Patent Application
20240385030
The disclosure relates to a method for monitoring a device state of a device, in particular a device having a rotatable component, wherein a structure-borne noise signal of the device is measured. Furthermore, the disclosure relates to a system for monitoring a device state of a device, in particular a device having a rotatable component, wherein the system comprises a structure-borne noise meter, which is designed to measure a structure-borne noise signal of the device.
Vibration-based monitoring of device states of a component can be used to detect and minimize unplanned machine failures caused by unexpected or unanticipated faults. Conventional systems for monitoring a device state usually require the extensive expertise of an expert during installation and operation. The costs and necessary effort related to the equipment, installation and operation are typically too high to enable widespread use.
Known state monitoring systems typically rely either on a machine-specific configuration that requires expert knowledge and frequently local customization in order to enable monitoring of the machine state, or they use only vibration signal power, which provides only very basic state monitoring information and with which reliable monitoring of a device state of a device is usually not possible.
DE 10 2017 124 281 A1 describes a method for monitoring an operating state of a device, in particular a device having a rotating component, wherein a structure-borne noise signal of the device is measured and a spectrum (X) or an envelope of the structure-borne noise signal is ascertained, and at least one spectral audio feature (M1, M2) of the ascertained spectrum (X) is determined in order to ascertain an operating state of the device.
U.S. Pat. No. 6,370,957 B1 describes a method for determining the operating state of a rotary machine, comprising monitoring the machine under a base operating condition and acquiring base vibration data.
DE 199 45 058 A1 describes a method for determining the remaining service life of the switching contacts in an electrical switching device, wherein structure-borne noise signals of the switching contact arrangement generated by the switching operation are detected, these are then subjected to a Fourier transformation in order to generate a sonogram in individual time windows, and individual function values are ascertained specifically from the sonogram and evaluated by means of an evaluation device.
It is an object of the present disclosure to provide a reliable and/or inexpensive method for monitoring a device state of a device, which preferably allows for uncomplicated installation and/or operability of the monitoring system. Furthermore, it is an object to provide a corresponding system.
According to the disclosure, the object is achieved by a method for monitoring a device state of a device, in particular a device having a rotatable component, wherein a structure-borne noise signal of the device is measured, characterized in that during the operation of the device
According to the disclosure, a cost-efficient and reliable state monitoring can be achieved, which at the same time is particularly advantageously automated, so that the requirements on the technical expertise of the user of the monitoring system can be kept low. This makes it possible to apply improved state monitoring to a wide range of devices and machines for which systems and methods known from the prior art would be too costly and not economical. According to the disclosure, it is particularly advantageous that faults or defects in the device can be detected and assessed without a configuration by a user being required. Mechanical defects in devices with rotating components can be detected by monitoring machine vibrations. Initially, defects typically reveal themselves in either a lower or an upper frequency band. As the fault severity increases, the excitation resulting from the fault increases in amplitude and may also propagate over wider frequency ranges.
Preferably, the device state of the device is determined and/or checked at least on the basis of the first time range feature state and the second time range feature state.
According to the disclosure, it is conceivable that the method is a computer-implemented method. In particular, one, several, or all steps of the method are carried out by a computer, in particular, in an automated manner.
The device state determined and/or checked according to the disclosure indicates, in particular, whether the device is functioning normally or without a fault, or whether there is a fault and/or an indication of a fault.
Preferably, it is possible for automatic alerting to take place depending on the determined device state of the device. Thus, a particularly advantageous oscillation-based or vibration-based state monitoring system with automatic alerting methods can be achieved.
In particular, the rotatable component is a component that rotates during the operation of the device. Such a rotating component typically results in a measurable structure-borne noise signal. With the aid of the present disclosure, for example, fault conditions in rolling bearings or toothings can be detected at an early stage. Advantageously, this enables timely planning of maintenance activities and reduces the likelihood of unplanned downtimes occurring.
According to the disclosure, it is possible, for example, to use an audio feature-based anomaly detection that is responsive to a change in sound or tone or a change in the structure-borne noise signal of the device, and further to use a frequency-dependent evaluation of the structure-borne noise signal, such as of the energy of the structure-borne noise signal, in order to assess the severity of the fault.
According to one embodiment of the present disclosure, it is conceivable that during the operation of the device
According to one embodiment of the present disclosure, it is conceivable that in a training phase, in which the device is in particular in a predetermined good state and/or normal operation, the first time range feature of the first frequency band of the structure-borne noise signal of the device and the second time range feature of the second frequency band of the structure-borne noise signal of the device are determined wherein, using the first time range feature of the first frequency band determined in the training phase, the upper and/or the lower first threshold relating to the first time range feature are determined and, in particular, stored,
According to one embodiment of the present disclosure, it is conceivable that in the training phase one or more further first time range features of the first frequency band of the structure-borne noise signal of the device and/or one or more further second time range features of the second frequency band of the structure-borne noise signal of the device are determined,
According to one embodiment of the present disclosure, it is conceivable that the first time range feature is one of the following features of the structure-borne noise signal relating to the first frequency band:
According to one embodiment of the present disclosure, it is conceivable that the second time range feature is one of the following features of the structure-borne noise signal relating to the second frequency band:
According to one embodiment of the present disclosure, it is conceivable that the structure-borne noise signal is a time range signal, wherein the structure-borne noise signal comprises in particular one or more of the following signals:
According to one embodiment of the present disclosure, it is conceivable that the first frequency band is a lower frequency band of the structure-borne noise signal and wherein the second frequency band is an upper frequency band of the structure-borne noise signal. In particular, the lower frequency band is below the upper frequency band. It is conceivable that the lower and upper frequency bands are spaced apart from one another. Alternatively, it is conceivable that the lower and upper frequency bands adjoin one another.
It is possible according to one embodiment of the present disclosure that the lower frequency band comprises a frequency range from 0 Hz to 750 Hz and/or that the upper frequency band comprises a frequency range from 750 Hz to 3000 Hz, preferably to 5000 Hz. In particular, it is conceivable that the lower frequency band extends from 0 Hz to 750 Hz and/or that the upper frequency band extends from 750 Hz to 3000 Hz, preferably from 750 Hz to 5000 Hz. Other values for the frequency bands are also conceivable. It is conceivable that technical characteristics of the device and/or empirical values concerning the device and/or technical restrictions are taken into account for the specific selection of the frequency bands. It is conceivable that the lower frequency band and/or the upper frequency band are fixed. Alternatively, it would be possible for the lower frequency band and/or the upper frequency band to be variable.
According to the disclosure, it is provided that the first time range feature state can be assigned to one of at least three categories, in particular to one of the following categories:
Accordingly, according to one embodiment of the present disclosure in which one or more further first time range features are used, it is possible for the one or more further first time range feature states each to be assignable to one of at least three categories, in particular to one of the following categories:
Accordingly, according to one embodiment of the present disclosure in which one or more further second time range features are used, it is possible for the one or more further second time range feature states each to be assignable to one of at least three categories, in particular to one of the following categories:
According to one embodiment of the present disclosure, it is conceivable that the ascertained device state of the device can be assigned to one of at least four categories, wherein the categories comprise in particular the following state categories:
According to one embodiment of the present disclosure, it is conceivable that the ascertained device state of the device is ascertained from the individual time range feature states considered such that:
According to one embodiment of the present disclosure, it is conceivable that an embodiment of the present disclosure, in particular an embodiment of the present disclosure described above, can be combined with an additional audio feature-based anomaly detection, for example a detection according to DE 10 2017 124 281 A1. It is conceivable that when an anomaly is detected according to a method of DE 10 2017 124 281 A1, the device state of the device is assigned at least to the category “suspicion of fault” and/or “suspected fault” (or even to the category “warning” or “significant warning” and/or “danger”).
According to one embodiment of the present disclosure, it is conceivable that an embodiment of the present disclosure, in particular an embodiment of the present disclosure described above, is combined with a consideration and/or evaluation of a temperature of the device. For this purpose, a temperature gauge is preferably provided, which is designed to measure a temperature of the device. If the measured temperature of the device is “elevated” (in particular, is above a first temperature threshold), the device state of the device is assigned at least to the category “suspicion of fault” and/or “suspected fault”. If the measured temperature of the device is “high” (in particular, is above a second temperature threshold greater than the first temperature threshold), the device state of the device is assigned at least to the category “warning”.
According to one embodiment of the present disclosure, it is conceivable that an embodiment of the present disclosure, in particular an embodiment of the present disclosure described above, is combined with a standard vibration signal feature for which known thresholds exist. This can be, for example, a velocity RMS (root mean square) value as defined in ISO 20816. By applying such a standardized absolute threshold, possible difficulties in determining the lower and upper (first and second) thresholds for the first time range feature/second time range feature/further first time range feature/further second time range feature, etc., (in the training phase, if the device is not in a normal state (good state) during this time) can be particularly advantageously reduced.
According to one embodiment of the present disclosure, it is conceivable that an embodiment of the present disclosure, in particular an embodiment of the present disclosure described above, is combined with rules for ascertaining the type or nature of a defect or fault. For example, if the ascertained device state of the device has a category of “warning” or “significant warning” and/or “danger,” it is conceivable that the probable nature of the fault is ascertained from the individual ascertained time range feature states (first time range feature state, second time range feature state, etc.). For this purpose, it is possible to use or take into account other additional information, for example the type of system/installation, when determining the type of fault.
According to one embodiment of the present disclosure, it is possible that depending on the ascertained device state, in particular in the case of an ascertained suspicion of a fault, a warning and/or a significant warning, a notification is automatically sent to a user so that the user can initiate countermeasures. Alternatively or additionally, it is conceivable that depending on the ascertained device state, in particular in the case of an ascertained suspicion of a fault, a warning and/or a significant warning, countermeasures are automatically initiated, for example a shutdown of the device. Other countermeasures are also conceivable alternatively or additionally.
A further object of the present disclosure is a system for monitoring a device state of a device, in particular a device having a rotatable component, wherein the system comprises a structure-borne noise meter, which is designed to measure a structure-borne noise signal of the device, characterized in that:
In particular, the system comprises switching means or a computer designed to carry out the steps of a method according to one embodiment of the present disclosure, preferably in an automated manner. In this context, the features, embodiments and advantages that have already been described in connection with the method according to the disclosure or in connection with an embodiment of the method according to the disclosure can be applied to the system according to the disclosure.
Further details and advantages of the disclosure will be explained below with reference to the exemplary embodiments shown in the drawings. In the figures:
Referring to
In a feature extraction 110, at least one first time range feature F1L and preferably one or more further first time range features F2L, . . . , FnL are ascertained for a first frequency band of the structure-borne noise signal 200. “F1L, . . . , FnL” here denote a total of “n” first time range features, wherein “n” is a natural number (“n” may be, for example, 2, 3, 4, 5, 6, 7, etc.). Furthermore, the feature extraction 110 ascertains at least one second time range feature F1H and preferably one or more further second time range features F2H, . . . , FmH for a second frequency band of the structure-borne noise signal 200. “F1H, . . . , FmH” here denote a total of “m” second time range features, wherein “m” is a natural number (“m” may be, for example, 2, 3, 4, 5, 6, 7, etc.).
In a feature state assessment 120, the ascertained first time range features F1L, . . . , FnL of the first frequency band are in each case compared with an upper and a lower first threshold. By means of this comparison, a corresponding own first time range feature state SF1L, . . . , SFnL is determined for each of the considered first time range features F1L, . . . , FnL.
Furthermore, in the feature state assessment 120, the ascertained second time range features F1H, . . . , FmH of the second frequency band are in each case compared with an upper and a lower second threshold. By means of this comparison, a corresponding second time range feature state SF1H, . . . , SFmH is determined for each of the considered second time range features F1H, . . . , FmH.
In a device state assessment 130, the device state 140 of the device 1 is then determined from the ascertained time range feature states SF1L, . . . , SFnL, SF1H, . . . , SFmH.
According to one embodiment of the present disclosure, a method according to the disclosure can comprise the following steps.
Two sets of one or more time range features F1L, . . . , FnL and F1H, . . . , FmH are, in each case, defined for a lower and an upper frequency band of a time range vibration signal (or structure-borne noise signal 200), which are used to ascertain a device state 140 of a device 1. The time range features F1L, . . . , FnL and F1H, . . . , FmH can comprise, for example, a standard deviation, a kurtosis, or other features specifically designed for vibration-based state monitoring systems. The time range vibration signal (or structure-borne noise signal 200) can be, for example, an acceleration signal or a velocity signal, which is ascertained, for example, by means of a structure-borne noise meter 2 on the device 1.
Baseline values for the considered time range features are preferably ascertained in an initial training phase during which the device 1 is in an assumed good state and in operation. From these baseline values, an upper and a lower threshold each are determined for each of the considered time range features F1L, . . . , FnL and F1H, . . . , FmH (and in particular per frequency band).
By monitoring the considered time range features F1L, . . . , FnL and F1H, . . . , FmH during further operation of the device 1, in particular after the training phase has been completed, a time range feature state SF1L, . . . , SFnL and SF1H, . . . , SFmH can be ascertained for each of the considered time range features F1L, . . . , FnL and F1H, . . . , FmH:
The device state 140 of the device 1 is obtained from the individual ascertained time range feature states SF1L, . . . , SFnL and SF1H, . . . , SFmH of the considered time range features F1L, . . . , FnL and F1H, . . . , FmH, in particular in accordance with the behavior of the development (previously already described) with respect to the amplitude and frequency range of the excitations:
Initially, defects typically reveal themselves in either a lower or an upper frequency band. As the fault severity increases, the excitation resulting from the fault increases in amplitude and may also propagate over wider frequency ranges.
The ascertained device state 140 of the device 1 can be specified using, for example, the following categories or classes:
According to one exemplary embodiment, the ascertained device state 140 of the device 1 is obtained from the individual time range feature states SF1L, . . . , SFnL, SF1H, . . . , SFmH considered as follows:
It is possible that depending on the ascertained device state 140, in particular in the case of an ascertained suspicion of a fault, a warning and/or a significant warning, a notification is automatically sent to a user so that the user can initiate countermeasures. Alternatively or additionally, it is conceivable that depending on the ascertained device state 140, in particular in the case of an ascertained suspicion of a fault, a warning and/or a significant warning, countermeasures are automatically initiated, for example a shutdown of the device 1.
Referring to
| Number | Date | Country | Kind |
|---|---|---|---|
| 102021109102.0 | Apr 2021 | DE | national |
This application is a U.S. national stage application under 35 U.S.C. § 371 that claims the benefit of priority under 35 U.S.C. § 365 of International Patent Application No. PCT/DE2022/100181, filed on Mar. 8, 2022, designating the United States of America, which in turn claims the benefit of priority under 35 U.S.C. §§ 119, 365 of German Patent Application No. 102021109102.0, filed Apr. 13, 2021, the contents of which are relied upon and incorporated herein by reference in their entirety.
| Filing Document | Filing Date | Country | Kind |
|---|---|---|---|
| PCT/DE2022/100181 | 3/8/2022 | WO |
