CN117892240A - Cloud computing-based power system fault prediction and diagnosis system - Google Patents
Cloud computing-based power system fault prediction and diagnosis system Download PDFInfo
- Publication number
- CN117892240A CN117892240A CN202311747202.8A CN202311747202A CN117892240A CN 117892240 A CN117892240 A CN 117892240A CN 202311747202 A CN202311747202 A CN 202311747202A CN 117892240 A CN117892240 A CN 117892240A
- Authority
- CN
- China
- Prior art keywords
- data
- real
- time
- missing
- unit
- 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
- 238000003745 diagnosis Methods 0.000 title claims abstract description 23
- 238000011049 filling Methods 0.000 claims abstract description 38
- 238000012544 monitoring process Methods 0.000 claims abstract description 21
- 238000012545 processing Methods 0.000 claims abstract description 20
- 238000001514 detection method Methods 0.000 claims abstract description 14
- 230000002159 abnormal effect Effects 0.000 claims description 42
- 238000003860 storage Methods 0.000 claims description 22
- 238000004458 analytical method Methods 0.000 claims description 21
- 238000012549 training Methods 0.000 claims description 20
- 238000011156 evaluation Methods 0.000 claims description 15
- 238000000605 extraction Methods 0.000 claims description 8
- 238000012360 testing method Methods 0.000 claims description 8
- 238000013500 data storage Methods 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 6
- 238000007689 inspection Methods 0.000 claims description 6
- 238000004140 cleaning Methods 0.000 claims description 5
- 238000002372 labelling Methods 0.000 claims description 5
- 230000007246 mechanism Effects 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000010223 real-time analysis Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 2
- 230000000295 complement effect Effects 0.000 abstract description 5
- 230000005856 abnormality Effects 0.000 abstract description 3
- 230000003044 adaptive effect Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 18
- 238000012423 maintenance Methods 0.000 description 10
- 238000000034 method Methods 0.000 description 9
- 238000007405 data analysis Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000005457 optimization Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000009471 action Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000012217 deletion Methods 0.000 description 2
- 230000037430 deletion Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000001427 coherent effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013501 data transformation Methods 0.000 description 1
- 238000013079 data visualisation Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000002688 persistence Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Landscapes
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention is suitable for the field of power failure detection, and provides a power system failure prediction and diagnosis system based on cloud computing, which comprises: the system comprises a data acquisition module, a data processing module, a missing data filling module, a model building module, a data monitoring module and an alarm module. The system can collect data of the power system in real time by utilizing the real-time data acquisition module, and monitor and detect the abnormality and the missing condition of the data by the missing data filling module, so that the continuity of the data is ensured. The missing data filling module can calculate and complement the detected data fracture and missing part. The system can calculate and complement missing data more accurately by establishing an adaptive filling model and combining the trend and the historical rule of the data, and improves the accuracy and reliability of fault prediction and diagnosis.
Description
Technical Field
The invention belongs to the field of power failure detection, and particularly relates to a cloud computing-based power system failure prediction and diagnosis system.
Background
The field of power failure detection refers to the identification and detection of failure conditions in a power system by data analysis and processing of the power system. During operation of the power system, various factors such as equipment faults, human operation errors, meteorological conditions and the like may cause faults or abnormal states in the system. Therefore, the objective of power failure detection is to accurately identify the failure and take timely action to ensure operational safety and reliability of the power system.
The key to power failure detection is the real-time monitoring and analysis of power system data. Modern power systems provide a large amount of real-time data including current, voltage, frequency, temperature, state parameters, etc. By collecting, transmitting, storing and processing these data, continuous monitoring and analysis of the power system can be achieved.
Conventional power system fault prediction and diagnosis techniques do not give sufficient attention to the critical issue of real-time data continuity. The consistency of real-time data refers to the time continuity and consistency of power system data, namely, the continuity of the data requires that the collection frequency and interval of the data are consistent, and the data should have correlation and have better trend consistency. If the real-time data of the power system is problematic in terms of consistency, the accuracy of fault prediction and diagnosis will be greatly affected.
Disclosure of Invention
The invention aims to provide a power system fault prediction and diagnosis system based on cloud computing, and aims to solve the technical problems in the prior art determined in the background art.
The invention is realized in such a way that a power system fault prediction and diagnosis system based on cloud computing comprises:
the data acquisition module is used for acquiring real-time data of the power system, establishing a storage database and a history database, storing the real-time data into the storage database and storing the history data of the power system into the history database;
the data processing module is used for preprocessing real-time data stored in the storage database and extracting characteristics of the data after the preprocessing is completed;
the missing data filling module is used for detecting the continuity of the real-time data, and calculating and filling the numerical value of the missing part when detecting that the real-time data has an incoherent part;
the model building module is used for building a fault prediction model and training the model by utilizing historical data;
the data monitoring module is used for analyzing the collected real-time data of the power system through the fault prediction model, setting an abnormal threshold interval and comparing an analysis result with the abnormal threshold interval;
and the alarm module is used for sending out alarm information when the analysis result exceeds or is lower than the abnormal threshold value interval.
As a further aspect of the present invention, the data acquisition module includes:
the data acquisition unit is used for acquiring real-time data of the power system through the sensor and the monitoring equipment;
the data storage unit is used for establishing a storage database and storing the acquired real-time data of the power system in the storage database;
the historical data storage unit is used for establishing a historical database and extracting historical data of the power system into the historical database;
and the quality inspection unit is used for performing quality inspection on the data in the storage database.
As a further aspect of the present invention, the data processing module includes:
the data cleaning unit is used for cleaning and filtering the acquired real-time data and removing abnormal values and noise;
and the feature extraction unit is used for extracting statistical features, frequency domain features and time domain features from the data and selecting features related to faults.
As a further aspect of the present invention, the missing data padding module includes:
the missing searching unit is used for detecting the continuity of the real-time data, and marking the missing part when detecting that the real-time data has a discontinuous part;
the data filling unit is used for acquiring all the real-time data missing parts, identifying the front and rear data trend and the data acquisition time of the missing parts, establishing a filling model, calculating the numerical value of the missing parts by utilizing the front and rear data trend of the missing parts and the historical data of the same acquisition time, and completing the real-time data.
As a still further aspect of the present invention, the missing retrieval unit includes:
the continuity detection unit is used for analyzing the data time stamp and the data value and detecting incoherent data and missing data;
the missing labeling unit is used for labeling the detected time periods of continuous interruption, data loss or data inconsistency of the data and distinguishing normal real-time data from missing data;
and the data positioning unit is used for identifying the time period and the spanned time window of the occurrence of the missing data according to the analysis of the data continuity.
As a further aspect of the present invention, the data shim unit includes:
the trend identification unit is used for judging the trend and rule of the data through analyzing the trend of the data before and after the real-time data missing part and the historical data of the same acquisition time;
the filling model building unit is used for building a filling model by utilizing a time window spanned by known historical data and missing data;
the data reckoning unit is used for reckoning the missing data in a reckoning mode by utilizing the filling model and combining the data patterns before and after the missing data in the time window and the rules of the historical data.
As a further aspect of the present invention, the model building module includes:
the model training unit is used for establishing a fault prediction model, dividing historical data in a historical database into a training set and a testing set, and training the selected fault prediction model through data of the training set;
the effect evaluation unit is used for evaluating the trained model by using the test set, calculating the evaluation index of the model and optimizing the model according to the evaluation result.
As a further aspect of the present invention, the data monitoring module includes:
the real-time analysis unit is used for inputting the real-time data subjected to filling and feature extraction into a fault prediction model, and predicting and diagnosing faults occurring in the future by using the model;
and the threshold setting unit is used for setting an abnormal threshold interval according to the historical data and the application requirement.
As a further aspect of the present invention, the alarm module includes:
the analysis and comparison unit is used for comparing the output result of the fault prediction model with a set abnormal threshold value and bringing the result of triggering an alarm and an abnormal state into alarm processing;
and the alarm triggering unit is used for triggering an alarm mechanism when the abnormal condition of the real-time data is monitored, and sending alarm information to related personnel in a notification mode.
As a further aspect of the present invention, the system further includes:
and the data re-storage module is used for marking the real-time data as historical data after the real-time data is subjected to data monitoring analysis and is stored in the historical database.
The beneficial effects of the invention are as follows:
the system can collect data of the power system in real time by utilizing the real-time data acquisition module, and monitor and detect the abnormality and the missing condition of the data by the missing data filling module, so that the continuity of the data is ensured.
The missing data filling module can calculate and complement the detected data fracture and missing part. The system can calculate and complement missing data more accurately by establishing an adaptive filling model and combining the trend and the historical rule of the data, and improves the accuracy and reliability of fault prediction and diagnosis.
The system can provide complete and coherent real-time data, and the data analysis and decision making capability of the system are enhanced. The complement of the missing data is helpful to more comprehensively analyze the characteristics and the trend of the data, so that the accuracy and the reliability of the fault prediction model and the system are improved. The enhanced data analysis capability provides more accurate decision basis for maintenance personnel, accelerates the fault processing speed, and improves the accuracy of fault diagnosis and the efficiency of fault processing.
Drawings
Fig. 1 is a block diagram of a power system fault prediction and diagnosis system based on cloud computing according to an embodiment of the present invention;
FIG. 2 is a block diagram of a data acquisition module according to an embodiment of the present invention;
FIG. 3 is a block diagram illustrating a data processing module according to an embodiment of the present invention;
FIG. 4 is a block diagram illustrating a missing data filling module according to an embodiment of the present invention;
FIG. 5 is a block diagram of a missing search unit according to an embodiment of the present invention;
FIG. 6 is a block diagram illustrating a missing shim cell according to an embodiment of the present invention;
FIG. 7 is a block diagram of a model building module according to an embodiment of the present invention;
FIG. 8 is a block diagram of a data monitoring module according to an embodiment of the present invention;
fig. 9 is a block diagram of an alarm module according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
It will be understood that the terms "first," "second," and the like, as used herein, may be used to describe various elements, but these elements are not limited by these terms unless otherwise specified. These terms are only used to distinguish one element from another element. For example, a first xx script may be referred to as a second xx script, and similarly, a second xx script may be referred to as a first xx script, without departing from the scope of the present application.
Fig. 1 is a block diagram of a power system fault prediction and diagnosis system based on cloud computing according to an embodiment of the present invention, as shown in fig. 1, and is characterized in that the system includes:
the data acquisition module 100 is used for acquiring real-time data of the power system, establishing a storage database and a history database, storing the real-time data into the storage database, and storing the history data of the power system into the history database;
in the module, the collected data is monitored in real time through a real-time data anomaly detection algorithm, the anomaly data is found and filtered, the problems of sensor faults, measurement anomalies or data transmission errors and the like can be found immediately, the anomaly data is filtered, and the accuracy and reliability of subsequent data processing and analysis are ensured; then, rationality checking is carried out on the collected real-time data, whether the data fall in a reasonable range is verified, the rationality checking is used for eliminating the collected unreasonable data, errors caused by sensor deviation or artificial interference and the like are reduced, and the quality and usability of the data are improved; the module can integrate real-time data from a plurality of data sources, including data acquired by different devices, different sensors or different data transmission channels, provides comprehensive data acquisition capability, can acquire real-time data of a power system more comprehensively, and increases the diversity and accuracy of the data; when data are acquired, reasonable acquisition frequency and time interval are set, automatic data acquisition is carried out in proper time, the workload of manual intervention is reduced, the efficiency and accuracy of data acquisition are improved, and the real-time performance and continuity of the data are ensured; and finally, storing the acquired real-time data in real time, providing a data visualization function, and displaying the state and the change trend of the power system in real time.
The data acquisition module can acquire real-time data of the power system more comprehensively and accurately, process and store the data, and provide a high-quality data basis for subsequent data processing, model establishment and fault prediction. Meanwhile, abnormal data can be monitored and filtered in real time, the quality and reliability of the data are guaranteed, and the comprehensive performance of the power system fault prediction and diagnosis system is improved.
The data processing module 200 is used for preprocessing the real-time data in the storage database and extracting the characteristics of the data after the preprocessing is completed;
in the module, the collected real-time data is normalized and standardized, and the data in different ranges are unified into the same scale, so that data deviation caused by different data types or dimensions can be eliminated, and the accuracy and stability of feature extraction and model training are improved; by means of data processing methods such as data transformation, dimension reduction, cross features and the like, features with more expression capability are constructed, features with more information quantity and correlation are extracted, and the detection and diagnosis capability of a fault prediction model on a power system fault is enhanced. Then, abnormal values in the data are detected and identified through an abnormal detection algorithm, and are repaired or replaced, so that the quality and the accuracy of the data can be improved, deviation caused by the abnormal values is eliminated, and the stability and the reliability of the model are enhanced; and meanwhile, the preprocessed data is stored in a persistence mode, a data warehouse is established, long-term data analysis and historical data backtracking are supported, long-term and consistent data are provided for subsequent model retraining, data analysis and performance evaluation, iterative optimization and decision assistance of a system are supported, the most relevant features of a fault prediction model can be automatically evaluated and selected by using an automatic feature selection algorithm, input dimensions and redundant features are reduced, complexity and dimensions of the features are reduced, calculation amount of model training and inference is reduced, and interpretation and generalization capability of the model are improved.
The missing data filling module 300 is configured to detect continuity of real-time data, and calculate and fill up a value of a missing portion when detecting that the real-time data has a discontinuous portion;
in the module, firstly, the data time stamp and the data value are analyzed, the discontinuity in the real-time data is detected, the missing data and the continuity interruption of the data are identified, the position and the range of the missing part in the real-time data are helped to be determined, and positioning information is provided for filling the missing data. And then marking the detected time periods of continuous interruption, data loss or data inconsistency of the data, distinguishing normal real-time data from missing data, and facilitating subsequent analysis and processing of the characteristics and rules of the missing data. And then judging the trend and rule of the data by analyzing the trend of the data before and after the real-time data missing part and the historical data of the same acquisition time. Finally, the time window spanned by the known historical data and the missing data is utilized. And calculating and filling the missing data by filling the model and combining the patterns of the data before and after the missing part and the rules of the historical data. By establishing a filling model and comprehensively analyzing the trends of the data before and after, the missing data is speculated and filled, the real-time data is completed, and the integrity and the continuity of the data are ensured.
The missing data filling module can analyze and process missing parts of real-time data more comprehensively and accurately, improves the integrity and continuity of the data in a filling calculation mode, and provides an accurate and reliable data basis for subsequent fault prediction and diagnosis.
The model building module 400 is configured to build a fault prediction model, and train the model by using historical data;
the model building module is a key part in a power system fault prediction and diagnosis system based on cloud computing. The function of the module is to build a fault prediction model, train and evaluate the model by using historical data, and ensure the accuracy and reliability of the model.
First, the model building module includes a model training unit. In the model training stage, historical data in a historical database is subjected to data preparation according to the division of a training set and a testing set. The selected fault prediction model is then trained using the data in the training set. These models may employ various techniques to flexibly accommodate different power system characteristics and forecast requirements.
Next, the module further comprises an effect evaluation unit. At this stage, predictions are made from the trained models using the reserved test data, and evaluation metrics such as accuracy, precision, recall, F1 score, etc. are calculated. The calculation of the evaluation index can enable a system administrator to better know the performance of the model, and the model can be further optimized and adjusted according to the performance of the model so as to improve the accuracy of prediction.
Such a modeling module provides the following effects:
the accuracy and the reliability of fault prediction are improved: by training the historical data, the model can gradually learn the mode and the characteristics of the power system, so that the accuracy and the reliability of fault prediction are improved. This helps to discover potential faults early and guides maintenance personnel to take appropriate action to prevent occurrence and impact of the faults.
Support fine maintenance and optimization decisions: by using the established fault prediction model, a system administrator can make decisions for optimizing the operation and maintenance of the power system according to the prediction result of the model. This makes the maintenance work more targeted and effective, improving the operating efficiency and reliability of the entire power system.
Evaluation and optimization of the model: by evaluating and optimizing the effect of the model, the performance of the model can be checked, and corresponding adjustment and improvement can be performed according to the evaluation result. The accuracy and the applicability of the model can be improved, and the fault prediction module is continuously perfected.
In summary, the improvement of the model building module expands the fault prediction capability of the power system. By means of the established fault prediction model, the system can obtain accurate prediction results and can support maintenance personnel to make more accurate maintenance and optimization decisions, so that the reliability and safety of the power system are improved. Meanwhile, the accuracy and the prediction performance of the model can be further improved by evaluating and optimizing the model.
The data monitoring module 500 is configured to analyze the collected real-time data of the power system through a fault prediction model, set an abnormal threshold interval, and compare the analysis result with the abnormal threshold interval;
the data monitoring module is a crucial part of a power system fault prediction and diagnosis system based on cloud computing. The module provides fault prediction and diagnosis functions by analyzing the real-time data subjected to filling and feature extraction in real time. First, the real-time data is pre-processed to further optimize the data quality. And secondly, inputting the preprocessed real-time data into a pre-established fault prediction model, and predicting and diagnosing faults by using the model. This helps to discover potential fault conditions in advance and to take reasonable maintenance and optimization measures to ensure stable operation of the power system.
In addition, the data monitoring module is also responsible for setting an abnormal threshold interval. By analyzing historical data characteristics and taking into account power system operational requirements, a system administrator may set appropriate anomaly thresholds. These thresholds are intended to identify whether the real-time data analysis results are outside or below an expected range. As long as the analysis result exceeds or is lower than the set threshold value interval, the alarm module can be triggered and immediately sends out alarm information. The real-time abnormal condition detection and warning mechanism enables faults and abnormal conditions to be found out rapidly and respond rapidly, and is helpful for timely taking measures to reduce the time and influence of the faults.
In summary, the data monitoring module plays an important role in real-time monitoring, analyzing fault prediction and diagnosing faults in a power system fault prediction and diagnosis system based on cloud computing. By analyzing the real-time data, the functions of fault prediction and diagnosis are provided, and the set abnormal threshold interval is favorable for timely finding potential fault conditions, so that the reliability and safety of the system are improved.
The alarm module 600 sends out alarm information when the analysis result exceeds or falls below the abnormal threshold interval.
The module has the capability of real-time abnormal condition detection and quick response. First, the output result of the failure prediction model is compared with a preset abnormality threshold by analysis and comparison. If the predicted result exceeds or falls below the set abnormal threshold interval, the predicted result is judged to be in an abnormal state, and a corresponding alarm is triggered. The alarm module can also monitor the state of real-time data in time so as to quickly discover any abnormal situation.
Once an abnormal condition is detected, the alarm module triggers an alarm mechanism. The related personnel receive the alarm information in a notification mode so as to ensure that the related personnel can know the abnormal condition of the power system in time. This may prompt the relevant personnel to take the necessary action and to quickly perform fault handling or maintenance. In addition, the alarm module also helps to provide decision support and enhance the operability of the fault. By sending alarm information to related personnel, a response team can be quickly organized, decision making during fault processing is enhanced, and maintenance efficiency and stability of the power system are improved.
In summary, the alarm module plays a key role in the power system fault prediction and diagnosis system. By means of real-time abnormal condition detection and alarm notification, the abnormal condition of the power system can be rapidly found, and measures can be timely taken for processing. The function of the module realizes monitoring, alarm notification and decision support of the abnormal state of the power system, thereby improving the reliability and safety of the power system.
Fig. 2 is a block diagram of a data acquisition module according to an embodiment of the present invention, as shown in fig. 2, where the data acquisition module includes:
a data acquisition unit 110 for acquiring real-time data of the power system through the sensor and the monitoring device;
the data storage unit 120 is configured to establish a storage database, and store the collected real-time data of the power system in the storage database;
a history data storage unit 130, configured to establish a history database, and extract history data of the power system into the history database;
and a quality inspection unit 140 for performing quality inspection on the data in the storage database.
Fig. 3 is a block diagram of a data processing module according to an embodiment of the present invention, and as shown in fig. 3, the data processing module includes:
the data cleaning unit 210 is configured to clean and filter the collected real-time data, and remove abnormal values and noise;
the feature extraction unit 220 is configured to extract statistical features, frequency domain features, and time domain features from the data, and select features related to the fault.
Fig. 4 is a block diagram of a missing data filling module according to an embodiment of the present invention, as shown in fig. 4, where the missing data filling module includes:
the missing retrieving unit 310 is configured to detect continuity of the real-time data, and mark a missing portion when detecting that there is a discontinuous portion in the real-time data;
the data filling unit 320 is configured to obtain all the missing parts of the real-time data, identify the front and rear data trend and the data acquisition time of the missing parts, build a filling model, calculate the values of the missing parts by using the front and rear data trend of the missing parts and the historical data of the same acquisition time, and complete the real-time data.
Fig. 5 is a block diagram of a deletion search unit according to an embodiment of the present invention, as shown in fig. 5, where the deletion search unit includes:
a continuity detecting unit 311 for analyzing the data time stamp and the data value, and detecting incoherent data and missing data;
a missing labeling unit 312, configured to label a time period in which the detected data is continuously interrupted, lost or inconsistent, and distinguish normal real-time data from missing data;
a data positioning unit 313 for identifying a time period and a time window spanned by the missing data from the analysis of the data continuity.
Fig. 6 is a block diagram of a missing shim cell according to an embodiment of the present invention, and as shown in fig. 6, the data shim cell includes:
a trend identifying unit 321, configured to determine a trend and a rule of data by analyzing trends of data before and after the real-time data missing portion and historical data of the same acquisition time;
a padding model building unit 322, configured to build a padding model using the time window spanned by the known history data and the missing data;
the data estimation unit 323 is configured to fill the missing data in an estimation manner by using a filling model and combining the data patterns before and after the missing data in the time window and the rules of the historical data.
Fig. 7 is a block diagram of a model building module according to an embodiment of the present invention, as shown in fig. 7, where the model building module includes:
the model training unit 410 is configured to establish a fault prediction model, divide the historical data in the historical database into a training set and a testing set, and train the selected fault prediction model through the data of the training set;
and the effect evaluation unit 420 is configured to evaluate the trained model using the test set, calculate an evaluation index of the model, and optimize the model according to the evaluation result.
Fig. 8 is a block diagram of a data monitoring module according to an embodiment of the present invention, as shown in fig. 8, where the data monitoring module includes:
the real-time analysis unit 510 is configured to input the real-time data after filling and feature extraction into a fault prediction model, and predict and diagnose a fault occurring in the future by using the model;
the threshold setting unit 520 is configured to set an abnormal threshold interval according to the history data and the application requirement.
Fig. 9 is a block diagram of an alarm module according to an embodiment of the present invention, as shown in fig. 9, where the alarm module includes:
the analysis and comparison unit 610 is configured to compare an output result of the fault prediction model with a set abnormal threshold value, and incorporate a result of triggering an alarm and an abnormal state into an alarm process;
and the alarm triggering unit 620 is configured to trigger an alarm mechanism when the abnormal condition of the real-time data is detected, and send alarm information to related personnel in a notification manner.
In an embodiment of the present invention, the system further includes:
the data re-storing module 700 is configured to mark the real-time data as historical data after the real-time data is subjected to data monitoring analysis, and store the historical data in the historical database.
It should be understood that, although the steps in the flowcharts of the embodiments of the present invention are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in various embodiments may include multiple sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor do the order in which the sub-steps or stages are performed necessarily performed in sequence, but may be performed alternately or alternately with at least a portion of the sub-steps or stages of other steps or other steps.
Those skilled in the art will appreciate that all or part of the processes in the methods of the above embodiments may be implemented by a computer program for instructing relevant hardware, where the program may be stored in a non-volatile computer readable storage medium, and where the program, when executed, may include processes in the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
The technical features of the above-described embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above-described embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples illustrate only a few embodiments of the invention and are described in detail herein without thereby limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.
Claims (10)
1. A cloud computing-based power system fault prediction and diagnosis system, the system comprising:
the data acquisition module is used for acquiring real-time data of the power system, establishing a storage database and a history database, and respectively storing the real-time data and the history data into the storage database and the history database;
the data processing module is used for preprocessing and extracting features of real-time data in the storage database;
the missing data filling module is used for detecting the continuity of the real-time data, and calculating and filling the numerical value of the missing part when detecting that the real-time data has an incoherent part;
the model building module is used for building a fault prediction model and training the model by utilizing historical data;
the data monitoring module is used for analyzing the collected real-time data of the power system through the fault prediction model, setting an abnormal threshold interval and comparing an analysis result with the abnormal threshold interval;
and the alarm module is used for sending out alarm information when the analysis result exceeds or is lower than the abnormal threshold value interval.
2. The system of claim 1, wherein the data acquisition module comprises:
the data acquisition unit is used for acquiring real-time data of the power system through the sensor and the monitoring equipment;
the data storage unit is used for establishing a storage database and storing the acquired real-time data of the power system in the storage database;
the historical data storage unit is used for establishing a historical database and extracting historical data of the power system into the historical database;
and the quality inspection unit is used for performing quality inspection on the data in the storage database.
3. The system of claim 2, wherein the data processing module comprises:
the data cleaning unit is used for cleaning and filtering the acquired real-time data and removing abnormal values and noise;
and the feature extraction unit is used for extracting statistical features, frequency domain features and time domain features from the data and selecting features related to faults.
4. The system of claim 3, wherein the missing data padding module comprises:
the missing searching unit is used for detecting the continuity of the real-time data, and marking the missing part when detecting that the real-time data has a discontinuous part;
the data filling unit is used for acquiring all the real-time data missing parts, identifying the front and rear data trend and the data acquisition time of the missing parts, establishing a filling model, calculating the numerical value of the missing parts by utilizing the front and rear data trend of the missing parts and the historical data of the same acquisition time, and completing the real-time data.
5. The system of claim 4, wherein the miss retrieval unit comprises:
the continuity detection unit is used for analyzing the data time stamp and the data value and detecting incoherent data and missing data;
the missing labeling unit is used for labeling the detected time periods of continuous interruption, data loss or data inconsistency of the data and distinguishing normal real-time data from missing data;
and the data positioning unit is used for identifying the time period and the spanned time window of the occurrence of the missing data according to the analysis of the data continuity.
6. The system of claim 5, wherein the data shim unit comprises:
the trend identification unit is used for judging the trend and rule of the data through analyzing the trend of the data before and after the real-time data missing part and the historical data of the same acquisition time;
the filling model building unit is used for building a filling model by utilizing a time window spanned by known historical data and missing data;
the data reckoning unit is used for reckoning the missing data in a reckoning mode by utilizing the filling model and combining the data patterns before and after the missing data in the time window and the rules of the historical data.
7. The system of claim 2, wherein the model building module comprises:
the model training unit is used for establishing a fault prediction model, dividing historical data in a historical database into a training set and a testing set, and training the selected fault prediction model through data of the training set;
the effect evaluation unit is used for evaluating the trained model by using the test set, calculating the evaluation index of the model and optimizing the model according to the evaluation result.
8. The system of claim 7, wherein the data monitoring module comprises:
the real-time analysis unit is used for inputting the real-time data subjected to filling and feature extraction into a fault prediction model, and predicting and diagnosing faults occurring in the future by using the model;
and the threshold setting unit is used for setting an abnormal threshold interval according to the historical data and the application requirement.
9. The system of claim 8, wherein the alarm module comprises:
the analysis and comparison unit is used for comparing the output result of the fault prediction model with a set abnormal threshold value and bringing the result of triggering an alarm and an abnormal state into alarm processing;
and the alarm triggering unit is used for triggering an alarm mechanism when the abnormal condition of the real-time data is monitored, and sending alarm information to related personnel in a notification mode.
10. The system of claim 9, wherein the system further comprises:
and the data re-storage module is used for marking the real-time data as historical data after the real-time data is subjected to data monitoring analysis and is stored in the historical database.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311747202.8A CN117892240A (en) | 2023-12-19 | 2023-12-19 | Cloud computing-based power system fault prediction and diagnosis system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311747202.8A CN117892240A (en) | 2023-12-19 | 2023-12-19 | Cloud computing-based power system fault prediction and diagnosis system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117892240A true CN117892240A (en) | 2024-04-16 |
Family
ID=90638616
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311747202.8A Pending CN117892240A (en) | 2023-12-19 | 2023-12-19 | Cloud computing-based power system fault prediction and diagnosis system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117892240A (en) |
-
2023
- 2023-12-19 CN CN202311747202.8A patent/CN117892240A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110414155B (en) | Fan component temperature abnormity detection and alarm method with single measuring point | |
| CN111542846B (en) | Fault Prediction System and Fault Prediction Method | |
| CA2426627C (en) | Method and system for analyzing fault and quantized operational data for automated diagnostics of locomotives | |
| CN108027611B (en) | Decision assistance system and method for machine maintenance using expert opinion supervised decision mode learning | |
| ES2742298T3 (en) | Process to optimize the maintenance of technical systems | |
| CN112083244B (en) | Integrated intelligent diagnosis system for faults of avionic equipment | |
| KR102427205B1 (en) | Apparatus and method for generating training data of artificial intelligence model | |
| CN112487356A (en) | Structural health monitoring data enhancement method | |
| CN111814954A (en) | Optical fiber quality analysis method and device, electronic equipment and storage medium | |
| CN114781476A (en) | Fault analysis system and method for measuring equipment | |
| CN111400850B (en) | Equipment fault analysis method, device, equipment and storage medium | |
| CN114462820A (en) | Bearing state monitoring and health management system performance testing and optimizing method and system | |
| CN116345690B (en) | Power monitoring false alarm identification method and system based on power supply system equipment list | |
| CN112396250B (en) | Diesel engine fault prediction method, device, equipment and storage medium | |
| CN111314110B (en) | Fault early warning method for distributed system | |
| CN112524077A (en) | Method, device and system for detecting fan fault | |
| CN117892240A (en) | Cloud computing-based power system fault prediction and diagnosis system | |
| CN115034094B (en) | Prediction method and system for operation state of metal processing machine tool | |
| CN115018220A (en) | Household appliance fault prediction method and system based on knowledge graph | |
| CN114322446A (en) | Cooling system fault early warning method and device, cooling system and operation machine | |
| KR102470804B1 (en) | Method and system for comprehensive diagnosis defects in rotating machinery | |
| CN115526345A (en) | Ship maintenance management method, system, readable storage medium and computer equipment | |
| JP2019211919A (en) | Monitoring device, monitoring method, and computer program | |
| CN112363432A (en) | Monitoring system and monitoring method for hydropower station auxiliary equipment | |
| CN117591949A (en) | Equipment abnormality identification method, equipment and medium |
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 |