Equipment state monitoring method and device, equipment, storage medium and program product

Abstract

The invention relates to an equipment state monitoring method and device, equipment, a storage medium and a program product. The method comprises the following steps: acquiring a real-time torque signal of target equipment in a current working cycle period, and determining a state monitoring result of the target equipment based on the real-time torque signal in the current working cycle period. The method can improve the accuracy of the state monitoring result of the target equipment.

Description

Equipment status monitoring method, device, equipment, storage medium and program product Technical Field

[0001] The present application relates to the technical field of mechanical equipment, and in particular to an equipment status monitoring method, apparatus, equipment, storage medium, and program product. Background Art

[0002] With the continuous development of science and technology and economy, the use of motors is indispensable in industrial production in all walks of life.

[0003] Typically, the operation of various industrial equipment relies on motor drive systems, so the normal operation of motor drive systems is a prerequisite for ensuring the normal operation of industrial equipment. Take the hot press machine in the battery production industry as an example. As a key equipment in lithium-ion battery production, the effective monitoring of the hot press machine's status is crucial to the efficiency of lithium-ion battery production.

[0004] However, in the related art, when monitoring the status of industrial equipment, there is a technical problem that the accuracy of the status monitoring results is low.

[0005] Summary of the Invention

[0006] Based on this, it is necessary to provide an equipment status monitoring method, device, equipment, storage medium and program product to address the above technical problems, which can improve the accuracy of industrial equipment status monitoring results.

[0007] In a first aspect, the present application provides a method for monitoring equipment status, the method comprising:

[0008] Obtain the real-time torque signal of the target device during the current working cycle;

[0009] Determine the status monitoring results of the target equipment based on the real-time torque signal within the current working cycle.

[0010] In an embodiment of the present application, a real-time torque signal of the target device within the current working cycle is obtained, and based on the real-time torque signal within the current working cycle, the state monitoring result of the target device is determined. In this embodiment, the real-time torque signal is the torque signal within the current working cycle, which is equivalent to collecting the real-time torque signal within a complete working cycle. The real-time torque signal within a complete working cycle can fully reflect the state of the target device. In this way, by analyzing the real-time torque signal within a complete working cycle, the accuracy of the target device state monitoring result can be increased. Furthermore, the state monitoring of the target device can be achieved directly by obtaining the real-time torque signal collected by the target device's own sensor. In this way, even if the industrial site adjusts the production mode of the target device, it is not necessary to readjust the parameters to be applicable, which improves the scenario applicability of the equipment state monitoring and meets the need to quickly adapt to the frequent changes in production modes.

[0011] In one embodiment, the condition monitoring result includes a predictive maintenance result of the target equipment; the condition monitoring result of the target equipment is determined based on the real-time torque signal within the current working cycle, including:

[0012] Obtain the standard torque curve of the target device;

[0013] The predictive maintenance results are determined based on the real-time torque signal and the standard torque curve during the current working cycle.

[0014] In an embodiment of the present application, a standard torque curve of the target device is obtained, and a predictive maintenance result is determined based on the real-time torque signal and the standard torque curve within the current working cycle. In this embodiment, by using the standard torque curve and the real-time torque signal of the target device, since the standard torque curve corresponds to the standard torque value of the target device, by measuring the degree of deviation between the real-time torque signal and the standard torque curve, predictive maintenance can be performed on the target device, and the predictive maintenance result of the target device can be determined to guide maintenance work at the industrial site; in this way, maintenance is only performed when it is needed, which saves labor costs when maintenance is not required many times compared to scheduled maintenance; in addition, predictive maintenance of the target device can determine the long-term degradation trend of the target device, which can be used to optimize the subsequent maintenance strategy of the target device and predict the service life of the target device.

[0015] In one embodiment, obtaining a standard torque curve of a target device includes:

[0016] According to the historical operating status information of the target device, the historical working condition signal and the historical torque signal of the target device are obtained;

[0017] Generate a standard torque curve for the target equipment based on historical operating condition signals and historical torque signals.

[0018] In this embodiment of the present application, historical operating condition signals and historical torque signals of the target device are obtained based on historical operating status information of the target device, and a standard torque curve for the target device is generated based on these historical operating condition signals and historical torque signals. In this embodiment, since the operating condition signals reflect the operating conditions of the target device, the accuracy of the standard torque curve for the target device can be improved by segmenting the historical torque signals based on the operating conditions, using the historical operating condition signals as a reference.

[0019] In one embodiment, generating a standard torque curve of a target device based on historical operating condition signals and historical torque signals includes:

[0020] Performing working condition segmentation on the historical torque signal according to the historical working condition signal to obtain the historical torque signals within multiple historical cycle periods;

[0021] According to the start time of the historical working condition signal, the historical torque signals in multiple historical cycles are time-aligned to obtain a historical torque curve composed of multiple historical cycles;

[0022] Generate the standard torque curve of the target equipment based on the historical torque curve.

[0023] In an embodiment of the present application, the historical torque signal is segmented according to the historical operating condition signal to obtain historical torque signals within multiple historical cycles. The historical torque signals within the multiple historical cycles are then time-aligned according to the start time of the historical operating condition signal to obtain a historical torque curve consisting of the multiple historical cycles. A standard torque curve for the target device is generated based on the historical torque curve. In this embodiment, the historical torque signal is segmented according to the historical operating condition signal, and the start time of the operating condition signal is used as a reference to time-align the historical torque signals within the multiple historical cycles. This makes the historical torque signals within the multiple historical cycles relatively uniform, improves the accuracy of the standard torque curve, and thus improves the accuracy of the target device status monitoring results.

[0024] In one embodiment, generating a standard torque curve for a target device based on a historical torque curve includes:

[0025] According to the preset time window, the historical torque curve is rasterized to obtain multiple grids;

[0026] Get the standard torque value at the middle moment of each grid;

[0027] The standard torque curve of the target device is constructed based on the standard torque value at the middle moment of each grid.

[0028] In this embodiment of the present application, a historical torque curve is rasterized according to a preset time window to obtain multiple grids. The standard torque value at the intermediate moment of each grid is then obtained. Then, a standard torque curve for the target device is constructed based on the standard torque value at the intermediate moment of each grid. In this embodiment, by rasterizing the historical torque curve and determining the standard torque curve based on the standard torque value at the intermediate moment of each grid, the standard torque value at the intermediate moment of each grid can represent the torque characteristics of each grid, thereby increasing the accuracy of the standard torque curve and thus the accuracy of the target device status monitoring results.

[0029] In one embodiment, obtaining the standard torque value at the intermediate moment of each grid includes:

[0030] Get the mean torque of each grid;

[0031] The torque mean of each grid is determined as the standard torque value at the middle moment of the corresponding grid.

[0032] In this embodiment of the present application, the mean torque value of each grid is obtained and determined as the standard torque value at the midpoint of the corresponding grid. In this embodiment, since the mean value can reflect the trend of a set of data, by using the mean torque value of each grid as the standard torque value at the midpoint of the corresponding grid, the grid's mean torque value is used to represent the standard torque value of that grid, thereby improving the accuracy of the standard torque curve and thus improving the accuracy of the target equipment status monitoring results.

[0033] In one embodiment, determining a predictive maintenance result based on a real-time torque signal and a standard torque curve during a current working cycle includes:

[0034] Match the real-time torque signal in the current working cycle with the standard torque curve at each moment to obtain the standard torque value corresponding to the real-time torque value at each moment in the real-time torque signal;

[0035] The predictive maintenance result of the target equipment is determined based on the standard torque value corresponding to the real-time torque value at each moment in the real-time torque signal.

[0036] In an embodiment of the present application, the real-time torque signal within the current working cycle is aligned with the standard torque curve at each moment to obtain the standard torque value corresponding to the real-time torque value at each moment in the real-time torque signal. Based on the standard torque value corresponding to each moment in the real-time torque signal, a predictive maintenance result for the target equipment is determined. In this embodiment, by aligning the real-time torque signal within the current working cycle with the standard torque curve at each moment, the accuracy of the standard torque value corresponding to each moment in the real-time torque signal is improved, thereby increasing the accuracy of the predictive maintenance result for the target equipment.

[0037] In one embodiment, determining a predictive maintenance result of a target device based on a standard torque value corresponding to a real-time torque value at each moment in a real-time torque signal includes:

[0038] Determine the health value of the target device in the current working cycle based on the real-time torque value at each moment in the real-time torque signal, the standard torque value corresponding to the real-time torque value at each moment, and the number of real-time torque values ​​in the current working cycle;

[0039] Determine the predictive maintenance results based on the health value.

[0040] In an embodiment of the present application, a health value of a target device in a current working cycle is determined based on the real-time torque value at each moment in the real-time torque signal, the standard torque value corresponding to the real-time torque value at each moment, and the number of real-time torque values ​​in the current working cycle. Then, a predictive maintenance result is determined based on the health value. In this embodiment, the relative error between the real-time torque signal in the current working cycle and the corresponding standard torque curve is calculated based on the real-time torque value of the real-time torque signal in the current working cycle and the standard torque value corresponding to the real-time torque value. The health value of the real-time torque signal of the target device in the current working cycle is determined based on the relative error between the real-time torque signal in the current working cycle and the corresponding standard torque curve. This can increase the accuracy of the health value of the target device determined in the current working cycle, thereby significantly increasing the accuracy of the predictive maintenance result for the target device.

[0041] In one embodiment, determining a predictive maintenance result based on the health value includes:

[0042] Obtain the historical health value of the target device during the previous working cycle;

[0043] The predictive maintenance results are determined based on the comparison results between the historical health value and the health value.

[0044] In an embodiment of the present application, the historical health value of the target device during the previous work cycle is obtained, and a predictive maintenance result is determined based on a comparison between the historical health value and the health value. In this embodiment, the predictive maintenance result of the target device is determined by comparing the historical health value of the target device during the previous work cycle with the health value during the current work cycle. This achieves a transition from a scheduled maintenance strategy to a predictive maintenance strategy, enabling timely maintenance of the target device when maintenance is required, thereby extending the service life of the target device.

[0045] In one embodiment, determining a predictive maintenance result based on a comparison result between a historical health value and a health value includes:

[0046] Get the difference between the historical health value and the health value;

[0047] If the difference is greater than the preset maintenance threshold, the predictive maintenance result is determined to be maintenance of the target equipment in the current working cycle.

[0048] In an embodiment of the present application, the difference between the historical health value and the health value is obtained. If the difference is greater than a preset maintenance threshold, the predictive maintenance result is determined to be maintenance on the target device during the current working cycle. In this embodiment, when the difference between the historical health value and the health value is greater than the preset maintenance threshold, the predictive maintenance result for the target device is determined to be maintenance on the target device during the current working cycle. This implements predictive maintenance when the target device deteriorates by a certain threshold, allowing timely maintenance on the target device when maintenance is required.

[0049] In one embodiment, the method further comprises:

[0050] Determine the performance degradation trend of the target device based on the health value of the target device throughout its life cycle;

[0051] Obtain the target duty cycle period in which the health value jitter exceeds a preset amplitude in the performance degradation trend graph;

[0052] Determine the maintenance time of the target equipment based on the target working cycle.

[0053] In an embodiment of the present application, a performance degradation trend graph of the target device is first determined based on the health value of the target device over its entire life cycle. A target duty cycle period in which the health value jitter exceeds a preset amplitude in the performance degradation trend graph is then obtained, and the maintenance time of the target device is determined based on the target duty cycle period. In this embodiment, a performance degradation trend graph of the target device is drawn through real-time calculation of the health value, so that when the degradation reaches a certain preset amplitude, predictive maintenance is performed on the target device, and the maintenance time of the target device is determined. This allows for timely maintenance of the target device when its performance degrades; and maintenance is performed only when the target device requires it, thereby reducing the maintenance time of the target device.

[0054] In one embodiment, the condition monitoring result includes a fault location result of the target device; and determining the condition monitoring result of the target device based on the real-time torque signal within the current working cycle includes:

[0055] Obtain a real-time torque curve based on the real-time torque signal within the current working cycle;

[0056] The fault location result is determined based on the real-time torque curve.

[0057] In an embodiment of the present application, a real-time torque curve is obtained based on the real-time torque signal within the current working cycle, and a fault location result is determined based on the real-time torque curve. In this method, fault location of the target device is performed based on the real-time torque curve, and the fault location of the target device can be determined, allowing maintenance personnel to directly perform maintenance and troubleshooting on the fault point, assisting in the rapid implementation of industrial on-site maintenance and saving time in repairing the target device. The fault location in this embodiment can be used for short-term anomaly detection. When the target device has a risk point but no fault has occurred, the risk point can be located. When a fault occurs, the fault location can be quickly located, helping on-site maintenance personnel to quickly repair it, reducing the downtime rate of the target device, improving the efficiency of the target device, assisting on-site personnel in diagnosis and decision-making, improving the efficiency of personnel and target equipment, and improving the intelligence level of the industrial site.

[0058] In one embodiment, determining the fault location result according to the real-time torque curve includes:

[0059] The real-time torque curve is divided according to the time window, and the abnormal boundary of the real-time torque curve is obtained according to the divided real-time torque curve;

[0060] Determine the fault location result of the target device based on the abnormal boundary.

[0061] In an embodiment of the present application, the real-time torque curve is first divided according to a time window, and the abnormal boundary of the real-time torque curve is obtained based on the divided real-time torque curve. Then, the fault location result of the target device is determined based on the abnormal boundary. In this embodiment, the real-time torque curve is divided according to the time window, and the abnormal boundary of the real-time torque curve is determined based on the divided real-time torque curve. The accuracy of the abnormal boundary of the real-time torque curve is improved by dividing the real-time torque curve. In addition, the fault location of the target device is performed based on the abnormal torque point, and the position of the target device at the time of abnormal torque is determined to locate the risk point or fault location. By locating the fault of the target device, industrial field maintenance personnel can quickly find the fault problem of the target device, thereby improving the work efficiency of target device maintenance.

[0062] In one embodiment, the abnormal boundary includes an upper abnormal boundary and a lower abnormal boundary; obtaining the abnormal boundary of the real-time torque curve according to the divided real-time torque curve includes:

[0063] Obtain the first quarter torque value and the second quarter torque value in the real-time torque curve;

[0064] determining an interquartile range value based on the first quartile torque value and the second quartile torque value;

[0065] An upper abnormal boundary is determined based on the first quartile torque values ​​and the interquartile range values; and a lower abnormal boundary is determined based on the second quartile torque values ​​and the interquartile range values.

[0066] In an embodiment of the present application, the first and second quartile torque values ​​in the real-time torque curve are obtained, and the interquartile range value is determined based on the first and second quartile torque values. Then, the upper abnormal boundary is determined based on the first quartile torque value and the interquartile range value; and the lower abnormal boundary is determined based on the second quartile torque value and the interquartile range value. In this embodiment, the upper and lower abnormal boundaries of the real-time torque curve are determined by the interquartile range method. The interquartile range method can truly and intuitively show the true appearance of the data distribution, is relatively objective in identifying abnormal values, and has high accuracy, thereby improving the accuracy of the fault location of the target equipment. Furthermore, by establishing the upper and lower envelope curves of the real-time torque curve, the method facilitates the subsequent positioning of the abnormal torque point where the real-time torque curve exceeds the envelope curve, thereby locating the location where risks or faults may occur, thereby performing necessary inspections and maintenance on the equipment.

[0067] In one embodiment, the abnormal boundary includes an upper abnormal boundary and a lower abnormal boundary; obtaining the abnormal boundary of the real-time torque curve according to the divided real-time torque curve includes:

[0068] According to the torque values ​​of each time window in the real-time torque curve, the torque mean and torque standard deviation of the real-time torque curve are obtained; the torque standard deviation is the torque standard deviation of the local time window or the torque standard deviation of the global real-time torque curve;

[0069] The upper and lower anomaly boundaries are determined based on the torque mean and torque standard deviation.

[0070] In this embodiment of the present application, the torque mean and standard deviation of the real-time torque curve are first obtained based on the torque values ​​in each time window of the real-time torque curve. The standard deviation is the torque standard deviation of the local time window or the torque standard deviation of the global real-time torque curve. The upper and lower abnormal boundaries are then determined based on the torque mean and standard deviation. In this embodiment, the torque standard deviation is used as the limiting error to determine the upper and lower abnormal boundaries of the real-time torque curve, improving the accuracy of the upper and lower abnormal boundaries and thus significantly increasing the accuracy of locating the target equipment fault.

[0071] In one embodiment, the abnormal boundary includes an upper abnormal boundary and a lower abnormal boundary; obtaining the abnormal boundary of the real-time torque curve according to the divided real-time torque curve includes:

[0072] Obtain the maximum torque value, minimum torque value and global torque standard deviation in each time window of the real-time torque curve;

[0073] Determine the upper anomaly boundary based on the maximum torque value and the global torque standard deviation;

[0074] The lower anomaly boundary is determined based on the minimum torque value and the global torque standard deviation.

[0075] In this embodiment of the present application, the maximum torque value, minimum torque value, and global torque standard deviation are obtained for each time window of the real-time torque curve. The upper abnormal boundary is determined based on the maximum torque value and the global torque standard deviation, and the lower abnormal boundary is determined based on the minimum torque value and the global torque standard deviation. In this embodiment, the abnormal boundary of the real-time torque curve is determined based on the maximum and minimum torque values ​​of each time window and the global standard deviation. This allows for local calculations while also taking into account the torque values ​​within the global scope, thereby avoiding the accuracy of the abnormal boundaries of the local time window and improving the accuracy of the upper and lower boundaries of the real-time torque curve.

[0076] In one embodiment, determining a fault location result of a target device based on an abnormal boundary includes:

[0077] Obtaining abnormal torque points outside the abnormal boundary in the real-time torque curve;

[0078] Determine the fault location result of the target equipment based on the abnormal torque point.

[0079] In this embodiment, abnormal torque points outside the abnormal boundaries of the real-time torque curve are obtained, and the fault location results of the target device are determined based on the abnormal torque points. In this embodiment, real-time abnormal torque point diagnosis is performed based on the upper and lower abnormal boundaries of the real-time torque curve, which can quickly determine the abnormal torque points and help maintenance personnel quickly locate the fault problem of the target device.

[0080] In one embodiment, determining a fault location result of a target device based on an abnormal torque point includes:

[0081] Obtain the real-time position signal of the target device within the current working cycle;

[0082] Based on the corresponding relationship between the torque value and the time in the real-time torque signal, and the corresponding relationship between the position and the time in the real-time position signal, the position corresponding to the abnormal torque point is determined;

[0083] The position corresponding to the abnormal torque point is determined as the fault position of the target equipment.

[0084] In an embodiment of the present application, a real-time position signal of a target device within a current working cycle is obtained, and based on the correspondence between the torque value and the time in the real-time torque signal, and the correspondence between the position and the time in the real-time position signal, the position corresponding to the abnormal torque point is determined, and then the position corresponding to the abnormal torque point is determined as the fault position of the target device. In this embodiment, based on the correspondence between the torque value and the time in the real-time torque signal, and the correspondence between the position and the time in the real-time position signal, the potential risk point or fault location of the target device is located according to the time when the real-time torque curve of the target device exceeds the abnormal boundary, thereby assisting in the rapid implementation of maintenance, saving time for repairing the target device, and improving the repair efficiency of the target device. In one embodiment, obtaining a real-time torque signal within the current working cycle of the target device includes:

[0085] According to a preset sampling period, the real-time torque signal of the target device in the current working cycle is collected from the controller of the motor drive system of the target device.

[0086] In an embodiment of the present application, a real-time torque signal of the target device within the current working cycle is collected from the controller of the motor drive system of the target device through a preset sampling period. By collecting the real-time torque signal through the sampling period, the real-time and accuracy of the torque signal are improved, thereby improving the real-time and accuracy of the status monitoring results of the target device.

[0087] In a second aspect, the present application further provides an equipment status monitoring device, the device comprising:

[0088] An acquisition module is used to acquire a real-time torque signal of a target device during a current working cycle; the real-time torque signal during the current working cycle is acquired through a built-in sensor of the target device;

[0089] The monitoring module is used to determine the status monitoring result of the target equipment based on the real-time torque signal within the current working cycle.

[0090] In a third aspect, an embodiment of the present application provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method provided in any embodiment of the first aspect when executing the computer program.

[0091] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method provided in any embodiment of the first aspect above.

[0092] In a fifth aspect, an embodiment of the present application further provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the method provided in any embodiment of the first aspect above.

[0093] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0094] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiment below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present application. The same reference numerals are used throughout the drawings to represent the same components. In the drawings:

[0095] FIG1 is a diagram illustrating an application environment of a device status monitoring method according to an embodiment;

[0096] FIG2 is a schematic flow chart of a method for monitoring device status in one embodiment;

[0097] FIG3 is a schematic flow chart of a device status monitoring method according to another embodiment;

[0098] FIG4 is a schematic flow chart of a method for monitoring device status in another embodiment;

[0099] FIG5 is a schematic flow chart of a device status monitoring method according to another embodiment;

[0100] FIG6 is a schematic diagram of a curve of a historical operating condition signal in one embodiment;

[0101] FIG7 is a schematic diagram of a curve of a historical torque signal in one embodiment;

[0102] FIG8 is a schematic diagram of operating condition segmentation of historical operating condition signals and historical torque signals in one embodiment;

[0103] FIG9 is a schematic diagram of historical torque curves for multiple cycles in one embodiment;

[0104] FIG10 is a schematic flow chart of a method for monitoring device status in another embodiment;

[0105] FIG11 is a schematic flow chart of a method for monitoring device status in another embodiment;

[0106] FIG12a is a schematic diagram of historical torque curves of multiple cycles in another embodiment;

[0107] FIG12 b is a schematic diagram of historical torque curves of multiple cycles in another embodiment;

[0108] FIG12c is a schematic diagram of historical torque curves of multiple cycles in another embodiment;

[0109] FIG13 is a scatter diagram of a standard torque curve of a device status monitoring method according to an embodiment;

[0110] FIG14 is a schematic flow chart of a device status monitoring method according to another embodiment;

[0111] FIG15 is a scatter diagram of a standard torque curve and a real-time torque signal in one embodiment;

[0112] FIG16 is a schematic flow chart of a method for monitoring device status in another embodiment;

[0113] FIG17 is a schematic flow chart of a method for monitoring device status in another embodiment;

[0114] FIG18 is a flow chart of a method for monitoring device status in another embodiment;

[0115] FIG19 is a schematic flow chart of a method for monitoring device status in another embodiment;

[0116] FIG20 is a diagram showing a device performance degradation trend of a device status monitoring method according to an embodiment;

[0117] FIG21 is a flow chart of a method for monitoring device status in another embodiment;

[0118] FIG22 is a schematic flow chart of a device status monitoring method according to another embodiment;

[0119] FIG23 is a flow chart of a method for monitoring device status in another embodiment;

[0120] FIG24 is a schematic flow chart of a method for monitoring device status in another embodiment;

[0121] FIG25 is a schematic diagram of an abnormal boundary of a real-time torque curve according to an embodiment;

[0122] FIG26 is a schematic flow chart of a device status monitoring method according to another embodiment;

[0123] FIG27 a is a schematic diagram of an abnormal boundary of a real-time torque curve in another embodiment;

[0124] FIG27 b is a schematic diagram of an abnormal boundary of a real-time torque curve in another embodiment;

[0125] FIG28 is a schematic flow chart of a device status monitoring method according to another embodiment;

[0126] FIG29 a is a schematic diagram of the boundaries of a real-time torque curve according to one embodiment;

[0127] FIG29 b is a schematic diagram of an abnormal boundary of a real-time torque curve in another embodiment;

[0128] FIG29c is a schematic diagram of an abnormal boundary of a real-time torque curve according to another embodiment;

[0129] FIG30 is a schematic flow chart of a device status monitoring method according to another embodiment;

[0130] FIG31 is a schematic diagram of a curve of a real-time position signal according to an embodiment;

[0131] FIG32 a is a schematic diagram of an abnormal boundary of a real-time torque curve according to another embodiment;

[0132] FIG32 b is a schematic diagram of an abnormal boundary of a real-time torque curve according to another embodiment;

[0133] FIG32c is a schematic diagram of an abnormal boundary of a real-time torque curve according to another embodiment;

[0134] FIG33 is a flow chart of a method for monitoring device status in another embodiment;

[0135] FIG34 is a block diagram of a device status monitoring apparatus according to an embodiment;

[0136] FIG35 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0137] The following embodiments of the technical solution of the present application will be described in detail with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present application and are therefore only examples and are not intended to limit the scope of protection of the present application.

[0138] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned figure descriptions are intended to cover non-exclusive inclusions.

[0139] In the description of the embodiments of the present application, the technical terms "first" and "second" are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "multiple" is more than two, unless otherwise clearly and specifically defined. Mentioning "embodiments" in this article means that the specific features, structures or characteristics described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments. In the description of the embodiments of the present application, the term "multiple" refers to more than two (including two).

[0140] In related technologies, motors are important power and auxiliary equipment for industrial production equipment. Each motor corresponds to a motor drive system. For example, the hot press in the hot pressing process of lithium-ion batteries, the coating machine in the coating process of lithium-ion battery packs, etc., all of these devices cannot work without the motor drive system. Taking the hot press in the hot pressing process of lithium-ion batteries as an example, when the hot press is working, the motor drives the gears and screws to transmit pressure to the upper and lower heating plates, applying pressure to the bare battery cells while conducting heat, which can eliminate the stress of the pole pieces and diaphragms. The pressure is maintained for a period of time so that the bare battery cells reach the specified physical thickness, ensuring the stability of the battery cell's external dimensions and facilitating the bare battery cells to be placed in the shell, thereby increasing the consistency and energy density of the bare battery cells.

[0141] Therefore, effectively monitoring the operating status of industrial production equipment such as hot presses and coating machines is crucial for ensuring production stability. Related technologies typically use vibration sensors attached to these equipment to collect vibration signals, then process and extract features to determine the equipment's operating status.

[0142] However, the above-mentioned method of extracting features through collected vibration signals may, on the one hand, fail to represent all the information of the data itself well due to the small number of extracted features or lack of typicality, and miss key information, resulting in low accuracy of equipment status monitoring. On the other hand, even if the extracted features are sufficient or typical enough, the large number of extracted features may cause different features to contain the same information, which may cause problems such as information redundancy and lead to low efficiency of status monitoring. In addition, the above-mentioned additional sensors on industrial production equipment are also costly, and the additional vibration sensors themselves may interfere with some signals in the equipment, affecting the working performance of the equipment. Furthermore, the production site environment of some industrial production equipment is harsh, such as small space, messy instruments or connecting wires, etc., which makes the industrial production equipment itself not suitable for additional sensors, and it is impossible to use the above-mentioned method to monitor the equipment status.

[0143] Furthermore, due to production needs, industrial production site equipment is frequently replaced, and status monitoring of the same production equipment under different production modes is not applicable. Or even if it is applicable, parameters need to be readjusted to adapt to the new production mode in order to perform status monitoring of the production equipment under the new production mode. The whole process is relatively complicated.

[0144] Based on the above considerations, in order to effectively monitor the status of industrial production equipment, the embodiment of the present application proposes a device status monitoring method, which obtains the real-time torque signal collected by the built-in sensor of the motor drive system in the target device, and then analyzes the torque signal collected by the built-in sensor of the target device to determine the status monitoring result of the device. In this way, the real-time torque signal is collected by the built-in sensor of the target device. The built-in sensor is integrated on the target device, which is equivalent to the real-time torque signal collected by the built-in sensor. It can more realistically and more closely reflect the torque signal characteristics of the motor drive system of the target device, thereby ensuring the accuracy of the collected real-time torque signal. In this way, directly analyzing the real-time torque signal can greatly increase the accuracy of the target device status monitoring result.

[0145] It should be understood that the technical effects that can be achieved by the equipment status monitoring method provided in the embodiments of the present application are not limited to this, and other technical effects can also be achieved. For example, there is no need to add additional sensors to the target equipment, which can reduce costs and overcome the inconvenience of installing external sensors to a certain extent. Moreover, even if there is a change in equipment at the industrial production site, there is no need to readjust the parameters of the equipment status monitoring method, which is suitable for different production modes and improves applicability.

[0146] It should be noted that the equipment status monitoring solution provided in this application is applicable to all industrial production equipment that uses a motor drive system, and is not limited to the battery field mentioned above. It is also applicable to industrial production equipment in other fields, and this is not limited in the embodiments of this application.

[0147] The device status monitoring method provided in the embodiment of the present application can be applied to the application environment shown in Figure 1. Among them, the target device 102 is connected to the computer device 104, and the two can communicate with each other, for example, wired communication, wireless communication, etc. Among them, the target device generally refers to any kind of equipment, for example, industrial production equipment in various fields such as the battery field, the electric vehicle field, etc., or other equipment that requires the use of motors. The embodiment of the present application does not limit the specific device to which the target device refers. Among them, computer devices include but are not limited to smart terminals, personal computers, workbenches, processors, wearable smart devices, laptops, and even servers. The specific type of computer devices in the embodiment of the present application is not limited.

[0148] The following describes the device status monitoring method provided in the embodiments of the present application.

[0149] In one embodiment, as shown in FIG2 , a device status monitoring method is provided. The method is described by applying it to the application environment shown in FIG1 . The embodiment includes the following steps:

[0150] S201, obtaining a real-time torque signal of a target device in a current working cycle.

[0151] The target device generally refers to a device driven by at least one motor drive system.

[0152] The real-time torque signal during the current working cycle can be collected by the target device's built-in sensors. In practical applications, when the target device is operating, the motor in its motor drive system, under the control of the controller, transmits power to the load through transmission mechanisms such as gears, screws, and couplings. Simultaneously, information about the motion state of the load and transmission mechanism, as well as motor operation signals acquired by the target device's built-in sensors and sensing capabilities, are fed back to the controller for storage.

[0153] Among them, the built-in sensors include but are not limited to current sensors, torque sensors, position sensors, etc. Correspondingly, the motor operation signals collected by these built-in sensors include the motor's current, torque, position and working condition signals, among which the time accuracy of the current signal, torque signal, position signal and working condition signal can all be in the millisecond level. Among them, the current signal refers to the current of the motor in the target device, the torque signal refers to the parameter of the torsional torque of the motor in the target device, which can reflect the motion characteristics of the motor in the target device, the position signal indicates the driving position of the motor in the target device; the working condition signal indicates the working condition of the motor in the target device. For example, the torque signal of the motor is collected by the built-in torque sensor, the position signal of the motor is collected by the built-in position sensor, and the position signal of the motor is collected by the built-in position sensor.

[0154] Typically, motor drive systems operate according to different duty cycles. A duty cycle refers to the period from the start to the end of a specific operation of a target device during an industrial production process. Therefore, the current duty cycle refers to the current duty cycle of the target device during its current operation.

[0155] Based on this, when the state of the target device is monitored in real time, the real-time torque signal of the target device in the current working cycle can be obtained.

[0156] In one embodiment, the method for obtaining the real-time torque signal of the target device in the current working cycle period can be to obtain the real-time torque signal in the current working cycle period from the controller of the motor drive system of the target device. The torque signal in the controller is collected by the target device's own sensor and the real-time torque signal is fed back to the controller.

[0157] In another embodiment, the real-time torque signal of the target device in the current working cycle can be obtained by receiving the signal transmitted by a third-party device or downloading the signal from a specific database.

[0158] In yet another embodiment, the real-time torque signal may also be a simulated torque signal simulated based on empirical values.

[0159] The embodiment of the present application is not limited to the method of obtaining the real-time torque signal of the target device within the current working cycle.

[0160] When acquiring the real-time torque signal of the target device in the current working cycle, different acquisition methods can be used.

[0161] In one embodiment, the acquisition method may be to acquire the real-time torque signal of the target device in the current working cycle from the controller of the motor drive system of the target device according to a preset sampling period.

[0162] For example, the sampling period may be 30ms, 40ms, 50ms, etc. The above are only examples. In actual applications, the specific sampling period may be determined according to actual conditions.

[0163] It is understandable that the sampling period is less than one working cycle. Therefore, in actual applications, the computer device can collect the above-mentioned real-time torque signal from the controller multiple times through a preset sampling period until a cycle is collected to obtain the real-time torque signal of the target device in the current working cycle.

[0164] In another embodiment, the acquisition method may be to acquire the real-time torque signal of the target device during the current working cycle from the controller via a received acquisition instruction. Specifically, only after receiving the acquisition instruction does the computer device execute an acquisition instruction to the controller, instructing the controller to provide feedback on the real-time torque signal of the target device during the current working cycle.

[0165] Another collection method is that the real-time torque signal collected by the target device's built-in sensor is fed back to the controller. After receiving the real-time torque signal within the current cycle, the controller immediately sends the real-time torque signal of the target device within the current cycle to the computer device.

[0166] It should be noted that the state monitoring result of the target device is determined by collecting the real-time torque signal within the current working cycle through the sensor provided by the target device. Since the built-in sensor is integrated on the target device, it can truly and more closely reflect the operating status of the target device, that is, the built-in sensor can collect the real operating status data of the target device. In this way, by collecting the real-time torque signal through the built-in sensor, the accuracy of the collected real-time torque signal can be higher, thereby greatly increasing the accuracy of the target device state monitoring result.

[0167] S202: Determine a status monitoring result of the target device based on the real-time torque signal in the current working cycle.

[0168] Based on the real-time torque signal obtained above, the target device's status monitoring result can be determined by analyzing the real-time torque signal. The target device's status monitoring result includes one or more of whether the target device requires maintenance, whether a fault exists, or the location of the fault.

[0169] For example, if the condition monitoring result indicates whether the target equipment requires maintenance, the need for maintenance can be called a predictive maintenance result. That is, compared to scheduled maintenance, predictive maintenance does not require scheduled maintenance, but rather predicts when maintenance is currently needed. For example, if the predictive maintenance result for the target equipment indicates that maintenance is required, maintenance personnel can be immediately notified to perform maintenance on the target equipment in a timely manner. If the predictive maintenance result for the target equipment indicates that maintenance is not required, condition monitoring will continue for the next working cycle of the target equipment.

[0170] Taking the status monitoring result as whether the target device has a fault as an example, if the status monitoring result of the target device is that the target device has a fault, the fault location of the target device can be further determined; if the status monitoring result of the target device is that the target device does not have a fault, the status monitoring of the next working cycle of the target device will continue.

[0171] It is understandable that the status monitoring results of the target equipment determined in the embodiments of the present application may be predictive maintenance results and fault location results, or may be predictive maintenance results or fault location results, and the embodiments of the present application do not limit this.

[0172] For example, when determining the status monitoring result of the target device based on the real-time torque signal, the real-time torque signal within the current working cycle may be analyzed using a preset monitoring model.

[0173] This monitoring model is a pre-trained model specifically used to determine the equipment status monitoring results. When applied, the real-time torque signal within the current working cycle is used as the input of the monitoring model. The real-time torque signal is analyzed by the monitoring model to output the status monitoring results of the target equipment.

[0174] Another way to determine the status monitoring result of the target device based on the real-time torque signal is to extract the change characteristics of the real-time torque signal within the current working cycle of the target device, and judge whether the change of the real-time torque signal conforms to the change law of the torque signal through the extracted characteristics, thereby determining the status monitoring result of the target device.

[0175] The device status monitoring method provided in the embodiment of the present application obtains the real-time torque signal of the target device during the current working cycle, and determines the status monitoring result of the target device based on the real-time torque signal during the current working cycle. In this method, the real-time torque signal is the torque signal during the current working cycle, which is equivalent to the real-time torque signal collected during a complete working cycle. The real-time torque signal during a complete working cycle can fully reflect the status of the target device. In this way, by analyzing the real-time torque signal during a complete working cycle, the accuracy of the target device status monitoring result can be increased. Furthermore, the status monitoring of the target device can be achieved directly by obtaining the real-time torque signal collected by the sensor of the target device. In this way, even if the production mode of the target device is adjusted at the industrial site, it is not necessary to readjust the parameters to be applicable, thereby improving the scenario applicability of the device status monitoring and meeting the need to quickly adapt to the frequent changes in production modes in production.

[0176] The above-mentioned condition monitoring results include predictive maintenance results and / or fault location results of the target equipment; the following describes, through specific embodiments, a process of determining the predictive maintenance results and / or fault location results of the target equipment based on the real-time torque signal within the current working cycle.

[0177] In one embodiment, as shown in FIG3 , determining the state monitoring result of the target device based on the real-time torque signal within the current working cycle includes the following steps:

[0178] S301, obtaining a standard torque curve of a target device.

[0179] The standard torque curve can be the most ideal torque curve when the target device is working normally. Therefore, by comparing and analyzing the standard torque curve and the real-time torque signal and using the standard torque curve as the judgment basis, the status monitoring result of the target device can be determined effectively, quickly and accurately.

[0180] Typically, when a target device is initially put into operation, its condition is relatively good, and the torque data obtained is relatively good, capable of representing the target device's normal operating condition. Therefore, a standard torque curve for the target device can be obtained by obtaining historical torque data from the target device during its initial operation, extracting relatively good torque values ​​from the historical torque data, filtering out relatively poor torque values, and fitting the filtered torque data to obtain the standard torque curve for the target device.

[0181] Optionally, the standard torque curve of the target device can also be obtained directly from the standard torque curves of different devices pre-stored in a database, that is, the database pre-stores standard torque curves of various types of devices. When the standard torque curve of the target device needs to be obtained, the standard torque curve of the device of the same type as the target device can be extracted from the database.

[0182] S302 : Determine a predictive maintenance result based on the real-time torque signal and the standard torque curve within the current working cycle.

[0183] Since the standard torque curve can characterize the torque state of the target equipment during normal operation, the real-time torque signal in the current working cycle can be compared with the standard torque curve to determine the error of the real-time torque signal relative to the standard torque curve, thereby determining the predictive maintenance result of the target equipment.

[0184] For example, if the changing pattern of the real-time torque signal is inconsistent with the changing pattern of the standard torque curve, and the error between the changing pattern of the real-time torque signal and the standard torque curve is large, it is determined that the real-time torque signal of the target device in the current working cycle is abnormal. Then, the predictive maintenance result of the target device is that the target device needs maintenance in the current working cycle.

[0185] The equipment status monitoring method provided in the embodiment of the present application first obtains the standard torque curve of the target equipment, and then determines the predictive maintenance result based on the real-time torque signal and the standard torque curve within the current working cycle. In this method, the standard torque curve and the real-time torque signal of the target equipment are used. Since the standard torque curve corresponds to the standard torque value of the target equipment, by measuring the degree of deviation between the real-time torque signal and the standard torque curve, predictive maintenance can be performed on the target equipment, and the predictive maintenance result of the target equipment can be determined to guide the maintenance work at the industrial site. In this way, maintenance is only performed when it is needed, which saves the labor cost of multiple times when maintenance is not required compared to scheduled maintenance. In addition, predictive maintenance of the target equipment can determine the long-term degradation trend of the target equipment, which can be used to optimize the subsequent maintenance strategy of the target equipment and predict the service life of the target equipment.

[0186] In one embodiment, as shown in FIG4 , the process of obtaining the standard torque curve of the target device includes the following steps:

[0187] S401 : Acquire historical operating condition signals and historical torque signals of the target device according to historical operating status information of the target device.

[0188] The historical operating status information of the target device is the operating status information of the target device at a historical time, and the operating status information includes a working condition signal, a torque signal, and a position signal of the target device.

[0189] Therefore, the historical operating condition signal and historical torque signal of the target device can be directly obtained from the database that stores the historical operating status information of the target device; wherein, the time of the historical operating condition signal and the historical torque signal corresponds to each other. For example, if the historical operating condition signal is the operating condition data of the target device in time period C, then the historical torque signal should also be the torque data of the target device in time period C.

[0190] Optionally, the historical torque signal may be a torque signal of the target device in a plurality of historical cycle periods.

[0191] S402 : Generate a standard torque curve of the target device according to historical operating condition signals and historical torque signals.

[0192] Because the historical torque signal represents torque signals from multiple historical cycles, there are time discontinuities between adjacent cycles, i.e., there is a time gap between the end of one cycle and the start of the next. Therefore, the historical torque signal of the target device during operation can be obtained from the historical operating condition signal to construct a standard torque curve for the target device.

[0193] In one embodiment, the standard torque curve of the target device may be constructed by using a preset construction algorithm, taking historical operating condition signals and historical torque signals as inputs of the construction algorithm, and obtaining the standard torque curve of the target device by running the construction algorithm.

[0194] In another embodiment, the method for constructing the standard torque curve of the target device may also be as shown in FIG5 , where the standard torque curve of the target device is generated based on the historical operating condition signal and the historical torque signal, including the following steps:

[0195] S501 , performing working condition segmentation on a historical torque signal according to a historical working condition signal to obtain historical torque signals within a plurality of historical cycle periods.

[0196] Since the historical torque signal is a signal collected by the target device at a historical time and includes multiple historical cycles, it is necessary to time-align the multiple historical cycles in the historical torque signal.

[0197] Before time-aligning the historical torque signals of multiple historical cycles, the historical torque signals need to be divided into working conditions.

[0198] Since the working condition signal is a time-series working condition signal, it can reflect the corresponding relationship between the operation of the equipment and time, and the torque signal is also a time-series torque signal, it can reflect the corresponding relationship between the torque value of the equipment and time. Therefore, the historical torque signal can be divided into working conditions according to the working time of the historical working condition signal.

[0199] Optionally, the working condition segmentation method may be to extract the historical torque signal corresponding to the working time in the historical working condition signal according to the historical working condition signal, and obtain the historical torque signal within a plurality of historical cycle periods.

[0200] As shown in Figures 6-8, Figure 6 is a curve diagram of the historical operating condition signal of the target device, where the operating condition signal is Boolean type data, 1 indicates that the target device is working, and 0 indicates that the target device is not working; Figure 7 is a curve diagram of the historical torque signal of the target device, where the torque signal is floating-point data; Figure 8 is the operating condition segmentation result of performing operating condition segmentation on the historical torque signal based on the historical operating condition signal.

[0201] S502 , time-aligning historical torque signals within a plurality of historical cycles according to the start time of the historical operating condition signal to obtain a historical torque curve consisting of the plurality of historical cycles.

[0202] Among them, the method of time-aligning the historical torque signals within multiple historical cycle periods can be to subtract the start time of the historical operating condition signal from the timing time of the historical torque signal of each historical cycle period in sequence, so that the torque data of different historical cycle periods are aligned in time, and a historical distortion curve composed of multiple historical cycle periods is obtained, as shown in Figure 9, which is a historical torque curve composed of 3000 historical cycle periods.

[0203] S503: Generate a standard torque curve of the target device based on the historical torque curve.

[0204] Since the historical torque curve is the torque curve of the target device during normal operation, the historical torque curve can be directly determined as the standard torque curve of the target device.

[0205] In an embodiment of the present application, the historical torque signal is segmented according to the historical operating condition signal to obtain historical torque signals within multiple historical cycles. The historical torque signals within the multiple historical cycles are then time-aligned according to the start time of the historical operating condition signal to obtain a historical torque curve consisting of the multiple historical cycles. A standard torque curve for the target device is generated based on the historical torque curve. In this embodiment, the historical torque signal is segmented according to the historical operating condition signal, and the start time of the operating condition signal is used as a reference to time-align the historical torque signals within the multiple historical cycles. This makes the historical torque signals within the multiple historical cycles relatively uniform, improves the accuracy of the standard torque curve, and thus improves the accuracy of the target device status monitoring results.

[0206] The device status monitoring method provided in an embodiment of the present application first obtains historical operating condition signals and historical torque signals of the target device based on historical operating status information of the target device. Based on these historical operating condition signals and historical torque signals, a standard torque curve for the target device is generated. In this method, since the operating condition signals reflect the operating conditions of the target device, the historical torque signals are segmented by operating condition using the historical operating condition signals as a reference to obtain the standard torque curve for the target device, thereby improving the accuracy of the standard torque curve.

[0207] The specific process of generating the standard torque curve of the target device based on the historical torque curve in the above embodiment is described below through an embodiment. In one embodiment, as shown in FIG10 , the process of generating the standard torque curve of the target device based on the historical torque curve includes the following steps:

[0208] S1001 , performing rasterization processing on a historical torque curve according to a preset time window to obtain a plurality of grids.

[0209] In order to meet the accuracy requirements while taking into account the real-time performance of condition monitoring, a smaller time window can be selected and the historical torque curve can be rasterized according to the smaller time window to obtain multiple grids, where one grid corresponds to one time window.

[0210] For example, taking 3 ms as a time window, the historical torque curve is rasterized to obtain multiple grids.

[0211] S1002, obtaining the standard torque value at the middle moment of each grid.

[0212] The standard torque value is a value reflecting the torque characteristics within a grid. The standard torque value of the grid is determined as the standard torque value at the middle moment of the grid. One grid corresponds to one standard torque value.

[0213] In one embodiment, the standard torque value at the middle moment of each grid may be obtained by obtaining the median torque at the middle moment of each grid and using the median torque of each grid as the standard torque value at the middle time of each grid.

[0214] In another embodiment, as shown in FIG11 , the process of obtaining the standard torque value at the intermediate moment of each grid includes the following steps:

[0215] S1101, obtaining the torque mean of each grid.

[0216] S1102: Determine the average torque value of each grid as the standard torque value at the middle moment of the corresponding grid.

[0217] After rasterizing the historical torque curve to generate multiple grids, the mean value of each grid can be obtained. This mean value is then used as the standard torque value at the midpoint of the grid. For example, if 0 to 3 ms is used as a grid, the mean value of the 0 to 3 ms grid corresponds to the midpoint of the 0 to 3 ms grid, 1.5 ms.

[0218] In this embodiment of the present application, the mean torque value of each grid is obtained and determined as the standard torque value at the midpoint of the corresponding grid. In this embodiment, since the mean value can reflect the trend of a set of data, by using the mean torque value of each grid as the standard torque value at the midpoint of the corresponding grid, the grid's mean torque value is used to represent the standard torque value of that grid, thereby improving the accuracy of the standard torque curve and thus improving the accuracy of the target equipment status monitoring results.

[0219] It should be noted that the method for obtaining the standard torque value at the intermediate moment of each grid is not limited, and any method that can reflect the characteristics of the grid torque value can be used as the method for obtaining the standard torque value at the intermediate moment of each grid.

[0220] S1003: Construct a standard torque curve of the target device according to the standard torque value at the middle moment of each grid.

[0221] The standard torque curve of the target device is constructed by the standard torque value at the middle moment of each grid and the middle moment of each grid.

[0222] As shown in Figure 12a, Figure 12a is a historical torque curve of multiple historical cycle periods after rasterization, Figure 12b is a schematic diagram of the torque curve corresponding to Figure 12a from 0 to 1600ms, and Figure 12c is a schematic diagram of the torque curve corresponding to Figure 12b from 300ms to 500ms. Figure 12c includes multiple grids of 3ms time windows.

[0223] Alternatively, a 3ms time window is used as a grid, and the standard torque time series corresponding to the standard torque value at the middle moment of each grid is determined based on the standard torque value at the middle moment of each grid. Then, the standard torque curve of the target device is constructed using the standard torque time series, as shown in FIG13 , which is a scatter plot of the standard torque curve. The standard torque time series corresponding to the standard torque value at the middle moment of each grid can be:

[0224] {0ms:-0.52, 3ms: 0.11, 6ms: 0.30,…, 21000ms: 31.77,…, 39477ms: 34.74}

[0225] The device status monitoring method provided in an embodiment of the present application first rasterizes a historical torque curve according to a preset time window to obtain multiple grids. The method then obtains the standard torque value at the midpoint of each grid, and constructs a standard torque curve for the target device based on the standard torque value at the midpoint of each grid. In this method, the historical torque curve is rasterized and the standard torque curve is determined using the standard torque value at the midpoint of each grid. Because the standard torque value at the midpoint of each grid can represent the torque characteristics of each grid, the accuracy of the standard torque curve is increased, thereby increasing the accuracy of the target device status monitoring results.

[0226] Based on the standard torque curve obtained above, the specific process of determining the predictive maintenance result of the target equipment is described below through an embodiment. In one embodiment, as shown in FIG14 , the process of determining the predictive maintenance result based on the real-time torque signal and the standard torque curve within the current working cycle includes the following steps:

[0227] S1401 , the real-time torque signal in the current working cycle is matched with the standard torque curve at each moment to obtain the standard torque value corresponding to the real-time torque value at each moment in the real-time torque signal.

[0228] The real-time torque signal and the standard torque curve are aligned at all times to obtain a scatter plot of the standard torque curve and the real-time torque signal, as shown in FIG15 .

[0229] From the standard torque curve, the standard torque value corresponding to the real-time torque value at each moment in the real-time torque signal is obtained. The method can be that, for any real-time torque value, the moment of the real-time torque value is obtained, and the standard torque value corresponding to the moment in the standard torque curve is determined as the standard torque value corresponding to the real-time torque value in the real-time torque signal.

[0230] Among them, the standard torque curve corresponds to a time torque sequence. If the time torque sequence of the standard torque curve is {0ms:-0.52, 3ms:0.11, 6ms:0.30,..., 21000ms:31.77,..., 39477ms:34.74}, then the standard torque value corresponding to the real-time torque value at each moment in the real-time torque signal is obtained according to the time torque sequence.

[0231] For example, if a real-time torque value in the real-time torque signal occurs at 29ms, the standard torque value corresponding to the real-time torque value at 29ms can be obtained based on the closest time principle. That is, since 29ms is closest to 30ms in the time-torque sequence of the standard torque curve, the standard torque value corresponding to the standard torque curve at 30ms is determined as the standard torque value corresponding to the real-time torque value at 29ms in the real-time torque signal. The closest time principle requires that a time in the real-time torque signal corresponds to a time in the standard torque curve that is closest to the time in the real-time torque signal.

[0232] In the same manner as above, the real-time torque signal in the current working cycle is matched with the standard torque curve at each moment to obtain the standard torque value corresponding to the real-time torque value at each moment in the real-time torque signal.

[0233] Among them, the method for obtaining the real-time torque signal of the target device in the current working cycle period can be to obtain the torque signal and working condition signal of the target device through a preset sampling period, and then perform working condition segmentation on the torque signal according to the working condition signal to obtain a real-time torque signal of a working cycle period. The real-time torque signal of the working cycle period is the real-time torque signal of the target device in the current working cycle period.

[0234] S1402 : Determine a predictive maintenance result of the target equipment based on a standard torque value corresponding to the real-time torque value at each moment in the real-time torque signal.

[0235] In one embodiment, a method for determining a predictive maintenance result of a target device may be to compare the real-time torque value at each moment in the real-time torque signal with its corresponding standard torque value. If the absolute value of the difference between the real-time torque value and its corresponding standard torque value is greater than a preset maintenance threshold, it is determined that the target device requires maintenance at the corresponding moment; wherein the maintenance threshold may be determined through historical experience.

[0236] The equipment condition monitoring method provided in an embodiment of the present application obtains the standard torque value corresponding to the real-time torque value at each moment in the real-time torque signal by moment-by-moment matching the real-time torque signal within the current working cycle with the standard torque curve. Based on the standard torque value corresponding to each moment in the real-time torque signal, the predictive maintenance result for the target equipment is determined. In this method, by moment-by-moment matching the real-time torque signal within the current working cycle with the standard torque curve, the accuracy of the standard torque value corresponding to each moment in the real-time torque signal is improved, thereby increasing the accuracy of the predictive maintenance result for the target equipment.

[0237] The following describes a specific embodiment of the process of determining the predictive maintenance result of the target equipment based on the standard torque value corresponding to the real-time torque value at each moment in the real-time torque signal.

[0238] In one embodiment, as shown in FIG16 , determining a predictive maintenance result of a target device based on a standard torque value corresponding to a real-time torque value at each moment in a real-time torque signal includes:

[0239] S1601, determining the health value of the target device in the current working cycle based on the real-time torque value at each moment in the real-time torque signal, the standard torque value corresponding to the real-time torque value at each moment, and the number of real-time torque values ​​in the current working cycle.

[0240] The calculation formula of the health value of the target device in the current working cycle is shown in formula (1).

[0241] Among them, M is the health value of the target device in the current working cycle, x i Perfect represents the standard torque value corresponding to the i-th real-time torque value in the real-time torque signal, x i current represents the i-th real-time torque value in the real-time torque signal, and n represents the number of real-time torque values ​​in the current working cycle, that is, the number of real-time torque values ​​in the real-time torque signal.

[0242] S1602: Determine a predictive maintenance result based on the health value.

[0243] The health value represents the health status of the target device.

[0244] The method of determining the predictive maintenance result based on the health value can be that if the health value is less than the preset health threshold, the predictive maintenance result of the target device is determined to be that the target device requires maintenance; if the health value is greater than or equal to the preset health threshold, the predictive maintenance result of the target device is determined to be that the target device does not need maintenance; optionally, the health threshold can be determined according to the state corresponding to the health value of the target device.

[0245] Optionally, maintenance levels can also be set, including level one maintenance level, level two maintenance level, and level three maintenance level. Each maintenance level corresponds to a health value range. If the health value of the target device in the current working cycle is within the health value range corresponding to a maintenance level, the predictive maintenance result of the target device in the current working cycle is the maintenance level of the corresponding level; each level of maintenance level represents the corresponding maintenance degree of the target device.

[0246] For example, if the health value of the target device in the current working cycle is within the health value range corresponding to the third-level maintenance level, the predictive maintenance result of the target device is the third-level maintenance level, where the third-level maintenance level indicates in-depth maintenance, the second-level maintenance level indicates basic maintenance, and the first-level maintenance level indicates no maintenance is required.

[0247] In the device status monitoring method provided in an embodiment of the present application, the health value of the target device in the current working cycle is determined based on the real-time torque value at each moment in the real-time torque signal, the standard torque value corresponding to the real-time torque value at each moment, and the number of real-time torque values ​​in the current working cycle. Then, a predictive maintenance result is determined based on the health value. In this method, the relative error between the real-time torque signal in the current working cycle and the corresponding standard torque curve is calculated based on the real-time torque value of the real-time torque signal in the current working cycle and the standard torque value corresponding to the real-time torque value. The health value of the real-time torque signal of the target device in the current working cycle is determined based on the relative error between the real-time torque signal in the current working cycle and the corresponding standard torque curve. This can make the accuracy of the health value of the target device determined in the current working cycle higher, thereby greatly increasing the accuracy of the predictive maintenance result of the target device.

[0248] The following describes a specific process of determining a predictive maintenance result based on a health value using an embodiment. In one embodiment, as shown in FIG17 , determining a predictive maintenance result based on a health value includes:

[0249] S1701: Obtain historical health values ​​of the target device in the previous working cycle.

[0250] After determining the health value of the target device in each working cycle, the health value may be stored in a database of the computer device. Thus, the historical health value of the target device in the previous working cycle may be directly obtained from the database.

[0251] Among them, the method for determining the historical health value is the same as the method for determining the health value of the target device in the current working cycle in the above embodiment, and the embodiment of this application will not be repeated here.

[0252] S1702: Determine a predictive maintenance result based on the comparison result between the historical health value and the health value.

[0253] First, the historical health value and the health value can be compared to obtain the comparison result of the historical health value and the health value, and the predictive maintenance result of the target equipment can be determined based on the comparison result.

[0254] In one embodiment, based on the comparison results of the historical health value and the health value, the method for determining the predictive maintenance result can be to first determine the size of the historical health value and the health value, and take the health value greater than or equal to the historical health value, or the health value less than the historical health value as the comparison result; further, if the health value is less than the historical health value, the predictive maintenance result is determined to be that the target equipment needs to be maintained in the current working cycle.

[0255] In another embodiment, as shown in FIG18 , determining a predictive maintenance result based on a comparison result of the historical health value and the health value further includes the following steps:

[0256] S1801, obtaining the difference between the historical health value and the health value.

[0257] S1802: If the difference is greater than the preset maintenance threshold, the predictive maintenance result is determined to be maintenance of the target equipment in the current working cycle.

[0258] Obtain the difference between the historical health value and the healthy value, and use the difference between the historical health value and the healthy value as the comparison result; if the difference between the historical health value and the healthy value is greater than the preset maintenance threshold, it is determined that the target device needs maintenance in the current working cycle; wherein, the preset maintenance threshold can be determined based on historical experience

[0259] Optionally, the preset maintenance threshold can be a larger value. When the difference between the historical health value and the health value is greater than the preset maintenance threshold, it means that the health value of the current working cycle has dropped sharply compared with the historical health value of the previous working cycle. At this time, the target equipment needs to be maintained and serviced in the current working cycle.

[0260] For example, if the preset maintenance threshold is 30, the historical health value is 93, and the health value is 61, then the difference between the historical health value and the health value is determined to be 32. If the difference between the historical health value and the health value is greater than the preset maintenance threshold, then the predictive maintenance result is determined to be that the target equipment needs to be maintained in the current working cycle.

[0261] In an embodiment of the present application, the difference between the historical health value and the health value is obtained. If the difference is greater than a preset maintenance threshold, the predictive maintenance result is determined to be maintenance on the target device during the current working cycle. In this embodiment, when the difference between the historical health value and the health value is greater than the preset maintenance threshold, the predictive maintenance result for the target device is determined to be maintenance on the target device during the current working cycle. This implements predictive maintenance when the target device deteriorates by a certain threshold, allowing timely maintenance on the target device when maintenance is required.

[0262] The device status monitoring method provided in the embodiments of the present application obtains the historical health value of the target device during the previous working cycle and determines the predictive maintenance result based on the comparison between the historical health value and the health value. In this method, the predictive maintenance result of the target device is determined by comparing the historical health value of the target device during the previous working cycle with the health value during the current working cycle. This achieves a transition from a scheduled maintenance strategy to a predictive maintenance strategy. When the target device needs maintenance, it can be maintained in a timely manner, thereby increasing the service life of the target device.

[0263] In an embodiment of the present application, a standard torque curve is established based on a small amount of historical data of industrial equipment. The health value of the equipment is quantified by measuring the degree of deviation between the real-time torque data and the standard torque curve. The generated health value curve is used to guide the maintenance and care of the equipment at the industrial site.

[0264] A health value can be obtained in each working cycle. Therefore, the health value of the target device in the entire life cycle can be calculated to obtain a performance degradation trend diagram of the target device in the entire life cycle. When the degradation reaches a certain threshold, predictive maintenance can be performed. The following is a detailed description of this through an embodiment. In one embodiment, as shown in FIG19 , the embodiment includes the following steps:

[0265] S1901: Determine a performance degradation trend graph of the target device based on the health value of the target device throughout its entire life cycle.

[0266] Obtain the health value of the target device in each working cycle throughout its life cycle. The method of obtaining the health value of the target device in each working cycle throughout its life cycle is the same as the above-mentioned method of obtaining the health value of the target device in the current working cycle, which will not be repeated here in this embodiment.

[0267] Based on the health value of the target device throughout its life cycle, a performance degradation trend chart of the target device throughout its life cycle is drawn.

[0268] S1902: Obtain a target duty cycle period in which the health value jitter exceeds a preset amplitude in the performance degradation trend graph.

[0269] According to the performance degradation trend graph, a working cycle period in which the health value jitter exceeds a preset amplitude is obtained from the performance degradation trend graph, wherein the health value jitter can represent the difference between the health values ​​of two adjacent working cycle periods in the performance degradation trend graph. Therefore, a target working cycle period corresponding to when the difference between the health values ​​of any two adjacent working cycle periods in the performance degradation trend graph exceeds the preset amplitude is obtained. The target working cycle period can be the working cycle period that comes earlier in time between the two adjacent working cycle periods.

[0270] S1903: Determine the maintenance time of the target equipment according to the target working cycle.

[0271] When the difference between the health values ​​of two adjacent working cycles is greater than the preset amplitude, it means that the change amplitude of the health value of the corresponding working cycle is large, and maintenance is required at this time. Therefore, the target working cycle can be directly determined as the maintenance time of the target equipment.

[0272] As shown in Figure 20, the target device's performance degradation trend chart shows time on the horizontal axis and health value on the vertical axis. The chart shows that the target device exhibits a long-term degradation trend, with the performance of its moving components slowly decreasing until failure as operating time accumulates. Therefore, the optimal maintenance strategy for the target device can be determined based on the performance degradation trend chart. As can be seen in Figure 20, points a, b, c, and d are maintenance points, and the times corresponding to these points are the target device's maintenance times. Maintenance of the target device is performed at the times corresponding to these maintenance points.

[0273] Furthermore, predictive maintenance can be performed on similar devices of the target device based on the performance degradation trend graph of the target device. For example, the maintenance time of the target device determined based on the performance trend graph of the target device is determined as the maintenance time of similar devices of the target device.

[0274] The device status monitoring method provided in the embodiment of the present application first determines the performance degradation trend graph of the target device based on the health value of the target device throughout its life cycle, then obtains the target working cycle period in which the health value jitter exceeds a preset amplitude in the performance degradation trend graph, and determines the maintenance time of the target device based on the target working cycle period. In this embodiment, the performance degradation trend graph of the target device is drawn through real-time calculation of the health value, so that when the degradation reaches a certain preset amplitude, predictive maintenance is performed on the target device, and the maintenance time of the target device is determined. This allows timely maintenance to be performed on the target device when its performance degrades; and maintenance is performed on the target device only when it needs maintenance, thereby reducing the maintenance time of the target device.

[0275] The above embodiments all describe predictive maintenance of target equipment. The following describes how to locate a fault based on its specific location using an embodiment. The condition monitoring result includes a fault location result for the target equipment. In one embodiment, as shown in FIG21 , the condition monitoring result for the target equipment is determined based on the real-time torque signal within the current working cycle, including the following steps:

[0276] S2101, obtaining a real-time torque curve based on the real-time torque signal in the current working cycle;

[0277] The torque value corresponding to the real-time torque signal in the current working cycle is obtained, and the real-time torque curve in the current working cycle is drawn based on the moment corresponding to the torque value.

[0278] S2102: Determine a fault location result based on the real-time torque curve.

[0279] The fault location result is determined based on the real-time torque signal within the current working cycle.

[0280] Since a fault in the target device indicates an abnormal operating state during its current operating cycle, the specific fault location must be analyzed using the real-time torque curve within the current operating cycle. For example, if the real-time torque curve within the current operating cycle is abnormal, the abnormal torque point within the real-time torque curve can be further determined based on the real-time torque curve. The fault location can then be determined based on the abnormal torque point and used as the fault location result.

[0281] The device status monitoring method provided in the embodiment of the present application obtains a real-time torque curve based on the real-time torque signal within the current working cycle, and determines the fault location result based on the real-time torque curve. In this method, the fault location of the target device is determined based on the real-time torque curve, and the fault location of the target device can be determined, allowing maintenance personnel to directly maintain and troubleshoot the fault point, assisting in the rapid implementation of industrial on-site maintenance and saving time in repairing the target device. The fault location in this method can be used for short-term anomaly detection. When the target device has a risk point and no fault has occurred, the risk point can be located. When a fault occurs, the fault location can be quickly located, helping on-site maintenance personnel to quickly repair it, reducing the downtime rate of the target device, improving the efficiency of the target device, assisting on-site personnel in diagnosis and decision-making, improving the efficiency of personnel and target equipment, and the level of intelligence of the industrial site.

[0282] In one embodiment, as shown in FIG22 , determining the fault location result according to the real-time torque curve includes the following steps:

[0283] S2201 : Divide the real-time torque curve according to time windows, and obtain an abnormal boundary of the real-time torque curve according to the divided real-time torque curve.

[0284] In order to improve real-time performance and accuracy, before obtaining the abnormal boundary of the real-time torque curve, the real-time torque curve can be divided according to time windows to obtain multiple time windows, each time window corresponding to the real-time torque curve.

[0285] Therefore, the real-time torque curve can be divided according to the preset time window to obtain multiple time windows; the size of the corresponding time window in the embodiment of the present application is not limited and can be specifically set according to actual conditions.

[0286] The abnormal boundaries corresponding to multiple time windows together constitute the abnormal boundaries of the real-time torque curve. Therefore, when obtaining the abnormal boundaries of the real-time torque curve, the abnormal boundaries of each time window can be obtained first, and then the abnormal boundaries of the real-time torque curve can be constructed according to the abnormal boundaries of each time window.

[0287] The abnormal boundary of each time window can be obtained by inputting the torque value in each time window into a preset abnormal boundary model. The abnormal boundary model analyzes the torque value in each time window and outputs the abnormal boundary of each time window.

[0288] S2202: Determine the fault location result of the target device according to the abnormal boundary.

[0289] The fault location result is the position of the motor drive of the target device.

[0290] In one embodiment, the method for determining the fault location result of the target device based on the abnormal boundary can be to determine the fault location result of the target device through a preset fault location model, input the abnormal boundary and the real-time torque curve into the fault location model, and directly output the fault location result through analysis of the fault location model.

[0291] In another embodiment, the method for determining the fault location result of the target device based on the abnormal boundary can also be to first determine the torque value outside the abnormal boundary in the real-time torque curve as the abnormal torque point, and then determine the fault location of the target device based on the abnormal torque point. As shown in FIG23, the specific process of determining the fault location result of the target device based on the abnormal boundary includes the following steps:

[0292] S2301: Acquire abnormal torque points outside the abnormal boundary in the real-time torque curve.

[0293] First, the real-time torque curve is time-matched with the abnormal boundary to obtain the abnormal torque points outside the abnormal boundary in the real-time torque curve.

[0294] For example, if the torque value at time t1 of the real-time torque curve is R1, the corresponding abnormal boundary at time t1 in the real-time torque curve is obtained. If the abnormal boundary at time t1 of the real-time torque curve is (D1, D2), the upper abnormal boundary is D2, the lower abnormal boundary is D1, and R1 is greater than D2, then it is determined that the torque point at time t1 of the real-time torque curve is outside the abnormal boundary, and the torque point at time t1 of the real-time torque curve is determined as the abnormal torque point.

[0295] If the torque value at time t2 of the real-time torque curve is R2, the abnormal boundary at time t2 in the real-time torque curve is obtained. If the abnormal boundary at time t2 of the real-time torque curve is (D3, D4), the upper abnormal boundary is D4, the lower abnormal boundary is D3, and R1 is greater than D3 and less than D4, then it is determined that the torque point at time t1 of the real-time torque curve is within the abnormal boundary, and the torque point at time t1 of the real-time torque curve is determined to be a normal torque point.

[0296] S2302: Determine the fault location result of the target device according to the abnormal torque point.

[0297] Since the fault location result of the target device is the fault position of the target device, the moment corresponding to the abnormal torque point can be obtained, and the moment can be determined as the torque abnormality moment. Then, the position where the target device is running at the torque abnormality moment is determined, and the position is the fault position of the target device.

[0298] In this embodiment, abnormal torque points outside the abnormal boundaries of the real-time torque curve are obtained, and the fault location results of the target device are determined based on the abnormal torque points. In this embodiment, real-time abnormal torque point diagnosis is performed based on the upper and lower abnormal boundaries of the real-time torque curve, which can quickly determine the abnormal torque points and help maintenance personnel quickly locate the fault problem of the target device.

[0299] The device status monitoring method provided in an embodiment of the present application first divides the real-time torque curve according to a time window, obtains the abnormal boundary of the real-time torque curve based on the divided real-time torque curve, and then determines the fault location result of the target device based on the abnormal boundary. In this method, the real-time torque curve is divided according to the time window, and then the abnormal boundary of the real-time torque curve is determined based on the divided real-time torque curve. The accuracy of the abnormal boundary of the real-time torque curve is improved by dividing the real-time torque curve. In addition, the fault of the target device is located based on the abnormal torque point, and the position of the target device at the time of abnormal torque is determined to locate the risk point or fault location. By locating the fault of the target device, industrial field maintenance personnel can quickly find the fault problem of the target device, thereby improving the work efficiency of the target device maintenance.

[0300] The abnormal boundaries mentioned above include an upper abnormal boundary and a lower abnormal boundary. The following describes in detail how to determine the abnormal boundary of the real-time torque curve through an embodiment. In one embodiment, as shown in FIG24 , obtaining the abnormal boundary of the real-time torque curve based on the divided real-time torque curve includes the following steps:

[0301] S2401, obtaining the first quarter torque value and the second quarter torque value in the real-time torque curve.

[0302] Obtaining the first and second quartile torque values ​​from the real-time torque curve essentially involves obtaining the first and second quartiles of the torque values ​​within each time window of the real-time torque curve. For any time window, the first quartile of the torque value within the time window can be the 25th percentile, and the second quartile can be the 75th percentile.

[0303] The first quartile and the second quartile may be obtained by first sorting the torque values ​​within the time window from smallest to largest, then finding the median value of the sorted torque values, creating a group above and below the median value, finding the median value for each created group, determining the median value of the first group as the first quartile, and determining the median value of the second group as the second quartile.

[0304] S2402: Determine an interquartile range value based on the first and second quartile torque values.

[0305] Based on the first quartile torque value and the second quartile torque value, an interquartile range (IQR) value may be determined by determining a difference between the first quartile torque value and the second quartile torque value as the interquartile range value.

[0306] S2403 : determining an upper abnormal boundary based on the first quartile torque values ​​and the interquartile range values; and determining a lower abnormal boundary based on the second quartile torque values ​​and the interquartile range values.

[0307] The upper abnormal boundary is determined by the sum of the first quartile torque value and the interquartile range value of the preset multiple, and the lower abnormal boundary is determined by the difference between the second quartile torque value and the interquartile range value of the preset multiple.

[0308] For example, the preset multiples of the interquartile range value may be 1, 1.5, 2, etc. The above are only examples. In actual applications, the specific preset multiples of the interquartile range value may be determined according to actual conditions.

[0309] For example, if the preset multiple of the interquartile range value is 1.5, the sum of the first quartile torque value and 1.5 times the interquartile range value is determined as the upper abnormal boundary, and the difference between the second quartile torque value and 1.5 times the interquartile range value is determined as the lower abnormal boundary; the first quartile torque value is represented by Q1, and the second quartile torque value is represented by Q3, then the interquartile range value IQR is (Q3-Q1), the lower abnormal boundary is Q1-1.5×IQR, and the upper abnormal boundary is Q3+1.5×IQR.

[0310] As shown in FIG25 , FIG25 is a diagram of the upper and lower abnormal boundaries of the real-time torque curve determined when the interquartile range value is 1.5, including the upper abnormal boundary, the real-time torque curve and the lower abnormal boundary.

[0311] The device status monitoring method provided in the embodiment of the present application obtains the first and second quartile torque values ​​in the real-time torque curve, determines the interquartile range value based on the first and second quartile torque values, and then determines the upper abnormal boundary based on the first quartile torque value and the interquartile range value; and determines the lower abnormal boundary based on the second quartile torque value and the interquartile range value. In this method, the upper and lower abnormal boundaries of the real-time torque curve are determined by the interquartile range method. The interquartile range method can truly and intuitively show the true appearance of the data distribution, and is relatively objective in identifying abnormal values ​​with high accuracy, thereby improving the accuracy of the fault location of the target device; further, the method establishes the upper and lower envelope curves of the real-time torque curve, which facilitates the subsequent positioning of the abnormal torque point where the real-time torque curve exceeds the envelope curve, and locates the location where risks or faults may occur, thereby performing necessary inspections and maintenance on the equipment.

[0312] In another embodiment, the abnormal boundary of the real-time torque curve can also be obtained by a normal distribution method. As shown in FIG26 , obtaining the abnormal boundary of the real-time torque curve according to the divided real-time torque curve includes the following steps:

[0313] S2601, based on the torque values ​​of each time window in the real-time torque curve, obtain the torque mean and torque standard deviation of the real-time torque curve; the torque standard deviation is the torque standard deviation of the local time window or the torque standard deviation of the global real-time torque curve.

[0314] The torque mean and torque standard deviation of the real-time torque curve are obtained based on the torque values ​​of each time window in the real-time torque curve. The torque mean is the mean of each time window in the real-time torque curve, and the torque standard deviation can be the standard deviation of the torque values ​​in each time window or the global standard deviation of the torque values ​​in the real-time torque curve.

[0315] S2602: Determine an upper abnormal boundary and a lower abnormal boundary based on the torque mean and the torque standard deviation.

[0316] Since the torque standard deviation is the torque standard deviation of the local time window or the torque standard deviation of the global real-time torque curve, there are two ways to determine the upper abnormal boundary and the lower abnormal boundary of the real-time torque curve.

[0317] In one case, the torque standard deviation is the torque standard deviation of the local time window, and the upper abnormal boundary and the lower abnormal boundary are determined by determining the upper abnormal boundary and the lower abnormal boundary of each time window according to the torque mean and the torque standard deviation of each time window, and the upper abnormal boundary and the lower abnormal boundary of the real-time torque curve are jointly constituted by the upper abnormal boundary and the lower abnormal boundary of each time window.

[0318] In another case, the torque standard deviation is the torque standard deviation of the global real-time torque curve, and the upper abnormal boundary and the lower abnormal boundary are determined by determining the upper abnormal boundary and the lower abnormal boundary of each time window based on the torque mean of each time window and the torque standard deviation of the global real-time torque curve, and the upper abnormal boundary and the lower abnormal boundary of the real-time torque curve are jointly constituted by the upper abnormal boundary and the lower abnormal boundary of each time window; wherein, the torque standard deviation of the global real-time torque curve is the standard deviation of the torque value in the real-time torque curve.

[0319] The upper and lower anomaly boundaries can be determined by the normal distribution principle.

[0320] Taking the sigma principle of normal distribution as an example, for example, using the 3sigma principle in normal distribution, the torque value exceeding 3sigma is determined to be an abnormal torque point. Therefore, the upper abnormal boundary of the real-time torque curve is: (μ+3σ), and the lower abnormal boundary of the real-time torque curve is: (μ-3σ), where μ is the torque mean and σ is the torque standard deviation.

[0321] As shown in Figure 27a and Figure 27b, Figure 27a is the upper and lower abnormal boundary diagram determined by the 3sigma principle corresponding to the torque standard deviation of the global real-time torque curve, and Figure 27b is the upper and lower abnormal boundary diagram determined by the 3sigma principle corresponding to the torque standard deviation of the local time window.

[0322] Optionally, the upper abnormal boundary and the lower abnormal boundary of the real-time torque curve may also be determined by the 1sigma principle or the 2sigma principle of the normal distribution, etc., which will not be described in detail in the embodiment of the present application.

[0323] The device status monitoring method provided in an embodiment of the present application first obtains the torque mean and torque standard deviation of the real-time torque curve based on the torque values ​​in each time window of the real-time torque curve. The torque standard deviation is the torque standard deviation of the local time window or the torque standard deviation of the global real-time torque curve. The upper and lower abnormal boundaries are then determined based on the torque mean and torque standard deviation. In this method, the torque standard deviation is used as the limiting error to determine the upper and lower abnormal boundaries of the real-time torque curve, improving the accuracy of the upper and lower abnormal boundaries and thus significantly increasing the accuracy of locating target equipment faults.

[0324] In another embodiment, the abnormal boundary of the real-time torque curve can be determined by the maximum and minimum values ​​of the grid. As shown in FIG28 , obtaining the abnormal boundary of the real-time torque curve based on the divided real-time torque curve includes the following steps:

[0325] S2801, obtaining the maximum torque value, the minimum torque value, and the global torque standard deviation in each time window of the real-time torque curve.

[0326] After the torque curves of different cycle periods are aligned according to the start time, as the number of curves increases, the boundary line of the real-time torque curve is fixed and no longer expands outward. Therefore, the maximum and minimum values ​​of the torque in each time window in the real-time torque curve are counted, and then the abnormal boundary line is determined in combination with different global torque standard deviations. This can determine the abnormal boundary of the real-time torque curve.

[0327] Therefore, the maximum torque value and the minimum torque value of each time window in the real-time torque curve, as well as the global torque standard deviation of the real-time torque curve are obtained respectively.

[0328] S2802: Determine an upper abnormal boundary based on the maximum torque value and the global torque standard deviation.

[0329] The upper abnormal boundary is determined according to the sum of the maximum torque value and the preset multiple of the global torque standard deviation.

[0330] For example, the preset multiple of the global torque standard deviation is 1, 2, or 3, etc. The above is only an example. In actual applications, the specific preset multiple of the global torque standard deviation can be determined according to actual conditions.

[0331] Taking the preset multiple of the global torque standard deviation as 1 as an example, the sum of the maximum torque value of each time window and the global torque standard deviation is determined as the upper abnormal boundary of the corresponding time window. The upper abnormal boundary of each time window constitutes the upper abnormal boundary of the real-time torque curve.

[0332] Taking the preset multiple of the global torque standard deviation as 3 as an example, the sum of the maximum torque value of each time window and 3 times the global torque standard deviation is determined as the upper abnormal boundary of the corresponding time window. The upper abnormal boundary of each time window constitutes the upper abnormal boundary of the real-time torque curve.

[0333] S2803: Determine the lower abnormal boundary based on the minimum torque value and the global torque standard deviation.

[0334] The lower abnormal boundary is determined according to the difference between the minimum torque value and the global torque standard deviation of the preset multiple, which corresponds to the upper abnormal boundary. The preset multiple is 1, 2 or 3, etc.

[0335] Taking the preset multiple of the global torque standard deviation as 1 as an example, the difference between the maximum torque value of each time window and the global torque standard deviation is determined as the lower abnormal boundary of the corresponding time window. The lower abnormal boundary of each time window constitutes the lower abnormal boundary of the real-time torque curve.

[0336] Taking the preset multiple of the global torque standard deviation as 3 as an example, the difference between the maximum torque value of each time window and 3 times the global torque standard deviation is determined as the lower abnormal boundary of the corresponding time window. The lower abnormal boundary of each time window constitutes the lower abnormal boundary of the real-time torque curve.

[0337] According to the maximum torque value of each time window, a curve of the maximum torque value corresponding to the real-time torque curve can be constructed, and according to the minimum torque value of each time window, a curve of the minimum torque value corresponding to the real-time torque curve can be constructed, as shown in Figure 29a; Figure 29b is the upper and lower boundary diagram of the real-time torque curve determined based on the maximum torque value, the minimum torque value and 1 times the global standard deviation; Figure 29c is the upper and lower boundary diagram of the real-time torque curve determined based on the maximum torque value, the minimum torque value and 3 times the global standard deviation.

[0338] In the equipment status monitoring method provided in an embodiment of the present application, the maximum torque value, minimum torque value, and global torque standard deviation in each time window of the real-time torque curve are obtained. The upper abnormal boundary is determined based on the maximum torque value and the global torque standard deviation, and the lower abnormal boundary is determined based on the minimum torque value and the global torque standard deviation. In this method, the abnormal boundary of the real-time torque curve is determined by the maximum and minimum torque values ​​of each time window and the global standard deviation. The torque value in the global range is considered while the local calculation is performed, thus avoiding the accuracy of the abnormal boundary of the local time window, thereby improving the accuracy of the upper and lower boundaries of the real-time torque curve.

[0339] The following describes in detail a specific process of determining a fault location result of a target device through an embodiment. In one embodiment, as shown in FIG30 , determining a fault location result of a target device based on an abnormal torque point includes the following steps:

[0340] S3001, obtaining a real-time position signal of a target device within a current working cycle.

[0341] The motion state of the target device also includes a position signal of the target device. Therefore, when obtaining the real-time torque signal of the target device in the current working cycle, the real-time position signal of the target device in the current working cycle can also be obtained at the same time.

[0342] Among them, the real-time position signal is a time series signal and is floating-point data, as shown in Figure 31, where the horizontal axis is time and the vertical axis is the position of the target device.

[0343] S3002: Determine the position corresponding to the abnormal torque point based on the corresponding relationship between the torque value and the time in the real-time torque signal and the corresponding relationship between the position and the time in the real-time position signal.

[0344] The real-time torque signal and the real-time position signal have a one-to-one correspondence, and both the real-time torque signal and the real-time position signal are time-series signals. That is, there is a correspondence between the torque value and the time in the real-time torque signal, and there is a correspondence between the position and the time in the real-time position signal. Therefore, if there is an abnormal torque point, the position corresponding to the abnormal torque point is determined based on the time corresponding to the abnormal torque point and the correspondence between the position and the time in the real-time position signal.

[0345] S3003: Determine the position corresponding to the abnormal torque point as the fault position of the target device.

[0346] The position corresponding to the abnormal torque point is the fault position of the motor drive of the target device when the torque is abnormal.

[0347] In the device status monitoring method provided in the embodiment of the present application, a real-time position signal of a target device within the current working cycle is obtained. Based on the correspondence between the torque value and time in the real-time torque signal, and the correspondence between the position and time in the real-time position signal, the position corresponding to the abnormal torque point is determined, and then the position corresponding to the abnormal torque point is determined as the fault location of the target device. In this method, based on the correspondence between the torque value and time in the real-time torque signal, and the correspondence between the position and time in the real-time position signal, the potential risk point or fault location of the target device is located according to the time when the real-time torque curve of the target device exceeds the abnormal boundary, thereby facilitating the rapid implementation of maintenance, saving time in repairing the target device, and improving the repair efficiency of the target device.

[0348] In one embodiment, the embodiment monitors the torque signal of a target device that performs cyclic reciprocating motion in an industrial field in real time, as shown in FIG32a . FIG32a is a schematic diagram of a real-time torque curve and upper and lower abnormal boundaries of the target device when the torque increases due to insufficient lubrication when the target device passes through the position. By determining the position of the abnormal torque point and then lubricating the point, abnormal wear of the target device and unnecessary power loss can be prevented.

[0349] As shown in Figure 32b, Figure 32b is a schematic diagram of the torque abnormality time period (0-2000ms) in Figure 32a. It can be seen from the figure that the actual torque value of the real-time torque curve between 250ms and 1650ms exceeds the upper and lower abnormal boundaries. The position corresponding to the time point of the abnormal torque value is obtained from Figure 32c through the time point of the abnormal torque value, and then the position segment is lubricated.

[0350] In the embodiments of the present application, the decline trend of industrial equipment and the location of faults are displayed through data visualization methods, which allows maintenance personnel to understand the health status and production status of industrial equipment while being away from the site, reducing the production site's dependence on maintenance personnel, optimizing the industrial site's maintenance strategy, and improving the maintenance personnel's work experience, which is conducive to the unmanned and intelligent construction of factories and improves the safety and production efficiency of industrial production.

[0351] In one embodiment, as shown in FIG33 , taking the target device as a heat press as an example, the embodiment includes the following steps:

[0352] S3301, obtain the historical torque signal and historical working condition signal of the hot press from the hot press control system.

[0353] S3302 , based on the historical working condition signal, the historical torque signal is divided into working conditions to obtain historical torque signals of multiple historical cycle periods.

[0354] S3303: Delete the torque signal of the abnormal working condition, and perform time alignment on the historical torque signals of multiple historical cycles according to the start time of the historical working condition signal to obtain a historical torque curve.

[0355] S3304: Perform grid processing on the historical torque curve to obtain multiple grids, and fit a standard torque curve based on the mean value of each grid.

[0356] S3305: According to a preset sampling period, a real-time torque signal of the hot press in the current working cycle is obtained from the hot press control system.

[0357] S3306: Calculate the degree of deviation of the real-time torque signal relative to the standard torque curve to obtain the health value of the hot press in the current working cycle.

[0358] S3307: Determine a predictive maintenance result of the hot press based on the health value of the hot press in the current working cycle and the historical health value of the previous working cycle.

[0359] S3308: Draw a performance degradation trend graph of the hot press based on the health value of the hot press in the current working cycle and the historical health value of the hot press.

[0360] S3309: Obtain a real-time torque curve according to the real-time torque signal, and perform rasterization processing on the real-time torque curve to obtain a plurality of grids.

[0361] S3310: Obtain upper and lower anomaly boundaries of each grid using an interquartile range method, and construct upper and lower anomaly boundaries of a real-time torque curve based on the upper and lower anomaly boundaries of each grid.

[0362] S3311, determining the upper and lower abnormal boundaries of each grid by the 3 sigma principle, and constructing the upper and lower abnormal boundaries of the real-time torque curve based on the upper and lower abnormal boundaries of each grid.

[0363] S3312, determining the upper and lower abnormal boundaries of each grid according to the maximum value, minimum value and standard deviation method, and forming the upper and lower abnormal boundaries of the real-time torque curve based on the upper and lower abnormal boundaries of each grid;

[0364] Among them, according to the maximum value, minimum value and standard deviation method, determining the upper and lower abnormal boundaries of each grid includes: obtaining the maximum value and minimum value of each grid, and the global standard deviation of the real-time torque curve respectively, determining the upper abnormal boundary of each grid according to the maximum value and the global standard deviation, and determining the lower abnormal boundary of each grid according to the minimum value and the global standard deviation.

[0365] S3313, obtaining an abnormal torque point that exceeds the upper and lower abnormal boundaries in the real-time torque curve, and obtaining the position corresponding to the moment of the abnormal torque point from the position signal based on the principle of closest time.

[0366] S3314: Determine the position corresponding to the moment of the abnormal torque point as the fault position of the hot press.

[0367] The specific limitations of the device status monitoring method provided in the embodiments of the present application can be found in the above step limitations of each embodiment of the device status monitoring method, which will not be repeated here.

[0368] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0369] Based on the same inventive concept, embodiments of the present application also provide a device state monitoring apparatus for implementing the aforementioned device state monitoring method. The implementation solution provided by this apparatus is similar to the implementation solution described in the aforementioned method. Therefore, the specific limitations in one or more device state monitoring apparatus embodiments provided below can be found in the limitations of the device state monitoring method described above and will not be repeated here.

[0370] In one embodiment, as shown in FIG34 , a device status monitoring apparatus 3400 is provided, comprising: an acquisition module 3401 and a monitoring module 3402 , wherein:

[0371] An acquisition module 3401 is used to acquire a real-time torque signal of a target device in a current working cycle;

[0372] The monitoring module 3402 is used to determine the status monitoring result of the target device based on the real-time torque signal in the current working cycle.

[0373] In one embodiment, the monitoring module 3402 includes:

[0374] A first acquiring unit, configured to acquire a standard torque curve of a target device;

[0375] The first determining unit is configured to determine a predictive maintenance result according to a real-time torque signal and a standard torque curve within a current working cycle.

[0376] In one embodiment, the first acquiring unit includes:

[0377] A first acquisition subunit is configured to acquire a historical operating condition signal and a historical torque signal of the target device based on historical operating status information of the target device;

[0378] The first generating subunit is used to generate a standard torque curve of the target device according to the historical working condition signal and the historical torque signal.

[0379] In one embodiment, the first generating subunit includes:

[0380] A segmentation subunit, configured to perform working condition segmentation on the historical torque signal according to the historical working condition signal, and obtain historical torque signals within a plurality of historical cycle periods;

[0381] An alignment subunit is used to time-align historical torque signals within multiple historical cycles according to the start time of the historical working condition signal, so as to obtain a historical torque curve composed of multiple historical cycles;

[0382] The second generating subunit is configured to generate a standard torque curve of the target device according to the historical torque curve.

[0383] In one embodiment, the second generating subunit includes:

[0384] Rasterization processing is used to perform rasterization processing on the historical torque curve according to a preset time window to obtain multiple grids;

[0385] The second acquisition subunit is used to obtain the standard torque value at the middle moment of each grid;

[0386] The construction subunit is used to construct a standard torque curve of the target device according to the standard torque value at the middle moment of each grid.

[0387] In one embodiment, the second acquiring subunit includes:

[0388] The third acquisition subunit is used to obtain the torque mean of each grid;

[0389] The first determining subunit is configured to determine the torque mean of each grid as the standard torque value at the middle moment of the corresponding grid.

[0390] In one embodiment, the first determining unit includes:

[0391] The fourth acquisition subunit is used to match the real-time torque signal in the current working cycle with the standard torque curve at each moment, and obtain the standard torque value corresponding to the real-time torque value at each moment in the real-time torque signal;

[0392] The second determining subunit is configured to determine a predictive maintenance result of the target device based on a standard torque value corresponding to the real-time torque value at each moment in the real-time torque signal.

[0393] In one embodiment, the second determining subunit includes:

[0394] a third determining subunit, configured to determine a health value of the target device in the current working cycle according to the real-time torque value at each moment in the real-time torque signal, the standard torque value corresponding to the real-time torque value at each moment, and the number of real-time torque values ​​in the current working cycle;

[0395] The fourth determining subunit is configured to determine a predictive maintenance result according to the health value.

[0396] In one embodiment, the fourth determining subunit includes:

[0397] The fifth acquisition subunit is used to obtain the historical health value of the target device in the previous working cycle;

[0398] The fifth determining subunit is configured to determine a predictive maintenance result based on a comparison result between the historical health value and the health value. The fifth determining subunit is configured to determine a predictive maintenance result based on a comparison result between the historical health value and the health value.

[0399] In one embodiment, the fifth determining subunit includes:

[0400] The difference acquisition subunit is used to obtain the difference between the historical health value and the health value;

[0401] The sixth determining subunit is configured to determine that the predictive maintenance result is to perform maintenance on the target equipment in the current working cycle if the difference is greater than a preset maintenance threshold.

[0402] In one embodiment, the apparatus 3400 further includes:

[0403] A first determination module is used to determine a performance degradation trend graph of the target device based on the health value of the target device over its entire life cycle;

[0404] A judgment module is used to obtain a target duty cycle period in which the health value jitter exceeds a preset amplitude in the performance degradation trend graph;

[0405] The second determining module is used to determine the maintenance time of the target equipment according to the target working cycle period.

[0406] In one embodiment, the monitoring module 3402 further includes:

[0407] The second acquisition unit acquires a real-time torque curve according to the real-time torque signal in the current working cycle;

[0408] The second determining unit is configured to determine a fault location result according to the real-time torque curve.

[0409] In one embodiment, the second determining unit includes:

[0410] a sixth acquisition subunit, configured to divide the real-time torque curve into time windows and obtain an abnormal boundary of the real-time torque curve according to the divided real-time torque curve;

[0411] The seventh determining subunit is configured to determine a fault location result of the target device according to the abnormal boundary.

[0412] In one embodiment, the sixth obtaining subunit includes:

[0413] An eighth acquisition subunit, configured to acquire a first quarter torque value and a second quarter torque value in the real-time torque curve;

[0414] an eighth determining subunit, configured to determine an interquartile range value according to the first and second quarter torque values;

[0415] The ninth determining subunit is configured to determine an upper abnormal boundary according to the first quartile torque value and the interquartile range value; and to determine a lower abnormal boundary according to the second quartile torque value and the interquartile range value.

[0416] In one embodiment, the sixth obtaining subunit includes:

[0417] a ninth acquisition subunit, configured to acquire a torque mean and a torque standard deviation of the real-time torque curve based on the torque values ​​of each time window in the real-time torque curve; the torque standard deviation being the torque standard deviation of the local time window or the torque standard deviation of the global real-time torque curve;

[0418] The tenth determining subunit is configured to determine an upper abnormal boundary and a lower abnormal boundary according to the torque mean and the torque standard deviation.

[0419] In one embodiment, the sixth obtaining subunit includes:

[0420] a tenth acquisition subunit, configured to acquire a maximum torque value, a minimum torque value, and a global torque standard deviation in each time window of the real-time torque curve;

[0421] An upper boundary determination subunit is used to determine an upper abnormal boundary according to the maximum torque value and the global torque standard deviation;

[0422] The lower boundary determination subunit is used to determine the lower abnormal boundary according to the minimum torque value and the global torque standard deviation.

[0423] In one embodiment, the seventh determining subunit includes:

[0424] An abnormal torque point acquisition subunit is used to acquire abnormal torque points outside the abnormal boundary in the real-time torque curve;

[0425] The fault location subunit is used to determine the fault location result of the target equipment according to the abnormal torque point.

[0426] In one embodiment, the fault location subunit includes:

[0427] The position signal acquisition subunit is used to obtain the real-time position signal of the target device within the current working cycle;

[0428] a position determination subunit, configured to determine a position corresponding to an abnormal torque point based on a correspondence between a torque value and a time in a real-time torque signal, and a correspondence between a position and a time in a real-time position signal;

[0429] The fault location determination subunit is used to determine the location corresponding to the abnormal torque point as the fault location of the target device.

[0430] In one embodiment, the acquisition module 3401 includes:

[0431] The acquisition unit is used to acquire the real-time torque signal of the target device in the current working cycle from the controller of the motor drive system of the target device according to a preset sampling period.

[0432] Each module in the aforementioned device status monitoring apparatus may be implemented in whole or in part through software, hardware, or a combination thereof. Each module may be embedded in or independent of a processor in a computer device in the form of hardware, or may be stored in a computer device memory in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0433] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in Figure 35. The computer device includes a processor, a memory, an input / output interface (I / O), and a communication interface. The processor, memory, and I / O interface are connected via a system bus, and the communication interface is connected to the system bus via the I / O interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store device status monitoring data. The I / O interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a device status monitoring method is implemented.

[0434] Those skilled in the art will understand that the structure shown in Figure 35 is merely a block diagram of a portion of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0435] In one embodiment, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0436] The implementation principles and technical effects of each step implemented by the processor in the embodiment of the present application are similar to those of the above-mentioned device status monitoring method and will not be repeated here.

[0437] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0438] The implementation principles and technical effects of the steps implemented when the computer program in the embodiment of the present application is executed by the processor are similar to the principles of the above-mentioned device status monitoring method and will not be repeated here.

[0439] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0440] The implementation principles and technical effects of the steps implemented when the computer program in the embodiment of the present application is executed by the processor are similar to the principles of the above-mentioned device status monitoring method and will not be repeated here.

[0441] It should be noted that the data involved in this application (including but not limited to data used for analysis, stored data, displayed data, etc.) are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0442] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0443] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0444] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A method for monitoring equipment status, It is characterized in that The method comprises: Obtain the real-time torque signal of the target device in the current working cycle; Based on the real-time torque signal within the current working cycle, a state monitoring result of the target device is determined.

2. The method according to claim 1, It is characterized in that The condition monitoring result includes a predictive maintenance result of the target device; the condition monitoring result of the target device is determined based on the real-time torque signal within the current working cycle, including: Obtaining a standard torque curve of the target device; The predictive maintenance result is determined according to the real-time torque signal in the current working cycle and the standard torque curve.

3. The method according to claim 2, It is characterized in that The step of obtaining a standard torque curve of the target device includes: According to the historical operating status information of the target device, obtaining the historical operating condition signal and the historical torque signal of the target device; A standard torque curve of the target device is generated according to the historical operating condition signal and the historical torque signal.

4. The method according to claim 3, It is characterized in that The step of generating a standard torque curve of the target device according to the historical operating condition signal and the historical torque signal comprises: Performing working condition segmentation on the historical torque signal according to the historical working condition signal to obtain historical torque signals within a plurality of historical cycle periods; According to the start time of the historical operating condition signal, time-align the historical torque signals in the multiple historical cycles to obtain a historical torque curve composed of the multiple historical cycles; A standard torque curve of the target device is generated according to the historical torque curve.

5. The method according to claim 4, It is characterized in that Generating the standard torque curve of the target device according to the historical torque curve includes: According to a preset time window, the historical torque curve is subjected to grid processing to obtain a plurality of grids; Obtaining the standard torque value at the middle moment of each grid; A standard torque curve of the target device is constructed according to the standard torque value at the middle moment of each grid.

6. The method according to claim 5, It is characterized in that The step of obtaining the standard torque value at the intermediate moment of each grid comprises: Obtaining a torque mean value of each grid; The torque mean value of each grid is determined as the standard torque value at the middle moment of the corresponding grid.

7. The method according to any one of claims 2 to 6, It is characterized in that Determining the predictive maintenance result according to the real-time torque signal in the current working cycle and the standard torque curve includes: Matching the real-time torque signal in the current working cycle with the standard torque curve at each moment to obtain a standard torque value corresponding to the real-time torque value at each moment in the real-time torque signal; Based on the standard torque value corresponding to the real-time torque value at each moment in the real-time torque signal, a predictive maintenance result of the target equipment is determined.

8. The method according to claim 7, It is characterized in that The step of determining the predictive maintenance result of the target device based on the standard torque value corresponding to the real-time torque value at each moment in the real-time torque signal comprises: Determine the health value of the target device in the current working cycle according to the real-time torque value at each moment in the real-time torque signal, the standard torque value corresponding to the real-time torque value at each moment, and the number of real-time torque values ​​in the current working cycle; The predictive maintenance result is determined according to the health value.

9. The method according to claim 8, It is characterized in that Determining the predictive maintenance result according to the health value includes: Obtaining the historical health value of the target device in the last working cycle; The predictive maintenance result is determined according to a comparison result between the historical health value and the health value.

10. The method according to claim 9, It is characterized in that The step of determining the predictive maintenance result according to the comparison result between the historical health value and the health value includes: Obtaining a difference between the historical health value and the health value; If the difference is greater than a preset maintenance threshold, the predictive maintenance result is determined to be maintenance of the target equipment in the current working cycle.

11. The method according to claim 8, It is characterized in that The method further comprises: Determine a performance degradation trend graph of the target device according to the health value of the target device over its entire life cycle; Obtaining a target duty cycle period in which the health value jitter exceeds a preset amplitude in the performance degradation trend graph; The maintenance time of the target equipment is determined according to the target working cycle.

12. The method according to claim 1, It is characterized in that The state monitoring result includes a fault location result of the target device; the state monitoring result of the target device is determined based on the real-time torque signal within the current working cycle, including: Acquire a real-time torque curve according to the real-time torque signal in the current working cycle; The fault location result is determined according to the real-time torque curve.

13. The method according to claim 12, It is characterized in that Determining the fault location result according to the real-time torque curve includes: Dividing the real-time torque curve according to time windows, and obtaining an abnormal boundary of the real-time torque curve according to the divided real-time torque curve; A fault location result of the target device is determined according to the abnormal boundary.

14. The method according to claim 13, It is characterized in that The abnormal boundary includes an upper abnormal boundary and a lower abnormal boundary; the step of obtaining the abnormal boundary of the real-time torque curve according to the divided real-time torque curve includes: Acquire a first quarter torque value and a second quarter torque value in the real-time torque curve; Determining an interquartile range value according to the first quartile torque value and the second quartile torque value; The upper abnormal boundary is determined according to the first quartile torque value and the interquartile range value; and the lower abnormal boundary is determined according to the second quartile torque value and the interquartile range value.

15. The method according to claim 13, It is characterized in that The abnormal boundary includes an upper abnormal boundary and a lower abnormal boundary; the step of obtaining the abnormal boundary of the real-time torque curve according to the divided real-time torque curve includes: According to the torque values ​​of each time window in the real-time torque curve, a torque mean value and a torque standard deviation of the real-time torque curve are obtained; the torque standard deviation is the torque standard deviation of the local time window or the torque standard deviation of the global real-time torque curve; The upper abnormal boundary and the lower abnormal boundary are determined according to the torque mean and the torque standard deviation.

16. The method according to claim 13, It is characterized in that The abnormal boundary includes an upper abnormal boundary and a lower abnormal boundary; the step of obtaining the abnormal boundary of the real-time torque curve according to the divided real-time torque curve includes: Obtaining the maximum torque value, the minimum torque value and the global torque standard deviation in each time window of the real-time torque curve; Determining the upper abnormal boundary according to the maximum torque value and the global torque standard deviation; The lower abnormal boundary is determined according to the minimum torque value and the global torque standard deviation.

17. The method according to claim 13, It is characterized in that The determining the fault location result of the target device according to the abnormal boundary includes: Acquire an abnormal torque point outside the abnormal boundary in the real-time torque curve; A fault location result of the target device is determined according to the abnormal torque point.

18. The method according to claim 17, It is characterized in that The determining the fault location result of the target device according to the abnormal torque point includes: Acquire the real-time position signal of the target device in the current working cycle; Based on the corresponding relationship between the torque value and the time in the real-time torque signal, and the corresponding relationship between the position and the time in the real-time position signal, determining the position corresponding to the abnormal torque point; The position corresponding to the abnormal torque point is determined as the fault position of the target device.

19. The method according to any one of claims 1 to 6, It is characterized in that The step of obtaining a real-time torque signal of the target device in the current working cycle includes: According to a preset sampling period, a real-time torque signal of the target device in the current working cycle is collected from a controller of the motor drive system of the target device.

20. An equipment status monitoring device, It is characterized in that The device comprises: An acquisition module, used to acquire the real-time torque signal of the target device in the current working cycle; The monitoring module is used to determine the status monitoring result of the target device based on the real-time torque signal within the current working cycle.

21. A computer device comprising a memory and a processor, wherein the memory stores a computer program. It is characterized in that When the processor executes the computer program, the steps of the method according to any one of claims 1 to 19 are implemented.

22. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 19 are implemented.

23. A computer program product comprising a computer program, It is characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 19 are implemented.

Images