Real-time predictive maintenance method for device by using cluster waveforms

Abstract

Disclosed is a real-time predictive maintenance method for a device by using cluster waveforms, comprising: an information collection step of collecting information on changes in energy magnitude over time measured by the device and collecting a large amount of energy waveform information for various operations performed by the device; a cluster waveform extraction step of classifying the large amount of energy waveforms collected in the information collection step into similar waveforms so as to form a plurality of similar clusters, and extracting a cluster waveform from each of the plurality of similar clusters; and a detection step of detecting an anomaly in the device in real time by, when the device operates and energy waveforms are measured from the device in real time, comparing real-time energy waveforms formed when the measurement begins with a plurality of cluster waveforms extracted in the cluster waveform extraction step and continuously eliminating waveforms that are not similar to the energy waveforms of the device being formed in real time from among the plurality of cluster waveforms.

Description

Predictive maintenance of real-time devices using cluster waveforms

[0001] The present invention relates to a real-time predictive maintenance method for a device using a cluster waveform, and more specifically, to a real-time predictive maintenance method for a device using a cluster waveform, which collects a large amount of energy waveform information measured from a device freely performing various operations while performing each operation, classifies the large amount of collected energy waveforms by similar waveforms to form a small number of similar clusters, extracts a small number of cluster waveforms representing each similar cluster based on the similar waveforms belonging to the similar clusters, and then searches and compares the real-time energy waveform measured from the device freely operating in real time with the small number of cluster waveforms to detect an abnormality in the device, thereby generating an alarm and inducing management such as replacement or repair in advance before a device malfunctions, thereby preventing economic losses, safety accidents, inconveniences, etc., caused by sudden device malfunctions.

[0002] In general, stable operation is very important for various devices used for automation processes of facilities.

[0003] For example, in the facilities of a large-scale production plant, tens or hundreds of devices are installed and operate in conjunction with each other to continuously produce products. If a single device among the many devices breaks down, a catastrophic situation can occur where the entire operation of the facility comes to a halt.

[0004] At this time, downtime due to equipment failure inevitably leads to enormous losses not only in equipment repair costs but also in operating costs and business effects wasted while the equipment is down.

[0005] To prevent such damage, predictive maintenance methods are being developed to detect and respond to abnormal signs in devices in advance and prevent damage caused by sudden device failures. However, these predictive maintenance methods have the problem that they are difficult to apply to devices that perform irregular and diverse operations because they detect abnormal signs in devices that perform repetitive and regular operations.

[0006] Therefore, for devices that freely (irregularly) perform various movements, such as elevators and cranes, it is still somewhat difficult to detect abnormal signs in advance, and conventional problems caused by sudden device failures still occur.

[0007] In particular, sudden breakdowns of equipment such as elevators can lead to safety accidents that can result in casualties or cause inconvenience to users.

[0008] The present invention has been proposed to solve the above-mentioned problems, and its purpose is to provide a real-time predictive maintenance method for a device using a cluster waveform, which collects a large amount of energy waveform information measured by the device when performing each operation from a device that freely performs various operations, classifies the collected large amount of energy waveforms by similar waveforms to form a small number of similar clusters, extracts a small number of cluster waveforms representing each similar cluster based on the similar waveforms belonging to the similar clusters, and then searches and compares the real-time energy waveform measured from the device that freely operates in real time with the small number of cluster waveforms to detect an abnormality in the device, and issues an alarm when the device is damaged, thereby inducing management such as replacement or repair in advance before the device malfunctions, thereby preventing economic losses, safety accidents, inconveniences, etc., caused by sudden device malfunctions in advance.

[0009] In addition, the present invention provides a real-time predictive maintenance method for a device using a cluster waveform, which can perform an operation in real time on the device and detect an abnormality of the device before the operation is completed, thereby enabling a more rapid response to an abnormality of the device.

[0010] In order to achieve the above object, the present invention provides a predictive maintenance method for a real-time device using a cluster waveform, comprising: an information collection step (S10) for collecting information on changes in energy size over time measured by a device performing each operation in a device performing various operations, thereby collecting a large amount of energy waveform information for various operations performed by the device; a cluster waveform extraction step (S20) for classifying a large amount of energy waveforms collected in the information collection step (S10) by similar waveforms to form a plurality of similar clusters, and extracting cluster waveforms from each of the plurality of similar clusters; and a detection step (S30) for detecting abnormal signs of the device in real time by comparing real-time energy waveforms that are formed when the device is operated in real time and measurement of energy waveforms from the device is started with the measurement started with a plurality of cluster waveforms extracted in the cluster waveform extraction step (S20), and continuously eliminating waveforms that are not similar to the energy waveform of the device being formed in real time from among the plurality of cluster waveforms.

[0011] In addition, the cluster waveform extraction step (S20) is characterized in that it includes a classification process (S21) of classifying and collecting a large amount of energy waveforms collected in the information collection step (S10) by similar waveforms to form a plurality of similar clusters, and an extraction process (S22) of forming and extracting cluster waveforms having a predetermined thickness for each similar cluster by overlapping energy waveforms belonging to similar clusters in the classification process (S21).

[0012] In addition, the detection step (S30) is characterized in that it includes a measurement process (S31) for collecting information on changes in energy size over time measured from a device performing real-time operation and measuring the energy waveform of the device for real-time operation, and when measurement starts from the device in the measurement process (S31) and a real-time energy waveform starts to be formed, an erasing process (S32) for sequentially erasing cluster waveforms that are dissimilar to the energy waveform of the device being formed in real time while searching and tracing a waveform similar to the real-time energy waveform that starts to be formed among a plurality of cluster waveforms extracted in the cluster waveform extraction step (S20), and a judgment process (S33) for determining that the device is in an unstable state and giving an alarm when all of the plurality of cluster waveforms extracted in the cluster waveform extraction step (S20) are erased in the process of forming an energy waveform collected by real-time measurement from the device performing the operation through the erasing process (S32).

[0013] In addition, in the above judgment process (S33), when the operation of the real-time device is completed and the real-time energy waveform measured and collected from the device is formed, if a cluster waveform that is similar to the real-time energy waveform and is not erased is searched and matched, the real-time device is judged to be in a stable state.

[0014] In addition, the energy measured and collected from the device is characterized in that any one of the following is selectively used: current consumed in operating the device, vibration generated when operating the device, noise generated when operating the device, frequency of power supplied to the device, temperature, humidity, and pressure of the device when operating the device.

[0015] As described above, according to the real-time predictive maintenance method of a device using a cluster waveform according to the present invention, a large amount of energy waveform information measured by the device while performing each operation is collected from a device that freely performs various operations, the collected large amount of energy waveforms are classified by similar waveforms to form a small number of similar clusters, and a small number of cluster waveforms representing each similar cluster are extracted based on the similar waveforms belonging to the similar clusters, and then the real-time energy waveform measured from the device that freely operates in real time is searched and compared with the small number of cluster waveforms, and when an abnormality of the device is detected, an alarm is issued to induce management such as replacement or repair in advance before a device failure occurs, thereby preventing in advance economic losses, safety accidents, inconveniences, etc. due to sudden device failure.

[0016] Additionally, it has the effect of enabling more rapid response to abnormalities in the device by performing actions in real time on the device and detecting abnormalities in the device before the action is completed.

[0017] FIG. 1 is a block diagram of a real-time device predictive maintenance method using a cluster waveform according to an embodiment of the present invention.

[0018] FIGS. 2 to 5 are drawings for explaining a real-time device predictive maintenance method using the cluster waveform illustrated in FIG. 1.

[0019] A method for predictive maintenance of real-time devices using cluster waveforms according to a preferred embodiment of the present invention is described in detail with reference to the attached drawings. Detailed descriptions of known functions and configurations that may unnecessarily obscure the gist of the present invention are omitted.

[0020] FIGS. 1 to 5 illustrate a predictive maintenance method for a real-time device using a cluster waveform according to an embodiment of the present invention. FIG. 1 is a block diagram of a predictive maintenance method for a real-time device using a cluster waveform according to an embodiment of the present invention, and FIGS. 2 to 5 are drawings each illustrating a predictive maintenance method for a real-time device using the cluster waveform illustrated in FIG. 1.

[0021] As illustrated in FIG. 1, the real-time device predictive maintenance method (100) using a cluster waveform according to an embodiment of the present invention includes an information collection step (S10), a cluster waveform extraction step (S20), and a detection step (S30).

[0022] The above information collection step (S10) is a step for collecting a large amount of energy waveform information for various operations performed by a device by collecting information on changes in energy size over time measured by the device while performing each operation.

[0023] Here, in the information collection step (S10), the energy measured and collected from the device performing various operations may be any one of the current consumed in operating the device, the vibration generated when operating the device, the noise generated when operating the device, the frequency of the power supplied to the device, the temperature, humidity, pressure, etc. of the device when operating the device. In the real-time device predictive maintenance method (100) using a cluster waveform of the present invention, the current consumed in operating the device is selectively used as the energy measured from the device, but the selection and use is not limited to this current.

[0024] That is, when information on changes in the size (value) of current consumed by a device performing an operation in the above information collection step (S10) is collected over time, a current (energy) waveform such as a graph is collected. Since the device performs various operations, various types of current waveforms are collected.

[0025] Here, there are devices such as elevators and cranes that freely (irregularly) perform various movements. For convenience of explanation, in the present invention, the above device is set as an elevator that is installed in a 10-story building and can accommodate about 10 people, and in the information collection step (S10), current consumed by the elevator was measured during the elevator's various movements for 30 days to collect various types of current waveforms.

[0026] As a result of measuring and collecting current waveforms from the elevator for 30 days, approximately 8,500 current waveforms were collected.

[0027] Since the real-time predictive maintenance method (100) of the present invention detects abnormal signs of a device that freely performs various operations, it is desirable to ensure that sufficient current waveform information on various operations performed by the device can be secured. As described above, the current waveform was measured and collected from the elevator for a total of 30 days. However, the period for collecting current waveform information can be freely set by considering the type of device, the surrounding environment in which the device is used, and other conditions.

[0028] Here, the various types of current waveform information collected from the device are used as a medium for extracting a small number of cluster waveforms that serve as a basis for detecting abnormal symptoms of the device in the cluster waveform extraction step (S20) to be described later. The current waveform information collected in the information collection step (S10) is assumed to have been measured and collected in an elevator operating in a normal state.

[0029] The above cluster waveform extraction step (S20) classifies a large amount of energy waveforms collected in the above information collection step (S10) by similar waveforms to form a plurality of similar clusters, and extracts cluster waveforms from each of the plurality of similar clusters, and is comprised of a classification process (S21) and an extraction process (S22).

[0030] The above classification process (S21) is a process of classifying and collecting a large amount of energy waveforms collected in the above information collection step (S10) by similar waveforms to form a number of similar clusters.

[0031] That is, in the information collection step (S10), a large number of current waveforms are collected and classified by similar waveforms to form a small number of clusters. As described above, about 8,500 current waveforms collected from the elevator are classified by similar waveforms, and a total of 91 similar clusters are classified, and these 91 similar clusters represent the entire current waveforms (about 8,500 current waveforms).

[0032] Figure 2 illustrates some of the few similar clusters classified by similar waveforms. When a total of 91 similar clusters are sequentially numbered as the 1st similar cluster, the 2nd similar cluster, …, the 91st similar cluster, the waveforms classified as the 20th similar cluster to the 40th similar cluster are shown.

[0033] The above extraction process (S22) is a process of forming and extracting a cluster waveform having a predetermined thickness for each similar cluster by overlapping energy waveforms belonging to similar clusters in the above classification process (S21).

[0034] That is, when energy waveforms belonging to similar clusters are superimposed, a single cluster waveform with a predetermined thickness is formed. In the classification process (S21), approximately 8,500 current waveforms collected from the elevator are classified into a total of 91 similar clusters, so a total of 91 cluster waveforms extracted from a total of 91 similar clusters will be formed as shown in FIG. 3, and the 91 cluster waveforms formed in this way have representativeness for the entire current waveform.

[0035] Here, among the current waveforms of the above similar clusters, current waveforms with an abnormal shape (noise cluster) are removed, and similar clusters are formed based on meaningful current waveforms, and cluster waveforms are extracted.

[0036] In addition, a cluster waveform having a predetermined thickness is extracted by overlapping energy waveforms belonging to the above-mentioned similar clusters, but a line connecting the center, bottom, or top of the waveform thickness formed by overlapping energy waveforms can also be formed and extracted as a cluster waveform.

[0037] As illustrated in FIG. 4, the detection step (S30) detects abnormal signs of the device in real time by comparing the real-time energy waveform that is formed when the device starts operating in real time and the measurement of the energy waveform from the device begins with the measurement with a plurality of cluster waveforms extracted in the cluster waveform extraction step (S20) and continuously eliminating waveforms that are not similar to the energy waveform of the device being formed in real time from among the plurality of cluster waveforms. The detection step (S30) consists of a measurement process (S31), an elimination process (S32), and a judgment process (S33).

[0038] The above measurement process (S31) is a process of collecting information on changes in energy size over time measured from a device performing real-time operation and measuring the energy waveform of the device for real-time operation.

[0039] That is, when the elevator operates to detect the status of the elevator in real time, the current waveform measured from the elevator during the operation is measured and collected in real time.

[0040] The above-mentioned erasure process (S32) is a process of sequentially erasing cluster waveforms that are dissimilar to the energy waveform of the device being formed in real time while searching and tracking waveforms similar to the real-time energy waveform that is beginning to be formed among a plurality of cluster waveforms extracted in the cluster waveform extraction step (S20) when measurement is started from the device in the above-mentioned measurement process (S31) and a real-time energy waveform is beginning to be formed.

[0041] That is, from the time when the current waveform measured and formed from the elevator starts to be measured in real time, the cluster waveforms similar to the real-time current waveforms are searched for by comparing them with a total of 91 cluster waveforms, and cluster waveforms that are not similar are sequentially removed while continuously comparing them with a total of 91 cluster waveforms in the process of forming current waveforms over time as the elevator performs its operation.

[0042] Here, the above erasure process (S32) can be completed before the elevator completes its operation if all 91 cluster waveforms are erased based on the current waveforms measured and extracted during the operation of the real-time elevator. If all 91 cluster waveforms are not erased, the erasure process is performed until the operation of the real-time elevator is completed.

[0043] The above judgment process (S33) is a process of determining that the device is in an unstable state and issuing an alarm when all of the cluster waveforms extracted in the cluster waveform extraction step (S20) are erased during the process of forming an energy waveform collected in real time from a device performing an operation through the above erasure process (S32).

[0044] That is, during the real-time elevator operation process, the current waveforms measured and collected are compared in real time with a total of 91 cluster waveforms, and all cluster waveforms are eliminated, which means that the current waveforms measured and collected in real time are waveforms of a different form from the current waveforms measured in a normal elevator, and such current waveforms are sufficient reason to suspect the status of the elevator, so an alarm is issued to determine that the elevator is in a somewhat unstable state so that management such as inspection or repair can be performed in advance before a breakdown occurs in the elevator.

[0045] Here, since the above judgment process (S33) has the characteristic of being able to detect abnormal symptoms (unstable state) of the device while the device is performing an operation, the occurrence of abnormal symptoms of the device can be detected quickly and accurately, leading to faster response, and thus very stable predictive maintenance of the device can be induced.

[0046] If, as shown in Fig. 5, the operation of the real-time device is completed in the above judgment process (S33) and a cluster waveform that is similar to the real-time energy waveform and has not been erased is searched and matched at the time of completion of the formation of the real-time energy waveform measured and collected from the device, it goes without saying that the real-time device is judged to be in a stable state.

[0047] That is, if the real-time current waveform measured from the elevator matches one of the cluster waveforms among a small number of cluster waveforms, it means that the real-time current waveform corresponds to a current waveform that can be measured in a normal elevator, and thus the real-time elevator is judged to be in a stable state.

[0048] Of course, if the elevator freely performs various operations, the current waveform for each operation can be measured in real time from the elevator, and the status of the elevator performing each operation can be continuously detected and judged in the same manner as above, so that abnormal signs of irregularly operating equipment can be easily detected in real time and effectively preventive maintenance can be performed.

[0049] The method (100) for predictive maintenance of real-time equipment using cluster waveforms of the present invention, which is comprised of the above-described process, collects a large amount of energy waveform information measured from equipment that freely performs various operations while performing each operation, classifies the collected large amount of energy waveforms by similar waveforms to form a small number of similar clusters, extracts a small number of cluster waveforms representing each similar cluster based on the similar waveforms belonging to the similar clusters, and then searches and compares the real-time energy waveforms measured from equipment that freely operates in real time with the small number of cluster waveforms to detect an abnormality in the equipment, thereby generating an alarm and inducing management such as replacement or repair in advance before equipment failure occurs, thereby preventing economic losses, safety accidents, inconveniences, etc., caused by sudden equipment failure in advance.

[0050] Additionally, it has the effect of enabling more rapid response to abnormalities in the device by performing actions in real time on the device and detecting abnormalities in the device before the action is completed.

[0051] While the present invention has been described with reference to the embodiments illustrated in the accompanying drawings, these are merely illustrative and are not limited to the above-described embodiments. Those skilled in the art will readily appreciate that various modifications and equivalent embodiments are possible. Furthermore, it should be understood that modifications are possible by those skilled in the art without departing from the spirit and scope of the present invention. Therefore, the scope of the claims in the present invention is not limited to the detailed description, but rather by the claims set forth below and their technical spirit.

[0052] The present invention is a predictive maintenance industry for equipment.

Claims

1. In a predictive maintenance method for a device that performs various movements irregularly, An information collection step (S10) that collects information on changes in energy size over time measured by the device and collects a large amount of energy waveform information on various operations performed by the device; A cluster waveform extraction step (S20) that classifies a large amount of energy waveforms collected in the above information collection step (S10) into similar waveforms to form a plurality of similar clusters, and extracts cluster waveforms from each of the plurality of similar clusters; and A method for predictive maintenance of a real-time device using a cluster waveform, characterized in that it includes a detection step (S30) for detecting abnormal signs of a real-time device by comparing the real-time energy waveform that is formed when the device starts operating in real time and the measurement of the energy waveform from the device starts with the measurement with a plurality of cluster waveforms extracted in the cluster waveform extraction step (S20) and continuously eliminating waveforms that are not similar to the energy waveform of the device being formed in real time from among the plurality of cluster waveforms.

2. In paragraph 1, The above cluster waveform extraction step (S20) is A classification process (S21) that collects a large amount of energy waveforms collected in the above information collection step (S10) and classifies them into similar waveforms to form a number of similar clusters, A predictive maintenance method for a device using a cluster waveform, characterized in that it includes an extraction process (S22) for forming and extracting a cluster waveform having a predetermined thickness for each similar cluster by overlapping energy waveforms belonging to similar clusters in the above classification process (S21).

3. In paragraph 2, The above detection step (S30) is A measurement process (S31) for measuring the energy waveform of a device for real-time operation by collecting information on changes in energy size over time measured from a device performing real-time operation, and In the above measurement process (S31), when measurement starts from the device and a real-time energy waveform starts to be formed, a process (S32) for sequentially eliminating cluster waveforms that are dissimilar to the energy waveform of the device being formed in real time by searching and tracking waveforms similar to the real-time energy waveform that starts to be formed among a plurality of cluster waveforms extracted in the cluster waveform extraction step (S20), A real-time predictive maintenance method for a device using a cluster waveform, characterized in that it includes a judgment process (S33) for determining that the device is in an unstable state and giving an alarm when all of the multiple cluster waveforms extracted in the cluster waveform extraction step (S20) are erased during the process of forming an energy waveform collected in real time from a device performing an operation through the above-mentioned erasure process (S32).

4. In paragraph 3, A predictive maintenance method for a real-time device using a cluster waveform, characterized in that when the operation of the real-time device is completed in the above judgment process (S33) and a cluster waveform that is not erased and is similar to the real-time energy waveform is searched and matched at the time of formation of the real-time energy waveform measured and collected from the device, the real-time device is judged to be in a stable state.

5. In paragraph 1, A real-time predictive maintenance method for a device using a cluster waveform, characterized in that the energy measured and collected from the device is selected from among the current consumed in operating the device, vibration generated during operation of the device, noise generated during operation of the device, frequency of power supplied to the device, temperature, humidity, and pressure of the device during operation.

Images