CN117271534B - Spectrum detection method and system for automobile parts - Google Patents
Spectrum detection method and system for automobile parts Download PDFInfo
- Publication number
- CN117271534B CN117271534B CN202311567243.9A CN202311567243A CN117271534B CN 117271534 B CN117271534 B CN 117271534B CN 202311567243 A CN202311567243 A CN 202311567243A CN 117271534 B CN117271534 B CN 117271534B
- Authority
- CN
- China
- Prior art keywords
- data
- nodes
- spectrum
- spectrum data
- distributed architecture
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001228 spectrum Methods 0.000 title claims abstract description 170
- 238000001514 detection method Methods 0.000 title claims abstract description 118
- 238000000034 method Methods 0.000 claims abstract description 36
- 230000007547 defect Effects 0.000 claims abstract description 28
- 238000012545 processing Methods 0.000 claims abstract description 27
- 238000004519 manufacturing process Methods 0.000 claims description 30
- 230000003595 spectral effect Effects 0.000 claims description 19
- 238000007781 pre-processing Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 12
- 238000004806 packaging method and process Methods 0.000 claims description 11
- 230000007246 mechanism Effects 0.000 claims description 8
- 238000010183 spectrum analysis Methods 0.000 claims description 7
- 238000007619 statistical method Methods 0.000 claims description 7
- 238000012546 transfer Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 4
- 230000003287 optical effect Effects 0.000 abstract description 6
- 230000002950 deficient Effects 0.000 description 12
- 238000010586 diagram Methods 0.000 description 10
- 238000012552 review Methods 0.000 description 5
- 239000011248 coating agent Substances 0.000 description 4
- 238000000576 coating method Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000005538 encapsulation Methods 0.000 description 1
- 230000001121 heart beat frequency Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000007847 structural defect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/22—Indexing; Data structures therefor; Storage structures
- G06F16/2228—Indexing structures
- G06F16/2255—Hash tables
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Software Systems (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Databases & Information Systems (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- General Factory Administration (AREA)
Abstract
The invention is applicable to the technical field of spectrum detection, and particularly relates to a spectrum detection method and system for automobile parts, wherein the method comprises the following steps: collecting spectrum data and processing the spectrum data; determining a hash function, carrying out hash on the spectrum data by utilizing the hash function, and calculating to obtain a hash value; determining cluster nodes and child nodes, constructing a distributed architecture, and transferring spectrum data into the distributed architecture to obtain a detection result of the spectrum data; and taking the detection result as an index item, and establishing an index table according to the hash value. According to the invention, the distributed architecture is constructed, so that the defect detection can be performed on the automobile parts, the serial number can be performed on the optical data by calculating the hash value of the optical data, and the defect parts can be rapidly positioned according to the defect detection result, so that the spectrum detection efficiency of the automobile parts is greatly improved.
Description
Technical Field
The invention relates to the technical field of spectrum detection, in particular to a spectrum detection method and system for automobile parts.
Background
In the spectrum detection of the automobile parts, the spectrum analysis technology can detect the information of components, structures, hardness and the like of the parts to evaluate the quality and performance of the parts, for example, the components and structures of the coating can be known by spectrum detection of the surface coating of the parts, and the performances of corrosion resistance, wear resistance and the like of the coating can be evaluated.
However, because online detection is required on a production line, a high requirement is put on the processing rate of data, and meanwhile, because the defective parts cannot be positioned quickly, the review of the defective parts is more difficult, so that how to process the spectrum analysis data of the automobile parts quickly and position the defective parts is the technical problem to be solved by the invention.
Disclosure of Invention
The invention aims to provide a spectrum detection method and a system for automobile parts, which are used for solving the problem of how to rapidly process detection data and position defective parts in the background technology.
In order to achieve the above purpose, the present invention provides the following technical solutions:
a method of spectral detection of an automotive component, the method comprising:
collecting spectrum data and processing the spectrum data;
determining a hash function, carrying out hash on the spectrum data by utilizing the hash function, and calculating to obtain a hash value;
determining cluster nodes and child nodes, constructing a distributed architecture, and transferring spectrum data into the distributed architecture to obtain a detection result of the spectrum data;
and taking the detection result as an index item, and establishing an index table according to the hash value.
Further, the step of collecting the spectrum data and processing the spectrum data includes:
preprocessing the collected spectrum data, and extracting features of the preprocessed data;
and packaging the extracted spectral data features to obtain package data.
Further, the step of determining a hash function, and hashing the spectrum data by using the hash function, and calculating to obtain a hash value includes:
inputting the packet data into a hash function, and calculating to obtain a hash value;
and establishing a one-to-one correspondence between the hash value and the spectrum data.
Further, determining cluster nodes and child nodes, and constructing a distributed architecture; transferring the spectral data into a distributed architecture; the step of obtaining the detection result of the spectrum data comprises the following steps:
determining cluster nodes and child nodes, constructing a distributed architecture, and transferring the packet data to the cluster nodes;
and classifying the packet data into sub-nodes by using the clustering nodes, and performing defect detection on the packet data to obtain a detection result.
Further, the step of establishing an index table by using the detection result as an index item according to the hash value includes:
traversing the hash value and the detection result, constructing an index relation between the detection result and spectrum data, and establishing an index table;
the index table is classified into child nodes.
Further, the method further comprises:
adding a central node to the distributed architecture;
and establishing a heartbeat mechanism by using the central node and the child nodes.
Further, the method further comprises:
collecting output results of the child nodes, and summarizing the output results to obtain summarized data;
and analyzing and processing the summarized data by using a preset statistical method.
Further, the system includes:
the acquisition module can acquire spectrum data and process the spectrum data;
the hash module is used for determining a hash function, carrying out hash on the spectrum data by utilizing the hash function, and calculating to obtain a hash value;
the detection module can determine cluster nodes and sub-nodes, construct a distributed architecture, and transfer spectrum data into the distributed architecture to obtain a detection result of the spectrum data;
and the index module can establish an index table by taking the detection result as an index item according to the hash value.
Further, the acquisition module includes:
the processing unit is capable of preprocessing the collected spectrum data and extracting characteristics of the preprocessed data;
and the packaging unit is used for packaging the extracted spectral data characteristics to obtain package data.
Further, the hash module includes:
the calculating unit can input the packet data into a hash function and calculate a hash value;
and the corresponding unit is used for establishing a one-to-one correspondence relation between the hash value and the spectrum data.
Compared with the prior art, the invention has the beneficial effects that:
1. the distributed architecture is constructed, so that the optical spectrum data can be rapidly processed, the defects of the automobile parts are detected, the optical spectrum data can be numbered by calculating the hash value of the optical spectrum data, the defects of the parts are rapidly positioned according to the defect detection result, the quality review of the defects of the parts is facilitated, and the detection efficiency of the automobile parts is effectively improved.
2. By establishing a heartbeat mechanism, the stability of the distributed architecture can be greatly improved, the working efficiency of the distributed architecture is higher, and the defect detection result of the automobile part can be statistically analyzed by analyzing and processing the sub-node output result, so that the production of the automobile part is better guided.
Drawings
FIG. 1 is a flow chart of a spectrum detection method for an automobile part according to an embodiment of the present invention;
FIG. 2 is a first sub-flowchart of a method for detecting a spectrum of an automobile part according to an embodiment of the present invention;
FIG. 3 is a second sub-flowchart of a method for detecting a spectrum of an automobile part according to an embodiment of the present invention;
FIG. 4 is a third sub-flowchart of a method for detecting a spectrum of an automobile part according to an embodiment of the present invention;
FIG. 5 is a fourth sub-flowchart of a method for detecting a spectrum of an automobile part according to an embodiment of the present invention;
FIG. 6 is a block diagram of a spectrum detection system for automotive parts according to an embodiment of the present invention;
FIG. 7 is a block diagram illustrating the components of the acquisition module in the spectrum detection system of the automobile part according to the embodiment of the present invention;
FIG. 8 is a block diagram illustrating a hash module in a spectrum detection system for an automotive component according to an embodiment of the present invention;
FIG. 9 is a block diagram of a detection module in a spectrum detection system for an automobile part according to an embodiment of the present invention;
fig. 10 is a block diagram of an index module in a spectrum detection system for an automobile part according to an embodiment of the present invention.
Detailed Description
Because the automobile parts need to be detected on the production line, the high requirement on the data processing rate is put forward, and meanwhile, because the defective parts cannot be positioned quickly, the review of the defective parts is more difficult, so that the technical problem of how to process the spectrum analysis data of the automobile parts quickly and position the defective parts is solved by the invention.
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
In embodiment 1, fig. 1 shows a spectrum detection method and a system implementation flow of an automobile part provided by the embodiment of the invention, and the following details are as follows:
s100: spectral data is collected and processed.
The method comprises the steps of performing spectrum detection on automobile parts by using spectrum detection equipment to obtain spectrum data, wherein the spectrum detection equipment can be a spectrum detector commonly used in the market; after the spectrum data is obtained by the spectrum detector, processing the spectrum data;
each automobile part corresponds to a group of spectrum data, the defect condition of the automobile part can be monitored by analyzing the spectrum data, meanwhile, according to the common sense of production, each automobile part is provided with an independent production code, the production code can be used for identifying specific information of a production process, a product or a material, the information can be manufacturer, age, vehicle category, vehicle characteristics and the like, and the tracking of product batches, the identification of the production process and the like are facilitated; the defects may be structural defects of automobile parts, coating defects, and the like.
S200: determining a hash function, carrying out hash on the spectrum data by utilizing the hash function, and calculating to obtain a hash value.
Selecting a proper hash function according to the use scene and the detection quantity of the automobile parts, carrying out hash on the spectrum data by utilizing the hash function, and calculating to obtain hash values, wherein the calculated hash values correspond to the spectrum data one by one;
by hashing the spectrum data, a unique number can be given to the spectrum data, and by retrieving the number, the spectrum data can be quickly positioned.
S300: determining cluster nodes and child nodes, constructing a distributed architecture, and transferring spectrum data into the distributed architecture to obtain a detection result of the spectrum data.
Determining cluster nodes and child nodes, wherein the number of the cluster nodes is one, and the number of the child nodes is not limited; the clustering nodes are mainly used for classifying the spectrum data, and the spectrum data can be classified into different child nodes by utilizing the clustering nodes; the child node then performs defect analysis on the data classified into the child node; by utilizing the clustering nodes and the child nodes, a distributed architecture can be constructed, so that the stability of the distributed architecture is further improved while the spectral data processing efficiency is ensured.
S400: and taking the detection result as an index item, and establishing an index table according to the hash value.
Establishing an index table according to the detection result of the spectrum data and the hash value; in daily production, the hash value of the defective part is searched according to the detection result, and each part corresponds to one hash value, so that the defective part can be quickly positioned after the hash value is determined, and the review of the defective part is realized.
In embodiment 2, fig. 2 shows a flowchart of the implementation of the method and the system for detecting the spectrum of the automobile part according to the embodiment of the invention, and the following steps for collecting the spectrum data and processing the spectrum data are described in detail, which are as follows:
s101: preprocessing the collected spectrum data, and extracting the characteristics of the preprocessed data.
After the spectrum data is collected, preprocessing the spectrum data, wherein the specific operation of preprocessing is to clean, smooth, correct baseline, remove noise and the like the spectrum data, the accuracy of spectrum detection of the automobile parts can be greatly improved through preprocessing the spectrum data, and after the automobile parts are preprocessed, the obtained data is subjected to feature extraction; by extracting the characteristics and removing useless data, the workload of spectrum detection can be reduced;
by analyzing the spectral characteristics, the result of the spectral analysis can be obtained, so that the defect condition of the automobile part can be determined.
S102: and packaging the extracted spectral data features to obtain package data.
After the feature extraction of the spectrum data is completed, the extracted features are packaged to obtain package data; the normal detection of the automobile parts can be prevented from being influenced by the loss of the characteristic data through the encapsulation of the characteristic data.
In embodiment 3, fig. 3 shows a flowchart of implementation of the method and system for detecting a spectrum of an automobile part according to the embodiment of the present invention, and the steps of determining a hash function, and hashing spectral data with the hash function to obtain a hash value are described in detail below:
s201: and inputting the packet data into a hash function, and calculating to obtain a hash value.
And selecting a proper hash function, inputting the packet data into the hash value function, and obtaining a hash value corresponding to the packet data through calculation.
S202: and establishing a one-to-one correspondence between the hash value and the spectrum data.
The corresponding relation between the hash value and the spectrum data is established, the corresponding spectrum data can be determined by determining the hash value, and meanwhile, the spectrum data corresponds to the parts one by one, so that each part corresponds to one hash value.
In embodiment 4, fig. 4 shows a spectrum detection method and a system implementation flow of an automobile part provided by the embodiment of the invention, and a distributed architecture is constructed for the determined cluster nodes and sub-nodes; transferring the spectral data into a distributed architecture; the steps for obtaining the detection result of the spectrum data are described in detail as follows:
s301: determining cluster nodes and child nodes, constructing a distributed architecture, and transferring the packet data to the cluster nodes.
Determining cluster nodes, wherein the cluster nodes are mainly used for classifying data, transferring the packaged data into the cluster nodes, classifying the packaged data into sub-nodes in the cluster nodes, wherein the number of the sub-nodes is not limited, analyzing and processing the packaged data in the sub-nodes, and constructing a distributed architecture by utilizing the cluster nodes and a plurality of sub-nodes; the processing capacity of the spectrum data can be greatly improved by utilizing the distributed architecture to analyze and process the packet data;
the spectrum detectors are arranged in the plurality of production lines, so that spectrum data of a plurality of automobile parts can be collected, and the nodes or node groups are utilized to respectively carry out spectrum analysis on the automobile parts on each group of production lines, so that the spectrum detection requirements of the plurality of production lines are met simultaneously; when a certain production line is started or stopped, the corresponding node can be stopped, and the whole distributed architecture is not required to be adjusted, so that the capacity can be better adjusted while the stability of spectrum detection is ensured.
S302: and classifying the packet data into sub-nodes by using the clustering nodes, and performing defect detection on the packet data to obtain a detection result.
The clustering node classifies the packaged data into sub-nodes, and detects defects of the packaged data in the sub-nodes; in actual production, one or more sub-nodes generally correspond to a production line, all spectrum detectors transfer collected spectrum data to a clustering node for classification after preprocessing, the clustering node classifies the spectrum data into the sub-nodes corresponding to the production line, and finally spectrum data processing is performed in the sub-nodes.
In embodiment 5, fig. 5 shows a spectrum detection method and a system implementation flow of an automobile part provided by the embodiment of the invention, and the following details are given on the steps of taking a detection result as an index item and establishing an index table according to a hash value, where the steps are as follows:
s401: traversing the hash value and the detection result, constructing an index relation between the detection result and the spectrum data, and establishing an index table.
Checking all hash values and detection results, removing useless data in the hash values and the detection results, constructing an index relation between the detection results and spectrum data, wherein the spectrum data has a corresponding relation with automobile parts, and obtaining the relation between the automobile parts and the detection results through relation conversion;
the display modes of the detection result are various, and the detection result can be qualified or unqualified, a superior product or an inferior product and the like, for example, when the detection result is qualified or unqualified, the unqualified detection result is searched in an index table, the spectrum data of the unqualified automobile part can be obtained, and the unqualified automobile part can be rapidly positioned through the spectrum data.
S402: the index table is classified into child nodes.
The sub-nodes are added in the distributed architecture, the index table is classified into the sub-nodes, the sub-nodes are utilized to store the index table, and meanwhile, the sub-nodes can be used for continuously sorting and summarizing the index table.
In embodiment 6, unlike embodiment 1, in an embodiment of the present invention, the method further includes:
adding a central node to the distributed architecture;
and establishing a heartbeat mechanism by using the central node and the child nodes.
The central node is added in the distributed architecture, wherein the central node has important management and control functions, and can provide functions of centralized management, load balancing, data assembly and integration, fault detection and recovery, safety control and the like so as to ensure the stability and reliability of the whole distributed architecture;
meanwhile, a heartbeat mechanism is built in the distributed architecture, and various factors including network protocols, heartbeat frequencies, exception handling, optimization and the like need to be comprehensively considered in the construction of the heartbeat mechanism;
the child nodes are kept in contact by establishing a heartbeat mechanism, which generally comprises sending heartbeat packets and receiving replies at regular time, and if a child node does not send heartbeat packets or does not receive replies beyond a preset time, the child node can be considered to be down or to have a fault. At this time, the distributed architecture may take corresponding measures, such as restarting the child node, moving it to a backup list, etc., to ensure normal and stable use of the distributed architecture;
meanwhile, the central node can also control the number of the child nodes, and when a certain production line is deactivated, the child nodes corresponding to the production line can be removed from the distributed architecture, so that the stability and reliability of the whole distributed architecture are ensured.
In embodiment 7, unlike embodiment 1, in an embodiment of the present invention, the method further includes:
collecting output results of the child nodes, and summarizing the output results to obtain summarized data;
and analyzing and processing the summarized data by using a preset statistical method.
And collecting output results of all the child nodes, independently creating another node for data processing, summarizing the output results into the node, and analyzing the summarized data through a preset statistical method, wherein the preset statistical method can be a yield statistical method, a yield statistical method and the like, and the production can be guided better through the statistics of the yield and the yield, so that the production efficiency of the automobile parts is further improved.
Fig. 6 shows a block diagram of a spectrum detection method and a system for an automobile part according to an embodiment of the present invention, where the spectrum detection method and the system 1 for an automobile part include:
the acquisition module 11 is capable of acquiring spectrum data and processing the spectrum data;
a hash module 12, configured to determine a hash function, and hash the spectrum data with the hash function to obtain a hash value;
the detection module 13 can determine cluster nodes and sub-nodes, construct a distributed architecture, and transfer the spectrum data into the distributed architecture to obtain a detection result of the spectrum data;
the index module 14 can use the detection result as an index item, and establish an index table according to the hash value.
Fig. 7 is a block diagram showing a spectrum detection method and a spectrum detection system for an automobile part according to an embodiment of the present invention, where the acquisition module 11 includes:
the processing unit 111 is capable of preprocessing the collected spectrum data and extracting features of the preprocessed data;
and the packaging unit 112 is configured to package the extracted spectral data features to obtain package data.
Fig. 8 is a block diagram showing a spectrum detection method and a spectrum detection system for an automobile part according to an embodiment of the present invention, where the hash module 12 includes:
a calculating unit 121, configured to input the packet data into a hash function, and calculate a hash value;
and a corresponding unit 122, configured to establish a one-to-one correspondence between the hash value and the spectrum data.
Fig. 9 is a block diagram showing a spectrum detection method and a spectrum detection system for an automobile part according to an embodiment of the present invention, where the detection module 13 includes:
the determining unit 131 is configured to determine a cluster node and a child node, construct a distributed architecture, and transfer the packet data to the cluster node;
the clustering unit 132 can classify the packet data into sub-nodes by using the clustering nodes, and perform defect detection on the packet data to obtain a detection result.
Fig. 10 is a block diagram showing a spectrum detection method and a spectrum detection system for an automobile part according to an embodiment of the present invention, where the index module 14 includes:
the traversing unit 141 is capable of traversing the hash value and the detection result, constructing an index relation between the detection result and the spectrum data, and establishing an index table;
a classifying unit 142, configured to classify the index table into child nodes.
In the embodiment, the distributed architecture is constructed, so that the defect detection can be performed on the automobile parts, the hash value of the spectrum data is calculated, the spectrum data can be numbered, the defect parts can be rapidly positioned according to the defect detection result, the quality review of the defect parts is facilitated, and the detection efficiency of the automobile parts is effectively improved.
By establishing a heartbeat mechanism, the stability of the distributed architecture can be greatly improved, the working efficiency of the distributed architecture is higher, and the defect detection result of the automobile part can be statistically analyzed by analyzing and processing the sub-node output result, so that the production of the automobile part is better guided.
The acquisition module 11 is mainly used for completing the step S100, and detecting defects of automobile parts by acquiring spectrum data, so that production is guided better; the hash module 12 is mainly used for completing step S200, and is more convenient for analyzing and processing the spectrum data while numbering the spectrum data by calculating the hash value of the spectrum data. The detection module 13 is mainly used for completing the step S300, and can process the optical data more efficiently by constructing a distributed architecture, so that the spectrum detection efficiency of the automobile parts is greatly improved; the index module 14 is mainly used for completing the step S400, and by establishing an index table, unqualified automobile parts can be positioned more quickly, so that the spectrum detection efficiency of the automobile parts is further improved;
the processing unit 111 is mainly used for completing step S101, by preprocessing the spectrum data, the accuracy of the spectrum data can be greatly improved, and the packaging unit 112 is mainly used for packaging the extracted features, so that the data loss is avoided;
the calculating unit 121 is mainly used for completing step S201, and can calculate the hash value of the packet data, so as to assign a unique hash value to each group of packet data; the corresponding unit 122 is mainly used for completing step S202, and is more convenient for positioning the defective parts by establishing a corresponding relation between the hash value and the spectrum data;
the determining unit 131 is mainly used for completing step S301, and the processing efficiency of the spectrum data is greatly improved by utilizing the distributed architecture to analyze and process the spectrum data; the clustering unit 132 is mainly used for completing the step S302, and by classifying the spectrum data into each sub-node, the analysis efficiency of the spectrum data is further improved;
the traversing unit 141 is mainly used for completing step S401, and by creating an index table, the defective components can be quickly located, and the classifying unit 142 is mainly used for completing step S402, and by classifying the index table into sub-nodes, the data in the index table can be better processed, so that the defect detection results of the automobile components can be collated and classified.
For example, a distributed architecture may be partitioned into one or more modules, one or more modules stored in a single computing device and executed by a processor to accomplish the present invention. One or more of the modules may be a series of distributed architecture capable of performing a particular function, with the instruction segments describing the execution of a computer program in a terminal device.
It will be appreciated by those skilled in the art that the foregoing description of the service device is merely an example and is not meant to be limiting, and may include more or fewer components than the foregoing description, or may combine certain components, or different components, such as may include input-output devices, network access devices, buses, etc.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
The technical features of the above-described embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above-described embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples illustrate only a few embodiments of the invention and are described in detail herein without thereby limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.
Claims (6)
1. A method for spectral detection of an automotive component, the method comprising:
collecting spectrum data and processing the spectrum data;
determining a hash function, carrying out hash on the spectrum data by utilizing the hash function, and calculating to obtain a hash value;
determining cluster nodes and child nodes, constructing a distributed architecture, and transferring spectrum data into the distributed architecture to obtain a detection result of the spectrum data;
taking the detection result as an index item, and establishing an index table according to the hash value;
the steps of collecting the spectrum data and processing the spectrum data comprise:
preprocessing the collected spectrum data, and extracting features of the preprocessed data;
packaging the extracted spectral data features to obtain package data;
determining cluster nodes and child nodes, and constructing a distributed architecture; transferring the spectral data into a distributed architecture; the step of obtaining the detection result of the spectrum data comprises the following steps:
determining cluster nodes and child nodes, constructing a distributed architecture, and transferring the packet data to the cluster nodes;
classifying the packet data into sub-nodes by using the clustering nodes, and performing defect detection on the packet data to obtain a detection result;
the step of establishing an index table by taking the detection result as an index item according to the hash value comprises the following steps:
traversing the hash value and the detection result, constructing an index relation between the detection result and spectrum data, and establishing an index table;
classifying the index table into child nodes;
determining cluster nodes and child nodes, wherein the number of the cluster nodes is one, and the number of the child nodes is not limited; the clustering nodes are mainly used for classifying the spectrum data, and the spectrum data can be classified into different child nodes by utilizing the clustering nodes; the child node then performs defect analysis on the data classified into the child node; by utilizing cluster nodes and child nodes, a distributed architecture can be built;
the spectrum detectors are arranged in the plurality of production lines, so that spectrum data of a plurality of automobile parts can be collected, and the nodes or node groups are utilized to respectively carry out spectrum analysis on the automobile parts on each group of production lines, so that the spectrum detection requirements of the plurality of production lines are met simultaneously; when a certain production line is started or stopped, the corresponding node can be stopped, and the whole distributed architecture is not required to be adjusted, so that the productivity can be better adjusted while the spectrum detection stability is ensured.
2. The method of claim 1, wherein the steps of determining a hash function and hashing the spectral data with the hash function, and calculating a hash value comprise:
inputting the packet data into a hash function, and calculating to obtain a hash value;
and establishing a one-to-one correspondence between the hash value and the spectrum data.
3. The method according to claim 1, wherein the method further comprises:
adding a central node to the distributed architecture;
and establishing a heartbeat mechanism by using the central node and the child nodes.
4. A method according to claim 3, characterized in that the method further comprises:
collecting output results of the child nodes, and summarizing the output results to obtain summarized data;
and analyzing and processing the summarized data by using a preset statistical method.
5. A spectral detection system for automotive components, the system comprising:
the acquisition module can acquire spectrum data and process the spectrum data;
the hash module is used for determining a hash function, carrying out hash on the spectrum data by utilizing the hash function, and calculating to obtain a hash value;
the detection module can determine cluster nodes and sub-nodes, construct a distributed architecture, and transfer spectrum data into the distributed architecture to obtain a detection result of the spectrum data;
the index module can take the detection result as an index item and establish an index table according to the hash value;
the steps of collecting the spectrum data and processing the spectrum data comprise:
preprocessing the collected spectrum data, and extracting features of the preprocessed data;
packaging the extracted spectral data features to obtain package data;
determining cluster nodes and child nodes, and constructing a distributed architecture; transferring the spectral data into a distributed architecture; the step of obtaining the detection result of the spectrum data comprises the following steps:
determining cluster nodes and child nodes, constructing a distributed architecture, and transferring the packet data to the cluster nodes;
classifying the packet data into sub-nodes by using the clustering nodes, and performing defect detection on the packet data to obtain a detection result;
the step of establishing an index table by taking the detection result as an index item according to the hash value comprises the following steps:
traversing the hash value and the detection result, constructing an index relation between the detection result and spectrum data, and establishing an index table;
classifying the index table into child nodes;
determining cluster nodes and child nodes, wherein the number of the cluster nodes is one, and the number of the child nodes is not limited; the clustering nodes are mainly used for classifying the spectrum data, and the spectrum data can be classified into different child nodes by utilizing the clustering nodes; the child node then performs defect analysis on the data classified into the child node; by utilizing cluster nodes and child nodes, a distributed architecture can be built;
the spectrum detectors are arranged in the plurality of production lines, so that spectrum data of a plurality of automobile parts can be collected, and the nodes or node groups are utilized to respectively carry out spectrum analysis on the automobile parts on each group of production lines, so that the spectrum detection requirements of the plurality of production lines are met simultaneously; when a certain production line is started or stopped, the corresponding node can be stopped, and the whole distributed architecture is not required to be adjusted, so that the productivity can be better adjusted while the spectrum detection stability is ensured;
the acquisition module comprises:
the processing unit is capable of preprocessing the collected spectrum data and extracting characteristics of the preprocessed data;
and the packaging unit is used for packaging the extracted spectral data characteristics to obtain package data.
6. The system of claim 5, the hash module comprising:
the calculating unit can input the packet data into a hash function and calculate a hash value;
and the corresponding unit is used for establishing a one-to-one correspondence relation between the hash value and the spectrum data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311567243.9A CN117271534B (en) | 2023-11-23 | 2023-11-23 | Spectrum detection method and system for automobile parts |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311567243.9A CN117271534B (en) | 2023-11-23 | 2023-11-23 | Spectrum detection method and system for automobile parts |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117271534A CN117271534A (en) | 2023-12-22 |
CN117271534B true CN117271534B (en) | 2024-03-05 |
Family
ID=89210933
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311567243.9A Active CN117271534B (en) | 2023-11-23 | 2023-11-23 | Spectrum detection method and system for automobile parts |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117271534B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117576102A (en) * | 2024-01-17 | 2024-02-20 | 长春汽车工业高等专科学校 | Automobile defect detection method and system based on reflection spectrum |
CN117969550B (en) * | 2024-03-29 | 2024-06-04 | 长春汽车工业高等专科学校 | Automobile defect analysis method and system based on image recognition |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1694099A (en) * | 2004-04-15 | 2005-11-09 | 微软公司 | Mining service requests for product support |
CN103744934A (en) * | 2013-12-30 | 2014-04-23 | 南京大学 | Distributed index method based on LSH (Locality Sensitive Hashing) |
CN103827864A (en) * | 2011-09-15 | 2014-05-28 | 甲骨文国际公司 | System and method for supporting a server-side event model in a distributed data grid |
CN111585950A (en) * | 2020-03-20 | 2020-08-25 | 中山大学 | Asymmetric encryption based on-site spectrum detection and analysis method, system and medium |
CN112016636A (en) * | 2020-10-22 | 2020-12-01 | 南京工业职业技术大学 | Crop spectral clustering analysis processing method based on Hadoop frame |
CN112905823A (en) * | 2021-02-22 | 2021-06-04 | 深圳市国科光谱技术有限公司 | Hyperspectral substance detection and identification system and method based on big data platform |
CN113806298A (en) * | 2021-08-09 | 2021-12-17 | 中国地质大学(武汉) | Distributed file system storage optimization method, computer equipment and storage medium |
CN114527995A (en) * | 2021-12-29 | 2022-05-24 | 浙江中控技术股份有限公司 | Graphical deployment and state monitoring integrated system and method |
CN115293259A (en) * | 2022-08-02 | 2022-11-04 | 山东财经大学 | Decentralized distributed clustering and result acquisition method |
CN115566804A (en) * | 2022-10-24 | 2023-01-03 | 江苏东港能源投资有限公司 | Electric power monitoring system based on distributed optical fiber sensing technology |
CN117097619A (en) * | 2023-10-20 | 2023-11-21 | 北京航空航天大学 | Method and system for optimizing configuration of general computing memory resources by vehicle-road cloud cooperation |
-
2023
- 2023-11-23 CN CN202311567243.9A patent/CN117271534B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1694099A (en) * | 2004-04-15 | 2005-11-09 | 微软公司 | Mining service requests for product support |
CN103827864A (en) * | 2011-09-15 | 2014-05-28 | 甲骨文国际公司 | System and method for supporting a server-side event model in a distributed data grid |
CN103744934A (en) * | 2013-12-30 | 2014-04-23 | 南京大学 | Distributed index method based on LSH (Locality Sensitive Hashing) |
CN111585950A (en) * | 2020-03-20 | 2020-08-25 | 中山大学 | Asymmetric encryption based on-site spectrum detection and analysis method, system and medium |
CN112016636A (en) * | 2020-10-22 | 2020-12-01 | 南京工业职业技术大学 | Crop spectral clustering analysis processing method based on Hadoop frame |
CN112905823A (en) * | 2021-02-22 | 2021-06-04 | 深圳市国科光谱技术有限公司 | Hyperspectral substance detection and identification system and method based on big data platform |
CN113806298A (en) * | 2021-08-09 | 2021-12-17 | 中国地质大学(武汉) | Distributed file system storage optimization method, computer equipment and storage medium |
CN114527995A (en) * | 2021-12-29 | 2022-05-24 | 浙江中控技术股份有限公司 | Graphical deployment and state monitoring integrated system and method |
CN115293259A (en) * | 2022-08-02 | 2022-11-04 | 山东财经大学 | Decentralized distributed clustering and result acquisition method |
CN115566804A (en) * | 2022-10-24 | 2023-01-03 | 江苏东港能源投资有限公司 | Electric power monitoring system based on distributed optical fiber sensing technology |
CN117097619A (en) * | 2023-10-20 | 2023-11-21 | 北京航空航天大学 | Method and system for optimizing configuration of general computing memory resources by vehicle-road cloud cooperation |
Also Published As
Publication number | Publication date |
---|---|
CN117271534A (en) | 2023-12-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN117271534B (en) | Spectrum detection method and system for automobile parts | |
CN109587008B (en) | Method, device and storage medium for detecting abnormal flow data | |
EP3432520A1 (en) | Efficient storage and querying of time series metrics | |
CN113254255B (en) | Cloud platform log analysis method, system, device and medium | |
KR20170090114A (en) | Factory smart analysis system and method based on bigdata | |
CN111722952A (en) | Fault analysis method, system, equipment and storage medium of business system | |
CN111858352B (en) | Method, device, equipment and storage medium for automatic test monitoring | |
CN106951360B (en) | Data statistical integrity calculation method and system | |
CN114429256A (en) | Data monitoring method and device, electronic equipment and storage medium | |
CN113810792B (en) | Edge data acquisition and analysis system based on cloud computing | |
CN113672506B (en) | Dynamic proportion test case sorting and selecting method and system based on machine learning | |
CN113254572B (en) | Electronic document classification supervision system based on cloud platform | |
CN111069098A (en) | Part machining qualification rate detection method based on big data | |
CN117540369B (en) | Numerical behavior safety base line generation method and device for safety analysis | |
CN113191708A (en) | Logistics distribution monitoring method, device, equipment and storage medium | |
CN106899447B (en) | Link determination method and device | |
CN117112336A (en) | Intelligent communication equipment abnormality detection method, equipment, storage medium and device | |
CN112487265A (en) | Data processing method and device, computer storage medium and electronic equipment | |
CN114816763B (en) | System and method for distributing computer resources by adopting big data technology | |
US20230213911A1 (en) | Method and device for testing product, computer device and readable storage medium | |
US20170230271A1 (en) | Data management apparatus and monitoring method of same | |
CN114969169B (en) | Sign-on data monitoring method, device, equipment and storage medium | |
CN113987240B (en) | Customs inspection sample tracing method and system based on knowledge graph | |
EP3828712A1 (en) | Data parsing method and device | |
CN112363893B (en) | Method, equipment and device for detecting time sequence index abnormity |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |