State evaluation system, state evaluation device, and state evaluation method

Abstract

The state evaluation system of the embodiment comprises a sensor, a filter, a signal processing unit and an evaluation unit. The sensor detects elastic waves generated from the running industrial equipment. The filter allows elastic waves having frequency characteristics caused by wear generated inside the industrial equipment to pass through. The signal processing unit extracts multiple feature quantities using the elastic waves passing through the filter. The evaluation unit evaluates the abnormality of the industrial equipment based on a combination of the extracted multiple feature quantities.

Description

Technical Field

[0001] Embodiments of the present invention relate to a state evaluation system, a state evaluation device, and a state evaluation method. Background Art

[0002] It is difficult to visually confirm the internal state of the compressor used in the air conditioning / heat source system from the time it is installed in the outdoor unit until the compressor reaches the end of its life. Therefore, in order to properly manage the replacement period of the compressor, it is necessary to use some method to monitor the occurrence and progress of abnormalities inside the compressor. In the past, as a method for detecting abnormalities in the compressor, a method using a signal obtained from an AE sensor installed outside the compressor was proposed (for example, refer to Patent Documents 1 and 2). The AE sensor may be able to detect changes in the signal at the time of an initial stage abnormality such as a tiny crack or wear that becomes the starting point of slight damage. Therefore, it is believed that if the elastic wave generated from the sliding part inside the compressor (for example, the combination of the shaft and bearing of the rotating body, the combination of the scraper and the roller) can be detected, the sliding state inside the compressor can be estimated from the outside of the shell without the need to build the sensor into the compressor. However, the compressor in operation always vibrates. Therefore, many of the elastic waves detected are caused by the vibration of the shell and the stress and strain of the compression process. In this case, it is difficult to distinguish whether the detected elastic wave is an elastic wave generated due to the abnormality of the equipment or an elastic wave generated due to stress and strain. Therefore, it is sometimes impossible to evaluate abnormalities inside the compressor with high accuracy. Such a problem is not limited to compressors, but occurs commonly in all industrial equipment having sliding parts.

[0003] Patent Document 1: Japanese Patent No. 3325015

[0004] Patent Document 2: Japanese Patent No. 4809455 Summary of the invention

[0005] Problem that the invention aims to solve

[0006] The problem to be solved by the present invention is to provide a state evaluation system, a state evaluation device, and a state evaluation method capable of evaluating abnormality of industrial equipment with high accuracy.

[0007] Solutions for solving problems

[0008] The state evaluation system of the embodiment comprises a sensor, a filter, a signal processing unit and an evaluation unit. The sensor detects elastic waves generated from the running industrial equipment. The filter allows elastic waves having frequency characteristics caused by wear generated inside the industrial equipment to pass through. The signal processing unit extracts multiple feature quantities using the elastic waves passing through the filter. The evaluation unit evaluates the abnormality of the industrial equipment based on a combination of the extracted multiple feature quantities. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 It is a diagram showing the configuration of a state evaluation system according to an embodiment.

[0010] Figure 2 It is a cross-sectional view of the AA portion of the compressor in the embodiment.

[0011] Figure 3 This is a diagram showing an example of an elastic wave signal not caused by wear in the embodiment.

[0012] Figure 4 This is a diagram showing an example of an elastic wave signal assumed to be caused by wear in the embodiment.

[0013] Figure 5 It is a schematic block diagram showing the functions of a signal processing unit in the embodiment.

[0014] Figure 6 This is a sequence diagram showing the flow of abnormality evaluation processing using the state evaluation system in the embodiment.

[0015] Figure 7 This is a scatter diagram obtained when no abnormality occurs in the compressor in the embodiment.

[0016] Figure 8 This is a scatter diagram obtained when an abnormality occurs in the compressor in the embodiment.

[0017] Fig. 9 This is a diagram showing an example of a scatter diagram obtained when no abnormality occurs in the compressor in the embodiment.

[0018] Fig.10 This is a diagram showing an example of a scatter diagram obtained when an abnormality occurs in the compressor in the embodiment.

[0019] Fig.11 This is a diagram showing the relationship between the rotation speed of the compressor and the correct answer rate of the evaluation result in the embodiment. DETAILED DESCRIPTION

[0020] Hereinafter, a state evaluation system, a state evaluation device, and a state evaluation method according to an embodiment will be described with reference to the drawings.

[0021] Figure 1: is a diagram showing the structure of a state evaluation system 100 of an embodiment. The state evaluation system 100 is used for abnormality evaluation of industrial equipment. In the present embodiment, a compressor is taken as an example of industrial equipment, but the industrial equipment is not limited to the compressor. The industrial equipment can be any equipment as long as it has a sliding part. For example, industrial equipment includes a prime mover, a motor, and a pump. The sliding part refers to a part that slides while rubbing against each other, such as a combination of a shaft and a bearing of a rotating body or a combination of a scraper and a roller. The abnormality of the industrial equipment in the present embodiment refers to, for example, damage to a sliding part provided inside the industrial equipment.

[0022] The state evaluation system 100 includes a compressor 1, a sensor 10, an amplifier 11, a filter 12, an amplifier 13, an A / D converter 14, a signal processing unit 15, and a state evaluation device 20. The signal processing unit 15 and the state evaluation device 20 are connected in a manner that allows communication via wired or wireless communication. When the signal processing unit 15 and the state evaluation device 20 are connected wirelessly, the wireless frequency band can use, for example, a so-called ISM band (Industry Science Medical Band) such as 2.4 GHz and 920 MHz (915 MHz to 928 MHz in Japan).

[0023] The compressor 1 is a device that pressurizes and compresses gases such as air and gas. The compressor 1 is, for example, a positive displacement compressor or a centrifugal compressor. In the present embodiment, the case where the compressor 1 is a positive displacement compressor is taken as an example for explanation. Among the positive displacement types, there are reciprocating, rotary, rolling, screw and other types. Assume that the compressor 1 is running at a rotation speed of 60rps (revolutions per second), for example. The compressor 1 is used in an industrial air conditioning heat source system, an air conditioning system for a building or a factory. The compressor 1 includes a casing 2 and an accumulator 3. The casing 2 and the accumulator 3 are connected via a pipe. The casing 2 has a discharge pipe 4 and an arc spot 6. The discharge pipe 4 discharges the compressed gas to the outside. The accumulator 3 inhales the refrigerant from the suction pipe 5 and separates the refrigerant into liquid refrigerant and gaseous refrigerant. In Figure 2 2 is a cross-sectional view of the AA portion in the compressor 1.

[0024] Figure 2 It is a cross-sectional view of the AA portion of the compressor 1 in the embodiment.

[0025] At least a cylinder 7 is provided inside the compressor 1. A compression chamber 8 is provided inside the cylinder 7. A sensor 10 is provided outside the compressor 1. In the compression chamber 8, the refrigerant is compressed by the sliding part. In the case where an abnormality occurs in the sliding part inside the compressor 1, elastic waves that are assumed to be caused by wear are generated due to the mutual friction between the shaft and the bearing of the rotating body. The elastic waves generated in the compressor 1 are easily detected around the arc spot 6 that fixes the housing 2 of the compressor 1 and the cylinder 7. Therefore, the sensor 10 is provided around the arc spot 6. It is desirable to set the installation position of the sensor 10 to be within a range of a specified multiple (for example, 3 times) of the diameter of the arc spot 6. Thereby, the detection accuracy of the elastic waves can be improved.

[0026] The elastic waves generated in the compressor 1 are not limited to those assumed to be caused by wear, and there are also elastic waves not caused by wear, such as vibration of the housing, stress and strain in the compression process, etc. Figure 3 and Figure 4 An example of an elastic wave signal generated in the compressor 1 is shown in FIG. Figure 3 This is a diagram showing an example of an elastic wave signal not caused by wear. Figure 4 FIG. 1 is a diagram showing an example of an elastic wave signal assumed to be caused by wear. Figure 3 and Figure 4 In the figure, the horizontal axis represents time and the vertical axis represents the amplitude of the elastic wave signal. Figure 3 and Figure 4 As shown, the waveform of the signal is different between the elastic wave assumed to be caused by wear and the elastic wave not caused by wear. Therefore, in the state evaluation device 20 of the present embodiment, the abnormality of the compressor 1 is evaluated by detecting the difference in the elastic waves.

[0027] Return to Figure 1 Let me continue to explain.

[0028] The sensor 10 is arranged around the arc spot 6 of the compressor 1. The sensor 10 can be directly arranged on the housing 2, or can be arranged on the housing 2 using a magnetic seat suitable for the shape of the sensor head in the sensor 10. When the sensor 10 is directly arranged on the housing 2, the sensor 10 is bonded to the housing 2 by an adhesive. When the sensor 10 is arranged on the housing 2 using a magnetic seat suitable for the shape of the sensor head, the contact surface between the sensor head and the housing is provided with grease or an elastic body. The sensor 10 detects elastic waves generated in the compressor 1. The sensor 10 outputs the detected elastic waves to the amplifier 11 as an electrical signal. In the sensor 10, a piezoelectric element having a sensitivity in the range of 10kHz to 1MHz is used, for example. The sensor 10 has a resonance type having a resonance peak in a frequency range, a wideband type with suppressed resonance, and the like, and the type of the sensor 10 can be any. As a method for the sensor 10 to detect elastic waves, there are a voltage output type, a resistance change type, and an electrostatic capacitance type, and the like, and any detection method can be used.

[0029] The amplifier 11 amplifies the elastic wave output from the sensor 10. The amplifier 11 outputs the amplified elastic wave to the filter 12. The amplifier 11 amplifies the elastic wave to a degree that can be processed by the filter 12, for example.

[0030] The filter 12 filters the elastic waves output from the amplifier 11. The filter 12 is a bandpass filter set to allow signals of a specified frequency band to pass. For example, the filter 12 is a filter set to allow elastic waves having frequency characteristics caused by wear to pass. For example, the filter 12 is set to allow signals with a frequency higher than 500 kHz to pass. In the case where the compressor 1 is a rotary compressor, it is desired that the filter 12 is set to allow signals from 520 kHz to 850 kHz to pass.

[0031] The amplifier 13 amplifies the elastic wave that has passed through the filter 12. The amplifier 13 outputs the amplified elastic wave to the A / D converter 14. The amplifier 13 amplifies the elastic wave that has passed through the filter 12 by a predetermined amount (for example, 10 to 100 times), for example.

[0032] The A / D converter 14 quantizes the amplified elastic wave and converts it into a digital signal. The A / D converter 14 outputs the digital signal to the signal processing unit 15 .

[0033] The signal processing unit 15 receives the digital signal output from the A / D converter 14 as input. The signal processing unit 15 performs signal processing on the input digital signal. The signal processing performed by the signal processing unit 15 is, for example, noise removal, feature extraction, etc. The signal processing unit 15 generates transmission data including the digital signal after signal processing. The signal processing unit 15 outputs the generated transmission data to the state evaluation device 20. The signal processing unit 15 is constructed using an analog circuit or a digital circuit. The digital circuit is implemented, for example, by an FPGA (Field Programmable Gate Array) or a microcomputer. The digital circuit can also be implemented by a dedicated LSI (Large-Scale Integration). The signal processing unit 15 can also be equipped with a non-volatile memory such as a flash memory or a detachable memory.

[0034] The state evaluation device 20 evaluates abnormality of the compressor 1 using the digital signal included in the transmission data output from the signal processing unit 15. The state evaluation device 20 includes a communication unit 21, a control unit 22, a storage unit 23, and a display unit 24.

[0035] The communication unit 21 receives the digital signal output from the signal processing unit 15 .

[0036] The control unit 22 controls the entire state evaluation device 20. The control unit 22 is configured using a processor such as a CPU (Central Processing Unit) and a memory. The control unit 22 functions as an acquisition unit 221 and an evaluation unit 222 by executing a program. The program for realizing the acquisition unit 221 and the evaluation unit 222 may be installed in the state evaluation device 20 at the time of shipment or may be installed separately.

[0037] The acquisition unit 221 acquires the transmission data output from the signal processing unit 15. For example, when the signal processing unit 15 and the state evaluation device 20 communicate wirelessly, the acquisition unit 221 functions as a communication interface and acquires the transmission data by wirelessly communicating with the signal processing unit 15. For example, when the signal processing unit 15 and the state evaluation device 20 communicate by wire, the acquisition unit 221 functions as a communication interface and acquires the transmission data by wired communication with the signal processing unit 15.

[0038] The evaluation unit 222 evaluates the abnormality of the compressor 1 based on the transmission data acquired by the acquisition unit 221. Specifically, the evaluation unit 222 evaluates the abnormality of the compressor 1 based on the combination of multiple feature quantities obtained from the elastic waves. More specifically, the evaluation unit 222 evaluates that the compressor 1 is abnormal when the ratio of the correlation between the multiple feature quantities of each of the multiple elastic waves deviates is greater than a threshold value.

[0039] The storage unit 23 stores the transmission data acquired by the acquisition unit 221. The storage unit 23 is configured using a storage device such as a magnetic hard disk device or a semiconductor storage device.

[0040] The display unit 24 is an image display device such as a liquid crystal display, an organic EL (Electro Luminescence) display, etc. The display unit 24 displays the evaluation result according to the control of the control unit 22. The display unit 24 may also be an interface for connecting the image display device to the state evaluation device 20. In this case, the display unit 24 generates an image signal for displaying the evaluation result, and outputs the image signal to the image display device connected to itself.

[0041] Figure 5 1 is a schematic block diagram showing the functions of the signal processing unit 15 in the embodiment. Figure 2 As shown, the signal processing unit 15 includes a waveform shaping filter 151 , a gate generation circuit 152 , a feature quantity extraction unit 153 , a transmission data generation unit 154 , a memory 155 , and an output unit 156 .

[0042] The waveform shaping filter 151 removes noise components outside a predetermined signal frequency band from the input digital signal of the time series data. The waveform shaping filter 151 is, for example, a digital bandpass filter (BPF). It is assumed that the waveform shaping filter 151 is set to pass the same frequency band as the filter 12, for example. The waveform shaping filter 151 outputs a signal after the noise component is removed (hereinafter referred to as a "noise-removed elastic wave signal") to the gate generation circuit 152 and the feature quantity extraction unit 153.

[0043] The gating generation circuit 152 receives the noise-removed elastic wave signal output from the waveform shaping filter 151 as input. The gating generation circuit 152 generates a gating signal indicating whether the waveform of the input noise-removed elastic wave signal is continuing. The gating generation circuit 152 is implemented, for example, by an envelope detector and a comparator. The envelope detector detects the envelope of the noise-removed elastic wave signal. The envelope is extracted, for example, by performing a prescribed processing (for example, processing using a low-pass filter, a Hilbert transform) on the output value obtained by squaring the noise-removed elastic wave signal. The comparator determines whether the envelope of the noise-removed elastic wave signal is above a prescribed threshold.

[0044] When the envelope of the noise-removed elastic wave signal becomes greater than a predetermined threshold, the gating generation circuit 152 outputs a first gating signal indicating that the waveform of the noise-removed elastic wave signal is continuing to the feature quantity extraction unit 153. On the other hand, when the envelope of the noise-removed elastic wave signal is less than a predetermined threshold, the gating generation circuit 152 outputs a second gating signal indicating that the waveform of the noise-removed elastic wave signal is not continuing to the feature quantity extraction unit 153.

[0045] The feature quantity extraction unit 153 receives as input the noise-removed elastic wave signal output from the waveform shaping filter 151 and the strobe signal output from the strobe generation circuit 152. The feature quantity extraction unit 153 extracts the feature quantity of the noise-removed elastic wave signal using the noise-removed elastic wave signal input during the period when the first strobe signal is input. The feature quantity is information indicating the feature of the noise-removed elastic wave signal.

[0046] The feature quantity is, for example, the waveform amplitude [mV], the waveform rise time [usec], the duration of the strobe signal [usec], the number of zero crossing counts [times], the waveform energy [arb.], the frequency [Hz], the arrival time, and the RMS (Root Mean Square) value, etc. The feature quantity extraction unit 153 outputs the parameters related to the extracted feature quantity to the transmission data generation unit 154.

[0047] The amplitude of a waveform is, for example, the value of the maximum amplitude in the noise-removed elastic wave signal. The rise time of a waveform is, for example, the time T1 from the rise of the selection signal to the time when the noise-removed elastic wave signal reaches its maximum value. The duration of the selection signal is, for example, the time from the rise of the selection signal to the time when the amplitude is less than a preset value. The zero crossing count is, for example, the number of times the noise-removed elastic wave signal crosses a baseline of zero value. The energy of a waveform is, for example, the value obtained by time-integrating the square of the amplitude of the noise-removed elastic wave signal at each time point. In addition, the definition of energy is not limited to the above example, and for example, it can also be obtained by approximation using the envelope of the waveform. The frequency is the frequency of the noise-removed elastic wave signal. The arrival time is the time when the elastic wave is detected. The RMS value is, for example, the value obtained by squaring the amplitude of the noise-removed elastic wave signal at each time point and taking the square root.

[0048] The transmission data generation unit 154 receives the parameter related to the feature amount as an input, and generates transmission data including the input parameter related to the feature amount.

[0049] The transmission data is stored in the memory 155. The memory 155 is, for example, a dual-port RAM (Random Access Memory).

[0050] The output unit 156 sequentially outputs the transmission data stored in the memory 155 to the state evaluation device 20 .

[0051] Figure 6 1 is a sequence diagram showing the flow of abnormality evaluation processing using the state evaluation system 100 in the embodiment. Figure 6 In the illustrated example, it is assumed that the compressor 1 is in operation, and the sensor and the like include a sensor 10 , an amplifier 11 , a filter 12 , an amplifier 13 , and an A / D converter 14 .

[0052] The sensor 10 detects elastic waves generated from the running compressor 1 (step S101). The sensor 10 outputs the detected elastic waves to the amplifier 11. The amplifier 11 amplifies the elastic waves output from the sensor 10 (step S102). The amplifier 11 outputs the amplified elastic waves to the filter 12. The amplified signal output from the amplifier 11 is filtered by the filter 12 (step S103). Thus, it is possible to extract elastic waves assumed to be caused by wear from the elastic waves detected from the running compressor 1, except for signals that are not caused by wear.

[0053] The elastic wave filtered by the filter 12 is input to the amplifier 13. The amplifier 13 amplifies the input elastic wave (step S104). The amplifier 13 outputs the amplified signal to the A / D converter 14. The A / D converter 14 quantizes the input elastic wave and converts it into a digital signal (step S105). The A / D converter 14 outputs the digital signal to the signal processing unit 15 (step S106).

[0054] The signal processing unit 15 is input with the digital signal output from the A / D converter 14. The signal processing unit 15 uses the input digital signal to extract the characteristic quantity of the elastic wave (step S107). Specifically, the characteristic quantity extraction unit 153 uses the noise-removed elastic wave signal as the digital signal input during the period when the first selection signal is input to extract the characteristic quantity of the noise-removed elastic wave signal. The signal processing unit 15 outputs the parameters related to the extracted characteristic quantity to the transmission data generation unit 154. The transmission data generation unit 154 generates transmission data including the parameters related to the characteristic quantity (step S108). The output unit 156 outputs the transmission data to the state evaluation device 20 one by one (step S109).

[0055] The communication unit 21 of the state evaluation device 20 receives the transmission data output from the signal processing unit 15. The acquisition unit 221 acquires the transmission data received by the communication unit 21. The acquisition unit 221 records the acquired transmission data in the storage unit 23 (step S110). When a predetermined number of transmission data is stored in the storage unit 23, the evaluation unit 222 uses the plurality of transmission data to generate a scatter diagram representing the correlation of a plurality of feature quantities (step S111). Specifically, first, the evaluation unit 222 acquires a plurality of feature quantities from each transmission data of the plurality of transmission data. For example, the evaluation unit 222 acquires the energy of the waveform and the duration of the gating signal from each transmission data of the plurality of transmission data as a plurality of feature quantities. Next, the evaluation unit 222 uses the acquired energy of the waveform and the duration of the gating signal to set the horizontal axis to the duration and the vertical axis to the energy to generate a scatter diagram representing the correlation.

[0056] exist Figure 7 and Figure 8 An example of a scatter plot is shown in FIG. Figure 7 This is a diagram showing an example of a scatter diagram obtained when no abnormality occurs in the compressor 1 . Figure 8 This is a diagram showing an example of a scatter diagram obtained when an abnormality occurs in the compressor 1 . Figure 7 and Figure 8 The points 30 shown are points plotted based on a plurality of characteristic quantities obtained from elastic waves. Figure 7 and Figure 8 The point 30 in FIG. 1 is plotted based on the energy of the waveform obtained from the elastic wave and the duration of the gate signal. In a compressor 1 having no damage in the sliding portion inside the compressor 1, as shown in FIG. Figure 7 As shown in FIG. 1 , the energy of the measured elastic wave tends to increase in proportion to the duration of the signal. On the other hand, when an abnormality exists in the sliding part inside the compressor 1, such as Figure 8 As shown in the area 31, points 30 that deviate from the relationship between the energy and duration of the elastic wave occur frequently. The evaluation unit 222 evaluates the abnormality inside the compressor 1 based on the proportion of the deviated points 30 (step S112). Specifically, the evaluation unit 222 draws an approximate straight line on the generated scatter plot, and evaluates it as an abnormality inside the compressor 1 when the proportion of the points 30 that are a specified distance away from the approximate straight line (the proportion among all the points 30) is greater than the threshold. The evaluation unit 222 outputs the evaluation result to the display unit 24. The display unit 24 displays the evaluation result output from the evaluation unit 222 (step S113). The display unit 24 can display the scatter plot as the evaluation result, and can also display the presence or absence of an abnormality as the evaluation result.

[0057] In the state evaluation system 100 constructed as described above, the elastic waves obtained from the sensor 10 installed on the housing 2 of the compressor 1 are filtered by the filter 12 to extract the elastic waves (elastic waves with small amplitude and relatively high frequency characteristics) caused by wear generated inside the running compressor 1. Then, in the state evaluation device 20, the abnormality of the compressor 1 is evaluated based on the combination of multiple characteristic quantities obtained from the elastic waves. In this way, the elastic waves caused by vibration and stress and strain of the compression process can be excluded for evaluation. Therefore, there is no need to distinguish between the elastic waves caused by vibration and stress and strain of the compression process and the elastic waves generated due to the abnormality of the compressor 1. Therefore, the abnormality inside the compressor can be evaluated with high accuracy.

[0058] The evaluation unit 222 evaluates that the compressor 1 is abnormal when the ratio of the deviation from the approximate straight line derived from the correlation between the multiple characteristic quantities of each of the multiple elastic waves is greater than the threshold value. The presence of the deviated elastic wave indicates that some abnormality may have occurred inside the device. However, when the deviation ratio is small (for example, less than the threshold value), it is possible that the elastic wave is accidentally generated. On the other hand, when the deviation ratio is greater than the threshold value, it can be assumed that the elastic wave is not accidentally generated, but a phenomenon that is not normally possible due to the occurrence of an abnormality inside the device. Therefore, by evaluating the compressor 1 as abnormal when the deviation ratio is greater than the threshold value, the evaluation unit 222 can detect the abnormality even if no sensor is provided inside the device.

[0059] Hereinafter, a modified example of the state evaluation system 100 will be described.

[0060] At least one of the amplifier 11, the filter 12, the amplifier 13, and the A / D converter 14 may be integrally configured with the signal processing unit 15. The signal processing unit 15 may be provided in the state evaluation device 20.

[0061] The functional units of the state evaluation device 20 may be partially or entirely provided in another housing. For example, the state evaluation device 20 may include a communication unit 21, a control unit 22, and a storage unit 23, and a display unit 24 may be provided in another housing. In such a configuration, the control unit 22 controls the communication unit 21 to output the evaluation result to the display unit 24 provided in another housing.

[0062] In this embodiment, a structure is shown in which the energy and duration of a waveform are used as multiple feature quantities, but the multiple feature quantities used by the evaluation unit 222 in the evaluation are not limited to this. The evaluation unit 222 may combine any feature quantities for evaluation as long as they are feature quantities obtained from elastic waves. For example, the evaluation unit 222 may use the energy of the waveform and the amplitude of the waveform as multiple feature quantities. Even in this case, the generation of the scatter diagram is the same as in the above-mentioned embodiment except that the feature quantities used in the generation of the scatter diagram are different. Fig. 9 and Fig.10 Evaluation based on a combination of other feature quantities (e.g., waveform energy and waveform amplitude) is described below. In this case, the evaluation unit 222 uses the acquired waveform energy and waveform amplitude to generate a scatter diagram with the horizontal axis being the waveform energy and the vertical axis being the waveform maximum amplitude.

[0063] Fig. 9 FIG. 2 shows an example of a scatter diagram obtained when no abnormality occurs in the compressor 1. Fig.10 An example of a scatter diagram obtained when an abnormality occurs in the compressor 1 is shown. Fig. 9 and Fig.10 The points 30 shown are points plotted based on a plurality of characteristic quantities obtained from elastic waves. Fig. 9 and Fig.10 Point 30 in is plotted based on the energy of the waveform obtained from the elastic wave and the amplitude of the waveform. In a compressor 1 in which an abnormality exists in the sliding portion inside the compressor 1, the energy of the elastic wave measured becomes larger than the case where there is no damage in the sliding portion inside the compressor 1. Therefore, when the number of plots above a certain energy set as a threshold value Th in the generated scatter diagram is greater than a prescribed number, the evaluation unit 222 evaluates that there is an abnormality inside the compressor 1. On the other hand, when the number of plots above a certain energy set as a threshold value Th in the generated scatter diagram is less than a prescribed number, the evaluation unit 222 evaluates that there is no abnormality inside the compressor 1. In addition, the threshold value Th is a predetermined value, which may be different depending on the type of the compressor 1 or may be the same.

[0064] In this embodiment, the rotation speed of the compressor 1 is described as 60 rps, but the rotation speed of the compressor 1 is not limited to this. For example, the rotation speed of the compressor 1 is preferably within the range of 30 rps to 70 rps. Fig.11 Provide explanation. Fig.11 2 is a graph showing the relationship between the rotation speed of the compressor 1 and the correct answer rate of the evaluation result of the evaluation unit 222. Fig.11 In FIG. 2 , the horizontal axis represents the rotation speed, and the vertical axis represents the correct answer rate. The correct answer rate is an indicator representing the evaluation accuracy of the evaluation unit 222. Fig.11The threshold in is a value that serves as a reference for the evaluation accuracy of the evaluation unit 222. If the correct answer rate is greater than the threshold, the evaluation accuracy of the evaluation unit 222 is good, and if the correct answer rate is less than the threshold, the evaluation accuracy of the evaluation unit 222 is poor. Fig.11 As shown, in the range of rotation speed of 30 rps to 70 rps, the correct answer rate is above the threshold value. In contrast, in the case where the rotation speed is less than 30 rps and more than 70 rps, the correct answer rate drops significantly. In the case of a low rotation speed (less than 30 rps), it is considered that the evaluation accuracy deteriorates because not many elastic waves can be detected. On the other hand, in the case of a high rotation speed (more than 70 rps), in addition to the elastic waves assumed to be caused by wear, a large number of elastic waves generated by collisions between internal devices are detected, so the evaluation accuracy deteriorates. Therefore, in order to detect damage inside the compressor 1 with high accuracy, it is considered that the rotation speed of the compressor 1 is preferably within the range of 30 rps to 70 rps.

[0065] In this embodiment, the evaluation unit 222 evaluates the abnormality of the compressor 1 based on the ratio of deviation from the approximate straight line derived from the correlation of multiple feature quantities. The evaluation unit 222 may also evaluate the abnormality of the compressor 1 using other methods based on the correlation of multiple feature quantities. For example, the evaluation unit 222 may also evaluate the abnormality of the compressor 1 based on the correlation coefficient and residual based on the correlation of multiple feature quantities. This will be described in detail below.

[0066] (When using the correlation coefficient)

[0067] When the duration of the strobe signal and the energy of the waveform are used as a plurality of feature quantities, the evaluation unit 222 calculates the correlation coefficient R between the duration of the strobe signal and the energy of the waveform based on the following equation (1). In equation (1), the duration of the strobe signal is x and the energy of the waveform is y.

[0068] [Mathematical formula 1]

[0069]

[0070] S in formula (1) xy It represents the covariance of the duration (x) of the strobe signal and the energy (y) of the waveform. x represents the standard deviation of the duration of the strobe signal. yThe standard deviation of the energy of the waveform. As the damage progresses and the number of separation points increases, the correlation between the multiple feature quantities is destroyed and the correlation coefficient decreases. Therefore, when the calculated correlation coefficient R is less than the threshold value, the evaluation unit 222 evaluates that an abnormality has occurred inside the compressor 1. When the calculated correlation coefficient R is greater than the threshold value, the evaluation unit 222 evaluates that no abnormality has occurred inside the compressor 1.

[0071] (Using residuals)

[0072] When the duration of the strobe signal and the energy of the waveform are used as a plurality of feature quantities, the evaluation unit 222 calculates the root mean square r of the residual when the correlation between the duration of the strobe signal and the energy of the waveform is expressed by linear approximation using the least squares method based on the following equation (2).

[0073] [Mathematical formula 2]

[0074]

[0075] f(x) in equation (2) represents an approximate straight line. N in equation (2) represents the number of data. The number of data is, for example, Figure 7 and Figure 8 The number of points 30 shown. When the calculated root mean square r is greater than the threshold, the evaluation unit 222 evaluates that an abnormality has occurred in the compressor 1. When the calculated root mean square r is less than the threshold, the evaluation unit 222 evaluates that no abnormality has occurred in the compressor 1.

[0076] According to at least one embodiment described above, there is a sensor, a filter, a signal processing unit, and an evaluation unit. The sensor detects elastic waves generated from the running industrial equipment. The filter allows elastic waves having frequency characteristics caused by wear generated inside the industrial equipment to pass through. The signal processing unit uses the elastic waves that have passed through the filter to extract multiple feature quantities. The evaluation unit evaluates the abnormality of the industrial equipment based on the combination of the extracted multiple feature quantities. In this way, the abnormality of the industrial equipment can be evaluated with high accuracy.

[0077] Several embodiments of the present invention are described, but these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in various other ways, and various omissions, substitutions, and changes can be made without departing from the scope of the invention. These embodiments and their variations are included in the scope and purpose of the invention, and are also included in the invention described in the claims and their equivalents.

Claims

1. A status evaluation system comprising: Sensors that detect elastic waves generated from operating industrial equipment; a filter capable of passing elastic waves having frequency characteristics caused by damage generated inside the industrial equipment; a signal processing unit that extracts a plurality of feature quantities using the elastic wave that has passed through the filter; and An evaluation unit evaluates abnormality of the industrial equipment based on a combination of the extracted plurality of feature quantities, The evaluation unit generates a scatter plot showing the correlation between the energy and duration of the elastic wave when the energy and duration of the elastic wave are used as the multiple feature quantities, draws an approximate straight line derived based on the correlation between the multiple feature quantities on the generated scatter plot, and when the proportion of points that are a specified distance away from the approximate straight line is greater than a threshold value, the industrial equipment is evaluated as abnormal.

2. The state evaluation system according to claim 1, wherein: The evaluation unit uses a plurality of elastic waves and evaluates that the industrial equipment is abnormal when a correlation coefficient derived from a plurality of feature quantities obtained from each of the plurality of elastic waves is smaller than a threshold value.

3. The state evaluation system according to claim 1, wherein: The evaluation unit uses a plurality of elastic waves and evaluates that the industrial equipment is abnormal when a root mean square of a residual with respect to an approximate straight line is greater than a threshold value, wherein the approximate straight line is derived based on a correlation relationship between a plurality of feature quantities obtained from each of the plurality of elastic waves.

4. A state evaluation device comprising an evaluation unit for evaluating abnormality of industrial equipment based on a combination of a plurality of feature quantities extracted using elastic waves, wherein: The elastic wave is detected by a sensor that detects the elastic wave generated from the operating industrial equipment, and the elastic wave has a frequency characteristic caused by damage. The evaluation unit generates a scatter plot showing the correlation between the energy and duration of the elastic wave when the energy and duration of the elastic wave are used as the multiple feature quantities, draws an approximate straight line derived based on the correlation between the multiple feature quantities on the generated scatter plot, and when the proportion of points that are a specified distance away from the approximate straight line is greater than a threshold value, the industrial equipment is evaluated as abnormal.

5. A condition evaluation method, which generates a scatter plot showing the correlation between the energy and duration of an elastic wave detected by a sensor for detecting elastic waves generated from a running industrial device and having frequency characteristics caused by damage, using the energy and duration of the elastic wave as multiple feature quantities extracted from the elastic wave, draws an approximate straight line derived based on the correlation between the multiple feature quantities on the generated scatter plot, and evaluates that the industrial device is abnormal when the proportion of points that are a specified distance away from the approximate straight line is greater than a threshold value.

Images