CN117349747A - Offline fault reason classification method for electric power Internet of things intelligent terminal - Google Patents
Offline fault reason classification method for electric power Internet of things intelligent terminal Download PDFInfo
- Publication number
- CN117349747A CN117349747A CN202311271792.1A CN202311271792A CN117349747A CN 117349747 A CN117349747 A CN 117349747A CN 202311271792 A CN202311271792 A CN 202311271792A CN 117349747 A CN117349747 A CN 117349747A
- Authority
- CN
- China
- Prior art keywords
- electric power
- intelligent terminal
- offline
- power internet
- fault
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 75
- 238000004458 analytical method Methods 0.000 claims abstract description 52
- 238000013528 artificial neural network Methods 0.000 claims abstract description 19
- 230000007246 mechanism Effects 0.000 claims abstract description 14
- 238000003066 decision tree Methods 0.000 claims description 21
- 238000007637 random forest analysis Methods 0.000 claims description 21
- 238000004590 computer program Methods 0.000 claims description 17
- 238000007477 logistic regression Methods 0.000 claims description 6
- 238000012706 support-vector machine Methods 0.000 claims description 6
- 238000012423 maintenance Methods 0.000 abstract description 13
- 238000010586 diagram Methods 0.000 description 11
- 238000012545 processing Methods 0.000 description 9
- 238000004422 calculation algorithm Methods 0.000 description 8
- 238000004891 communication Methods 0.000 description 8
- 230000008859 change Effects 0.000 description 7
- 230000000875 corresponding effect Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 238000013507 mapping Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 235000006629 Prosopis spicigera Nutrition 0.000 description 1
- 240000000037 Prosopis spicigera Species 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00002—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by monitoring
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Engineering & Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- Strategic Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Operations Research (AREA)
- Primary Health Care (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Quality & Reliability (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Probability & Statistics with Applications (AREA)
- Power Engineering (AREA)
- Entrepreneurship & Innovation (AREA)
Abstract
The invention discloses an offline fault reason classification method for an intelligent terminal of an electric power internet of things. The method comprises the following steps: acquiring historical time sequence data of the electric power internet of things intelligent terminal; inputting the historical time sequence data into a fault cause analysis model to obtain a fault cause probability set, wherein the fault cause analysis model comprises a GRU-DNN-Attention model combined by a gating circulation unit GRU, a deep neural network DNN and an Attention mechanism Attention; and determining the offline fault reason of the electric power Internet of things intelligent terminal according to the fault reason probability set. According to the method, the offline fault cause probability set of the electric power Internet of things intelligent terminal can be determined through the GRU-DNN-Attention model, and the offline fault cause of the electric power Internet of things intelligent terminal is determined according to the fault cause probability set, so that the operation and maintenance efficiency of the electric power Internet of things intelligent terminal is improved.
Description
Technical Field
The embodiment of the invention relates to the technical field of electric power Internet of things, in particular to an offline fault reason classification method for an intelligent terminal of an electric power Internet of things.
Background
Along with the rapid construction of a novel power system, a perception object extends from the side of a power grid to a source charge end, new energy and new business are continuously accessed, the data scale is exponentially increased, and the number and the scale of the intelligent terminals of the Internet of things required for accurate acquisition in each link of source network charge storage are also increased year by year. Based on the mass data collected by the electric power internet of things intelligent terminal, the operation state of the electric power system can be more accurately perceived and controlled by combining with analysis of technical means such as artificial intelligence, big data and the like. However, in the operation process of the intelligent terminal of the electric power internet of things, offline faults often occur, and offline fault reasons need to be determined as soon as possible, and maintenance is performed, so that the offline time of equipment is reduced as much as possible. In the current overhaul work, manual experience is mainly used, the fault cause is determined through checking the field state of equipment, and then the fault is processed. Therefore, the prior art cannot quickly and accurately determine the offline fault reason of the intelligent terminal.
Disclosure of Invention
The invention provides an offline fault reason classification method of an intelligent terminal of an electric power Internet of things, which aims to solve the problem that the offline fault reason of the intelligent terminal cannot be rapidly and accurately determined in the prior art.
According to one aspect of the invention, an offline fault cause classification method of an electric power internet of things intelligent terminal is provided, and the method comprises the following steps:
acquiring historical time sequence data of the electric power internet of things intelligent terminal;
inputting the historical time sequence data into a fault cause analysis model to obtain a fault cause probability set, wherein the fault cause analysis model comprises a GRU-DNN-Attention model combined by a gating circulation unit GRU, a deep neural network DNN and an Attention mechanism Attention;
and determining the offline fault reason of the electric power Internet of things intelligent terminal according to the fault reason probability set.
According to another aspect of the present invention, there is provided an offline fault cause classification device of an electric power internet of things intelligent terminal, the device comprising:
the acquisition module is used for acquiring historical time sequence data of the electric power internet of things intelligent terminal;
the analysis module is used for inputting the historical time sequence data into a fault cause analysis model to obtain a fault cause probability set, and the fault cause analysis model comprises a GRU-DNN-Attention model combined by a gating circulation unit GRU, a deep neural network DNN and an Attention mechanism Attention;
and the determining module is used for determining the offline fault reason of the electric power Internet of things intelligent terminal according to the fault reason probability set.
According to another aspect of the present invention, there is provided an electronic apparatus including: at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor, so that the at least one processor can execute the offline fault cause classification method of the electric power internet of things intelligent terminal according to any embodiment of the invention.
According to another aspect of the present invention, there is provided a computer readable storage medium storing computer instructions for implementing the offline fault cause classification method of the electric power internet of things intelligent terminal according to any embodiment of the present invention when executed by a processor.
The embodiment of the invention discloses an offline fault reason classification method of an intelligent terminal of an electric power internet of things, which comprises the following steps: acquiring historical time sequence data of the electric power internet of things intelligent terminal; inputting the historical time sequence data into a fault cause analysis model to obtain a fault cause probability set, wherein the fault cause analysis model comprises a GRU-DNN-Attention model combined by a gating circulation unit GRU, a deep neural network DNN and an Attention mechanism Attention; and determining the offline fault reason of the electric power Internet of things intelligent terminal according to the fault reason probability set. According to the method, the offline fault cause probability set of the intelligent terminal of the electric power Internet of things can be determined through the GRU-DNN-Attention model, and the offline fault cause of the intelligent terminal of the electric power Internet of things is determined according to the fault cause probability set, so that the problem that the offline fault cause of the intelligent terminal cannot be determined rapidly and accurately in the prior art is solved, and the operation and maintenance efficiency of the intelligent terminal of the electric power Internet of things is improved. Through the fault cause analysis model, operation and maintenance personnel can be assisted to rapidly and accurately locate faults of the electric power and electric power internet of things intelligent terminal, so that the operation and maintenance efficiency of the terminal is improved, an operation and maintenance mode of manual field debugging is changed, debugging operation and maintenance cost is effectively saved, and the operation and maintenance digitization level of a power grid is improved.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of an offline fault cause classification method of an intelligent terminal of an electric power internet of things according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a network structure of a GRU-DNN-Attention model according to an embodiment of the present invention;
fig. 3 is a schematic diagram of offline fault cause classification of an electric power internet of things intelligent terminal according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of weight change according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an offline fault cause classification device of an intelligent terminal of an electric power internet of things according to a second embodiment of the present invention;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention. It should be understood that the various steps recited in the method embodiments of the present invention may be performed in a different order and/or performed in parallel. Furthermore, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the invention is not limited in this respect.
The term "including" and variations thereof as used herein are intended to be open-ended, i.e., including, but not limited to. The term "based on" is based at least in part on. The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments. Related definitions of other terms will be given in the description below.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be noted that references to "one", "a plurality" and "a plurality" in this disclosure are intended to be illustrative rather than limiting, and those skilled in the art will appreciate that "one or more" is intended to be construed as "one or more" unless the context clearly indicates otherwise.
The names of messages or information interacted between the devices in the embodiments of the present invention are for illustrative purposes only and are not intended to limit the scope of such messages or information.
It will be appreciated that prior to using the technical solutions disclosed in the embodiments of the present disclosure, the user should be informed and authorized of the type, usage range, usage scenario, etc. of the personal information related to the present disclosure in an appropriate manner according to the relevant legal regulations.
For example, in response to receiving an active request from a user, a prompt is sent to the user to explicitly prompt the user that the operation it is requesting to perform will require personal information to be obtained and used with the user. Thus, the user can autonomously select whether to provide personal information to software or hardware such as an electronic device, an application program, a server or a storage medium for executing the operation of the technical scheme of the present disclosure according to the prompt information.
As an alternative but non-limiting implementation, in response to receiving an active request from a user, the manner in which the prompt information is sent to the user may be, for example, a popup, in which the prompt information may be presented in a text manner. In addition, a selection control for the user to select to provide personal information to the electronic device in a 'consent' or 'disagreement' manner can be carried in the popup window.
It will be appreciated that the above-described notification and user authorization process is merely illustrative and not limiting of the implementations of the present disclosure, and that other ways of satisfying relevant legal regulations may be applied to the implementations of the present disclosure.
It will be appreciated that the data (including but not limited to the data itself, the acquisition or use of the data) involved in the present technical solution should comply with the corresponding legal regulations and the requirements of the relevant regulations.
Example 1
Fig. 1 is a flow chart of an offline fault cause classification method of an electric power internet of things intelligent terminal according to an embodiment of the present invention, where the method may be applicable to a case of analyzing an offline cause of the electric power internet of things intelligent terminal, and the method may be performed by an offline fault cause classification device of the electric power internet of things intelligent terminal, where the device may be implemented by software and/or hardware and is generally integrated on an electronic device, and in this embodiment, the electronic device includes but is not limited to: a computer, etc.
As shown in fig. 1, the offline fault cause classification method for an intelligent terminal of an electric power internet of things provided by the embodiment of the invention includes the following steps:
s110, acquiring historical time sequence data of the electric power Internet of things intelligent terminal.
The intelligent terminal of the electric power internet of things is equipment which is mainly applied to the side end side, realizes data acquisition such as electric quantity, environment quantity, state quantity, video image and the like, calculates edges and transmits data through a network layer, and is responsible for various functions such as data acquisition, processing, encryption and transmission. The historical time sequence data can be time sequence data before the intelligent terminal of the electric power internet of things, and the time sequence data refers to state change information of a certain object in a historical time dimension.
In this embodiment, in the operation process of the electric power internet of things intelligent terminal, a large amount of equipment state information is collected, and this embodiment can obtain the information of the electric power internet of things intelligent terminal, namely, historical time sequence data, based on the information, the reason of offline fault of the electric power internet of things intelligent terminal can be analyzed, and relevant professional operation and maintenance personnel can be timely distributed for maintenance, so that operation and maintenance efficiency is improved.
S120, inputting the historical time sequence data into a fault cause analysis model to obtain a fault cause probability set.
The fault cause analysis model comprises a GRU-DNN-Attention model combined by a gating circulating unit GRU, a deep neural network DNN and an Attention mechanism Attention.
The fault cause analysis model can be a model for analyzing offline causes of the electric power internet of things intelligent terminal. The fault cause probability set can be a set of probabilities of fault causes of the offline electric power internet of things intelligent terminal, and the probability of each fault cause can be included in the fault cause probability set. The gated loop unit (Gate Recurrent Unit, GRU) is one type of loop neural network. Deep neural networks (Deep Neural Networks, DNN) are the basis for deep learning. Attention mechanisms (Attention) are a resource allocation scheme that is a primary means of solving the information overload problem, allocating computing resources to more important tasks.
In this embodiment, a GRU-DNN-Attention model may be constructed to implement classification of offline fault reasons of terminal devices, and specifically, historical time sequence data may be input into the GRU-DNN-Attention model to obtain a fault reason probability set. By utilizing the characteristic that the GRU can keep the historical time sequence data, the algorithm can notice the abnormal situation in the historical data through the Attention layer so as to improve the accuracy of the offline reason classification of the terminal, and fig. 2 is a schematic diagram of a network structure of the GRU-DNN-Attention model provided by the embodiment of the invention. By introducing an attention mechanism, attention to important data can be achieved.
Specifically, in building the GRU-DNN-Attention model, one linear mapping may be used first, and given that the hidden state of the input sequence is denoted as x, the Attention mechanism calculates the Attention weight first by the following linear mapping:
s＝W att ·x+b att
wherein W is att Is the learning parameter of attention weight, b att Is a bias term.
Then, the attention score s is softmax normalized to obtain the attention weight a i ：
Wherein T is the number of time steps of the sequence, a i The attention weight of the ith time step is represented.
Then, the attention weight a is used i For hidden state x i Performing weighted aggregation to obtain a weighted result c:
wherein x is i Is the hidden state of the ith time step.
Finally, the weighted result c may be passed to the neural network DNN for subsequent processing and classification.
The model may be allowed to dynamically assign weights according to the importance of each time step by an attention mechanism, focusing on the portions of the sequence data that have critical information. This helps to improve the performance and behavior of the model in processing the sequence data.
According to the embodiment, the information in the historical time sequence data can be well mined through the constructed GRU-DNN-Attention network, and the classification of offline reasons of the intelligent terminal equipment is realized.
S130, determining the offline fault reason of the electric power Internet of things intelligent terminal according to the fault reason probability set.
The fault cause may be a cause of offline fault of the electric power internet of things intelligent terminal. The types of the fault causes can be classified according to actual conditions.
In this embodiment, in obtaining the failure cause probability set, the offline failure cause of the electric power internet of things intelligent terminal may be determined according to the probability corresponding to each failure cause in the failure cause probability set. For example, the fault cause with the largest probability may be used as the fault cause, and when there are two largest fault cause probabilities, the fault cause of the final electric power internet of things intelligent terminal offline may also be determined by continuous comparison, which is not limited in this embodiment.
In one embodiment, the historical timing data includes at least: network delay data, ambient temperature, device temperature, CPU utilization and memory utilization; the fault reasons at least comprise: network failure, device hardware failure, device software failure, and power failure.
In this embodiment, the historical timing data may include network delay data, ambient temperature, device temperature, CPU usage, and memory usage, and the failure causes may include network failures, device hardware failures, device software failures, and power failures. It is understood that the historical time series data and the cause of the failure are not limited to the above data.
The embodiment of the invention provides a method for classifying offline fault reasons of an intelligent terminal of an electric power internet of things, which comprises the following steps: acquiring historical time sequence data of the electric power internet of things intelligent terminal; inputting the historical time sequence data into a fault cause analysis model to obtain a fault cause probability set, wherein the fault cause analysis model comprises a GRU-DNN-Attention model combined by a gating circulation unit GRU, a deep neural network DNN and an Attention mechanism Attention; and determining the offline fault reason of the electric power Internet of things intelligent terminal according to the fault reason probability set. According to the method, the offline fault cause probability set of the intelligent terminal of the electric power Internet of things can be determined through the GRU-DNN-Attention model, and the offline fault cause of the intelligent terminal of the electric power Internet of things is determined according to the fault cause probability set, so that the problem that the offline fault cause of the intelligent terminal cannot be determined rapidly and accurately in the prior art is solved, and the operation and maintenance efficiency of the intelligent terminal of the electric power Internet of things is improved.
On the basis of the above embodiments, modified embodiments of the above embodiments are proposed, and it is to be noted here that only the differences from the above embodiments are described in the modified embodiments for the sake of brevity of description.
In one embodiment, the fault cause analysis model further comprises at least one of: decision trees, random forests, naive bayes, support vector machines, and logistic regression.
The decision tree is a prediction model, and represents a mapping relationship between the object attribute and the object value. Random forests are an algorithm for integrating a plurality of trees through the Bagging concept of ensemble learning. Naive bayes are one of the bayesian classification algorithms. The support vector machine is a binary model. Logistic regression is a machine learning method used to solve the classification problem.
In this embodiment, the failure cause analysis model further includes at least one of: decision trees, random forests, naive bayes, support vector machines, and logistic regression. Because the demand of the neural network for the historical data is large, and at the early stage of the construction of the intelligent electric power object conjunct system, enough data is not available for the neural network to train, so that the performance of the equipment offline fault cause classification method based on the GRU-DNN-Attention network is difficult to reach the expectations under the condition of lacking enough data support. Therefore, the present embodiment may also incorporate other models for determining the failure cause probability set.
In one embodiment, when the failure cause analysis model includes at least two models, inputting the historical time series data into the failure cause analysis model to obtain a failure cause probability set includes:
inputting the historical time sequence data into a fault cause analysis model to obtain an initial fault cause probability set output by different fault cause analysis models;
and determining a final fault cause probability set according to the weights corresponding to the different fault cause analysis models and the initial fault cause probability set.
The initial failure cause probability set may be a set of failure cause probabilities output by each different failure cause analysis model.
In this embodiment, the initial failure cause probability set may be determined by different failure cause analysis models, and then the final failure cause probability set is calculated by means of weighted summation.
In one embodiment, the method for determining weights of the GRU-DNN-Attention model, the decision tree, the random forest and the naive Bayes comprises the following steps:
wherein w is G Is GRU-DNN-Attention model, w max,G Maximum weight, w, of GRU-DNN-Attention network model R Is the weight of random forest, w D Weight of decision tree, w B Is the weight of the naive Bayes method, n is the number of historical time sequence data, and k R Is the weight parameter, k of random forest D K is the weight parameter of the decision tree B Weight parameters, w, are naive Bayes min,R Is the minimum weight of random forest, w min,D Is the minimum weight of the decision tree, w min,B Is of plain natureMinimum weight, w, of the prime Bayes method 0,R Is the initial weight of random forest, w 0,D For initial weights of decision tree, w 0,B Initial weights are naive bayes, σ is the tuning parameter.
In this embodiment, three algorithms, such as decision tree, random forest and naive bayes, are combined with a GRU-DNN-Attention network model to construct an integrated fault cause analysis model, and it should be noted that the integrated learning architecture of the present invention may incorporate other types of algorithms, such as support vector machine, logistic regression, etc., according to actual situations. Fig. 3 is a schematic diagram illustrating offline fault cause classification of an electric power internet of things intelligent terminal according to an embodiment of the present invention. After the weight of each model is determined by the weight determination method, the historical time sequence data can be input into different fault cause analysis models to obtain a fault cause probability set output by each model. And then calculating the occurrence probability of each fault reason through the following formula:
wherein M is the number of fault cause analysis models participating in ensemble learning, P i Probability of occurrence of failure cause, w, output for ith failure cause analysis model i The weights of the model are analyzed for the ith failure cause.
The weight in this embodiment may be dynamically set, and when the data size is sufficient, the classification capability of the GRU-DNN-Attention network model for offline reasons of the intelligent device is higher than that of other methods, so the weight may be dynamically set according to the size of the data size.
The weight determination formula in this embodiment introduces a sigmoid function to limit the weight value between 0 and 1, and introduces a concept of maximum and minimum weights, so that the variation range of the weights can be controlled. Fig. 4 is a schematic diagram of weight change provided by the embodiment of the present invention, as shown in fig. 4, and the trend of the weight value of each method along with the training data is shown in the above weight formula. It can be seen from the graph that the weight values of the methods can be well limited between the maximum weight and the minimum weight, and the change speed of different weights can be controlled through the change of the data quantity. In general, as the historical time series data of training increases, the GRU-DNN-Attention network model weight values are progressively increasing, while the weight values of other methods are progressively decreasing.
Aiming at the problem that the neural network is not well represented in the small data set, the embodiment can propose a generalized integrated learning algorithm based on dynamic weight self-adaption based on the integrated learning idea, and gradually change the classification weights of different algorithm results according to the change of the number of the data sets, thereby avoiding the influence caused by the deterioration of the neural network result under the small data set, and fully playing the accuracy advantage of the neural network in a large number of data sets.
In one embodiment, the method further comprises:
acquiring historical offline state data of different electric power internet-of-things intelligent terminals; determining offline association relations of different electric power Internet of things intelligent terminals according to the historical offline state data; and updating the power failure probability in the failure cause probability set according to the association relation.
The historical offline state data can be offline state data of the electric power internet of things intelligent terminal in historical time, and whether the electric power internet of things intelligent terminal is online or not can be determined according to the historical offline state data. The association relationship may be a relationship that the intelligent terminals of different electric power internet of things are offline, for example, when the device a is offline, if the device B is also offline, the device a and the device B may be considered to have the association relationship.
In this embodiment, the offline association relationship of the different electric power internet of things intelligent terminals can be determined according to the historical offline state data by acquiring the historical offline state data of the different electric power internet of things intelligent terminals, and the power failure probability in the failure cause probability set is updated according to the association relationship. The offline reasons of intelligent equipment such as power failure are difficult to classify through historical time sequence data, but the intelligent equipment can judge manual knowledge relatively conveniently through the online/offline states of other adjacent equipment. Therefore, the embodiment can integrate knowledge into a data driving method, and learn a data-knowledge coupling classification method based on generalized integration.
The embodiment can introduce the pearson correlation coefficient to assist in refining the artificial knowledge, and further correct the power failure probability in the failure cause probability set by using the artificial knowledge so as to further improve the algorithm performance.
In one embodiment, the method for determining the association relationship includes:
wherein v ij The offline association relation of the electric power internet of things intelligent terminal i and j is x k Is the offline state (0 or 1) of the electric power Internet of things intelligent terminal i at the kth time point, y k Is the offline state of the electric power internet of things intelligent terminal j at the kth time point,and->The method is an offline state average value corresponding to the electric power internet of things intelligent terminals i and j. After calculating the correlation coefficient, if the absolute value of the correlation coefficient is larger (approaching 1), the two devices are highly correlated in the off-line condition and possibly powered by the same power supply, otherwise, the two devices are weak in the off-line condition and possibly powered by different power supplies.
Further, the probability that each off-line device is offline because of a power failure can be calculated through the association relation:
wherein P is i (E|O) is the probability that the offline source of the ith offline device is a power failure, Z in When the ith equipment is offline, the online/offline state of the nth equipment is v in For the ith device andthe association relation between the nth equipment can simply obtain the v if the connection condition of the power supply line of each terminal is known in If the power supply line connection condition of each terminal device is unknown, it can be determined by fitting historical data, for example, two devices are always offline at the same time, and the association relationship is weighted greatly.
Furthermore, a power failure probability update formula for knowledge-data fusion can be constructed:
wherein P is E For the probability of equipment offline due to power failure, γ is a weight coefficient for equalizing weight values of a data driving result and a knowledge driving result.
Example two
Fig. 5 is a schematic structural diagram of an offline fault cause classification device for an electric power internet of things intelligent terminal according to a second embodiment of the present invention, where the device may be adapted to a case of analyzing an offline cause of the electric power internet of things intelligent terminal, and the device may be implemented by software and/or hardware and is generally integrated on an electronic device.
As shown in fig. 5, the apparatus includes:
the acquiring module 210 is configured to acquire historical time sequence data of the electric power internet of things intelligent terminal;
the analysis module 220 is configured to input the historical time-series data into a fault cause analysis model to obtain a fault cause probability set, where the fault cause analysis model includes a GRU-DNN-Attention model combined by a gate control circulation unit GRU, a deep neural network DNN, and an Attention mechanism Attention;
and the determining module 230 is configured to determine, according to the probability set of failure causes, a failure cause of the offline electric power internet of things intelligent terminal.
The second embodiment provides an offline fault cause classification device of an electric power internet of things intelligent terminal, which is used for acquiring historical time sequence data of the electric power internet of things intelligent terminal; the analysis module is used for inputting the historical time sequence data into a fault cause analysis model to obtain a fault cause probability set, and the fault cause analysis model comprises a GRU-DNN-Attention model combined by a gating circulation unit GRU, a deep neural network DNN and an Attention mechanism Attention; and the determining module is used for determining the offline fault reason of the electric power Internet of things intelligent terminal according to the fault reason probability set. The GRU-DNN-Attention model is used for determining the offline fault cause probability set of the intelligent terminal of the electric power Internet of things, and determining the offline fault cause of the intelligent terminal of the electric power Internet of things according to the offline fault cause probability set, so that the problem that the offline fault cause of the intelligent terminal cannot be rapidly and accurately determined in the prior art is solved, and the operation and maintenance efficiency of the intelligent terminal of the electric power Internet of things is improved.
Further, the fault cause analysis model further comprises at least one of the following: decision trees, random forests, naive bayes, support vector machines, and logistic regression.
Further, when the failure cause analysis model includes at least two models, the analysis module 220 includes:
inputting the historical time sequence data into a fault cause analysis model to obtain an initial fault cause probability set output by different fault cause analysis models;
and determining a final fault cause probability set according to the weights corresponding to the different fault cause analysis models and the initial fault cause probability set.
Further, the weight determining method of the GRU-DNN-Attention model, the decision tree, the random forest and the naive Bayes comprises the following steps:
wherein w is G Is GRU-DNN-Attention model, w max,G Maximum weight, w, of GRU-DNN-Attention network model R Is the weight of random forest, w D Weight of decision tree, w B Is the weight of the naive Bayes method, n is the number of historical time sequence data, and k R Is the weight parameter, k of random forest D K is the weight parameter of the decision tree B Weight parameters, w, are naive Bayes min,R Is the minimum weight of random forest, w min,D Is the minimum weight of the decision tree, w min,B Minimum weight, w, for naive Bayes method 0,R Is the initial weight of random forest, w 0,D For initial weights of decision tree, w 0,B Initial weights are naive bayes, σ is the tuning parameter.
Further, the historical time sequence data at least comprises: network delay data, ambient temperature, device temperature, CPU utilization and memory utilization; the fault reasons at least comprise: network failure, device hardware failure, device software failure, and power failure.
Further, the device further comprises:
acquiring historical offline state data of different electric power internet-of-things intelligent terminals;
determining offline association relations of different electric power Internet of things intelligent terminals according to the historical offline state data;
and updating the power failure probability in the failure cause probability set according to the association relation.
Further, the method for determining the association relationship includes:
wherein v ij The offline association relation of the electric power internet of things intelligent terminal i and j is x k Is the offline state of the electric power internet of things intelligent terminal i at the kth time point, y k Is the offline state of the electric power internet of things intelligent terminal j at the kth time point,and->Is offline corresponding to the electric power internet of things intelligent terminals i and jAnd (5) a state average value.
The offline fault reason classification device of the electric power internet of things intelligent terminal can execute the offline fault reason classification method of the electric power internet of things intelligent terminal provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
Example III
Fig. 6 shows a schematic diagram of the structure of an electronic device 10 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 6, the electronic device 10 includes at least one processor 11, and a memory, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, etc., communicatively connected to the at least one processor 11, in which the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 may also be stored. The processor 11, the ROM 12 and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.
Various components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, etc.; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as the offline fault cause classification method of the electric power internet of things intelligent terminal.
In some embodiments, the offline fault cause classification method of the power thing intelligent terminal may be implemented as a computer program, which is tangibly embodied on a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the offline fault cause classification method of the power-on-demand intelligent terminal described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the offline fault cause classification method of the power thing intelligent terminal in any other suitable manner (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. An offline fault cause classification method of an electric power internet of things intelligent terminal is characterized by comprising the following steps:
acquiring historical time sequence data of the electric power internet of things intelligent terminal;
inputting the historical time sequence data into a fault cause analysis model to obtain a fault cause probability set, wherein the fault cause analysis model comprises a GRU-DNN-Attention model combined by a gating circulation unit GRU, a deep neural network DNN and an Attention mechanism Attention;
and determining the offline fault reason of the electric power Internet of things intelligent terminal according to the fault reason probability set.
2. The method of claim 1, wherein the fault cause analysis model further comprises at least one of: decision trees, random forests, naive bayes, support vector machines, and logistic regression.
3. The method of claim 2, wherein when the failure cause analysis model includes at least two models, inputting the historical time series data into the failure cause analysis model results in a failure cause probability set, comprising:
inputting the historical time sequence data into a fault cause analysis model to obtain an initial fault cause probability set output by different fault cause analysis models;
and determining a final fault cause probability set according to the weights corresponding to the different fault cause analysis models and the initial fault cause probability set.
4. A method according to claim 2 or 3, characterized in that the weight determination method of the GRU-DNN-Attention model, decision tree, random forest and naive bayes comprises:
wherein w is G Is GRU-DNN-Attention model, w max,G Maximum weight, w, of GRU-DNN-Attention network model R Is the weight of random forest, w D Weight of decision tree, w B Is the weight of the naive Bayes method, n is the number of historical time sequence data, and k R Is the weight parameter, k of random forest D K is the weight parameter of the decision tree B Weight parameters, w, are naive Bayes min,R Is the minimum weight of random forest, w min,D Is the minimum weight of the decision tree, w min,B Minimum weight, w, for naive Bayes method 0,R Is the initial weight of random forest, w 0,D For initial weights of decision tree, w 0,B Initial weights are naive bayes, σ is the tuning parameter.
5. The method of claim 1, wherein the historical timing data comprises at least: network delay data, ambient temperature, device temperature, CPU utilization and memory utilization; the fault reasons at least comprise: network failure, device hardware failure, device software failure, and power failure.
6. The method according to claim 1, wherein the method further comprises:
acquiring historical offline state data of different electric power internet-of-things intelligent terminals;
determining offline association relations of different electric power Internet of things intelligent terminals according to the historical offline state data;
and updating the power failure probability in the failure cause probability set according to the association relation.
7. The method according to claim 6, wherein the method for determining the association relation comprises:
wherein v ij The offline association relation of the electric power internet of things intelligent terminal i and j is x k Is the offline state of the electric power internet of things intelligent terminal i at the kth time point, y k Is the offline state of the electric power internet of things intelligent terminal j at the kth time point,and->The method is an offline state average value corresponding to the electric power internet of things intelligent terminals i and j.
8. An offline fault reason classification device of an electric power internet of things intelligent terminal, which is characterized in that the device comprises:
the acquisition module is used for acquiring historical time sequence data of the electric power internet of things intelligent terminal;
the analysis module is used for inputting the historical time sequence data into a fault cause analysis model to obtain a fault cause probability set, and the fault cause analysis model comprises a GRU-DNN-Attention model combined by a gating circulation unit GRU, a deep neural network DNN and an Attention mechanism Attention;
and the determining module is used for determining the offline fault reason of the electric power Internet of things intelligent terminal according to the fault reason probability set.
9. An electronic device, the device comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of offline fault cause classification for an electric power internet of things intelligent terminal of any one of claims 1-7.
10. A computer readable storage medium, wherein the computer readable storage medium stores computer instructions for causing a processor to implement the offline fault cause classification method of the electric power internet of things intelligent terminal according to any one of claims 1-7 when executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311271792.1A CN117349747A (en) | 2023-09-27 | 2023-09-27 | Offline fault reason classification method for electric power Internet of things intelligent terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311271792.1A CN117349747A (en) | 2023-09-27 | 2023-09-27 | Offline fault reason classification method for electric power Internet of things intelligent terminal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117349747A true CN117349747A (en) | 2024-01-05 |
Family
ID=89355129
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311271792.1A Pending CN117349747A (en) | 2023-09-27 | 2023-09-27 | Offline fault reason classification method for electric power Internet of things intelligent terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117349747A (en) |
-
2023
- 2023-09-27 CN CN202311271792.1A patent/CN117349747A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114265979B (en) | Method for determining fusion parameters, information recommendation method and model training method | |
| CN115221795A (en) | Training method, prediction method, device, equipment and medium of capacity prediction model | |
| CN114494776A (en) | Model training method, device, equipment and storage medium | |
| CN113657538A (en) | Model training method, data classification method, device, equipment, storage medium and product | |
| CN117474091A (en) | Knowledge graph construction method, device, equipment and storage medium | |
| CN113379153A (en) | Method for predicting power load, prediction model training method and device | |
| CN113420792A (en) | Training method of image model, electronic equipment, road side equipment and cloud control platform | |
| CN116755974A (en) | Cloud computing platform operation and maintenance method and device, electronic equipment and storage medium | |
| CN116975081A (en) | Log diagnosis set updating method, device, equipment and storage medium | |
| CN117273450A (en) | Power system risk assessment method, device, equipment and storage medium | |
| CN113612777B (en) | Training method, flow classification method, device, electronic equipment and storage medium | |
| CN117349747A (en) | Offline fault reason classification method for electric power Internet of things intelligent terminal | |
| CN115600607A (en) | Log detection method and device, electronic equipment and medium | |
| CN114819095A (en) | Method and device for generating business data processing model and electronic equipment | |
| CN114565105A (en) | Data processing method and deep learning model training method and device | |
| CN117010947B (en) | NPS investigation method, device, equipment and storage medium based on business activity | |
| CN114331379B (en) | Method for outputting task to be handled, model training method and device | |
| CN115512188A (en) | Multi-target detection method, device, equipment and medium | |
| CN116302538A (en) | Yun Bianduan coordinated resource management method, device, equipment and medium | |
| CN117592618A (en) | Active user prediction method, device, server and storage medium | |
| CN117195120A (en) | Detection method, detection device, detection equipment and storage medium | |
| CN117216633A (en) | Parameter analysis model training and parameter analysis method, device, equipment and medium | |
| CN118014018A (en) | Building energy consumption prediction method, device, equipment and storage medium | |
| CN117194018A (en) | Processing method and device of system temperature control algorithm in multi-core and multi-chip environment | |
| CN116594708A (en) | Method, device, equipment and medium for generating multi-model loading configuration file |
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 |