CN113702862A - Power supply state panoramic monitoring method and device based on cloud deployment - Google Patents
Power supply state panoramic monitoring method and device based on cloud deployment Download PDFInfo
- Publication number
- CN113702862A CN113702862A CN202111007926.XA CN202111007926A CN113702862A CN 113702862 A CN113702862 A CN 113702862A CN 202111007926 A CN202111007926 A CN 202111007926A CN 113702862 A CN113702862 A CN 113702862A
- Authority
- CN
- China
- Prior art keywords
- data
- processing
- signal data
- unified
- virtual
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/40—Testing power supplies
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Neurology (AREA)
- Debugging And Monitoring (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses a power supply state panoramic monitoring method and device based on cloud deployment, wherein the method comprises the following steps: acquiring multi-source heterogeneous signal data of a power supply terminal based on a data acquisition sensor, and uniformly processing the multi-source heterogeneous signal data to obtain uniform signal data; uploading the unified signal data to a virtual data server based on a virtual interface server for partitioned storage processing; the virtual computing server extracts unified signal data from the partitioned storage of the virtual data server based on the service instruction, and performs service analysis processing on the extracted unified signal data to obtain an analysis result; and pushing the analysis result to a terminal, and generating a user playing interface matched with browser software at the terminal based on the extensible markup language to play and display the analysis result. In the embodiment of the invention, the related management user can visually carry out panoramic monitoring on the power supply and know the health state of the power supply in time.
Description
Technical Field
The invention relates to the technical field of power supplies, in particular to a power supply state panoramic monitoring method and device based on cloud deployment.
Background
In the high-power multistage amplification radio frequency power supply, a power multistage amplifier adopts an all-solid-state power tube, a radio frequency driving signal is input to provide an excitation source for the multistage amplifier, and an impedance matcher realizes maximum power output through impedance matching; therefore, it is urgently needed to establish a platform, so that data of each node of the power supply in different regions can be integrated, and the state of the power supply can be monitored in real time and early warning of possible faults can be realized by using a related big data processing technology, so that the purpose of panoramic monitoring of the state of the power supply is achieved.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, and provides a power supply state panoramic monitoring method and device based on cloud deployment, which can enable related management users to visually perform panoramic monitoring on a power supply and know the health state of the power supply in time.
In order to solve the above technical problem, an embodiment of the present invention provides a power state panoramic monitoring method based on cloud deployment, where the method includes:
acquiring multi-source heterogeneous signal data of a power supply terminal based on a data acquisition sensor, and uniformly processing the multi-source heterogeneous signal data to obtain uniform signal data;
uploading the unified signal data to a virtual data server based on a virtual interface server for partitioned storage processing;
the virtual computing server extracts unified signal data from the partitioned storage of the virtual data server based on the service instruction, and performs service analysis processing on the extracted unified signal data to obtain an analysis result, wherein the service analysis processing comprises real-time state evaluation processing and real-time fault diagnosis processing;
and pushing the analysis result to a terminal, and generating a user playing interface matched with browser software at the terminal based on the extensible markup language to play and display the analysis result.
Optionally, the acquiring of the multi-source heterogeneous signal data of the power terminal based on the data acquisition sensor includes:
and respectively arranging data acquisition sensors on each node of the power terminal, and acquiring signal data on each node of the power terminal based on the data acquisition sensors to form multi-source heterogeneous signal data.
Optionally, the uniformly processing the multi-source heterogeneous signal data to obtain uniform signal data includes:
sampling, holding and quantizing the multi-source heterogeneous signal data in sequence to obtain a processing result;
carrying out unique identification coding processing on the processing result according to the acquisition time stamp and the node sensor number contained in the corresponding multi-source heterogeneous signal data to obtain a processing result after unique coding;
denoising the processing result after the unique coding based on digital filtering to obtain a denoising processing result;
and carrying out data cleaning and unified processing on the denoising processing result to obtain unified signal data.
Optionally, the performing data cleaning and unified processing on the denoising processing result to obtain unified signal data includes:
carrying out invalid and repeated data deletion on the denoising processing result based on a decision tree of a rough set theory to obtain a denoising processing result after deletion;
carrying out abnormal data correction processing on the de-noising processing result after deletion processing, and carrying out filling missing data processing on the corrected data based on a difference method to obtain filled data;
and carrying out format unified processing on the supplemented data to obtain unified signal data.
Optionally, the uploading, by the virtual interface-based server, the unified signal data to a virtual data server for partition storage processing includes:
uploading the unified signal data to a virtual data server based on a virtual interface server, and converting the unified signal data into binary information after the virtual data server receives the unified signal data;
and carrying out partition storage processing on the binary information in a partition memory according to a storage queue structure formed by acquisition time.
Optionally, the extracting, by the virtual computing server, unified signal data in the partitioned storage of the virtual data server based on the service instruction includes:
and the virtual computing server extracts unified signal data in the partitioned storage of the virtual data server according to the storage queue structure of the unified signal data based on the service instruction.
Optionally, the performing service analysis processing on the extracted unified signal data to obtain an analysis result includes:
carrying out real-time state evaluation processing on the extracted unified signal data to obtain a real-time evaluation result;
performing real-time fault diagnosis processing on the extracted unified signal data to obtain a real-time fault diagnosis result; the real-time fault diagnosis processing model comprises a training converged BP neural network model and a fuzzy set theory optimized by a genetic algorithm; and the BP neural network model is optimized by using a genetic algorithm before training.
Optionally, the performing real-time fault diagnosis processing on the extracted unified signal data to obtain a real-time fault diagnosis result includes:
performing feature extraction processing on the extracted unified signal data based on time domain analysis and frequency domain analysis by using a signal statistical analysis method to obtain signal extraction features;
confirming that the signal extraction features are direct-current power supply signal extraction features or low-voltage power supply signal extraction features;
when the signal extraction features are direct-current power supply signal extraction features, inputting the signal extraction features into a BP neural network model with training convergence to perform real-time fault diagnosis processing, and outputting fault diagnosis information corresponding to the signal extraction features;
and when the signal extraction features are low-voltage power supply signal extraction features, inputting the signal extraction features into a fuzzy set theory optimized by using a genetic algorithm to perform real-time fault diagnosis processing, and outputting fault diagnosis information corresponding to the signal extraction features.
Optionally, after performing service analysis processing on the extracted unified signal data, the method further includes:
deleting the extracted unified signal data in the partitioned storage in the virtual data server, and marking the extracted unified signal data by using an analysis result corresponding to the extracted unified signal data to obtain marked unified signal data;
and storing the marked unified signal data into a historical data storage partition.
In addition, the embodiment of the invention also provides a power supply state panoramic monitoring method based on cloud deployment, which comprises the following steps:
a unified processing module: the data acquisition sensor is used for acquiring multi-source heterogeneous signal data of the power terminal and uniformly processing the multi-source heterogeneous signal data to obtain uniform signal data;
a storage module: the unified signal data are uploaded to a virtual data server based on a virtual interface server to be subjected to partition storage processing;
an analysis module: the virtual computing server extracts unified signal data from the partitioned storage of the virtual data server based on the service instruction, and performs service analysis processing on the extracted unified signal data to obtain an analysis result, wherein the service analysis processing comprises real-time state evaluation processing and real-time fault diagnosis processing;
the playing and displaying module: and the system is used for pushing the analysis result to a terminal and generating a user playing interface matched with browser software at the terminal based on the extensible markup language to play and display the analysis result.
In the embodiment of the invention, the power supply can be monitored in a panoramic way by related management users visually, and the health state of the power supply can be known in time; the method can realize the integration of data of each node of the power supply in different regions, and realize the real-time monitoring of the state of the power supply and the early warning of possible faults by using a relevant big data processing technology, thereby achieving the purpose of panoramic monitoring of the state of the power supply.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart diagram illustrating a power state panoramic monitoring method based on cloud deployment in an embodiment of the present invention;
fig. 2 is a schematic structural composition diagram of a power state panoramic monitoring apparatus based on cloud deployment in an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example one
Referring to fig. 1, fig. 1 is a schematic flowchart of a power state panoramic monitoring method based on cloud deployment according to an embodiment of the present invention.
As shown in fig. 1, a power state panoramic monitoring method based on cloud deployment, the method includes:
s11: acquiring multi-source heterogeneous signal data of a power supply terminal based on a data acquisition sensor, and uniformly processing the multi-source heterogeneous signal data to obtain uniform signal data;
in a specific implementation process of the invention, the acquiring of the multi-source heterogeneous signal data of the power terminal based on the data acquisition sensor comprises the following steps: and respectively arranging data acquisition sensors on each node of the power terminal, and acquiring signal data on each node of the power terminal based on the data acquisition sensors to form multi-source heterogeneous signal data.
Further, the unified processing of the multi-source heterogeneous signal data to obtain unified signal data includes: sampling, holding and quantizing the multi-source heterogeneous signal data in sequence to obtain a processing result; carrying out unique identification coding processing on the processing result according to the acquisition time stamp and the node sensor number contained in the corresponding multi-source heterogeneous signal data to obtain a processing result after unique coding; denoising the processing result after the unique coding based on digital filtering to obtain a denoising processing result; and carrying out data cleaning and unified processing on the denoising processing result to obtain unified signal data.
Further, the data cleaning and unified processing are performed on the denoising processing result to obtain unified signal data, including: carrying out invalid and repeated data deletion on the denoising processing result based on a decision tree of a rough set theory to obtain a denoising processing result after deletion; carrying out abnormal data correction processing on the de-noising processing result after deletion processing, and carrying out filling missing data processing on the corrected data based on a difference method to obtain filled data; and carrying out format unified processing on the supplemented data to obtain unified signal data.
Specifically, each node exists in the power supply terminal, a corresponding data acquisition sensor is arranged on each node of the power supply terminal, and then signal data on each node of the power supply terminal are acquired according to the data acquisition sensors and are converged to form multi-source heterogeneous signal data.
For multi-source heterogeneous data, relevant processing is required, subsequent processing requirements are facilitated, namely the multi-source heterogeneous signal data are required to be converted and denoised, analog signals are mainly converted into digital signals, subsequent reading and denoising processing is facilitated, impurity influence can be effectively reduced, and monitoring precision is improved.
After multi-source heterogeneous signal data are converted through an analog-to-digital converter, sampling, holding and quantizing are sequentially carried out, so that a processing result is obtained, then the processing result is subjected to unique identification coding processing according to an acquisition timestamp and a node sensor number contained in the corresponding multi-source heterogeneous signal data, the processing result after unique coding is obtained, and the specific unique coded data can be conveniently inquired or called through the coding in the follow-up process; then, denoising the processing result after the unique coding according to digital filtering to obtain a denoising processing result, namely, filtering and denoising the data signal by adopting a digital filtering algorithm, wherein the digital filtering comprises classical filtering and modern filtering; the classical filtering is an engineering concept proposed according to Fourier analysis and transformation, and according to high mathematics theory, any signal meeting a certain condition can be regarded as being formed by superposing infinite sine waves, namely the engineering signal is formed by linearly superposing sine waves with different frequencies, and the sine waves with different frequencies forming the signal are called frequency components or harmonic components of the signal; modern filtering is to use the nature of randomness of signals, regard signals and their noise as random signals, estimate the signals themselves by using their statistical characteristics, once the signals are estimated, the signals themselves obtained are much higher than the original signal-to-noise ratio, typical digital filters are Kalman filtering, Wenner filtering, adaptive filtering, wavelet transform (wavelet) and so on; the digital filtering has the advantages of high precision, high reliability, programmable change of characteristics or multiplexing, convenience in integration and the like; the digital filtering is of low-pass, high-pass, band-stop, all-pass and other types; may be time-invariant or time-variant, causal or non-causal, linear or non-linear; the most widely used is the linear, time-invariant digital filter; and finally, data cleaning and unified processing are needed to be carried out on the denoising processing result, so that unified signal data are obtained.
In the data cleaning and unified processing, the decision tree of the rough set theory is adopted to carry out invalid and repeated data deletion processing on the denoising processing result to obtain the denoising processing result after the deletion processing, the decision tree of the rough set theory can realize induction on the data, so that redundant impurity data in the data are removed, and the formed data are relatively simplified; then, abnormal data correction processing is carried out on the de-noising processing result after deletion processing, missing data compensation processing is carried out on the corrected data based on a difference method, preprocessed multi-source heterogeneous signal data are obtained, when abnormal data are corrected, abnormal values are judged by adopting a three-sigma criterion to realize abnormal data correction, and the abnormal values are values of which the deviation from the average value exceeds 3 times of standard deviation in a group of measured values; the three sigma criterion is also called Lauda criterion, which is that firstly, a group of detection data is supposed to only contain random errors, the detection data is calculated to obtain standard deviation, an interval is determined according to a certain probability, the error exceeding the interval is considered not to belong to the random errors but to be coarse errors, and the data containing the errors are removed; in the completion missing processing process, an interpolation algorithm is adopted to realize completion missing data, and concretely, Lagrange interpolation, Newton interpolation, Hermite interpolation, segmented interpolation, spline interpolation and the like can be used for realizing completion missing data; after the complemented data is obtained, format unification processing is required, that is, format unification is performed on the complemented data with multi-source isomerism, so that unified signal data is obtained.
S12: uploading the unified signal data to a virtual data server based on a virtual interface server for partitioned storage processing;
in a specific implementation process of the present invention, the uploading the unified signal data to a virtual data server for partition storage processing by a virtual interface-based server includes: uploading the unified signal data to a virtual data server based on a virtual interface server, and converting the unified signal data into binary information after the virtual data server receives the unified signal data; and carrying out partition storage processing on the binary information in a partition memory according to a storage queue structure formed by the acquisition time.
Specifically, unified signal data are uploaded to a virtual data server according to a virtual interface server, and then are converted into binary information after the virtual data server receives the unified signal data, so that the binary information can be used for conveniently performing related storage processing in a memory; because the unified signal data contains the acquisition time, a storage queue structure is formed according to the acquisition time, and then the binary information is subjected to partition storage processing in a partition memory according to the storage queue structure formed by the acquisition time; when the queue structure is stored, a first-in first-out principle can be realized, and when the stored data is subsequently extracted, the stored data can be extracted according to the storage sequence, so that the condition that any stored data is not missed is ensured; meanwhile, in the storage process, the stored unified signal data are correspondingly bound by using a unique score, so that binary information corresponding to the unified signal data is converted into a message chain form, and subsequent storage and query are facilitated.
S13: the virtual computing server extracts unified signal data from the partitioned storage of the virtual data server based on the service instruction, and performs service analysis processing on the extracted unified signal data to obtain an analysis result, wherein the service analysis processing comprises real-time state evaluation processing and real-time fault diagnosis processing;
in a specific implementation process of the present invention, the extracting, by the virtual computing server, unified signal data in the partitioned storage of the virtual data server based on a service instruction includes: and the virtual computing server extracts unified signal data in the partitioned storage of the virtual data server according to the storage queue structure of the unified signal data based on the service instruction.
Further, the performing service analysis processing on the extracted unified signal data to obtain an analysis result includes: carrying out real-time state evaluation processing on the extracted unified signal data to obtain a real-time evaluation result; performing real-time fault diagnosis processing on the extracted unified signal data to obtain a real-time fault diagnosis result; the real-time fault diagnosis processing model comprises a training converged BP neural network model and a fuzzy set theory optimized by a genetic algorithm; and the BP neural network model is optimized by using a genetic algorithm before training.
Further, the performing real-time fault diagnosis processing on the extracted unified signal data to obtain a real-time fault diagnosis result includes: performing feature extraction processing on the extracted unified signal data based on time domain analysis and frequency domain analysis by using a signal statistical analysis method to obtain signal extraction features; confirming that the signal extraction features are direct-current power supply signal extraction features or low-voltage power supply signal extraction features; when the signal extraction features are direct-current power supply signal extraction features, inputting the signal extraction features into a BP neural network model with training convergence to perform real-time fault diagnosis processing, and outputting fault diagnosis information corresponding to the signal extraction features; and when the signal extraction features are low-voltage power supply signal extraction features, inputting the signal extraction features into a fuzzy set theory optimized by using a genetic algorithm to perform real-time fault diagnosis processing, and outputting fault diagnosis information corresponding to the signal extraction features.
Further, after the service analysis processing is performed on the extracted unified signal data, the method further includes: deleting the extracted unified signal data in the partitioned storage in the virtual data server, and marking the extracted unified signal data by using an analysis result corresponding to the extracted unified signal data to obtain marked unified signal data; and storing the marked unified signal data into a historical data storage partition.
Specifically, the virtual computing server extracts unified signal data according to a storage queue structure of the unified signal data in the partitioned storage of the virtual data server according to the service instruction; after extracting the uniform signal data, feature extraction needs to be performed on the uniform signal data, and in general, feature extraction processing is performed on the extracted uniform signal data according to time domain analysis and frequency domain analysis by using a signal statistical analysis method, so as to obtain signal extraction features.
When the extracted unified signal data is subjected to service analysis processing, the method mainly comprises real-time state evaluation processing and real-time fault diagnosis processing; the model for real-time fault diagnosis processing comprises a BP neural network model for training convergence and a fuzzy set theory for genetic algorithm optimization; and the BP neural network model is optimized by using a genetic algorithm before training.
When real-time fault diagnosis processing is carried out, firstly, the signal extraction characteristic is required to be confirmed to be a direct-current power supply signal extraction characteristic or a low-voltage power supply signal extraction characteristic; when the signal extraction features are confirmed to be the direct-current power supply signal extraction features, inputting the signal extraction features into a BP neural network model with training convergence for fault diagnosis processing, and outputting fault diagnosis information corresponding to the signal extraction features after diagnosis is completed; and when the signal extraction features are low-voltage power supply signal extraction features, inputting the signal extraction features into a fuzzy set theory optimized by using a genetic algorithm to perform fault diagnosis processing, and outputting fault diagnosis information corresponding to the signal extraction features.
After the extracted unified signal data are subjected to service analysis processing, the extracted unified signal data need to be deleted in partition storage in a virtual data server, and then the analysis result corresponding to the extracted unified signal data is utilized to carry out marking processing, so that marked unified signal data are obtained; and finally, storing the marked uniform signal data into a historical data storage partition to form historical data, so that the subsequent checking or model training and learning can be facilitated.
S14: and pushing the analysis result to a terminal, and generating a user playing interface matched with browser software at the terminal based on the extensible markup language to play and display the analysis result.
In The specific implementation process of The invention, The analysis result is pushed to The terminal, and The terminal adopts terminal adaptation software to generate a user interface matched with browser software according to XHTML/XML (The Extensible Hypertext Markup Language). The real-time query display, the fault early warning display, the state evaluation display and other index display of the power terminal monitoring data are realized.
In the embodiment of the invention, the power supply can be monitored in a panoramic way by related management users visually, and the health state of the power supply can be known in time; the method can realize the integration of data of each node of the power supply in different regions, and realize the real-time monitoring of the state of the power supply and the early warning of possible faults by using a relevant big data processing technology, thereby achieving the purpose of panoramic monitoring of the state of the power supply.
Example two
Referring to fig. 2, fig. 2 is a schematic structural composition diagram of a power status panoramic monitoring apparatus based on cloud deployment according to an embodiment of the present invention.
As shown in fig. 2, a power state panoramic monitoring method based on cloud deployment includes:
the unified processing module 21: the data acquisition sensor is used for acquiring multi-source heterogeneous signal data of the power terminal and uniformly processing the multi-source heterogeneous signal data to obtain uniform signal data;
in a specific implementation process of the invention, the acquiring of the multi-source heterogeneous signal data of the power terminal based on the data acquisition sensor comprises the following steps: and respectively arranging data acquisition sensors on each node of the power terminal, and acquiring signal data on each node of the power terminal based on the data acquisition sensors to form multi-source heterogeneous signal data.
Further, the unified processing of the multi-source heterogeneous signal data to obtain unified signal data includes: sampling, holding and quantizing the multi-source heterogeneous signal data in sequence to obtain a processing result; carrying out unique identification coding processing on the processing result according to the acquisition time stamp and the node sensor number contained in the corresponding multi-source heterogeneous signal data to obtain a processing result after unique coding; denoising the processing result after the unique coding based on digital filtering to obtain a denoising processing result; and carrying out data cleaning and unified processing on the denoising processing result to obtain unified signal data.
Further, the data cleaning and unified processing are performed on the denoising processing result to obtain unified signal data, including: carrying out invalid and repeated data deletion on the denoising processing result based on a decision tree of a rough set theory to obtain a denoising processing result after deletion; carrying out abnormal data correction processing on the de-noising processing result after deletion processing, and carrying out filling missing data processing on the corrected data based on a difference method to obtain filled data; and carrying out format unified processing on the supplemented data to obtain unified signal data.
Specifically, each node exists in the power supply terminal, a corresponding data acquisition sensor is arranged on each node of the power supply terminal, and then signal data on each node of the power supply terminal are acquired according to the data acquisition sensors and are converged to form multi-source heterogeneous signal data.
For multi-source heterogeneous data, relevant processing is required, subsequent processing requirements are facilitated, namely the multi-source heterogeneous signal data are required to be converted and denoised, analog signals are mainly converted into digital signals, subsequent reading and denoising processing is facilitated, impurity influence can be effectively reduced, and monitoring precision is improved.
After multi-source heterogeneous signal data are converted through an analog-to-digital converter, sampling, holding and quantizing are sequentially carried out, so that a processing result is obtained, then the processing result is subjected to unique identification coding processing according to an acquisition timestamp and a node sensor number contained in the corresponding multi-source heterogeneous signal data, the processing result after unique coding is obtained, and the specific unique coded data can be conveniently inquired or called through the coding in the follow-up process; then, denoising the processing result after the unique coding according to digital filtering to obtain a denoising processing result, namely, filtering and denoising the data signal by adopting a digital filtering algorithm, wherein the digital filtering comprises classical filtering and modern filtering; the classical filtering is an engineering concept proposed according to Fourier analysis and transformation, and according to high mathematics theory, any signal meeting a certain condition can be regarded as being formed by superposing infinite sine waves, namely the engineering signal is formed by linearly superposing sine waves with different frequencies, and the sine waves with different frequencies forming the signal are called frequency components or harmonic components of the signal; modern filtering is to use the nature of randomness of signals, regard signals and their noise as random signals, estimate the signals themselves by using their statistical characteristics, once the signals are estimated, the signals themselves obtained are much higher than the original signal-to-noise ratio, typical digital filters are Kalman filtering, Wenner filtering, adaptive filtering, wavelet transform (wavelet) and so on; the digital filtering has the advantages of high precision, high reliability, programmable change of characteristics or multiplexing, convenience in integration and the like; the digital filtering is of low-pass, high-pass, band-stop, all-pass and other types; may be time-invariant or time-variant, causal or non-causal, linear or non-linear; the most widely used is the linear, time-invariant digital filter; and finally, data cleaning and unified processing are needed to be carried out on the denoising processing result, so that unified signal data are obtained.
In the data cleaning and unified processing, the decision tree of the rough set theory is adopted to carry out invalid and repeated data deletion processing on the denoising processing result to obtain the denoising processing result after the deletion processing, the decision tree of the rough set theory can realize induction on the data, so that redundant impurity data in the data are removed, and the formed data are relatively simplified; then, abnormal data correction processing is carried out on the de-noising processing result after deletion processing, missing data compensation processing is carried out on the corrected data based on a difference method, preprocessed multi-source heterogeneous signal data are obtained, when abnormal data are corrected, abnormal values are judged by adopting a three-sigma criterion to realize abnormal data correction, and the abnormal values are values of which the deviation from the average value exceeds 3 times of standard deviation in a group of measured values; the three sigma criterion is also called Lauda criterion, which is that firstly, a group of detection data is supposed to only contain random errors, the detection data is calculated to obtain standard deviation, an interval is determined according to a certain probability, the error exceeding the interval is considered not to belong to the random errors but to be coarse errors, and the data containing the errors are removed; in the completion missing processing process, an interpolation algorithm is adopted to realize completion missing data, and concretely, Lagrange interpolation, Newton interpolation, Hermite interpolation, segmented interpolation, spline interpolation and the like can be used for realizing completion missing data; after the complemented data is obtained, format unification processing is required, that is, format unification is performed on the complemented data with multi-source isomerism, so that unified signal data is obtained.
The storage module 22: the unified signal data are uploaded to a virtual data server based on a virtual interface server to be subjected to partition storage processing;
in a specific implementation process of the present invention, the uploading the unified signal data to a virtual data server for partition storage processing by a virtual interface-based server includes: uploading the unified signal data to a virtual data server based on a virtual interface server, and converting the unified signal data into binary information after the virtual data server receives the unified signal data; and carrying out partition storage processing on the binary information in a partition memory according to a storage queue structure formed by the acquisition time.
Specifically, unified signal data are uploaded to a virtual data server according to a virtual interface server, and then are converted into binary information after the virtual data server receives the unified signal data, so that the binary information can be used for conveniently performing related storage processing in a memory; because the unified signal data contains the acquisition time, a storage queue structure is formed according to the acquisition time, and then the binary information is subjected to partition storage processing in a partition memory according to the storage queue structure formed by the acquisition time; when the queue structure is stored, a first-in first-out principle can be realized, and when the stored data is subsequently extracted, the stored data can be extracted according to the storage sequence, so that the condition that any stored data is not missed is ensured; meanwhile, in the storage process, the stored unified signal data are correspondingly bound by using a unique score, so that binary information corresponding to the unified signal data is converted into a message chain form, and subsequent storage and query are facilitated.
The analysis module 23: the virtual computing server extracts unified signal data from the partitioned storage of the virtual data server based on the service instruction, and performs service analysis processing on the extracted unified signal data to obtain an analysis result, wherein the service analysis processing comprises real-time state evaluation processing and real-time fault diagnosis processing;
in a specific implementation process of the present invention, the extracting, by the virtual computing server, unified signal data in the partitioned storage of the virtual data server based on a service instruction includes: and the virtual computing server extracts unified signal data in the partitioned storage of the virtual data server according to the storage queue structure of the unified signal data based on the service instruction.
Further, the performing service analysis processing on the extracted unified signal data to obtain an analysis result includes: carrying out real-time state evaluation processing on the extracted unified signal data to obtain a real-time evaluation result; performing real-time fault diagnosis processing on the extracted unified signal data to obtain a real-time fault diagnosis result; the real-time fault diagnosis processing model comprises a training converged BP neural network model and a fuzzy set theory optimized by a genetic algorithm; and the BP neural network model is optimized by using a genetic algorithm before training.
Further, the performing real-time fault diagnosis processing on the extracted unified signal data to obtain a real-time fault diagnosis result includes: performing feature extraction processing on the extracted unified signal data based on time domain analysis and frequency domain analysis by using a signal statistical analysis method to obtain signal extraction features; confirming that the signal extraction features are direct-current power supply signal extraction features or low-voltage power supply signal extraction features; when the signal extraction features are direct-current power supply signal extraction features, inputting the signal extraction features into a BP neural network model with training convergence to perform real-time fault diagnosis processing, and outputting fault diagnosis information corresponding to the signal extraction features; and when the signal extraction features are low-voltage power supply signal extraction features, inputting the signal extraction features into a fuzzy set theory optimized by using a genetic algorithm to perform real-time fault diagnosis processing, and outputting fault diagnosis information corresponding to the signal extraction features.
Further, after the service analysis processing is performed on the extracted unified signal data, the method further includes: deleting the extracted unified signal data in the partitioned storage in the virtual data server, and marking the extracted unified signal data by using an analysis result corresponding to the extracted unified signal data to obtain marked unified signal data; and storing the marked unified signal data into a historical data storage partition.
Specifically, the virtual computing server extracts unified signal data according to a storage queue structure of the unified signal data in the partitioned storage of the virtual data server according to the service instruction; after extracting the uniform signal data, feature extraction needs to be performed on the uniform signal data, and in general, feature extraction processing is performed on the extracted uniform signal data according to time domain analysis and frequency domain analysis by using a signal statistical analysis method, so as to obtain signal extraction features.
When the extracted unified signal data is subjected to service analysis processing, the method mainly comprises real-time state evaluation processing and real-time fault diagnosis processing; the model for real-time fault diagnosis processing comprises a BP neural network model for training convergence and a fuzzy set theory for genetic algorithm optimization; and the BP neural network model is optimized by using a genetic algorithm before training.
When real-time fault diagnosis processing is carried out, firstly, the signal extraction characteristic is required to be confirmed to be a direct-current power supply signal extraction characteristic or a low-voltage power supply signal extraction characteristic; when the signal extraction features are confirmed to be the direct-current power supply signal extraction features, inputting the signal extraction features into a BP neural network model with training convergence for fault diagnosis processing, and outputting fault diagnosis information corresponding to the signal extraction features after diagnosis is completed; and when the signal extraction features are low-voltage power supply signal extraction features, inputting the signal extraction features into a fuzzy set theory optimized by using a genetic algorithm to perform fault diagnosis processing, and outputting fault diagnosis information corresponding to the signal extraction features.
After the extracted unified signal data are subjected to service analysis processing, the extracted unified signal data need to be deleted in partition storage in a virtual data server, and then the analysis result corresponding to the extracted unified signal data is utilized to carry out marking processing, so that marked unified signal data are obtained; and finally, storing the marked uniform signal data into a historical data storage partition to form historical data, so that the subsequent checking or model training and learning can be facilitated.
The playing and displaying module 24: and the system is used for pushing the analysis result to a terminal and generating a user playing interface matched with browser software at the terminal based on the extensible markup language to play and display the analysis result.
In The specific implementation process of The invention, The analysis result is pushed to The terminal, and The terminal adopts terminal adaptation software to generate a user interface matched with browser software according to XHTML/XML (The Extensible Hypertext Markup Language). The real-time query display, the fault early warning display, the state evaluation display and other index display of the power terminal monitoring data are realized.
In the embodiment of the invention, the power supply can be monitored in a panoramic way by related management users visually, and the health state of the power supply can be known in time; the method can realize the integration of data of each node of the power supply in different regions, and realize the real-time monitoring of the state of the power supply and the early warning of possible faults by using a relevant big data processing technology, thereby achieving the purpose of panoramic monitoring of the state of the power supply.
Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by associated hardware instructed by a program, which may be stored in a computer-readable storage medium, and the storage medium may include: a Read Only Memory (ROM), a Random Access Memory (RAM), a magnetic or optical disk, or the like.
In addition, the power supply state panoramic monitoring method and device based on cloud deployment provided by the embodiment of the present invention are described in detail above, and a specific embodiment should be adopted herein to explain the principle and the implementation manner of the present invention, and the description of the above embodiment is only used to help understanding the method and the core idea of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (10)
1. A power state panoramic monitoring method based on cloud deployment is characterized by comprising the following steps:
acquiring multi-source heterogeneous signal data of a power supply terminal based on a data acquisition sensor, and uniformly processing the multi-source heterogeneous signal data to obtain uniform signal data;
uploading the unified signal data to a virtual data server based on a virtual interface server for partitioned storage processing;
the virtual computing server extracts unified signal data from the partitioned storage of the virtual data server based on the service instruction, and performs service analysis processing on the extracted unified signal data to obtain an analysis result, wherein the service analysis processing comprises real-time state evaluation processing and real-time fault diagnosis processing;
and pushing the analysis result to a terminal, and generating a user playing interface matched with browser software at the terminal based on the extensible markup language to play and display the analysis result.
2. The power state panoramic monitoring method of claim 1, wherein the collecting power terminal multi-source heterogeneous signal data based on the data collecting sensor comprises:
and respectively arranging data acquisition sensors on each node of the power terminal, and acquiring signal data on each node of the power terminal based on the data acquisition sensors to form multi-source heterogeneous signal data.
3. The power state panoramic monitoring method of claim 1, wherein the uniformly processing the multi-source heterogeneous signal data to obtain uniform signal data comprises:
sampling, holding and quantizing the multi-source heterogeneous signal data in sequence to obtain a processing result;
carrying out unique identification coding processing on the processing result according to the acquisition time stamp and the node sensor number contained in the corresponding multi-source heterogeneous signal data to obtain a processing result after unique coding;
denoising the processing result after the unique coding based on digital filtering to obtain a denoising processing result;
and carrying out data cleaning and unified processing on the denoising processing result to obtain unified signal data.
4. The power state panoramic monitoring method according to claim 3, wherein the performing data cleaning and unified processing on the denoising processing result to obtain unified signal data includes:
carrying out invalid and repeated data deletion on the denoising processing result based on a decision tree of a rough set theory to obtain a denoising processing result after deletion;
carrying out abnormal data correction processing on the de-noising processing result after deletion processing, and carrying out filling missing data processing on the corrected data based on a difference method to obtain filled data;
and carrying out format unified processing on the supplemented data to obtain unified signal data.
5. The power state panoramic monitoring method according to claim 1, wherein the uploading the unified signal data to a virtual data server for partition storage processing based on a virtual interface server comprises:
uploading the unified signal data to a virtual data server based on a virtual interface server, and converting the unified signal data into binary information after the virtual data server receives the unified signal data;
and carrying out partition storage processing on the binary information in a partition memory according to a storage queue structure formed by the acquisition time.
6. The power state panoramic monitoring method of claim 1, wherein the virtual compute server extracts unified signal data in the partitioned storage of the virtual data server based on traffic instructions, comprising:
and the virtual computing server extracts unified signal data in the partitioned storage of the virtual data server according to the storage queue structure of the unified signal data based on the service instruction.
7. The power state panoramic monitoring method according to claim 1, wherein the performing traffic analysis processing on the extracted unified signal data to obtain an analysis result includes:
carrying out real-time state evaluation processing on the extracted unified signal data to obtain a real-time evaluation result;
performing real-time fault diagnosis processing on the extracted unified signal data to obtain a real-time fault diagnosis result; the real-time fault diagnosis processing model comprises a training converged BP neural network model and a fuzzy set theory optimized by a genetic algorithm; and the BP neural network model is optimized by using a genetic algorithm before training.
8. The power state panoramic monitoring method according to claim 7, wherein the performing real-time fault diagnosis processing on the extracted unified signal data to obtain a real-time fault diagnosis result comprises:
performing feature extraction processing on the extracted unified signal data based on time domain analysis and frequency domain analysis by using a signal statistical analysis method to obtain signal extraction features;
confirming that the signal extraction features are direct-current power supply signal extraction features or low-voltage power supply signal extraction features;
when the signal extraction features are direct-current power supply signal extraction features, inputting the signal extraction features into a BP neural network model with training convergence to perform real-time fault diagnosis processing, and outputting fault diagnosis information corresponding to the signal extraction features;
and when the signal extraction features are low-voltage power supply signal extraction features, inputting the signal extraction features into a fuzzy set theory optimized by using a genetic algorithm to perform real-time fault diagnosis processing, and outputting fault diagnosis information corresponding to the signal extraction features.
9. The power state panoramic monitoring method of claim 1, wherein after the traffic analysis processing of the extracted unified signal data, the method further comprises:
deleting the extracted unified signal data in the partitioned storage in the virtual data server, and marking the extracted unified signal data by using an analysis result corresponding to the extracted unified signal data to obtain marked unified signal data;
and storing the marked unified signal data into a historical data storage partition.
10. A power state panoramic monitoring method based on cloud deployment is characterized by comprising the following steps:
a unified processing module: the data acquisition sensor is used for acquiring multi-source heterogeneous signal data of the power terminal and uniformly processing the multi-source heterogeneous signal data to obtain uniform signal data;
a storage module: the unified signal data are uploaded to a virtual data server based on a virtual interface server to be subjected to partition storage processing;
an analysis module: the virtual computing server extracts unified signal data from the partitioned storage of the virtual data server based on the service instruction, and performs service analysis processing on the extracted unified signal data to obtain an analysis result, wherein the service analysis processing comprises real-time state evaluation processing and real-time fault diagnosis processing;
the playing and displaying module: and the system is used for pushing the analysis result to a terminal and generating a user playing interface matched with browser software at the terminal based on the extensible markup language to play and display the analysis result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111007926.XA CN113702862B (en) | 2021-08-27 | 2021-08-27 | DC power supply state panoramic monitoring method and device based on cloud deployment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111007926.XA CN113702862B (en) | 2021-08-27 | 2021-08-27 | DC power supply state panoramic monitoring method and device based on cloud deployment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113702862A true CN113702862A (en) | 2021-11-26 |
| CN113702862B CN113702862B (en) | 2022-10-14 |
Family
ID=78657101
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111007926.XA Active CN113702862B (en) | 2021-08-27 | 2021-08-27 | DC power supply state panoramic monitoring method and device based on cloud deployment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113702862B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20140075847A (en) * | 2012-11-30 | 2014-06-20 | 한국과학기술정보연구원 | Method and system for protecting a data information and expert support in cloud system environment |
| CN107146018A (en) * | 2017-05-04 | 2017-09-08 | 北京许继电气有限公司 | Data Management Analysis method and system based on electric network state monitoring system |
| CN110084106A (en) * | 2019-03-19 | 2019-08-02 | 中国地质大学（武汉） | Microgrid inverter method for diagnosing faults based on wavelet transformation and probabilistic neural network |
| CN110609864A (en) * | 2019-08-30 | 2019-12-24 | 广州奇化有限公司 | Chemical supply chain-oriented data visualization management method and device |
| CN110861123A (en) * | 2019-11-14 | 2020-03-06 | 华南智能机器人创新研究院 | Method and device for visually monitoring and evaluating running state of robot |
-
2021
- 2021-08-27 CN CN202111007926.XA patent/CN113702862B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20140075847A (en) * | 2012-11-30 | 2014-06-20 | 한국과학기술정보연구원 | Method and system for protecting a data information and expert support in cloud system environment |
| CN107146018A (en) * | 2017-05-04 | 2017-09-08 | 北京许继电气有限公司 | Data Management Analysis method and system based on electric network state monitoring system |
| CN110084106A (en) * | 2019-03-19 | 2019-08-02 | 中国地质大学（武汉） | Microgrid inverter method for diagnosing faults based on wavelet transformation and probabilistic neural network |
| CN110609864A (en) * | 2019-08-30 | 2019-12-24 | 广州奇化有限公司 | Chemical supply chain-oriented data visualization management method and device |
| CN110861123A (en) * | 2019-11-14 | 2020-03-06 | 华南智能机器人创新研究院 | Method and device for visually monitoring and evaluating running state of robot |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113702862B (en) | 2022-10-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110861123A (en) | Method and device for visually monitoring and evaluating running state of robot | |
| CN108805059B (en) | Sparse regularization filtering and self-adaptive sparse decomposition gearbox fault diagnosis method | |
| CN113687257A (en) | Power supply health state dynamic evaluation method and device | |
| CN111426905B (en) | Power distribution network common bus transformation relation abnormity diagnosis method, device and system | |
| CN104572976B (en) | Website data update method and system | |
| CN103346797A (en) | Real-time compression method for gear fault signals | |
| CN109962742A (en) | Portable remote monitoring data monitoring platform and monitoring method | |
| JP2001168948A (en) | Remote maintenance system | |
| CN113702861B (en) | Power failure position prediction method and device based on big data analysis | |
| CN113702862B (en) | DC power supply state panoramic monitoring method and device based on cloud deployment | |
| CN113157663B (en) | Network flow prediction method and device based on data reconstruction and hybrid prediction | |
| CN114004996A (en) | Abnormal sound detection method, abnormal sound detection device, electronic equipment and medium | |
| CN113961612A (en) | Satellite health data comprehensive analysis system and method based on deep learning | |
| CN115757363A (en) | Multi-level management method and system for three-dimensional cadastral database | |
| CN115754692A (en) | System, method, equipment and medium for identifying state of disconnecting link of electrical equipment | |
| CN115905827A (en) | Steam turbine fault diagnosis method and device based on neural network | |
| JP2005266965A (en) | Data monitoring device and method | |
| CN111803060B (en) | Electrocardio artifact signal removing method and device | |
| CN113837042A (en) | Wavelet threshold automatic deformation monitoring signal denoising method based on local mean decomposition | |
| CN114184270A (en) | Equipment vibration data processing method, device, equipment and storage medium | |
| CN112486096A (en) | Machine tool operation state monitoring method | |
| CN117828285B (en) | Production data management system and method | |
| CN118035227A (en) | Data intelligent processing method and system based on big data evaluation | |
| CN115031966A (en) | Rolling bearing fault diagnosis method and device, electronic equipment and storage medium | |
| WO2024104406A1 (en) | Anomaly detection method and cloud network platform |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |