. The user sets whether the setting specified by "choice" is normal (Normal) or abnormal (Abnormal). In this embodiment, normal is set by default, and the setting is changed from normal to abnormal only when abnormal, but it is also possible to change the setting from abnormal to normal. By thus labeling the selected sound/vibration data as abnormal, either Normal or Abnormal is set in the label column of the table T2.

The discriminator generation unit 117 generates the discriminator 2000 using the labeled sound/vibration data for which the labeling of the table T2 has been completed, and stores the generated discriminator 2000 . FIG. 12 shows an explanatory diagram of the process of generating the discriminator 2000. As shown in FIG. As shown in FIG. 12, the discriminator generation unit 117 generates a discriminator 2000 based on the setting of the label column of the table T2. For example, the discriminator 2000 that calculates how much deviation is compared to the normal time by performing machine learning such as One-Class SVM and autoencoder using only normal data among the settings of the label column to generate

The abnormality detection unit 118 uses the generated discriminator 2000 to detect whether the sound/vibration data (set in the table T3) to be detected for abnormality is abnormal, and the detection result, that is, whether it is normal or abnormal. is stored in table T4. FIG. 13 shows an explanatory diagram of abnormality detection of sound/vibration data using the discriminator 2000 and storage of the detection result. As shown in FIG. 13, signals (sound/vibration data) to be detected are set in a table T3. The abnormality detection unit 118 uses the generated classifier 2000 to detect whether or not the sound/vibration data in the table T3 is abnormal, and saves the detection result in the table T4. In this way, sound/vibration data not used for analysis can be detected for abnormalities using a discriminator, and the results of the detection can be used as indicators for maintenance work.

FIG. 14 is a diagram showing an example of the overall configuration of a UI screen on which a user performs labeling processing. FIG. 14 includes a feature space display area E1, a basic information display area E2 for displaying signal data (sound/vibration data) a1 and frequency distribution data, a sound reproduction operation area E3, and a label setting area E4. be Each area may be displayed on one screen, or may be divided into a plurality of screens and switched by pressing a tab or button.

FIG. 15 is an example of a UI screen. FIG. 15 shows a screen when the feature space display area E1 and the waveform of the basic information display area E2 are displayed. In the feature amount space display area E1, groups of frequency distributions are grouped by color and displayed so that the user can intuitively grasp the feature amount distribution. This makes it easier to intuitively find the point of interest. In addition, in FIG. 15, for the sake of explanation, areas of the same color for four of the six groups are indicated by enclosed lines (broken lines). Enclosing lines are omitted for the other two groups. The basic information display area E2 shows the waveform data and the spectrogram of the feature points (marked with x) selected in the feature space display area E1.

Next, a flow of labeling processing performed by the control unit 110 of the diagnostic device 100 will be described. This labeling process is performed by executing the program of the ROM 62 by the CPU 61, thereby realizing each function shown in FIGS.

FIG. 16 is a diagram showing an example of the flow of labeling processing performed by the control unit 110 of the diagnostic device 100. As shown in FIG. The control unit 110 acquires the signal data a1 stored in the storage 120, and first performs frequency analysis (step S11). Subsequently, the control unit 110 performs multivariate analysis on the frequency distribution Data obtained by the frequency analysis (step S12), and saves the obtained feature amount in the table T1 (step S13). Note that the steps up to this point may be automatically performed after the program is started.

After that, when receiving an input operation to start analysis from the user, the control unit 110 displays a feature amount screen (see FIG. 14) showing each feature in a three-dimensional feature amount space based on the setting of the feature amounts stored in the table T1. is displayed (step S21). At this stage, no data is selected from the feature amount space, so no data is displayed in the basic information display area E2. Also, "choice" is not displayed in the label setting area.

Subsequently, when one of the data is selected from the feature amount space by the user's input operation, the basic information corresponding to that data is displayed in the basic information display area E2 (basic information screen) (step S22).

Subsequently, when the user operates the UI for sound operation and accepts sound reproduction, the control unit 110 reproduces the corresponding sound data and outputs it from the speaker (step S23).

When the user operates the UI 1100 for labeling and selects abnormal (or normal) for the data being selected, the control unit 110 updates the setting of the data to the setting labeled by the user (step S24). ).

When another piece of data in the feature space is subsequently selected by the user's input operation, the control unit 110 repeats steps S22 to S24 to label that data. When the selection of labeling by the user ends, the control unit 110 saves the setting of the labeled sound/vibration data after labeling in the table T2 (step S25).

Then, the control unit 110 generates the discriminator 2000 based on the setting of the stored labeled sound/vibration data (step S26), and stores the generated discriminator 2000 (step S27).

After that, the control unit 110 acquires sound/vibration data for detection, performs abnormality detection by the stored classifier 2000 (step S28), and stores the detection result (step S29).

The above-described flow can be operated by the CPU executing the program, but the functional blocks assigned in FIG. 16 may be realized by hardware and performed by hardware. Also, part of each function may be realized by a program and the rest may be realized by hardware.

When the labeling function described in the present embodiment is realized by executing a program, the program may be provided by being incorporated in a ROM in advance. In addition, it is provided by being recorded in a computer-readable recording medium such as a CD-ROM, a flexible disk (FD), a CD-R, a DVD (Digital Versatile Disk), etc. as a file in an installable format or an executable format. good too. Alternatively, the software may be stored on a computer connected to a network such as the Internet, and provided by being downloaded via the network.

Also, the labeling function described in the present embodiment can be provided in the form of an arithmetic device including some or all of the functional blocks, or in the form of various devices including the arithmetic device. The computing device is, for example, a computing device having a CPU and a ROM in which a program is written.

As described above, in the present embodiment, the sound/vibration data is analyzed, and the analysis results are displayed in a low-dimensional (three-dimensional in this example) display that allows the user to intuitively judge whether the data is normal or abnormal. . Therefore, it becomes easier for the user to intuitively find data that seems to be abnormal from a huge amount of sound/vibration data. In addition, since the original sound/vibration data can be reproduced and the sound can be heard, whether or not the data is really abnormal can be easily and accurately determined. In other words, according to this embodiment, the user does not need to label all the data one by one. Therefore, the user can efficiently perform the labeling work. In addition, the setting of normal or abnormal is the result of judgment by the user by actually listening to the sound. Data can be set as normal. By generating a classifier with high accuracy in this way, even if a minor failure occurs in a device to be diagnosed, such as a processing machine, if it can be operated, it does not become abnormal and can be continued to be used as normal.

In addition, it can be widely applied to various things, not limited to processing machines. A suitable type of sensor is used according to the physical quantity to be read from the object to be detected. It can handle a wide range of objects to be detected, from large objects such as windmills that generate wind power to small objects such as measuring instruments. For example, when acquiring a sound (such as an operation sound) emitted by a detection target, a microphone is arranged as a sensor. Also, when reading the acceleration of the detection target, the rotation speed of the detection target, or the like, an acceleration sensor, a speed sensor, or the like is arranged on the detection target. Further, the sensor may be a camera having an image sensor such as a CCD or CMOS that captures images of the detection target and its surroundings.

100 diagnostic device 102 abnormality detection unit 111 frequency analysis processing unit 112 multivariate analysis processing unit 113 feature amount display unit 114 basic information display unit 115 acoustic data reproduction unit 116 labeling work processing unit 117 discriminator generation unit 118 abnormality detection unit 130 input unit 140 display unit 211 sensor 202 communication control unit

JP 2004-246622 A

Claims (7)

A system having a device to be diagnosed and a diagnostic device for diagnosing the device,
The device to be diagnosed is
Having an output unit that outputs a signal indicating a change in the physical quantity of the diagnosis target,
The diagnostic device
a frequency analysis processing unit that performs frequency analysis on an output signal that indicates a change in the physical quantity of the diagnosis target that is output by the output unit;
a low-dimensional data display unit that displays the low-dimensional feature amount obtained by the frequency analysis with the low-dimensional setting;
a reception unit that receives selection of one data from the data displayed by the low-dimensional data display unit;
a high-dimensional data output unit that outputs high-dimensional information of the selected data;
a discrimination data setting unit for setting discrimination data of the data received by the reception unit;
a discrimination unit that discriminates an output signal indicating a change in the physical quantity to be diagnosed based on the discrimination data set by the discrimination data setting unit;
A system characterized by comprising: The low-dimensional data display unit displays the low-dimensional feature amount in three dimensions, which is the low-dimensional setting.
2. The system of claim 1, wherein: The low-dimensional data display unit displays the low-dimensional feature amount by color-coding for each group,
3. A system according to claim 1 or 2, characterized in that: the output signal indicating the change in the physical quantity is acoustic data or vibration data;
The high-dimensional data output unit outputs the acoustic data or the vibration data as the high-dimensional information.
3. A system according to claim 1 or 2, characterized in that: The high-dimensional data output unit outputs the sound of the acoustic data or the vibration data from a speaker,
5. The system of claim 4, wherein: a frequency analysis processing unit that performs frequency analysis on an output signal that indicates a change in physical quantity to be diagnosed;
a low-dimensional data display unit that displays the low-dimensional feature amount obtained by the frequency analysis with the low-dimensional setting;
a reception unit that receives selection of one data from the data displayed by the low-dimensional data display unit;
a high-dimensional data output unit that outputs high-dimensional information of the selected data;
a discrimination data setting unit for setting discrimination data of the data received by the reception unit;
a discrimination unit that discriminates an output signal indicating a change in the physical quantity to be diagnosed based on the discrimination data set by the discrimination data setting unit;
A computing device characterized by comprising: the computer,
a frequency analysis processing unit that performs frequency analysis on an output signal that indicates a change in physical quantity to be diagnosed;
a low-dimensional data display unit that displays the low-dimensional feature amount obtained by the frequency analysis with the low-dimensional setting;
a reception unit that receives selection of one data from the data displayed by the low-dimensional data display unit;
a high-dimensional data output unit that outputs high-dimensional information of the selected data;
a discrimination data setting unit for setting discrimination data of the data received by the reception unit;
A program for functioning as a discriminating unit that discriminates an output signal indicating a change in the physical quantity of the diagnosis target based on the discriminating data set by the discriminating data setting unit.

Images