CN117952252A - Intelligent scheduling early warning method and system for hardware processing - Google Patents
Intelligent scheduling early warning method and system for hardware processing Download PDFInfo
- Publication number
- CN117952252A CN117952252A CN202410015590.9A CN202410015590A CN117952252A CN 117952252 A CN117952252 A CN 117952252A CN 202410015590 A CN202410015590 A CN 202410015590A CN 117952252 A CN117952252 A CN 117952252A
- Authority
- CN
- China
- Prior art keywords
- fault
- activity data
- operation activity
- network
- fault analysis
- 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 32
- 238000004458 analytical method Methods 0.000 claims abstract description 151
- 230000000694 effects Effects 0.000 claims abstract description 128
- 238000004519 manufacturing process Methods 0.000 claims abstract description 119
- 230000002159 abnormal effect Effects 0.000 claims abstract description 59
- 238000005457 optimization Methods 0.000 claims abstract description 15
- 230000006870 function Effects 0.000 claims description 40
- 238000012795 verification Methods 0.000 claims description 18
- 238000004891 communication Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 6
- 238000002372 labelling Methods 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 4
- 230000001939 inductive effect Effects 0.000 claims description 2
- 230000002265 prevention Effects 0.000 abstract description 3
- 238000003860 storage Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 5
- 230000005856 abnormality Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000014759 maintenance of location Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06316—Sequencing of tasks or work
-
- 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
- G06Q50/04—Manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Manufacturing & Machinery (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Educational Administration (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- General Factory Administration (AREA)
Abstract
The embodiment of the invention provides an intelligent scheduling early warning method and system for hardware processing, which are used for acquiring target scheduling operation activity data to be analyzed and extracting abnormal scheduling operation activity data from the target scheduling operation activity data through an abnormal prediction network for knowledge learning. And analyzing the abnormal production operation activity data by using a fault analysis network subjected to knowledge learning to generate a fault analysis result. If the fault analysis result is based on the fault in the hardware processing production process, the early warning information is induced. When the network iterative optimization requirement is met, the fault analysis network is subjected to iterative optimization by using the target production scheduling operation activity data with faults, and the re-extracted target production scheduling operation activity data is analyzed according to the optimized fault analysis network. Therefore, abnormal conditions in the production process of the hardware processing equipment can be timely and accurately detected and analyzed, and powerful support is provided for effective fault treatment and prevention.
Description
Technical Field
The invention relates to the technical field of hardware processing, in particular to an intelligent scheduling early warning method and system for hardware processing.
Background
In the hardware processing production process, the production scheduling operation activity data of the equipment is an important decision reference basis. However, due to the complex and variable production environment, production operation activity data may be abnormal, and these abnormalities may cause production failure, affecting production efficiency and product quality.
Traditional fault detection and analysis methods rely primarily on human experience or simple data statistics, which presents a number of problems for processing large-scale, high-dimensional production run-time data. For example, the detection and analysis precision of abnormal data is not high, and production faults can not be found and processed timely and accurately; the processing mode of the abnormal data is single, and corresponding processing measures cannot be adopted according to different types of abnormal data.
Disclosure of Invention
In view of the above, an object of the embodiments of the present invention is to provide an intelligent scheduling early warning method and system for hardware processing, firstly, obtain target scheduling operation activity data to be analyzed, and extract abnormal scheduling operation activity data from the target scheduling operation activity data through an abnormal prediction network that has undergone knowledge learning. And then, analyzing the abnormal production operation activity data by using a fault analysis network subjected to knowledge learning to generate a fault analysis result. If the fault analysis result is based on the fault in the hardware processing production process, the early warning information is induced. When the network iterative optimization requirement is met, the fault analysis network is subjected to iterative optimization by using the target production scheduling operation activity data with faults, and the re-extracted target production scheduling operation activity data is analyzed according to the optimized fault analysis network. Therefore, abnormal conditions in the production process of the hardware processing equipment can be timely and accurately detected and analyzed, and powerful support is provided for effective fault treatment and prevention.
According to an aspect of the embodiment of the invention, an intelligent scheduling early warning method and system for hardware processing are provided, and the method comprises the following steps:
Acquiring target scheduling operation activity data to be analyzed;
The abnormal prediction network based on knowledge learning extracts abnormal production operation activity data from the target production operation activity data;
analyzing the abnormal production operation activity data based on the fault analysis network after knowledge learning to generate a fault analysis result;
when the fault analysis result is based on the fault in the hardware processing production process, the early warning information is induced;
When the network iterative optimization requirement is met, iteratively optimizing the fault analysis network based on the target production scheduling operation activity data with faults, and analyzing the re-extracted target production scheduling operation activity data based on the iteratively optimized fault analysis network.
In an alternative embodiment, the knowledge-learned fault analysis network includes:
A fault prediction network and a fault root cause positioning network;
The fault analysis network after knowledge learning analyzes the abnormal production operation activity data to generate a fault analysis result, which comprises the following steps:
loading the abnormal production operation activity data into the fault prediction network for analysis, and generating target fault prediction data analyzed from the abnormal production operation activity data;
And carrying out fault root positioning on the target fault prediction data based on the fault root positioning network, and determining a fault analysis result corresponding to the corresponding target production scheduling operation activity data based on the fault root positioning result.
In an alternative embodiment, the target production scheduling operational activity data is a plurality of; when it is determined that a fault exists in the hardware processing production process based on the fault analysis result, the pre-warning information is induced, including:
clustering the corresponding target production operation activity data based on the fault analysis result to obtain a clustering result;
Performing fault analysis on the corresponding hardware processing production process based on the clustering result;
When the fault exists in the hardware processing production process, the early warning information is induced, and the target production scheduling operation activity data with the fault and the corresponding fault analysis result are recorded;
And the recorded target production operation activity data and the corresponding fault analysis result are used for iteratively optimizing the fault analysis network.
In an alternative embodiment, the fault analysis network is obtained by knowledge learning based on a cloud computing system; a step of configuring the failure analysis network based on the cloud computing system, comprising:
acquiring a sample scheduling operation activity data sequence based on the cloud computing system; the sample scheduling operation activity data sequence comprises sample abnormal scheduling operation activity data and corresponding fault marking data, wherein the sample abnormal scheduling operation activity data and the corresponding fault marking data are extracted from sample scheduling operation activity data;
based on the cloud computing system, the example abnormal scheduling operation activity data is used as loading characteristics, corresponding fault labeling data is used as an expected output result, knowledge learning is conducted on the fault analysis network of the initialization weight parameters, and the fault analysis network after knowledge learning is generated.
In an alternative embodiment, the step of configuring the fault analysis network for initializing the weight parameter includes:
acquiring a numerical value interval corresponding to each function weight to be determined based on the cloud computing system, and determining a plurality of function weight sequences based on the numerical value interval;
Acquiring a target network learning data sequence and a verification network learning data sequence based on the cloud computing system, and performing knowledge learning based on the target network learning data sequence according to each function weight sequence to generate a corresponding reference fault analysis network;
And verifying the reference fault analysis network based on the verification network learning data sequence based on the cloud computing system, selecting an objective function weight sequence from the function weight sequences based on a verification result, and initializing the fault analysis network based on the objective function weight sequence to obtain an initialization weight parameter.
According to another aspect of the embodiment of the invention, an intelligent scheduling and early warning method and system for hardware processing are provided, wherein the system comprises:
The acquisition module is used for acquiring target production scheduling operation activity data to be analyzed;
The analysis module is used for extracting abnormal production operation activity data from the target production operation activity data based on the abnormal prediction network after knowledge learning;
The analysis module is also used for analyzing the abnormal production operation activity data based on the fault analysis network after knowledge learning to generate a fault analysis result;
The early warning module is used for inducing early warning information when the fault exists in the hardware processing production process based on the fault analysis result;
And the optimization module is used for iteratively optimizing the fault analysis network based on the target production operation activity data with faults when the network iteration optimization requirement is met, and analyzing the re-extracted target production operation activity data based on the iteratively optimized fault analysis network.
In an alternative embodiment, the system further comprises:
The target production scheduling operation activity data is multiple;
the optimizing module is further used for clustering fault analysis results corresponding to the target production scheduling operation activity data to obtain clustering results;
Performing fault analysis on the corresponding hardware processing production process based on the clustering result;
When the fault exists in the hardware processing production process, the early warning information is induced, and the target production scheduling operation activity data with the fault and the corresponding fault analysis result are recorded;
And the recorded target production operation activity data and the corresponding fault analysis result are used for iteratively optimizing the fault analysis network.
In an alternative embodiment, the system further comprises:
the fault analysis network is obtained by knowledge learning based on a cloud computing system; configuring the failure analysis network based on the cloud computing system, comprising:
acquiring a sample scheduling operation activity data sequence based on the cloud computing system; the sample scheduling operation activity data sequence comprises sample abnormal scheduling operation activity data and corresponding fault marking data, wherein the sample abnormal scheduling operation activity data and the corresponding fault marking data are extracted from sample scheduling operation activity data;
based on the cloud computing system, the example abnormal scheduling operation activity data is used as loading characteristics, corresponding fault labeling data is used as an expected output result, knowledge learning is conducted on the fault analysis network of the initialization weight parameters, and the fault analysis network after knowledge learning is generated.
In an alternative embodiment, the system further comprises:
The configuration process of the fault analysis network for initializing the weight parameters comprises the following steps:
acquiring a numerical value interval corresponding to each function weight to be determined based on the cloud computing system, and determining a plurality of function weight sequences based on the numerical value interval;
Acquiring a target network learning data sequence and a verification network learning data sequence based on the cloud computing system, and performing knowledge learning based on the target network learning data sequence according to each function weight sequence to generate a corresponding reference fault analysis network;
And verifying the reference fault analysis network based on the verification network learning data sequence based on the cloud computing system, selecting an objective function weight sequence from the function weight sequences based on a verification result, and initializing the fault analysis network based on the objective function weight sequence to obtain an initialization weight parameter.
According to another aspect of an embodiment of the present invention, there is provided a server including: the device comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus; the memory is used for storing a computer program; and the processor is used for realizing the steps of the intelligent production scheduling early warning method for hardware processing according to any one of the above steps when executing the computer program.
According to another aspect of the embodiments of the present invention, there is provided a readable storage medium having a computer program stored thereon, the computer program, when executed by a processor, performing the steps of the above-described intelligent production scheduling method for hardware processing.
The foregoing objects, features and advantages of embodiments of the invention will be more readily apparent from the following detailed description of the embodiments taken in conjunction with the accompanying drawings.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 shows a schematic diagram of components of a server provided by an embodiment of the present invention;
Fig. 2 shows a flow diagram of an intelligent scheduling early warning method for hardware processing according to an embodiment of the present invention;
Fig. 3 is a functional block diagram of an intelligent scheduling early warning system according to hardware processing according to an embodiment of the present invention.
Detailed Description
In order to enable those skilled in the art to better understand the present invention, a technical solution of the present embodiment of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiment of the present invention, and it is apparent that the described embodiment is only a part of the embodiment of the present invention, not all the embodiments. All other embodiments, which can be made by those skilled in the art, in light of the embodiments of the present invention without undue burden are within the scope of the present invention.
The terms first, second, third and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar elements 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, for example, 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.
Fig. 1 shows an exemplary component diagram of a server 100. The server 100 may include one or more processors 104, such as one or more Central Processing Units (CPUs), each of which may implement one or more hardware threads. The server 100 may also include any storage medium 106 for storing any kind of information such as code, settings, data, etc. For example, and without limitation, storage medium 106 may include any one or more of the following combinations: any type of RAM, any type of ROM, flash memory devices, hard disks, optical disks, etc. More generally, any storage medium may store information using any technique. Further, any storage medium may provide volatile or non-volatile retention of information. Further, any storage medium may represent fixed or removable components of server 100. In one case, the server 100 may perform any of the operations of the associated instructions when the processor 104 executes the associated instructions stored in any storage medium or combination of storage media. The server 100 also includes one or more drive units 108, such as a hard disk drive unit, an optical disk drive unit, etc., for interacting with any storage media.
The server 100 also includes input/output 110 (I/O) for receiving various inputs (via input unit 112) and for providing various outputs (via output unit 114). One particular output mechanism may include a presentation device 116 and an associated Graphical User Interface (GUI) 118. The server 100 may also include one or more network interfaces 120 for exchanging data with other devices via one or more communication units 122. One or more communication buses 124 couple the components described above together.
The communication unit 122 may be implemented in any manner, for example, via a local area network, a wide area network (e.g., the internet), a point-to-point connection, etc., or any combination thereof. The communication unit 122 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers 100, etc., governed by any protocol or combination of protocols.
Fig. 2 is a schematic flow chart of an intelligent scheduling and early-warning method and system for hardware processing, which are provided in an embodiment of the present invention, and the intelligent scheduling and early-warning method and system for hardware processing may be executed by the server 100 shown in fig. 1, and detailed steps of the intelligent scheduling and early-warning method for hardware processing are described as follows.
Step S110, acquiring target production scheduling operation activity data to be analyzed;
step S120, extracting abnormal production operation activity data from the target production operation activity data based on the abnormality prediction network after knowledge learning;
step S120, analyzing the abnormal production operation activity data based on the fault analysis network after knowledge learning to generate a fault analysis result;
Step S130, when the fault analysis result is based on the fault in the hardware processing production process, the early warning information is induced;
And step S140, when the network iterative optimization requirement is met, iteratively optimizing the fault analysis network based on the target production operation activity data with faults, and analyzing the re-extracted target production operation activity data based on the iteratively optimized fault analysis network.
Based on the above steps, the present embodiment first obtains target production run activity data to be analyzed, and extracts abnormal production run activity data from the target production run activity data through an abnormal prediction network that has performed knowledge learning. And then, analyzing the abnormal production operation activity data by using a fault analysis network subjected to knowledge learning to generate a fault analysis result. If the fault analysis result is based on the fault in the hardware processing production process, the early warning information is induced. When the network iterative optimization requirement is met, the fault analysis network is subjected to iterative optimization by using the target production scheduling operation activity data with faults, and the re-extracted target production scheduling operation activity data is analyzed according to the optimized fault analysis network. Therefore, abnormal conditions in the production process of the hardware processing equipment can be timely and accurately detected and analyzed, and powerful support is provided for effective fault treatment and prevention.
In an alternative embodiment, the knowledge-learned fault analysis network includes:
A fault prediction network and a fault root cause positioning network;
The fault analysis network after knowledge learning analyzes the abnormal production operation activity data to generate a fault analysis result, which comprises the following steps:
loading the abnormal production operation activity data into the fault prediction network for analysis, and generating target fault prediction data analyzed from the abnormal production operation activity data;
And carrying out fault root positioning on the target fault prediction data based on the fault root positioning network, and determining a fault analysis result corresponding to the corresponding target production scheduling operation activity data based on the fault root positioning result.
In an alternative embodiment, the target production scheduling operational activity data is a plurality of; when it is determined that a fault exists in the hardware processing production process based on the fault analysis result, the pre-warning information is induced, including:
clustering the corresponding target production operation activity data based on the fault analysis result to obtain a clustering result;
Performing fault analysis on the corresponding hardware processing production process based on the clustering result;
When the fault exists in the hardware processing production process, the early warning information is induced, and the target production scheduling operation activity data with the fault and the corresponding fault analysis result are recorded;
And the recorded target production operation activity data and the corresponding fault analysis result are used for iteratively optimizing the fault analysis network.
In an alternative embodiment, the fault analysis network is obtained by knowledge learning based on a cloud computing system; a step of configuring the failure analysis network based on the cloud computing system, comprising:
acquiring a sample scheduling operation activity data sequence based on the cloud computing system; the sample scheduling operation activity data sequence comprises sample abnormal scheduling operation activity data and corresponding fault marking data, wherein the sample abnormal scheduling operation activity data and the corresponding fault marking data are extracted from sample scheduling operation activity data;
based on the cloud computing system, the example abnormal scheduling operation activity data is used as loading characteristics, corresponding fault labeling data is used as an expected output result, knowledge learning is conducted on the fault analysis network of the initialization weight parameters, and the fault analysis network after knowledge learning is generated.
In an alternative embodiment, the step of configuring the fault analysis network for initializing the weight parameter includes:
acquiring a numerical value interval corresponding to each function weight to be determined based on the cloud computing system, and determining a plurality of function weight sequences based on the numerical value interval;
Acquiring a target network learning data sequence and a verification network learning data sequence based on the cloud computing system, and performing knowledge learning based on the target network learning data sequence according to each function weight sequence to generate a corresponding reference fault analysis network;
And verifying the reference fault analysis network based on the verification network learning data sequence based on the cloud computing system, selecting an objective function weight sequence from the function weight sequences based on a verification result, and initializing the fault analysis network based on the objective function weight sequence to obtain an initialization weight parameter.
Fig. 3 shows a functional block diagram of an intelligent production scheduling and early warning system 200 according to an embodiment of the present invention, where functions implemented by the intelligent production scheduling and early warning system 200 according to hardware processing may correspond to steps executed by the above-described method. The intelligent scheduling and early warning system 200 according to hardware processing can be understood as the server 100, or the processor of the server 100, or can be understood as a component which is independent from the server 100 or the processor and is controlled by the server 100 to implement the functions of the present invention, as shown in fig. 3, and the functions of each functional module of the intelligent scheduling and early warning system 200 according to hardware processing are described in detail below.
An acquisition module 210, configured to acquire target production scheduling operation activity data to be analyzed;
An analysis module 220, configured to extract abnormal production operation activity data from the target production operation activity data based on the abnormality prediction network after knowledge learning;
The analysis module 220 is further configured to analyze the abnormal production operation activity data based on the fault analysis network after knowledge learning, and generate a fault analysis result;
The early warning module 230 is configured to induce early warning information when it is determined that a fault exists in the hardware processing production process based on the fault analysis result;
and the optimization module 240 is configured to iteratively optimize the failure analysis network based on the target production operation activity data with the failure when the network iteration optimization requirement is met, and analyze the re-extracted target production operation activity data based on the iteratively optimized failure analysis network.
In an alternative embodiment, the optimizing module 240 is further configured to:
The target production scheduling operation activity data is multiple;
The optimizing module 240 is further configured to cluster the fault analysis results corresponding to the target production scheduling operation activity data to obtain a clustered result;
Performing fault analysis on the corresponding hardware processing production process based on the clustering result;
When the fault exists in the hardware processing production process, the early warning information is induced, and the target production scheduling operation activity data with the fault and the corresponding fault analysis result are recorded;
And the recorded target production operation activity data and the corresponding fault analysis result are used for iteratively optimizing the fault analysis network.
In an alternative embodiment, the analysis module 220 is further configured to:
the fault analysis network is obtained by knowledge learning based on a cloud computing system; configuring the failure analysis network based on the cloud computing system, comprising:
acquiring a sample scheduling operation activity data sequence based on the cloud computing system; the sample scheduling operation activity data sequence comprises sample abnormal scheduling operation activity data and corresponding fault marking data, wherein the sample abnormal scheduling operation activity data and the corresponding fault marking data are extracted from sample scheduling operation activity data;
based on the cloud computing system, the example abnormal scheduling operation activity data is used as loading characteristics, corresponding fault labeling data is used as an expected output result, knowledge learning is conducted on the fault analysis network of the initialization weight parameters, and the fault analysis network after knowledge learning is generated.
In an alternative embodiment, the analysis module 220 is further configured to:
The configuration process of the fault analysis network for initializing the weight parameters comprises the following steps:
acquiring a numerical value interval corresponding to each function weight to be determined based on the cloud computing system, and determining a plurality of function weight sequences based on the numerical value interval;
Acquiring a target network learning data sequence and a verification network learning data sequence based on the cloud computing system, and performing knowledge learning based on the target network learning data sequence according to each function weight sequence to generate a corresponding reference fault analysis network;
And verifying the reference fault analysis network based on the verification network learning data sequence based on the cloud computing system, selecting an objective function weight sequence from the function weight sequences based on a verification result, and initializing the fault analysis network based on the objective function weight sequence to obtain an initialization weight parameter.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.
Claims (10)
1. An intelligent scheduling early warning method for hardware processing is characterized by comprising the following steps:
Acquiring target scheduling operation activity data to be analyzed;
The abnormal prediction network based on knowledge learning extracts abnormal production operation activity data from the target production operation activity data;
analyzing the abnormal production operation activity data based on the fault analysis network after knowledge learning to generate a fault analysis result;
when the fault analysis result is based on the fault in the hardware processing production process, the early warning information is induced;
When the network iterative optimization requirement is met, iteratively optimizing the fault analysis network based on the target production scheduling operation activity data with faults, and analyzing the re-extracted target production scheduling operation activity data based on the iteratively optimized fault analysis network.
2. The intelligent scheduling and early warning method for hardware processing according to claim 1, wherein the knowledge-learned fault analysis network comprises:
A fault prediction network and a fault root cause positioning network;
The fault analysis network after knowledge learning analyzes the abnormal production operation activity data to generate a fault analysis result, which comprises the following steps:
loading the abnormal production operation activity data into the fault prediction network for analysis, and generating target fault prediction data analyzed from the abnormal production operation activity data;
And carrying out fault root positioning on the target fault prediction data based on the fault root positioning network, and determining a fault analysis result corresponding to the corresponding target production scheduling operation activity data based on the fault root positioning result.
3. The intelligent scheduling and early warning method for hardware processing according to claim 1, wherein the target scheduling and operation activity data is a plurality of; when it is determined that a fault exists in the hardware processing production process based on the fault analysis result, the pre-warning information is induced, including:
clustering the corresponding target production operation activity data based on the fault analysis result to obtain a clustering result;
Performing fault analysis on the corresponding hardware processing production process based on the clustering result;
When the fault exists in the hardware processing production process, the early warning information is induced, and the target production scheduling operation activity data with the fault and the corresponding fault analysis result are recorded;
And the recorded target production operation activity data and the corresponding fault analysis result are used for iteratively optimizing the fault analysis network.
4. The intelligent scheduling early warning method for hardware processing according to claim 1, wherein the fault analysis network is obtained by knowledge learning based on a cloud computing system; a step of configuring the failure analysis network based on the cloud computing system, comprising:
acquiring a sample scheduling operation activity data sequence based on the cloud computing system; the sample scheduling operation activity data sequence comprises sample abnormal scheduling operation activity data and corresponding fault marking data, wherein the sample abnormal scheduling operation activity data and the corresponding fault marking data are extracted from sample scheduling operation activity data;
based on the cloud computing system, the example abnormal scheduling operation activity data is used as loading characteristics, corresponding fault labeling data is used as an expected output result, knowledge learning is conducted on the fault analysis network of the initialization weight parameters, and the fault analysis network after knowledge learning is generated.
5. The intelligent scheduling and early warning method for hardware processing according to claim 4, wherein the step of configuring the fault analysis network for initializing the weight parameters comprises the steps of:
acquiring a numerical value interval corresponding to each function weight to be determined based on the cloud computing system, and determining a plurality of function weight sequences based on the numerical value interval;
Acquiring a target network learning data sequence and a verification network learning data sequence based on the cloud computing system, and performing knowledge learning based on the target network learning data sequence according to each function weight sequence to generate a corresponding reference fault analysis network;
And verifying the reference fault analysis network based on the verification network learning data sequence based on the cloud computing system, selecting an objective function weight sequence from the function weight sequences based on a verification result, and initializing the fault analysis network based on the objective function weight sequence to obtain an initialization weight parameter.
6. An intelligent scheduling early warning system for hardware processing, which is characterized in that the device comprises:
The acquisition module is used for acquiring target production scheduling operation activity data to be analyzed;
The analysis module is used for extracting abnormal production operation activity data from the target production operation activity data based on the abnormal prediction network after knowledge learning;
The analysis module is also used for analyzing the abnormal production operation activity data based on the fault analysis network after knowledge learning to generate a fault analysis result;
The early warning module is used for inducing early warning information when the fault exists in the hardware processing production process based on the fault analysis result;
And the optimization module is used for iteratively optimizing the fault analysis network based on the target production operation activity data with faults when the network iteration optimization requirement is met, and analyzing the re-extracted target production operation activity data based on the iteratively optimized fault analysis network.
7. The intelligent scheduling and early warning system for hardware processing according to claim 6, wherein the target scheduling and operation activity data is a plurality of;
the optimizing module is further used for clustering fault analysis results corresponding to the target production scheduling operation activity data to obtain clustering results;
Performing fault analysis on the corresponding hardware processing production process based on the clustering result;
When the fault exists in the hardware processing production process, the early warning information is induced, and the target production scheduling operation activity data with the fault and the corresponding fault analysis result are recorded;
And the recorded target production operation activity data and the corresponding fault analysis result are used for iteratively optimizing the fault analysis network.
8. The intelligent scheduling early warning system for hardware processing according to claim 6, wherein the fault analysis network is obtained by knowledge learning based on a cloud computing system; configuring the failure analysis network based on the cloud computing system, comprising:
acquiring a sample scheduling operation activity data sequence based on the cloud computing system; the sample scheduling operation activity data sequence comprises sample abnormal scheduling operation activity data and corresponding fault marking data, wherein the sample abnormal scheduling operation activity data and the corresponding fault marking data are extracted from sample scheduling operation activity data;
based on the cloud computing system, the example abnormal scheduling operation activity data is used as loading characteristics, corresponding fault labeling data is used as an expected output result, knowledge learning is conducted on the fault analysis network of the initialization weight parameters, and the fault analysis network after knowledge learning is generated.
9. The intelligent scheduling and early warning system for hardware processing according to claim 8, wherein the configuration process of the fault analysis network for initializing the weight parameters comprises:
acquiring a numerical value interval corresponding to each function weight to be determined based on the cloud computing system, and determining a plurality of function weight sequences based on the numerical value interval;
Acquiring a target network learning data sequence and a verification network learning data sequence based on the cloud computing system, and performing knowledge learning based on the target network learning data sequence according to each function weight sequence to generate a corresponding reference fault analysis network;
And verifying the reference fault analysis network based on the verification network learning data sequence based on the cloud computing system, selecting an objective function weight sequence from the function weight sequences based on a verification result, and initializing the fault analysis network based on the objective function weight sequence to obtain an initialization weight parameter.
10. A server, comprising:
The device comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;
the memory is used for storing a computer program;
The processor is configured to implement the steps of the intelligent scheduling and early warning method for hardware processing according to any one of claims 1 to 5 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410015590.9A CN117952252A (en) | 2024-01-05 | 2024-01-05 | Intelligent scheduling early warning method and system for hardware processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410015590.9A CN117952252A (en) | 2024-01-05 | 2024-01-05 | Intelligent scheduling early warning method and system for hardware processing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117952252A true CN117952252A (en) | 2024-04-30 |
Family
ID=90801203
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410015590.9A Pending CN117952252A (en) | 2024-01-05 | 2024-01-05 | Intelligent scheduling early warning method and system for hardware processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117952252A (en) |
-
2024
- 2024-01-05 CN CN202410015590.9A patent/CN117952252A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10452510B2 (en) | Hybrid clustering-partitioning techniques that optimizes accuracy and compute cost for prognostic surveillance of sensor data | |
| US11397633B2 (en) | Unifying semi-supervised approach for machine condition monitoring and fault diagnosis | |
| US11294754B2 (en) | System and method for contextual event sequence analysis | |
| US20170060546A1 (en) | System and method for providing software build violation detection and self-healing | |
| CN105488539B (en) | The predictor method and device of the generation method and device of disaggregated model, power system capacity | |
| JP6828807B2 (en) | Data analysis device, data analysis method and data analysis program | |
| CN106201757A (en) | A kind of abnormality eliminating method and device | |
| CN117729119A (en) | Equipment operation data processing method and system for edge computing gateway | |
| CN116975938B (en) | Sensor data processing method in product manufacturing process | |
| CN117952252A (en) | Intelligent scheduling early warning method and system for hardware processing | |
| CN117033053A (en) | Data analysis method and system applied to automobile marketing management system software | |
| CN111948967B (en) | Power data acquisition method and system based on big data | |
| CN113298622A (en) | Method and system for processing e-commerce business orders based on machine learning | |
| CN117033052B (en) | Object abnormality diagnosis method and system based on model identification | |
| CN114245895A (en) | Method for generating consistent representation for at least two log files | |
| CN117272207A (en) | Data center anomaly analysis method and system | |
| CN117077809A (en) | Abnormal data analysis method and system based on wind control decision and visualization | |
| CN114474150B (en) | Stability test method and system for seven-axis robot | |
| CN117031421B (en) | Anomaly analysis method and system of radar signal simulation system | |
| CN117216701B (en) | Intelligent bridge monitoring and early warning method and system | |
| CN113905407B (en) | Terminal equipment monitoring information acquisition method and system in distributed wireless networking | |
| CN116926241B (en) | Immune cell culture control method and system | |
| CN117519034A (en) | Abnormality monitoring method and system applied to corrugated board production control system | |
| CN117541024A (en) | Hardware processing equipment scheduling optimization method and system | |
| CN116956196A (en) | Abnormal signal detection method and system |
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 |