Device and method for determining operating state of rotating machine

Abstract

An apparatus and method of determining an operating state of a rotating machine. The method includes receiving a plurality of parameter values corresponding to a plurality of parameters measured by one or more sensors placed in proximity to the rotating machine. The plurality of parameter values belong to one or more measurement axes supported by the one or more sensors. The method further includes selecting, among the plurality of parameter values, a set of parameter values having a maximum value measured by each sensor, and comparing the set of parameter values to corresponding predefined thresholds. Thereafter, the method includes determining a set of intermediate operating states of the rotating machine based on the comparison, and determining a final operating state of the rotating machine based on the set of intermediate operating states.

Description

Technical Field

[0001] This disclosure generally relates to rotating machinery. More specifically, this disclosure relates to monitoring the operating status of rotating machinery. Background Technology

[0002] Rotary electric motors are widely used in various industries, including blowers, fans, machine tools, pumps, turbines, power tools, alternators, compressors, rolling mills, ships, lawnmowers, paper machines, and more. The continuous rotation of these motors causes a gradual decline in bearing life and grease quality. Failure to schedule maintenance at appropriate intervals can lead to catastrophic failures of rotating equipment. To address this issue, sensors such as vibration sensors, magnetic field sensors, and acoustic sensors, along with signal analysis techniques, have been employed to determine the operating status of these motors. By analyzing the operating status of rotating equipment, the duration of operation can be estimated, and valuable insights such as relubrication recommendations and bearing life predictions can be provided.

[0003] However, in current industrial settings, stray vibrations caused by surrounding rotating equipment significantly impact the detection of operating conditions. These vibrations can interfere with measurement accuracy, leading to unreliable results. Furthermore, the traditional use of current sensors to determine motor operating conditions is not considered a cost-effective solution due to their limitations in accurately assessing operating conditions.

[0004] Therefore, to overcome these challenges and enhance maintenance practices associated with rotary electric motors, an improved solution is needed. Techniques are required to address stray vibration problems, which can hinder the detection of operating conditions and to effectively mitigate their effects. Summary of the Invention

[0005] This disclosure overcomes one or more of the disadvantages discussed above and provides additional advantages. Additional features and advantages are achieved through the technology of this disclosure. Other embodiments and aspects of this disclosure are described in detail herein and are considered part of this disclosure.

[0006] In one non-limiting embodiment of this disclosure, a method for determining the operating state of a rotating machine is disclosed. The method includes receiving multiple parameter values ​​corresponding to multiple parameters measured by one or more sensors placed near the rotating machine, wherein the multiple parameter values ​​belong to one or more measurement axes supported by the one or more sensors. The method further includes selecting a set of parameter values ​​having the maximum value measured by each sensor from the multiple parameter values, and comparing the set of parameter values ​​with corresponding predefined thresholds. Thereafter, the method includes determining a set of intermediate operating states of the rotating machine based on the comparison results; and determining a final operating state of the rotating machine based on the set of intermediate operating states.

[0007] In another non-limiting embodiment of this disclosure, the plurality of parameters are selected from the group consisting of: peak-to-average power ratio (PAPR) measured from the spectrum of sensor data, and achieved by finding the peak-to-average power ratio (PAPR) within a predetermined frequency range of interest.

[0008] In yet another non-limiting embodiment of this disclosure, the parameters are selected from the group consisting of correlation coefficients calculated from a predetermined spectral range of sensor data between different axes.

[0009] In another non-limiting embodiment of this disclosure, the intermediate operating states of the rotating machine are determined separately using one or more sensors, using predefined threshold logic, or using a classifier developed using machine learning techniques.

[0010] In another non-limiting embodiment of this disclosure, determining the final operating state of the rotating machine based on the group of intermediate operating states includes: when all operating states in the group of operating states indicate the operating state of the rotating machine, the final operating state is determined as the operating state; when any operating state in the group of operating states indicates the closed state of the rotating machine, the final operating state is determined as the closed state.

[0011] In another non-limiting embodiment of this disclosure, the method further includes: performing data acquisition for monitoring the condition of the rotating machine when the final operating state is an on state; and preventing data acquisition and further processing for monitoring the condition of the rotating machine when the final operating state is a off state.

[0012] In another non-limiting embodiment of this disclosure, a method for determining the operating state of a rotating machine is disclosed. The method includes determining multiple parameter values ​​associated with the operation of the rotating machine based on measurement data obtained for the rotating machine. The method further includes generating a comparison matrix comprising multiple index values ​​corresponding to the multiple parameter values, wherein each index value indicates whether the corresponding parameter value is less than, equal to, or greater than a corresponding threshold. Furthermore, the method includes generating a quality matrix by processing the multiple index values ​​of the comparison matrix and identifying the highest index value present in the quality matrix. The method also includes mapping the highest index value of the quality matrix to the corresponding index value in the comparison matrix to determine the operating state of the rotating machine.

[0013] In another non-limiting embodiment of this disclosure, the comparison matrix is ​​generated by comparing a plurality of parameter values ​​with corresponding plurality of thresholds, wherein the plurality of parameter values ​​belong to one or more measurement axes supported by one or more sensors providing measurement data; and generating the comparison matrix based on the comparisons.

[0014] In another non-limiting embodiment of this disclosure, the parameters include one or more of the following: root mean square (RMS) magnetic flux, signal-to-noise ratio (SNR), harmonic energy ratio, velocity RMS, the ratio of peak magnetic flux to magnetic flux time-domain RMS, and the ratio of peak acceleration to velocity RMS.

[0015] In another non-limiting embodiment of this disclosure, the comparison matrix is ​​M. The matrix N is a matrix where M represents the number of parameter values ​​and N represents the number of measurement axes corresponding to the received parameter values.

[0016] In another non-limiting embodiment of this disclosure, measurement data obtained from one or more sensors are associated with at least one of the magnetic field of the rotating machine and the acceleration of the rotating machine.

[0017] In another non-limiting embodiment of this disclosure, generating a quality matrix by processing multiple index values ​​of a comparison matrix includes: using the comparison matrix, performing row-by-row and column-by-column comparisons on each index value of the comparison matrix with subsequent index values ​​of the comparison matrix; when performing row-by-row comparisons in the comparison matrix, generating a first matrix by incrementing the index values ​​of the comparison matrix by a first predefined value when an index value matches a subsequent index value; and when performing column-by-column comparisons in the comparison matrix, generating a second matrix by incrementing the index values ​​of the comparison matrix by a second predefined value when an index value matches a subsequent index value. The method further includes generating a third matrix by summing the first and second matrices, and generating the quality matrix by multiplying multiple index values ​​of the third matrix by their corresponding weights.

[0018] In yet another non-limiting embodiment of this disclosure, determining the operating state of the rotating machine includes: determining the operating state as an "on" state when the index value of the comparison matrix mapped to the highest index value is equal to or greater than a threshold value; and determining the operating state as a "off" state when the index value of the comparison matrix mapped to the highest index value is less than a threshold value.

[0019] In another non-limiting embodiment of this disclosure, an apparatus for determining the operating state of a rotating machine is disclosed. The apparatus includes: a processing unit configured to: receive multiple parameter values ​​corresponding to multiple parameters measured by one or more sensors placed near the rotating machine, wherein the multiple parameter values ​​belong to one or more measurement axes supported by the one or more sensors; select a set of parameter values ​​from the multiple parameter values ​​having the maximum value measured by each sensor; compare the set of parameter values ​​with corresponding predefined thresholds; determine a set of intermediate operating states of the rotating machine based on the comparisons; and determine a final operating state of the rotating machine based on the set of intermediate operating states.

[0020] The foregoing overview is illustrative only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments, and features described above, other aspects, embodiments, and features will become apparent from the accompanying drawings and the following detailed description. Attached Figure Description

[0021] The accompanying drawings, which are incorporated in and form a part of this disclosure, illustrate exemplary embodiments and, together with the description, serve to explain the principles disclosed. Some embodiments of apparatuses and / or methods according to this subject matter will now be described by way of example only and with reference to the accompanying drawings, in which:

[0022] Figure 1 An exemplary block diagram of an apparatus for determining the operating state of a rotating machine according to an embodiment of the present disclosure is shown;

[0023] Figure 2 A block diagram of a process for determining the operating state of a rotating machine according to an embodiment of the present disclosure is shown;

[0024] Figure 3 A flowchart illustrating an exemplary method for determining the operating state of a rotating machine according to some embodiments of the present disclosure is shown; and

[0025] Figure 4 A flowchart illustrating an exemplary method for determining the operating state of a rotating machine according to some embodiments of the present disclosure is shown.

[0026] Those skilled in the art will understand that any block diagram herein represents a conceptual view of an illustrative system embodying the principles of the subject matter. Similarly, it should be understood that any flowchart, diagram, state transition diagram, pseudocode, etc., represents various processes that can be substantially represented in a computer-readable medium and executed by a computer or processor, whether or not such computer or processor is explicitly shown. Detailed Implementation

[0027] In this document, the term "exemplary" is used herein to mean "as an example, instance, or illustration." Any embodiment or implementation of the subject matter described herein as "exemplary" is not necessarily to be construed as more preferred or advantageous than other embodiments.

[0028] While this disclosure is readily adaptable to various modifications and alternatives, specific embodiments thereof have been illustrated by way of example in the accompanying drawings and will be described in detail below. However, it should be understood that this is not intended to limit this disclosure to the specific forms disclosed, but rather to cover all modifications, equivalents, and alternatives falling within the spirit and scope of this disclosure.

[0029] The terms “comprise(s)”, “comprising”, “include(s)”, or any other variations thereof are intended to cover non-exclusive inclusion. Therefore, an arrangement, device, apparatus, system, or method that comprises a list of components or steps may include not only those components or steps but also other components or steps not expressly listed, or other components or steps inherent in such an arrangement, device, apparatus, system, or method. In other words, one or more elements in an apparatus, system, or system introduced by “comprising…one” do not exclude the presence of other elements or additional elements in the system, unless further constraints are imposed.

[0030] In the following detailed description of embodiments of this disclosure, reference is made to the accompanying drawings, which form a part of this disclosure, and are illustrated in the drawings by way of explaining specific embodiments in which this disclosure may be practiced. These embodiments have been described in sufficient detail to enable those skilled in the art to practice this disclosure, and it should be understood that other embodiments may be utilized and changes may be made without departing from the scope of this disclosure. Therefore, the following description is not restrictive. Well-known functions or structures are not described in detail in the following description because they would be obscured by unnecessary detail.

[0031] To address the aforementioned challenges, this disclosure proposes a solution based on non-invasive sensors. By utilizing sensor data, various signal processing techniques can be employed to accurately determine the operating state of a motor in a cost-effective manner. These techniques may include, but are not limited to, analytical parameters such as root mean square (RMS) flux, signal-to-noise ratio (SNR), harmonic energy ratio, velocity RMS, the ratio of peak flux to the time-domain RMS of flux, and the ratio of peak acceleration to the velocity RMS. These disclosed techniques mitigate the influence of adjacent motors, thereby providing accurate determination of the operating state of rotating machinery.

[0032] By utilizing non-invasive sensors and developing advanced signal processing techniques, this disclosure aims to provide a cost-effective and accurate solution for determining the operating status of rotary electric motors. The disclosed technology overcomes the limitations of current sensor-based methods and enables proactive maintenance planning, reduces downtime, and improves the overall operating efficiency and reliability of rotary electric motors.

[0033] Figure 1 This is a block diagram of a system for monitoring the operating status of a rotating machine according to embodiments of the present disclosure. Figure 1As shown, system 100 may include a rotating machine 102 and a monitoring device 104 for determining the operating state of the rotating machine 102. Monitoring device 104 may include a processing unit 106, a sensor 108, a memory 110, and a communication unit 112. Processing unit 106 may include at least one processor, which may include, but is not limited to, a microprocessor, microcomputer, microcontroller, central processing unit, state machine, logic circuit device, and / or any device that manipulates signals based on operating instructions. In embodiments of this disclosure, processing unit 106 may also be implemented as a combination of devices, such as a combination of multiple microprocessors or any other such configuration. At least one memory 110 may be communicatively coupled to processing unit 106 and may include various instructions. At least one memory 110 may include random access memory (RAM) cells and / or non-volatile memory cells, such as read-only memory (ROM), optical disc drives, disk drives, flash memory, electrically erasable read-only memory (EEPROM), storage space on servers or in the cloud, etc. Processing unit 106 may be configured to execute one or more instructions stored in memory 110. The memory 110 can also store data processed by the processing unit 106 and the sensor 108. The communication unit 112 can be a wireless communication unit that can be used to send or receive any kind of data or information to or from external components. The communication unit 112 enables the device 104 to exchange data with a cloud (not shown) for further processing.

[0034] In one embodiment, the monitoring device 104 (which may also be used interchangeably as device 104) can be a portable device. In one embodiment, device 104, together with processing unit 106, sensor 108, and memory 110, can be easily held and carried by an operator to allow unrestricted movement around rotating machine 102. The operator can easily position device 104 at different locations on the machine to be tested or monitored. In a factory where rotating machine is located, there may be other machines located at different locations relative to rotating machine. In some cases, these machines may be located near rotating machine, leaving no available space for installing monitoring device 104. By integrating sensor 108 with portable monitoring device 104, the operator can flexibly place monitoring device 104 without any obstacles, effectively addressing different situations. This adaptability proves valuable in performing monitoring, adapting to different machine arrangements found within the factory.

[0035] In one embodiment, sensor 108 may include, but is not limited to, a magnetometer, a torque sensor, a microphone, and an accelerometer. Sensor 108 can be used to collect measurement data associated with rotating machinery. In one embodiment, a magnetometer can be used to collect information about the magnetic field surrounding the rotating machinery. This data is valuable for assessing magnetic interference, detecting anomalies, or monitoring magnetism. Furthermore, a torque sensor allows for the accurate measurement and monitoring of the rotational forces of the rotating machinery. By accurately quantifying torque, a torque sensor can provide insights into the machine's performance, efficiency, and stress. This information can be used for predictive maintenance, identifying potential problems, or optimizing operating parameters. Additionally, a microphone enables device 104 to capture acoustic signals propagating through the air. The microphone can convert audio signals into electrical signals, making it possible to detect audible vibrations and noise emitted by the rotating machinery. Furthermore, an accelerometer can be used to measure acceleration, vibration, and motion. By utilizing this sensor, monitoring device 104 can capture and interpret the dynamic motion and vibration exhibited by the rotating machinery. This allows for the assessment of structural integrity, machine vibration, or any deviation from normal operating conditions. Therefore, by selecting one or more sensors, monitoring device 104 can provide a comprehensive and accurate analysis of the operating status, health, and surrounding environment of the motor.

[0036] In one embodiment, a device 104 including one or more sensors 108 may be placed near a rotating machine to measure data associated with the machine's operation. This data may include, for example, magnetic field data, electric field data, and vibration data. The measurement data may be processed by a processing unit 106 to determine multiple parameter values ​​associated with the operation of the rotating machine 102 based on the measurement data obtained from the rotating machine. In an exemplary embodiment, the multiple parameters may include, but are not limited to, root mean square (RMS) magnetic flux, signal-to-noise ratio (SNR), harmonic energy ratio, velocity RMS, the ratio of peak magnetic flux to the time-domain RMS of magnetic flux, and the ratio of peak acceleration to the velocity RMS. In a non-limiting exemplary embodiment, device 104 may include a dedicated unit to calculate the values ​​of the multiple parameters by processing the aforementioned data provided by the sensors 108. In one embodiment, the sensor 108 may be a multi-axis sensor, such as a triaxial sensor, but is not limited to. Therefore, the multiple parameter values ​​may belong to one or more measurement axes supported by the sensor 108.

[0037] In one embodiment, if a particular machine is in an on state, a rotating magnetic flux exists around it. Therefore, it can be determined whether the magnetic flux exceeds a certain threshold. Regarding the ratio of the peak value in the magnetic spectrum to the time-domain RMS of the magnetic flux, the dominant peak value of the magnetic spectrum and whether it exceeds a desired threshold limit when compared to the total magnetic RMS are determined. Furthermore, when the machine is running, the velocity RMS will also exceed a certain limit. Therefore, it can be determined whether the velocity RMS exceeds a certain threshold. Additionally, it is checked whether the dominant peak value in the acceleration spectrum exceeds a certain limit when compared to the velocity RMS. Regarding the harmonic energy ratio, for the operating speed of the rotating machine, the velocity harmonic energy (i.e., the square root of the sum of the squares of the maximum velocity amplitudes of all velocity harmonics) and the total energy (i.e., the square root of the sum of the squares of the squares of all velocity amplitudes in the velocity vibration spectrum) are determined, and then the harmonic energy ratio (i.e., the ratio of harmonic energy to total energy) is determined. Regarding SNR, for the operating speed of a rotating machine, the peak energy (i.e., the sum of squares of the velocity harmonic amplitudes) and noise energy (i.e., the square root of the sum of squares of all values ​​in the velocity amplitude array except for the velocity harmonic amplitudes) are calculated, and the SNR is then the ratio of peak energy to noise energy. Furthermore, regarding the ratio of peak values ​​in the magnetic spectrum to the time-domain RMS of the magnetic flux, the dominant peaks of the magnetic spectrum are identified, and it is determined whether they exceed a desired threshold limit when compared to the total magnetic RMS.

[0038] After obtaining the values ​​of multiple parameters, the processing unit can compare these values ​​with corresponding predefined thresholds. In one embodiment, when using sensor 108 to measure data associated with a rotating machine, it is important to mitigate the influence of adjacent machines. The measurements obtained from sensor 108 can be affected by the operation of adjacent machines or external factors. To address this issue, predefined thresholds are used. The threshold can serve as a reference point or limit, against which the measured parameter values ​​are compared. By comparing the parameter values ​​with the predefined thresholds, the influence of adjacent machines or external factors can be filtered out.

[0039] Based on the comparison, the processing unit can generate a comparison matrix, which includes multiple index values ​​corresponding to multiple parameter values. Each index value indicates whether the corresponding parameter value is less than, equal to, or greater than the corresponding threshold. In a non-limiting exemplary embodiment, the index values ​​can be in the form of "0" and "1". "0" indicates that the parameter value is less than the corresponding threshold, while "1" indicates that the parameter value is greater than or equal to the corresponding threshold. Those skilled in the art will understand that any other index value can be used instead of "0" and "1".

[0040] In one embodiment, processing unit 106 may perform necessary calculations and algorithms to generate a comparison matrix. The comparison matrix may represent the relationship between measured parameter values ​​and their compliance with predefined thresholds. The comparison matrix may be M... The matrix N is a number of parameters, where M represents the number of measurement axes corresponding to the received parameter values.

[0041] In one embodiment, if only accelerometer data is available, only the following four parameter values ​​can be determined: harmonic energy ratio, velocity RMS, the ratio of peak flux to the time-domain RMS of flux, and the ratio of peak acceleration to the velocity RMS. Therefore, a value of 4 can be generated. A 3x3 matrix. The size of the matrix is ​​determined by the combination of four parameters and three axes (depending on the number of axes supported by the accelerometer sensor). However, if only magnetometer data is available, only the following two parameter values ​​can be determined: root mean square (RMS) magnetic flux and signal-to-noise ratio (SNR). Therefore, a 2x3 matrix can be generated. A 3x3 matrix. The size of the matrix is ​​determined by the combination of two parameters and three axes (depending on the number of axes supported by the magnetometer sensor). However, if both accelerometer and magnetometer sensor data are available, the following six parameter values ​​can be determined: root mean square (RMS) magnetic flux, signal-to-noise ratio (SNR), harmonic energy ratio, velocity RMS, the ratio of peak magnetic flux to the time-domain RMS of magnetic flux, and the ratio of peak acceleration to the velocity RMS. Therefore, a 6x3 matrix can be generated. A matrix of size 3. The size of the matrix is ​​determined by the combination of six parameters and three axes.

[0042] Furthermore, the processing unit 106 can generate a quality matrix by processing multiple index values ​​of the comparison matrix. In one embodiment, to generate a quality matrix by processing multiple index values ​​of the comparison matrix, the processing unit 106 can perform row-by-row comparisons and column-by-column comparisons on each index value of the comparison matrix with subsequent index values ​​of the comparison matrix. When performing row-by-row comparisons in the first matrix, when an index value matches a subsequent index value, the processing unit 106 can generate a first matrix by incrementing the index value of the first matrix by a first predefined value. Furthermore, when performing column-by-column comparisons in the first matrix, when an index value matches a subsequent index value, the processing unit 106 can generate a second matrix by incrementing the index value of the first matrix by a second predefined value. Subsequently, the processing unit 106 can generate a third matrix by summing the first and second matrices.

[0043] Subsequently, processing unit 106 generates a quality matrix by multiplying the index values ​​of the third matrix by their corresponding weights. Processing unit 106 identifies the highest index value in the quality matrix and maps this highest index value to the corresponding index value in the comparison matrix to determine the operating state of the rotating machine. When the index value of the comparison matrix mapped to the highest index value is equal to or greater than a threshold, processing unit 106 can determine the operating state as "on," and when the index value of the comparison matrix mapped to the highest index value is less than the threshold, it can determine the operating state as "off."

[0044] The examples mentioned in each paragraph can be easily understood using the following examples. Let's assume the comparison matrix is ​​a 4 3-matrix. 1 0 1 0 1 1 1 0 0 1 1 0

[0045] Processing unit 106 can perform row-by-row comparisons between each index value in the comparison matrix and subsequent index values. When performing a row-by-row comparison, if an index value in the comparison matrix matches a subsequent adjacent value, processing unit 106 can increment the index value by a first predefined value. Let's assume the first predefined value is 1. In the first row: • The first indicator value (1) is compared with the subsequent indicator value (0). • The second indicator value (0) is compared with the subsequent indicator value (1). • The third indicator value (1) is compared with the subsequent indicator value, namely the first indicator value (end of line, the first indicator value that wraps back to the same line). Therefore, in this case, the comparison results are as follows: • The first indicator value (1) is compared with the subsequent indicator value (0), and the result is a mismatch. • The second indicator value (0) is compared with the subsequent indicator value (1), and the result is a mismatch. • The third indicator value (1) is compared with the subsequent indicator value (1) in the same row, and the result is a match. For the remaining rows, a row-by-row comparison is performed in a similar manner. After performing the row-by-row comparison, processing unit 106 can generate the first matrix, as shown below: 1 0 2 0 2 1 1 2 0 2 1 0

[0046] Similar to row-wise comparisons, processing unit 106 can perform column-by-column comparisons between each index value in the comparison matrix and its subsequent adjacent value in the same column. When performing a column-by-column comparison, if an index value in the comparison matrix matches a subsequent adjacent value, the processing unit can increment the index value by a second predefined value. Let's assume the second predefined value is 2. Processing unit 106 can perform column-by-column comparisons (using the technique described above) on the entire matrix and generate a third matrix, as shown below: 1 0 3 0 1 1 3 0 2 3 1 0

[0047] After generating the first and second matrices, the processing unit 106 can generate the third matrix by summing the first and second matrices, as shown below: 205 0 3 2 4 2 2 5 2 0

[0048] After generating the third matrix, processing unit 106 can generate a quality matrix by multiplying the index values ​​of the third matrix by their corresponding weights. In one example, the weights might look like this: 1 0 2 0 1 0 1 1 1 1 2 1

[0049] The quality matrix can be obtained by element-wise multiplication of the third matrix and the weights. The quality matrix is ​​as follows: 2010 0 3 0 4 2 2 5 4 0

[0050] Subsequently, processing unit 106 can identify the highest index value, i.e., 10, present in the quality matrix. Processing unit 106 can map the highest index value of the quality matrix to the corresponding index value in the comparison matrix to determine the operating state of the rotating machine. In this example, the index value of the comparison matrix mapped to the highest index value (10) is 1. Therefore, processing unit 106 can determine the operating state as "on state" because the index value of the mapped comparison matrix is ​​"1".

[0051] In this way, the monitoring device can reduce the impact on operational status detection. The device can accurately monitor the motor's operational status in a cost-effective and efficient manner.

[0052] In another embodiment, this disclosure provides an alternative solution for monitoring the operating status of a rotating machine. The alternative solution provides a technique for determining the operating status of a rotating machine 102, which has the following characteristics: independence from set thresholds, low computational and spatial complexity, suitability for operation on different types of machines, different frame sizes and vibration levels, suitability for handling different environmental and noise conditions (such as adjacent interference), and detection of steady-state and transient states, but is not limited thereto. Figure 2 The illustration shows a block diagram for monitoring operational status according to this embodiment.

[0053] In this embodiment, the processing unit 106 of device 104 can receive multiple parameter values ​​corresponding to multiple parameters measured by one or more sensors placed near the rotating machine, as shown in block 202. In one embodiment, the multiple parameters may be one or more of the following: peak-to-average power ratio (PAPR) measured from the spectrum of sensor data, and implemented by finding the PAPR in a predetermined frequency range of interest, but not limited thereto. In another embodiment, the multiple parameters are selected from the following: correlation coefficients calculated from a predetermined spectral range of sensor data between different axes, but not limited thereto.

[0054] Processing unit 106 can select a set of parameter values ​​from a plurality of parameter values ​​that have the maximum value measured by each sensor, as shown in block 204. Furthermore, processing unit 106 can compare this set of parameter values ​​with corresponding predefined thresholds, as shown in block 206. Subsequently, processing unit 106 can determine a set of intermediate operating states of the rotating machine based on this comparison, as shown in block 208. The intermediate operating states of the rotating machine can be determined using sensor 108, using predefined threshold logic, or using a classifier developed using machine learning techniques. In one embodiment, algorithms and techniques of TinyML (Micro Machine Learning) can be used to develop machine learning models to create models that can be effectively deployed and executed on embedded devices.

[0055] Subsequently, processing unit 106 can determine the final operating state of the rotating machine based on a set of intermediate operating states, as shown in block 210. Specifically, when all operating states in the set indicate that the rotating machine 102 is in an "on" state, processing unit 106 can determine the final operating state as "on," and when any operating state in the set indicates that the rotating machine 102 is in a "off" state, processing unit 106 can determine the final operating state as "off." After determining the final operating state of the rotating machine 102, when the final operating state is "on," processing unit 106 can allow data acquisition and further processing for monitoring the condition of the rotating machine 102 (as shown in block 212), and when the final operating state is "off," processing unit 106 can prevent data acquisition and further processing for monitoring the condition of the rotating machine 102 (as shown in block 214).

[0056] The embodiments mentioned in each paragraph can be easily understood through the examples shown in Table-1 below. Table 1 above describes the states obtained from the accelerometer and the magnetometer. The state can be "on" or "off." As shown in the table, when the states from the accelerometer and magnetometer indicate that the rotating machine 102 is on, the machine 102 can be determined to be on. However, if one of these indicates a off state, the final operating state can be determined to be off. Table 1 also indicates the transient state of matter based on the on and off states indicated by the accelerometer and magnetometer.

[0057] In this way, monitoring device 104 can mitigate the impact on operational status detection. Device 104 can accurately monitor the motor's operational status in a cost-effective manner. Furthermore, the disclosed technology allows processing only when the machine is on, rather than continuously calculating KPIs on the device regardless of its on / off state, which improves the battery life of various processing and monitoring devices. In addition, this technology is independent of setting thresholds for on / off detection, saving considerable resources.

[0058] Figure 3 This is a flowchart illustrating an exemplary method 300 for determining the operating state of a rotating machine. For ease of explanation, Figure 3 The blocks in the flowchart shown are arranged in a generally sequential manner; however, it should be understood that this arrangement is merely exemplary and that it should be recognized that, with method 300 (and...), the actual arrangement is different. Figure 3 The processes associated with the block shown may occur in different orders (e.g., at least some of the processes associated with the block are executed in parallel and / or in an event-driven manner).

[0059] In step 302, the method describes determining multiple parameter values ​​associated with the operation of the rotating machine based on obtained measurement data of the rotating machine. In one embodiment, the measurement data obtained from one or more sensors may be associated with at least one of the magnetic field and acceleration of the rotating machine. Furthermore, the multiple parameter values ​​belong to one or more measurement axes supported by one or more sensors. In one embodiment, the one or more sensors may be selected from the group consisting of, but are not limited to, magnetometers, torque sensors, microphones, and accelerometers. In another embodiment, the multiple parameters may include one or more of, but are not limited to, root mean square (RMS) magnetic flux, signal-to-noise ratio (SNR), harmonic energy ratio, velocity RMS, the ratio of peak magnetic flux to the time-domain RMS of magnetic flux, and the ratio of peak acceleration to velocity RMS.

[0060] The method in step 304 describes generating a comparison matrix comprising multiple index values ​​corresponding to multiple parameter values. Each index value can indicate whether the corresponding parameter value is less than, equal to, or greater than a corresponding threshold. The comparison matrix is ​​generated by comparing multiple parameter values ​​with their corresponding thresholds and generating the comparison matrix based on these comparisons. In one embodiment, the comparison matrix may be M. The matrix N is a number of parameters, where M represents the number of measurement axes corresponding to the received parameter values.

[0061] In step 306, the method describes generating a quality matrix by processing multiple index values ​​of a comparison matrix. In one embodiment, generating the quality matrix by processing multiple index values ​​of a comparison matrix may include performing row-by-row and column-by-column comparisons on each index value of the comparison matrix with subsequent index values ​​of the comparison matrix. Subsequently, when performing row-by-row comparisons in the comparison matrix, a first matrix can be generated by incrementing the index values ​​of the comparison matrix by a predefined value when an index value matches a subsequent index value. Furthermore, when performing column-by-column comparisons in the comparison matrix, a second matrix can be generated by incrementing the index values ​​of the comparison matrix by a second predefined value when an index value matches a subsequent index value. A third matrix can then be generated by summing the first and second matrices. Finally, the quality matrix can be generated by multiplying the multiple index values ​​of the third matrix by their corresponding weights.

[0062] In step 308, the method describes identifying the highest index value present in the quality matrix. In step 310, the method describes mapping the highest index value of the quality matrix to a corresponding index value in a comparison matrix to determine the operating state of the rotating machine. In one embodiment, determining the operating state of the rotating machine includes: determining the operating state as an "on" state when the index value of the comparison matrix mapped to the highest index value is equal to or greater than a threshold, and determining the operating state as a "off" state when the index value of the comparison matrix mapped to the highest index value is less than the threshold.

[0063] In this way, the method reduces the impact on operational status detection. The device can accurately monitor the motor's operational status in a cost-effective and efficient manner.

[0064] Figure 4 This is a flowchart illustrating another exemplary method 400 for determining the operating state of a rotating machine. For ease of explanation, Figure 4 The blocks in the flowchart shown are arranged in a general order; however, it should be understood that this arrangement is merely exemplary and that it should be recognized that, with method 400 (and...), the actual arrangement is different. Figure 4 The processes associated with the block shown may occur in different orders (e.g., at least some of the processes associated with the block are executed in parallel and / or in an event-driven manner).

[0065] In step 402, the method describes receiving multiple parameter values ​​corresponding to multiple parameters measured by one or more sensors placed near the rotating machine, wherein the multiple parameter values ​​belong to one or more measurement axes supported by the one or more sensors. In one embodiment, the one or more sensors may be selected from the group consisting of magnetometers, torque sensors, microphones, and accelerometers, but are not limited thereto. In another embodiment, the multiple parameters may be selected from the group consisting of peak-to-average power ratio (PAPR) measured from the spectrum of sensor data, and implemented by finding the PAPR within a predetermined frequency range of interest, but are not limited thereto. In yet another embodiment, the multiple parameters may be selected from the group consisting of correlation coefficients calculated from a predetermined spectral range of sensor data between different axes, but are not limited thereto.

[0066] In step 404, the method describes selecting a set of parameter values ​​from a plurality of parameter values ​​that have the maximum value measured by each sensor. In step 406, the method describes comparing this set of parameter values ​​with corresponding predefined thresholds. In step 408, the method describes determining a set of intermediate operating states of the rotating machine based on the comparison. In one embodiment, the intermediate operating states of the rotating machine can be determined using one or more sensors, using predefined threshold logic, or using a classifier developed using machine learning techniques. In step 410, the method describes determining the final operating state of the rotating machine based on the set of intermediate operating states. In one embodiment, step 410, i.e., determining the final operating state of the rotating machine based on the set of intermediate operating states, includes: determining the final operating state as the "on" state when all operating states in the set indicate that the rotating machine is in an "on" state, and determining the final operating state as the "off" state when any operating state in the set indicates that the rotating machine is in a "off" state.

[0067] In one embodiment, method 400 further includes performing data acquisition for monitoring the condition of the rotating machine when the final operating state is an on state; and preventing data acquisition and further processing for monitoring the condition of the rotating machine when the final operating state is a off state.

[0068] In this way, the monitoring device can mitigate the impact of detecting operational status. The device can accurately monitor the motor's operating status in a cost-effective manner. Furthermore, the disclosed technology allows processing only when the machine is on, rather than continuously calculating KPIs on the device regardless of its on / off state, which improves the battery life of various processing and monitoring devices. In addition, the technology is independent of setting thresholds for on / off detection, saving considerable resources.

[0069] Methods 300 and 400 described above can be described within the general context of computer-executable instructions. Generally, computer-executable instructions can include routines, programs, objects, components, data structures, procedures, modules, and functions that perform specific functionalities or implement specific abstract data types.

[0070] The order of the various operations described in the method is not intended to be construed as limiting, and any number of described method blocks can be combined in any order to implement the method. Furthermore, individual blocks may be removed from the method without departing from the spirit and scope of the subject matter described herein. Moreover, the method can be implemented in any suitable hardware, software, firmware, or a combination thereof.

[0071] It should be noted that, for reference Figures 1 to 4 The subject matter of some or all of the described embodiments may be related to the method, and will not be repeated for the sake of brevity.

[0072] The various operations described above can be performed by any suitable equipment capable of performing the corresponding functions. This equipment may include various hardware and / or software components (one or more) and / or modules (one or more), including but not limited to circuits, application-specific integrated circuits (ASICs), or processors. Generally, in cases where operations are illustrated in the figures, these operations can be performed by any suitable corresponding equipment plus functional components.

[0073] Furthermore, one or more computer-readable storage media may be used when implementing embodiments consistent with this disclosure. A computer-readable storage medium refers to any type of physical memory capable of storing processor-readable information or data. Therefore, a computer-readable storage medium may store instructions executable by one or more processors, including instructions for causing the processor to perform steps or stages consistent with the embodiments described herein. The term "computer-readable medium" should be understood to include tangible articles and exclude carrier waves and transient signals, i.e., non-transient signals. Examples include random access memory (RAM), read-only memory (ROM), volatile memory, non-volatile memory, hard disk drives, optical disc (CD) ROMs, digital video discs (DVDs), flash drives, magnetic disks, and any other known physical storage media.

[0074] Some aspects may include computer program products for performing the operations described herein. For example, such computer program products may include computer-readable media on which instructions are stored (and / or encoded) that can be executed by one or more processors to perform the operations described herein. In some aspects, computer program products may include packaging materials.

[0075] Various components, modules, or units are described in this disclosure to emphasize the functional aspects of a device configured to perform the disclosed techniques, but they do not necessarily need to be implemented by different hardware units. Rather, as described above, various units may be combined in hardware units with appropriate software and / or firmware, or provided by a collection of interoperable hardware units, including one or more processors as described above.

[0076] As used herein, the phrases “at least one” or “one or more” in the list of items refer to any combination of these items, including individual members. For example, “at least one of a, b, or c” is intended to cover a, b, c, ab, ac, bc, and abc. The terms “a,” “an,” and “the” mean “one or more” unless otherwise expressly stated. The terms “comprising,” “including,” “having,” and variations thereof, when used in the claims, are used in a non-exclusive sense and are not intended to exclude the presence of other elements or steps in the claimed structure or method unless otherwise expressly stated.

[0077] Finally, the language used in this specification has been chosen primarily for readability and instructional purposes, and may not be intended to depict or limit the subject matter of the invention. Therefore, the scope of the invention is intended not to be limited by this detailed description, but rather by any of the claims of the applications based thereon. Thus, the embodiments disclosed herein are intended to illustrate, rather than limit, the scope of the invention, which is set forth in the appended claims.

Claims

1. A method for determining the operating state of a rotating machine, the method comprising: Receive multiple parameter values, the multiple parameter values ​​corresponding to multiple parameters measured by one or more sensors placed near the rotating machine, wherein the multiple parameter values ​​belong to one or more measurement axes supported by the one or more sensors; Select a set of parameter values ​​that have the maximum value measured by each sensor from the plurality of parameter values; Compare the set of parameter values ​​with the corresponding predefined thresholds; Based on the comparison, a set of intermediate operating states of the rotating machine is determined; as well as The final operating state of the rotating machine is determined based on the set of intermediate operating states.

2. The method of claim 1, wherein the plurality of parameters are selected from a set of peak-to-average power ratios (PAPRs) measured from the spectrum of the sensor data, and are achieved by finding the PAPRs within a predetermined frequency range of interest.

3. The method of claim 1, wherein the plurality of parameters are selected from a set of correlation coefficients calculated from a predetermined spectral range of the sensor data between different axes.

4. The method of claim 1, wherein intermediate operating states of the rotating machine are determined separately using the one or more sensors with predetermined threshold logic or a classifier developed using machine learning techniques.

5. The method of claim 1, wherein determining the final operating state of the rotating machine based on the set of intermediate operating states comprises: When all operating states in the set of operating states indicate that the rotating machine is in the open state, the final operating state is determined to be the open state; as well as When any of the operating states in the set of operating states indicates the shutdown state of the rotating machine, the final operating state is determined to be the shutdown state.

6. The method of claim 5, further comprising: When the final operating state is the open state, data acquisition is performed to monitor the condition of the rotating machine; as well as When the final operating state is the off state, the data acquisition and further processing for monitoring the condition of the rotating machine are prevented.

7. A method for determining the operating state of a rotating machine, the method comprising: Multiple parameter values ​​associated with the operation of the rotating machine are determined based on measurement data obtained for the rotating machine; Generate a comparison matrix including multiple index values ​​corresponding to the multiple parameter values, wherein each index value indicates whether the corresponding parameter value is less than, equal to or greater than the corresponding threshold; A quality matrix is ​​generated by processing the multiple index values ​​of the comparison matrix; Identify the highest index value present in the quality matrix; as well as The highest index value of the quality matrix is ​​mapped to the corresponding index value of the comparison matrix to determine the operating state of the rotating machine.

8. The method of claim 7, wherein the comparison matrix is ​​generated in the following manner: The plurality of parameter values ​​are compared with the corresponding plurality of thresholds, wherein the plurality of parameter values ​​belong to one or more measurement axes supported by one or more sensors providing the measurement data; and The comparison matrix is ​​generated based on the comparison.

9. The method of claim 7, wherein the plurality of parameters includes one or more of the following: root mean square (RMS) magnetic flux, signal-to-noise ratio (SNR), harmonic energy ratio, velocity RMS, the ratio of peak magnetic flux to magnetic flux time-domain RMS, and the ratio of peak acceleration to velocity RMS.

10. The method of claim 7, wherein the comparison matrix is ​​M. N matrix, where M represents the number of the plurality of parameter values ​​and N represents the number of measurement axes corresponding to the plurality of parameter values.

11. The method of claim 7, wherein the measurement data obtained from the one or more sensors is associated with at least one of the magnetic field of the rotating machine and the acceleration of the rotating machine.

12. The method of claim 7, wherein generating the quality matrix by processing the plurality of index values ​​of the comparison matrix comprises: Using the comparison matrix Perform row-by-row and column-by-column comparisons between each index value in the comparison matrix and the subsequent index values ​​in the comparison matrix; When performing the row-by-row comparison in the comparison matrix, when the index value matches the subsequent index value, a first matrix is ​​generated by incrementing the index value of the comparison matrix by a first predefined value. as well as When performing the column-by-column comparison in the comparison matrix, when the index value matches the subsequent index value, a second matrix is ​​generated by incrementing the index value of the comparison matrix by a second predefined value; The third matrix is ​​generated by summing the first and second matrices. as well as The quality matrix is ​​generated by multiplying the multiple index values ​​of the third matrix with their corresponding weights.

13. The method of claim 7, wherein determining the operating state of the rotating machine comprises: When the index value of the comparison matrix mapped to the highest index value is equal to or greater than the threshold, the running state is determined to be in the on state; as well as When the index value of the comparison matrix mapped to the highest index value is less than the threshold, the running state is determined to be a closed state.

14. An apparatus for determining the operating state of a rotating machine, the apparatus comprising: Processing unit, the processing unit being configured to: Receive multiple parameter values, the multiple parameter values ​​corresponding to multiple parameters measured by one or more sensors placed near the rotating machine, wherein the multiple parameter values ​​belong to one or more measurement axes supported by the one or more sensors; Select a set of parameter values ​​that have the maximum value measured by each sensor from the plurality of parameter values; Compare the set of parameter values ​​with the corresponding predefined thresholds; Based on the comparison, a set of intermediate operating states of the rotating machine is determined; as well as The final operating state of the rotating machine is determined based on the set of intermediate operating states.

Images