Scan pattern probability calculation for speed and defect identification

Abstract

A method and system for performing speed and defect identification of components such as bearings are provided. The method can be implemented by a computer such that the computer receives condition monitoring data from one or more sensors. The computer scans a pattern along a speed range for the condition monitoring data and multiplies each pattern component of the pattern by a matching ambient frequency spectrum component. The computer then adds the pattern components together to produce one or more results.

Description

Technical Field

[0001] This invention relates to a probability calculation method for a scanned pattern used for speed and defect identification. Background Technology

[0002] A train can have many railcars, each with multiple axles and corresponding axle boxes. Each axle box can house bearings from the same or different manufacturers. Over time, bearings develop defects due to various reasons (e.g., contamination, surface defects, lubrication problems, etc.), which can be detected in the bearing's vibration harmonics. The area of ​​collecting and monitoring these vibration harmonics, and addressing the defects detected in them, is called condition monitoring.

[0003] Furthermore, regardless of whether traditional condition monitoring applications are online or offline, installing, utilizing, and maintaining shaft speed sensors that support the collection and monitoring of bearing vibration harmonics can be problematic and / or expensive. For example, traditional condition monitoring applications require knowledge of the shaft speed within a few percent of the tolerance to identify vibration frequency components / symptoms associated with bearing defects within the bearing vibration harmonics. Even with approximate shaft speed knowledge, traditional condition monitoring applications are redundant or unreliable, and these applications cannot detect bearing defects.

[0004] In traditional condition monitoring applications, managing parameters that may affect axle speed calculations (such as the wheel diameter of each axle box) and updating the database in a timely manner can be costly (or time-consuming) relative to man-hours, and is also prone to errors. Summary of the Invention

[0005] According to one or more embodiments, a method is provided herein. The method can be implemented by a computer, which receives condition monitoring data from one or more sensors. The computer scans a pattern along a velocity range against the condition monitoring data and multiplies each pattern component of the pattern by a matching direct environmental spectral component or a matching interpolated environmental spectral component. The interpolated environmental spectral component can be determined by performing a linear or polynomial analysis that matches the pattern components to the corresponding environmental spectral components. The computer then adds the pattern components together using one or more methods to produce one or more results.

[0006] According to one or more implementation methods, the above methods can be implemented as systems, devices and / or computer program products.

[0007] Further features and advantages are achieved through the technology disclosed herein. Other embodiments and aspects of this disclosure are described in detail herein. For a better understanding of the advantages and features of this disclosure, please refer to the specification and accompanying drawings. Attached Figure Description

[0008] This subject matter is specifically pointed out and explicitly claimed in the claims. The foregoing and other features and advantages of the embodiments herein will become apparent from the following detailed description taken in conjunction with the accompanying drawings:

[0009] Figure 1 A system according to one or more embodiments is described;

[0010] Figure 2 A processing flow according to one or more embodiments is described;

[0011] Figure 3 A graph depicting one or more embodiments; and

[0012] Figure 4 Example algorithms according to one or more implementations are described. Detailed Implementation

[0013] The embodiments described herein involve swept pattern probability calculation (SPPC) for speed and defect identification within bearings. According to one or more embodiments, the SPPC automatic detection algorithm can be implemented by one or more devices to automatically detect bearing defects in bearings and related machinery without knowing the exact shaft speed. Bearing defects in bearings and related machinery can include, but are not limited to, spalls or flakes detaching from the bearing raceway (inner or outer raceway) and / or rollers and / or roller cages due to brinelling, false brinelling, corrosion, contamination, lack of lubrication, or excessive rolling pressure (e.g., due to spalling and fracture).

[0014] For example, because the bearings and related machinery of a railway axle-box can provide a vibration spectrum during use (e.g., bearing vibration harmonics), when bearing defects develop, defect components / symptoms may appear in the vibration spectrum. The SPPC automated detection algorithm uses defect-specific patterns of inner and outer raceways, rollers, and / or cages to identify the most likely defect components / symptoms present in the railway axle-box bearings and related machinery, and identifies the precise axle speed. Further diagnostic operations and / or degradation analysis can then be performed using the precise axle speed. Although the embodiments described herein are for railway axle-boxes, the embodiments herein are not limited thereto. In other words, although the implementation herein involves handling track condition monitoring errors (such as wheel diameter management errors required to convert GPS linear velocity into shaft rotation speed), the implementation herein is suitable for many condition monitoring applications across many industries (where tachometers or speed inputs are not installed or available).

[0015] Figure 1 A system 100 according to one or more embodiments is depicted. System 100 includes at least one railcar 101, and the railcar 101 includes at least one axle box 103. The axle box 103 includes one or more wheels 104 (e.g., railbogie wheels) attached thereto by fastening elements. Note that although only a single axle box is shown, most railcars have two bogies and therefore two axles with eight wheels and eight axle boxes attached thereto (e.g., via axle box bearings of the railbogie wheels). Typically, the bearing housing of the axle box 103 includes axle box bearings (e.g., one or more bearings) of the railbogie wheels and bolted connections, the railbogie wheel axle box bearings supporting the corresponding wheels 104, and the bolted connections attaching the bearing housing to the axle box 103. For example, a train typically includes two to more than seventy railcars 101, which means that there can be thousands of bearings within a system 100 that includes a fleet of trains.

[0016] Furthermore, system 100 is generally shown according to one or more embodiments. System 100 may include an electronic computer framework that includes and / or employs any number and combination of computing devices and networks utilizing various communication technologies (as described herein). System 100 can be readily scalable, extensible, and modular, with the ability to be changed for different services or to reconfigure some features independently of other features.

[0017] System 100 includes at least one sensor device 110 from a plurality of condition monitoring sensor devices. Each sensor device 110 is an electronic device that may include: a housing 111, a battery 112, at least one sensor 113 (e.g., a transducer for vibration, temperature, etc.), a data collector 115 (e.g., a processor and memory as described herein), a GPS 114, data transmission electronics 117 (e.g., a wireless modem and / or a near-field communication (NFC) transponder), and an attachment assembly 118 (e.g., one of its plurality of fixing bolts) for securing the sensor device 110 to a wheel 104. The attachment assembly 118 may be any bracket, flange, etc., for attaching the sensor device 110 to the mechanical system to be monitored.

[0018] For example, each sensor device 110 may be a compact, battery-operated device (e.g., using battery 112) that measures static and dynamic data (e.g., condition monitoring data) of the bearings of the wheel 104 to which it is attached (e.g., specifically, at least one of the fastening elements attached to the wheel 104). Each sensor device 110 may wirelessly transmit the condition monitoring data (as indicated by double arrow 119) to devices, servers, and systems such as computing device 120 via data transmission electronics 117.

[0019] According to one or more embodiments, the memory and / or data transmission electronics 117 of the data collector 115 of each sensor device 110 may store condition monitoring (results) and / or may be associated with a unique sensor identifier. For example, an NFC transponder may be pre-programmed with a unique sensor identifier associated with the wireless modulation internals of the sensor device 110, and / or with details relating to that particular sensor and its installation location (e.g., whether it is mounted on or near the axle box bearing of a track bogie wheel). Furthermore, the sensor device 110 records condition monitoring data at various predefined intervals and with speed gating (e.g., when the railcar 101 is moving and not parked in the rail yard).

[0020] The computing device 120 includes one or more central processing units (CPUs) (collectively or generally referred to as processor 121). Processor 121 is connected to memory 122 and various other components via a system bus. Memory 122 may include read-only memory (ROM) and random access memory (RAM). ROM is connected to the system bus and may include a basic input / output system (BIOS) that controls specific basic functions of the computing device 120. RAM is a read-write memory connected to the system bus for use by processor 121. Memory 122 stores data 124 and software 125.

[0021] Data 124 includes a set of values ​​for qualitative or quantitative variables organized in various data structures to support and be used by the operation of software 125. According to one or more embodiments, memory 122 may accumulate and / or store data 124 from sensor device 110 for use by computing device 120. In this regard, for example, data 124 may include condition monitoring data (e.g., bearing vibration and temperature, bearing vibration harmonics) and speed ranges (e.g., the range from the highest desired speed to the lowest desired speed at which the shaft of axle housing 103 can rotate / revolve due to the bearing), speed values, root mean square (RSS) values, bearing designations, unique sensor identifiers, predefined intervals for data accumulation, and one or more specific patterns specific to bearing defects. In one or more examples, the shaft speed may be defined as revolutions per minute, as determined by GPS calculations using an approximate orbital wheel diameter.

[0022] Further note that each of the one or more patterns can be a set of frequencies relating to a particular bearing defect over time (e.g., as the bearing defect develops). In this respect, the set of frequencies is associated with the defect component / symptom outside of normal bearing operation. The patterns can be weighted such that the maximum match (e.g., the maximum match between a frequency and a defect component / symptom) gives the highest value relative to the other matches. Each defect component / symptom in the pattern has a maximum value of 1, but is typically less than 1. Examples of one or more patterns may include a Ball Over Frequency Outside (BPFO) pattern for detecting the frequency of outer raceway defects, a Ball Over Frequency Inside (BPFI) radial and axial load pattern for detecting the frequency of inner raceway defects, a Ball Spin Frequency (BSF) pattern for detecting the frequency of ball bearing defects, and a Cage Baseband Frequency (FTF) pattern for detecting the frequency of cage defects. Pattern weighting can be applied so that the BPFO pattern has 1×BPFO for every 5 harmonics, the BPFI radial and axial load patterns have 1×BPFI for every 3 harmonics and have 1×N sidebands, the BSF pattern has 1×BSF or 2×BSF and a small number of harmonics with FTF sidebands, and the cage FTF pattern has 1×FTF and a small number of harmonics.

[0023] Software 125 is stored as instructions for execution on processor 121. That is, memory 122 is also an example of a tangible storage medium that can be read by processor 121, wherein software is stored as instructions for execution by processor 121 to make system 100 run (or operate), such as, see here. Figures 2 to 3 The instructions described herein. Note that software 125 can reside anywhere within many types of condition monitoring systems and can provide storage operations, trend (analysis) operations, and alarm operations. When a defect is present, SPPC provides axle speed, defect type, and frequency for use in calculating the corresponding system condition indicator (CI). For example, according to one or more embodiments, as described herein, the software may include an SPPC automatic detection algorithm. Typically, the SPPC automatic detection algorithm can be implemented by computing device 120 to automatically detect bearing defects on bearings (e.g., track axle box bearings) of axle box 103 without knowing the accurate axle speed, thereby saving costs (e.g., labor time) and reducing errors in managing constantly changing wheel diameters.

[0024] Furthermore, when executing the software's SPPC automatic detection algorithm, the computing device 120 scans several specific weighted patterns across a specified speed range, simultaneously calculating RSS values ​​for each speed step and each pattern type. The speed is then identified as the speed with the maximum value provided, and the defect type is identified by the specific pattern that gives (or assigns) that maximum value. If no defect component / symptom exists, the software does not notice the speed (e.g., because it is unimportant). If a defect component / symptom exists, these identified defect components / symptoms are correlated with the specific pattern to calculate the shaft speed, the frequency of bearing defects, and the type of bearing defect.

[0025] Computing device 120 includes one or more input / output (I / O) adapters 123 coupled to a system bus. The one or more I / O adapters 123 may include a Small Computer System Interface (SCSI) adapter that communicates with system memory 122 and / or any other similar components. The one or more I / O adapters 123 may include an NFC transponder that communicates with an NFC transponder of sensor device 110. For example, the one or more I / O adapters 123 may interconnect the system bus with network 130 (which may be an external network), enabling system 100 to communicate with other such systems (i.e., server 140).

[0026] System 100 also includes network 130 and server 140. Network 130 includes a group of computers connected together and sharing resources. As described herein, network 130 can be any type of network, including local area network (LAN), wide area network (WAN), or Internet. Server 140 includes processor 142 and memory 144 (as described herein) and provides various functions to computing device 120, such as sharing and storing data 124, providing processing resources, and / or performing calculations (e.g., implementing software 125).

[0027] According to one or more embodiments, for example, server 140 may be a cloud-hosted condition monitoring system that executes software (e.g., software 125 including an SPPC automatic detection algorithm) stored in memory 144 via processor 142. Furthermore, at various predefined intervals (e.g., when the railcar 101 is parked in a rail parking lot at the end of its use), the cloud-hosted condition monitoring system of server 140 downloads and stores data (e.g., data 124 including unique sensor identifiers and / or corresponding condition monitoring data) from sensor device 110. Therefore, the software of server 140 can use the data therein to perform operations similar to those of software 125 of computing device 120.

[0028] Now go to Figure 2 A processing flow 200 implemented by system 100 is described according to one or more embodiments. Processing flow 200 can be implemented by any component of system 100. Typically, with respect to processing flow 200, the speed is unknown, while bearing details are known. That is, although the precise shaft speed (e.g., rpm) is unknown, the precise bearing details (e.g., bearing defect frequency) are known, and it operates within a specific band (e.g., a narrow bandwidth of + / -10% and / or a wide bandwidth of + / -40%). Note that the band can be center-fixed or can be derived from GPS processing. Processing flow 200 can also be enhanced by various methods to “zero” spectral blanket noise and unidentifiable peaks higher than the blanket (noise).

[0029] In traditional condition monitoring, if the bearing speed variation is small, a fixed center speed configuration uses a large search band (e.g., + / - 5% or greater); however, this can lead to false detections / alarms (e.g., false positives) because the probability of selecting spectral components from sources other than defects is high. This necessitates analysts spending significant time manually analyzing the spectrum and other machine information to accept or discard alarms. In contrast, Process 200 offers the technical effectiveness and benefits of reducing false alarms by using the specific frequency bands described herein.

[0030] Processing flow 200 begins at block 210, and a computer (e.g., computing device 120 and / or server 140) receives / accumulates status monitoring data from one or more sensors (e.g., sensor device 110). According to one or more embodiments, the status monitoring data, as well as other data described herein, can be transmitted from sensor device 110 (e.g., such as...). Figure 1 (As indicated by the double arrow 119 in the diagram) to the computing device 120. More specifically, the condition monitoring data includes the vibration harmonics of the bearing. The computing device 120 can also forward the condition monitoring data, along with other data described herein, to the server 140 via the network 130. Thus, both the computing device 120 and the server 140 accumulate sufficient information to support the execution of the processing flow 200. The accumulation of condition monitoring data can occur at predefined intervals, and in some cases, the accumulation (operation) is performed twice a day (e.g., before the railcar 101 leaves the rail parking lot and after its return).

[0031] At box 220, a computer (e.g., computing device 120 and / or server 140) scans one or more patterns along a speed range for condition monitoring data. According to one or more embodiments, computing device 120 and / or server 140 may store the speed range in their respective memories 122 and 144. This speed range may be predefined from the highest desired speed to the lowest desired speed for the conditions at the time of measurement and includes multiple speed steps. According to a non-limiting embodiment, the defect pattern is "scanned" across a frequency range derived from the speed range in many iterations, where each iteration is referred to as a "speed step". Furthermore, computing device 120 and / or server 140 may execute software (e.g., software 125) to scan / apply these patterns according to each speed step of the speed range, the software calculating a speed / pattern-related RSS value (e.g., a small portion of a window at the highest frequency component) for each speed step and each pattern type. One or more windows correspond to the spectrum such that if there is a 1000 Hz spectrum with 800 lines, then each window for each line has a value of how much vibrational energy is associated with the center frequency of that window (e.g., a width of 1.25 Hz).

[0032] Go to Figure 3Graph 300 is depicted according to one or more embodiments. Graph 300 shows an example of vibration harmonics 310 scanned 320 by pattern 330 of the SPPC automatic detection algorithm. Vibration component frequencies 351 are identified by pattern components 352. In one or more embodiments, each pattern component 352 corresponds to several components defined by the order and the number of sidebands on either side of each order. During scanning, pattern components 352 become coincident with vibration components 351. As pattern components 352 become coincident with vibration components 351, the product obtained by multiplying the RSS (root mean square) value of the weighted pattern components by the corresponding spectral window (bin) value (which are aligned in the scan step) reaches the maximum value of the pattern. Therefore, among several types of defect patterns, the defect pattern with the largest maximum value identifies the most likely type of defect. As shown, graph 300 also shows other examples of vibration harmonics 360 and 370 scanned by pattern components 380 and 380 of the SPPC automatic detection algorithm, respectively. In one or more non-limiting embodiments, each implemented bearing has a known or predetermined bearing defect frequency. Therefore, accurate speeds can be identified at least in part based on the known bearing defect frequency ratio (i.e., bearing type), allowing for the identification of defect frequency components (i.e., the frequencies at which component defects occur) using a narrow search band. In this way, the number of false alarms can be significantly reduced, thereby increasing the confidence (or reliability) when the software (e.g., software 125) marks true positives. This increases the reliability of software detection (e.g., alarms) and reduces the required man-hours. It should also be noted that pattern weighting ensures that if more than one pattern spans a set of spectral components, only the pattern with the best match (probability) gives (or assigns) the highest value.

[0033] At block 240, the computer multiplies each pattern component (e.g., one or more patterns) by a matching environmental spectral component. In some example implementations, the multiplication of each pattern component in one or more patterns by the matching environmental spectral component is performed using an interpolated matching environmental spectral component. In other example implementations, the multiplication of each pattern component in one or more patterns by the matching environmental spectral component is performed using a quadratic peak interpolated matching environmental spectral peak. At block 250, the computer adds the components together. The addition by the computer includes adding the pattern components together. In some example implementations, the pattern components may be added together using the root mean square (RSS) ( / statistical squared tolerance / square root of the sum of squares of statistical data / / root square root of the sum) (RSS = Root Sum Square). At operation 260, the addition identifies one or more results. The results include, but are not limited to, the most probable defect, the bearing defect frequency ratio, and the accurate shaft speed (i.e., the precise or true shaft speed determined by the defects present in the vibration signal and the known bearing defect ratio).

[0034] At dashed box 270 (e.g., optional box), the computer outputs one or more results. In this respect, a technician can easily identify any bearing problems monitored by the computer and take remedial measures (e.g., replace or repair the bearing). Note that if no defect component is present, it is not important whether the speed is known. If other spectral components exist in the condition monitoring data (e.g., from machine dynamics / mechanics), these other spectral components can also have patterns associated with them to calculate the speed even in the absence of bearing defects.

[0035] Figure 4An example algorithm 400 according to one or more embodiments is depicted. Example algorithm 400 begins with blocks 401, 402, and 404 receiving initial conditioning monitoring data. The initial conditioning monitoring data includes, but is not limited to, a vibration spectrum of envelope acceleration measurements for shaft rpm (as shown in block 401), pre-determined bearing defect-specific pattern components (as shown in block 402), a calculated velocity range, a bearing defect-specific calculated baseband frequency range and sideband frequency range, and a sweepstep size (as shown in block 404). In one or more non-limiting embodiments, when the GPS has an error range (e.g., + / - 5%) and the wheel diameter has an error value (e.g., + / - 5% from the diameter used to calculate RPM (shaft speed), the velocity range of the sweep pattern includes an acceptable minimum error value based at least in part on the GPS error range and the wheel diameter error value, in this example, the wheel diameter error value would be at least about + / - 10%.

[0036] Then, at box 410, example algorithm 400 initializes the variables. For example, it initializes the correlation value, baseband frequency, and sideband frequency to zero, respectively. At box 415, for each vibration harmonic of the bearing, it enters the FOR loop. More specifically, for the baseband range (low to high), example algorithm 400 progresses through the baseband step size to cross the vibration harmonic scan pattern. At decision block 425 (as indicated by the DO arrow), the FOR loop includes determining whether the number of sidebands is greater than zero. If the number of sidebands is not greater than zero, example algorithm 400 proceeds to box 430 (e.g., following the "No" arrow).

[0037] At box 430, the relevant function is invoked, and at decision box 440, it is determined whether any of the relevant values ​​is greater than the stored value. If the relevant value is greater than the stored value, the example algorithm 400 proceeds to box 445 (e.g., following the "yes" arrow). The example algorithm 400 then proceeds to the next pattern at box 450 by returning to box 415. After returning to box 415, the example algorithm 400 returns the specific defect type (e.g., for any identified relevant value, baseband frequency, and sideband frequency; as shown in box 451).

[0038] At box 445, update the correlation value and frequency. If the correlation value of the sideband is not greater than the stored value, then example algorithm 400 proceeds to box 450 (e.g., following the "No" arrow).

[0039] Returning to decision box 425, if the number of sidebands is greater than zero, example algorithm 400 proceeds to box 460 (e.g., following the "Yes" arrow). At box 460, for each vibration harmonic of the bearing, another FOR loop is entered. More specifically, for the sideband range (low to high), example algorithm 400 progressively moves across the vibration harmonic scan pattern by sideband step size. At box 465, the correlation function is called. At decision box 470, it is determined whether any correlation value in the correlation values ​​is greater than the stored value. If the correlation value is not greater than the stored value, example algorithm 400 proceeds to box 450 (e.g., following the "No" arrow). If the correlation value is greater than the stored value, example algorithm 400 proceeds to box 480 (e.g., following the "Yes" arrow). At box 480, the correlation value and frequency are updated. Then, example algorithm 400 proceeds to box 450.

[0040] Various embodiments of the invention have been described herein with reference to the accompanying drawings. Alternative embodiments of the invention are conceived without departing from its scope. Various connections and positional relationships (e.g., above, below, adjacent, etc.) between elements are illustrated in the above description and drawings. Unless otherwise stated, these connections and / or positional relationships may be direct or indirect, and the invention is not intended to be limited in this respect. Thus, the connection of entities may refer to direct or indirect connection, and the positional relationship between entities may be direct or indirect positional relationship. Furthermore, the various tasks and processing steps described herein may be incorporated (or included) into a more comprehensive procedure or process with additional steps or functions not described in detail herein.

[0041] The following limitations and abbreviations are used to interpret the claims and description. As used herein, the terms “comprising,” “including,” “comprise,” “having,” “containing,” or “comprising,” or any other variations thereof, are intended to cover non-exclusive inclusion. For example, a composition, mixture, process, method, article, or apparatus that comprises a list of elements is not necessarily limited to those elements, but may include other elements not expressly listed or inherent to such a composition, mixture, process, method, article, or apparatus.

[0042] Additionally, the term "exemplary" is used herein to mean "serving as an example, instance, or illustration." Any implementation or design described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other implementations or designs. The terms "at least one" and "one or more" can be understood to include any integer greater than or equal to one, i.e., one, two, three, four, etc. The term "multiple" can be understood to include any integer greater than or equal to two, i.e., two, three, four, five, etc. The term "connection" can include both indirect "connection" and direct "connection."

[0043] The terms “about,” “generally,” “approximately,” and variations thereof are intended to include the degree of error associated with a measurement based on a specific quantity of equipment available at the time of filing this application. For example, “about” may include a range of ±8%, ±5%, or ±2% of a given value.

[0044] For the sake of brevity, conventional techniques related to the implementation and use of aspects of the invention may or may not be described in detail herein. In particular, various aspects of the computing systems and specific computer programs used to implement the various technical features described herein are well known. Therefore, for the sake of brevity, many conventional implementation details are only briefly mentioned or omitted entirely, without providing details of well-known systems and / or processes.

[0045] This invention can be a system, method, and / or computer program product at any possible level of technical detail integration. The computer program product may include a computer-readable storage medium (or media) having computer-readable program instructions on it for causing a processor to execute aspects of the invention.

[0046] Computer-readable storage media can be tangible means capable of holding and storing instructions for use by an instruction execution device. Computer-readable storage media can be, for example, but not limited to, electronic storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination of the foregoing. A non-exhaustive list of more specific examples of computer-readable storage media includes the following: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable optical disc read-only memory (CD-ROM), digital versatile optical disc (DVD), memory sticks, floppy disks, machine encoding devices (such as punched cards or raised structures in slots on which instructions are recorded), and any suitable combination of the foregoing. As used herein, computer-readable storage media should not be construed as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses passing through fiber optic cables), or electrical signals transmitted through wires.

[0047] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to a suitable computing / processing device, or downloaded via a network (e.g., the Internet, a local area network, a wide area network, and / or a wireless network) to an external computer or external storage device. The network may include copper transmission cables, optical fiber transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to a computer-readable storage medium within the suitable computing / processing device.

[0048] Computer-readable program instructions used to perform the operations of this invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, integrated circuit configuration data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​(such as Smalltalk, C++, etc.) and procedural programming languages ​​(such as the "C" programming language or similar programming languages). The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the latter case, the remote computer may be connected to the user's computer via any type of network (including a local area network (LAN) or a wide area network (WAN)) or may be connected to an external computer (e.g., via the Internet provided by an Internet service provider). In some embodiments, electronic circuitry including, for example, programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs) may execute computer-readable program instructions by personalizing the electronic circuitry with state information utilizing the computer-readable program instructions to perform aspects of the invention.

[0049] Various aspects of the invention will be described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block (or frame) in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0050] These computer-readable program instructions may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus for production machines, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / actions specified in one or more boxes of the flowchart and / or block diagram. These computer-readable program instructions may also be stored in a computer-readable storage medium (which can instruct a computer, programmable data processing apparatus, and / or other means to function in a particular manner), such that the computer-readable storage medium storing the instructions includes an article of manufacture comprising instructions for implementing aspects of the functions / actions specified in one or more boxes of the flowchart and / or block diagram.

[0051] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer-implemented process, and to cause the instructions to be performed on the computer, other programmable apparatus or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0052] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of feasible implementations of systems, methods, and computer program products according to various embodiments of the invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of instructions comprising one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions indicated in the blocks may not be executed in the order shown in the drawings. For example, depending on the function involved, two consecutively shown blocks may actually be executed substantially simultaneously, or these blocks may sometimes be executed in reverse order. It will also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified function or action or implements a combination of dedicated hardware and computer instructions.

[0053] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting. Unless the context clearly indicates otherwise, the singular form is intended to include the plural form as used herein. It will be further understood that when the terms “comprising” and / or “including” are used in this specification, they enumerate the presence of the stated features, quantities, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, quantities, steps, operations, elements, components, and / or groups thereof.

[0054] Various embodiments have been described herein for illustrative purposes, but are not intended to be exhaustive or limited to the disclosed embodiments. Many variations and modifications will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology chosen for use herein is for the best explanation of the principles, practical applications, or technical improvements to existing (or discovered) technologies in the market, or to enable those skilled in the art to understand the embodiments disclosed herein.

Claims

1. A method comprising: A computer receives condition monitoring data from one or more sensors, wherein the condition monitoring data includes the vibration spectrum of the machinery; The computer scans one or more patterns along a speed range based on the condition monitoring data, wherein the one or more patterns are a set of frequencies associated with defects in the machinery; The computer multiplies each of the multiple pattern components of the one or more patterns by a matching environmental spectrum component, wherein the matching environmental spectrum component is a spectral window value corresponding to the vibration component in the vibration spectrum that coincides with the pattern component. The computer adds together the plurality of pattern components multiplied by the matched environmental spectral components; and One or more results related to the condition monitoring of the machine are generated based on the result of adding the multiple pattern components together.

2. The method according to claim 1, characterized in that, The condition monitoring data includes bearing vibration harmonics.

3. The method according to claim 1, characterized in that, The one or more sensors measure, record, and transmit the bearing condition monitoring data.

4. The method according to claim 1, characterized in that, The speed range is predefined from the highest desired speed to the lowest desired speed, and includes multiple speed steps.

5. The method according to claim 1, characterized in that, The one or more results include at least one of shaft speed, most likely defect, and most likely defect frequency.

6. The method according to claim 1, characterized in that, The step of multiplying each pattern component of the one or more patterns by the matched environmental spectrum component is performed by the computer using the interpolated matched environmental spectrum component.

7. The method according to claim 1, characterized in that, The step of multiplying each pattern component of the one or more patterns by the matched environmental spectrum component is performed by the computer using the matched environmental spectrum peak after quadratic peak interpolation.

8. The method according to claim 1, characterized in that, The root mean square (RSS) method is used to perform the step of adding the multiple pattern components together by the computer.

9. A computer program product comprising a computer-readable storage medium having program instructions embodied therein, the program instructions being computer-executable to cause: The computer receives status monitoring data from one or more sensors, wherein, The condition monitoring data includes the vibration spectrum of the machinery; The computer scans one or more patterns along a speed range based on the condition monitoring data, wherein the one or more patterns are a set of frequencies associated with defects in the machinery; The computer multiplies each of the multiple pattern components of the one or more patterns by a matching environmental spectrum component, wherein the matching environmental spectrum component is a spectral window value corresponding to the vibration component in the vibration spectrum that coincides with the pattern component. The computer adds together the plurality of pattern components multiplied by the matched environmental spectral components; and One or more results related to the condition monitoring of the machine are generated based on the result of adding the multiple pattern components together.

10. The computer program product according to claim 9, characterized in that, The condition monitoring data includes bearing vibration harmonics.

11. The computer program product according to claim 9, characterized in that, The one or more sensors measure, record, and transmit the bearing condition monitoring data.

12. The computer program product according to claim 9, characterized in that, The speed range is predefined from the highest desired speed to the lowest desired speed, and includes multiple speed steps.

13. The computer program product according to claim 9, characterized in that, The one or more results include shaft speed and the most likely defect.

14. The computer program product according to claim 9, characterized in that, The step of multiplying each pattern component of the one or more patterns by the computer with the matched ambient spectrum component is performed using the interpolated matched ambient spectrum component.

15. The computer program product according to claim 9, characterized in that, The step of multiplying each pattern component of the one or more patterns by the matching environmental spectrum component by the computer uses the matching environmental spectrum peak value after quadratic peak interpolation.

16. The computer program product according to claim 9, characterized in that, The step of adding the multiple pattern components together by the computer is performed using the root mean square (RSS) method.

17. A system comprising: One or more sensors are configured to output condition monitoring data, wherein the condition monitoring data includes the vibration spectrum of the machinery; and A computer, communicating with the one or more sensor signals to receive the status monitoring data, is configured to perform operations including: The condition monitoring data is scanned along a speed range using one or more patterns, wherein the one or more patterns are a set of frequencies associated with defects in the machinery; Each pattern component of the plurality of pattern components of the one or more patterns is multiplied by a matching environmental spectrum component, wherein the matching environmental spectrum component is a spectral window value corresponding to the vibration component in the vibration spectrum that coincides with the pattern component. The plurality of pattern components, multiplied by the matched environmental spectral components, are added together; and One or more results related to the condition monitoring of the machine are generated based on the result of adding the multiple pattern components together.

18. The system according to claim 17, characterized in that, The condition monitoring data includes bearing vibration harmonics.

19. The system according to claim 17, characterized in that, The one or more sensors measure, record, and transmit the bearing condition monitoring data.

20. The system according to claim 17, characterized in that, The speed range is predefined from the highest desired speed to the lowest desired speed, and includes multiple speed steps.

Images