System, device and method for estimating the remaining useful life of at least one bearing

Abstract

A system (100), apparatus (110) and method for estimating a remaining useful life of at least one bearing are provided. The method includes receiving a request from a source (115, 125, 130) to analyze defects in a bearing, determining a vibration spectrum of the bearing from received operational data, monitoring impacts of defects on the bearing over a period of time based on the determined vibration spectrum, determining a characteristic value for which impacts of defects on the bearing are above a threshold range from the vibration spectrum, determining an impact force during operation of the at least one bearing based on the determined characteristic value and one or more parameters obtained from a virtual bearing model, determining a remaining useful life of the bearing based on the determined impact force during the period of time, and generating a notification on an output device indicating the remaining useful life of the bearing.

Description

Technical Field

[0001] This invention relates to the field of bearing monitoring systems, and more particularly to estimating the remaining service life of at least one bearing. Background Technology

[0002] In industry, bearings are used in various machines to reduce friction between two rotating parts. These bearings also restrict the relative motion between rotating parts to the desired movement. However, bearings can fail unexpectedly due to factors such as poor lubrication and contamination within the bearing's structure. For example, lubrication within the bearing may fail due to excessively high temperatures during the bearing's operation. Contamination can occur due to impurities, particles, moisture, etc., entering the bearing's structure. These factors lead to failure modes in bearings such as corrosion, spalling, pitting, electrolytic corrosion, plastic deformation, and the like. As a result, the expected fatigue life of the bearing assembly decreases, eventually leading to failure. Therefore, bearing failure can cause unexpected downtime of machinery, resulting in production and financial losses. In safety-critical applications, bearing failure can also put human lives at risk.

[0003] Given the above, there is a need to estimate the remaining service life of the bearing. Summary of the Invention

[0004] Therefore, the object of the present invention is to provide a system, apparatus and method for estimating the remaining service life of at least one bearing.

[0005] The object of the present invention is achieved by a method for estimating the remaining service life of at least one bearing.

[0006] The method includes receiving a request to analyze defects in the at least one bearing. As used herein, the term "defect" refers to any structural deformation within the at least one bearing that causes abnormal operation of the bearing. The request includes operational data associated with the at least one bearing. In one embodiment, the operational data includes the real-time output of at least one sensing unit associated with the bearing. It must be understood that, as used herein, the term "sensing unit" includes both transducers and sensors. In addition to the above, the request may specify one or more bearing parameters.

[0007] Advantageously, this invention facilitates the estimation of the remaining service life of bearings of any size based on relevant operating data.

[0008] The method includes determining the vibration spectrum of the at least one bearing from the received operational data. Advantageously, the conversion of the operational data from the time domain to the frequency domain helps to envelop the signal and protects the signal from unwanted vibrations caused by sources from external physical factors. Furthermore, determining the remaining service life of the at least one bearing based on the vibration spectrum improves accuracy.

[0009] The method includes monitoring the impact of a defect on the at least one bearing over a time period based on a determined vibration spectrum. As used herein, the term "impact" refers to a deviation from normal bearing operation caused by the defect. In an embodiment, when monitoring the impact of the defect, the method includes monitoring for anomalies in the output of the at least one sensing unit.

[0010] Advantageously, the present invention facilitates real-time, continuous monitoring of impacts caused by defects in the bearing.

[0011] The method includes determining one or more characteristic values ​​from a vibration spectrum indicating that the impact on a defect on the bearing exceeds a threshold range. In an example, determining the one or more characteristic values ​​includes analyzing operational data associated with the at least one bearing.

[0012] The method involves determining the impact force during operation of the at least one bearing based on one or more determined characteristic values ​​and one or more parameters obtained from a virtual bearing model. As used herein, the term "impact force" refers to the contact force or maximum compressive force experienced by the ball as it enters the edge of a defect.

[0013] In an embodiment, determining the impact force during operation of the at least one bearing includes generating a virtual bearing model for a bearing group corresponding to the at least one bearing.

[0014] In an embodiment, generating a virtual bearing model includes determining a test operation profile based on test operation data associated with the bearing assembly. Further, the method includes simulating predetermined defects on a predefined bearing model, the predefined bearing model comprising datasets according to dynamic load rating standards and rated life standards associated with the bearing assembly. Further, the method includes generating a simulation operation profile in the frequency domain associated with the bearing assembly based on the simulation of the predetermined defects on the predefined bearing model. In a preferred embodiment, determining the impact force during operation of the at least one bearing includes determining the calibration impact force of the bearing assembly based on a correlation model obtained from the spectrum of simulated vibration signals and the generated simulation operation profile in the frequency domain associated with the bearing assembly.

[0015] In this embodiment, the virtual bearing model is generated based on one or more of simulation data, experimental data, and mathematical data associated with the bearing assembly.

[0016] In one embodiment, determining the impact force further includes using a machine learning model to optimize one or more parameters in the determined calibrated impact force of the bearing assembly.

[0017] In an embodiment, determining the impact force further includes determining the dynamic parameters of the at least one bearing based on one or more parameters determined for each of the bearings in the bearing assembly.

[0018] Advantageously, the present invention uses the impact force during this time period to obtain the remaining service life of the bearing.

[0019] The method includes determining the remaining service life of the at least one bearing based on impact forces and operational data during the time period. As used herein, the term "remaining service life" refers to the duration between the initiation of a detectable failure mode and a functional failure of the bearing. In a preferred embodiment, in determining the remaining service life, the method includes using a virtual model of the bearing to calculate dynamic parameters associated with the bearing based on impact forces. In one embodiment, the dynamic parameters are dynamic equivalent loads on the bearing.

[0020] Furthermore, the remaining service life model of the bearing is configured based on dynamic parameters. The remaining service life model is a dynamic model that correlates the dynamic parameters with the bearing's lifespan. Further, the remaining service life of the bearing is calculated based on the configured remaining service life model and operational data.

[0021] Advantageously, this invention facilitates the use of impact forces to determine dynamic parameters that affect bearing degradation.

[0022] The method includes generating a notification on an output device indicating the remaining service life of a bearing. In addition to the remaining service life, the notification may further include diagnostic information associated with the bearing. For example, the diagnostic information may indicate impact force curves, RUL curves, time-domain and frequency-domain rate curves, and indications of degradation conditions on the RUL curve.

[0023] The object of this invention is achieved by an apparatus for estimating the remaining service life of a bearing. The apparatus includes one or more processing units and a memory unit communicatively coupled to the one or more processing units. The memory unit includes a bearing management module stored in the form of machine-readable instructions executable by the one or more processing units. The bearing management module is configured to perform the method steps described above. The execution of the bearing management module can also be performed using a coprocessor such as a graphics processing unit (GPU), a field-programmable gate array (FPGA), or a neural processing / computing engine.

[0024] According to embodiments of the present invention, the device may be an edge computing device. As used herein, "edge computing" refers to a computing environment capable of operating on an edge device (e.g., connected at one end to a sensing unit in an industrial setup and at the other end to one or more remote servers such as computing servers or cloud computing servers), which may be a compact computing device with a small form factor and resource constraints in terms of computing power. A network of the edge computing device can also be used to implement the device. Such a network of edge computing devices is called a fog network.

[0025] In another embodiment, the device is a cloud computing system with a cloud-based platform configured to provide cloud services for analyzing defects in bearings. As used herein, "cloud computing" refers to a processing environment that includes configurable computational physical and logical resources (e.g., networks, servers, storage devices, applications, services, etc.) and data distributed over a network (e.g., the Internet). The cloud computing platform can be implemented as a service for analyzing defects in bearings. In other words, the cloud computing system provides on-demand network access to a shared pool of configurable computational physical and logical resources. This network may be, for example, a wired network, a wireless network, a communication network, or a network formed from any combination of these networks.

[0026] Additionally, the object of the present invention is achieved by a system for estimating the remaining service life of a bearing. This system includes one or more sources capable of providing operational data associated with a bearing and device communicatively coupled to the one or more sources as described above. As used herein, the term "source" refers to an electronic device configured to acquire operational data and transmit the operational data to the device. Non-limiting examples of sources include sensing units, controllers, and edge devices.

[0027] The object of the present invention is also achieved by storing a computer-readable medium thereon a program code segment of a computer program, which, when executed, can be loaded into and / or executed by a processor performing the methods described above. Attached Figure Description

[0028] The attributes, features, and advantages of the invention mentioned above, as well as the ways in which they are implemented, will become more apparent and understandable (clear) from the following description of embodiments of the invention in conjunction with the accompanying drawings. The illustrated embodiments are intended to illustrate, not limit, the invention.

[0029] Figure 1A The diagram illustrates a system for estimating the remaining service life of at least one bearing according to an embodiment of the present invention.

[0030] Figure 1B The illustration shows a block diagram of an apparatus for estimating the remaining service life of at least one bearing according to an embodiment of the present invention;

[0031] Figure 2A The diagram illustrates the structure of a ball bearing;

[0032] Figure 2B The diagram illustrates a defect in the outer ring of a ball bearing;

[0033] Figure 3 The illustration shows an experimental test setup for constructing a virtual model of a bearing according to an embodiment of the present invention;

[0034] Figure 4A This is a graphical user interface view showing an example time-rate curve of operational data obtained from a sensing unit according to an embodiment of the present invention;

[0035] Figure 4B This is a graphical user interface view illustrating the peak amplitude value when a signal passes through a bandpass filter, according to an embodiment of the present invention.

[0036] Figure 5 A flowchart illustrating a method for estimating the remaining service life of a bearing according to an embodiment of the present invention is provided.

[0037] Figure 6 This is an exemplary web-based interface according to an embodiment of the present invention, which enables a user to provide values ​​of one or more bearing parameters from a client device;

[0038] Figure 7 This is a graphical user interface view illustrating an example of the determined output according to an embodiment of the present invention;

[0039] Figure 8 This is a graphical user interface view illustrating an example of impact force and velocity curves according to an embodiment of the present invention;

[0040] Figure 9A This is a graphical user interface view illustrating an example of ball velocity, such as that obtained from operational data in the time domain, according to an embodiment of the present invention.

[0041] Figure 9B This is a graphical user interface view illustrating an example of a power spectrum in the frequency domain according to an embodiment of the present invention;

[0042] Figure 10 This is a graphical user interface view illustrating degradation during the remaining useful life, according to embodiments of the present disclosure. Detailed Implementation

[0043] Hereinafter, embodiments for carrying out the invention are described in detail. Various embodiments are described with reference to the accompanying drawings, in which the same reference numerals are consistently used to refer to the same elements. In the following description, numerous specific details are set forth for purposes of explanation in order to provide a thorough understanding of one or more embodiments. It will be apparent that such embodiments may be practiced without these specific details.

[0044] Figure 1A A block diagram of a system 100 for estimating the remaining service life of a bearing 105 according to an embodiment of the present invention is illustrated. For example, the bearing 105 may be part of rotating equipment such as an industrial motor (not shown). Non-limiting examples of bearings include deep groove ball bearings, cylindrical roller bearings, tapered roller bearings, thrust bearings, angular contact ball bearings, needle roller ball bearings, and the like. In this embodiment, the bearing 105 includes an inner ring, an outer ring, and a plurality of rolling elements disposed in a gap between the inner and outer rings. The bearing 105 further includes a cage positioned between the inner and outer rings to maintain a symmetrical radial clearance between the rolling elements. Reference will be made later in this disclosure. Figure 2A Example describing a bearing.

[0045] System 100 includes a device 110 communicatively coupled to one or more edge devices 115. The one or more edge devices 115 are connected to device 110 via a network 120 (e.g., a local area network (LAN), wide area network (WAN), WiFi, etc.). Each of the edge devices 115 is configured to receive sensor data from at least one sensing unit 125 associated with bearing 105. The at least one sensing unit 125 may include, for example, a vibration sensor, a velocity sensor, an acceleration sensor, and a force sensor. The sensor data corresponds to the output of the at least one sensing unit 125. For example, the output from the at least one sensing unit 125 may be in the form of vibration data, velocity data, acceleration data, or force data. In an embodiment, the sensor data is obtained through a data acquisition interface on the edge device 115. The edge device 115 provides the sensor data to device 110 in real time.

[0046] Additionally, the edge device 115 is also configured to provide the device 110 with one or more bearing parameters associated with the bearing 105. These one or more bearing parameters include, but are not limited to, standard bearing number, ball size, bearing static load, material density, angular rate, internal clearance, bearing diameter, number of rolling elements, rolling element radius, inner ring diameter, outer ring diameter, defect size, fatigue load limit, and type of lubricant used in the bearing 105. It must be understood that the standard bearing number indicates certain specifications provided by the manufacturer of the bearing 105, such as ball size, bearing static load, material density, internal clearance, bearing diameter, number of rolling elements, rolling element radius, inner ring diameter, outer ring diameter, fatigue load limit, bearing width, and the like. Therefore, in embodiments, a standard bearing number associated with the bearing 105 can be provided instead of the bearing parameters described above.

[0047] The one or more bearing parameters may be stored in the memory of edge device 115 or may be input to edge device 115 by an operator. For example, edge device 115 may be communicatively coupled to client device 130. Non-limiting examples of client devices include personal computers, workstations, personal digital assistants, and human-machine interfaces. Client device 130 may enable a user to input the values ​​of the one or more bearing parameters via a web-based interface. Upon receiving the one or more bearing parameters from the user, edge device 115 transmits a request to device 110 to analyze defects in bearing 105. Defects arise due to the initiation of failure modes in bearing 105. Non-limiting examples of failure modes include spalling, pitting, plastic deformation, wear, electrical erosion, and corrosion, typically on the outer ring of bearing 105. Defects may arise due to the presence of contaminants or due to the nature of the lubricant used within bearing 105. The request includes the one or more bearing parameters along with sensor data.

[0048] In this embodiment, device 110 is deployed in a cloud computing environment. As used herein, "cloud computing environment" refers to a processing environment that includes configurable computational physical and logical resources (e.g., networks, servers, storage devices, applications, services, etc.) and data distributed on network 120 (e.g., the Internet). The cloud computing environment provides on-demand network access to a shared pool of configurable computational physical and logical resources. Device 110 may include a module for estimating the remaining service life of a given bearing based on corresponding sensor data and the one or more bearing parameters. Additionally, device 110 may include a network interface for communicating with the one or more edge devices 115 via network 120.

[0049] like Figure 1BAs shown, device 110 includes a processing unit 135, a memory unit 140, a storage unit 145, a communication unit 150, a network interface 155, and a standard interface or bus 160. Device 110 may be a computer, a workstation, a virtual machine running on host hardware, a microcontroller, or an integrated circuit. Alternatively, device 110 may be a real or virtual computer group (the technical term for a real computer group is "cluster," and the technical term for a virtual computer group is "cloud").

[0050] As used herein, the term "processing unit" 135 refers to any type of computing circuitry, such as, but not limited to, a microprocessor, microcontroller, complex instruction set computing microprocessor, reduced instruction set computing microprocessor, very long instruction word microprocessor, explicit parallel instruction computing microprocessor, graphics processor, digital signal processor, or any other type of processing circuitry. Processing unit 135 may also include embedded controllers, such as general-purpose or programmable logic devices or arrays, application-specific integrated circuits (ASICs), single-chip computers, and the like. Generally, processing unit 135 may include hardware and software elements. Processing unit 135 can be configured for multithreading, meaning that processing unit 135 can simultaneously host different computational processes, execute any one in parallel, or switch between active and passive computational processes.

[0051] Memory unit 140 can be volatile or non-volatile memory. Memory unit 140 can be coupled for communication with processing unit 135. Processing unit 135 can execute instructions and / or code stored in memory unit 140. A wide variety of computer-readable storage media can be stored in and accessed from memory unit 140. Memory unit 140 can include any suitable elements for storing data and machine-readable instructions, such as read-only memory, random access memory, erasable programmable read-only memory, electrically erasable programmable read-only memory, hard disk drive, compact disk, digital video disk, magnetic disk, tape cartridge, memory card, and removable media drives such as these.

[0052] Memory unit 140 includes a bearing management module 165, which is in the form of machine-readable instructions on any of the storage media mentioned above, and can communicate with and be executed by processing unit 135. Bearing management module 165 includes a preprocessing module 170, an impact monitoring module 175, an impact force calculation module 180, a life estimation module 185, and a notification module 190. Preprocessing module 170 is configured to receive a request to analyze defects in bearing 105. The request includes operational data associated with bearing 105 and the one or more bearing parameters. Preprocessing module 170 is configured to determine the vibration spectrum of the at least one bearing from the received operational data. Impact monitoring module 175 is configured to monitor impacts on defects in bearing 105 over a time period. Impact monitoring module 175 is further configured to determine one or more frequencies from the vibration spectrum that indicate impacts on defects in its bearings are above a threshold range. Impact force calculation module 180 is configured to determine the impact force during operation of the at least one bearing based on the determined one or more frequencies and one or more parameters obtained from a virtual bearing model. The life estimation module 185 is configured to determine the remaining service life of the bearing 105 based on impact force and operational data during the said time period. The notification module 190 is configured to generate a notification on an output device indicating the remaining service life of the bearing 105. In this embodiment, the output device may be a client device 130.

[0053] Storage unit 145 includes non-volatile memory that stores default bearing parameters associated with a standard bearing number. Storage unit 145 includes a database 195 and one or more lookup tables, the database 195 including default values ​​for the bearing parameters, and the one or more lookup tables including predetermined values ​​for factors that vary with the operating conditions of bearing 105. Bus 160 serves as an interconnect between processing unit 135, memory unit 140, storage units, and network interface 155. Communication unit 150 enables device 110 to receive requests from one or more edge devices 115. The communication module can support different standard communication protocols, such as Transmission Control Protocol / Internet Protocol (TCP / IP), Profinet, Profibus, and Internet Protocol Version 1 (IPv).

[0054] Those skilled in the art will understand that Figure 1A and 1BThe hardware depicted may vary for different implementations. For example, optical disc drives and other peripherals such as LAN / WAN / wireless (e.g., Wi-Fi) adapters, graphics adapters, disk controllers, input / output (I / O) adapters, and network connectivity devices may also be used additionally or in place of the depicted hardware. The examples depicted are provided for illustrative purposes only and are not intended to imply any architectural limitations with respect to this disclosure.

[0055] Figure 2A The diagram illustrates the structure of a ball bearing 200. The ball bearing 200 includes an outer ring 210 with a diameter of D, and each bearing has a radius of r. 球 The device comprises a plurality of balls 215, a cage 220, and an inner ring 225 with a diameter d. The plurality of balls 215 are disposed in the gap between the outer ring 210 and the inner ring 225. The cage 220 maintains a symmetrical radial spacing between the balls 215. Figure 2B The illustration shows the size d of the defect on the wall of the outer ring 210 in contact with the ball 210. 缺陷 The defect is a pit in the housing caused by pitting corrosion. In this example, the defect is defined as a depression in the housing due to pitting corrosion. The defect size can be defined as the distance traveled by the ball of the ball bearing 200 between entering and leaving the defect. As shown, the defect is at an angle θ to the center of ball 215A among the plurality of balls 215. 中心 The angular rate of the shaft on which the ball bearing 200 is mounted is indicated as ω.

[0056] Figure 3 An experimental test setup 300 for constructing a virtual model of a bearing according to an embodiment of the present invention is illustrated. In this embodiment, the virtual model corresponds to a ball bearing. Those skilled in the art will understand that virtual models can be constructed for other types of bearings in a similar manner.

[0057] Virtual models can be based on one or more of the following: physical models, computer-aided design (CAD) models, computer-aided engineering (CAE) models, one-dimensional (ID) models, two-dimensional (2D) models, three-dimensional (3D) models, finite element (FE) models, descriptive models, meta-models, stochastic models, parametric models, reduced-order models, statistical models, heuristic models, predictive models, aging models, machine learning models, artificial intelligence models, deep learning models, system models, surrogate models, and the like.

[0058] In this embodiment, the virtual model is constructed based on test operation data, such as simulation data, experimental data, and mathematical data associated with multiple bearings under various operating conditions. These operating conditions can be generated based on a Design of Experiments (DOE) for varying values ​​of load, angular rate, and defect size. Here, the term "load" refers to the static load on the bearing. For example, the defect size can be selected as one of 0.1 mm, 0.2 mm, 1 mm, 2 mm, 3 mm, 4 mm, and 5 mm. The load can be one of 400 N and 500 N. The angular rate can be one of 1000 rad / s, 1200 rad / s, 1400 rad / s, and 1600 rad / s. In this embodiment, simulation data, experimental data, and mathematical data associated with a bearing assembly comprising three standard ball bearings can be used. For example, the first bearing of the three bearings can have a standard bearing number 6205, the second bearing can have a standard bearing number 6213, and the third bearing can have a standard bearing number 6319.

[0059] Experimental setup 300 includes a bearing 305, at least one force sensor 310 attached to the bearing 305, and at least one vibration sensor 315. Similar to device 110, the force sensor 310 and vibration sensor 315 are communicatively coupled to device 320. In an embodiment, device 320 may include a data acquisition interface for receiving signals from the force sensor 310 and vibration sensor 315. The bearing 305 is mounted on a rotating shaft. In this example, the rotating shaft is part of a rotating apparatus. Further, one or more defects are artificially introduced into the outer race of the bearing 305. Each of the defects is associated with a known defect size as specified in the operating conditions. The force sensor 310 is configured to measure the impact force generated by a bearing ball passing through the defect. As used herein, the term "impact force" refers to the contact force experienced by the ball as it enters the edge of the defect. In this example, the force sensor 310 is a triaxial piezoelectric crystal. The vibration sensor 315 is configured to measure the vibration or acceleration value generated by the ball passing through the defect. In this example, the vibration sensor 315 is an accelerometer. Further, test or experimental data is recorded. The test operation data includes the impact force measured by force sensor 310 and the corresponding acceleration value measured by vibration sensor 315 for each of the operating conditions. Similarly, experimental data corresponding to each of the three bearings are recorded.

[0060] The simulation data is generated by simulating the bearing's behavior using a multiphysics simulation model. The operating conditions can be provided as input to the multiphysics simulation model within the simulation environment. For example, the simulation environment can be provided by a computer-aided simulation tool on device 320. The simulation model includes finite element models of the outer ring, cage, multiple rolling elements, inner ring, and guard associated with the bearing. In this example, the rolling elements are balls. Further, the simulation model corresponding to each of the standard ball bearings is configured to model defects in the outer ring of the specified defect size in the operating conditions. For example, the defects can be associated with one or a combination of spalling, pitting, plastic deformation, wear, electrical erosion, or corrosion.

[0061] Based on the configured simulation model, simulation instances are generated. These simulation instances are executed in the simulation environment to generate simulation data for each bearing corresponding to the simulation data, which is generated under the same operating conditions used to generate the test operation data. The simulation data includes the value of the simulated maximum impact force corresponding to each of the operating conditions. Similarly, simulation data is generated for each of the three bearings.

[0062] Apparatus 320 further constructs a virtual model of the bearing based on simulation data, experimental data, and mathematical data. In one embodiment, the virtual model is a surrogate model. The virtual model is further validated based on test data generated using experimental setup 300. The test data includes a set of operating conditions for the bearing, including known values ​​of defect size, angular rate, and load. The output of the force sensor is compared with the output of the virtual model to detect errors associated with the virtual model. Furthermore, the parameters of the virtual model are tuned to minimize these errors. The tuned virtual model can be used to predict the maximum impact force associated with any bearing for any given set of operating conditions.

[0063] Figure 5 A flowchart of a method 500 for estimating the remaining service life of a bearing according to an embodiment of the present invention is depicted.

[0064] At step 505, processing unit 135 receives a request to analyze defects in the bearing. This request includes one or more bearing parameters associated with the bearing, received from a client device similar to client device 130, along with sensor data received from at least one sensing unit attached to the bearing. The sensor data may include the output of the at least one sensing unit associated with the bearing. Both the client device and the at least one sensing unit are communicatively coupled to an edge device similar to edge device 115. In this embodiment, the at least one sensing unit includes an accelerometer mounted on a bearing housing associated with the bearing. The output of the at least one sensing unit is an acceleration signal in the time domain.

[0065] In implementation, users can initiate a request by providing one or more bearing parameters through a web-based interface provided on the client device. These parameters may include, for example, ball radius, bearing static load, material density, angular rate, defect size, and internal clearance. Figure 6 An exemplary web-based interface 600 according to an embodiment of the present invention is illustrated, which enables a user to provide values ​​of the one or more bearing parameters from a client device.

[0066] In one embodiment, one or more of the bearing parameters are specified using a standard bearing number based on an international standard such as the ISO size series. For example, if the standard bearing number is 6213, the bearing size in mm is 65 × 120 × 23, where 65 mm is the inner ring diameter, 120 mm is the outer ring diameter, and 23 mm is the bearing width. A web-based interface can provide a drop-down menu for selecting a bearing number from multiple bearing numbers. In this example, the bearing number can be selected as 6319.

[0067] Based on the bearing number, dimensions such as ball radius and bearing diameter can be automatically populated on the web-based interface. Similarly, if the bearing number is not displayed in a drop-down menu, the web-based interface can also provide the user with the option to manually input bearing parameters. Furthermore, the user can confirm the values ​​of one or more bearing parameters by pressing the "Submit" button on the web-based interface to initiate a request. In a preferred embodiment, the sensor data corresponds to the real-time operating conditions of the bearing.

[0068] At step 510, the vibration spectrum of the at least one bearing is determined from the received operational data. The operational data received from the sensing unit 125 is in the time domain. In a preferred embodiment, the ball velocity is obtained from the vibration sensor 315 and represented in the time domain. Figure 4A This is a graphical user interface view 400A illustrating an example time-rate curve of operating data obtained from sensing unit 125 according to an embodiment of the present invention. The time-domain vibration signal is converted to the frequency domain using signal processing techniques such as Fourier transform, Fast Fourier transform (FFT), Continuous wavelet transform (CWT), Discrete wavelet transform (DWT), and the like.

[0069] In the example, the continuous wavelet transform is given by the following equation:

[0070]

[0071] Specifically, the Hilbert transform is used to convert the time-domain vibration signal into the frequency domain.

[0072] In the example, the Hilbert transform of the signal u(t) is given by the following equation:

[0073]

[0074] The Hilbert transform helps to enclose the signal and protects it from unwanted vibrations caused by settings or sources from external physical factors.

[0075] At step 515, the impact of a defect on the bearing is monitored over a time period. The impact of the defect is monitored based on anomalies present within the sensor data. These anomalies can be indicated by characteristics of the signal generated by the at least one sensing unit. These characteristics may include, but are not limited to, amplitude, frequency, harmonics, spectral energy, RMS rate, presence of impact pulses or transients, repetitive pulses, and the like. In this embodiment, the sensor data includes a vibration signal in the time domain that has been converted to the frequency domain. Using kurtosis analysis, impacts can be identified from the vibration signal. More specifically, the kurtosis of the envelope signal at different time intervals is performed to find the frequency band with the highest noise signal. In this example, the following mathematical relationship is used to perform the kurtosis of the signal:

[0076]

[0077] After kurtosis analysis, a bandpass filter was applied to the signal to remove noise. The resulting signal is... Figure 4B The Chinese side indicated that... Figure 4B This is a graphical user interface view 400B illustrating the peak amplitude value when a signal passes through a bandpass filter, according to an embodiment of the present invention.

[0078] In the example, the amplitude of the filtered signal can indicate the periodic impact of the defect. Upon identifying the presence of such an impact, step 520 is executed.

[0079] At step 520, one or more characteristic values ​​are determined from the vibration spectrum that indicate an impact exceeding a threshold range for a defect on the bearing. These one or more characteristic values ​​indicate the impact caused by the defect within a defined time period. More specifically, these one or more characteristic values ​​indicate values ​​indicating a high impact caused by the defect for the rolling elements. In a preferred embodiment, the characteristic value may be the peak amplitude of a rate signal, the peak amplitude of an acceleration signal, or the peak amplitude of a displacement signal, as obtained from operational data. The threshold range may be predefined by the operator or may be based on specifications provided by the bearing manufacturer. For example, the threshold may be defined as 2 mm / s. Based on the results of envelope analysis, if the amplitude of the rate signal exceeds the threshold, a time period in which the amplitude of the envelope is greater than 2 mm / s is identified.

[0080] At step 525, the impact force during operation of the at least one bearing is determined based on one or more determined characteristic values ​​and one or more parameters obtained from the virtual bearing model. As used herein, the term "impact force" refers to the contact force or maximum compressive force experienced by the ball as it enters the edge of the defect. The impact force of the at least one bearing against the requested defect is determined from the one or more determined characteristic values. The impact force relationship includes dynamic parameters that affect the remaining service life of the bearing. The dynamic parameters are determined based on one or more determined parameters obtained for each bearing in the bearing set (i.e., three standard bearings).

[0081] In one embodiment, determining the impact force includes generating a virtual bearing model for a bearing assembly corresponding to the at least one bearing. The bearing assembly includes three standard bearings as mentioned above. In one embodiment, the virtual bearing model is a hybrid model generated based on one or more of simulation data, experimental data, and mathematical data associated with the bearing assembly. In one embodiment, generating the virtual bearing model includes determining a test operation profile based on test operation data associated with the bearing assembly. Further, the method includes simulating a predetermined defect on a predefined bearing model, which includes datasets according to dynamic load rating standards and rated life standards associated with the bearing assembly. Further, the method includes generating a simulation operation profile in the frequency domain associated with the bearing assembly based on the simulation of the predetermined defect on the predefined bearing model. The simulation operation profile is generated by transforming the simulation data to the frequency domain. The simulation operation profile in the spectrum is used for the determined simulated impact force of the bearing assembly. Subsequently, a calibrated impact force is determined from the simulated impact force.

[0082] In a preferred embodiment, determining the impact force includes determining the calibrated impact force of the bearing assembly based on a correlation model obtained from the velocity spectrum of the vibration signal and a generated simulation operation profile in the frequency domain associated with the bearing assembly. Furthermore, the correlation model is generated from the vibration signal and the velocity spectrum of the force on the bearing. The force is calculated from the mathematical relationships based on simulation data and various regression models as follows:

[0083]

[0084] in,

[0085] F is the force released by the ball at the edge of the defect.

[0086] X is the maximum displacement of the ball bearing interacting with the defect edge.

[0087] P is the peak amplitude of the spectrum obtained from the vibration signal of the bearing.

[0088] n, a, b, and c are equation constants optimized using simulation data obtained from a virtual bearing model.

[0089] In this example, the correlation model is a regression model that maps peak values ​​obtained from the spectrum of the simulated vibration signal to forces calculated from mathematical equations. More specifically, code is generated in an integrated development environment (IDE) using any known programming language. In this example, the code is developed in Python. The Python code is configured to construct an optimal curve that correlates the peak values ​​of the vibration spectrum with the forces. Further, a mathematical relationship is generated that associates the forces with the peak values. Further still, based on the output of the correlation model and the generated simulation operation profile, simulated impact forces are determined for the bearing assembly. More specifically, simulated impact forces are predicted for the bearing assembly by extracting peak values ​​from the simulation operation profile. Further still, each peak value obtained from the experimental bearing setup is thus fitted to the mathematical relationship generated from the correlation model to obtain a prediction of the corresponding force during the test operation of the bearing assembly.

[0090] Once the simulated impact force is determined, we further obtain the calibration impact force through impact force analysis. In an embodiment, determining the impact force further includes using a machine learning model to optimize one or more parameters in the determined calibration impact force of the bearing assembly. In the calibration impact force equation, Hertzian contact theory is used as a fundamental constant in the equation. Thus, the maximum compressive or impact force of the ball interacting with a defect in the bearing race is obtained using Newtonian mechanics. This force can be calculated using the given mathematical relation (4):

[0091]

[0092] in,

[0093] F is the force released by the ball at the edge of the defect.

[0094] X is the maximum displacement of the ball bearing interacting with the defect edge.

[0095] P is the peak amplitude of the spectrum obtained from the vibration signal of the bearing.

[0096] n, a, b, and c are equation constants optimized using simulation data obtained from a virtual bearing model.

[0097] It should be noted that, apart from the fundamental constants In addition, we also use other constants (n, a, b, c) along with powers of the amplitude peak values ​​obtained from the spectrum of the vibration signal.

[0098] The mathematical data used to calculate the maximum impact force or maximum compression in a ball bearing is based on a mathematical model of the bearing. This mathematical model has the following form:

[0099]

[0100] It can be rearranged as follows:

[0101]

[0102] Among them, X imax This is the maximum deflection of the ball, measured in millimeters.

[0103]

[0104]

[0105] Where v is Poisson's ratio associated with the bearing material, E is Young's modulus associated with the material, and E eq It is the equivalent stiffness of the material. For example, if the bearing is made of EN31 steel, then Poisson's ratio is 0.3 and Young's modulus is 210 GPa.

[0106] r eq =0.5098*r 球 (9)

[0107] Where r 球 It is the radius of the sphere

[0108]

[0109]

[0110]

[0111] Where, r 轴承 The radius of the bearing is given by the following formula:

[0112] r 轴承 =d m +Internal clearance / 2 (13)

[0113]

[0114] Where ω is the angular velocity, which is the angular frequency of the ball as it rotates around the edge of the defect.

[0115] In the equations above, parameters p1 and p2 are tuned based on bearing parameters. In an embodiment, a trained machine learning model is used to tune the parameters. The trained machine learning model is an evolutionary algorithm. Similarly, parameters p1 and p2 are obtained for three bearings. In an embodiment, determining the impact force further includes determining the dynamic parameters of the at least one bearing based on the one or more parameters determined for each bearing in the bearing group. The dynamic parameters are calculated for the at least one bearing for its real-time analysis to address the defect. In the example, the ball radius is used as a normalized scale in the bearing. That is, the parameter is correlated as a linear function of the ball diameter. Further, this relationship is used to calculate the bearing parameters for any bearing of arbitrary shape. It will be appreciated that this helps us calculate the required bearing parameters for any bearing of arbitrary shape for its predicted remaining service life.

[0116] Furthermore, the impact force F on the ball originates from x according to the following equation (4). imax calculate:

[0117]

[0118] Here, F represents the mathematically calculated maximum impact force on the ball. Therefore, the maximum impact force is calculated for the bearing whose remaining service life is to be calculated.

[0119] At step 530, the remaining service life of the bearing is determined based on the determined impact force and operating data, which are based on one or more determined frequencies. In one example, the remaining service life can be expressed as the number of revolutions before failure. In another example, the remaining service life is expressed as the number of operating hours at a constant speed before failure. In a preferred embodiment, the remaining service life model of the bearing is configured based on the following rated service life model:

[0120]

[0121] Among them, a iso The lifetime modification factor is based on the system approach used for lifetime calculation and is given by the following formula:

[0122]

[0123] Where a1 is the reliability lifetime modification factor, and C u The fatigue load limit is expressed in Newtons, e c It is a contaminant specific to defect size, P a C is the dynamic equivalent reference axial load measured in Newtons. a It is the basic dynamic equivalent axial load rating, and K is the viscosity ratio.

[0124] Therefore, the remaining service life is the time required to power bearing P. a The function of the dynamic equivalent load on is as follows:

[0125]

[0126] Here, the dynamic parameter used to configure the rated life model is the dynamic equivalent radial load.

[0127] The reliability life modification factor is a predefined value specified in ISO 281:2007 for a given reliability value. For example, if the reliability can be considered 90%, then a1 is set to 1. The reliability value is defaulted to 90%. In embodiments of this disclosure, the reliability value can be modified by an operator via a client device. Based on the reliability value, the reliability life modification factor can be further obtained from a first lookup table stored in database 195. The fatigue load limit and dynamic equivalent radial load rating are obtained from the one or more bearing parameters associated with the bearing.

[0128] The contamination factor is determined based on defect size. This is because defects in the bearing cause small, discrete particles of material to be removed from the bearing structure. These discrete particles increase the concentration of contaminants inside the bearing. The concentration of contaminants increases further with increasing defect size. Defect size is provided as input to a trained classification model that categorizes defect size into one of several severity levels. For example, these severity levels may correspond to “normal cleanliness,” “slight to typical contamination,” “severe contamination,” and “very severe contamination.” Based on defect size, the trained classification model outputs a severity level. The determined severity level is then further used to select an appropriate contamination factor from a second lookup table stored in database 195. The second lookup table may include values ​​for the contamination factor corresponding to each severity level. Those skilled in the art will understand that the classification model can be trained to classify defect sizes into any number of severity levels.

[0129] The viscosity ratio indicates the lubrication condition of the bearing during operation. The viscosity ratio is calculated as the ratio of the lubricant's operating viscosity to its rated viscosity. The operating viscosity is calculated based on the lubricant's viscosity grade and operating temperature. The oil's viscosity grade can be obtained from a third lookup table that includes viscosity grades corresponding to different types of lubricants. In one embodiment, the bearing's operating temperature can be obtained from a temperature sensor associated with the bearing. In another embodiment, a virtual model of the bearing can be used to determine the bearing's thermal profile based on sensor data. The rated viscosity is obtained from a fourth lookup table based on the bearing's dimensions and angular rate.

[0130] The equation (17) for the rated life is as follows:

[0131]

[0132] Here, the dynamic equivalent radial load P is the same as the impact force calculated by the virtual model based on sensor data. Therefore, the remaining service life is a function of the determined impact force.

[0133] Therefore, the remaining useful life model is configured as follows:

[0134]

[0135] Based on equation (18), the remaining service life (RUL) of the bearing is calculated.

[0136] At step 535, a notification indicating the remaining service life of the bearing is generated on the output device. This output may be a notification that indicates the remaining service life of the bearing as a dynamically changing parameter based on real-time sensor data. For example, the notification may include the message "The remaining service life of bearing 6319 is 56 hours." Furthermore, the output may also include, for example... Figure 7 The values ​​shown are the peak amplitude, force, and remaining service life. Figure 7 This is a GUI view 700 that displays the peak amplitude values ​​of operating data received from the at least one bearing, the force applied to the ball due to defects, and the remaining service life of the bearing in hours. The output may also include, for example... Figure 8 The impact force curve shown is shown. Figure 8 This is a graphical user interface view 800 illustrating an example of impact force and velocity curves according to an embodiment of the present invention. The GUI view 800 depicts the relationship between impact force and ball velocity on the bearing for various defect sizes. Furthermore, the output may also include operational data as represented in the time and frequency domains. Figure 9A This is a graphical user interface view 900A illustrating an example of ball velocity obtained from operational data in the time domain, according to an embodiment of the present invention. Figure 9B This is a graphical user interface view 900B illustrating an example of a power spectrum in the frequency domain according to an embodiment of the present invention. Furthermore, the output may also include, for example... Figure 10 The RUL value is further indicated on the RUL curve shown. Figure 10 This is a GUI view 1000 illustrating the degradation (shown as predicted life in hours) in the remaining useful life according to an embodiment of this disclosure. As can be seen from the curves, the RUL curve begins with a potential failure in the at least one bearing and propagates all the way to a functional failure based on vibration spectrum analysis, such as an increase in rate.

[0137] This invention facilitates the accurate calculation of the remaining service life of a bearing based on the impact force calculated from the vibration spectrum of a real-time signal from a sensing unit 315 associated with the at least one bearing. The invention continuously monitors real-time operating data obtained from the bearing, converts it to the frequency domain, and accurately determines the remaining service life of the bearing based on the relationship between the impact force and the spectral signal determined in real-time from the bearing's operating data.

[0138] This invention is not limited to a specific computer system platform, processing unit, operating system, or network. One or more aspects of this invention can be distributed across one or more computer systems, such as servers configured to provide one or more services to one or more client computers or to perform a complete task in a distributed system. For example, according to various embodiments, one or more aspects of this invention can be implemented on a client-server system comprising components distributed across one or more server systems performing multiple functions. These components include, for example, executable, intermediate, or interpreted code that communicates over a network using communication protocols. This invention is not limited to being executable on any particular system or group of systems, nor is it limited to any particular distributed architecture, network, or communication protocol.

[0139] While the invention has been described and illustrated in detail with the aid of preferred embodiments, it is not limited to the disclosed examples. Those skilled in the art can derive other variations without departing from the scope of the claimed invention.

Claims

1. A computer-implemented method for estimating the remaining service life of at least one bearing (105), the method comprising: The processing unit (135) receives a request from the sources (115, 125, 130) to analyze defects in the bearing, wherein the request includes operational data associated with the bearing. The vibration spectrum of the at least one bearing is determined from the received operational data; The impact of defects on at least one bearing over a time period is monitored based on the determined spectrum. Determine one or more characteristic values ​​from the vibration spectrum that indicate an impact exceeding a threshold range against a defect on the bearing. The impact force during operation of the at least one bearing is determined based on one or more characteristic values ​​and one or more parameters obtained from the virtual bearing model. The remaining service life of the bearing is determined based on the impact force determined during the time period. as well as Generate a notification on the output device (130) indicating the remaining service life of the bearing. The impact forces determined during the operation of the at least one bearing (105) include: The calibration impact force of the bearing assembly is determined based on the correlation model obtained from the vibration spectrum of the simulated vibration signal and the generated simulation operation profile in the frequency domain associated with the bearing assembly.

2. The method of claim 1, wherein the operating data includes the output of at least one sensing unit associated with the bearing in real time.

3. The method according to any one of claims 1 or 2, wherein monitoring the impact of a defect on the bearing (105) over a time period includes monitoring for anomalies in the output of the at least one sensing unit (125).

4. The method of claim 1, wherein determining the impact force during operation of the at least one bearing (105) based on one or more determined characteristic values ​​and one or more parameters obtained from the virtual bearing model comprises generating a virtual bearing model for a bearing group corresponding to the at least one bearing.

5. The method according to any one of claims 1 or 4, wherein the virtual bearing model is generated based on one or more of simulation data, experimental data, and mathematical data associated with the bearing assembly.

6. The method of claim 4, wherein generating the virtual bearing model comprises: The test operation profile is determined based on the test operation data associated with the bearing assembly; Predetermined defects are simulated on a predefined bearing model, which includes datasets based on dynamic load ratings and rated life standards associated with the bearing assembly; and A simulation profile in the frequency domain associated with the bearing assembly is generated based on the simulation of predetermined defects on a predefined bearing model.

7. The method of claim 1, wherein determining the impact force during operation of the at least one bearing (105) further comprises: Machine learning models are used to optimize one or more parameters in the determined calibrated impact force of the bearing assembly.

8. The method according to any one of claims 1 or 7, wherein determining the impact force during operation of the at least one bearing (105) further comprises: The parameters of the at least one bearing are determined based on one or more parameters for each bearing in the bearing assembly.

9. The method according to any one of claims 1 or 2, wherein determining the remaining service life of the at least one bearing based on the determined impact force during the time period comprises: The remaining service life model of the at least one bearing is configured based on the determined parameters and contamination and / or lubrication effects; as well as The remaining service life of the at least one bearing is calculated based on the configured remaining service life model and operating data.

10. An apparatus (110) for estimating the remaining service life of at least one bearing, the apparatus (110) comprising: One or more processing units (135); as well as A memory unit (140) communicatively coupled to the one or more processing units (135), wherein the memory unit (140) includes a bearing management module (165) stored in the form of machine-readable instructions executable by the one or more processing units (135), wherein the bearing management module (165) is configured to perform method steps according to any one of claims 1 to 9.

11. A system (100) for estimating the remaining service life of a bearing, the system (100) comprising: One or more sources (115, 125, 130) are configured to provide operating data associated with the bearing; as well as The device (110) of claim 10 is communicatively coupled to one or more sources (115, 125, 130), wherein the device (110) is configured to estimate the remaining service life of a bearing based on operating data according to any one of method claims 1 to 9.

12. A computer program product wherein machine-readable instructions are stored, which, when executed by one or more processing units (135), cause the processing units (135) to perform the method according to any one of claims 1 to 9.

13. A computer-readable storage medium including instructions that, when executed by a data processing system, cause the data processing system to perform the method according to any one of claims 1 to 9.

Images