Equipment health and fault management system

Abstract

The invention provides an equipment health and fault management system. The equipment health and fault management system comprises a detection module which is configured to detect operation data of at least one detection point of equipment; the processing module is configured to process the operation data to extract a plurality of indexes; the alarm module is configured to judge the state of the equipment according to the operation data, the multiple indexes and a pre-specified alarm model, the alarm model comprises a hard threshold value alarm model and a self-adaptive threshold value alarm model, the hard threshold value alarm model compares the multiple indexes with corresponding first fixed threshold values, and the self-adaptive threshold value alarm model outputs the corresponding first fixed threshold values; the adaptive threshold alarm model determines corresponding first adaptive thresholds according to stored historical operation data within a predetermined period of time before the detection time and a plurality of corresponding historical indicators, and compares the plurality of indicators with the corresponding first adaptive thresholds. According to the equipment health and fault management system disclosed by the embodiment of the invention, health and fault management can be carried out on various equipment.

Description

Technical Field

[0001] The present disclosure generally relates to the field of industrial equipment, and more particularly, to an equipment health and fault management system. Background Art

[0002] Industrial equipment is one of the company's important assets. How to improve the utilization rate of industrial equipment and reduce equipment maintenance costs is crucial to the company. Taking coal mining equipment as an example, with the advancement of intelligent construction of coal mines and the start of intelligent construction of non-coal mines, the scale of corporate receivables will continue to grow.

[0003] Equipment health management and fault diagnosis, intelligent solution design and service platform play a vital role in the development of industrial equipment such as coal mining equipment.

[0004] At present, industrial equipment such as coal mining equipment has defects such as poor fault diagnosis accuracy and high false alarm rate, making it difficult to accurately determine whether the status of industrial equipment such as coal mining equipment is abnormal.

[0005] In addition, operation and maintenance personnel cannot timely understand the operating status and health status of industrial equipment such as coal mining equipment, making it difficult to detect failures of industrial equipment at an early stage and easily miss the best time to deal with the failures. Summary of the invention

[0006] One of the objectives of exemplary embodiments of the present disclosure is to provide an equipment health and fault management system capable of determining and monitoring the status of various industrial equipment.

[0007] According to one aspect of the present disclosure, an equipment health and fault management system includes: a detection module, configured to detect operating data of at least one measuring point of the equipment; a processing module, configured to process the operating data to extract multiple indicators; an alarm module, configured to determine the status of the equipment based on the operating data, multiple indicators and a pre-specified alarm model, wherein the alarm model includes a hard threshold alarm model and an adaptive threshold alarm model, the hard threshold alarm model compares multiple indicators with a corresponding first fixed threshold, and the adaptive threshold alarm model determines a corresponding first adaptive threshold based on historical operating data stored within a predetermined time period before the detection moment and the corresponding multiple historical indicators, and compares the multiple indicators with the corresponding first adaptive threshold.

[0008] According to an embodiment of the present disclosure, the alarm module may be further configured to: determine that the state of the device is abnormal in response to multiple indicators being greater than corresponding first fixed thresholds and / or multiple indicators being greater than corresponding first adaptive thresholds.

[0009] According to an embodiment of the present disclosure, the adaptive threshold alarm model can utilize at least one of statistical regression, time series prediction, and machine learning to process historical operating data within a predetermined time period before the stored detection moment and corresponding multiple historical indicators to automatically obtain a corresponding first adaptive threshold. The corresponding first fixed threshold is pre-set by the user, and the alarm model is specified by the user.

[0010] According to an embodiment of the present disclosure, the alarm module may be further configured to determine the abnormality of the device state according to the difference between multiple indicators and corresponding thresholds, classify the abnormality of the device state, and push corresponding alarm information in a graded manner.

[0011] According to an embodiment of the present disclosure, the operating data may include rotation speed and vibration data, and the plurality of indices may include a waveform index, a spectrum index, and an envelope index of the vibration data.

[0012] According to an embodiment of the present disclosure, the alarm module may be further configured to: comprehensively judge the status of the device by combining a pre-established health and fault knowledge base and a health and fault case base.

[0013] According to an embodiment of the present disclosure, the equipment health and fault management system may further include a fault diagnosis module, and the equipment is a coal mining equipment including at least one rotating component, and the fault diagnosis module is configured to: receive alarm information from the alarm module, and in response to the alarm information being alarm information indicating that the state of the equipment is abnormal, determine a fault diagnosis item corresponding to the at least one rotating component; process vibration data in the operating data to obtain characteristic data; and determine whether at least one rotating component has a fault corresponding to the fault diagnosis item based on the obtained characteristic data and the fault characteristics of the fault diagnosis item.

[0014] According to an embodiment of the present disclosure, the fault diagnosis module can be further configured to: in response to the acquired characteristic data presenting at least one of the fault characteristics of gear fault, power frequency fault, belt fault and bearing fault, determine that at least one rotating component has a fault corresponding to the fault diagnosis item.

[0015] According to an embodiment of the present disclosure, the at least one rotating component may include at least one of a crusher, a belt conveyor, a scraper, a vibrating screen, and a briquetting machine.

[0016] According to an embodiment of the present disclosure, at least one measuring point of a crusher may include: at least one of a motor free end, a motor load end, a gearbox shaft output side, a gearbox shaft input side, a gearbox shaft output side, a crushing shaft input side, and a crushing shaft output side; at least one measuring point of a belt conveyor may include: at least one of a drum pedestrian side, a drum non-pedestrian side, a motor free end, a motor load end, a hydraulic coupling input side, a hydraulic coupling output side, a gearbox input shaft, a gearbox output shaft, a gearbox shaft input side, a gearbox shaft output side, a drive drum driving side, a drive drum non-driving side, a tensioner drum pedestrian side, and a tensioner drum non-pedestrian side; at least one measuring point of a scraper may include: a motor At least one of the free end, the load end of the motor, the gearbox input shaft, the gearbox output shaft, the gearbox shaft input side, the gearbox shaft output side, the head sprocket input side, the head sprocket output side, the tail sprocket input side, and the tail sprocket output side; at least one measuring point of the vibrating screen includes: at least one of the belt-related measuring point, the motor free end, the motor load end, and the vibrating screen main shaft; at least one measuring point of the briquetting machine includes: at least one of the motor free end, the motor load end, the reducer shaft input side, the reducer shaft output side, the movable roller shaft input side, the movable roller shaft output side, the fixed roller shaft input side, the fixed roller shaft output side, the forced feeder motor load end, and the forced feeder reducer shaft input side.

[0017] According to an embodiment of the present disclosure, the logical architecture of the equipment health and fault management system may include a perception layer, a data platform layer and an application layer, the detection module is located in the perception layer, the processing module is located in the data platform layer, a part of the alarm module is located in the data platform layer, another part of the alarm module is located in the application layer, a part of the fault diagnosis module is located in the data platform layer, and another part of the fault diagnosis module is located in the application layer.

[0018] The equipment health and fault management system according to the embodiment of the present disclosure can accurately issue an alarm message when a fault is found. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The above and other objects and features of the exemplary embodiments of the present disclosure will become more apparent through the following description in conjunction with the accompanying drawings which exemplarily illustrate the embodiments, in which:

[0020] Figure 1 is a block diagram illustrating a device health and fault management system according to an embodiment of the present disclosure;

[0021] Figure 2 is a block diagram showing a specific configuration of an alarm module according to an embodiment of the present disclosure;

[0022] Figure 3 is a graph showing threshold settings of an alarm module according to an embodiment of the present disclosure;

[0023] Figure 4 is a block diagram showing a fault diagnosis module of a device health and fault management system according to an embodiment of the present disclosure;

[0024] Figure 5 is a logical architecture diagram showing a device health and fault management system according to an embodiment of the present disclosure;

[0025] Figure 6 is a diagram showing a physical deployment of a device health and fault management system according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0026] The following detailed description is provided to help gain a comprehensive understanding of the methods, devices and / or systems described herein. However, the order of operations described herein is only an example and is not limited to those orders set forth herein, but may be equivalently replaced or changed except for operations that must occur or be performed in a specific order. In addition, for greater clarity and simplicity, the description of content known in the art will be omitted or simplified.

[0027] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as those generally understood by a person of ordinary skill in the art to which the present disclosure belongs after understanding the present disclosure. Unless explicitly defined as such herein, terms (such as those defined in a general dictionary) should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and the present disclosure, and should not be interpreted in an idealized or overly formal manner.

[0028] Unless otherwise specified, the same reference numerals generally refer to the same elements (e.g., components, steps, and methods). Reference numerals described in the previous embodiments may be omitted if they appear again in the subsequent embodiments. In addition, the technical features described in different or the same embodiments may be combined in any manner, as long as the combined embodiments or technical solutions are complete and can solve the technical problems of the present application or achieve the technical effects described or not described in the present application but can be determined based on the above complete technical solutions.

[0029] The equipment health and fault management system disclosed in the present invention includes two alarm models, namely a hard threshold alarm model and an adaptive threshold alarm model. The adaptive threshold alarm model disclosed in the present invention can adaptively change the threshold. For example, the adaptive threshold alarm model can determine the corresponding first adaptive threshold based on the historical operation data stored in a predetermined time period before the detection moment and the corresponding multiple historical indicators, and compare the multiple indicators with the corresponding first adaptive threshold, and then determine whether the status of the equipment is normal based on the comparison result.

[0030] Figure 1is a block diagram showing a device health and fault management system according to an embodiment of the present disclosure, Figure 2 is a block diagram showing a specific configuration of an alarm module according to an embodiment of the present disclosure, Figure 3 is a graph showing the threshold setting of the alarm module according to an embodiment of the present disclosure, Figure 4 is a block diagram showing a fault diagnosis module of a device health and fault management system according to an embodiment of the present disclosure.

[0031] The equipment health and fault management system (CPHM) 100 according to the embodiment of the present disclosure may include a detection module 110 , a processing module 120 , and an alarm module 130 .

[0032] The detection module 110 can detect the operation data of at least one measuring point of the equipment. The equipment here can be various industrial equipment (for example, coal mining equipment), and the operation data may include speed data and vibration data, and may also include equipment model (basic information of the equipment (for example, the type of equipment)) and the like.

[0033] For example, the detection module 110 may obtain vibration data of at least one measuring point of at least one rotating component of coal mining equipment. The detection module 110 here may be various sensors or a data reading module of a software module.

[0034] That is, operating data such as vibration data of various components of industrial equipment can be detected by sensors, and as the number of connected devices increases, the data detected by the sensors can be input into the IoT system, and the IoT system can be expanded to accommodate the influx of various data.

[0035] The device health and fault management system disclosed in the present invention may be a part of an Internet of Things system. The data writing of the Internet of Things system is characterized by being stable, continuous, high-concurrency and high-throughput. Usually, more writing is done than reading. The data recently generated by the sensor is written in real time, and there may be almost no data update operations.

[0036] As an example, at least one rotating component of equipment (e.g., industrial equipment such as coal mining equipment) can be various moving components, and at least one rotating component of equipment (e.g., industrial equipment such as coal mining equipment) may include various key components. For example, at least one rotating component of coal mining equipment may include any one of a crusher, a belt conveyor, a scraper, a vibrating screen and a briquetting machine, or any combination of two or more thereof, but this is merely an example, and at least one rotating component of the equipment may also include other types of components.

[0037] As an example, the present disclosure takes coal mine equipment as a typical industrial equipment, and will use it as an example to describe the main functional modules of the equipment health and fault management system of the present disclosure. The five important equipment in the workflow of the coal mine industry are taken as the objects of health and fault management. In order to quickly engineer the health and fault management system, a unified health and fault management process can be adopted. Due to the different functions of various components or equipment in the coal mine, the components of each type of equipment are different, but the equipment health and management module of the present disclosure can achieve the same alarm function, which is convenient for early warning and advance maintenance of equipment.

[0038] The processing module 120 may be configured to process the operating data to extract a plurality of indicators.

[0039] As an example, the processing module 120 may process the operation data such as vibration data, such as filtering and / or feature extraction, etc. The noise portion in the operation data may be filtered out by a filter, and then a signal analysis (e.g., spectrum analysis, time domain index multi-trend, trend waveform spectrum, multi-time domain spectrum, multi-time domain waveform, trend chart analysis, order analysis, cepstrum analysis, envelope spectrum analysis, spectrum analysis, original waveform analysis, long waveform analysis, etc.) may be performed on the operation data from which the noise portion has been filtered out, thereby extracting multiple indicators (e.g., fault sensitive indicators such as waveform indicators (time domain features), spectrum indicators (e.g., spectrum features), and envelope indicators (envelope features)).

[0040] The processing module 120 may also calculate the rotation speed and the effective value of the low-frequency acceleration according to the operation data, and process the operation data when the rotation speed and the effective value of the low-frequency acceleration meet preset conditions.

[0041] As an example, the operation data of the device may be processed when the rotation speed and the effective value of the low-frequency acceleration of the operation data of the device are respectively greater than the preset thresholds. The preset threshold here may be an empirical value, and may be determined according to the minimum rotation speed and the minimum low-frequency acceleration of the device during normal operation. For example, the minimum rotation speed and the minimum low-frequency acceleration may be set as corresponding thresholds, respectively. That is, the processing module 120 may perform the judgment of starting and stopping the device.

[0042] Reference Figure 2 In addition to extracting various indicators and determining whether to start or stop the machine, the processing module 120 can also perform timing alignment and error signal processing.

[0043] As an example, the processing module 120 may remove data during the device startup process to prevent various indicators from exceeding limits during the device startup. Specifically, the processing module 120 may determine whether the device is starting up based on the speed data, etc., and remove the data during the device startup period to prevent false alarms. In addition, the processing module 120 may also determine whether operating data such as vibration data is data collected when the device is in a specific working condition. If it is determined that the data is collected under a specific working condition, the processing module 120 may also remove the corresponding multiple indicator data to prevent false alarms.

[0044] The alarm module 130 may determine the status of the device according to the operation data (eg, rotation speed data), multiple indicators, and a pre-specified alarm model.

[0045] As an example, the alarm module 130 can determine the state of the device based on the rotation speed data, multiple extracted sensitive fault indicators (e.g., waveform indicators (e.g., effective value of timing waveform), spectrum indicators (e.g., fundamental frequency amplitude), envelope indicators (amplitude of fault characteristic frequency), etc.) and a pre-specified alarm model. The alarm model here can be specified by the user or automatically triggered by the software.

[0046] Reference Figure 2 , the alarm model may include a hard threshold alarm model and an adaptive threshold alarm model.

[0047] The hard threshold alarm model can compare multiple indicators with the corresponding first fixed threshold, however, the adaptive threshold alarm model can determine the corresponding first adaptive threshold based on the stored historical operating data within a predetermined time period before the detection moment and the corresponding multiple historical indicators, and compare the multiple indicators with the corresponding first adaptive threshold.

[0048] Reference Figure 2 The hard threshold alarm model is a classic vibration alarm model. Equipment managers can determine the absolute thresholds for warning and danger alarms based on national, industry, and enterprise standards, and can refer to historical operating data vertically and compare operating data of similar equipment horizontally.

[0049] That is, the first fixed threshold value as the absolute alarm threshold value may be determined according to various standards and historical operation data.

[0050] The hard threshold alarm model is easy to deploy, simple and easy to use, and has a large number of applications in industrial fields such as the coal industry. The system can easily set relevant thresholds.

[0051] Reference Figure 3 It is difficult to obtain an absolutely reasonable hard threshold. Setting too high a hard threshold alarm threshold or threshold will cause the risk of failure to alarm. If the hard threshold alarm model is too low, it will cause a large number of false alarms, causing great pressure on on-site processing.

[0052] On the other hand, the hard threshold alarm model generally only refers to a few fault characteristic indicators such as the total vibration value, and the fault modes that can be discovered are limited. In addition, the hard threshold alarm model generally requires manual adjustment of the hard threshold, which is labor-intensive.

[0053] However, the adaptive threshold alarm model disclosed in the present invention is different from the hard threshold alarm model. The adaptive threshold alarm model can minimize invalid alarms without missing equipment fault alarms, and can have the characteristics of a rich alarm indicator system, that is, a large number of stable fault indicators can be extracted to form an alarm indicator system, which comprehensively improves the coverage of fault modes and the effectiveness of alarms.

[0054] The adaptive threshold alarm model can determine a corresponding first adaptive threshold based on the stored historical operating data within a predetermined time period before the detection moment and corresponding multiple historical indicators, and compare the multiple indicators with the corresponding first adaptive threshold.

[0055] For example, the adaptive threshold alarm model can automatically obtain the optimal alarm threshold based on the historical performance of key indicators through statistical regression, time series prediction, machine learning and other algorithms, without the need for external manual setting and adjustment, thereby ensuring that equipment failures are not missed and the number of false alarms is minimized. As an example, the adaptive threshold alarm module may include a threshold adaptive calculation module that calculates the corresponding threshold.

[0056] The adaptive threshold alarm model can utilize at least one of statistical regression, time series prediction, and machine learning to process historical operating data within a predetermined time period before the stored detection moment and corresponding multiple historical indicators to automatically obtain a corresponding first adaptive threshold (for example, a waveform indicator threshold, a spectrum indicator threshold, and an envelope indicator threshold).

[0057] You can choose to alarm from either the adaptive threshold alarm model or the hard threshold alarm model, or you can choose to alarm from both models at the same time (for example, you can first execute the hard threshold alarm model, and when the threshold is exceeded in the hard threshold alarm model, you can further execute the adaptive threshold alarm model. If the adaptive threshold alarm model triggers an alarm, it can be determined that the status of the equipment is abnormal).

[0058] The alarm module 130 may determine that the status of the device is abnormal in response to multiple indicators (eg, at least two indicators) being greater than corresponding first fixed thresholds and / or multiple indicators (eg, at least two indicators) being greater than corresponding first adaptive thresholds.

[0059] As an example, the alarm module 130 may determine that the state of the device is abnormal in response to the spectrum index (e.g., the amplitude at a predetermined frequency) being greater than a corresponding first fixed threshold and / or the spectrum index being greater than a corresponding first adaptive threshold. As an example, the spectrum index here may be the amplitude at a predetermined frequency. The corresponding first fixed threshold is preset by the user.

[0060] The alarm module 130 may determine that the state of the device is abnormal in response to the spectrum index being greater than the corresponding first fixed threshold or the spectrum index being greater than the corresponding first adaptive threshold. As an example, the spectrum index here may be an amplitude at a predetermined frequency.

[0061] The alarm module 130 may automatically execute the adaptive threshold alarm model in response to multiple indicators (e.g., at least two indicators) being greater than the corresponding first fixed threshold, and may determine that the state of the device is abnormal in response to multiple indicators (e.g., at least two indicators) being greater than the corresponding first adaptive threshold. The at least two indicators here may include an envelope indicator and a spectrum indicator.

[0062] The alarm module 130 may determine the abnormality of the device state according to the size of the difference between the multiple indicators and the corresponding thresholds. As an example, the alarm module 130 may determine the degree of abnormality of the device according to the size of the difference between the spectrum indicator and the corresponding first fixed threshold or the spectrum indicator and the corresponding first adaptive threshold. For example, if the difference between the spectrum indicator and the corresponding first fixed threshold or the spectrum indicator and the corresponding first adaptive threshold is in the first range (the first over-limit situation), the state of the device is determined to be a first-level abnormal state. If the difference between the spectrum indicator and the corresponding first fixed threshold or the spectrum indicator and the corresponding first adaptive threshold is in the second range (the second over-limit situation), the state of the device is determined to be a second-level abnormal state. If the difference between the spectrum indicator and the corresponding first fixed threshold or the spectrum indicator and the corresponding first adaptive threshold is in the third range (the third over-limit situation), the state of the device is determined to be a third-level abnormal state, and the abnormal levels of the first-level abnormal state, the second-level abnormal state, and the third-level abnormal state gradually increase. That is, the greater the over-limit, the higher the abnormal level.

[0063] In addition, when one indicator exceeds the corresponding threshold, the alarm module 130 can further determine the degree to which another indicator exceeds the corresponding threshold, and determine the state or classify the abnormal state level according to the degree to which the other indicator exceeds the corresponding threshold. For example, when the envelope indicator exceeds the corresponding threshold, the alarm module 130 can further determine the degree to which the waveform indicator exceeds the corresponding threshold, and then determine whether it is an acceptable normal state or an abnormal state that requires shutdown maintenance. In other words, the alarm model can fuse multiple indicators.

[0064] In addition, the alarm module 130 can make a comprehensive judgment based on the operating data of multiple measuring points, and can trigger an alarm signal when multiple indicators extracted from the operating data of multiple measuring points of the same component are all out of limit.

[0065] Therefore, the alarm module 130 can classify the abnormality of the device status and push corresponding alarm information in a graded manner (for example, alarm information corresponding to the first level abnormal status, the second level abnormal status, and the third level abnormal status).

[0066] Reference Figure 4 The alarm module 130 may include an alarm classification module, which can perform indicator fusion (combining multiple indicators to make judgments), measurement point fusion (combining multiple measurement points to make judgments) and over-limit indicators (judgment based on whether the limit is exceeded).

[0067] Therefore, the alarm module 130 can determine the severity of equipment failure based on multi-dimensional information such as indicator type and amplitude level, push alarm information in a graded manner, and help professionals reasonably arrange the processing plan of alarm information to ensure that the most serious alarms receive the highest priority.

[0068] When an alarm is triggered, the alarm module 130 can push the alarm signal to the corresponding handler, who will handle it through the alarm processing process. After on-site confirmation, the on-site investigation information will be recorded. After diagnosis confirmation, the diagnosis conclusion and preventive measures will be improved. If maintenance is required, the maintenance record of the equipment will be recorded. After the fault is handled, a post-evaluation including verification conclusions, explanations and analysis processes can be performed. After the processing is completed, the status will be switched to closed, and the corresponding alarm event will be closed synchronously.

[0069] The alarm module 130 can also display alarm information. For example, the alarm list of the alarm module can display: including processing status, device name, device path (controlled by the number of display path layers of the organization node in the advanced settings-device tree settings, alarm level (displaying the highest alarm level of the alarm measurement point under the device), alarm type (adaptive threshold alarm (or intelligent alarm), hard threshold alarm (threshold or threshold alarm)), alarm time (the time when the alarm is triggered under the current device measurement point), alarm processing time (the time when the alarm processing is completed), last operator (the last operator after the alarm processing is completed), etc. In addition, the alarm list displays the basic information of the alarm event. The user can click the "Details" or "Processing" button displayed by the alarm module to enter the alarm details page, which displays the measurement point name, alarm name, fault type, alarm time and maintenance suggestions of the alarm event (displayed in the form of cards, and the diagnostic conclusion or result pushed by the intelligent diagnosis is displayed here).

[0070] In addition, the following method can be used to handle alarm events triggered by the alarm module: first, the user (for example, a professional) views the confirmed event, confirms the cause and suggestion of the event triggering (the vibration analyst analyzes the cause of the fault); if it is confirmed that maintenance is required, maintenance is carried out and then evaluated, and after evaluation, it is included in the fault case library (described later); if maintenance is not required, the event is canceled and the reason for cancellation is filled in.

[0071] The alarm module can combine the pre-established health and fault knowledge base and health and fault case base to comprehensively judge the status of the equipment. The health and fault knowledge base and the health and fault case base can be established based on the output results of the fault diagnosis module.

[0072] Figure 5 is a block diagram showing a fault diagnosis module of a device health and fault management system according to an embodiment of the present disclosure. The device health and fault management system may further include a fault diagnosis module.

[0073] The fault diagnosis module can determine the type of fault based on the processed (e.g., pre-processed) fault sensitive indicators or operating data (e.g., speed data, equipment information in the equipment model), etc. and the algorithm library. In addition, the fault diagnosis device can also perform fault diagnosis in combination with the previously established case library and knowledge library. The results of the fault diagnosis can form a fault case, and the historical fault cases can form a case library. The knowledge or experience formed by the diagnosis process of the fault case can form a knowledge library. Both the case library and the knowledge library can be used to accurately determine whether the equipment has a fault. In addition, the results of the fault diagnosis can be verified by external experts, etc.

[0074] As an example, the fault diagnosis module may receive alarm information from the alarm module, determine a fault diagnosis item corresponding to at least one rotating component in response to the alarm information being alarm information indicating an abnormal state of the equipment, process vibration data in the operating data to obtain characteristic data, and determine whether at least one rotating component has a fault corresponding to the fault diagnosis item based on the obtained characteristic data and the fault characteristics of the fault diagnosis item.

[0075] For example, the fault diagnosis module may determine that at least one rotating component has a fault corresponding to the diagnosis item in response to the acquired characteristic data presenting at least one fault characteristic of a gear fault, a power frequency fault, a belt fault, and a bearing fault. As described above, the at least one rotating component may include at least one of a crusher, a belt conveyor, a scraper, a vibrating screen, and a briquetting machine.

[0076] The equipment health and fault management system can perform fault detection on two or more measuring points of at least one rotating component of coal mining equipment, thereby ensuring the accuracy of fault diagnosis.

[0077] At least one measuring point of the crusher may include: at least one of the free end of the motor, the load end of the motor, the output side of the gearbox shaft, the input side of the gearbox shaft, the output side of the gearbox, the input side of the crushing shaft, and the output side of the crushing shaft. According to the structure of the crusher, the specific measuring points and fault diagnosis items may be shown in Table 1 below.

[0078] Table 1

[0079]

[0080]

[0081] The crusher may include multiple drive parts, each of which may include a motor, a gearbox, a crushing shaft, etc. Vibration data can be detected at multiple measuring points of each component of the crusher's drive part, and each measuring point collects data through its own measuring point channel to prevent vibration data from different measuring points from interfering with each other. Fault detection at multiple measuring points of the same component of the crusher can accurately determine whether the component has failed, providing a guarantee for predictive maintenance.

[0082] At least one measuring point of the belt conveyor may include: at least one of the pedestrian side of the roller, the non-pedestrian side of the roller, the free end of the motor, the load end of the motor, the input side of the hydraulic coupler, the output side of the hydraulic coupler, the input shaft of the gearbox, the output shaft of the gearbox, the input side of the gearbox shaft, the output side of the gearbox shaft, the driving side of the driving roller, the non-driving side of the driving roller, the pedestrian side of the tensioning roller, and the non-pedestrian side of the tensioning roller. According to the structure of the belt conveyor, the specific measuring points and fault diagnosis items may be shown in Table 2 below.

[0083] Table 2

[0084]

[0085]

[0086] The belt conveyor may include a belt conveyor, multiple drive units and rollers, each of which may include a motor, a gearbox, etc. Vibration data may be detected at the measuring points of each component of the belt conveyor, and each measuring point collects data through its own measuring point channel to prevent vibration data from different measuring points from interfering with each other. Fault detection at multiple measuring points of the same component of the belt conveyor can improve the accuracy of fault diagnosis and provide a basis for predictive maintenance.

[0087] At least one measuring point of the scraper may include: at least one of the free end of the motor, the load end of the motor, the input shaft of the gearbox, the output shaft of the gearbox, the input side of the gearbox shaft, the output side of the gearbox shaft, the input side of the head sprocket, the output side of the head sprocket, the input side of the tail sprocket, and the output side of the tail sprocket. According to the structure of the scraper, the specific measuring points and fault diagnosis items may be shown in Table 3 below.

[0088] Table 3

[0089]

[0090]

[0091] The scraper may include a motor, a gearbox, a head and a tail. Vibration data can be detected at the measuring points of each component of the scraper, and each measuring point collects data through its own measuring point channel to prevent vibration data from different measuring points from interfering with each other. Fault detection at multiple measuring points of the same component of the scraper (e.g., motor, gearbox) can improve the accuracy of fault diagnosis, which is conducive to early maintenance based on the fault diagnosis results, thereby increasing the service life of related components and improving equipment safety.

[0092] At least one measuring point of the vibrating screen may include: at least one of the belt-related measuring point, the motor free end, the motor load end, and the vibrating screen main shaft. According to the structure of the vibrating screen, the specific measuring points and fault diagnosis items may be shown in Table 4 below.

[0093] Table 4

[0094]

[0095] The vibrating screen may include a belt, a motor and a spindle. The measuring points of the vibrating screen belt may correspond to the measuring points of the motor, and data may be collected through the measuring point channels 2H and 3H. Vibration data may be detected at the measuring points of each component of the vibrating screen, and each measuring point collects data through its own measuring point channel to prevent vibration data from different measuring points from interfering with each other. Fault detection at multiple measuring points of the same component of the vibrating screen (e.g., motor, spindle) may improve the accuracy of fault diagnosis, facilitate early maintenance based on the fault diagnosis results, thereby increasing the service life of related components and improving equipment safety.

[0096] At least one measuring point of the briquetting machine includes: at least one of the free end of the motor, the load end of the motor, the input side of the reducer shaft, the output side of the reducer shaft, the input side of the movable roller shaft, the output side of the movable roller shaft, the input side of the fixed roller shaft, the output side of the fixed roller shaft, the load end of the motor of the forced feeder, and the input side of the reducer shaft of the forced feeder. According to the structure of the briquetting machine, the specific measuring points and fault diagnosis items can be shown in Table 5 below.

[0097] Table 5

[0098]

[0099] The briquetting machine may include a motor, a reducer, etc. Vibration data may be detected at the measuring points of each component of the briquetting machine, and each measuring point collects data through its own measuring point channel. Performing fault detection at multiple measuring points of the same component of the briquetting machine (e.g., motor, reducer) can improve the accuracy of fault diagnosis, which is conducive to early maintenance according to the fault diagnosis results, thereby increasing the service life of related components and improving equipment safety.

[0100] As an example, the coal mine diagnosis module can determine the fault diagnosis items corresponding to the motor (for example, power frequency fault and bearing fault). As a result, the fault diagnosis accuracy of key components of key equipment can be improved. The vibration data of multiple measuring points of the motor can be obtained through different detection channels, and the two do not interfere with each other, but this is just an example, and the vibration data of multiple measuring points can be obtained through a single channel.

[0101] As an example, the fault diagnosis module may determine that at least one rotating component has a gear fault and the type of the gear fault is a gear wear fault in response to the obtained characteristic data being characterized in the frequency domain as the presence of a natural frequency of the gear, accompanied by gear speed frequency sidebands on both sides of the natural frequency of the gear, and the amplitude of the gear meshing frequency being greater than a normal value for more than a predetermined number of times. The gear meshing frequency GMF is equal to the number of teeth of the low-speed gear multiplied by the rotational frequency of the low-speed gear, and is equal to the number of teeth of the high-speed gear multiplied by the rotational frequency of the high-speed gear.

[0102] In addition, the characteristic data of gear wear faults in the frequency domain often show that the amplitude (or magnitude) under 2GMF and 3GMF is often very high (for example, 2 or 3 times that of normal conditions).

[0103] The fault diagnosis module can determine that at least one rotating component has a gear fault and the type of the gear fault is a gear crack, and determine that at least one rotating component has a gear fault and the type of the gear fault is a gear crack in response to the acquired characteristic data, which is manifested in the time domain as an impact pulse with a period corresponding to the time of the gear rotation frequency and in the frequency domain as a main frequency domain feature with multiples of the gear rotation frequency.

[0104] The fault diagnosis module can respond to the acquired characteristic data expressed in the frequency domain as the gear meshing frequency and the gear meshing harmonic frequency as the carrier frequency, the rotation frequency of the shaft where the gear is located and the multiples of the rotation frequency as the modulation frequency, the various orders of natural frequencies of the gear as the carrier frequency and the modulation sideband is wider and higher than the sideband bandwidth under normal circumstances, and determine that at least one rotating component has a gear fault and the type of gear fault is a broken gear.

[0105] The fault diagnosis module can determine that there is a gear fault in at least one rotating component and the type of gear fault is gear eccentricity in response to the acquired characteristic data, which is manifested in the time domain as amplitude modulated vibration, in the frequency domain as a pulse amplitude at the gear rotation frequency greater than a predetermined value, and there is a load fluctuation with a period of one gear rotation and the gear rotation frequency as the modulation frequency.

[0106] The fault diagnosis module can determine that there is a gear fault in at least one rotating component and the type of gear fault is gear misalignment in response to the acquired characteristic data being expressed in the frequency domain as the gear meshing frequency and the gear meshing harmonic frequency as the carrier frequency, the rotation frequency of the shaft where the gear is located and the multiples of the rotation frequency as the modulation frequency, the amplitude at the double frequency of the modulation frequency is the largest, and the amplitudes of the sideband frequencies on the left and right sides of the gear meshing frequency and the gear meshing harmonic frequency are unequal.

[0107] The fault diagnosis module can determine that there is a belt fault in at least one rotating component and the type of the belt fault is belt wear, belt looseness or belt mismatch in response to the acquired characteristic data showing in the frequency domain that the double frequency of the belt speed frequency is dominant over the belt speed frequency, the vibration amplitude of the belt is unstable, the vibration amplitude at the belt vibration frequency is greater than the vibration amplitude at the belt vibration harmonic frequency, and the belt vibration frequency is lower than the belt driven speed frequency.

[0108] The fault diagnosis module can determine that at least one rotating component has a belt fault and the type of the belt fault is belt resonance in response to the obtained characteristic data, which is manifested in the frequency domain as a vibration amplitude greater than a third predetermined threshold when the belt's natural frequency is consistent with the belt's driven speed frequency, and the natural frequency changes when the belt tension changes.

[0109] The fault diagnosis module can determine that at least one rotating component has a belt fault and the type of the belt fault is belt eccentricity in response to the obtained characteristic data being manifested in the frequency domain as a vibration amplitude of the pulley at the belt speed frequency being greater than a fourth predetermined threshold.

[0110] The fault diagnosis module can determine that at least one rotating component has a belt fault and the type of the belt fault is misalignment of the belt or pulley in response to the obtained characteristic data being expressed in the frequency domain as an axial vibration amplitude of the pulley at the belt speed frequency being greater than a fifth predetermined threshold. The above-mentioned pulley-related predetermined thresholds can all be empirical values.

[0111] Power frequency faults may include rotor dynamic unbalance, rotor misalignment and other power frequency faults.

[0112] The fault diagnosis module can determine that at least one rotating component has an industrial frequency fault and the type of the industrial frequency fault is rotor dynamic imbalance in response to the obtained characteristic data showing in the frequency domain that the amplitude of the fundamental frequency is greater than a first predetermined threshold and the amplitude at one times the industrial frequency is greater than the amplitude at twice the industrial frequency.

[0113] The fault diagnosis module can determine that at least one rotating component has a power frequency fault and the type of the power frequency fault is rotor misalignment in response to the acquired characteristic data showing in the frequency domain that the amplitude at twice the power frequency is greater than a second predetermined threshold and greater than or equal to the amplitude at one times the power frequency.

[0114] In addition to the above two faults, there may be other power frequency faults such as rotor bending. The specific characteristics are shown in Table 6.

[0115] Table 6

[0116]

[0117] The power frequency fault can be judged as rotor bending by at least two of the characteristics in Table 6.

[0118] Among the failures of rotating parts, bearing failures are divided into inner ring failure, outer ring failure, rolling element failure and cage failure according to the location of occurrence.

[0119] In bearing fault diagnosis, the main methods may include time series waveform effective value analysis, kurtosis coefficient method and envelope spectrum analysis, etc. Time series waveform effective value analysis method is applicable to the condition of long-term wear or surface roughness. The higher the effective value, the greater the degree of wear. The kurtosis coefficient method is applicable to early fault judgment and is more sensitive to large impacts. In envelope spectrum analysis, the fault is mainly defined based on the amplitude of the fault characteristic frequency of the inner ring, outer ring, rolling element and cage.

[0120] Specifically, the fault diagnosis module may determine that at least one rotating component has a bearing fault in response to the acquired characteristic data being represented in the frequency domain as an amplitude at the bearing frequency exceeding a predetermined threshold (eg, a sixth threshold). The predetermined threshold here may also be an empirical value.

[0121] Figure 5 is a logical architecture diagram showing a device health and fault management system according to an embodiment of the present disclosure, Figure 6 is a diagram showing a physical deployment of a device health and fault management system according to an embodiment of the present disclosure.

[0122] Reference Figure 5According to the logical architecture of the equipment health and fault management system of the embodiment of the present disclosure, the detection module 110 may be located in the perception layer, the processing module 120 may be located in the data platform layer, a part of the alarm module 130 may be located in the data platform layer, another part of the alarm module 130 may be located in the application layer, a part of the fault diagnosis module may be located in the data platform layer, and another part of the fault diagnosis module may be located in the application layer.

[0123] Reference Figure 5 The data storage, data processing (or data processing), model calculation, etc. involved in the equipment health and fault management system of the embodiment of the present disclosure can all be located in the data platform layer. Data processing and model calculation related to the fault diagnosis module can all be located in the data platform layer, and the algorithm model of the fault diagnosis module and related analysis tools can all be located in the application layer.

[0124] The perception layer can collect real-time operation data of equipment through sensors, PLC / DCS and edge gateways, and can extract multiple indicators from it. The data platform layer is responsible for managing data, including data acquisition, storage, analysis and calculation, and providing data services for upper-level applications.

[0125] The data platform layer needs to establish unified data standards, accept data uploaded by edge gateways, and provide data for business services, model training, and calculations.

[0126] The application layer provides services to end users. Based on the underlying data support and service middle platform, it provides users with module services such as equipment operation and maintenance, asset management, energy consumption management, quality control, and process optimization.

[0127] A portion of the fault diagnosis module of the embodiment of the present disclosure may be located at the application layer, and another portion of the fault diagnosis module may be located at the data platform layer.

[0128] Reference Figure 6 , the equipment operation data collected by the sensor can be stored in the CMS data receiving server through the core switch, and can be stored in the CMS data storage server (the number of CMS data storage servers can be two) through the core switch after passing through the firewall. The CPHM algorithm model platform can also exchange data with the CPHM application server through the core switch, and positive isolation is adopted between the CPHM application server and the CPHM HMI. The CMS data receiving server, CMS data storage server, CMHM application server, CPHM data server, and CPHM algorithm model platform can all be deployed in the production network, and the CPHMHMI is deployed in the office network. The physical deployment diagram of the equipment health and fault management system according to the embodiment of the present disclosure is not specifically limited.

[0129] It should be understood that each unit or module according to the exemplary embodiments of the present disclosure can be implemented by hardware components and / or software components. Those skilled in the art can implement each unit according to the processing performed by each defined unit, for example, using a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a software algorithm, etc.

[0130] According to various embodiments of the present disclosure, a device (e.g., a module or their functions) or a method may be implemented by a program or instruction stored in a computer-readable storage medium. When the instruction is executed by a processor, the processor may perform a function corresponding to the instruction or perform a method corresponding to the instruction. At least a portion of a module may be implemented (e.g., executed) by a processor. At least a portion of a programming module may include a module, a program, a routine, an instruction set, and a process for performing at least one function. In one example, an instruction or software includes a machine code (such as a machine code generated by a compiler) directly executed by one or more processors or computers.

[0131] Computer-readable storage media include non-transitory computer-readable storage media, for example, magnetic media such as floppy disks and tapes, optical media (including compact disks (CD) ROMs and DVD ROMs), magneto-optical media such as floppy disks, hardware devices such as ROMs, RAMs, and flash memories designed to store and execute program commands. Program commands include language codes executable by a computer using an interpreter and machine language codes generated by a compiler. The above-mentioned hardware devices can be implemented by one or more software modules for performing the operations of the various embodiments of the present disclosure.

[0132] The module or programming module of the present disclosure may include at least one of the aforementioned components when some components are omitted or other components are added. The operation of the module, programming module or other components may be performed sequentially, in parallel, in a loop or in a tentative manner. In addition, some operations may be performed in different orders, may be omitted or extended with other operations.

[0133] The equipment health and fault management system according to the embodiment of the present disclosure can accurately judge the status of the equipment and perform predictive maintenance on faults, which will effectively improve enterprise management efficiency and reduce the comprehensive operation and maintenance management costs of the enterprise.

[0134] The equipment health and fault management system according to the embodiment of the present disclosure can avoid excessive maintenance, prevent the reduction of equipment accuracy due to unnecessary disassembly, and extend the life of the equipment.

[0135] Although some exemplary embodiments of the present disclosure have been shown and described, it will be understood by those skilled in the art that modifications may be made to these embodiments without departing from the principles and spirit of the present disclosure, the scope of which is defined by the claims and their equivalents; for example, the technical features of different embodiments may be combined.

Claims

1. A device health and fault management system, characterized in that: The equipment health and fault management system includes: A detection module, configured to detect operation data of at least one measurement point of the device; a processing module, configured to process the operation data to extract a plurality of indicators; an alarm module, configured to determine the state of the device according to the operating data, the multiple indicators and a pre-specified alarm model, Among them, the alarm model includes a hard threshold alarm model and an adaptive threshold alarm model. The hard threshold alarm model compares the multiple indicators with the corresponding first fixed threshold. The adaptive threshold alarm model determines the corresponding first adaptive threshold based on the historical operation data stored in a predetermined time period before the detection moment and the corresponding multiple historical indicators, and compares the multiple indicators with the corresponding first adaptive threshold.

2. The equipment health and fault management system according to claim 1, characterized in that: The alarm module is further configured to: in response to the multiple indicators being greater than corresponding first fixed thresholds and / or the multiple indicators being greater than corresponding first adaptive thresholds, determine that the state of the device is abnormal.

3. The equipment health and fault management system according to claim 1, characterized in that: The adaptive threshold alarm model processes the stored historical operation data within a predetermined time period before the detection moment and the corresponding multiple historical indicators by using at least one of statistical regression, time series prediction and machine learning to automatically obtain the corresponding first adaptive threshold. The corresponding first fixed threshold is preset by a user, and the alarm model is specified by a user.

4. The equipment health and fault management system according to claim 2, characterized in that: The alarm module is further configured to determine the abnormality degree of the device state according to the difference between the multiple indicators and the corresponding threshold values, classify the abnormality degree of the device state, and push corresponding alarm information in a graded manner.

5. The equipment health and fault management system according to claim 4, characterized in that: The operation data includes rotation speed and vibration data, and the multiple indicators include waveform indicators, spectrum indicators and envelope indicators of the vibration data.

6. The equipment health and fault management system according to claim 5, characterized in that: The alarm module is further configured to comprehensively judge the status of the device by combining a pre-established health and fault knowledge base and a health and fault case base.

7. The equipment health and fault management system according to claim 1, characterized in that: The equipment health and fault management system further comprises a fault diagnosis module, and the equipment is a coal mining equipment comprising at least one rotating component, The fault diagnosis module is configured to: receive alarm information from the alarm module, and in response to the alarm information being alarm information indicating that the state of the device is abnormal, determine a fault diagnosis item corresponding to the at least one rotating component; process the vibration data in the operation data to obtain characteristic data; According to the acquired characteristic data and the fault characteristic of the fault diagnosis item, it is determined whether the at least one rotating component has a fault corresponding to the fault diagnosis item.

8. The equipment health and fault management system according to claim 7, characterized in that: The fault diagnosis module is further configured to: in response to the acquired characteristic data presenting at least one fault characteristic of a gear fault, a power frequency fault, a belt fault and a bearing fault, determine that the at least one rotating component has a fault corresponding to the fault diagnosis item.

9. The equipment health and fault management system according to claim 8, characterized in that: The at least one rotating component includes at least one of a crusher, a belt conveyor, a scraper, a vibrating screen, and a briquetting machine.

10. The equipment health and fault management system according to claim 9, characterized in that: The at least one measuring point of the crusher includes at least one of: a motor free end, a motor load end, a gearbox shaft output side, a gearbox shaft input side, a gearbox output side, a crushing shaft input side, and a crushing shaft output side; The at least one measuring point of the belt conveyor includes: at least one of the pedestrian side of the roller, the non-pedestrian side of the roller, the free end of the motor, the load end of the motor, the input side of the hydraulic coupler, the output side of the hydraulic coupler, the input shaft of the gearbox, the output shaft of the gearbox, the input side of the gearbox shaft, the output side of the gearbox shaft, the driving side of the driving part roller, the non-driving side of the driving part roller, the pedestrian side of the tensioning room roller, and the non-pedestrian side of the tensioning room roller; The at least one measuring point of the scraper comprises: at least one of the free end of the motor, the load end of the motor, the input shaft of the gearbox, the output shaft of the gearbox, the input side of the gearbox shaft, the output side of the gearbox shaft, the input side of the head sprocket, the output side of the head sprocket, the input side of the tail sprocket, and the output side of the tail sprocket; The at least one measuring point of the vibrating screen includes: at least one of a belt-related measuring point, a motor free end, a motor load end, and a main shaft of the vibrating screen; At least one measuring point of the briquetting machine includes: at least one of the free end of the motor, the load end of the motor, the input side of the reducer shaft, the output side of the reducer shaft, the input side of the movable roller shaft, the output side of the movable roller shaft, the input side of the fixed roller shaft, the output side of the fixed roller shaft, the load end of the forced feeder motor, and the input side of the forced feeder reducer shaft.

11. The equipment health and fault management system according to claim 7, characterized in that: The logical architecture of the equipment health and fault management system includes a perception layer, a data platform layer and an application layer. The detection module is located in the perception layer, the processing module is located in the data platform layer, a part of the alarm module is located in the data platform layer, another part of the alarm module is located in the application layer, a part of the fault diagnosis module is located in the data platform layer, and another part of the fault diagnosis module is located in the application layer.

Images