CN108921305B - Component life period monitoring method - Google Patents
Component life period monitoring method Download PDFInfo
- Publication number
- CN108921305B CN108921305B CN201810621885.5A CN201810621885A CN108921305B CN 108921305 B CN108921305 B CN 108921305B CN 201810621885 A CN201810621885 A CN 201810621885A CN 108921305 B CN108921305 B CN 108921305B
- Authority
- CN
- China
- Prior art keywords
- data
- model
- component
- aging
- factor
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Testing Resistance To Weather, Investigating Materials By Mechanical Methods (AREA)
Abstract
The invention relates to the field of health management and fault prediction of equipment components, in particular to a component life period monitoring method. A method for monitoring the lifetime of a component, comprising the steps of: A) establishing a baseline model of the life cycle of the component; B) adjusting the baseline model according to the use condition of each component to obtain an independent model of each component; C) and comparing the use condition of the component with the independent model of the component to obtain the life monitoring information of the component. The substantial effects of the invention are as follows: the method is combined with the life pressure test, the number of the obtained effective data samples is sufficient, the data acquisition is comprehensive, and the model establishment for life period comparison is more detailed, so that the life period of the part can be monitored more comprehensively and accurately.
Description
Technical Field
The invention relates to the field of health management and fault prediction of equipment components, in particular to a component life period monitoring method.
Background
With the development of the mechanical electronic industry in China, the functions of mechanical electronic equipment are more and more abundant and diversified, and the problems that the mechanical electronic equipment tends to be more complex and unreliable while the production and the life of people are greatly improved are also solved. In order to maintain a good and safe operation of the electromechanical device, which includes many parts and electronics, the operator must regularly organize the maintenance and service of the electromechanical device. At present, the maintenance tasks of electromechanical equipment mainly comprise two modes of original factory charge and third party contract, and the adopted maintenance method is almost that maintenance personnel are dispatched regularly to carry out field maintenance operation. Due to the lack of effective supervision measures, the problem that the maintenance quality does not reach the standard exists in field maintenance of maintenance personnel, so that many electromechanical equipment operate with diseases, and great potential safety hazards exist. According to statistics in the industry, eighty percent of the causes of failure and accidents of electromechanical equipment are caused by insufficient maintenance. At present, the economic development of China is rapid, the deployment amount and increment of electromechanical equipment are all in high positions, the number of maintenance personnel cannot be increased, and the problems that the work of the maintenance personnel is heavy, and the maintenance personnel have general training deficiency and poor quality are caused. And the increase of wages and training expenses for maintenance personnel leads to the fact that part of maintenance contract units are pressed down to be used for budget of maintenance equipment purchase, and the quality and reliability of periodic field maintenance are further reduced. Maintenance personnel maintain the products on site at regular intervals, and the defects of unbalanced maintenance, lack of pertinence and low efficiency exist. Today, the maintenance task is increasingly heavy, and the requirement for safe and stable operation of the electromechanical equipment can not be met by only depending on a manual regular field maintenance mode.
At present, some technical schemes for improving the monitoring effect of the maintenance field appear, the contradiction that the existing electromechanical equipment is lack of sufficient maintenance and insufficient maintenance resources and low in quality can be relieved, all-round guidance can not be provided for maintenance operation, and the life cycle and the health condition of the electromechanical equipment and parts can not be monitored. If the life cycle and the health state of the electromechanical device and the component can be accurately grasped, accurate maintenance can be performed. The maintenance task amount is greatly reduced, and the maintenance quality can be improved. The component can be discovered immediately before damage or failure, and corresponding measures are taken to avoid adverse consequences. However, the current methods for fault prediction and alarm of electromechanical devices and components have the following problems: 1) the modeling theory basis is insufficient, the algorithm model is simple, the industry generally adopts a historical fault library as a comparison basis at present, only can give an alarm on main faults which frequently occur, and can not judge whether faults which do not occur or have small probability or even frequently misjudge whether faults occur or not; 2) data sharing is difficult, the number of effective samples is insufficient, and due to the fact that fault data need to be accumulated, sample data can be obtained only after equipment fails, so that the sample data collection period is long, the total amount of the sample data is small, unified standards are lacked among service systems, fault recording samples are stored independently, and sharing is difficult to form; 3) the method for predicting the pseudo-aging period exists, a small amount of fault symptoms of electromechanical equipment and parts or data collected by a main sensor are directly used as early warning information in the industry at present, and the one-sided fault symptom judgment brings more uncertainty and reduces the accuracy of a monitoring result; 4) the false alarm rate is high, the prediction result is divergent, and due to the lack of a modeling theoretical basis, simple and crude comparison foundation, less total amount of effective sample data and rough prediction model of the aging period, the false alarm rate is high, and the convergence of the prediction result is poor.
Chinese patent CN 106952028A, published 2017, 7, month 14, a method and a system for electromechanical equipment fault pre-diagnosis and health management, comprising: acquiring data, namely acquiring data information of electromechanical equipment; self-diagnosis, namely performing feature extraction and model establishment on historical data information of a certain electromechanical device in different operation modes and health states, comparing the data information acquired in the current state with the historical data information by using the established model, and automatically identifying the current health state of the electromechanical device; predicting the health state, namely predicting the future health state change of the electromechanical equipment according to the current health state and the historical health state of the electromechanical equipment obtained after self-diagnosis; and cluster analysis, namely clustering, analyzing and comparing the data information of the plurality of electromechanical equipment in the electromechanical equipment cluster according to the current health state of the single electromechanical equipment to obtain the health state grades and risk distribution of the plurality of electromechanical equipment. The technical scheme still adopts the historical fault library of the equipment and the components as a comparison reference, so that the problems of small number of effective samples and rough comparison model exist, and the monitoring result is incomplete and poor in accuracy.
Chinese patent CN 103241658B, open day 2015 year 9 months 23 days, hoist metal structure health monitoring and safety precaution system based on thing networking includes: the system comprises an Internet of things sensing layer, an Internet of things network layer and an Internet of things application layer, wherein the Internet of things sensing layer is used for acquiring optical signals of health parameters of a metal structure of the crane, demodulating the optical signals into electric signals, compressing and packaging the electric signals of sensing data and transmitting the electric signals to the Internet of things network layer; the Internet of things network layer is used for receiving the electric signal data, identifying the electric signal and sending the identified data to the Internet of things application layer; and the Internet of things application layer calculates the received data and judges whether to send out an alarm signal. The invention is based on the technology of the Internet of things, can carry out real-time health monitoring and safety early warning on the metal structure of the large crane in the whole life cycle all day long, and has the characteristics of no electromagnetic interference, high precision, wide range, high reliability, long service life and the like. The problem of incomplete data acquisition does not exist because strain information is acquired aiming at a mechanical structure, but the problem of incomplete data acquisition does not exist, but an effective and comprehensive comparison reference is lacked although required information can be acquired, and the comparison reference still depends on historical fault data, so that the problem of incomplete and inaccurate life period monitoring results is still not solved.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: at present, the technical problem that the monitoring of the life cycle of electromechanical equipment and parts is not complete and inaccurate is solved. The method for monitoring the life cycle of the component is more comprehensive and more accurate in the life cycle monitoring result of the comparison model established by combining the life pressure test data and the historical fault data.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows: a method of component lifetime monitoring, comprising the steps of: A) establishing a baseline model of the life cycle of the component; B) adjusting the baseline model according to the use condition of each component to obtain an independent model of each component; C) and comparing the use condition of the component with the independent model of the component to obtain the life monitoring information of the component. At present, a historical fault library is used as a comparison reference for fault and life cycle monitoring, and a component life cycle baseline model obtained by an accelerated life test is used as the comparison reference, so that a more comprehensive and accurate monitoring result can be obtained. In the accelerated life test process, the sensors used in the practical application and the accelerated life test process can be unified, so that the matching degree of the test data and the actually acquired data is higher, and the accuracy of life period monitoring is improved. In the baseline model, a plurality of adjustable coefficient values exist, and the values of all the coefficients can be determined according to an accelerated life test to form a reference coefficient; however, in practical application, because the deployment environments of each component are different, if the life cycle models of different components are classified into one model, the model lacks pertinence, and therefore, an independent model of each component is established after a reference coefficient is corrected according to the component deployment environments during life cycle monitoring, the adaptation degree of a single component mode is improved, the life cycle monitoring accuracy and reliability are further improved, and the false alarm rate is reduced.
Preferably, the method for establishing the baseline model comprises the following steps: A1) defining aging factors, environmental factors and life time feedback of the component; A2) taking an engineering theoretical model and/or an industry experience life period model as a basic model; A3) carrying out accelerated life test and/or simulation test on each aging factor to obtain single aging factor test data, and substituting the single aging factor test data into the basic model to obtain a life period model of the single aging factor; A4) carrying out accelerated life test and/or simulation test on each pair of single environmental factors and the combination of the single aging factors to obtain test data of the combination of the single environmental factors and the single aging factors, and substituting the test data into the basic model to obtain a life period model of the combination of the single environmental factors and the single aging factors; A5) carrying out accelerated life test and/or simulation test on a plurality of environmental factors and a plurality of aging factors to obtain multi-factor data; A6) manually setting a functional relation with an initial weight value for a life model of a single aging factor and a life model of a single environmental factor and a single aging factor combination to form an initial baseline model, establishing a fitting model of the weight value, the aging factor and the environmental factor according to multi-factor data, and combining the fitting model and the initial baseline model to serve as a life baseline model of the component.
Preferably, the aging factors are subjected to accelerated life tests, and the data acquisition method for acquiring the test data of the single aging factor comprises the following steps: if the aging factor is transient from the environmental state to the test state, acquiring aging factor data and life cycle feedback data at intervals t1 and associating the data with time data when the aging factor is in the test state, otherwise, acquiring the aging factor data and the life cycle feedback data at intervals t2 and associating the data with the time data through a conversion function when the aging factor is changed from the environmental state to the test state, and then acquiring the aging factor data and the life cycle feedback data at intervals t1 and associating the data with the time data when the aging factor is in the test state; the accelerated life test is carried out on each pair of the environmental factors and the combination of the aging factors, and the method for obtaining the test data of the single environmental factor and the single aging factor combination comprises the following steps: if the aging factor and the environmental factor are transient processes from the environmental state to the test state, the aging factor data, the environmental factor data and the life cycle feedback data are collected at intervals of time t1 and are associated with the time data when the aging factor and the environmental factor are in the test state, otherwise, the aging factor data, the environmental factor data and the life cycle feedback data are collected at intervals of time t2 and are associated with the time data through a conversion function when the aging factor and the environmental factor are in the test state, and then the aging factor data, the environmental factor data and the life cycle feedback data are collected at intervals of time t1 and are associated with the time data when the aging factor and the environmental factor are in the test state, wherein the intervals of time t1 and t2 are set manually. In the existing accelerated life test process, a part or equipment is placed in a test state, the part or the equipment is taken out only after the duration of set time to detect whether the part or the equipment is invalid or not, data acquisition is not carried out on the intermediate process, and the obtained life test data is rough. In the accelerated life test, if the test factor can not be transient, if the temperature drop can not be transient, a cooling time is needed, in the existing accelerated life test, data in the cooling process is not collected, and data resources are wasted.
Preferably, the life feedback includes a component failure sign and a failure symptom, and a failure sign model and a failure symptom model of the component are established by the factor data. The failure sign model indicates that the component has a bad state, but still can finish the data expression when the function is completed, and at the moment, the failure sign alarm is carried out, and maintenance personnel are assigned to carry out on-site inspection and confirmation; and the failure symptom refers to data representation when the component fails to complete the function, and at the moment, failure alarm is carried out and automatic repair is called.
Preferably, the aging factor, environmental factor and life feedback data of the component each include sensor sampling data and manual testing setting data. If the part has aging factors or environmental factors needing manual intervention, the value of the aging factors or environmental factors can be partially acquired by a sensor (such as the lubricating oil level), but in some cases, the sensor is difficult to acquire (such as whether the lubricating grease is sufficient or not), and manual setting is needed (such as setting the lubricating grease to be sufficient after the lubricating grease is added).
Preferably, the sensor sampling data of the aging factors, the environmental factors and the life cycle feedback data are acquired and uploaded by a sensor with the function of the internet of things, which is arranged on the component.
Preferably, the set data of the aging factors, the environmental factors and the life cycle feedback data are uploaded and set during manual detection, and are kept unchanged or changed according to a set function during two times of manual detection; and after the artificial detection, calculating a difference value between the detection value and the value calculated by the setting function according to the last detection value, wherein the setting data of the artificial detection of the aging factors and the environmental factors which are changed according to the setting function are uploaded as life cycle feedback data. The setting function is given by an empirical function (if the part needs to use lubricating grease, standard dosage of lubricating grease is added during maintenance, sufficient lubricating grease is set and is represented by a number 1, then the value of the lubricating grease serving as an environmental factor is gradually reduced from 1 along the setting function before the next maintenance, the setting function can be determined after multiple tests are manually carried out, during the next maintenance, the residual quantity of the lubricating grease is manually judged, the calculated residual quantity is compared with the residual quantity calculated according to the setting function, the difference value is used as life-period feedback data, if the actual residual quantity of the lubricating grease of the part is lower than the residual quantity calculated according to the setting function, and the difference value exceeds a threshold value, the working state of the part is judged to be poor, and the lubricating grease consumption speed is too high).
Preferably, the method for establishing the independent model comprises the following steps: B1) partitioning the area for each environmental factor; B2) when the part is deployed for the first time or the interval where the environmental factors of the part are located changes, N1 data collected later are substituted into the baseline model, and the independent model of the part is updated, wherein N1 is a positive integer set by a human. When the part is newly deployed by inspection and acceptance, the part is unlikely to break suddenly and is most trusted to the performance and reliability of the part, the acquired data are considered as data in the health state of the part, the part of data is used for correcting the baseline model and is reliable, after the independent model is obtained, the independent model is not modified, the acquired data are used for comparing with the independent model, and the difference value is used as a basis for judging whether the part works healthily; if the change of the environmental factor interval is detected, parameters in the independent model need to be adjusted, the first N1 times of sampling of the model after the change of the environmental factor interval is detected are used for correcting the independent model, and the acquired data are used as a basis for judging whether the component runs healthily. The value of N1 should be adjusted as needed for all coefficients involved in environmental changes. As recommendation, the value of N1 is 2-5, when the number of the coefficients needing to be adjusted is large, the value is large, and when the number of the coefficients needing to be adjusted is small, the value is small.
Preferably, in step C, the method for comparing the usage of the component with the independent model of the component to obtain the lifetime monitoring information of the component includes: C1) substituting the collected aging factors and environmental factor data of the component into the independent component model, if the difference value between the life-time feedback data calculated by the independent model and the collected life-time feedback data exceeds a set threshold value, sending out a warning and/or marking a maintenance project of the component, otherwise, updating the residual life of the component; C2) when the collected aging factors, environmental factors and life cycle feedback data of the components accord with the failure symptom model, sending out warning and/or marking maintenance items of the components; C3) and when the collected aging factors, environmental factors and life-span feedback data of the components accord with the failure symptom model, warning and/or automatic repair are/is given out.
Preferably, in step C, the service condition of the component is compared with the independent model and the similar model of the component at the same time, and the life cycle monitoring information of the component is obtained; the method for establishing the same-class model comprises the following steps: CC 1) all components in the monitoring are divided into a plurality of groups according to the use condition and/or the environmental condition; CC 2) collecting N2 data of the aging factors, the environmental factors and the life cycle feedback of each component in each group, and eliminating the data of the aging factors or the environmental factors with the data values beyond the set range in the set, wherein N2 is a positive integer set by people; CC 3) respectively substituting each group of data into the basic model and carrying out equalization processing to obtain the same type model of each group of components. The single component has its independent model, the basis of independent model establishment is the sampling data of baseline model and only single component, because the individual data lacks stability and accuracy, therefore the invention adopts and groups the component under the similar working condition, make statistics and order to a large number of individuals in the group, remove the data sample with trouble, only keep the data of the normal working individual, put into the baseline model after the equalization, solve the homogeneous model, the homogeneous model has higher accuracy compared with the baseline model, and its establishment is flexible, can be on the basis of data collected in short term after the apparatus is put into operation, the data collection and modeling cycle are short.
Preferably, the method for comparing the use condition of the component with the independent model and the similar model of the component at the same time comprises the following steps: and respectively substituting the collected aging factors and environmental factor data of the component into the independent model and the similar model of the component, and if the difference value between the life feedback data calculated by the independent model or the similar model and the collected life feedback data exceeds a set threshold value, sending out a warning and/or marking the maintenance project of the component.
Preferably, step C is followed by the step of: D) and when the quantity of the collected aging factors, environmental factors and life cycle feedback data of the components of the same model exceeds a set value, correcting the basic model, and updating the life cycle baseline model of the components in the step A. After a large amount of actual data is obtained, manual analysis can be carried out, a new experience model or theoretical model in the industry is established, the baseline model is updated accordingly, a more accurate reference baseline model is provided for subsequently deployed components, and the life cycle monitoring accuracy is further improved.
Preferably, when the component performs maintenance work, the maintenance field data used for correcting the basic model is collected, and the aging factor, the environmental factor and the life cycle feedback data of the component are uploaded. And when maintaining the site, collecting sound data and/or image data of the maintenance site, wherein the sound data and/or image data are used as life cycle feedback data of the component, and providing data support for establishing a new basic model. When the field data is accumulated sufficiently, the life cycle monitoring of the component can be added with sound and/or images to serve as life cycle feedback data, so that the accuracy of the life cycle monitoring result is verified in an auxiliary mode, and the monitoring accuracy is improved.
The substantial effects of the invention are as follows: the method is combined with the life pressure test, the number of the obtained effective data samples is sufficient, the data acquisition is comprehensive, and the model establishment for life period comparison is more detailed, so that the life period of the part can be monitored more comprehensively and accurately.
Drawings
Fig. 1 is a flow chart of a life cycle monitoring method.
Detailed Description
The following provides a more detailed description of the present invention, with reference to the accompanying drawings.
As shown in fig. 1, the lifetime monitoring method includes the following steps: A) establishing a baseline model of the life cycle of the component; B) adjusting the baseline model according to the use condition of each component to obtain an independent model of each component; C) and comparing the use condition of the component with the independent model of the component to obtain the life monitoring information of the component.
For illustration purposes: the ultraviolet intensity and the using times are used as independent variables of the baseline model, a coefficient is set for the ultraviolet intensity and the using times, and a group of reference coefficients can be determined according to the accelerated life test result data. In practical application, the change range of the environmental ultraviolet rays is limited, so that the reference coefficient can accord with the change rule of the environmental ultraviolet rays on the life cycle; however, the accelerated life test cannot exhaust all environmental states, when the component is deployed in a state that the ultraviolet intensity is far higher than the accelerated life test state, such as in space, the ultraviolet intensity is far higher than the intensity when the component is used on the ground, and the corresponding coefficient does not accord with the change rule of the ultraviolet change to the life stage any more, so that the coefficient of the ultraviolet needs to be increased, the proportion of the ultraviolet to the aging of the life stage is improved, and a baseline model after the coefficient is adjusted is used as an independent model for monitoring the component.
The method for establishing the baseline model comprises the following steps: A1) defining aging factors, environmental factors and life time feedback of the component; A2) taking an engineering theoretical model and/or an industry experience life period model as a basic model; A3) carrying out accelerated life test and/or simulation test on each aging factor to obtain single aging factor test data, and substituting the single aging factor test data into the basic model to obtain a life period model of the single aging factor; A4) carrying out accelerated life test and/or simulation test on each pair of single environmental factors and the combination of the single aging factors to obtain test data of the combination of the single environmental factors and the single aging factors, and substituting the test data into the basic model to obtain a life period model of the combination of the single environmental factors and the single aging factors; A5) carrying out accelerated life test and/or simulation test on a plurality of environmental factors and a plurality of aging factors to obtain multi-factor data; A6) and manually setting a functional relation with an initial weight value for a life model of a single aging factor and a life model of a single environmental factor and a single aging factor combination to form an initial baseline model, establishing a fitting model of the weight value, the aging factor and the environmental factor according to multi-factor data, and combining the fitting model and the initial baseline model to serve as a life model of the component.
For illustration purposes: let A, B and C be aging factors, respectively establishing life period models W (A), W (B) and W (C) of single aging factors and life period models W (AD), W (BE) and W (CF) of single environmental factors and single aging factor combination in step A3 and step A4, artificially setting the function relationship with initial weight value to form an initial baseline model of Wbase= aw (a) + bw (B) + cw (C) + dw (ad) + ew (be) + fw (cf), where a, B, C, D, E and F are weight values, a large number of W, a, B, C, D, E, F are obtained in step a5]Data sets of the format, i.e. multifactor data, will be each set [ W, A, B, C, D, E, F]Substitution into Wbase= aW (A) + bW (B) + cW (C) + dW (AD) + eW (BE) + fW (CF), aging factors and environmental factor data [ A, B, C, D, E, F can be obtained]And model coefficients [ a, b, c, d, e, f [ ]]Fitting the mapping relation to obtain a fitting model Q ([ A, B, C, D, E, F) of the weight value, the aging factor and the environmental factor],[a,b,c,d,e,f]) When in application, the collected aging factor and environmental factor data [ A, B, C, D, E, F]Substituting into fitting model Q ([ A, B, C, D, E, F)],[a,b,c,d,e,f]) To obtain corresponding [ a, b, c, d, e, f [ ]]The resulting [ a, b, c, d, e, f ] is]Substitution into WbaseThe baseline model solution value W can be obtained by = aW (A) + bW (B) + cW (C) + dW (AD) + eW (BE) + fW (CF)baseFeedback data W and W of life period collected actuallybaseAnd comparing, if the difference exceeds the threshold value, judging that the model does not accord with the baseline model, otherwise, judging that the model accords with the baseline model. In this case WbaseIn the model (a), (b), (c), (ad), (be) and (cf), the calculation relationship may be other types, such as a multiplication relationship, a combination of multiplication and addition, or an exponential relationship, the setting of the calculation relationship only affects the calculation amount and the required data amount of the model establishment, and does not necessarily affect the model accuracy, the model may be established using the addition relationship as an initial relationship, and the calculation relationship may be adjusted according to the data and experience accumulation in the actual application process.
The accelerated life test is carried out on the aging factors, and the data acquisition method for acquiring the test data of the single aging factor comprises the following steps: if the aging factor is transient from the environmental state to the test state, acquiring aging factor data and life cycle feedback data at intervals t1 and associating the data with time data when the aging factor is in the test state, otherwise, acquiring the aging factor data and the life cycle feedback data at intervals t2 and associating the data with the time data through a conversion function when the aging factor is changed from the environmental state to the test state, and then acquiring the aging factor data and the life cycle feedback data at intervals t1 and associating the data with the time data when the aging factor is in the test state; the accelerated life test is carried out on each pair of the environmental factors and the combination of the aging factors, and the method for obtaining the test data of the single environmental factor and the single aging factor combination comprises the following steps: if the aging factor and the environmental factor are transient processes from the environmental state to the test state, the aging factor data, the environmental factor data and the life cycle feedback data are collected at intervals of time t1 and are associated with the time data when the aging factor and the environmental factor are in the test state, otherwise, the aging factor data, the environmental factor data and the life cycle feedback data are collected at intervals of time t2 and are associated with the time data through a conversion function when the aging factor and the environmental factor are in the test state, and then the aging factor data, the environmental factor data and the life cycle feedback data are collected at intervals of time t1 and are associated with the time data when the aging factor and the environmental factor are in the test state, wherein the intervals of time t1 and t2 are set manually.
The life feedback comprises component failure signs and failure symptoms, and a failure sign model and a failure symptom model of the component are established through factor data. The failure sign model indicates that the part generates a bad state or has obvious difference compared with a normal state, but still can finish the data expression when the function is completed, and at the moment, the failure sign alarm is carried out, and maintenance personnel are assigned to carry out on-site inspection and confirmation; and the failure symptom refers to data representation when the component fails to complete the function, and at the moment, failure alarm is carried out and automatic repair is called.
The aging factors, environmental factors and life feedback data of the components comprise sensor sampling data and manual detection setting data. The sensor sampling data of the aging factors, the environmental factors and the life cycle feedback data are acquired and uploaded by a sensor with the function of the Internet of things, which is arranged on the component. If there is a component having a aging factor or an environmental factor requiring manual intervention, the value of the aging factor or the environmental factor may be partially collected by a sensor, such as the level of the lubricating oil, but in some cases, it is difficult to collect by a sensor, such as whether the grease is sufficient or not, and since the grease in a paste form is inconvenient to detect using a sensor, it is necessary to manually check or perform data setting after the grease addition, such as setting the grease to be sufficient after the grease addition.
The set data of the aging factors, the environmental factors and the life cycle feedback data are uploaded and set during manual detection, and are kept unchanged or changed according to a set function during two manual detections; the aging factors and the environmental factors changed according to the set function are artificially detected, and the difference between the detection value and the value calculated by the set function according to the last detection value is calculated after artificial detection, and is uploaded as life cycle feedback data. Wherein the setting function is given by an empirical function. Specific examples include that grease is needed to be used for the part, standard amount of grease is added during maintenance, the grease is set to be sufficient and is represented by numeral 1, and then the value of the grease as an environmental factor is gradually reduced from 1 along a set function before the next maintenance, wherein the set function can be determined after multiple tests are manually carried out; and during next maintenance, manually judging the residual amount of the lubricating grease, comparing the calculated residual amount with the residual amount calculated according to the set function, and taking the difference value as life cycle feedback data, wherein if the actual residual amount of the lubricating grease of the component is lower than the residual amount calculated according to the set function and the difference value exceeds a threshold value, the working state of the component is judged to be poor, and the lubricating grease consumption speed is too high.
The method for establishing the independent model comprises the following steps: B1) partitioning the area for each environmental factor; B2) when the part is deployed for the first time or the interval where the environmental factors of the part are located changes, N1 data collected later are substituted into the baseline model, and the independent model of the part is updated, wherein N1 is a positive integer set by a human. When the part is newly deployed by inspection and acceptance, the part is unlikely to break suddenly and is most trusted to the performance and reliability of the part, the acquired data are considered as data in the health state of the part, the part of data is used for correcting the baseline model and is reliable, after the independent model is obtained, the independent model is not modified, the acquired data are used for comparing with the independent model, and the difference value is used as a basis for judging whether the part works healthily; if the change of the environmental factor interval is detected, parameters in the independent model need to be adjusted, the first N1 times of sampling of the model after the change of the environmental factor interval is detected are used for correcting the independent model, and the acquired data are used as a basis for judging whether the component runs healthily. The value of N1 should be adjusted as needed for all coefficients involved in environmental changes. As recommendation, the value of N1 is 2-5, when the number of the coefficients needing to be adjusted is large, the value is large, and when the number of the coefficients needing to be adjusted is small, the value is small.
In step C, comparing the usage of the component with the independent model of the component, and obtaining the lifetime monitoring information of the component is as follows: C1) substituting the collected aging factors and environmental factor data of the component into the independent component model, if the difference value between the life-time feedback data calculated by the independent model and the collected life-time feedback data exceeds a set threshold value, sending out a warning and/or marking a maintenance project of the component, otherwise, updating the residual life of the component; C2) when the collected aging factors, environmental factors and life cycle feedback data of the components accord with the failure symptom model, sending out warning and/or marking maintenance items of the components; C3) and when the collected aging factors, environmental factors and life-span feedback data of the components accord with the failure symptom model, warning and/or automatic repair are/is given out.
After step B, the step of: C) and when the quantity of the collected aging factors, the environmental factors and the life cycle feedback data of the components of the same model exceeds a set value, modifying the basic model to form a new experience life cycle model, and updating the life cycle baseline model of the components in the step A. After a large amount of actual data is obtained, manual analysis can be carried out, a new experience model in the industry is established, the baseline model is updated accordingly, a more accurate reference baseline model is provided for subsequently deployed components, and the life period monitoring accuracy is further improved.
When the component is subjected to maintenance operation, the maintenance field data is collected, and the aging factor, the environmental factor and the life cycle feedback data of the component are uploaded. And when the field is maintained, sound data and/or image data of the maintenance field are collected, and when the field data are accumulated sufficiently, a data base is provided for monitoring the life cycle of the component by adding sound and/or images as monitoring bases.
The first embodiment is as follows: the method for monitoring the life cycle of the button switch comprises the following steps:
F1) analyzing the function, failure mode, failure symptom and physical property of the button switch, wherein the button is a trigger device with an automatic rebounding function, when the button is pressed, the polar plate is connected to send an electric signal, then the button is rebounded rapidly after the external force is removed, and the polar plate is restored to the disconnected state. The button comprises two polar plates and a rubber layer which is arranged on the two polar plates and directly plays a role in resilience, when the rubber layer loses elasticity due to aging, the button polar plates rebound and slow after external force is removed, so that the on-time of the polar plates is prolonged, the performance of the button switch is reduced, and when the button switch is used, the button switch is startedThe rubber layer continues to age, so that the polar plate is always connected, namely the button is invalid and needs to be replaced; according to the combination of the physical knowledge, the failure main reason of the switch button is fatigue aging and oxidation aging of the rubber layer, the main reason influencing the fatigue aging of the rubber layer in practical application is the use times, the main reason influencing the oxidation aging of the rubber layer is temperature and ultraviolet intensity, (the oxygen concentration is stable, so the influence is constant and has no monitoring property), the use times of human factors are taken as aging factors, the temperature and the ultraviolet intensity are taken as environmental factors, and a theoretical model of setting the button switch is established as Wk-b=60000-a*n-b*T*ec*xWherein n is the number of times of use, x is the ultraviolet intensity index, T is the temperature, and a, b and c are model coefficients;
F2) the accelerated life test of the push-button switch was carried out, and the life results of the push-button switch under the influence of the number of times of use were carried out only, and the temperature and the ultraviolet intensity were kept constant, and sufficient W was obtainedk-b,n]Data set of the format, [ W ]k-b,n]Data sets of formats are substituted into Wk-b=60000-a*n-b*T*ec*xCalculating the values of a, b and c with the same number as the data sets, and after averaging, obtaining an aging model W (n) of the button switch for the aging factor with single use times;
F3) the accelerated life test is carried out on the button switch, and the influence of the use times on the life result of the button switch under the conditions of higher than environmental ultraviolet intensity, lower than environmental ultraviolet intensity, higher than environmental temperature or lower than environmental temperature is respectively carried out to obtain [ Wk-b,n,x]And [ W ]k-b,n,T]A data set of formats, like step F2, resulting in aging models W (n, x) of the push-button switches with respect to the number of uses and the ultraviolet intensity and aging models W (n, T) of the number of uses and the temperature;
F4) the accelerated life test is carried out on the button switch, and the influence of the use times on the life result of the button switch is obtained under the conditions that the intensity of ultraviolet rays is higher than or lower than the intensity of ultraviolet rays in the environment and the temperature is higher than or lower than the environment temperature, so that Wk-b,n,x,T]A data set of formats;
F5) establishing an initial baseline modelType (2): wbase= qW (n) + rW (n, x) + sW (n, T) where q, r, s are the initial coefficients, [ Wk-b,n,x,T]Substitution of the formatted data into the initial baseline model yields a set of values [ q, r, s [ ]]Establishing [ n, x, T ]]And [ q, r, s]And fitted to a function F ([ n, x, T)],[q,r,s]) The function F is used as a coefficient model, and the coefficient model is used as a baseline model of the button switch after being associated with the initial baseline model;
F6) the ultraviolet intensity is divided into three grades, namely high, medium and low, and the temperature is also divided into three grades, namely high temperature, normal temperature and low temperature;
F7) in practical application, after the button switch is deployed, the data acquisition is carried out on the button switch at intervals of 3 times a day, the acquired data comprises ultraviolet intensity, use times and ambient temperature, and actual measurement [ n, x, T ] is obtained]Data, by a function F ([ n, x, T) of a coefficient model],[q,r,s]) Calculating to obtain [ q, r, s [ ]]Is a reaction of [ q, r, s]Substituting into baseline model Wbase= qW (n) + rW (n, x) + sW (n, T) independent model W of tested push-button switchd;
F8) In the subsequent monitoring, the collected data comprises ultraviolet intensity, using times and ambient temperature, and the measured [ n, x, T ] is obtained]Data, substitution into independent model WdPerforming middle calculation, wherein the calculation result is used as the residual life result of the button switch;
F9) when the ultraviolet intensity or the temperature grade is detected to be changed, the step F7 is executed again, and then the steps F8-F9 are executed in a circulating mode until the life cycle monitoring task of the button switch is completed;
F10) all data of all monitored push switches are collected as effective sample data, a new industry experience model is manually established, and then steps F1-F10 are executed for the push switches which are subsequently put into use.
As an extended embodiment of the present invention, in step B, the service condition of the component is compared with the independent model and the similar model of the component at the same time, and the life cycle monitoring information of the component is obtained; the method for establishing the same model comprises the following steps: CC 1) all components in the monitoring are divided into a plurality of groups according to the use condition and/or the environmental condition; CC 2) collecting N2 data of the aging factors, the environmental factors and the life cycle feedback of each component in each group, and eliminating the data of the aging factors or the environmental factors with the data values beyond the set range in the set, wherein N2 is a positive integer set by people; CC 3) respectively substituting each group of data into the basic model and carrying out equalization processing to obtain the same type model of each group of components. The single component has its independent model, the basis of independent model establishment is the sampling data of baseline model and only single component, because the individual data lacks stability and accuracy, therefore the invention adopts and groups the component under the similar working condition, make statistics and order to a large number of individuals in the group, remove the data sample with trouble, only keep the data of the normal working individual, put into the baseline model after the equalization, solve the homogeneous model, the homogeneous model has higher accuracy compared with the baseline model, and its establishment is flexible, can be on the basis of data collected in short term after the apparatus is put into operation, the data collection and modeling cycle are short.
The method for comparing the use condition of the part with the independent model and the similar model of the part at the same time comprises the following steps: and respectively substituting the collected aging factors and environmental factor data of the component into the independent model and the similar model of the component, if the difference value between the life feedback data calculated by the independent model or the similar model and the collected life feedback data exceeds a set threshold value, sending out a warning and/or marking the maintenance project of the component, otherwise, updating the residual life of the component.
Example two: the method for monitoring the residual life of the rolling bearing by adopting the life cycle monitoring method with the same type of model comprises the following steps: H1) analyzing and obtaining the aging factor of the rolling bearing as the use number N, wherein the environmental factors comprise a load N, an impact load N ', dust D and a lubrication state E, the load N is taken as the working environment of the rolling bearing and is included as the environmental factor, and similarly to the first embodiment, establishing a baseline model W of the rolling bearing about the use number N, the load N, the impact load N', the dust D and the lubrication state EbaseAnd independent model WdAre not described herein again; H2) collecting data of enough rolling bearings which are put into use for a set time length, dividing the load into a light load gear and a heavy load gear, and according to the actual condition of the rolling bearings which are put into use and the actual condition of the rolling bearings which are put into useAccording to the load grade, whether impact load exists, whether dust exists and whether the lubrication state is good or not, the rolling bearings with the same working state are divided into the same group, and if all the rolling bearings in the first group are light load, impact load does not exist, dust does not exist and the lubrication state is good; H3) collecting the use times N, load N, impact load N', dust D, lubrication state E and life cycle feedback data of the rolling bearings in the same group, eliminating the data of the rolling bearings with faults, only retaining the data of normal working individuals, substituting the data into a basic model to obtain the coefficients [ k1, k2, … ks ] of different rolling bearings](ki is the baseline model coefficient, i ∈ [1, s ]]S is the number of baseline model parameters) and aging factor and environmental factor data [ N, N, N', D, E]The coefficients [ k1, k2, … kn ] of different rolling bearings are mapped]And [ N, N, N', D, E]After the data pair is subjected to averaging processing, fitting into a coefficient function:
F’([n,N,N’,D,E],[k1,k2,…kn]) Then, the coefficient function F' is associated with the baseline model to be used as a same group model Wg; H4) in practical application, the using times N of the rolling bearing, the load N, the impact load N', the dust D and the lubricating state E are collected and substituted into the independent model WdAnd solving to obtain an independent model result, substituting the independent model result into the same group of models Wg with the same use condition division, solving to obtain the same group of model results, taking the smaller value of the independent model result and the same group of model results as the life cycle monitoring result of the rolling bearing to be detected, and performing the rest steps similarly to the first embodiment, which can be implemented by referring to the first embodiment.
The above-described embodiments are only preferred embodiments of the present invention, and are not intended to limit the present invention in any way, and other variations and modifications may be made without departing from the spirit of the invention as set forth in the claims.
Claims (10)
1. A method for monitoring the life cycle of a component is characterized in that,
the method comprises the following steps:
A) establishing a baseline model of the life cycle of the component;
B) adjusting the baseline model according to the use condition of each component to obtain an independent model of each component;
C) comparing the use condition of the component with the independent model of the component to obtain the life period monitoring information of the component;
the method for establishing the baseline model comprises the following steps:
A1) defining aging factors, environmental factors and life time feedback of the component;
A2) taking an engineering theoretical model and/or an industry experience life period model as a basic model;
A3) carrying out accelerated life test and/or simulation test on each aging factor to obtain single aging factor test data, and substituting the single aging factor test data into the basic model to obtain a life period model of the single aging factor;
A4) carrying out accelerated life test and/or simulation test on each pair of single environmental factors and the combination of the single aging factors to obtain test data of the combination of the single environmental factors and the single aging factors, and substituting the test data into the basic model to obtain a life period model of the combination of the single environmental factors and the single aging factors;
A5) carrying out accelerated life test and/or simulation test on a plurality of environmental factors and a plurality of aging factors to obtain multi-factor data;
A6) manually setting a functional relation with an initial weight value for a life model of a single aging factor and a life model of a single environmental factor and a single aging factor combination to form an initial baseline model, establishing a fitting model of the weight value, the aging factor and the environmental factor according to multi-factor data, and combining the fitting model and the initial baseline model to serve as a life model of the component;
the method for establishing the independent model comprises the following steps:
B1) partitioning the area for each environmental factor;
B2) when the component is deployed for the first time or the interval where the environmental factors of the component are located changes, N1 collected data are substituted into the baseline model, the weight parameter value of the baseline model is adjusted to enable the difference value between the calculation result and the detection result of the substituted baseline model of the N1 collected data to be smaller than a set threshold value, the adjusted baseline model is used as an independent model of the component, and N1 is set manually.
2. A method for monitoring the lifetime of a component according to claim 1,
the accelerated life test is carried out on the aging factors, and the data acquisition method for acquiring the test data of the single aging factor comprises the following steps: if the aging factor is transient from the environmental state to the test state, acquiring aging factor data and life cycle feedback data at intervals t1 and associating the data with time data when the aging factor is in the test state, otherwise, acquiring the aging factor data and the life cycle feedback data at intervals t2 and associating the data with the time data through a conversion function when the aging factor is changed from the environmental state to the test state, and then acquiring the aging factor data and the life cycle feedback data at intervals t1 and associating the data with the time data when the aging factor is in the test state;
the accelerated life test is carried out on each pair of the environmental factors and the combination of the aging factors, and the method for obtaining the test data of the single environmental factor and the single aging factor combination comprises the following steps: if the aging factor and the environmental factor are transient processes from the environmental state to the test state, the aging factor data, the environmental factor data and the life cycle feedback data are collected at intervals of time t1 and are associated with the time data when the aging factor and the environmental factor are in the test state, otherwise, the aging factor data, the environmental factor data and the life cycle feedback data are collected at intervals of time t2 and are associated with the time data through a conversion function when the aging factor and the environmental factor are in the test state, and then the aging factor data, the environmental factor data and the life cycle feedback data are collected at intervals of time t1 and are associated with the time data when the aging factor and the environmental factor are in the test state, wherein the intervals of time t1 and t2 are set manually.
3. A method for monitoring the lifetime of a component according to claim 1 or 2,
the life feedback comprises component failure signs and failure symptoms, and a failure sign model and a failure symptom model of the component are established through factor data.
4. A method for monitoring the lifetime of a component according to claim 1 or 2,
the aging factors, the environmental factors and the life cycle feedback data of the component comprise sensor sampling data and manual detection setting data.
5. A component lifetime monitoring method according to claim 4,
the set data of the aging factors, the environmental factors and the life cycle feedback data are uploaded and set during manual detection, and are kept unchanged or changed according to a set function during two manual detections;
and after the artificial detection, calculating a difference value between the detection value and the value calculated by the setting function according to the last detection value, wherein the setting data of the artificial detection of the aging factors and the environmental factors which are changed according to the setting function are uploaded as life cycle feedback data.
6. A method for monitoring the lifetime of a component according to claim 1 or 2,
in step C, the method for comparing the usage of the component with the independent model of the component to obtain the lifetime monitoring information of the component comprises the following steps:
C1) substituting the collected aging factors and environmental factor data of the component into the component independent model, and if the difference value between the life-time feedback data calculated by the independent model and the collected life-time feedback data exceeds a set threshold value, sending out a warning and/or marking a maintenance item of the component;
C2) when the collected aging factors, environmental factors and life cycle feedback data of the components accord with the failure symptom model, sending out warning and/or marking maintenance items of the components;
C3) and when the collected aging factors, environmental factors and life-span feedback data of the components accord with the failure symptom model, warning and/or automatic repair are/is given out.
7. A method for monitoring the lifetime of a component according to claim 1 or 2,
in the step C, the service condition of the component is simultaneously compared with the independent model and the similar model of the component to obtain the life cycle monitoring information of the component;
the method for establishing the same-class model comprises the following steps:
CC 1) all components in the monitoring are divided into a plurality of groups according to the use condition and/or the environmental condition;
CC 2) collecting N2 data of the aging factors, the environmental factors and the life cycle feedback of each component in each group, and eliminating the data of the aging factors or the environmental factors with the data values exceeding the set range in the set, wherein N2 is manually set;
CC 3) adjusting the weight parameter value of the baseline model to ensure that the difference value between the calculation result and the detection result of the baseline model by substituting N2 data collected by each group is less than the set threshold value, and the adjusted baseline model is used as the same model of each group of components.
8. A component lifetime monitoring method according to claim 7,
the method for simultaneously comparing the use condition of the component with the independent model and the similar model of the component comprises the following steps:
and respectively substituting the collected aging factors and environmental factor data of the component into the independent model and the similar model of the component, and if the difference value between the life feedback data calculated by the independent model or the similar model and the collected life feedback data exceeds a set threshold value, sending out a warning and/or marking the maintenance project of the component.
9. A method for monitoring the lifetime of a component according to claim 1 or 2,
after step C, the step of: D) and when the quantity of the collected aging factors, environmental factors and life cycle feedback data of the components of the same model exceeds a set value, correcting the basic model, and updating the life cycle baseline model of the components in the step A.
10. A component lifetime monitoring method according to claim 9,
when the component is subjected to maintenance operation, collecting maintenance field data for correcting the basic model, and uploading aging factors, environmental factors and life cycle feedback data of the component.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810621885.5A CN108921305B (en) | 2018-06-15 | 2018-06-15 | Component life period monitoring method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810621885.5A CN108921305B (en) | 2018-06-15 | 2018-06-15 | Component life period monitoring method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108921305A CN108921305A (en) | 2018-11-30 |
CN108921305B true CN108921305B (en) | 2021-07-02 |
Family
ID=64420551
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810621885.5A Active CN108921305B (en) | 2018-06-15 | 2018-06-15 | Component life period monitoring method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108921305B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111311883B (en) * | 2020-05-12 | 2020-08-14 | 成都千嘉科技有限公司 | Gas alarm replacement early warning method and device and electronic equipment |
CN111967778A (en) * | 2020-08-19 | 2020-11-20 | 杭州铂钰信息科技有限公司 | Data security detection method and system based on security baseline model |
CN113551716B (en) * | 2021-09-22 | 2021-12-17 | 江西省公路工程检测中心 | Stress-strain detection method for mechanical property safety monitoring cloud system |
CN116953417B (en) * | 2023-09-20 | 2023-12-15 | 国网湖北省电力有限公司经济技术研究院 | Power transformer service life assessment device and method |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102567560A (en) * | 2010-12-27 | 2012-07-11 | 北京圣涛平试验工程技术研究院有限责任公司 | Method and system for estimating service life of MOS (Metal Oxide Semiconductor) device |
Family Cites Families (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2006146763A (en) * | 2004-11-24 | 2006-06-08 | Shimizu Corp | Care-need certificated person number prediction system |
US20090228230A1 (en) * | 2008-03-06 | 2009-09-10 | General Electric Company | System and method for real-time detection of gas turbine or aircraft engine blade problems |
KR101091754B1 (en) * | 2011-06-23 | 2011-12-08 | (주)티앤테크 | Equipment maintanance management system and method thereof |
CN102508957B (en) * | 2011-10-28 | 2015-07-15 | 北京航空航天大学 | Assessment method of electronic complete machine acceleration service life |
CN103778280B (en) * | 2014-01-08 | 2016-07-06 | 上海交通大学 | There is the lithium ion battery residual life Forecasting Methodology of model active more New Policy |
CN103926536A (en) * | 2014-03-07 | 2014-07-16 | 南京航空航天大学 | Method for predicting residual service life of lithium ion battery on basis of DST and BMC technologies |
CN105468850B (en) * | 2015-11-26 | 2018-08-07 | 电子科技大学 | Electronic product degradation trend prediction technique based on more residual error regression forecasting algorithms |
CN105653851B (en) * | 2015-12-27 | 2018-09-21 | 北京化工大学 | Rolling bearing method for predicting residual useful life based on physical model stage by stage and particle filter |
-
2018
- 2018-06-15 CN CN201810621885.5A patent/CN108921305B/en active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102567560A (en) * | 2010-12-27 | 2012-07-11 | 北京圣涛平试验工程技术研究院有限责任公司 | Method and system for estimating service life of MOS (Metal Oxide Semiconductor) device |
Also Published As
Publication number | Publication date |
---|---|
CN108921305A (en) | 2018-11-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108921305B (en) | Component life period monitoring method | |
CN110647133B (en) | Rail transit equipment state detection maintenance method and system | |
US11067973B2 (en) | Data collection system, abnormality detection method, and gateway device | |
US10852357B2 (en) | System and method for UPS battery monitoring and data analysis | |
CN115329812B (en) | Bridge infrastructure anomaly monitoring method based on artificial intelligence | |
CN104200288B (en) | A kind of equipment fault Forecasting Methodology based on dependency relation identification between factor and event | |
CN106093838B (en) | Gateway electric energy meter remote online verification method and system | |
CN109741927B (en) | Intelligent prediction system for equipment faults and potential defective products of miniature transformer production line | |
CN110826855A (en) | Method and system for testing network access performance of intelligent power distribution room state monitoring sensor | |
CN111458149B (en) | Method and system for predicting performance and service life of rolling bearing | |
CN117134503B (en) | State monitoring method and system for large-scale power supply device | |
CN110703743A (en) | Equipment failure prediction and detection system and method | |
CN115640860B (en) | Electromechanical equipment remote maintenance method and system for industrial cloud service | |
KR20180031454A (en) | Appartus and method monitoring insulator strings | |
CN116399402B (en) | Fault early warning system of wireless sensor for ecological environment monitoring | |
CN107884646B (en) | Emergency warning method for transformer substation online monitoring system | |
CN112734977A (en) | Equipment risk early warning system and algorithm based on Internet of things | |
CN112414576A (en) | Factory environment temperature detection system based on wireless sensor network | |
CN111339661A (en) | Automatic planning method for high-voltage cable inspection cycle | |
CN105741184B (en) | Transformer state evaluation method and device | |
CN113153262A (en) | Offshore oilfield accessible capacity evaluation method based on cable thermal characteristics | |
CN117494009A (en) | Electrical equipment state evaluation method based on insulating material pyrolysis analysis and cloud platform | |
CN104991222B (en) | metering automation terminal quality evaluation system | |
CN112782236B (en) | Material state monitoring method, system and device of converter cabinet and storage medium | |
Łęczycki et al. | Extended sensor reliability evaluation method in multi-sensor control systems |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |