Sound inspection system and sound inspection method

Abstract

To enable abnormality level outputs of multiple sensor devices to be compared on the same criteria.SOLUTION: A sound inspection system that determines the state of an inspection target on the basis of a sound of the inspection target includes: a model generation unit that generates a normal sound model from normal operating sounds of the inspection target; a sampling unit that samples multiple feature values from the normal sound model; an abnormality calculation unit that calculates an abnormality level of each of the sampled multiple feature values on the basis of the normal sound model; and a gamma distribution generating unit that generates an abnormality level correction model by fitting the frequency distribution of the abnormality level with a gamma distribution. Using the abnormality level correction model, the abnormality level is linked with an occurrence probability.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a sound inspection system and a sound inspection method. [Background technology]

[0002] At power plants, chemical plants, steel plants, and other such sites, workers often listen to the operating sounds of equipment to determine whether it is normal. However, experience is required to be able to distinguish between abnormal sounds. Furthermore, workers are burdened with walking around a large site and inspecting it by ear. Moreover, in recent years, skilled workers have been aging, making it difficult to secure new workers. Therefore, as described in Patent Document 1, a system has been proposed that detects acoustic data of a monitored object using a microphone and wirelessly transmits it to a monitoring processing device located away from the monitored object. Specifically, Patent Document 1 states that "the device comprises a pressure-resistant explosion-proof housing 18 having a pressure-resistant explosion-proof structure, a microphone 20 built into the pressure-resistant explosion-proof housing 18 for detecting sound in the equipment to be monitored, a camera 22 built into the pressure-resistant explosion-proof housing 18 for capturing images of the equipment to be monitored, an information processor 24 built into the pressure-resistant explosion-proof housing 18 for processing sound data from the microphone 20 and image data from the camera 22 and controlling the microphone 20 and the camera 22, a wireless device 26 for transmitting the sound data and image data processed by the information processor 24 and receiving control signals for the microphone 20 and the camera 22, and an antenna 28 built into the pressure-resistant explosion-proof housing 18 and connected to the wireless device 26." [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2009-273113 A Summary of the Invention [Problem to be solved by the invention]

[0004] In the conventional technology described in Patent Document 1, the monitoring processing device calculates a frequency spectrum from the acoustic data received from the on-site monitoring device, and detects the occurrence of an abnormality in the monitored object using a neural network model. However, the sound data has a large data size as is, so the measurement and analysis processing is heavy and increases the power consumption.

[0005] When installing a sensor device on a plant's on-site equipment as a so-called retrofit, it is difficult to obtain a wired power source. Therefore, since the sensor device operates using an internal battery as a power source, the battery runs out quickly when a process that consumes a lot of power is executed, and the battery needs to be replaced frequently, resulting in low usability. Therefore, a sensor device has been proposed that extracts features from recorded sounds, compares them with a normal sound model that is generated when the sensor device is installed and stored in the sensor terminal, calculates the deviation from the normal sound model as an anomaly level, and then collects only the anomaly level. This reduces the amount of data communication and enables the sensor to be operated for a long period of time using the internal battery.

[0006] In the sensor devices described above, a different normal sound model is generated for each sensor device, and the degree of abnormality is calculated based on this. This is because the normal sound models generated differ slightly depending on the installation conditions of the sensor devices and the minute individual differences of the sensor devices, even when monitoring the operating sounds of equipment of the same model number. In such cases, the difference in the standard normal sound model for each sensor device leads to a difference in the meaning of the degree of abnormality calculated for each sensor device, making it difficult to set a standard for comparing the values ​​of the degree of abnormality between different sensor devices in a system in which multiple sensor devices are in operation. For this reason, it is not possible to set a common threshold for multiple sensors to monitor multiple devices, making it difficult to use for equipment monitoring.

[0007] The present invention has been made in consideration of the above-mentioned problems, and its object is to provide a sound inspection system and a sound inspection method that are capable of comparing the abnormality level outputs of multiple sensor devices using the same criteria. [Means for solving the problem]

[0008] In order to solve the above problems, one representative sound inspection system of the present invention is a sound inspection system that determines the state of an object to be inspected based on the sound of the object to be inspected, and includes a model generation unit that generates a normal sound model from the normal operating sound of the object to be inspected, a sampling unit that samples a number of features from the normal sound model, an abnormality calculation unit that calculates the degree of abnormality of each of the sampled features based on the normal sound model, and a gamma distribution generation unit that fits the frequency distribution of the degree of abnormality with a gamma distribution to generate an abnormality correction model, and is characterized in that the degree of abnormality and the occurrence probability are linked using the anomaly correction model. Furthermore, one representative sound inspection method of the present invention is a sound inspection method for determining the state of an object to be inspected based on the sound of the object to be inspected, in which a learning device generates a normal sound model from the normal operating sound of the object to be inspected, samples a plurality of features from the normal sound model, calculates the degree of abnormality of each of the sampled features based on the normal sound model, and fits the frequency distribution of the degree of abnormality with a gamma distribution to generate an abnormality correction model, and a data management device, when determining the state of the object to be inspected, links the degree of abnormality calculated based on the sound of the object to be inspected and the normal sound model to an occurrence probability using the abnormality correction model. Effect of the Invention

[0009] According to the present invention, it is possible to compare the abnormality degree outputs of a plurality of sensor devices based on the same criteria. Problems, configurations and effects other than those described above will become apparent from the following description of the embodiments. [Brief description of the drawings]

[0010] [Figure 1] FIG. 13 is an overall explanatory diagram of the sound inspection system during learning. [Diagram 2] 13 is a flowchart for creating an anomaly correction model. [Diagram 3] An example of fitting the sampled anomaly distribution with a gamma distribution. [Figure 4]An example of the relationship between the degree of anomaly and occurrence probability. [Diagram 5] An example of threshold settings for different anomaly time series per site. [Figure 6] Overall explanation of the sound inspection system when in operation (part 1). [Figure 7] Overall explanation of the sound inspection system when in operation (part 2). [Figure 8] Overall explanation of the sound inspection system when in operation (part 3). [Figure 9] A table to compare data from multiple devices. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. In this embodiment, as described in detail below, operation sounds generated in on-site equipment such as a plant are collected by a sensor device, and operation sounds when the equipment is in a normal state are learned by a learning terminal as normal sounds.

[0012] A number of feature quantities are randomly sampled from the normal sound model generated in the learning terminal as a result of learning, and the degree of anomaly is calculated for each of the obtained feature quantities using the normal sound model. Furthermore, the distribution of the obtained degrees of anomaly is fitted with a gamma distribution to obtain an expression for the gamma distribution that well explains the distribution of the degrees of anomaly. Finally, an anomaly correction model that links any degree of anomaly with its occurrence probability is generated using the right-side cumulative distribution of the gamma distribution, making it possible to interpret the degrees of anomaly calculated using different normal sound models for each sensor device using a common index, the occurrence probability of the corresponding degree of anomaly. EXAMPLES

[0013] An embodiment will be described with reference to Figures 1 to 9. Figure 1 shows an overall configuration diagram of a sound inspection system 1. The sound inspection system 1 of this embodiment is applied to plants such as power plants, chemical plants, and steel plants.

[0014] In a plant, there are installed equipment (inspection object 2) that generates sounds, such as motors, pumps, compressors, turbines, boilers, etc. The sounds generated here are steady rotation sounds generated by rotating machines, and it is known that deterioration of the bearings installed as bearings is observed as a change in the operating sounds. The role of the sound inspection system is to detect this change in the operating sounds.

[0015] A sensor device 10 is provided in the vicinity of the inspection object 2. The sensor device 10 may be provided in contact with the inspection object 2, or may be provided away from the inspection object 2. A plurality of sensor devices 10 may be provided on one inspection object 2.

[0016] The sensor device 10 includes, for example, a microphone 11, an analysis unit 12, a communication unit 13, and a power supply unit 14. Here, a device in which a sensor function and a communication function are integrated is shown, but the sensor function and the wireless communication function may be separately configured and connected.

[0017] The microphone 11 collects sounds emitted by the inspection target object 2 and outputs them as an electrical signal. The electrical signal output from the microphone 11 is input to the analysis unit 12. The analysis unit 12 includes at least a normal sound model 15 and an AD conversion unit 16, and converts the sounds collected by the microphone 11 into digital data, which is then sent to the communication unit 13 as a data string. The communication unit 13 transmits the collected sound data string to the learning device 20. The communication means L1 may be either wired or wireless, but a high-speed communication protocol is desirable since sound data has a large data volume.

[0018] The power supply unit 14 supplies power from an internal battery to the microphone 11, the analysis unit 12, and the communication unit 13 of the sensor device 10. Any type of internal battery may be used.

[0019] The learning device 20 includes, for example, a communication unit 21, a learning unit 22, a model storage unit 23, and a network communication unit 24. For example, the learning device 20 may be configured as a general-purpose computer.

[0020] The communication unit 21 has a function of receiving a data string of sound data from the sensor device 10 and inputting it to the learning unit 22. For example, a USB, Bluetooth (registered trademark), or the like is used as the serial communication means.

[0021] The learning unit 22 includes a feature extraction unit 25, a model generation unit 26, a baseline correction unit 27, a random sampling unit 29, an abnormality degree calculation unit 30, a frequency distribution generation unit 31, and a gamma distribution generation unit 32. The learning unit 22 has a function of generating a normal model by processing normal sound data acquired by the sensor device 10, and a function of generating an abnormality degree correction model using the normal sound model.

[0022] The feature extraction unit 25 calculates a vector indicating the characteristics of the sound data received from the sensor device 10 as a feature. For example, this feature is a vector of about 100 dimensions expressing the characteristics of the frequency components of the sound data and the changes in the frequency components over time. The feature extraction unit 25 may include an iterative calculation in which a long-duration sound source is divided into multiple short-duration sound sources and a feature is extracted for each short-duration sound source. In this case, multiple features are extracted according to the length of the sound source.

[0023] The model generation unit 26 generates the part of the normal sound model excluding the baseline correction by using the feature quantity output by the feature quantity extraction unit 25. For example, a GMM (Gaussian Mixture Distribution) or the like is used as the normal sound model, but the present invention is not limited to this and cases where various distributions are adopted are also included in the scope of the present patent.

[0024] Below, we will describe the case where a normal sound model is constructed using GMM. As shown in formula 1, a normal sound model is constructed by a linear combination of multiple Gaussian distributions. Here, K indicates the number of Gaussian distributions, and in the kth Gaussian distribution, πk is the weighting coefficient of the Gaussian distribution, μk is the mean vector of the Gaussian distribution, and Σk is the variance-covariance matrix. Modeling may be performed after formula 1 is determined in advance, or the number of Gaussian distributions may be adaptively changed according to the feature amount. Also, a model may be generated by incremental learning, which sequentially learns multiple feature amounts, or by batch learning, which learns multiple feature amounts at once.

number

[0025] The baseline correction unit 27 is a functional block that corrects the degree of anomaly using a baseline obtained by multiplying the average value of the log likelihood for M features by minus 1 for the GMM obtained by formula 1. The baseline correction is introduced for the purpose of correcting the expected value in the normal case to zero when the degree of anomaly is calculated by applying the features to the GMM.

[0026] The baseline b calculated by the baseline correction unit 27 and πk, μk, and Σk calculated by the model generation unit 26 are combined to form (b, πk, μk, Σk), which is stored in the model storage unit 23 as a normal sound model 28. Here, k indicates the k-th Gaussian distribution in the GMM consisting of K Gaussian distributions.

[0027] The random sampling unit 29 extracts multiple feature vectors according to the GMM shown in Equation 1. There are several known random sampling methods, such as the direct method and Gibbs sampling, and any method may be used. However, in the case of Gibbs sampling, a certain number of sampling results from the start of sampling must be discarded as a burn-in period, and the output of the random sampling unit 29 is the discarded sampling results from this burn-in period.

[0028] The anomaly degree calculation unit 30 calculates the degree of anomaly using the sampling results obtained by the random sampling unit 29 as an input y. For multiple sampling results, the operation of calculating one degree of anomaly for each is repeated the number of times equal to the number of samples.

[0029] The frequency distribution generating unit 31 generates a frequency distribution of the multiple degrees of anomaly generated by the degree of anomaly calculating unit 30. The data interval for generating the frequency distribution is adjusted to a certain degree of freedom depending on the number of samples in the random sampling unit 29. For example, when 100,000 points are sampled, it is preferable to set the data interval of the degree of anomaly to about 0.5 to 1.

[0030] The gamma distribution generation unit 32 performs fitting on the frequency distribution obtained by the frequency distribution generation unit 31 using the gamma distribution function shown in Equation 2. Here, the fitting parameters are α, β, and A. In Equation 2, b is the baseline correction value included in the normal sound model 28. The fitting result (α, β, A) is stored in the model storage unit 23 as the abnormality correction model 33.

number

[0031] The model storage unit 23 has a function of storing the normal sound model 28 and the abnormality degree correction model 33 generated by the learning unit 22. The model storage unit 23 includes information for identifying which sensor device the normal sound model 28 and the abnormality degree correction model 33 correspond to. As an example, unique ID information of the sensor device is used. The normal sound model is also transferred to the sensor device via the communication unit. The abnormality degree correction model 33 is also transferred to the data management device 40 via the network communication unit 24.

[0032] The network communication unit 24 connects the learning device 20 and the data management device 40 via communication means L2. When the learning device 20 is configured as, for example, a general computer, the network communication unit is, for example, a wired and wireless LAN.

[0033] The data management device 40 is composed of a network communication unit 41, an anomaly correction model 42, anomaly data 43, an anomaly threshold setting unit 44, and a time-series data generation unit 45, and has the function of generating, storing, and visualizing time-series data on anomaly.

[0034] The network communication unit 41 is used by the data management device 40 to receive the anomaly degree correction model 42 and the anomaly degree data 43 from the learning device 20 via the communication means L2. The anomaly degree data 43 also includes additional information such as a unique ID for identifying the sensor device 10 and a timestamp at which the anomaly degree was acquired.

[0035] The anomaly correction model is generated by the learning device 20 and stored in the data management device 40. The anomaly threshold setting unit 44 sets a threshold value as the degree of anomaly that results in a certain occurrence probability according to the anomaly correction model .

[0036] The time-series data generating unit 45 has a function of generating, displaying, and storing time-series data including a threshold value using information from the abnormality threshold setting unit 44 and the abnormality data 43.

[0037] The procedure for generating an anomaly degree correction model will be described using the flow shown in FIG.

[0038] Sound data is acquired in S100, and then features are extracted in S101. Next, a normal sound model is acquired by learning a plurality of features (S102). Hereinafter, GMM is assumed as the normal sound model in the explanation of Fig. 2. However, the normal sound model here is not limited to GMM, and other probability distributions may be used.

[0039] The generated GMM is stored as a normal sound model (S103). Next, the obtained GMM is used to randomly sample multiple features according to the GMM (S104). As a guideline, about 1000 to 10000 points are preferable in terms of speed and accuracy.

[0040] The degree of abnormality of the randomly sampled features is applied to the GMM obtained in S103 to calculate the log likelihood, and the average value of the multiple log likelihoods is saved in the normal sound model as the baseline b (S105).

[0041] Next, random sampling of features for generating an anomaly correction model is performed from the normal sound model (S106). The number of samples at this time is preferably about 10,000 to 100,000. If the number of sampling points is too small, the shape of the frequency distribution becomes rough and the accuracy of the anomaly correction model decreases, whereas if the number of sampling points is too large, sampling takes time and the processing time becomes long.

[0042] Next, the degree of anomaly of the sampled features is calculated using a normal sound model as the log-likelihood of the GMM (S107).

[0043] The obtained degree of abnormality is subjected to a frequency analysis to obtain a frequency distribution (S108).

[0044] Using Equation 2, the frequency distribution at anomaly degree x>0 is fitted with a gamma distribution to obtain fitting parameters A, α, and β (S109). These fitting parameters are the anomaly degree correction model.

[0045] Finally, the obtained anomaly correction model is used to perform a calculation to link the anomaly degree x with its occurrence probability P(x) (S110), where P(x) is given by the right-sided cumulative distribution of the gamma distribution.

[0046] The fitting shown in S109 in Fig. 2 will be described with reference to Fig. 3. Fig. 3 shows an example of a result 311 of fitting a frequency distribution 310 using a gamma distribution. As shown in Fig. 3, the frequency distribution of the degree of anomaly can be fitted well using an appropriate set of parameters A, α, β and a baseline b.

[0047] The relationship between the degree of anomaly and the occurrence probability is shown in Figure 4. 412 is a plot of the right-side cumulative distribution of the gamma distribution calculated using the anomaly correction model against the degree of anomaly. This relationship is generated individually when multiple sensor devices exist. In other words, the relationship between the degree of anomaly and its occurrence probability is unique to each sensor device. Therefore, the relationship shown in Figure 4 (anomaly correction model 42) is calculated and stored for each sensor device.

[0048] With reference to FIG. 5, a description will be given of how the sound inspection system provided in this embodiment enables time series of various abnormalities in different sensor devices A to C to be interpreted in a unified manner.

[0049] Sensor devices A to C are different sensor devices installed in different facilities, and the obtained anomaly level values ​​are calculated for each normal sound model. Therefore, the anomaly level values ​​obtained from each sensor device cannot be compared with those of other sensor devices. However, since the relationship between the anomaly level and the occurrence probability can be calculated using the anomaly level correction model in each sensor device, it is possible to set an anomaly level with an occurrence probability of, for example, 1E-10 in each sensor device. If this is set as an example threshold, it becomes possible to operate in such a way that an alert is raised when an anomaly level exceeding the occurrence probability of 1E-10 is observed in all sensor devices.

[0050] A first example of equipment monitoring performed by the sound inspection system of the first embodiment will be shown using Fig. 6. Note that Fig. 1 shows a system for generating a normal sound model and an abnormality degree correction model, and that there are new functional blocks that are used when equipment monitoring is performed.

[0051] The sensor device 10 includes, for example, a microphone 11, an analysis unit 12, a communication unit 13, and a power supply unit 14. Here, a device in which a sensor function and a wireless communication function are integrated is shown, but the sensor function and the wireless communication function may be separately configured and connected.

[0052] The microphone 11 collects sounds emitted by the inspection target object 2 and outputs them as an electrical signal. The electrical signal output from the microphone 11 is input to the analysis unit 12. The analysis unit 12 includes a normal sound model 15, an AD conversion unit 16, a feature extraction unit 17, and an abnormality degree calculation unit 18, analyzes the sounds collected by the microphone 11, and sends the analysis results to the communication unit 13.

[0053] The AD conversion unit 16 samples and quantizes the amplitude of the analog signal, converts it into a digital value, and transmits it to the feature extraction unit 17. The feature extraction unit 17 has the same function as the feature extraction unit 25 in FIG. 1. However, unlike FIG. 1, it operates in the sensor device 10. The anomaly degree calculation unit 18 is a functional block that calculates the degree of anomaly using the normal sound model 15, similar to the anomaly degree calculation unit 30 in FIG. 1. However, unlike FIG. 1, it operates in the sensor device 10. The normal sound model 15 is generated by the learning device 20 in FIG. 1 and transferred to and stored in the sensor device 10.

[0054] The communication unit 13 communicates with the communication unit 21 of the wireless base station 60 to transmit a packet of the analysis result generated by the analysis unit 12 to the data management device 40. The packet of the analysis result is transmitted to the wireless base station 60 as shown by communication means L1, which is a wireless communication path, and is further transmitted from the wireless base station 60 to the data management device 40 as shown by communication means L2, which is a wireless communication path.

[0055] The power supply unit 14 supplies power from an internal battery to the microphone 11, the analysis unit 12, and the communication unit 13 of the sensor device 10, which is a wireless slave station. Any type of internal battery may be used.

[0056] The wireless master station 60 is a relay device constituting part of a sensor network spread throughout the plant. A sound sensor network may be included as part of the sensor network. In this case, the sensor network may include a sensor network that detects temperature, humidity, pressure, voltage value, current value, frequency, resistance value, flow rate, flow velocity, color, image, etc., in addition to the sound sensor network that detects and diagnoses abnormal sounds. Alternatively, all of the sensor networks in the plant may be sound sensor networks.

[0057] The wireless master station 60 can wirelessly communicate with a plurality of sensor devices 10 and transmit packets (analysis result data) from each sensor device 10 to the data management device 40. Packets can also be transferred between adjacent sensor devices 10 by a so-called bucket brigade method.

[0058] The data management device 40 may have the function of the wireless master station 60. In this case, the sensor device 10 can directly communicate with the data management device 40 by wireless communication.

[0059] The data management device 40 holds the analysis results received from the sensor device 10. The data management device 40 may be configured as a computer including, for example, a microprocessor, a main memory device, an auxiliary memory device, an input / output circuit, a communication circuit, a user interface device (none of which are shown), and the like.

[0060] The data management device 40 includes, for example, a network communication unit 41, an anomaly degree correction model 42, anomaly degree data 43, an anomaly degree threshold setting unit 44, and a time-series data generating unit 45.

[0061] The network communication unit 41 has a function of communicating with the wireless master station 60. The anomaly degree data 43 is data extracted from a packet of analysis results received from the sensor device 10, which is a wireless slave station, and stored in association with the time of collection. The functions of the anomaly degree correction model 42 and the anomaly degree threshold setting unit 44 are the same as those in FIG. 1.

[0062] The time-series data generating unit 45 is a function that provides time-series data and threshold information from the anomaly degree threshold setting unit 44 and the anomaly degree data 43 in response to a request from the monitoring terminal 50. The monitoring terminal 50 outputs the time-series data to a display, a printer, etc., in the form of a graph display or the like. It is also possible to analyze the variation pattern of the anomaly degree for the time-series data held by the time-series data generating unit 45 by providing a data analysis process such as a clustering process in the data management device.

[0063] 7 shows a second example of the case where the sound inspection system of the embodiment 1 performs facility monitoring. The configuration of the analysis unit of the sensor device 10 is different from that of the first example shown in FIG.

[0064] 6 in that the analysis unit 12 of the sensor device 10 has an anomaly degree conversion unit 19 and an anomaly degree correction model 42. The anomaly degree correction model 42 is the same as the anomaly degree correction model 42 in Fig. 1 at the time of learning, and is transferred to the sensor device 10 from the learning device 20 and stored therein.

[0065] The abnormality degree conversion unit 19 has a function of converting the abnormality degree into an occurrence probability by using the abnormality degree correction model 42. For this conversion, for example, the relationship shown in FIG.

[0066] 8 shows a third example of the case where the sound inspection system of the first embodiment performs facility monitoring. The configuration of the data management device is different from that of the first example shown in FIG.

[0067] The data management device 40 differs from that shown in Fig. 6 in that it is newly provided with an anomaly degree conversion unit 19. This anomaly degree conversion unit 19 has a function of converting the degree of anomaly into the occurrence probability of that degree of anomaly, using an anomaly degree correction model 42 and anomaly degree data 46. For this conversion, the relationship shown in Fig. 4, for example, is used.

[0068] Figure 9 is a table comparing data from multiple devices, for example to determine repair priorities. By applying the method according to the present invention, the anomaly probability is calculated using the same criteria for different devices, and this can be used to accurately compare the device conditions. This enables condition-based maintenance, whereby maintenance is given priority to devices with a high anomaly probability.

[0069] As described above, the disclosed system is a sound inspection system 1 that determines the state of an object to be inspected based on the sound of the object to be inspected, and includes a model generation unit 26 that generates a normal sound model from the normal operating sound of the object to be inspected, a sampling unit (random sampling unit 29) that samples a plurality of features from the normal sound model, an anomaly calculation unit 30 that calculates the degree of anomaly of each of the sampled features based on the normal sound model, and a gamma distribution generation unit 32 that fits the frequency distribution of the degree of anomaly with a gamma distribution to generate an anomaly correction model, and is characterized in that the degree of anomaly is linked to the occurrence probability using the anomaly correction model. This system can indicate the degree of abnormality in the condition of the object being inspected in terms of its occurrence probability, eliminating the effects of installation conditions and individual differences and making it possible to compare the abnormality outputs of multiple sensor devices using the same criteria.

[0070] The disclosed system also includes a learning device 20 having the model generation unit 26, the sampling unit, the anomaly calculation unit 30, and the gamma distribution generation unit 32, a sensor device 10 that collects sounds of the inspection object, and a data management device 40, wherein the model generation unit 26 generates a normal sound model from the operating sounds collected by the sensor device 10, and the data management device 40 links the degree of anomaly with the occurrence probability using the anomaly correction model generated by the learning device 20. In this system, the learning device that generates the normal sound model and the abnormality correction model can be removed from the configuration during inspection.

[0071] Moreover, the data management device 40 calculates the right-sided cumulative distribution of a gamma distribution using the abnormality correction model in order to link the abnormality degree with the occurrence probability. Therefore, the occurrence probability can be easily calculated from the gamma distribution.

[0072] As an example, when determining the condition of the inspection object, the sensor device 10 collects the sound of the inspection object, calculates the degree of abnormality of the collected sound based on the normal sound model, and transmits the calculated degree of abnormality, and the data management device 40 outputs data indicating the condition of the inspection object based on the degree of abnormality transmitted by the sensor device. In this configuration, the processing load of the sensor device 10 is reduced, and the data management device 40 can output the degree of abnormality of the sensor device 10 according to a unified standard.

[0073] As an example, when determining the condition of the inspection object, the sensor device 10 collects sounds from the inspection object, calculates the degree of abnormality of the collected sounds based on the normal sound model, and converts the degree of abnormality into an occurrence probability based on the abnormality correction model. In this configuration, the sensor device 10 converts the degree of anomaly into an occurrence probability, so that the outputs of the sensor device 10 can be directly compared.

[0074] As an example, when determining the condition of the inspection object, the sensor device collects the sound of the inspection object, calculates the degree of abnormality of the collected sound based on the normal sound model, transmits the calculated degree of abnormality, and the data management device converts the degree of abnormality into an occurrence probability based on the abnormality correction model. In this configuration, the processing load of the sensor device 10 is reduced, and the data management device 40 can output the occurrence probability of the state of the sensor device 10 .

[0075] Moreover, in the disclosed system, the learning device 20 generates a plurality of anomaly degree correction models corresponding to the plurality of sensor devices 10 . Moreover, the data management device 40 displays and outputs a plurality of occurrence probabilities for a plurality of the sensor devices 10 in a comparable manner. Therefore, by calculating the relationship between the degree of abnormality calculated based on a normal sound model that differs for each sensor device and the probability of occurrence of that degree of abnormality, the degree of abnormality and the occurrence probability are linked, making it possible to set a threshold based on the occurrence probability value and perform monitoring.

[0076] The present invention is not limited to the above-mentioned embodiment, and various modifications are included. For example, the above-mentioned embodiment is described in detail to easily explain the present invention, and is not necessarily limited to the embodiment having all the described configurations. Moreover, the present invention is not limited to the deletion of the configurations, and it is also possible to replace or add the configurations. For example, the object of inspection is not limited to a rotating machine, as long as it is a device that continuously generates a certain sound. The abnormality to be detected will be one that appears as a change in the continuously generated sound. Also, there may be multiple output thresholds. [Explanation of symbols]

[0077] 1: Sound inspection system, 2: Inspection object, 10: Sensor device, 11: Microphone, 12: Analysis unit, 13: Communication unit, 14: Power supply unit, 15: Normal sound model, 16: AD conversion unit, 17: Feature extraction unit, 18: Anomaly calculation unit, 19: Anomaly conversion unit, 20: Learning device, 21: Communication unit, 22: Learning unit, 23: Model storage unit, 24: Network communication unit, 25: Feature extraction unit, 26: Model generation unit, 27: Base line correction unit, 28: normal sound model, 29: random sampling unit, 30: abnormality degree calculation unit, 31: frequency distribution generation unit, 32: gamma distribution generation unit, 33: abnormality degree correction model, 40: data management device, 41: network communication unit, 42: abnormality degree correction model, 43: abnormality degree data, 44: abnormality degree threshold setting unit, 45: time series data generation unit, 46: abnormality degree data, 50: monitoring terminal, 60: wireless master station

Claims

1. A sound inspection system for determining a state of an inspection object based on a sound of the inspection object, a model generation unit that generates a normal sound model from the normal operation sound of the inspection object; a sampling unit for sampling a plurality of feature quantities from the normal sound model; an abnormality degree calculation unit that calculates an abnormality degree of each of the sampled feature quantities based on the normal sound model; a gamma distribution generating unit that generates an anomaly correction model by fitting the frequency distribution of the anomaly with a gamma distribution; Equipped with A sound inspection system characterized in that the degree of abnormality is linked to the occurrence probability using the abnormality correction model.

2. 2. A sound inspection system according to claim 1, a learning device including the model generation unit, the sampling unit, the anomaly calculation unit, and the gamma distribution generation unit; A sensor device that collects sounds from the inspection object; A data management device, The model generation unit generates a normal sound model from the operation sound collected by the sensor device, The sound inspection system is characterized in that the data management device links the degree of anomaly with an occurrence probability using the anomaly correction model generated by the learning device.

3. 3. A sound inspection system according to claim 2, The sound inspection system, wherein the data management device calculates a right-sided cumulative distribution of a gamma distribution using the anomaly correction model in order to link the anomaly degree and the occurrence probability.

4. 3. A sound inspection system according to claim 2, When determining the state of the inspection object, the sensor device collects sounds from the inspection object, calculates an abnormality level of the collected sounds based on the normal sound model, and transmits the calculated abnormality level; The sound inspection system is characterized in that the data management device outputs data indicating the state of the inspection object based on the degree of abnormality transmitted by the sensor device.

5. 3. A sound inspection system according to claim 2, When determining the state of the inspection object, the sensor device Collecting sounds from the object to be inspected; Calculating an abnormality level of the collected sound based on the normal sound model; The abnormality degree is converted into an occurrence probability based on the abnormality degree correction model. A sound inspection system comprising:

6. 3. A sound inspection system according to claim 2, When determining the state of the inspection object, the sensor device collects sounds from the inspection object, calculates an abnormality level of the collected sounds based on the normal sound model, and transmits the calculated abnormality level; The sound inspection system according to claim 1, wherein the data management device converts the degree of abnormality into an occurrence probability based on the degree of abnormality correction model.

7. 3. A sound inspection system according to claim 2, The sound inspection system is characterized in that the learning device generates a plurality of abnormality degree correction models corresponding to a plurality of the sensor devices.

8. A sound inspection system according to claim 7, The sound inspection system is characterized in that the data management device displays and outputs a plurality of occurrence probabilities for a plurality of the sensor devices in a comparative manner.

9. A sound inspection method for determining a state of an inspection object based on a sound of the inspection object, comprising: The learning device generating a normal sound model from the normal operating sound of the inspection object; Sampling a plurality of feature amounts from the normal sound model; Calculating the degree of abnormality of each of the sampled features based on the normal sound model; fitting the frequency distribution of the anomaly with a gamma distribution to generate an anomaly correction model; The data management device, when determining the state of the inspection object, A sound inspection method, comprising: linking the degree of abnormality calculated based on the sound of the inspection object and the normal sound model to an occurrence probability using the abnormality degree correction model.

Images