CN113077172A - Equipment state trend analysis and fault diagnosis method - Google Patents
Equipment state trend analysis and fault diagnosis method Download PDFInfo
- Publication number
- CN113077172A CN113077172A CN202110421190.4A CN202110421190A CN113077172A CN 113077172 A CN113077172 A CN 113077172A CN 202110421190 A CN202110421190 A CN 202110421190A CN 113077172 A CN113077172 A CN 113077172A
- Authority
- CN
- China
- Prior art keywords
- trend
- equipment
- analysis
- data set
- algorithm model
- 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.)
- Pending
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
- G06Q10/06—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
-
- 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
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 And Monitoring For Control Systems (AREA)
Abstract
The invention relates to the technical field of trend analysis and fault diagnosis of industrial equipment, and aims to provide an equipment state trend analysis and fault diagnosis method, which comprises the following steps: acquiring historical operating parameters of equipment to be diagnosed; preprocessing historical operating parameters to obtain an analysis data set; establishing a trend algorithm model according to the analysis data set; acquiring current operation parameters of the equipment to be diagnosed, inputting the current operation parameters into a current trend algorithm model, and comparing the current operation parameters with preset normal state parameters to obtain the degradation degree of the equipment to be diagnosed; and obtaining a predictive trend curve according to the current trend algorithm model, and obtaining a predictive maintenance time window according to the predictive trend curve, the current operation parameters and a preset standard limit value. The invention can realize real-time monitoring of the equipment state, is convenient for equipment users to master the accurate operation condition of the equipment, and provides a sufficient time window for the maintenance of the subsequent equipment.
Description
Technical Field
The invention relates to the technical field of trend analysis and fault diagnosis of industrial equipment, in particular to a method for analyzing equipment state trend and diagnosing faults.
Background
At present, a method of manual experience judgment is mainly adopted for trend analysis and fault diagnosis of industrial equipment. Most of enterprises adopt a mode of maintenance according to a plan, namely, a node collects the current operation parameters of the running equipment at the planned time point, and then judges the current operation condition of the equipment through the manual experience of an engineer. However, this method is mainly based on the current data to draw conclusions, and cannot judge the future operation trend of the equipment. In an enterprise with better information construction, historical operation data of equipment can be collected, and the operation state of the equipment is displayed in real time in a centralized control center, so that the current and past equipment operation data can be seen. However, this method cannot predict and judge the remaining operating time of the equipment and the expected equipment failure time.
With the improvement of the requirement on equipment asset management, the requirements of mastering the operation condition of the equipment in real time, predicting the residual operation time of the equipment and the like exist, so that a method for analyzing the state trend of the equipment and diagnosing faults is needed to be researched.
Disclosure of Invention
The present invention is directed to solve the above technical problems at least to some extent, and the present invention provides a method for analyzing a state trend of a device and diagnosing a fault.
The technical scheme adopted by the invention is as follows:
a method for analyzing equipment state trend and diagnosing faults comprises the following steps:
acquiring historical operating parameters of equipment to be diagnosed;
preprocessing historical operating parameters to obtain an analysis data set;
establishing a trend algorithm model according to the analysis data set;
acquiring current operation parameters of the equipment to be diagnosed, inputting the current operation parameters into a current trend algorithm model, and comparing the current operation parameters with preset normal state parameters to obtain the degradation degree of the equipment to be diagnosed;
and obtaining a predictive trend curve according to the current trend algorithm model, and obtaining a predictive maintenance time window according to the predictive trend curve, the current operation parameters and a preset standard limit value.
Preferably, the historical operating parameters include a vibration time series and a temperature time series; the vibration time sequence array is vibration frequency data with a time label, and the temperature time sequence array is temperature data with a time label.
Preferably, when the historical operating parameters are preprocessed, the steps are as follows: and performing data cleaning processing, data alignment processing and/or data abnormal value elimination processing on the historical operating parameters.
Preferably, after the pre-processing of the historical operating parameters, the method further comprises the following steps:
and performing smoothing processing, filtering processing and/or validation processing on the historical operating parameters.
Preferably, when the trend algorithm model is established based on the analysis data set, the steps are as follows:
carrying out sample division on an analysis data set to obtain a training data set and an evaluation data set;
establishing a trend algorithm model according to the training data set;
and optimizing the trend algorithm model according to the evaluation data set to obtain the optimized trend algorithm model.
Further, the analysis data set is subjected to sample division according to a method of an expert rule.
Further, a trend algorithm model is established by adopting curve fitting in an artificial intelligence machine learning technology and a BP neural network.
Preferably, after obtaining the deterioration degree of the device to be diagnosed, the method further comprises the following steps:
and performing characteristic analysis on the current operation parameters according to the current trend algorithm model to obtain a fault preliminary diagnosis indication.
Further, after obtaining the preliminary diagnosis indication of the fault, the method also comprises the following steps:
and acquiring the frequency characteristics corresponding to the current operating parameters, and comparing the frequency characteristics with preset characteristics in an industrial standard to obtain the fault reasons.
The invention has the beneficial effects that:
1) the device can monitor the operation condition of the device in real time, and acquire the historical vibration time sequence and temperature time sequence of the device and the current operation parameters of the device to be diagnosed, so that a device user can conveniently monitor the state of the device in real time;
2) existing data are analyzed by adopting a big data analysis method such as a logistic regression calculation method, a neural network learning method and the like, a trend algorithm model is established, a prediction result of the residual working life of the equipment can be obtained, an equipment user can conveniently master the accurate operation condition of the equipment, and meanwhile, a sufficient time window is provided for the maintenance of subsequent equipment;
3) when the failure prediction point of the equipment is obtained, the method can complete the conversion of the vibration data from the time domain to the frequency domain, and analyze the fault type and the fault position of the equipment on line through the vibration map, thereby avoiding adopting additional equipment or manual judgment.
Drawings
FIG. 1 is a flow chart of a method of equipment state trend analysis and fault diagnosis in accordance with the present invention;
FIG. 2 is a diagram illustrating the results of an optimized trend algorithm model in accordance with the present invention;
FIG. 3 is a diagram showing the results of an optimized trend algorithm model in the operation of the apparatus of the present invention;
FIG. 4 is a diagram of the frequency domain spectrum at a predetermined time and the industry standard screenshot in the present invention.
Detailed Description
The invention is further described with reference to the following figures and specific embodiments.
It should be understood that, for the term "and/or" as may appear herein, it is merely an associative relationship that describes an associated object, meaning that three relationships may exist, e.g., a and/or B may mean: a exists alone, B exists alone, and A and B exist at the same time; for the term "/and" as may appear herein, which describes another associative object relationship, it means that two relationships may exist, e.g., a/and B, may mean: a exists independently, and A and B exist independently; in addition, for the character "/" that may appear herein, it generally means that the former and latter associated objects are in an "or" relationship.
It should also be noted that, in some alternative implementations, the functions/acts noted may occur out of the order noted in the figures. For example, two figures shown in succession may, in fact, be executed substantially concurrently, or the figures may sometimes be executed in the reverse order, depending upon the functionality/acts involved.
Example 1:
the embodiment provides an equipment state trend analysis and fault diagnosis method, which comprises the following steps:
s1, obtaining historical operating parameters of equipment to be diagnosed;
s2, preprocessing historical operating parameters to obtain an analysis data set; so as to meet the time domain and frequency domain analysis requirements of historical operating parameters; it should be noted that the analysis data set is used as a parameter set input by a subsequent trend analysis algorithm and/or a fault diagnosis algorithm, and may be set as a temperature risk data set or a vibration analysis data set according to different selections judged by the equipment;
s3, establishing a trend algorithm model according to the analysis data set;
s4, obtaining current operation parameters of the equipment to be diagnosed, inputting the current operation parameters into a current trend algorithm model, and comparing the current operation parameters with preset normal state parameters to obtain the degradation degree of the equipment to be diagnosed;
it should be noted that the degradation degree refers to a difference between the data at the current time and the data in the normal state, and the magnitude of the difference represents the strength of the degradation degree. The larger the difference value is, the higher the degradation degree is, in addition, through the different degradation degrees obtained in real time, the degradation trend of the equipment can be known, for example, the degradation degree of the equipment is deepened or the degradation degree is weakened, and the degradation degree and the degradation trend can be referred by equipment users so as to know the operation condition of the current equipment.
In this embodiment, the determination of the normal state parameter can be implemented by the following two methods:
1) the method is specified by the industry standard, but only the approximate acquisition frequency and the obtained calculation method are specified, in the embodiment, the normal state parameters are obtained by acquiring vibration frequency data or temperature data in a fixed acquisition time interval and then averaging the data. The calculation method of the acquisition time interval and the average value can be determined according to the type of the equipment and the operation condition of the equipment, can be set at the initial stage of the establishment of the algorithm model, and can be set finally after the type and the operation condition of the equipment are determined, and can be modified at the later stage; the time interval of the acquisition can be in the order of minutes and hours, and the average value can be calculated by, but not limited to, arithmetic average, square average, harmonic average, and the like, and is not limited herein.
2) The method is realized according to a dynamic adaptive evaluation method, wherein the adaptive evaluation method can be realized by, but is not limited to, the adaptive evaluation method adopted by the characteristic data desensitized to the working condition in the invention patent with the publication number of CN108280543B, and is not described herein again.
S5, acquiring a predicted trend curve according to the current trend algorithm model, and obtaining a predictive maintenance time window according to the predicted trend curve, the current operation parameters and a preset standard limit value; the simulation result of the current trend algorithm model is shown in fig. 2, the short-dashed curve in the graph is a predicted trend curve, it should be understood that the vibration standard limit of the equipment has a definite regulation in the international standard, and the time span between the time point corresponding to the intersection point of the standard limit and the predicted trend curve and the time point of the current operation parameter is the maintenance time window.
The embodiment can monitor the operation condition of the equipment in real time, and is convenient for an equipment user to monitor the equipment state in real time by acquiring historical operation parameters and the current operation parameters of the equipment to be diagnosed; in the embodiment, the historical operating parameters are analyzed, and a trend algorithm model is established, so that the prediction result of the residual working life of the equipment can be obtained in real time or when needed, a user of the equipment can conveniently master the accurate operating condition of the equipment, and meanwhile, a sufficient time window is provided for the maintenance of the subsequent equipment.
Example 2:
the present embodiment provides a method for analyzing a device status trend and diagnosing a fault, as shown in fig. 1, including the following steps:
s1, obtaining historical operating parameters of equipment to be diagnosed;
specifically, the historical operating parameters include a vibration time series and a temperature time series; the vibration time sequence array is vibration frequency data with a time label, and the temperature time sequence array is temperature data with a time label. The selection of the vibration frequency data is determined according to the difference of the equipment to be diagnosed and the difference of the signal acquisition equipment, and can be selected as a vibration displacement signal, a vibration speed signal and/or a vibration acceleration signal.
S2, preprocessing historical operating parameters to obtain an analysis data set; so as to meet the time domain and frequency domain analysis requirements of historical operating parameters; it should be noted that the analysis data set is used as a parameter set input by a subsequent trend analysis algorithm and/or a fault diagnosis algorithm, and may be set as a temperature risk data set or a vibration analysis data set according to different selections judged by the equipment;
specifically, when the historical operating parameters are preprocessed, the steps are as follows: and performing data cleaning processing, data alignment processing and/or data abnormal value elimination processing on the historical operating parameters.
In this embodiment, the preprocessing of the historical operating parameters may be realized by, but not limited to, a method in a data preparation stage in CRISP-index standard process for data mining (cross-industry data mining standard process).
Wherein, the data cleaning step comprises: setting historical operating parameters as data in a predetermined format, for example, selecting only one calculated value (temperature data or vibration frequency data) at a specific time;
the data alignment step comprises: uniformly setting the time step lengths of the historical operating parameters with the same source as a preset value to obtain the historical operating parameters with uniform step lengths; the same data time acquisition intervals are unified, when the sources of the historical operating parameters are the same, the time intervals of the same acquisition signal source of the same equipment must be the same, for example, the time step of the historical operating parameters obtained from the sources of the same historical operating parameters is uniformly set to be 20 milliseconds;
the data outlier excluding step includes: acquiring abnormal values, repeated values and null values in the historical operating parameters with the uniform step length, then eliminating the abnormal values and the repeated values in the historical operating parameters with the uniform step length through a simulation algorithm, and supplementing the null values to obtain an analysis data set; the simulation algorithm may be, but is not limited to, a bp (back propagation) neural network algorithm.
Further, after the data cleaning processing, the data alignment processing and/or the data abnormal value removing processing are/is carried out on the historical operating parameters, the smoothing processing, the filtering processing and/or the validation processing can be carried out on the historical operating parameters according to the operating condition of the equipment and the purpose of fault diagnosis.
S3, establishing a trend algorithm model according to the analysis data set;
in this embodiment, when the trend algorithm model is established according to the analysis data set, the following steps are performed:
s301, carrying out sample division on an analysis data set to obtain a training data set and an evaluation data set; it should be noted that the training data set is used for training the algorithm model in the later period to obtain the trained algorithm model, and the evaluation data set is used for verifying the reliability, accuracy and the like of the trained algorithm model.
In this embodiment, the analysis data set is subjected to sample division by an Expert rule (Expert rules) method. It should be understood that the expert rules method is implemented by using a neural network algorithm, so as to achieve the purpose of machine partitioning through the neural network algorithm, thereby reducing manual intervention sample partitioning.
S302, establishing a trend algorithm model according to the training data set;
in this embodiment, a trend algorithm model is established by using methods such as curve fitting in an artificial intelligence machine learning technology and a bp (back propagation) neural network.
And S303, optimizing the trend algorithm model according to the evaluation data set to obtain the optimized trend algorithm model.
The simulation result of the trend algorithm model is shown in fig. 2, the adopted historical operating parameters are vibration time sequence series, the ordinate in the figure represents the effective vibration value in the historical operating parameters, and the abscissa represents time; the system comprises a data acquisition unit, a data acquisition unit and a data processing unit, wherein a dot-dash line curve and a solid line curve are collected operation trends of historical operation parameters, wherein the dot-dash line curve refers to a training data set, and the; the thick solid curve is a fitting curve of the training data set, and the long dotted curve is a fitting curve of the evaluation data set; the short-dashed curve is a trend prediction curve obtained through a trend algorithm model and refers to a predicted value. It should be understood that the trend prediction curve is used for predicting the subsequent actual vibration data of the current equipment, and as shown in fig. 3, a comparison graph of the change curve of the subsequent actual vibration data with time and the trend prediction curve is displayed.
It should be noted that, in this embodiment, a trend algorithm model is established according to a training data set, specifically: obtaining a fitting curve of the training data set according to the training data set, and then obtaining a trend prediction curve according to the fitting curve of the training data set; meanwhile, optimizing the trend algorithm model according to the evaluation data set, specifically: and optimizing the trend algorithm model by taking the evaluation data set as future prediction data of the training data set, obtaining a fitting curve of the evaluation data set through the evaluation data set, and further optimizing the trend prediction curve according to the fitting curve of the evaluation data set to obtain a final trend prediction curve, thereby realizing the optimization processing of the trend algorithm model.
In the process of optimizing the trend algorithm model, the reliability of the trend model algorithm is judged by carrying out error analysis on the evaluation data set and the predicted value obtained through the trend algorithm model; in the process, because the process of establishing and optimizing the trend algorithm model is continuously performed, after a period of time, the current evaluation data set can be relegated to the training data set, and a new evaluation data set is generated, and the sample division of the training data set and the evaluation data set can be realized by a recurrent neural network, but not limited to.
S4, obtaining current operation parameters of the equipment to be diagnosed, inputting the current operation parameters into a current trend algorithm model, and comparing the current operation parameters with preset normal state parameters to obtain the degradation degree of the equipment to be diagnosed;
as shown in fig. 2, the degradation degree refers to the difference between the data at the current time and the data in the normal state, and the magnitude of the difference represents the strength of the degradation degree. The larger the difference value is, the higher the degradation degree is, in addition, through the different degradation degrees obtained in real time, the degradation trend of the equipment can be known, for example, the degradation degree of the equipment is deepened or the degradation degree is weakened, and the degradation degree and the degradation trend can be referred by equipment users so as to know the operation condition of the current equipment.
In this embodiment, the determination of the normal state parameter can be implemented by the following two methods:
1) the method is specified by the industry standard, but only the approximate acquisition frequency and the obtained calculation method are specified, in the embodiment, the normal state parameters are obtained by acquiring vibration frequency data or temperature data in a fixed acquisition time interval and then averaging the data. The calculation method of the acquisition time interval and the average value can be determined according to the type of the equipment and the operation condition of the equipment, can be set at the initial stage of the establishment of the algorithm model, and can be set finally after the type and the operation condition of the equipment are determined, and can be modified at the later stage; the time interval of the acquisition can be in the order of minutes and hours, and the average value can be calculated by, but not limited to, arithmetic average, square average, harmonic average, and the like, and is not limited herein.
2) The method is realized according to a dynamic adaptive evaluation method, wherein the adaptive evaluation method can be realized by, but is not limited to, the adaptive evaluation method adopted by the characteristic data desensitized to the working condition in the invention patent with the publication number of CN108280543B, and is not described herein again.
S5, acquiring a predicted trend curve according to the current trend algorithm model, and obtaining a predictive maintenance time window according to the predicted trend curve, the current operation parameters and a preset standard limit value; it should be understood that the vibration standard limit of the equipment is specified in the international standard, and the time span between the time point corresponding to the intersection point of the standard limit and the predicted trend curve and the time point of the current operation parameter is the maintenance time window, as shown in fig. 2.
In the prior art, an enterprise may set an alarm threshold according to experience or standard regulation of equipment operation in a practical process of historical operation parameters, and when monitoring that collected real-time operation data exceeds the threshold, software may display alarm information, such as a red warning mark, on a software end. However, the alarm threshold value specified by the standard is a fixed limit value, that is, the current work can only alarm according to the fixed threshold value, but cannot indicate the failure reason of the equipment or the possible failure reason of the equipment, and still needs to be judged manually or according to another set of detection system (such as a handheld detection device); meanwhile, the method cannot predict the remaining operation time of the equipment.
In order to further solve the above technical problem, in this embodiment, after obtaining the degradation degree of the device to be diagnosed, the method further includes the following steps:
and S6, performing characteristic analysis on the current operation parameters according to the current trend algorithm model to obtain a fault preliminary diagnosis indication, wherein the preliminary diagnosis indication can be misalignment, imbalance, bearing characteristic frequency and the like. When the current operation parameters are subjected to characteristic analysis, the method is realized by performing frequency domain analysis on the vibration time sequence series, and comprises the following steps: when the operation fault diagnosis is needed, the time domain spectrum of a certain moment in the vibration time sequence array is converted into the frequency domain spectrum of the current moment through a fast Fourier transform method.
In this embodiment, after obtaining the preliminary diagnosis indication of the fault, the method further includes the following steps:
s7, acquiring a frequency domain spectrum corresponding to the current operation parameter, acquiring frequency characteristics through the current frequency domain spectrum, and comparing the frequency characteristics with preset characteristics in an industrial standard to obtain a fault reason; wherein, the frequency domain spectrum is the frequency domain spectrum of the current moment obtained by conversion in the step. It should be understood that the predetermined characteristics in the industry standard all match the cause of the fault, for example, a 5 × frequency-doubled characteristic line segment with frequency is obtained from the frequency domain spectrum at the current time, that is, the cause of the fault at the current time can be obtained from the industry standard as follows: the loose connection of the equipment, including but not limited to the loose foundation bolt, the loose connecting piece and the loose fastener, needs to be confirmed through field investigation.
As shown in fig. 4, the left-side graph is a frequency domain spectrum of the current time obtained by a fast fourier transform method, and the right-side picture is an industry standard screenshot, wherein in the frequency domain spectrum, the amplitude of the abscissa represents the frequency of the current operating parameter, the amplitude of the ordinate represents the amplitude intensity of the current operating parameter, in the industry standard screenshot, a solid line circle in a "frequency" number sequence represents that a characteristic value occurs in 5X frequency multiplication, the numerical value of a virtual line circle is determined as an interference factor of a product in vibration, and since no special multiple relation occurs, the virtual line circle is determined as an item to be checked and is not used as a basis for determining a fault reason, and in the industry standard screenshot, a "vibration value" number sequence represents a vibration value at a specified frequency. In the implementation process, according to the left side frequency domain spectrum, the frequency corresponding to the current operation parameter with stronger amplitude in the frequency domain spectrum is compared with the frequency in the industry standard screenshot, so that the vibration value corresponding to the current operation parameter can be obtained, and further the fault reason can be obtained according to the vibration value. It should be understood that the relationship between frequency signature and cause of failure is a common industry knowledge in the art, which has industrial applicability and has been recognized throughout the industry.
The embodiment can monitor the operation condition of the equipment in real time, and collects the historical vibration time sequence and temperature time sequence of the equipment and the current operation parameters of the equipment to be diagnosed, so that the equipment user can conveniently monitor the equipment state in real time; in addition, in the embodiment, existing data are analyzed by adopting a big data analysis method such as a logistic regression calculation method, a neural network learning method and the like, a trend algorithm model is established, and a prediction result of the residual working life of the equipment can be obtained in real time or when needed, so that an equipment user can conveniently master the accurate operation condition of the equipment and simultaneously provide a sufficient time window for the maintenance of subsequent equipment; when a predicted point of equipment failure is obtained, the conversion of vibration data from a time domain to a frequency domain can be completed through a physical method, the fault type and the fault position of the equipment are analyzed on line through a vibration map, and extra equipment or manual judgment is avoided.
It will be apparent to those skilled in the art that the modules or steps of the present invention described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and they may alternatively be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, or fabricated separately as individual integrated circuit modules, or fabricated as a single integrated circuit module from multiple modules or steps. Thus, the present invention is not limited to any specific combination of hardware and software.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: modifications of the technical solutions described in the embodiments or equivalent replacements of some technical features may still be made. And such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Finally, it should be noted that the present invention is not limited to the above alternative embodiments, and that various other forms of products can be obtained by anyone in light of the present invention. The above detailed description should not be taken as limiting the scope of the invention, which is defined in the claims, and which the description is intended to be interpreted accordingly.
Claims (9)
1. A method for analyzing equipment state trend and diagnosing faults is characterized in that: the method comprises the following steps:
acquiring historical operating parameters of equipment to be diagnosed;
preprocessing historical operating parameters to obtain an analysis data set;
establishing a trend algorithm model according to the analysis data set;
acquiring current operation parameters of the equipment to be diagnosed, inputting the current operation parameters into a current trend algorithm model, and comparing the current operation parameters with preset normal state parameters to obtain the degradation degree of the equipment to be diagnosed;
and obtaining a predictive trend curve according to the current trend algorithm model, and obtaining a predictive maintenance time window according to the predictive trend curve, the current operation parameters and a preset standard limit value.
2. The equipment state trend analysis and fault diagnosis method according to claim 1, wherein: the historical operating parameters comprise a vibration time sequence and a temperature time sequence; the vibration time sequence array is vibration frequency data with a time label, and the temperature time sequence array is temperature data with a time label.
3. The equipment state trend analysis and fault diagnosis method according to claim 1, wherein: when the historical operating parameters are preprocessed, the steps are as follows: and performing data cleaning processing, data alignment processing and/or data abnormal value elimination processing on the historical operating parameters.
4. The equipment state trend analysis and fault diagnosis method according to claim 1 or 3, characterized in that: after the historical operating parameters are preprocessed, the method further comprises the following steps:
and performing smoothing processing, filtering processing and/or validation processing on the historical operating parameters.
5. The equipment state trend analysis and fault diagnosis method according to claim 1, wherein: when a trend algorithm model is established according to the analysis data set, the steps are as follows:
carrying out sample division on an analysis data set to obtain a training data set and an evaluation data set;
establishing a trend algorithm model according to the training data set;
and optimizing the trend algorithm model according to the evaluation data set to obtain the optimized trend algorithm model.
6. The equipment state trend analysis and fault diagnosis method according to claim 5, wherein: and carrying out sample division on the analysis data set according to an expert rule method.
7. The equipment state trend analysis and fault diagnosis method according to claim 5, wherein: and adopting curve fitting in an artificial intelligence machine learning technology and a BP neural network to establish a trend algorithm model.
8. The equipment state trend analysis and fault diagnosis method according to claim 1, wherein: after the deterioration degree of the equipment to be diagnosed is obtained, the method also comprises the following steps:
and performing characteristic analysis on the current operation parameters according to the current trend algorithm model to obtain a fault preliminary diagnosis indication.
9. The equipment state trend analysis and fault diagnosis method according to claim 8, wherein: after obtaining the preliminary diagnosis indication of the fault, the method further comprises the following steps:
and acquiring the frequency characteristics corresponding to the current operating parameters, and comparing the frequency characteristics with preset characteristics in an industrial standard to obtain the fault reasons.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110421190.4A CN113077172A (en) | 2021-04-19 | 2021-04-19 | Equipment state trend analysis and fault diagnosis method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110421190.4A CN113077172A (en) | 2021-04-19 | 2021-04-19 | Equipment state trend analysis and fault diagnosis method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113077172A true CN113077172A (en) | 2021-07-06 |
Family
ID=76618061
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110421190.4A Pending CN113077172A (en) | 2021-04-19 | 2021-04-19 | Equipment state trend analysis and fault diagnosis method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113077172A (en) |
Cited By (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113473118A (en) * | 2021-08-23 | 2021-10-01 | 追觅创新科技(苏州)有限公司 | Data timestamp alignment method, device, equipment and storage medium |
| CN113554224A (en) * | 2021-07-20 | 2021-10-26 | 上海航天测控通信研究所 | Fault diagnosis method and system combining multipoint statistics with health trend prediction |
| CN113723493A (en) * | 2021-08-25 | 2021-11-30 | 中车资阳机车有限公司 | Internal combustion engine vibration analysis early warning method and device based on clustering and trend prediction |
| CN113792944A (en) * | 2021-11-16 | 2021-12-14 | 深圳普菲特信息科技股份有限公司 | Predictive maintenance method and system |
| CN114066044A (en) * | 2021-11-12 | 2022-02-18 | 国能龙源环保有限公司 | Method and device for predicting blockage condition of limestone slurry supply pipeline |
| CN114091792A (en) * | 2022-01-21 | 2022-02-25 | 华电电力科学研究院有限公司 | Hydro-generator degradation early warning method, equipment and medium based on stable working conditions |
| CN114167282A (en) * | 2021-12-03 | 2022-03-11 | 深圳市双合电气股份有限公司 | Motor fault diagnosis and degradation trend prediction method and system |
| CN114237128A (en) * | 2021-12-21 | 2022-03-25 | 华能澜沧江水电股份有限公司 | Hydropower station equipment real-time monitoring data monitoring system and monitoring method based on trend alarm |
| CN114236314A (en) * | 2021-12-17 | 2022-03-25 | 瀚云科技有限公司 | Fault detection method, device, equipment and storage medium |
| CN114418042A (en) * | 2021-12-30 | 2022-04-29 | 智昌科技集团股份有限公司 | Industrial robot operation trend diagnosis method based on cluster analysis |
| CN114442543A (en) * | 2021-10-29 | 2022-05-06 | 南京河海南自水电自动化有限公司 | Computer monitoring method suitable for early warning of hydropower station fault |
| CN114626615A (en) * | 2022-03-21 | 2022-06-14 | 江苏仪化信息技术有限公司 | Production process monitoring and management method and system |
| CN114818206A (en) * | 2022-06-29 | 2022-07-29 | 杭州未名信科科技有限公司 | Tower crane maintenance data identification system and method and intelligent tower crane |
| CN114924188A (en) * | 2022-05-13 | 2022-08-19 | 上海擎测机电工程技术有限公司 | Thermal power generating unit startup and shutdown monitoring method and system |
| CN115022151A (en) * | 2022-07-04 | 2022-09-06 | 青岛佳世特尔智创科技有限公司 | Pump unit state monitoring and analyzing method and system |
| CN115169650A (en) * | 2022-06-20 | 2022-10-11 | 四川观想科技股份有限公司 | Equipment health prediction method for big data analysis |
| CN115186935A (en) * | 2022-09-08 | 2022-10-14 | 山东交通职业学院 | Electromechanical device nonlinear fault prediction method and system |
| CN115358281A (en) * | 2022-10-21 | 2022-11-18 | 深圳市耐思特实业有限公司 | Machine learning-based cold and hot all-in-one machine monitoring control method and system |
| CN115438756A (en) * | 2022-11-10 | 2022-12-06 | 济宁中银电化有限公司 | Method for diagnosing and identifying fault source of rectifying tower |
| CN115509626A (en) * | 2022-11-07 | 2022-12-23 | 首都师范大学 | Method and device for realizing pause state setting based on energy prediction in nonvolatile processor |
| CN115774847A (en) * | 2022-11-22 | 2023-03-10 | 上海船舶运输科学研究所有限公司 | Diesel engine performance evaluation and prediction method and system |
| CN115858212A (en) * | 2022-11-23 | 2023-03-28 | 廊坊燕京职业技术学院 | Computer hardware state diagnosis system and method |
| CN115864995A (en) * | 2023-02-16 | 2023-03-28 | 东方电气集团科学技术研究院有限公司 | Inverter conversion efficiency diagnosis method and device based on big data mining |
| CN116155956A (en) * | 2023-04-18 | 2023-05-23 | 武汉森铂瑞科技有限公司 | Multiplexing communication method and system based on gradient decision tree model |
| CN117060409A (en) * | 2023-10-13 | 2023-11-14 | 国网甘肃省电力公司白银供电公司 | Automatic detection and analysis method and system for power line running state |
| CN117349602A (en) * | 2023-12-06 | 2024-01-05 | 江西省水投江河信息技术有限公司 | Water conservancy facility operation state prediction method, system and computer |
| CN117726144A (en) * | 2024-02-07 | 2024-03-19 | 青岛国彩印刷股份有限公司 | Intelligent digital printing management system and method based on data processing |
| CN117742304A (en) * | 2024-02-09 | 2024-03-22 | 珠海市南特金属科技股份有限公司 | Fault diagnosis method and system for crankshaft double-top vehicle control system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105928710A (en) * | 2016-04-15 | 2016-09-07 | 中国船舶工业系统工程研究院 | Diesel engine fault monitoring method |
| CN108875841A (en) * | 2018-06-29 | 2018-11-23 | 国家电网有限公司 | A kind of pumped storage unit vibration trend forecasting method |
| CN109782680A (en) * | 2019-01-30 | 2019-05-21 | 王军 | A kind of status early warning method and system of generating set |
| CN109857079A (en) * | 2018-12-05 | 2019-06-07 | 上海交通大学 | The intelligent diagnosing method and device of machining center axis system working condition exception |
| CN111006758A (en) * | 2019-12-11 | 2020-04-14 | 东方电气风电有限公司 | Wind generating set steady-state vibration online trend prediction method and trend prediction system |
| KR20200049295A (en) * | 2018-10-31 | 2020-05-08 | 한국전력공사 | A method to predict health index transition and residual life for turbomachinery |
| CN112527613A (en) * | 2020-11-30 | 2021-03-19 | 北京航天智造科技发展有限公司 | Equipment fault maintenance method and device based on cloud edge cooperation |
-
2021
- 2021-04-19 CN CN202110421190.4A patent/CN113077172A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105928710A (en) * | 2016-04-15 | 2016-09-07 | 中国船舶工业系统工程研究院 | Diesel engine fault monitoring method |
| CN108875841A (en) * | 2018-06-29 | 2018-11-23 | 国家电网有限公司 | A kind of pumped storage unit vibration trend forecasting method |
| KR20200049295A (en) * | 2018-10-31 | 2020-05-08 | 한국전력공사 | A method to predict health index transition and residual life for turbomachinery |
| CN109857079A (en) * | 2018-12-05 | 2019-06-07 | 上海交通大学 | The intelligent diagnosing method and device of machining center axis system working condition exception |
| CN109782680A (en) * | 2019-01-30 | 2019-05-21 | 王军 | A kind of status early warning method and system of generating set |
| CN111006758A (en) * | 2019-12-11 | 2020-04-14 | 东方电气风电有限公司 | Wind generating set steady-state vibration online trend prediction method and trend prediction system |
| CN112527613A (en) * | 2020-11-30 | 2021-03-19 | 北京航天智造科技发展有限公司 | Equipment fault maintenance method and device based on cloud edge cooperation |
Cited By (40)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113554224A (en) * | 2021-07-20 | 2021-10-26 | 上海航天测控通信研究所 | Fault diagnosis method and system combining multipoint statistics with health trend prediction |
| CN113554224B (en) * | 2021-07-20 | 2022-11-25 | 上海航天测控通信研究所 | Fault diagnosis method and system combining multipoint statistics with health trend prediction |
| CN113473118A (en) * | 2021-08-23 | 2021-10-01 | 追觅创新科技(苏州)有限公司 | Data timestamp alignment method, device, equipment and storage medium |
| CN113723493B (en) * | 2021-08-25 | 2023-05-30 | 中车资阳机车有限公司 | Internal combustion engine vibration analysis early warning method and device based on clustering and trend prediction |
| CN113723493A (en) * | 2021-08-25 | 2021-11-30 | 中车资阳机车有限公司 | Internal combustion engine vibration analysis early warning method and device based on clustering and trend prediction |
| CN114442543A (en) * | 2021-10-29 | 2022-05-06 | 南京河海南自水电自动化有限公司 | Computer monitoring method suitable for early warning of hydropower station fault |
| CN114066044A (en) * | 2021-11-12 | 2022-02-18 | 国能龙源环保有限公司 | Method and device for predicting blockage condition of limestone slurry supply pipeline |
| CN113792944A (en) * | 2021-11-16 | 2021-12-14 | 深圳普菲特信息科技股份有限公司 | Predictive maintenance method and system |
| CN113792944B (en) * | 2021-11-16 | 2022-03-11 | 深圳普菲特信息科技股份有限公司 | Predictive maintenance method and system |
| CN114167282A (en) * | 2021-12-03 | 2022-03-11 | 深圳市双合电气股份有限公司 | Motor fault diagnosis and degradation trend prediction method and system |
| CN114167282B (en) * | 2021-12-03 | 2022-08-12 | 深圳市双合电气股份有限公司 | Motor fault diagnosis and degradation trend prediction system |
| CN114236314A (en) * | 2021-12-17 | 2022-03-25 | 瀚云科技有限公司 | Fault detection method, device, equipment and storage medium |
| CN114237128A (en) * | 2021-12-21 | 2022-03-25 | 华能澜沧江水电股份有限公司 | Hydropower station equipment real-time monitoring data monitoring system and monitoring method based on trend alarm |
| CN114418042A (en) * | 2021-12-30 | 2022-04-29 | 智昌科技集团股份有限公司 | Industrial robot operation trend diagnosis method based on cluster analysis |
| CN114091792A (en) * | 2022-01-21 | 2022-02-25 | 华电电力科学研究院有限公司 | Hydro-generator degradation early warning method, equipment and medium based on stable working conditions |
| CN114626615A (en) * | 2022-03-21 | 2022-06-14 | 江苏仪化信息技术有限公司 | Production process monitoring and management method and system |
| CN114626615B (en) * | 2022-03-21 | 2023-02-03 | 江苏仪化信息技术有限公司 | Production process monitoring and management method and system |
| CN114924188A (en) * | 2022-05-13 | 2022-08-19 | 上海擎测机电工程技术有限公司 | Thermal power generating unit startup and shutdown monitoring method and system |
| CN115169650B (en) * | 2022-06-20 | 2022-11-22 | 四川观想科技股份有限公司 | Equipment health prediction method for big data analysis |
| CN115169650A (en) * | 2022-06-20 | 2022-10-11 | 四川观想科技股份有限公司 | Equipment health prediction method for big data analysis |
| CN114818206A (en) * | 2022-06-29 | 2022-07-29 | 杭州未名信科科技有限公司 | Tower crane maintenance data identification system and method and intelligent tower crane |
| CN115022151A (en) * | 2022-07-04 | 2022-09-06 | 青岛佳世特尔智创科技有限公司 | Pump unit state monitoring and analyzing method and system |
| CN115022151B (en) * | 2022-07-04 | 2023-06-23 | 青岛佳世特尔智创科技有限公司 | Pump unit state monitoring and analyzing method and system |
| CN115186935A (en) * | 2022-09-08 | 2022-10-14 | 山东交通职业学院 | Electromechanical device nonlinear fault prediction method and system |
| CN115186935B (en) * | 2022-09-08 | 2023-04-07 | 山东交通职业学院 | Electromechanical device nonlinear fault prediction method and system |
| CN115358281B (en) * | 2022-10-21 | 2023-01-13 | 深圳市耐思特实业有限公司 | Machine learning-based cold and hot all-in-one machine monitoring control method and system |
| CN115358281A (en) * | 2022-10-21 | 2022-11-18 | 深圳市耐思特实业有限公司 | Machine learning-based cold and hot all-in-one machine monitoring control method and system |
| CN115509626B (en) * | 2022-11-07 | 2024-02-02 | 首都师范大学 | Method and device for realizing energy prediction-based pause state setting in nonvolatile processor |
| CN115509626A (en) * | 2022-11-07 | 2022-12-23 | 首都师范大学 | Method and device for realizing pause state setting based on energy prediction in nonvolatile processor |
| CN115438756A (en) * | 2022-11-10 | 2022-12-06 | 济宁中银电化有限公司 | Method for diagnosing and identifying fault source of rectifying tower |
| CN115774847A (en) * | 2022-11-22 | 2023-03-10 | 上海船舶运输科学研究所有限公司 | Diesel engine performance evaluation and prediction method and system |
| CN115858212A (en) * | 2022-11-23 | 2023-03-28 | 廊坊燕京职业技术学院 | Computer hardware state diagnosis system and method |
| CN115864995A (en) * | 2023-02-16 | 2023-03-28 | 东方电气集团科学技术研究院有限公司 | Inverter conversion efficiency diagnosis method and device based on big data mining |
| CN116155956A (en) * | 2023-04-18 | 2023-05-23 | 武汉森铂瑞科技有限公司 | Multiplexing communication method and system based on gradient decision tree model |
| CN116155956B (en) * | 2023-04-18 | 2023-08-22 | 武汉森铂瑞科技有限公司 | Multiplexing communication method and system based on gradient decision tree model |
| CN117060409A (en) * | 2023-10-13 | 2023-11-14 | 国网甘肃省电力公司白银供电公司 | Automatic detection and analysis method and system for power line running state |
| CN117060409B (en) * | 2023-10-13 | 2023-12-29 | 国网甘肃省电力公司白银供电公司 | Automatic detection and analysis method and system for power line running state |
| CN117349602A (en) * | 2023-12-06 | 2024-01-05 | 江西省水投江河信息技术有限公司 | Water conservancy facility operation state prediction method, system and computer |
| CN117726144A (en) * | 2024-02-07 | 2024-03-19 | 青岛国彩印刷股份有限公司 | Intelligent digital printing management system and method based on data processing |
| CN117742304A (en) * | 2024-02-09 | 2024-03-22 | 珠海市南特金属科技股份有限公司 | Fault diagnosis method and system for crankshaft double-top vehicle control system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113077172A (en) | Equipment state trend analysis and fault diagnosis method | |
| CN109001649B (en) | Intelligent power supply diagnosis system and protection method | |
| CN110647133B (en) | Rail transit equipment state detection maintenance method and system | |
| CN110766277B (en) | Health assessment and diagnosis system and mobile terminal for nuclear industry field | |
| JP2018156151A (en) | Abnormality detecting apparatus and machine learning device | |
| KR20180108446A (en) | System and method for management of ict infra | |
| CN106407589B (en) | Fan state evaluation and prediction method and system | |
| JP3651693B2 (en) | Plant monitoring diagnosis apparatus and method | |
| KR102343752B1 (en) | Computer-implemented method and system for automatically monitoring and determining the status of entire process segments in a process unit | |
| CN111255674B (en) | System and method for detecting state of rotating mechanical equipment | |
| KR102102346B1 (en) | System and method for condition based maintenance support of naval ship equipment | |
| CN116670608A (en) | Hybrid ensemble method for predictive modeling of Internet of things | |
| CN111124852A (en) | Fault prediction method and system based on BMC health management module | |
| CN110597235A (en) | Universal intelligent fault diagnosis method | |
| KR102545672B1 (en) | Method and apparatus for machine fault diagnosis | |
| CN112906775A (en) | Equipment fault prediction method and system | |
| CN109523030B (en) | Telemetering parameter abnormity monitoring system based on machine learning | |
| RU2687848C1 (en) | Method and system of vibration monitoring of industrial safety of dynamic equipment of hazardous production facilities | |
| CN114648212A (en) | Cloud computing-based ship equipment performance intelligent management system and method | |
| KR102130272B1 (en) | Method for optimizing predictive algorithm based empirical model | |
| CN112850387B (en) | Elevator state acquisition and diagnosis system and method | |
| KR102108975B1 (en) | Apparatus and method for condition based maintenance support of naval ship equipment | |
| CN117435908A (en) | Multi-fault feature extraction method for rotary machine | |
| CN112859741A (en) | Method and system for evaluating operation reliability of sequential action units of machine tool | |
| Xin et al. | Dynamic probabilistic model checking for sensor validation in Industry 4.0 applications |
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 |