JPH08219955A - Diagnostic system for machine - Google Patents

Abstract

PURPOSE: To obtain a diagnostic system for machine in which reliability is enhanced in the diagnosis of abnormality by detecting the micro difference in the sound generated from the machine containing an oscillatory element or in the oscillatory state thereof. CONSTITUTION: The diagnostic system for machine comprises means 7, 9, 10, 12 for detecting a sound S generated from a machine 1 or oscillation thereof, a wavelet converter 16 producing a conversion data Yij, and a processor 20 for detecting abnormality of the machine based on the conversion data. The processor 20 comprises means for operating the features of conversion data, means for comparing the operated value with a preset reference value, and means for delivering an alarm A when the operated value exceeds a predetermined relationship with respect to the reference value.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention detects a sound or vibration generated from an automobile component such as a transmission or an engine (hereinafter simply referred to as a component) or a device including a vibration element such as various facilities and machines. The present invention relates to a device diagnostic device for detecting an abnormality, and more particularly to a device diagnostic device with improved reliability of abnormality diagnosis.

[0002]

2. Description of the Related Art In general, components having a vibration source, for example, components such as transmissions mounted on mass-produced automobiles, need to be checked for defects at the production stage to prevent defective products from leaking to the market. This is because, for example, when a defective transmission resulting from defective machining or assembly of parts is mounted on an automobile and used, abnormal noise is generated from the transmission, and the transmission may be damaged. This is because there is a possibility that various inconveniences may be caused by the failure of.

Therefore, for example, in order to deal with the case where a defective transmission occurs, it is necessary to detect an abnormality in the transmission and take a pre-treatment before mounting the transmission on an automobile. The above is extremely important for quality control of transmission production.

FIG. 18 shows, for example, the Society of Automotive Engineers,
"Onomatopoeia investigation report of car, mainly on passenger car noise, March 1992", edited by Vibration and Noise Division Committee (19
It is a block diagram which shows the conventional diagnostic apparatus of the transmission (apparatus) inferred from the content described in April 1, 1992). In the figure, reference numeral 1 denotes a device having a vibration source, for example, a transmission, which is configured by the following elements 2 to 6.

Reference numeral 2 designates, for example, a first shaft serving as an output shaft, 3 a second shaft for transmitting a rotational force to the first shaft 2, and 4 a first shaft 2 and a second shaft 3. It is a plurality of gears that are engaged at different gear ratios. Reference numeral 5 denotes a clutch provided corresponding to, for example, the input shaft, and selectively disengages the input shaft from the second shaft 3. 6 is a speed change mechanism (corresponding to a shift lever) for selecting the gear 4 of the transmission 1 by manual operation.
Is.

Reference numeral 7 denotes a microphone that detects a sound S generated from the transmission 1 including the first shaft 2 to the transmission mechanism 6 and outputs an electric signal E corresponding to the detected sound S. Reference numeral 9 amplifies the electric signal E. The amplifier 10 is a filter for passing a predetermined frequency component of the amplified electric signal E to be detected, 11
Is a sound pressure calculation device that calculates the sound pressure P from the electric signal E that has passed through the filter 10.

Reference numeral 12 is an A for converting the sound pressure P calculated by the sound pressure calculation device 11 from an analog signal to a digital signal.
A D converter, 13 is a CPU (central processing unit) for judging an abnormality of the transmission 1 based on the digitally converted sound pressure P,
Reference numeral 14 is an automatic range switching device that sets the optimum range of the AD converter 12 according to the sound pressure P output from the sound pressure calculation device 11, and 15 is an output device that displays or prints the determination result of the CPU 13.

Examples of equipment including a vibration source that generates noise or vibration include not only the transmission 1 but also other components such as an engine. FIG. 19 is a configuration diagram showing a general automobile engine (hereinafter, simply referred to as an engine), and 31 is an engine including the following elements 32 to 36.

Reference numeral 32 is a crankshaft which is driven to rotate by combustion of the fuel mixture, 33 is a piston which is connected to the crankshaft 32 and is pressed down when the fuel mixture explodes, and 34 is exhaust gas at the time of intake of the fuel mixture and after combustion. A valve 35 is opened and closed when gas is exhausted, a camshaft 35 rotates once while the crankshaft 32 rotates twice, and a cam 36 is fixed to the camshaft 35 and controls the drive timing of the valve 34 and the like. The diagnostic device including the microphone 7 to the output device 15 in FIG. 18 may be provided for the engine 31 as shown in FIG.

Next, taking the case of the transmission 1 as an example, FIG.
The operation of the conventional apparatus diagnostic device shown in FIG. First, the transmission 1
When the vehicle is driven, the second shaft 3 engaged with the input shaft by the operation of the clutch 5 transmits the rotational force to the first shaft 2 via the gear 4 selected by the speed change mechanism 6. At this time, the sound S generated from the transmission 1 is detected by the microphone 7 and converted into an electric signal E. The electric signal E obtains an appropriate gain through the amplifier 9 and an appropriate gain through the filter 10. After the frequency band is extracted, it is input to the sound pressure calculation device 11.

The sound pressure calculation device 11 calculates the effective value of the sound pressure P based on the electric signal E, and the AD converter 12 converts the sound pressure P into digital data and transfers it to the CPU 13. At this time, the automatic range switching device 14 uses the AD converter 1
In order to perform the optimum AD conversion in 2, the range is automatically switched.

The CPU 13 compares the digital data indicating the sound pressure P transferred from the AD converter 12 with the reference effective value (abnormality judgment reference) preset in the CPU 13, and the sound pressure P is determined as the reference effective value. When it exceeds, it is determined that the transmission 1 has an abnormality, and the abnormality determination result is output to the output device 15. Thereby, the observer can recognize the abnormality of the transmission 1 and deal with the abnormality before mounting the transmission 1 on the vehicle.

However, the sound S generated from the transmission 1
The difference in the effective value of is between the normal state and the abnormal state is very small. Further, the effective value of the generated sound S in the normal state of the transmission 1 may exceed the effective value in the abnormal state. Therefore, with the configuration of FIG. 18, it is difficult to accurately distinguish between the normal state and the abnormal state of the transmission 1. The same applies when the engine 31 (see FIG. 19) is targeted as another component.

[0014]

As described above, the conventional diagnostic apparatus for equipment is abnormal only when the effective value of the sound S generated from the transmission 1 exceeds a certain alarm value (reference effective value). Since the difference between the effective value of the generated sound S in the normal state and the abnormal state is small, the effective value in the normal state may exceed the effective value in the abnormal state. Therefore, there is a problem that the abnormality cannot be accurately determined.

The present invention has been made in order to solve the above-mentioned problems, and discriminates a slight difference between a normal state and an abnormal state of sound or vibration generated from equipment,
It is an object of the present invention to obtain a device diagnostic device with improved reliability of abnormality diagnosis.

[0016]

According to a first aspect of the present invention, there is provided a device diagnostic apparatus which detects a sound or a vibration generated from a device including a vibrating element and outputs a signal corresponding to the sound or the vibration. Means, a wavelet transform calculator for performing wavelet transform on the signal and outputting the transformed data, and an abnormality detection processing device for detecting an abnormality of the device based on the transformed data. A calculation means for calculating the characteristic and outputting the calculated value, a comparison means for comparing the calculated value with a preset reference value, and a calculated value having a predetermined relationship with the reference value based on the comparison result of the comparison means. It also includes an alarm means for outputting an alarm when the number is exceeded.

According to a second aspect of the present invention, there is provided a device diagnosis apparatus according to the first aspect, wherein the reference value is set based on a signal obtained when the device is in a normal state.

Further, a diagnostic device for equipment according to a third aspect of the present invention is the apparatus according to the first or second aspect, further comprising a visualization means for visualizing at least one of the converted data, the calculated value and the reference value. is there.

According to a fourth aspect of the present invention, there is provided a device diagnostic apparatus, which detects a sound or a vibration generated from a device including a vibrating element and outputs a signal corresponding to the sound or the vibration, and a signal detecting means. A wavelet transform calculator that performs wavelet transform on the output data and outputs the converted data, and an abnormality detection processing device that detects an abnormality of the device based on the converted data.The abnormality detection processing device calculates the characteristics of the converted data. And outputs a calculated value, and a visualization means for visualizing at least one of the converted data and the calculated value.

According to a fifth aspect of the present invention, there is provided a device diagnosing device according to any one of the first to fourth aspects, wherein a device state detecting means for detecting a predetermined state of the equipment is provided, and the signal detecting means is The operation is started in response to a predetermined state.

According to a sixth aspect of the present invention, there is provided a device diagnostic apparatus according to any one of the first to fifth aspects, wherein the arithmetic means calculates the energy component in a predetermined frequency component region with respect to the converted data. It is configured by an average value calculator that outputs the average value of the distribution as the calculated value.

According to a seventh aspect of the present invention, there is provided a diagnostic apparatus for equipment according to any one of the first to fifth aspects, wherein the calculating means determines the energy component in the predetermined frequency component region with respect to the converted data. It is configured by a variance value calculator that outputs the variance value of the distribution as a calculated value.

According to an eighth aspect of the present invention, there is provided a device diagnostic apparatus according to any one of the first to fifth aspects, in which the calculating means determines the energy component in the predetermined frequency component region with respect to the converted data. It is configured by a skewness calculator that outputs the skewness of the distribution as a calculated value.

According to a ninth aspect of the present invention, there is provided a diagnostic apparatus for equipment according to any one of the first to fifth aspects, in which the arithmetic means calculates the energy component in the predetermined frequency component region with respect to the converted data. The kurtosis calculator is configured to output the kurtosis of the distribution as a calculated value.

According to a tenth aspect of the present invention, there is provided a device diagnostic apparatus according to any one of the first to fifth aspects, wherein the arithmetic means is configured to calculate the energy component in a predetermined frequency component region with respect to the converted data. It is composed of a maximum value calculator that outputs the maximum value of the distribution as a calculated value.

According to an eleventh aspect of the present invention, in the apparatus diagnostic apparatus according to any one of the first to fifth aspects, the calculating means is configured to calculate the energy component in the predetermined frequency component range with respect to the converted data. It is configured by a neural network calculator that outputs the learning value of the distribution neural network as a calculated value.

According to a twelfth aspect of the present invention, in the apparatus diagnostic apparatus according to any one of the first to fifth aspects, the calculation means is configured to calculate the energy component in the predetermined frequency component region with respect to the converted data. It is composed of a probability density distribution function calculator that calculates a probability density distribution function of distribution, and a feature extractor that outputs the characteristics of the probability density distribution function according to fuzzy rules as calculation values.

According to a thirteenth aspect of the present invention, in the apparatus diagnostic apparatus according to any one of the first to fifth aspects, the calculating means is configured to calculate the energy component in the predetermined frequency component region with respect to the converted data. It is configured by a variance value deviation calculator that outputs the deviation between the distribution dispersion value and the maximum value as a calculation value.

[0029]

According to the first aspect of the present invention, the comparison result when the signal detected corresponding to the sound or vibration generated from the device is wavelet-transformed and the calculated value showing the characteristic of the converted data is compared with the reference value. Based on the above, an alarm is output when the calculated value exceeds a predetermined relationship with the reference value. As a result, if only the signals exist in the normal state, the calculated value will be close to the normal value, and the alarm will not be erroneously output.

Further, according to the second aspect of the present invention, the reference value is set based on the signal detected when the device is in the normal state, and the abnormality determination of the device is ensured.

According to the third aspect of the present invention, the contents of at least one of the converted data, the calculated value and the reference value are visualized and displayed to the observer to improve the reliability of the abnormality determination of the equipment.

Further, in claim 4 of the present invention, the contents of at least one of the converted data and the calculated value are visualized and displayed to the observer to improve the reliability of the abnormality determination of the equipment.

Further, in the fifth aspect of the present invention, when the predetermined state of the device is detected, the operation of the signal detecting means is started to improve the detection reproducibility of the signal to ensure the abnormality determination of the device.

According to the sixth aspect of the present invention, the average value of the energy component distribution in the predetermined frequency component region is calculated with respect to the transform data obtained by wavelet transforming the detected signal, and the average value becomes the reference value. An alarm is output when a predetermined relationship is exceeded. As a result, if only the signals exist in the normal state, the average value becomes close to the normal value, and the alarm is not erroneously output.

According to a seventh aspect of the present invention, the variance value of the energy component distribution in the predetermined frequency component region is calculated for the transform data obtained by performing the wavelet transform on the detected signal, and the variance value becomes the reference value. An alarm is output when a predetermined relationship is exceeded. As a result, if only the signals exist in the normal state, the variance value becomes close to the normal value, and the alarm is not erroneously output.

Further, in the eighth aspect of the present invention, the skewness of the energy component distribution in the predetermined frequency component region is calculated for the transform data obtained by performing the wavelet transform on the detected signal, and the skewness becomes the reference value. An alarm is output when a predetermined relationship is exceeded. As a result, if only the signals exist in the normal state, the skewness becomes close to the normal value,
No alarm is output erroneously.

In the ninth aspect of the present invention, the kurtosis of the energy component distribution in the predetermined frequency component region is calculated with respect to the transform data obtained by performing the wavelet transform on the detected signal, and the kurtosis is set to the reference value. An alarm is output when a predetermined relationship is exceeded. As a result, the kurtosis will be close to the normal value if only the signals exist in the normal state.
No alarm is output erroneously.

In the tenth aspect of the present invention,
The maximum value of the energy component distribution in the predetermined frequency component region is calculated for the converted data obtained by wavelet transforming the detected signal, and an alarm is output when the maximum value exceeds the predetermined relationship with the reference value. . As a result, if only the signals existing in the normal state are present, the maximum value becomes close to the normal value, so that the alarm is not erroneously output.

In the eleventh aspect of the present invention,
The learning value of the neural network of the energy component distribution in the predetermined frequency component area is calculated for the converted data obtained by wavelet transforming the detected signal, and an alarm is issued when the learning value exceeds the predetermined relationship with the reference value. Is output. As a result, if only the signals exist in the normal state, the learning value of the neural network becomes close to the normal value, so that the alarm is not erroneously output.

According to claim 12 of the present invention,
The probability density distribution function of the energy component distribution in the predetermined frequency component area is calculated for the transform data obtained by wavelet transforming the detected signal, and the feature of the probability density distribution function based on the fuzzy rule has a predetermined relationship with the reference value. An alarm is output when the value exceeds. As a result, if only the signals exist in the normal state, the features of the probability density distribution function according to the fuzzy rules are close to the normal values, so that the alarm is not erroneously output.

In the thirteenth aspect of the present invention,
The deviation between the maximum value and the variance value of the energy component distribution in the predetermined frequency component area is calculated for the transform data obtained by wavelet transforming the detected signal, and the variance value deviation exceeds the predetermined relationship with the reference value. An alarm is output when As a result, if only the signals exist in the normal state, the variance value deviation is close to the normal value, and the alarm is not erroneously output.

[0042]

【Example】

Example 1. Embodiment 1 of the present invention will be described below with reference to the drawings. 1 to 4 are block diagrams showing a schematic configuration of Embodiment 1 of the present invention, and FIG. 5 is a functional block diagram showing a specific configuration example of the abnormality detection processing device in FIGS. 1 to 4.

In each figure, 1 to 7, 9, 10, 12,
S and E are the same as described above. A microphone 7 (see FIGS. 1 and 3) that detects a sound S generated from a device including a vibration element, for example, the transmission 1 and outputs an electric signal E corresponding to the generated sound S is an amplifier 9 that processes the electric signal E. , The filter 10 and the AD converter 12 constitute signal detecting means.

Reference numeral 16 is an amplifier 9, a filter 10 and an AD.
A wavelet transform calculator that performs a wavelet transform on the electric signal E that has passed through the converter 12, and is three-dimensional data Yij (see FIGS. 1 and 2) or column data Yi.
(See FIGS. 3 and 4) is output as converted data.
Reference numeral 17 is a parameter setter for externally setting parameters used in the wavelet transform calculator 16 and calculation modes. Wavelet transform calculator 1
6 performs wavelet transformation according to the parameters set by the parameter setter 17.

Three-dimensional data Yij (i = 1, 2, ...,
N) (j = 1, 2, ..., M) is a wavelet transform of time series data corresponding to the voltage level of the sound S detected by the microphone 7 or the vibration detector 18 or the electric signal E corresponding to the vibration. It is digital data obtained by, and consists of time-series frequency component sequence data. The three-dimensional data Yij is the two-dimensional digital string data Yi.
Can be output as

Reference numeral 18 denotes a vibration detector (see FIGS. 2 and 4) provided in the transmission 1 instead of the microphone 7.
A vibration generated from the transmission 1 is detected, an electric signal E corresponding to the vibration is output, and the amplifier 9, the filter 10, and the AD converter 12 constitute a signal detection means.

Reference numeral 19 denotes a phase detector provided on the input shaft of the transmission 1, which constitutes a device state detecting means for detecting a predetermined state of the transmission 1, and which is located at an arbitrary position (for example, phase) of the rotational phase. The detection signal is output at an angle of 10 °) and is input to the AD converter 12 in the signal detection means. AD converter 1
2 starts the AD conversion operation of the electric signal E in response to the predetermined state indicated by the detection signal from the phase detector 19.

Reference numeral 20 denotes an abnormality detection processing device for detecting an abnormality of the transmission 1 based on the converted data (three-dimensional data Yij or column data Yi), which is composed of a CPU for performing various arithmetic processing on the converted data. As shown in FIG.
It is composed of 24 and 26 elements. Although FIG. 5 shows the case where the conversion data is the three-dimensional data Yij, it can be similarly applied to the column data Yi.

In FIG. 5, 21 is the three-dimensional data Yij.
An arithmetic unit that calculates the characteristics of (converted data) and outputs an arithmetic value μ, 22 is a reference value setter that sets a reference value μr learned in advance based on the arithmetic value μ, and 23 is an arithmetic value μ and a reference value. It is a comparator for comparing with μr and outputting a comparison result. The reference value μr used in the comparator 23 is set by the three-dimensional data Yij based on the electric signal E detected when the transmission 1 is in the normal state, as shown by the broken line.

Reference numeral 24 is an alarm device which operates based on the comparison result of the comparator 23, and outputs an alarm A when the calculated value μ exceeds a predetermined relationship with the reference value μr. Reference numeral 26 is a visualizer for visualizing and displaying various data values and the like, and visualizes at least one of the converted data, that is, the three-dimensional data Yij, the characteristic of the converted data, that is, the calculated value μ and the reference value μr.

The abnormality detection processing device 20 has two operation modes (a setting mode of the reference value μr and a diagnosis mode of the transmission 1) which are switched by an external command based on a manual operation or the like. In addition, in FIG. 5, the broken arrow indicates the flow of each signal in the reference value setting mode, and the solid arrow indicates the flow of each signal in the diagnostic mode of the transmission 1 (device). The same flow applies to each of the embodiments described later.

Hereinafter, with reference to FIGS. 1 to 5, as in the above, as a device having a vibration source for generating noise,
Taking the case of the transmission 1 as an example, a specific operation of the first embodiment of the present invention will be described.

Even if the microphone 7 is used as shown in FIGS. 1 and 3 as a signal detector for outputting a signal corresponding to sound or vibration generated from the device, that is, the electric signal E, the signal detector shown in FIGS. Thus, the vibration detector 18 may be used. The conversion data input to the abnormality detection processing device 20 is the three-dimensional data Y as shown in FIGS.
Even if ij is used, as shown in FIGS. 3 and 4, the column data Yi
May be used.

First, the AD converter 12 includes the phase detector 19
In response to the detection signal (operation command) from the electric signal E, the electric signal E passing through the amplifier 9 and the filter 10 is sampled at equal intervals, and time-sequential N column data (digital signal) is sampled.
Is output.

Subsequently, the wavelet transform calculator 16
Performs wavelet conversion on the electric signal E converted into a digital signal by the AD converter 12 as in the following formula (1), and the three-dimensional data Yij (or column data Yi) is converted into conversion data. Output.

Φ (to, a) = (1 / √a) ∫g [(t-to) / a] · X (t) ... (1)

However, in the equation (1), the calculation range of the integral term is −∞ to ∞, to represents a time series, and a represents a sequence of frequency components. X (t) corresponds to the time series data obtained from the electric signal E, and g [(t-to) /
a] corresponds to a function called a basis function.

The wavelet transform method based on the equation (1) is described, for example, in "Interface" by CQ Publishing Co., Ltd. (January 1994, Keiichiro Minami and Satoshi Kawada), Chapter 4, "Characteristic changes with time." New Signal Analysis Method (Time-Frequency Analysis) "(p. 117-119). Here, the basis function can be expressed using a function such as MexicanHat as in the following Expression (2).

[0059] ^{g (t) = (d 2} / dt 2) exp (-t 2/2) ... (2)

Thus, the three-dimensional data Yij is obtained by performing the wavelet transform of the equation (1) on the electric signal E detected during the diagnosis of the transmission 1. Further, in the equation (1), for example, the frequency component sequence a
Is set to be constant, the three-dimensional data is converted into column data Yi.
Can also be output as

The arithmetic unit 21 in the abnormality detection processing device 20 is
The wavelet-transformed three-dimensional data Yij is taken in, and index data indicating the property of the three-dimensional data Yij is output as a calculation value μ. The index-based calculated value μ indicating the property of the three-dimensional data Yij is, for example, three-dimensional data Yij.
Is an energy component at a predetermined frequency when frequency analysis is performed, it is expressed by the following equation (3).

Μ = F (ω) = (1 / 2π) ∫f (t) · e ^−j ω ^t (3)

However, in the equation (3), the calculation range of the integral term is −∞ to ∞. Further, the reference value setting device 22 is a data (calculated value) learned in advance in the reference value setting mode (see the broken line in FIG. 5) based on the three-dimensional data Yij obtained when the transmission 1 is normal. Is output as a reference value μr. The reference value μr may be stored in advance in the reference value setter 22 using a transmission that is a normal sample.

On the other hand, in the diagnostic mode of the transmission 1 (see the solid line in FIG. 5), the comparator 23 compares the calculated value μ from the calculator 21 with the reference value μr from the reference value setter 22, The comparison result indicating whether or not the transmission 1 is abnormal is output.
That is, the comparator 23 determines that the calculated value μ (diagnosis data) has a predetermined relationship with the reference value μr (for example, the reference value μr).
3 times), the comparison result indicating an abnormality of the transmission 1 is output.

Therefore, the alarm device 24 determines the abnormality of the transmission 1 in response to the comparison result from the comparator 23, and issues the alarm A. At this time, the visualizer 26 displays at least one or all of the three-dimensional data Yij, the calculated value μ and the reference value μr to the observer so that the contents of the detected data and the calculated data can be easily grasped.

For example, when the device to be diagnosed is the engine 31 (see FIG. 19), the visualizer 26 determines that the operation timing of the intake valve of the second cylinder is 0.1 from the start of data measurement.
If it is after 2 seconds, the data of only 0.02 seconds after 0.1 seconds of the obtained three-dimensional data Yij is displayed to the observer. Such data display portions may be set for a plurality of times and may be arbitrarily switched according to a request.

The above series of operations in the diagnostic mode of the transmission 1 (apparatus) is repeated, for example, in a fixed cycle. Thus, the electrical signal E from the transmission 1 in the normal state is
Based on the above, the operation of the reference value setting mode is executed in advance, the learned reference value μr is stored, and then the operation of the diagnostic mode is executed at the time of device diagnosis to generate from each transmission 1 to be diagnosed. The calculated value μ indicating the property of the sound S or vibration is sequentially obtained, and this calculated value μ is compared with the reference value μr in the normal state.

As a result, when the electric signal E in the diagnostic mode indicates an abnormality of the transmission 1 and the difference in the calculated value μ with respect to the reference value μr is large (exceeds a predetermined relationship), the alarm device 24 indicates an abnormality. The alarm A shown can be reliably generated. On the other hand, the electric signal E in the diagnostic mode is the transmission 1
If it indicates a normal state of, the calculated value μ is the reference value μr
It is equivalent to (normal), and the alarm device 24 does not generate the alarm A.

As described above, by using the transform data (Yij or Yi) obtained by performing the wavelet transform on the electric signal E for the diagnosis, the sound S or the vibration is divided into the time axis and the frequency component axis to obtain the distribution of the energy component. be able to.

That is, a change in the frequency component of the generated energy component with time of the electric signal E, a change in the energy component with time of the predetermined frequency component, etc. are found, and a subtle difference in sound quality or vibration is calculated from the calculated value μ. Can be diagnosed.

The above diagnosis is effective when the abnormality of the electric signal E is caused not by the sound pressure of the generated sound S but by the difference in sound quality, for example, when the bearing of the transmission 1 is improperly assembled. Therefore, a reliable diagnosis can be performed by a relatively simple process as shown in the above formula (3).

Further, as shown in FIG. 1, if the generated sound S is detected by using the microphone 7, the sound S can be detected in a non-contact manner, which adversely affects the surface shape and material of the diagnostic object. Diagnosis can be performed without giving.
On the other hand, as shown in FIG.
By directly detecting the generated vibration of the electric signal E, it is possible to prevent the influence of other noise and noise (background noise).
The ratio can be increased to improve the reliability of diagnosis.

Although the microphone 7 or the vibration detector 18 is used as the signal detecting means in the case of detecting the sound S or the vibration generated from the device, the electromagnetic wave is detected by using the optical sensor or the heat sensor. Alternatively, the electric signal E can be obtained by detecting light or heat.

Example 2. Although the specific processing of the calculator 21 is not described in the first embodiment, for example, an average value may be calculated for the converted data. Figure 6
Is a functional block diagram showing a configuration of an abnormality detection processing device 20 according to a second embodiment of the present invention using an average value calculator 21A as calculating means, and Yi and A are the same as those described above. In addition, 21A to 24A, 26A, μ1 and μ
1r corresponds to 21 to 24, 26, μ and μr in FIG. 5, respectively.

Although the column data Yi is used as the conversion data input to the abnormality detection processing device 20 in FIG. 6, three-dimensional data Yij may be used. Further, the peripheral configuration (not shown) may be any of the configurations shown in FIGS. The above also applies to other embodiments described later.

In this case, the average value calculator 21A in the abnormality detection processing device 20 calculates the average value μ1 of the distribution of the energy component in the predetermined frequency component region for the column data Yi (converted data) as the calculated value (electrical signal). It is output as a feature of the column data Yi based on E).

Further, the average value setter 22A stores the average value output from the average value calculator 21A in the reference value setting mode as the reference value μ1r, and the comparator 23A stores the average value μ1 and the reference value in the diagnostic mode. Compare with μ1r,
The alarm device 24A outputs an alarm A in response to the comparison result of the comparator 23A, and the visualization device 26A displays the column data Yi, the average value μ1 and the reference value μ1r.

The specific operation of the second embodiment of the present invention shown in FIG. 6 will be described below. First, like the above,
In response to the detection signal from the phase detector 19 (see FIGS. 1 to 4), the AD converter 12 generates N column data obtained by sampling at equal intervals, and the wavelet transform calculator Reference numeral 16 denotes, for example, column data Yi (i = 1, 2,
, N).

Subsequently, the average value calculator 21A in the abnormality detection processing device 20 calculates the column data Yi according to the following equation (4).
The average value μ1 of is calculated.

Μ1 = (1 / N) Σ (Yi) (4)

However, in the summation term in the equation (4), the column data Yi is added for i = 0, 1, ..., N−1. In the reference value setting mode, the average value μ1 calculated in this way is indicated by the average value setting unit 2 as shown by the broken line in FIG.
It is stored as a reference value μ1r in 2A and is input to the comparator 23A as shown by the solid line in the diagnostic mode.

In the diagnosis mode, the comparator 23A outputs a comparison result indicating abnormality when the average value μ1 exceeds three times the reference value μ1r, and activates the alarm 24A to generate the alarm A. The above operation is repeated in a constant cycle as described above, and the display content of the visualizer 26A can be arbitrarily selected.

The diagnosis based on the average value μ1 as described above is generally performed as compared with the case where the distribution of the energy components of the column data Yi is normal as in the case where the casing of the transmission 1 is in contact with a movable part. It is especially effective when moving.
Further, by using the wavelet transform, the diagnostic result can be obtained by a relatively simple process as in the above formula (4).

Example 3. Although the average value calculator 21A is used as the calculating means in the second embodiment, the variance value may be calculated for the converted data. FIG. 7 is a functional block diagram showing the configuration of the abnormality detection processing device 20 according to the third embodiment of the present invention using the variance value calculator 21B as the calculating means. Yi and A are the same as those described above, and 21B
.About.24B, 26B, .mu.2 and .mu.2r correspond to 21 to 24, 26, .mu. And .mu.r in FIG. 5, respectively.

In this case, the variance value calculator 21B in the abnormality detection processing device 20 takes in, for example, the column data Yi as conversion data, and with respect to the column data Yi, the variance value μ2 of the distribution of energy components in a predetermined frequency component region. Is output as a calculated value. Further, the variance value setter 22B stores the variance value in the reference value setting mode as the reference value μ2r, the comparator 23B compares the variance value μ2 and the reference value μ2r in the diagnostic mode, and the alarm device 24B compares them. The alarm A is output in response to the result, and the visualizer 26B displays the column data Yi, the variance value μ2, the reference value μ2r, and the like.

The specific operation of the third embodiment of the present invention shown in FIG. 7 will be described below. Variance value calculator 21B
For the column data Yi obtained in the same manner as described above,
After calculating the average value μ1 using the above equation (4), the variance value μ2 is further calculated using the following equation (5).

Μ2 = √ {(1 / N) Σ (Yi−μ1) ² } (5)

Also in the summation term of the above equation (5), the column data Yi is added for i = 0, 1, ..., N-1. Hereinafter, similarly to the above, the variance value μ2 is stored in the variance value setter 22B in the reference value setting mode (see the broken line), and is input to the comparator 23B together with the reference value μ2r in the diagnostic mode (see the solid line). For example, variance value μ2
When the value exceeds 3 times the reference value μ2r (at the time of abnormality determination), the alarm A is output.

In the diagnosis using the variance value μ2 of the conversion data, the distribution of the energy components of the column data Yi is dispersed as in the case of gear eccentricity of the gear 4 in the transmission 1 ( This is especially effective when the energy is large overall. Further, by using the wavelet transform, the diagnosis result can be obtained by a relatively simple process as shown in Expression (5).

Example 4. Although the variance value calculator 21B is used as the calculating means in the third embodiment, the skewness may be calculated for the converted data. FIG. 8 is a functional block diagram showing the configuration of the abnormality detection processing device 20 according to the fourth embodiment of the present invention using the skewness calculator 21C as the calculating means. Yi and A are the same as those described above, and 21C to 21C.
24C, 26C, μ3 and μ3r are respectively shown in FIG.
21 to 24, 26, μ and μr.

In this case, the skewness calculator 21C in the abnormality detection processing device 20 fetches, for example, the column data Yi as converted data, and the skewness μ3 of the distribution of the energy component in the predetermined frequency component region with respect to the column data Yi. Is output as a calculated value. Further, the skewness setting unit 22C stores the skewness in the reference value setting mode as the reference value μ3r, and the comparator 23
C compares the skewness μ3 and the reference value μ3r in the diagnostic mode, the alarm device 24C outputs the alarm A in response to the comparison result, and the visualization device 26C displays the column data Yi, the skewness μ3 and the reference value μ3r. Etc. are displayed.

The specific operation of the fourth embodiment of the present invention shown in FIG. 8 will be described below. The skewness calculator 21C is
With respect to the column data Yi, the mean value μ1 and the variance value μ2 are calculated using the above formulas (4) and (5), and then the skewness μ3 is calculated using the following formula (6).

Μ3 = (1 / N) · {1 / (μ2) ³ } Σ (Yi−μ1) ³ (6)

Also in the summation term of the above equation (6), the column data Yi is added for i = 0, 1, ..., N-1. Hereinafter, the skewness μ3 is stored in the skewness setter 22C in the reference value setting mode (see a broken line), and is input to the comparator 23C together with the reference value μ3r in the diagnostic mode (see a solid line). When the value exceeds three times the reference value μ3r (at the time of abnormality determination), the alarm A is output.

In the diagnosis using the skewness μ3 of the converted data, there is a large deviation in the distribution of the energy components of the column data Yi, as in the case where the movable part collides with the casing of the transmission 1, for example. It is especially effective when it occurs. Further, by using the wavelet transform, the diagnostic result can be obtained by a relatively simple process as in the above formula (6).

Example 5. Although the skewness calculator 21C is used as the calculating means in the fourth embodiment, the kurtosis may be calculated for the converted data. FIG. 9 is a functional block diagram showing the configuration of the abnormality detection processing device 20 according to the fifth embodiment of the present invention, which uses the kurtosis calculator 21D as the calculation means.
Yi and A are the same as those described above, and are 21D to 24D.
D, 26D, μ4 and μ4r correspond to 21 to 24, 26, μ and μr in FIG. 5, respectively.

In this case, the kurtosis calculator 21D in the abnormality detection processing device 20 fetches, for example, the column data Yi as conversion data, and with respect to the column data Yi, the kurtosis μ4 of the distribution of energy components in the predetermined frequency component region. Is output as a calculated value. Further, the kurtosis setter 22D stores the kurtosis in the reference value setting mode as the reference value μ4r, and the comparator 23
D compares the kurtosis μ4 with the reference value μ4r in the diagnostic mode, the alarm device 24D outputs the alarm A in response to the comparison result, and the visualization device 26D displays the column data Yi, the kurtosis μ4 and the reference value μ4r. Etc. are displayed.

The specific operation of the fifth embodiment of the present invention shown in FIG. 9 will be described below. The kurtosis calculator 21D is
For the column data Yi, the mean value μ1 and the variance value μ2 are calculated using the above equations (4) and (5), and then the kurtosis μ4 is further calculated using the following equation (7).

Μ4 = (1 / N) · {1 / (μ2) ⁴ } Σ {(Yi-μ1) ³ } -3 ... (7)

Also in the summation term of the above equation (7), the column data Yi is added for i = 0, 1, ..., N-1. Hereinafter, the kurtosis μ4 is stored in the kurtosis setter 22D in the reference value setting mode (see the broken line), and is input to the comparator 23D together with the reference value μ4r in the diagnostic mode (see the solid line). When the value exceeds three times the reference value μ4r (at the time of abnormality determination), the alarm A is output.

In the diagnosis using the kurtosis μ4 of such conversion data, a large sharpness or spread occurs in the distribution of the energy component of the column data Yi, such as the gear eccentricity of the gear 4 in the transmission 1. This is especially effective in the case. Further, by using the wavelet transform, the diagnostic result can be obtained by a relatively simple process as in the above formula (7).

Example 6. Although the kurtosis calculator 21D is used as the calculating means in the fifth embodiment, the maximum value may be calculated for the converted data. FIG. 10 is a functional block diagram showing the configuration of the abnormality detection processing device 20 according to the sixth embodiment of the present invention using the maximum value calculator 21E as the calculation means. Yi and A are the same as those described above, and 21E
˜24E, 26E, μ5 and μ5r correspond to 21 to 24, 26, μ and μr in FIG. 5, respectively.

The sixth embodiment of the present invention shown in FIG. 10 will be described below.
The specific operation of will be described. In this case, the maximum value calculator 21E in the abnormality detection processing device 20 fetches, for example, the column data Yi as converted data, and calculates the maximum value μ5 of the distribution of the energy component in the predetermined frequency component region for the column data Yi. , And outputs this as a calculated value.

The maximum value setter 22E stores the maximum value found in the reference value setting mode as the reference value μ5r (see broken line), and the comparator 23E stores the maximum value μ5 and the reference value in the diagnostic mode (see solid line). The alarm device 24E compares the maximum value μ5 with the reference value μ5r, and compares it with μ5r.
Alarm A in response to the comparison result indicating an abnormality when the number of times exceeds
Is output. Further, the visualizer 26E uses the column data Yi,
The maximum value μ5 and the reference value μ5r are displayed.

In the diagnosis using the maximum value μ5 of the conversion data, for example, such as a dent of the gear 4 in the transmission 1, the column data Yi has a large energy component only instantaneously on a long time axis. It is especially effective when occurs. Also, the diagnostic result can be obtained by a relatively simple process of maximum value calculation using the wavelet transform.

Embodiment 7 FIG. Although the maximum value calculator 21E is used as the calculating means in the sixth embodiment, the learning value of the neural network may be calculated for the converted data. FIG. 11 is a functional block diagram showing the configuration of the abnormality detection processing device 20 according to the seventh embodiment of the present invention using a neural network computing unit 21F as the computing means.
i and A are the same as those described above, and 21F to 24
F, 26F, N1 and N1r correspond to 21 to 24, 26, μ and μr in FIG. 5, respectively.

Embodiment 7 of the present invention shown in FIG. 11 will be described below.
The specific operation of will be described. In this case, the neural network computing unit 21F in the abnormality detection processing device 20
Is a learning value N1 (0 <0 <0) indicating the fitness of the distribution shape of the energy component in a predetermined frequency component region by using, for example, the column data Yi as converted data and using a neural network built in advance for the column data Yi.
N1 <1) is output as a calculated value.

More specifically, the neural network calculator 21F is composed of a unit having a sigmoid characteristic with respect to the pair of the column data Yi which is the input data and the learning value N1 which is the output data (teaching signal). Using a multi-layer network and a well-known method called an error back-propagation learning method, considering the error evaluation function of learning, the value obtained by the gradient method for the connection weight that minimizes this error evaluation function is the learning value. Calculate as N1.

Further, the reference value setting device 22F of the neural network stores the learning value of the neural network in the reference value setting mode as the reference value N1r (see the broken line). The comparator 23F compares the learning value N1 with the reference value N1r in the diagnostic mode (see the solid line). For example, when the learning value N1 is less than 1/2 times the reference value N1r (the degree of conformity is 1/2 or less). At the time), the comparison result indicating the abnormality is output.

In response to the comparison result, the alarm device 24F outputs the alarm A, and the visualization device 26F displays the column data Yi, the learning value N1 of the neural network, the reference value N1r, and the like. Diagnosis using the learning value N1 of the neural network for such converted data is performed using the column data Y
Since it is only necessary to learn the neural network from i, it is not necessary to determine the signal processing and the calculation method in advance,
The calculation process can be simplified and the reliability of the diagnosis result is improved.

Example 8. In the seventh embodiment, the learning value N1 of the neural network is calculated by using the neural network calculator 21F as the calculation means. However, the probability density distribution function is calculated for the converted data, and the fuzzy based on the probability density distribution function is calculated. Features based on rules (reference value in membership function) may be used.

FIG. 12 is a functional block diagram showing the configuration of the abnormality detection processing device 20 according to the eighth embodiment of the present invention, which uses the probability density distribution function calculator 25G and the feature extractor 21G as the calculating means, and Yi and A are 21G-24G, 26G, F2 and F2r, as described above.
Are respectively 21 to 24, 26, μ and μ in FIG.
Corresponds to r.

Reference numeral 25G is a probability density distribution function calculator that takes in the column data Yi as converted data.
Then, the probability density distribution function F1 of the distribution of energy components in the predetermined frequency component region is calculated. Reference numeral 21G is a feature extractor that digitizes the feature F2 of the probability density distribution function F1 based on the fuzzy rule and outputs it as an operation value, which constitutes an operation means together with the probability density distribution function operation device 25G.

F2a is a membership reference function given from the outside in the reference value setting mode (see the broken line), 2
2G is a membership function setter that stores a membership function (reference value of fuzzy rule) F2r based on the feature F2 and the membership reference function F2a in the reference value setting mode.

The probability density distribution function calculator 25G uses, for example, a function representing the distribution of each amplitude value (probability indicating what value the amplitude of one irregular waveform appears at a certain time). It is calculated as the density distribution function F1. Further, the probability density distribution function F1 can be obtained based on various time-series distribution characteristics regarding the column data Yi, such as the amplitude (corresponding to the voltage level) and the frequency count number.

Further, the probability density distribution function calculator 25G is
Since the column data Yi is digitally processed, the amplitude range is divided into, for example, equal intervals, and the probability that the amplitude value is included in each divided range is obtained. As a result, the data of the probability density distribution function F1 becomes a data string corresponding to the number of divisions of the amplitude range. Specifically, for example, as a ratio of how many data belonging to each division range exists in the column data Yi. Desired.

In this case, the comparator 23G is the feature extractor 2
Feature F symbolized by fuzzy rules in 1G
2 is compared with the membership function F2r for executing the fuzzy rule, and the alarm device 24G is operated by the comparator 23G.
Alarm A is generated based on the comparison result of
Displays column data Yi, probability density distribution function F1, feature F2, reference value F2r, and the like.

FIG. 13 is an explanatory diagram showing an example of a reference signal used to obtain the probability density distribution function F1, where the horizontal axis represents time t and the vertical axis represents the count of a predetermined amplitude or the like for each time based on the column data Yi. Is a number. Note that the count number can be composed of various elements as described above.

FIG. 14 is an explanatory diagram showing the probability density distribution function F1 obtained based on the reference signal of FIG. 13, where the horizontal axis is the count number and the vertical axis is the number of appearances at each count number. Here, as the probability density distribution function F1 corresponding to the reference value (normal value) N1r, the case where the number of counts “100” is “50” and the number of counts “90” is “10” is shown.

15 and 16 show the probability density distribution function F
It is explanatory drawing which shows an example of the membership function F2r of the fuzzy rule obtained based on 1 (refer FIG. 14),
The horizontal axis represents the number with respect to the count numbers (90 and 100), and the vertical axis represents the membership function value (0 to 1) for determining normality or abnormality. Here, it is determined to be abnormal when the membership function value is 0 to 0.5,
When it is 0.5 to 1, it is determined to be normal.

FIG. 15 shows the membership function F2r (90) when the count number is "90". As is clear from FIG. 14, when the number is "10", the membership function value is the maximum value "1". It will be. Further, FIG. 16 shows the membership function F2r (1 when the count number is "100".
00), and the membership function value becomes the maximum value "1" when the number is "50".

Each membership function F2r is obtained, for example, by adding the feature F2 based on the fuzzy rule to the membership reference function F2a. The feature F2 consisting of the number is represented as a numerical value of the probability density of an appropriate amplitude energy region, for example, but any numerical value can be selected as necessary. Further, the membership reference function F2a is not limited to the shapes shown in FIGS. 15 and 16, and can be arbitrarily selected.

Next, the operation of the eighth embodiment of the present invention shown in FIG. 12 will be described with reference to FIGS. 1 to 4 and 13 to 16. First, the probability density distribution function calculator 2
5G calculates the probability density distribution function F1 for the wavelet-transformed time series column data Yi, and then,
The feature extractor 21G uses the feature F2 of the probability density distribution function F1.
To extract.

In the reference value setting mode, the extracted feature F2 is input to the membership function setting unit 22G together with the membership reference function F2a (see the broken line in FIG. 12), and the membership function, that is, the fuzzy rule reference. It is stored as the value F2r. In the diagnostic mode, it is input to the comparator 23G (see the solid line in FIG. 12).

In the device diagnostic mode, the feature extractor 2
For example, 1G extracts the number data (see FIG. 14) for the count numbers “100” and “90” from the probability density distribution function F1 as the feature F2. Subsequently, the comparator 23G causes the membership functions F2r (90) (see FIG. 15) and F2r (100), which are the reference values of the fuzzy rules stored in the membership function setting unit 22G.
The matching degree of the feature F2 with respect to (see FIG. 16) is compared.

At this time, a normal reference signal (see FIG. 13)
The center of the number (horizontal axis) of the membership functions F2r (90) and F2r (100) (see FIGS. 15 and 16) obtained from the probability density distribution function F1 of
2) are "10" and "50", respectively.

Now, the sound S of the transmission 1 to be diagnosed is generated.
The feature F2 extracted from the probability density distribution function F1 of is the number “8” and the count “10” for the count number “90”.
It is assumed that the number "49" for "0" is shown. These number “8” and “49” are used as the membership functions F2r (90) and F2r (10 in FIG. 15 and FIG. 16, respectively.
0) When compared above, the function values are "0.8", respectively.
And "0.95".

Therefore, 0.5 <“value of membership function F2r (90)” ≦ 1.0, and 0.5 <
“Value of membership function F2r (100)” ≦ 1.
Since 0 is satisfied at the same time, the transmission 1 to be diagnosed
Is judged to be normal. On the contrary, if at least one of the membership function values becomes 0.5 or less,
The transmission 1 to be diagnosed is determined to be abnormal, and the comparator 23
In response to the abnormality determination result from G, the alarm A is issued from the alarm device 24G.

As described above, the series of operations in the diagnostic mode is repeated in a fixed cycle, and the suitability indicating the nature of the sound S generated by each transmission 1 is sequentially determined. At this time, since the logical signal processing and determination are performed by the membership function F2r fitted to the fuzzy rule, the reliability can be further improved. Here, the number corresponding to the count numbers “90” and “100” is extracted as the feature F2, but it goes without saying that any other feature may be extracted and the number of extraction may be arbitrarily selected.

Example 9. In the eighth embodiment, as the index data of the column data Yi based on the electric signal E,
Although the feature of the fuzzy rule based on the probability density distribution function is used, the deviation between the variance value and the maximum value of the column data Yi may be used.

FIG. 17 is a functional block diagram showing the structure of the abnormality detection processing device 20 according to the ninth embodiment of the present invention using the variance value deviation calculator 21H as the calculating means. Yi and A are the same as those described above. Yes, 21H-24H, 26
H, μ6, and μ6r are 21 and 2 in FIG. 5, respectively.
It corresponds to 4, 26, μ and μr.

Embodiment 9 of the present invention shown in FIG. 17 will be described below.
The specific operation of will be described. In this case, the variance value deviation calculator 21H calculates the variance value deviation μ6 between the variance value μ2 and the maximum value μ5 of the distribution of the energy component in the predetermined frequency component region with respect to the column data Yi (converted data) by the following expression ( The calculation is performed according to 8), and this is output as a calculation value.

Μ6 = | μ5 | −μ2 (8)

In the above equation (8), the variance value μ2 is obtained from the above equations (4) and (5), and the maximum value μ5 of the column data Yi is also obtained as described above.

Subsequently, the reference value setting unit 22H determines the dispersion value deviation obtained in the reference value setting mode as the reference value μ6r.
(See the broken line), the comparator 23H displays the variance value deviation μ6 and the reference value μ6r in the diagnostic mode (see the solid line).
And the alarm device 24H determines, for example, the variance value deviation μ6.
When exceeds 3 times the reference value μ6r, the alarm A is output in response to the comparison result indicating the abnormality. Also, the visualizer 26H
Is column data Yi, variance deviation μ6 and reference value μ6r
Etc. are displayed.

In the diagnosis using the variance value deviation μ6 of such conversion data, the column data Yi shows the average energy on the long time axis as in the case where the gear 4 of the transmission 1 is defective. Is particularly effective when a large energy component is generated only instantly as compared with the generation of. Further, the diagnosis result can be obtained by a relatively simple process such as Expression (8) using the wavelet transform.

In each of the above-mentioned embodiments, the visualizers (26, 26A to 26H) use the converted data (Yi or Yi) which has been wavelet-transformed based on the electric signal E.
j) and a calculated value (μ, μ1 to 1 that indicates the converted data as an index)
μ6, N1 or F2) and reference values (μr, μ1r to μ
6r, N1r or F2r) is displayed, but any number of data may be selectively displayed.

Example 10. Further, by displaying the converted data and the arithmetic unit, the comparator (23, 23A to 23A-23
H) and alarms (24, 24A-24H) are omitted,
It is also possible to let the observer decide the abnormality of the equipment.

Although the transmission 1 is used as a diagnosis target and the generated sound S is used as a parameter in each of the above-described embodiments, other devices such as the engine 31 (see FIG. 19) are used as targets, and other parameters (vibration) are used. It is needless to say that the same effect can be obtained even when (i.e., electromagnetic waves, etc.) is detected.

[0140]

As described above, according to claim 1 of the present invention, signal detecting means for detecting a sound or vibration generated from a device including a vibrating element and outputting a signal corresponding to the sound or vibration, The wavelet transform calculator for performing wavelet transform on the signal and outputting the converted data, and the abnormality detection processing device for detecting the abnormality of the device based on the converted data, the abnormality detection processing device calculates the characteristics of the converted data When the calculated value exceeds the predetermined relationship with the reference value based on the comparison result of the comparing means and the comparing means for comparing the calculated value with the preset reference value The alarm means for outputting an alarm is also included, and the alarm is output only when the calculated value that indicates the characteristics of the converted data indicates an abnormality to prevent erroneous output of the alarm. Others to determine the minute difference of the oscillation state, the effect of the diagnostic device is obtained for the abnormality diagnosis device reliability has improved the.

According to the second aspect of the present invention, in the first aspect, the reference value is set based on the signal obtained when the device is in the normal state. There is an effect that can be obtained.

Further, according to claim 3 of the present invention, since the visualization means for visualizing at least one of the converted data, the calculated value and the reference value is provided in claim 1 or claim 2, it is displayed to the observer. As a result, there is an effect that a diagnostic apparatus for a device with improved reliability of abnormality determination can be obtained.

According to claim 4 of the present invention, a signal detecting means for detecting a sound or a vibration generated from a device including a vibrating element and outputting a signal corresponding to the sound or the vibration, and a wavelet for the signal. A wavelet transform calculator that performs conversion and outputs converted data, and an abnormality detection processing device that detects an abnormality of the device based on the conversion data are provided.The abnormality detection processing device calculates the characteristics of the conversion data and calculates the calculated value. The circuit configuration is simplified because it includes an arithmetic means for outputting and a visualization means for visualizing at least one of the converted data and the calculated value, and enables an observer to make an abnormality determination based on the contents of the converted data and the calculated value. In addition, there is an effect that a diagnostic apparatus for equipment with improved reliability of abnormality determination can be obtained.

According to a fifth aspect of the present invention, in any one of the first to fourth aspects, a device state detecting means for detecting a predetermined state of the equipment is provided, and the signal detecting means is in a predetermined state. Since the operation is started in response, there is an effect of improving the detection reproducibility of the signal and providing the diagnostic apparatus for the device in which the abnormality determination is ensured.

According to a sixth aspect of the present invention, in any one of the first to fifth aspects, the calculating means is configured to make an average value of an energy component distribution in a predetermined frequency component region with respect to the converted data. Since it is composed of an average value calculator that outputs as a calculated value, there is an effect that a diagnostic apparatus for a device with improved reliability of abnormality diagnosis can be obtained.

According to a seventh aspect of the present invention, in any one of the first to fifth aspects, the computing means is configured to set the variance value of the distribution of the energy component in the predetermined frequency component region with respect to the converted data. Since it is composed of a distributed value calculator that outputs as a calculated value, there is an effect that a diagnostic apparatus for a device with improved reliability of abnormality diagnosis can be obtained.

Further, according to claim 8 of the present invention, in any one of claims 1 to 5, the computing means is configured to set the skewness of the distribution of the energy component in the predetermined frequency component region with respect to the converted data. Since it is configured by a skewness calculator that outputs as a calculated value, there is an effect that a diagnostic apparatus for a device with improved reliability of abnormality diagnosis can be obtained.

According to a ninth aspect of the present invention, in any one of the first to fifth aspects, the calculating means is arranged to convert the converted data into kurtosis of an energy component distribution in a predetermined frequency component region. Since it is composed of a kurtosis calculator that outputs as a calculated value, there is an effect that a diagnostic device for a device with improved reliability of abnormality diagnosis can be obtained.

According to a tenth aspect of the present invention, in any one of the first to fifth aspects, the calculating means is configured to set the maximum value of the distribution of the energy component in the predetermined frequency component region with respect to the converted data. Since it is composed of a maximum value calculator that outputs as a calculated value, there is an effect that a diagnostic apparatus for a device with improved reliability of abnormality diagnosis can be obtained.

Further, according to claim 11 of the present invention, in any one of claims 1 to 5, the computing means is configured to use the neural network of the distribution of the energy component in the predetermined frequency component region with respect to the converted data. Since it is configured by the neural network arithmetic unit that outputs the learned value of 1 as the arithmetic value, there is an effect that a diagnostic device for equipment with improved reliability of abnormality diagnosis can be obtained.

According to a twelfth aspect of the present invention, in any one of the first to fifth aspects, the computing means is configured to cause the conversion data to have a probability density of a distribution of energy components in a predetermined frequency component region. Since it is composed of a probability density distribution function calculator that calculates a distribution function and a feature extractor that outputs the characteristics of the probability density distribution function according to fuzzy rules as calculation values, a diagnostic device for equipment with improved reliability of abnormality diagnosis. There is an effect that can be obtained.

According to a thirteenth aspect of the present invention, in any one of the first to fifth aspects, the calculating means is configured to set the variance value of the distribution of the energy component in the predetermined frequency component region with respect to the converted data. Since it is configured by a variance value deviation calculator that outputs the deviation between the maximum value and the maximum value as a calculated value, there is an effect that a diagnostic apparatus for a device with improved reliability of abnormality diagnosis can be obtained.

[Brief description of drawings]

FIG. 1 is a block diagram showing a schematic configuration in a case where a microphone is used as a signal detection means and three-dimensional data is used as conversion data in Embodiment 1 of the present invention.

FIG. 2 is a block diagram showing a schematic configuration in the case where a vibration detector is used as a signal detection unit and three-dimensional data is used as conversion data in the first embodiment of the present invention.

FIG. 3 is a block diagram showing a schematic configuration in the case where a microphone is used as signal detection means and column data is used as conversion data in the first embodiment of the present invention.

FIG. 4 is a block diagram showing a schematic configuration in the case where a vibration detector is used as a signal detection unit and column data is used as conversion data in the first embodiment of the present invention.

FIG. 5 is a functional block diagram showing a configuration example of the abnormality detection processing device according to the first embodiment of the present invention.

FIG. 6 is a functional block diagram showing a configuration example of an abnormality detection processing device according to a second embodiment of the present invention.

FIG. 7 is a functional block diagram showing a configuration example of an abnormality detection processing device according to a third embodiment of the present invention.

FIG. 8 is a functional block diagram showing a configuration example of an abnormality detection processing device according to a fourth embodiment of the present invention.

FIG. 9 is a functional block diagram showing a configuration example of an abnormality detection processing device according to a fifth embodiment of the present invention.

FIG. 10 is a functional block diagram showing a configuration example of an abnormality detection processing device according to a sixth embodiment of the present invention.

FIG. 11 is a functional block diagram showing a configuration example of an abnormality detection processing device according to a seventh embodiment of the present invention.

FIG. 12 is a functional block diagram showing a configuration example of an abnormality detection processing device according to an eighth embodiment of the present invention.

FIG. 13 is a waveform diagram showing an example of a reference signal in a normal state used by the probability density distribution function calculator in FIG.

14 is a waveform diagram showing an example of a probability density distribution function in a normal state obtained from the reference signal of FIG.

15 is a waveform chart showing an example of a membership function of a fuzzy rule used in the comparator in FIG.

16 is a waveform chart showing an example of a membership function of a fuzzy rule used in the comparator in FIG.

FIG. 17 is a functional block diagram showing a configuration example of an abnormality detection processing device according to a ninth embodiment of the present invention.

FIG. 18 is a block diagram showing a schematic configuration of a conventional device diagnosis apparatus.

FIG. 19 is a configuration diagram showing another example (engine) of general equipment.

[Explanation of symbols]

1 transmission (equipment), 7 microphone (signal detection means), 12 AD converter (signal detection means), 16 wavelet transform calculator, 18 vibration detector (signal detection means), 19 phase detector (equipment state detection means) ), 20
Abnormality detection processing device, 21 calculator, 21A average value calculator, 21B variance value calculator, 21C skewness calculator, 21
D kurtosis calculator, 21E maximum value calculator, 21F neural network calculator, 21G feature extractor, 21
H variance value deviation calculator, 22, 22A to 22H reference value setter, 23, 23A to 23H comparator, 24, 24A
~ 24H alarm device, 25 probability density distribution function calculator, 2
6, 26A to 26H Visualizer, 31 Engine (equipment), A alarm, E electric signal, F1 probability density distribution function, F2 feature, N1 learning value of neural network, S generated sound, Yi column data, Yij three-dimensional data, μ calculation value, μ1 average value, μ2 variance value, μ3
Skewness, μ4 kurtosis, μ5 maximum value, μ6 variance deviation,
F2r, N1r, μr, μ1r to μ6r Reference value.

Claims (13)

[Claims] 1. A signal detecting means for detecting a sound or a vibration generated from a device including a vibrating element and outputting a signal corresponding to the sound or the vibration, and wavelet transforming the signal to output converted data. And an abnormality detection processing device that detects an abnormality of the device based on the conversion data, wherein the abnormality detection processing device calculates a characteristic of the conversion data and outputs a calculation value. Means, comparing means for comparing the calculated value with a preset reference value, and outputting an alarm when the calculated value exceeds a predetermined relationship with the reference value based on the comparison result of the comparing means. A diagnostic device for equipment, comprising: 2. The device diagnostic apparatus according to claim 1, wherein the reference value is set based on a signal obtained when the device is in a normal state. 3. The apparatus diagnostic apparatus according to claim 1, further comprising a visualization unit that visualizes at least one of the converted data, the calculated value, and the reference value. 4. A signal detecting means for detecting a sound or a vibration generated from a device including a vibrating element and outputting a signal corresponding to the sound or the vibration, and wavelet transforming the signal to output converted data. And an abnormality detection processing device that detects an abnormality of the device based on the conversion data, wherein the abnormality detection processing device calculates a characteristic of the conversion data and outputs a calculation value. A diagnostic device for equipment, comprising: means and a visualization means for visualizing at least one of the converted data and the calculated value. 5. A device state detecting means for detecting a predetermined state of the device is provided, and the signal detecting means starts an operation in response to the predetermined state. A diagnostic device for a device according to any one of 1. 6. The calculating means is constituted by an average value calculator for outputting the average value of the distribution of energy components in a predetermined frequency component region to the converted data as the calculated value. A diagnostic device for a device according to any one of claims 1 to 5. 7. The calculation means is composed of a variance value calculator that outputs, as the calculated value, the variance value of the distribution of energy components in a predetermined frequency component region with respect to the converted data. A diagnostic device for a device according to any one of claims 1 to 5. 8. The calculation means is configured by a skewness calculator that outputs, as the calculated value, the skewness of the distribution of energy components in a predetermined frequency component region for the converted data. A diagnostic device for a device according to any one of claims 1 to 5. 9. The kurtosis calculator configured to output the kurtosis of the distribution of energy components in a predetermined frequency component region as the calculated value for the converted data. A diagnostic device for a device according to any one of claims 1 to 5. 10. The calculating means is constituted by a maximum value calculator for outputting the maximum value of the distribution of energy components in a predetermined frequency component region to the converted data as the calculated value. A diagnostic device for a device according to any one of claims 1 to 5. 11. The calculation means is constituted by a neural network calculator that outputs, as the calculated value, a learning value of a neural network of an energy component distribution in a predetermined frequency component region for the converted data. The diagnostic device for equipment according to any one of claims 1 to 5. 12. The calculation means, a probability density distribution function calculator for calculating a probability density distribution function of the distribution of energy components in a predetermined frequency component region for the converted data, and a fuzzy rule of the probability density distribution function. The device diagnostic apparatus according to any one of claims 1 to 5, further comprising a feature extractor that outputs the feature according to (1) as the calculated value. 13. The calculation means comprises a dispersion value deviation calculator that outputs, as the calculated value, a deviation between a dispersion value and a maximum value of a distribution of energy components in a predetermined frequency component region for the converted data. The diagnostic device for equipment according to any one of claims 1 to 5, characterized in that