CN120744527B - Special equipment state identification method and system based on electrical parameter pattern matching - Google Patents
Special equipment state identification method and system based on electrical parameter pattern matchingInfo
- Publication number
- CN120744527B CN120744527B CN202511165575.3A CN202511165575A CN120744527B CN 120744527 B CN120744527 B CN 120744527B CN 202511165575 A CN202511165575 A CN 202511165575A CN 120744527 B CN120744527 B CN 120744527B
- Authority
- CN
- China
- Prior art keywords
- state
- hierarchical
- real
- fault
- stage
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B1/00—Control systems of elevators in general
- B66B1/34—Details, e.g. call counting devices, data transmission from car to control system, devices giving information to the control system
- B66B1/3415—Control system configuration and the data transmission or communication within the control system
- B66B1/3423—Control system configuration, i.e. lay-out
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B5/00—Applications of checking, fault-correcting, or safety devices in elevators
- B66B5/0006—Monitoring devices or performance analysers
- B66B5/0018—Devices monitoring the operating condition of the elevator system
- B66B5/0031—Devices monitoring the operating condition of the elevator system for safety reasons
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/254—Fusion techniques of classification results, e.g. of results related to same input data
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2123/00—Data types
- G06F2123/02—Data types in the time domain, e.g. time-series data
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Automation & Control Theory (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
本发明公开了基于电气参数模式匹配的特种设备状态识别方法及系统，涉及数据处理技术领域。所述方法包括：对配电柜多监测指标进行特种设备状态敏感性验证，得到动态分级敏感指标集；生成电梯状态模式库；调取多级实时运行参数；触发层级式设备状态映射，输出层级化状态置信度向量；进行状态转移预测，输出状态转移概率矩阵；融合层级化状态置信度向量和状态转移概率矩阵，输出实时故障概率分布；根据实时故障概率分布生成多级预警信号，触发梯级安全防护响应。解决了现有技术中特种设备状态识别依赖传感器的技术问题，实现了基于电气参数对电梯运行状态的精准识别，从而降低对外部传感器的依赖，提升了状态监测的实时性与可靠性的技术效果。
This invention discloses a method and system for special equipment status identification based on electrical parameter pattern matching, belonging to the field of data processing technology. The method includes: verifying the sensitivity of multiple monitoring indicators of the distribution cabinet to special equipment status, obtaining a dynamically graded sensitive indicator set; generating an elevator status pattern library; retrieving multi-level real-time operating parameters; triggering hierarchical equipment status mapping, outputting a hierarchical status confidence vector; performing state transition prediction, outputting a state transition probability matrix; fusing the hierarchical status confidence vector and the state transition probability matrix, outputting a real-time fault probability distribution; generating multi-level early warning signals based on the real-time fault probability distribution, triggering a ladder-level safety protection response. This solves the technical problem of relying on sensors for special equipment status identification in existing technologies, achieving accurate identification of elevator operating status based on electrical parameters, thereby reducing dependence on external sensors and improving the real-time performance and reliability of status monitoring.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a special equipment state identification method and system based on electric parameter pattern matching.
Background
In the running process of special equipment, safety state monitoring and fault identification are important links for guaranteeing stable running of the equipment and personnel safety. In the prior art, the operation state identification of the elevator mainly depends on a plurality of types of sensors arranged at key parts of equipment, and the operation state identification is analyzed by collecting physical quantities such as vibration, temperature, displacement and the like. However, the method has the defects that on one hand, the sensor is high in installation and maintenance cost and is easily influenced by factors such as installation positions, environmental interference, performance attenuation of the sensor and the like, so that stability and accuracy of monitoring data are difficult to guarantee, on the other hand, the change rule of electrical parameters in different running states is not fully utilized, the conventional scheme lacks pattern recognition capability based on the electrical parameters, and accurate state recognition and trend prediction are difficult to continuously realize under the condition that the sensor is limited or fails.
Disclosure of Invention
The application provides a special equipment state identification method and a special equipment state identification system based on electrical parameter pattern matching, which solve the technical problem that the special equipment state identification in the prior art depends on a sensor.
In a first aspect of the present application, there is provided a method for identifying a state of a special device based on pattern matching of electrical parameters, the method comprising:
Carrying out special equipment state sensitivity verification on multiple monitoring indexes of a power distribution cabinet to obtain a dynamic grading sensitive index set, carrying out offline pre-construction on a multi-stage state mode sub-library according to the dynamic grading sensitive index set, generating an elevator state mode library through hierarchical association integration, calling multi-stage real-time operation parameters step by step according to the sensitivity priority from the power distribution cabinet according to the dynamic grading sensitive index set, dynamically loading the multi-stage real-time operation parameters to the elevator state mode library, triggering hierarchical equipment state mapping, outputting a hierarchical state confidence vector, carrying out state transition prediction on the hierarchical state confidence vector, outputting a state transition probability matrix, fusing the hierarchical state confidence vector and the state transition probability matrix, outputting a real-time fault probability distribution, generating multi-stage early warning signals according to the real-time fault probability distribution, and triggering a step safety protection response.
In a second aspect of the present application, there is provided a special equipment status recognition system based on electrical parameter pattern matching, the system comprising:
The system comprises a sensitivity verification module, a mode library construction module, a parameter retrieval module, a state mapping module, a fault probability output module and a warning response module, wherein the sensitivity verification module is used for carrying out special equipment state sensitivity verification on multiple monitoring indexes of a power distribution cabinet to obtain a dynamic grading sensitivity index set, the mode library construction module is used for carrying out offline pre-construction on a multi-level state mode sub-library according to the dynamic grading sensitivity index set and generating an elevator state mode library through hierarchical association integration, the parameter retrieval module is used for retrieving multi-level real-time operation parameters from the power distribution cabinet step by step according to sensitivity priority according to the dynamic grading sensitivity index set, the state mapping module is used for dynamically loading the multi-level real-time operation parameters to the elevator state mode library, triggering hierarchical equipment state mapping and outputting a hierarchical state confidence vector, the state transition prediction module is used for carrying out state transition prediction on the hierarchical state confidence vector and outputting a state transition probability matrix, and the fault probability output module is used for fusing the hierarchical state confidence vector and the state transition probability matrix and outputting real-time fault probability distribution, and the warning response module is used for generating a multi-level warning signal according to the real-time fault probability distribution and triggering step safety protection response.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
Firstly, carrying out special equipment state sensitivity verification on multiple monitoring indexes of a power distribution cabinet to obtain a dynamic grading sensitivity index set. And simultaneously, according to the dynamic grading sensitive index set, gradually retrieving multistage real-time operation parameters from the power distribution cabinet according to the sensitivity priority. Further, the multistage real-time operation parameters are dynamically loaded to an elevator state mode library, the hierarchical equipment state mapping is triggered, and the hierarchical state confidence vector is output. Next, state transition prediction is performed on the hierarchical state confidence vector, and a state transition probability matrix is output. And then, integrating the hierarchical state confidence vector and the state transition probability matrix, and outputting the real-time fault probability distribution. And finally, generating a multi-stage early warning signal according to the real-time fault probability distribution, and triggering a step safety protection response. The method solves the technical problem that the state identification of special equipment depends on the sensor in the prior art, and realizes the accurate identification of the elevator running state based on the electrical parameters, thereby reducing the dependence on the external sensor and improving the technical effects of real-time performance and reliability of state monitoring.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following description will briefly explain the drawings needed in the description of the embodiments, which are merely examples of the present invention, and other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a special equipment state identification method based on electrical parameter pattern matching according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a special equipment state recognition system based on electrical parameter pattern matching according to an embodiment of the present application.
Reference numerals illustrate a sensitivity verification module 11, a pattern library construction module 12, a parameter retrieval module 13, a state mapping module 14, a state transition prediction module 15, a fault probability output module 16 and an early warning response module 17.
Detailed Description
The application solves the technical problem that the state identification of the special equipment depends on a sensor in the prior art by providing the state identification method and the state identification system of the special equipment based on the electric parameter mode matching.
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. It will be apparent that the described embodiments are only some, but not all, embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
It should be noted that the terms "comprises" and "comprising" are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.
In a first embodiment, as shown in fig. 1, the present application provides a special equipment state identification method based on electrical parameter pattern matching, where the method includes:
and carrying out special equipment state sensitivity verification on multiple monitoring indexes of the power distribution cabinet to obtain a dynamic grading sensitivity index set.
And constructing equipment fingerprints based on the application environment characteristics and equipment model codes of the power distribution cabinet, and calling full-dimension operation log data of a plurality of equipment with the same type as the retrieval condition. And then, the collected operation logs are aggregated according to the index types to form a multi-state time sequence data set corresponding to a plurality of monitoring indexes. And dividing the data by using equipment state labels according to multi-state time sequence data of each monitoring index to construct a reference state record set and a plurality of groups of fault state record sets. And quantifying the sensitivity scores of the monitoring indexes on different fault states by calculating the KL divergence of the reference state and each fault state record set. And combining the recurrence frequency of the fault states, and carrying out weighted summarization on the sensitivity scores of the fault states to obtain the comprehensive operation sensitivity of each monitoring index. And finally, dynamically grading the monitoring index according to the comprehensive operation sensitivity to form a dynamic grading sensitive index set.
Furthermore, the state sensitivity verification of special equipment is carried out on the multi-monitoring indexes of the power distribution cabinet to obtain a dynamic grading sensitivity index set, and the method comprises the following steps:
The method comprises the steps of acquiring application environment characteristics of a power distribution cabinet, taking the application environment characteristics and a power distribution cabinet model code as equipment fingerprint code retrieval conditions, calling a plurality of equipment full-dimension operation logs, aggregating the equipment full-dimension operation logs based on index types to obtain a plurality of multi-state time sequence data sets of a plurality of operation indexes, quantifying state sensitivity of special equipment based on the plurality of multi-state time sequence data sets, outputting a plurality of operation comprehensive sensitivities, dynamically grading the plurality of operation indexes according to the plurality of operation comprehensive sensitivities, and outputting the dynamic grading sensitivity index set.
The method comprises the steps of firstly, calling application environment characteristics of a target power distribution cabinet, wherein the application environment characteristics comprise but are not limited to installation positions, power supply topological structures, load types, environment temperature and humidity ranges and the like, obtaining power distribution cabinet model codes, combining the application environment characteristics with the model codes to generate unique equipment fingerprint codes, calling full-dimension operation logs of a plurality of similar power distribution cabinets matched with the equipment fingerprints from a historical operation database as search conditions, and the operation logs comprise time sequence records of all monitoring indexes in various operation states. And then, carrying out aggregation processing on the full-dimension operation logs of the plurality of devices according to the index types, classifying the same type of monitoring data into corresponding operation indexes, and forming a multi-state time sequence data set corresponding to the operation indexes, wherein the multi-state comprises a reference state and a plurality of fault states, and each state corresponds to the monitoring record of one or more time periods. The method comprises the steps of carrying out state sensitivity quantitative analysis on each operation index based on a plurality of multi-state time sequence data sets, specifically, respectively calculating distribution difference metric values between each index and a reference state under each fault state by taking index distribution characteristics of the reference state as a reference, wherein the metrics can adopt Kullback-Leibler divergence (KL divergence), jensen-Shannon divergence (JSD) or other statistical distance algorithms, and carrying out weighted summation on the difference metric values of each fault state according to the historical repeated frequency of the fault state to obtain the operation comprehensive sensitivity of the operation index. And finally, performing descending order sorting according to the operation comprehensive sensitivity of all the operation indexes, dynamically grading the operation comprehensive sensitivity according to a preset grading threshold or a grading interval, dividing the index with higher sensitivity into high sensitivity levels, dividing the index with medium sensitivity into medium sensitivity levels and dividing the index with lower sensitivity into low sensitivity levels, and outputting a dynamic grading sensitivity index set containing index identifications, sensitivity scores, sensitivity levels and main associated fault types for subsequent state mode construction and real-time state identification and calling.
Further, the method comprises quantifying state sensitivity of the special equipment based on the multiple multi-state time sequence data sets, and outputting multiple operation comprehensive sensitivities, wherein the method comprises the following steps:
Decomposing the multiple multi-state time sequence data sets based on equipment state labels to obtain multiple reference state record sets and multiple groups of fault state record sets, quantifying the multiple groups of fault state record sets by using KL divergence based on the multiple reference state record sets to output multiple groups of fault state KL sensitivity scores, weighting the multiple groups of fault state KL sensitivity scores in groups according to the recurrence frequency of M fault states, and outputting the multiple operation comprehensive sensitivities.
Firstly, using equipment state labels corresponding to multi-state time sequence data sets to perform state decomposition on the multi-state time sequence data sets, dividing data in a normal running state into reference state record sets, dividing data in different types of fault states into a plurality of groups of fault state record sets respectively, wherein each group of fault state record sets corresponds to one fault type. And then taking a plurality of reference state record sets as reference references to respectively carry out distribution difference measurement on each fault state record set and the corresponding reference state record set of each operation index, specifically, respectively carrying out probability density estimation on the reference state record set and the fault state record set to obtain reference distribution and fault distribution, and calculating the distribution difference of the reference state record set and the fault state record set by adopting a Kullback-Leibler divergence (KL divergence) to obtain the KL sensitivity score of the operation index in the fault state. And then constructing corresponding weight coefficients according to the recurrence frequency of M fault states in the historical operation data, wherein the weight coefficients are in direct proportion to the recurrence frequency of the faults and normalized, and carrying out weighted summation on the KL sensitivity scores of each operation index under each fault state according to the corresponding weight coefficients to obtain the operation comprehensive sensitivity of the operation index. And finally, outputting the operation comprehensive sensitivity of all the operation indexes as an input basis for generating a subsequent dynamic grading sensitive index set.
And pre-constructing a multi-stage state mode sub-library offline according to the dynamic hierarchical sensitive index set, and generating an elevator state mode library through hierarchical association integration.
And decomposing the sensitive indexes according to a hierarchical relation based on the dynamic hierarchical sensitive index set to obtain a multi-level sensitive index set. And taking the first-level sensitive index as a screening condition, calling corresponding multiple groups of sample fault state time sequence data from the full-dimension operation log of the equipment, and combining different fault grade labels to form multiple groups of multiple-state sample data sets. And carrying out index fluctuation scale analysis on the sample data, extracting a representative state characteristic template, and constructing a first-stage state mode sub-library. And then, iteratively constructing a second-level state mode sub-library and a higher-level state mode sub-library according to the hierarchical sequence of the sensitive indexes, and establishing a bidirectional mapping index between the multi-level sensitive indexes and the multi-level state mode sub-library. Finally, a complete elevator state mode library is generated through hierarchical association and integration, and a structured mode basis is provided for subsequent real-time state matching and recognition.
Further, the method includes the steps of pre-constructing a multi-level state mode sub-library offline according to the dynamic hierarchical sensitive index set, and generating an elevator state mode library through hierarchical association integration, wherein the method comprises the following steps:
the method comprises the steps of obtaining a dynamic hierarchical sensitive index set, obtaining a multi-stage sensitive index by decomposing the dynamic hierarchical sensitive index set based on a hierarchical relation, taking a specific index set of a first-stage sensitive index as a screening condition, calling a plurality of groups of sample fault state time sequence data sets of a plurality of sample fault states under a plurality of groups of sample fault levels from a plurality of equipment full-dimensional operation logs, carrying out index fluctuation scale analysis on the plurality of groups of sample fault state time sequence data sets to output a plurality of groups of state feature templates, storing the plurality of sample fault states, the plurality of groups of sample fault levels and the plurality of groups of sample state feature templates in a hierarchical relation mode sub-library, constructing a multi-stage state mode sub-library in a hierarchical sequence iteration mode, constructing a bidirectional mapping relation index table of the multi-stage sensitive index and the multi-stage state mode sub-library, and generating the elevator state mode sub-library.
And carrying out hierarchical relation decomposition on the dynamic hierarchical sensitive index sets based on the sensitivity level, dividing each operation index into a first-level sensitive index, a second-level sensitive index, a third-level sensitive index and an N-level sensitive index from high sensitivity to low sensitivity, wherein each level of sensitive index set is used for constructing a corresponding state mode sub-library. And in the retrieval process, classifying according to a plurality of preset sample fault states (such as door machine faults, brake faults, traction system faults and the like) and a plurality of groups of sample fault levels (such as slight, medium and serious) to obtain a plurality of groups of sample fault state time sequence data sets. And then, carrying out index fluctuation scale analysis on the time sequence data sets of the fault states of the multiple groups of samples, including but not limited to calculating mean fluctuation amplitude, standard deviation change rate, peak-to-valley ratio, transient fluctuation energy, frequency spectrum characteristic quantity and the like, so as to capture statistics and time sequence characteristics of the sensitive index under different states, and packaging analysis results into multiple groups of state characteristic templates, wherein each template corresponds to one fault state and the level thereof. And then, carrying out hierarchical association storage on the plurality of sample fault states, the plurality of groups of sample fault levels and the corresponding state feature templates to construct a first-stage state mode sub-library, wherein the first-stage state mode sub-library stores state labels, feature templates and association relations with sensitive index items. On the basis, the steps of data retrieval, feature template generation and hierarchical association storage are repeated for the second-level to N-level sensitive indexes according to the hierarchical sequence, a multi-level state mode sub-library is constructed in an iterative mode, and in the construction process, a bidirectional mapping relation index table of the multi-level sensitive indexes and the corresponding multi-level state mode sub-library is built, so that the corresponding mode sub-library can be quickly positioned through the sensitive indexes in the operation process, and otherwise, the associated sensitive index set can be reversely searched according to the state mode sub-library. And finally, uniformly storing all the multi-stage state mode sub-libraries and the bidirectional mapping relation index table to form an elevator state mode library.
And according to the dynamic grading sensitive index set, gradually calling multi-stage real-time operation parameters from the power distribution cabinet according to the sensitivity priority.
And acquiring sensitivity levels of all monitoring indexes in the dynamic grading sensitivity index set, and sorting according to the sensitivity from high to low to form a sensitivity priority list. And sequentially calling real-time operation parameters of corresponding indexes from a real-time data acquisition system of the power distribution cabinet according to the sensitivity priority list, preferentially acquiring real-time data of the high-sensitivity indexes to serve as primary operation parameters, then calling real-time data of the medium-sensitivity indexes to serve as secondary operation parameters, and similarly calling the real-time operation parameters corresponding to each sensitivity level step by step to form multi-level real-time operation parameters.
Dynamically loading the multistage real-time operation parameters to the elevator state mode library, triggering hierarchical equipment state mapping, and outputting a hierarchical state confidence vector.
Further, dynamically loading the multi-level real-time operation parameters into the elevator status mode library, triggering hierarchical device status mapping, and outputting a hierarchical status confidence vector, the method comprises:
The method comprises the steps of acquiring a first-stage operation parameter sequence of a first-stage sensitive index from a power distribution cabinet in real time, extracting features of the first-stage operation parameter sequence to obtain a first-stage feature vector, loading the first-stage feature vector into a first-stage state mode sub-library of an elevator state mode library, matching and outputting an initial state mapping set, and if the initial state mapping set is an empty set, performing monitoring circulation of the first-stage sensitive index until the initial state mapping set is a non-empty set, and triggering hierarchical equipment state mapping.
The method comprises the steps of acquiring a first-stage operation parameter sequence corresponding to a first-stage sensitive index from a real-time data acquisition system of a power distribution cabinet, extracting characteristics of the first-stage operation parameter sequence, extracting multidimensional characteristic vectors comprising time domain and frequency domain characteristics, wherein the specific characteristics comprise mean value, variance, kurtosis, spectral energy distribution and the like, so as to form the first-stage characteristic vector, loading the first-stage characteristic vector into a first-stage state mode sub-library in an elevator state mode sub-library, matching and outputting an initial state mapping set by calculating the similarity of the first-stage characteristic vector and each state characteristic template in the first-stage state mode sub-library, and if the initial state mapping set is an empty set, indicating that the current characteristic vector cannot be matched with any known state template, continuously carrying out real-time monitoring circulation on the first-stage sensitive index by the system, repeatedly extracting the operation parameter sequence, carrying out characteristic extraction and matching until the matching is successful, obtaining a non-empty initial state mapping set, and triggering subsequent hierarchical equipment state mapping processing.
Further, the first-level feature vector is loaded to a first-level state mode sub-library of the elevator state mode library, and an initial state mapping set is output in a matching mode, and the method comprises the following steps:
The method comprises the steps of traversing the first-level feature vector and a plurality of groups of sample state feature templates Euclidean distance matrixes in a first-level state mode sub-library to output a plurality of groups of state similarity, retrieving a plurality of real-time fault levels from the plurality of groups of sample fault levels according to the largest value arranged in a descending order in the plurality of groups of state similarity, taking the plurality of largest similarity as a plurality of real-time fault probabilities of the plurality of real-time fault levels, traversing the plurality of real-time fault probabilities based on a preset similarity threshold, screening P real-time fault levels and P real-time fault probabilities of P sample fault states from the plurality of real-time fault levels, storing the P sample fault states, the P real-time fault levels and the P real-time fault probabilities in a correlated mode, and outputting the initial state mapping set, wherein the initial state mapping set is an empty set if the plurality of real-time fault probabilities are smaller than the preset similarity threshold.
The method comprises the steps of firstly traversing and calculating Euclidean distance matrixes between a first-level feature vector and a plurality of groups of sample state feature templates in a first-level state mode sub-library to measure similarity between input features and each sample template, then converting Euclidean distance into similarity indexes (for example, mapping through reciprocal or exponential functions), arranging similarity values of each template in a descending order in a group, screening sample states corresponding to a plurality of maximum similarity values, calling a plurality of real-time fault levels according to historical fault level information corresponding to the sample states, taking the corresponding maximum similarity values as real-time fault probabilities of the fault levels to form a corresponding relation between a plurality of pairs of real-time fault levels and the real-time fault probabilities, then traversing the real-time fault probabilities based on preset similarity threshold values, screening out first P sample fault states with similarity higher than the threshold value and corresponding P real-time fault levels and real-time fault probabilities, finally, storing the screened P sample fault states, the corresponding P real-time fault levels and the real-time fault probabilities in an associated mode as an initial state mapping set, and outputting all the obtained P sample fault states, and the corresponding P sample fault levels and the real-time fault probabilities as an initial state mapping set, and judging that if all the preset fault probabilities are lower than the initial fault probabilities are lower than the threshold value and the current fault level is not known, and the current state is not matched with the current state is judged.
Further, dynamically loading the multi-level real-time operating parameters into the elevator status pattern library, triggering a hierarchical device status mapping, and outputting a hierarchical status confidence vector, the method further comprising:
If the initial state mapping set is a non-empty set, a second-level sensitive index is called from the dynamic grading sensitive index set; the power distribution cabinet backtracks a second-level operation parameter sequence according to the index composition of the second-level sensitive index, obtains a second-level feature vector through feature extraction, fuses and loads the first-level feature vector and the second-level feature vector to a second-level state mode sub-library of the elevator state mode library, matches and outputs a first verification state mapping set, adopts the first verification state mapping set to conduct state reliability verification of the initial state mapping set, outputs first state confidence, weights and fuses the initial state mapping set and the first verification state mapping set to generate the hierarchical state confidence vector if the first state confidence is higher than a preset confidence threshold, and iteratively calls the next-level sensitive index to verify if the first state confidence is lower than the preset confidence threshold until the confidence reaches the standard, and outputs the hierarchical state confidence vector by integrating a multi-level mapping result.
If the initial state mapping set is a non-empty set, a second-stage sensitive index set is called from the dynamic hierarchical sensitive index set, a corresponding second-stage operation parameter sequence is called back from the historical data of the power distribution cabinet according to index composition of the second-stage sensitive index, feature extraction is carried out on the second-stage operation parameter sequence to obtain a second-stage feature vector, the first-stage feature vector and the second-stage feature vector are fused and then loaded into a second-stage state mode sub-library of an elevator state mode library, the fused feature is matched by using a state feature template of the sub-library, a first verification state mapping set is output, state reliability verification is carried out on the initial state mapping set by using the first verification state mapping set, a first state confidence is calculated and output, when the first state confidence is higher than a preset confidence threshold, the initial state mapping set and the first verification state mapping set are fused on the basis of a weighted fusion algorithm, a final level confidence vector is generated, if the first state confidence is lower than the preset confidence threshold, the next lower-stage sensitive index is called repeatedly until the verification process reaches the preset level confidence level mapping standard, and the integrated level comprehensive state mapping result is output.
Further, the state reliability verification of the initial state mapping set is performed by adopting the first verification state mapping set, and a first state confidence is output, and the method comprises the following steps:
performing state conflict detection on the first verification state mapping set and the initial state mapping set, and screening and outputting the first conflict state mapping set and the initial conflict mapping set; and calculating the first JSD distribution similarity of the first conflict state mapping set and the initial conflict mapping set as the first state confidence.
And comparing the first verification state mapping set with the fault state types and the fault grades in the initial state mapping set one by one, and identifying state conflicts existing in the two mapping sets, namely screening out the first conflict state mapping set and the initial conflict mapping set, wherein the conflicts refer to state pairs with inconsistent fault state types or obvious differences in fault grades in the two mapping sets. Based on the first conflict state mapping set and the initial conflict mapping set, the Jensen-Shannon divergence (JSD) distribution similarity of the probability distribution of the corresponding fault state is calculated, and the specific calculation steps comprise smoothing the two probability distributions, calculating intermediate mixed distribution, and then obtaining a similarity value according to JSD definition. And finally, taking the JSD distribution similarity as a measurement index of the first state confidence coefficient, and reflecting the consistency and the credibility between the initial state mapping set and the first verification state mapping set.
And carrying out state transition prediction on the hierarchical state confidence vector, and outputting a state transition probability matrix.
Further, performing state transition prediction on the hierarchical state confidence vector, and outputting a state transition probability matrix, wherein the method comprises the following steps:
The method comprises the steps of interactively obtaining a plurality of sample state confidence vector sequences, carrying out state transition frequency statistics on the plurality of sample state confidence vector sequences to output a state transition frequency chain, constructing a reference state transition frequency matrix based on the state transition frequency chain, carrying out state transition probability normalization correction on the hierarchical state confidence vector based on the reference state transition frequency matrix, and outputting the state transition probability matrix.
The method comprises the steps of obtaining a state confidence vector sequence of a plurality of historical samples in an interaction mode, wherein the state confidence vector sequence covers the time evolution process of normal and various fault states, obtaining a state transition frequency chain by counting transition relations of adjacent states in the state confidence vector sequence of the plurality of samples, recording transition times and frequencies among different states, constructing a reference state transition frequency matrix based on the state transition frequency chain, wherein elements in the matrix represent transition frequencies among the states, rows of the matrix represent the current state and columns represent possible next states, normalizing and correcting the state transition probabilities based on the reference state transition frequency matrix aiming at the hierarchical state confidence vector at the current moment, generating a state transition probability matrix after correction, reflecting transition probability distribution among the states, and finally outputting the state transition probability matrix to provide basis for calculation of the follow-up real-time fault probability distribution and generation of multi-stage early warning signals.
And fusing the hierarchical state confidence vector and the state transition probability matrix, and outputting real-time fault probability distribution.
The method comprises the steps of firstly taking a hierarchical state confidence vector at the current moment as an initial probability distribution of a fault state, then carrying out weighted correction and time sequence prediction on the initial probability distribution according to a state transition probability matrix, calculating the condition transition probability of each fault state to obtain a state probability distribution adjusted based on a history transition rule, then fusing the corrected probability distribution with the initial confidence vector, generating comprehensive real-time fault probability distribution through methods such as weighted average or Bayesian updating, and finally outputting the real-time fault probability distribution for supporting fault diagnosis, risk assessment and generation of multi-stage early warning signals.
And generating a multi-stage early warning signal according to the real-time fault probability distribution, and triggering a step safety protection response.
Setting a multi-level early warning threshold value based on probability values corresponding to each fault state in the real-time fault probability distribution, respectively corresponding to low-level early warning, medium-level early warning and high-level early warning levels, comparing each fault state probability with a preset threshold value, judging the current fault risk level, generating early warning signals of corresponding levels when the fault probability exceeds the corresponding threshold value, triggering safety protection response measures of corresponding steps according to the generated multi-level early warning signals, and particularly comprises, but is not limited to, alarm prompt, operation limitation, automatic shutdown, emergency fault processing program start and the like.
In summary, the embodiment of the application has at least the following technical effects:
Firstly, carrying out special equipment state sensitivity verification on multiple monitoring indexes of a power distribution cabinet to obtain a dynamic grading sensitivity index set. And simultaneously, according to the dynamic grading sensitive index set, gradually retrieving multistage real-time operation parameters from the power distribution cabinet according to the sensitivity priority. Further, the multistage real-time operation parameters are dynamically loaded to an elevator state mode library, the hierarchical equipment state mapping is triggered, and the hierarchical state confidence vector is output. Next, state transition prediction is performed on the hierarchical state confidence vector, and a state transition probability matrix is output. And then, integrating the hierarchical state confidence vector and the state transition probability matrix, and outputting the real-time fault probability distribution. And finally, generating a multi-stage early warning signal according to the real-time fault probability distribution, and triggering a step safety protection response. The method solves the technical problem that the state identification of special equipment depends on the sensor in the prior art, and realizes the accurate identification of the elevator running state based on the electrical parameters, thereby reducing the dependence on the external sensor and improving the technical effects of real-time performance and reliability of state monitoring.
In a second embodiment, based on the same inventive concept as the special equipment state recognition method based on electrical parameter pattern matching in the foregoing embodiment, as shown in fig. 2, the present application provides a special equipment state recognition system based on electrical parameter pattern matching, where the system includes:
The system comprises a sensitivity verification module 11, a mode library construction module 12, a parameter retrieval module 13, a state mapping module 14, a state transition prediction module 15, a fault probability output module 16, a warning response module 17, a warning response module and a warning response module, wherein the sensitivity verification module is used for carrying out special equipment state sensitivity verification on multiple monitoring indexes of a power distribution cabinet to obtain a dynamic hierarchical sensitivity index set, the mode library construction module 12 is used for carrying out offline pre-construction on a multi-level state mode sub-library according to the dynamic hierarchical sensitivity index set and generating an elevator state mode library through hierarchical association integration, the parameter retrieval module 13 is used for retrieving multi-level real-time operation parameters step by step according to the sensitivity priority from the power distribution cabinet according to the dynamic hierarchical sensitivity index set, the state mapping module 14 is used for dynamically loading the multi-level real-time operation parameters to the elevator state mode library, triggering hierarchical equipment state mapping and outputting a hierarchical state confidence vector, the state transition prediction module 15 is used for carrying out state transition prediction on the hierarchical state confidence vector and outputting a state transition probability matrix, and the fault probability output module 16 is used for fusing the hierarchical state confidence vector and the state transition probability matrix to output real-time fault probability distribution, and a warning response module 17 is used for generating a multi-level warning signal according to the real-time fault probability distribution and triggering safety protection response.
Further, the sensitivity verification module 11 is configured to perform the following method:
The method comprises the steps of acquiring application environment characteristics of a power distribution cabinet, taking the application environment characteristics and a power distribution cabinet model code as equipment fingerprint code retrieval conditions, calling a plurality of equipment full-dimension operation logs, aggregating the equipment full-dimension operation logs based on index types to obtain a plurality of multi-state time sequence data sets of a plurality of operation indexes, quantifying state sensitivity of special equipment based on the plurality of multi-state time sequence data sets, outputting a plurality of operation comprehensive sensitivities, dynamically grading the plurality of operation indexes according to the plurality of operation comprehensive sensitivities, and outputting the dynamic grading sensitivity index set.
Further, the schema library construction module 12 is configured to perform the following method:
the method comprises the steps of obtaining a dynamic hierarchical sensitive index set, obtaining a multi-stage sensitive index by decomposing the dynamic hierarchical sensitive index set based on a hierarchical relation, taking a specific index set of a first-stage sensitive index as a screening condition, calling a plurality of groups of sample fault state time sequence data sets of a plurality of sample fault states under a plurality of groups of sample fault levels from a plurality of equipment full-dimensional operation logs, carrying out index fluctuation scale analysis on the plurality of groups of sample fault state time sequence data sets to output a plurality of groups of state feature templates, storing the plurality of sample fault states, the plurality of groups of sample fault levels and the plurality of groups of sample state feature templates in a hierarchical relation mode sub-library, constructing a multi-stage state mode sub-library in a hierarchical sequence iteration mode, constructing a bidirectional mapping relation index table of the multi-stage sensitive index and the multi-stage state mode sub-library, and generating the elevator state mode sub-library.
Further, the state mapping module 14 is configured to perform the following method:
The method comprises the steps of acquiring a first-stage operation parameter sequence of a first-stage sensitive index from a power distribution cabinet in real time, extracting features of the first-stage operation parameter sequence to obtain a first-stage feature vector, loading the first-stage feature vector into a first-stage state mode sub-library of an elevator state mode library, matching and outputting an initial state mapping set, and if the initial state mapping set is an empty set, performing monitoring circulation of the first-stage sensitive index until the initial state mapping set is a non-empty set, and triggering hierarchical equipment state mapping.
Further, the state mapping module 14 is configured to perform the following method:
If the initial state mapping set is a non-empty set, a second-level sensitive index is called from the dynamic grading sensitive index set; the power distribution cabinet backtracks a second-level operation parameter sequence according to the index composition of the second-level sensitive index, obtains a second-level feature vector through feature extraction, fuses and loads the first-level feature vector and the second-level feature vector to a second-level state mode sub-library of the elevator state mode library, matches and outputs a first verification state mapping set, adopts the first verification state mapping set to conduct state reliability verification of the initial state mapping set, outputs first state confidence, weights and fuses the initial state mapping set and the first verification state mapping set to generate the hierarchical state confidence vector if the first state confidence is higher than a preset confidence threshold, and iteratively calls the next-level sensitive index to verify if the first state confidence is lower than the preset confidence threshold until the confidence reaches the standard, and outputs the hierarchical state confidence vector by integrating a multi-level mapping result.
Further, the state mapping module 14 is configured to perform the following method:
The method comprises the steps of traversing the first-level feature vector and a plurality of groups of sample state feature templates Euclidean distance matrixes in a first-level state mode sub-library to output a plurality of groups of state similarity, retrieving a plurality of real-time fault levels from the plurality of groups of sample fault levels according to the largest value arranged in a descending order in the plurality of groups of state similarity, taking the plurality of largest similarity as a plurality of real-time fault probabilities of the plurality of real-time fault levels, traversing the plurality of real-time fault probabilities based on a preset similarity threshold, screening P real-time fault levels and P real-time fault probabilities of P sample fault states from the plurality of real-time fault levels, storing the P sample fault states, the P real-time fault levels and the P real-time fault probabilities in a correlated mode, and outputting the initial state mapping set, wherein the initial state mapping set is an empty set if the plurality of real-time fault probabilities are smaller than the preset similarity threshold.
Further, the state mapping module 14 is configured to perform the following method:
performing state conflict detection on the first verification state mapping set and the initial state mapping set, and screening and outputting the first conflict state mapping set and the initial conflict mapping set; and calculating the first JSD distribution similarity of the first conflict state mapping set and the initial conflict mapping set as the first state confidence.
Further, the state transition prediction module 15 is configured to perform the following method:
The method comprises the steps of interactively obtaining a plurality of sample state confidence vector sequences, carrying out state transition frequency statistics on the plurality of sample state confidence vector sequences to output a state transition frequency chain, constructing a reference state transition frequency matrix based on the state transition frequency chain, carrying out state transition probability normalization correction on the hierarchical state confidence vector based on the reference state transition frequency matrix, and outputting the state transition probability matrix.
Further, the sensitivity verification module 11 is configured to perform the following method:
Decomposing the multiple multi-state time sequence data sets based on equipment state labels to obtain multiple reference state record sets and multiple groups of fault state record sets, quantifying the multiple groups of fault state record sets by using KL divergence based on the multiple reference state record sets to output multiple groups of fault state KL sensitivity scores, weighting the multiple groups of fault state KL sensitivity scores in groups according to the recurrence frequency of M fault states, and outputting the multiple operation comprehensive sensitivities.
It should be noted that the sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this specification. The processes depicted in the accompanying drawings do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
The foregoing description of the preferred embodiments of the application is not intended to limit the application to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the application are intended to be included within the scope of the application.
The specification and figures are merely exemplary illustrations of the present application and are considered to cover any and all modifications, variations, combinations, or equivalents that fall within the scope of the application. It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the scope of the application. Thus, the present application is intended to include such modifications and alterations insofar as they come within the scope of the application or the equivalents thereof.
Claims (8)
1. The special equipment state identification method based on the electrical parameter pattern matching is characterized by comprising the following steps of:
carrying out special equipment state sensitivity verification on multiple monitoring indexes of the power distribution cabinet to obtain a dynamic grading sensitivity index set;
pre-constructing a multi-stage state mode sub-library offline according to the dynamic hierarchical sensitive index set, and generating an elevator state mode library through hierarchical association integration;
according to the dynamic grading sensitive index set, multi-stage real-time operation parameters are gradually fetched from the power distribution cabinet according to the sensitivity priority;
dynamically loading the multistage real-time operation parameters to the elevator state mode library, triggering hierarchical equipment state mapping, and outputting a hierarchical state confidence vector;
performing state transition prediction on the hierarchical state confidence vector, and outputting a state transition probability matrix;
Fusing the hierarchical state confidence vector and the state transition probability matrix, and outputting real-time fault probability distribution;
Generating a multi-stage early warning signal according to the real-time fault probability distribution, and triggering a step safety protection response;
carrying out special equipment state sensitivity verification on multiple monitoring indexes of the power distribution cabinet to obtain a dynamic grading sensitivity index set, wherein the method comprises the following steps:
The application environment characteristics of the power distribution cabinet are called, the application environment characteristics and the power distribution cabinet model codes are used as equipment fingerprint code retrieval conditions, and a plurality of equipment full-dimension operation logs are called;
Aggregating the plurality of equipment full-dimension operation logs based on index types to obtain a plurality of multi-state time sequence data sets of a plurality of operation indexes;
carrying out state sensitivity quantification of special equipment based on the multiple multi-state time sequence data sets, and outputting multiple operation comprehensive sensitivities;
According to the comprehensive sensitivity of the operation, carrying out dynamic classification on the operation indexes and outputting the dynamic classification sensitive index set;
pre-constructing a multi-stage state mode sub-library offline according to the dynamic hierarchical sensitive index set, and generating an elevator state mode library through hierarchical association integration, wherein the method comprises the following steps:
decomposing the dynamic grading sensitive index set based on the hierarchical relation to obtain a multi-grade sensitive index;
Taking a specific index set of the first-stage sensitive index as a screening condition, and calling a plurality of groups of sample fault state time sequence data sets of a plurality of sample fault states under a plurality of groups of sample fault levels from the plurality of equipment full-dimension operation logs;
Outputting a plurality of groups of state feature templates by carrying out index fluctuation scale analysis on the plurality of groups of sample fault state time sequence data sets;
the multiple sample fault states, multiple groups of sample fault levels and multiple groups of sample state feature templates are stored in a hierarchical association mode, and a first-stage state mode sub-library is obtained;
and constructing a multi-stage state mode sub-library in a hierarchical sequence iteration mode, constructing a bidirectional mapping relation index table of the multi-stage sensitive index and the multi-stage state mode sub-library, and generating the elevator state mode library.
2. The electrical parameter pattern matching-based specialty equipment status identification method of claim 1, wherein dynamically loading the multi-level real-time operating parameters into the elevator status pattern library, triggering a hierarchical equipment status map, outputting a hierarchical status confidence vector, the method comprising:
A first-stage operation parameter sequence of the first-stage sensitive index is called from the power distribution cabinet in real time;
Extracting the characteristics of the first-stage operation parameter sequence to obtain a first-stage characteristic vector;
loading the first-stage feature vector to a first-stage state mode sub-library of the elevator state mode library, and outputting an initial state mapping set in a matching way;
and if the initial state mapping set is an empty set, performing monitoring circulation of the first-stage sensitive index until the initial state mapping set is a non-empty set, and triggering hierarchical equipment state mapping.
3. The electrical parameter pattern matching based specialty equipment status identification method of claim 2, wherein dynamically loading the multi-level real-time operational parameters to the elevator status pattern library, triggering a hierarchical equipment status map, outputting a hierarchical status confidence vector, the method further comprising:
if the initial state mapping set is a non-empty set, a second-level sensitive index is called from the dynamic grading sensitive index set;
The power distribution cabinet backtracks and invokes a second-level operation parameter sequence according to the index composition of the second-level sensitive index, and a second-level feature vector is obtained through feature extraction;
The first-stage feature vector and the second-stage feature vector are fused and loaded to a second-stage state mode sub-library of the elevator state mode library, and a first verification state mapping set is output in a matching mode;
Carrying out state credibility verification on the initial state mapping set by adopting the first verification state mapping set, and outputting a first state confidence;
If the first state confidence coefficient is higher than a preset confidence threshold value, weighting and fusing the initial state mapping set and the first verification state mapping set to generate the hierarchical state confidence coefficient vector;
And if the first state confidence coefficient is lower than a preset confidence threshold value, iteratively calling a next-stage sensitive index to verify until the confidence coefficient reaches the standard, and integrating the multi-stage mapping result to output a hierarchical state confidence coefficient vector.
4. The electrical parameter pattern matching-based specialty equipment status identification method of claim 2, wherein loading the first level feature vector into a first level status pattern sub-library of the elevator status pattern library matches an output initial status mapping set, the method comprising:
Traversing and calculating Euclidean distance matrixes of a plurality of groups of sample state feature templates in the first-stage feature vector and the first-stage state pattern sub-library, and outputting a plurality of groups of state similarity;
According to the intra-group descending order maximum values of the multiple groups of state similarity, multiple real-time fault levels are fetched from the multiple groups of sample fault levels, and the multiple maximum similarity is used as multiple real-time fault probabilities of the multiple real-time fault levels;
Traversing the plurality of real-time fault probabilities based on a preset similarity threshold, and screening P real-time fault levels and P real-time fault probabilities of P sample fault states from the plurality of real-time fault levels;
The P sample fault states, the P real-time fault levels and the P real-time fault probabilities are stored in an associated mode, and the initial state mapping set is output;
And if the real-time fault probabilities are smaller than a preset similarity threshold, the initial state mapping set is an empty set.
5. The electrical parameter pattern matching-based specialty equipment state identification method of claim 3, wherein the state reliability verification of the initial state mapping set is performed using the first verification state mapping set, and a first state confidence is output, the method comprising:
Performing state conflict detection on the first verification state mapping set and the initial state mapping set, and screening and outputting the first conflict state mapping set and the initial conflict mapping set;
And calculating the first JSD distribution similarity of the first conflict state mapping set and the initial conflict mapping set as the first state confidence.
6. The electrical parameter pattern matching-based specialty equipment state identification method of claim 1, wherein state transition prediction is performed on the hierarchical state confidence vector, and a state transition probability matrix is output, the method comprising:
a plurality of sample state confidence vector sequences are obtained interactively, and state transition frequency statistics is carried out on the plurality of sample state confidence vector sequences, so that a state transition frequency chain is output;
constructing a reference state transition frequency matrix based on the state transition frequency chain;
And carrying out state transition probability normalization correction on the hierarchical state confidence vector based on the reference state transition frequency matrix, and outputting the state transition probability matrix.
7. The electrical parameter pattern matching-based specialty equipment status recognition method of claim 1, wherein specialty equipment status sensitivity quantification is based on the plurality of multi-state time series data sets, outputting a plurality of operational integrated sensitivities, the method comprising:
Decomposing the multiple multi-state time sequence data sets based on the equipment state labels to obtain multiple reference state record sets and multiple fault state record sets;
Quantifying the multiple groups of fault state record sets by using the multiple reference state record sets as references and outputting multiple groups of fault state KL sensitivity scores by using KL divergence;
and performing intra-group weighting on the multiple groups of fault state KL sensitivity scores according to the recurrence frequency of M fault states, and outputting the multiple operation comprehensive sensitivities.
8. A special equipment state recognition system based on electrical parameter pattern matching, characterized in that it is used for implementing the special equipment state recognition method based on electrical parameter pattern matching according to any one of claims 1-7, said system comprising:
The sensitivity verification module is used for carrying out special equipment state sensitivity verification on multiple monitoring indexes of the power distribution cabinet to obtain a dynamic grading sensitivity index set;
the mode library construction module is used for pre-constructing a multi-stage state mode sub-library offline according to the dynamic hierarchical sensitive index set and generating an elevator state mode library through hierarchical association integration;
The parameter calling module is used for calling multistage real-time operation parameters step by step according to the dynamic grading sensitivity index set from the power distribution cabinet and the sensitivity priority;
The state mapping module dynamically loads the multistage real-time operation parameters to the elevator state mode library, triggers hierarchical equipment state mapping and outputs a hierarchical state confidence vector;
the state transition prediction module is used for carrying out state transition prediction on the hierarchical state confidence vector and outputting a state transition probability matrix;
the fault probability output module is used for fusing the hierarchical state confidence vector and the state transition probability matrix and outputting real-time fault probability distribution;
and the early warning response module is used for generating a multi-stage early warning signal according to the real-time fault probability distribution and triggering a step safety protection response.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202511165575.3A CN120744527B (en) | 2025-08-20 | 2025-08-20 | Special equipment state identification method and system based on electrical parameter pattern matching |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202511165575.3A CN120744527B (en) | 2025-08-20 | 2025-08-20 | Special equipment state identification method and system based on electrical parameter pattern matching |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN120744527A CN120744527A (en) | 2025-10-03 |
| CN120744527B true CN120744527B (en) | 2025-11-25 |
Family
ID=97187412
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202511165575.3A Active CN120744527B (en) | 2025-08-20 | 2025-08-20 | Special equipment state identification method and system based on electrical parameter pattern matching |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN120744527B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN120180197A (en) * | 2025-05-19 | 2025-06-20 | 江苏恒润电力设计院有限公司 | Substation equipment condition monitoring and intelligent fault warning method based on deep learning |
-
2025
- 2025-08-20 CN CN202511165575.3A patent/CN120744527B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN120180197A (en) * | 2025-05-19 | 2025-06-20 | 江苏恒润电力设计院有限公司 | Substation equipment condition monitoring and intelligent fault warning method based on deep learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN120744527A (en) | 2025-10-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN118940167A (en) | A lightweight equipment fault prediction system based on multidimensional data | |
| CN105677791B (en) | Method and system for analyzing operational data of wind turbines | |
| CN116737510B (en) | Data analysis-based intelligent keyboard monitoring method and system | |
| CN116075733A (en) | Battery management system for sorting battery modules | |
| CN118520517B (en) | Solid state disk data protection system based on error check | |
| CN119105325A (en) | A digital GIS equipment fault intelligent monitoring and management system | |
| CN118191622B (en) | State monitoring method, device and equipment of energy storage lithium battery and storage medium | |
| CN115659271A (en) | Sensor anomaly detection method, model training method, system, device and medium | |
| CN118821028A (en) | A risk prediction method and skid-mounted system for transmission pipelines based on big data | |
| CN118821072A (en) | Method, device, equipment, storage medium and vehicle for determining characteristic parameters | |
| CN115905368A (en) | An experimental association information system based on cloud data | |
| CN120744527B (en) | Special equipment state identification method and system based on electrical parameter pattern matching | |
| CN120674631A (en) | Lithium ion battery thermal runaway early warning method based on sound signals | |
| CN117406044B (en) | Discharge detection method, device and equipment for liquid crystal display screen and storage medium | |
| CN119377898A (en) | An accurate modeling method for photovoltaic module faults based on fusion algorithm | |
| CN116910526B (en) | Model training methods, devices, communication equipment, and readable storage media | |
| CN117932342A (en) | Wind turbine generator gearbox fault diagnosis method and system | |
| CN118211111A (en) | A method and system for identifying electricity theft users | |
| CN120746305B (en) | Intelligent integrated service method and system for anti-overflow anti-static controller | |
| CN118965825B (en) | AGM separator thermal stability monitoring method and system | |
| CN119149350B (en) | Abnormal state early warning method of energy storage system | |
| CN121324906B (en) | Method, equipment and medium for rapidly estimating service life of LED chip | |
| CN119270071B (en) | A battery fault identification model training method and device | |
| CN120705688A (en) | Method, device and electronic equipment for identifying abnormal data in electric energy meter circuit | |
| CN119690843A (en) | Software defect location method and system based on mobile terminal technology development |
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 |