CN118818273B - Automatic test fixture for single-coil magnetic encoder - Google Patents

Automatic test fixture for single-coil magnetic encoder Download PDF

Info

Publication number
CN118818273B
CN118818273B CN202411307111.7A CN202411307111A CN118818273B CN 118818273 B CN118818273 B CN 118818273B CN 202411307111 A CN202411307111 A CN 202411307111A CN 118818273 B CN118818273 B CN 118818273B
Authority
CN
China
Prior art keywords
test result
semantic
global
principal component
feature vector
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
Application number
CN202411307111.7A
Other languages
Chinese (zh)
Other versions
CN118818273A (en
Inventor
张继周
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Linhai Xinrui Electronic Technology Co ltd
Original Assignee
Linhai Xinrui Electronic Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Linhai Xinrui Electronic Technology Co ltd filed Critical Linhai Xinrui Electronic Technology Co ltd
Priority to CN202411307111.7A priority Critical patent/CN118818273B/en
Publication of CN118818273A publication Critical patent/CN118818273A/en
Application granted granted Critical
Publication of CN118818273B publication Critical patent/CN118818273B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/28—Testing of electronic circuits, e.g. by signal tracer
    • G01R31/2801—Testing of printed circuits, backplanes, motherboards, hybrid circuits or carriers for multichip packages [MCP]
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
    • G01D18/00—Testing or calibrating apparatus or arrangements provided for in groups G01D1/00 - G01D15/00
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/28—Testing of electronic circuits, e.g. by signal tracer
    • G01R31/2801—Testing of printed circuits, backplanes, motherboards, hybrid circuits or carriers for multichip packages [MCP]
    • G01R31/2803—Testing of printed circuits, backplanes, motherboards, hybrid circuits or carriers for multichip packages [MCP] by means of functional tests, e.g. logic-circuit-simulation or algorithms therefor
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F8/00—Arrangements for software engineering
    • G06F8/60—Software deployment
    • G06F8/61—Installation
    • G06F8/63—Image based installation; Cloning; Build to order
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G06N3/0455—Auto-encoder networks; Encoder-decoder networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Biophysics (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Computational Linguistics (AREA)
  • Artificial Intelligence (AREA)
  • Mathematical Physics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Hardware Design (AREA)
  • Microelectronics & Electronic Packaging (AREA)
  • Machine Translation (AREA)

Abstract

本申请涉及一种单圈磁编码器自动化测试工装。其包括：启动所述上位机；选择待测试的编辑器主板和相应的固件数据；所述上位机通过RS‑485与所述下位机进行通信以发送烧录指令和所述固件数据；所述下位机通过FPGA芯片选择正确的编码器主板，并通过ISP下载协议将所述固件数据下载到所述编辑器主板的编辑器芯片；完成烧录后，所述下位机根据多摩川编码器协议读取编码器数据以检查所述编辑器主板的工作状态；通过所述下位机收集测试数据并发送给所述上位机；所述上位机对所述测试数据进行分析以得到测试结果。这样，提高了处理大量测试数据的效率，同时能够全面捕捉变量之间的复杂关系，提供更深入的测试结果理解，使得测试数据处理更加智能化。

The present application relates to an automated testing tool for a single-turn magnetic encoder. It includes: starting the host computer; selecting the editor mainboard to be tested and the corresponding firmware data; the host computer communicates with the lower computer via RS‑485 to send a burning instruction and the firmware data; the lower computer selects the correct encoder mainboard via the FPGA chip, and downloads the firmware data to the editor chip of the editor mainboard via the ISP download protocol; after the burning is completed, the lower computer reads the encoder data according to the Tamagawa encoder protocol to check the working status of the editor mainboard; the test data is collected by the lower computer and sent to the host computer; the host computer analyzes the test data to obtain the test results. In this way, the efficiency of processing a large amount of test data is improved, and at the same time, the complex relationship between variables can be fully captured, providing a deeper understanding of the test results, making the test data processing more intelligent.

Description

Automatic test fixture for single-coil magnetic encoder
Technical Field
The application relates to the technical field of single-turn magnetic encoders, in particular to an automatic testing tool for a single-turn magnetic encoder.
Background
The single-turn magnetic encoder used in the servo motor is a high-precision position sensor, can provide accurate angle measurement in a single-turn range, and is widely applied to occasions needing high-precision positioning control, such as industrial robots, precision machining equipment and the like.
At present, firmware burning and function testing of a servo motor single-turn encoder main board still depend on a developer to manually burn and test a board by using a tool carried by a chip manufacturer. However, this approach cannot meet the high throughput requirements of modern manufacturing because a person can only handle a single motherboard at a time. In a high-rhythm production environment, the production period is greatly prolonged by the low-efficiency manual operation mode, and the overall efficiency of the production line is seriously affected. In addition, manual inconsistencies may result in incomplete firmware burn-in, or missing critical steps in the testing process, which may result in unstable or unacceptable product performance. For example, incomplete firmware burn-in may cause the encoder to fail under certain conditions, and omission in the test may result in failure to detect a potential problem.
Therefore, an optimized single turn magnetic encoder test fixture is desired.
Disclosure of Invention
This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.
In a first aspect, the present application provides a single-turn magnetic encoder automated test fixture, the fixture comprising: the upper computer and the lower computer, wherein, the working process of upper computer with the lower computer includes: starting the upper computer; selecting an editor main board to be tested and corresponding firmware data; the upper computer communicates with the lower computer through RS-485 to send a burning instruction and the firmware data; the lower computer selects a correct encoder main board through an FPGA chip, and downloads the firmware data to an editor chip of the editor main board through an ISP download protocol; after the burning is finished, the lower computer reads the encoder data according to the multi-Moire encoder protocol to check the working state of the editor main board; collecting test data through the lower computer and sending the test data to the upper computer; and the upper computer analyzes the test data to obtain a test result.
Optionally, the upper computer analyzes the test data to obtain a test result, including: performing embedded coding on each test result item in the test data by using a test embedded coding matrix to obtain a set of test result item embedded coding vectors; the test result item is embedded into a set of coding vectors and input into a global semantic association coder between test results based on a converter structure to obtain a test result global semantic coding feature vector; embedding the test result item into a set of coding vectors and inputting the set of the test result item into a local semantic association coder among test results to obtain a test result local semantic coding feature vector; inputting the test result global semantic coding feature vector and the test result local semantic coding feature vector into a significant fusion network based on feature principal component query matching to obtain a test result multi-scale sparse fusion representation vector; and obtaining the test result based on the test result multi-scale sparse fusion expression vector.
Optionally, the embedding the test result item into the set of encoding vectors is input into a local semantic association encoder between test results to obtain a test result local semantic encoding feature vector, including: and embedding the test result items into a set of coding vectors, and inputting the set of the test result items into a 1D-CNN model-based inter-test result local semantic association encoder to obtain the test result local semantic coding feature vectors.
Optionally, inputting the test result global semantic coding feature vector and the test result local semantic coding feature vector into a salient fusion network based on feature principal component query matching to obtain a test result multi-scale sparse fusion representation vector, including: carrying out standardized processing on the global semantic coding feature vector of the test result and the local semantic coding feature vector of the test result to obtain a global semantic coding feature vector of the standardized test result and a local semantic coding feature vector of the standardized test result; calculating a sample covariance matrix of the standardized test result global semantic coding feature vector and the standardized test result local semantic coding feature vector to obtain a test result global semantic sample covariance matrix and a test result local semantic sample covariance matrix; extracting feature vectors based on matrix decomposition from the test result global semantic sample covariance matrix and the test result local semantic sample covariance matrix to obtain a set of test result global semantic principal component feature vectors and a set of test result local semantic principal component feature vectors; inputting the set of the global semantic principal component feature vectors of the test result and the set of the local semantic principal component feature vectors of the test result into a maximum approximate query matching network to obtain a set of best matching pairs of the global semantic principal component feature vectors of the test result and the local semantic principal component feature vectors of the test result; inputting the optimal matched pairs of the global semantic principal component feature vector of the test result and the local semantic principal component feature vector of the test result into a semantic fine granularity gating joint module to obtain a set of global semantic principal component fusion feature vectors of the test result and a set of local semantic principal component fusion feature vectors of the test result; and cascading the set of the test result global-test result local semantic principal component fusion feature vectors to obtain the test result multi-scale sparse fusion representation vector.
Optionally, performing normalization processing on the test result global semantic coding feature vector and the test result local semantic coding feature vector to obtain a normalized test result global semantic coding feature vector and a normalized test result local semantic coding feature vector, including: respectively calculating the mean value and standard deviation of the global semantic coding feature vector of the test result to obtain the mean value of the global semantic coding feature of the test result and the standard deviation of the global semantic coding feature of the test result; position-based division is carried out on the test result global semantic coding feature vector and the test result global semantic coding feature mean value to obtain a position-based division of the obtained test result global semantic offset vector and the test result global semantic coding feature standard deviation so as to obtain the standardized test result global semantic coding feature vector; respectively calculating the mean value and standard deviation of the local semantic coding feature vector of the test result to obtain the mean value of the local semantic coding feature of the test result and the standard deviation of the local semantic coding feature of the test result; and carrying out position-by-position subtraction on the test result local semantic coding feature vector and the test result local semantic coding feature mean value, and carrying out position-by-position division on the obtained test result local semantic offset vector and the test result local semantic coding feature standard deviation to obtain the standardized test result local semantic coding feature vector.
Optionally, calculating a sample covariance matrix of the normalized test result global semantic coding feature vector and the normalized test result local semantic coding feature vector to obtain a test result global semantic sample covariance matrix and a test result local semantic sample covariance matrix, including: multiplying the transpose vector of the standardized test result global semantic coding feature vector with the standardized test result global semantic coding feature vector, and then dividing the obtained standardized test result global semantic association matrix with a numerical value obtained by subtracting one from the length of the standardized test result global semantic coding feature vector by positions to obtain the test result global semantic sample covariance matrix; multiplying the transpose vector of the normalized test result local semantic coding feature vector with the normalized test result local semantic coding feature vector, and then dividing the obtained normalized test result local semantic association matrix by a value obtained by subtracting one from the length of the normalized test result local semantic coding feature vector according to positions to obtain the test result local semantic sample covariance matrix.
Optionally, inputting the set of test result global semantic principal component feature vectors and the set of test result local semantic principal component feature vectors into a maximum approximation query matching network to obtain a set of best matching pairs of test result global semantic principal component feature vectors and test result local semantic principal component feature vectors, including: extracting a preset test result global semantic principal component feature vector in the test result global semantic principal component feature vector set; calculating cosine similarity between the preset test result global semantic principal component feature vector and each test result local semantic principal component feature vector in the test result local semantic principal component feature vector set to obtain a matched query similarity set; and taking the test result local semantic principal component feature vector corresponding to the largest matching query similarity in the set of matching query similarities and the preset test result global semantic principal component feature vector as the optimal matching pair of the preset test result global semantic principal component feature vector and the test result local semantic principal component feature vector.
Optionally, inputting each of the sets of best matched pairs of the test result global semantic principal component feature vector and the test result local semantic principal component feature vector into a semantic fine granularity gating joint module to obtain a set of test result global-test result local semantic principal component fusion feature vector, including: respectively calculating the position-by-position difference value, the position-by-position point multiplication and the position-by-position addition between the best matching pair of the test result global semantic principal component feature vector and the test result local semantic principal component feature vector to obtain a test result global-local semantic principal component difference vector, a test result global-local semantic principal component point multiplication vector and a test result global-local semantic principal component addition vector; cascading the test result global-local semantic principal component differential vector, the test result global-local semantic principal component dot product vector and the test result global-local semantic principal component addition vector, and then carrying out one-dimensional convolution coding to obtain a test result global-local semantic principal component multidimensional fusion vector; and carrying out maximum pooling processing based on a local window on the test result global-local semantic principal component multi-dimensional fusion vector to obtain the test result global-test result local semantic principal component fusion feature vector.
Optionally, based on the test result multi-scale sparse fusion representation vector, obtaining the test result includes: inputting the test result multi-scale sparse fusion representation vector into a classifier-based test result generator to obtain the test result.
By adopting the technical scheme, the upper computer is started; selecting an editor main board to be tested and corresponding firmware data; the upper computer communicates with the lower computer through RS-485 to send a burning instruction and the firmware data; the lower computer selects a correct encoder main board through an FPGA chip, and downloads the firmware data to an editor chip of the editor main board through an ISP download protocol; after the burning is finished, the lower computer reads the encoder data according to the multi-Moire encoder protocol to check the working state of the editor main board; collecting test data through the lower computer and sending the test data to the upper computer; and the upper computer analyzes the test data to obtain a test result. Therefore, the efficiency of processing a large amount of test data is improved, complex relations among variables can be comprehensively captured, deeper test result understanding is provided, and the test data processing is more intelligent.
Additional features and advantages of the application will be set forth in the detailed description which follows.
Drawings
The above and other features, advantages and aspects of embodiments of the present application will become more apparent by reference to the following detailed description when taken in conjunction with the accompanying drawings. The same or similar reference numbers will be used throughout the drawings to refer to the same or like elements. It should be understood that the figures are schematic and that elements and components are not necessarily drawn to scale.
In the drawings: FIG. 1 is a flow chart illustrating a single turn magnetic encoder automated test fixture, according to an exemplary embodiment.
FIG. 2 is a flowchart showing a step S107 of a single turn magnetic encoder automated test fixture according to the embodiment shown in FIG. 1.
Fig. 3 is a block diagram of an electronic device, according to an example embodiment.
FIG. 4 is an application scenario diagram of a single turn magnetic encoder automated test fixture, according to an example embodiment.
Detailed Description
Embodiments of the present application will be described in more detail below with reference to the accompanying drawings. While the application is susceptible of embodiment in the drawings, it is to be understood that the application may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but rather are provided to provide a more thorough and complete understanding of the application. It should be understood that the drawings and embodiments of the application are for illustration purposes only and are not intended to limit the scope of the present application.
It should be understood that the various steps recited in the method embodiments of the present application may be performed in a different order and/or performed in parallel. Furthermore, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the application is not limited in this respect.
The term "including" and variations thereof as used herein are intended to be open-ended, i.e., including, but not limited to. The term "based on" is based at least in part on. The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments. Related definitions of other terms will be given in the description below.
It should be noted that the terms "first," "second," and the like herein are merely used for distinguishing between different devices, modules, or units and not for limiting the order or interdependence of the functions performed by such devices, modules, or units.
It should be noted that references to "one", "a plurality" and "a plurality" in this disclosure are intended to be illustrative rather than limiting, and those skilled in the art will appreciate that "one or more" is intended to be construed as "one or more" unless the context clearly indicates otherwise.
The names of messages or information interacted between the devices in the embodiments of the present application are for illustrative purposes only and are not intended to limit the scope of such messages or information.
At present, a servo motor single-turn encoder main board is burnt and tested, or a developer uses a tool carried by a chip manufacturer, and a piece of board is manually burnt and tested. This approach is inefficient and prone to error, and obviously cannot accommodate the production environment. It is now desirable to design a new rapid test fixture to accommodate the automated burn-in firmware and test requirements of the production environment. The new single-turn encoder rapid test tool consists of a PC end upper computer and a lower computer control board program; the upper computer provides a man-machine interaction interface, and the lower computer completes the functions of selecting a main board of the encoder, downloading firmware, testing and the like. The upper computer and the lower computer communicate through RS-485.
The following describes specific embodiments of the present application in detail with reference to the drawings. FIG. 1 is a flow chart of a single turn magnetic encoder automated test fixture, as shown in FIG. 1, according to an exemplary embodiment, the fixture comprising: the upper computer and the lower computer, wherein, the working process of upper computer with the lower computer includes: step S101, starting the upper computer.
Step S102, selecting an editor main board to be tested and corresponding firmware data.
And step S103, the upper computer communicates with the lower computer through RS-485 to send the burning instruction and the firmware data.
And step S104, the lower computer selects a correct encoder mainboard through an FPGA chip, and downloads the firmware data to an editor chip of the editor mainboard through an ISP download protocol.
And step 105, after the burning is completed, the lower computer reads the encoder data according to the multi-Moire encoder protocol to check the working state of the editor main board.
And S106, collecting test data through the lower computer and sending the test data to the upper computer.
And step S107, the upper computer analyzes the test data to obtain a test result.
All logic flows such as burning and testing are carried out by an upper computer, a lower computer is only a communication transfer station, the lower computer needs to have two serial ports, one serial port is connected with a PC serial port for communication with the upper computer, and the other serial port is connected with an FPGA chip (responsible for selecting an encoder main board). The lower computer needs to realize a modbus slave station for receiving the instruction and the data sent by the upper computer; the lower computer needs to realize the function of selecting the main board of the encoder by communicating with the FPGA. The lower computer needs to realize ISP downloading protocol, and downloads the firmware program transmitted by the pc upper computer to the encoder chip; the lower computer needs to read the motor encoder data according to the Moire encoder protocol to test whether the encoder works normally. The PC upper computer needs to have serial port selection and setting functions and display serial port communication states, and the PC upper computer needs to have a function of selecting an encoder test board. The PC upper computer needs to select the firmware to be burned and automatically records the configuration file, and the next time the PC upper computer is opened, the position of the file path of the last firmware to be burned can be automatically recorded. The PC upper computer needs to select whether to enter the next test according to the firmware burning state transmitted back by the lower computer; the PC upper computer needs to display the burning and testing states of 10 encoder main boards to be tested, and after all the encoder main boards are tested, the PC upper computer needs to display the final test result PASS/NG.
Therefore, the single-circle magnetic encoder automatic test fixture disclosed by the application can process a plurality of mainboards at the same time, and the production throughput is obviously improved. And through the collaborative work of the upper computer and the lower computer, batch burning and testing can be realized, the production period is greatly shortened, and the high-efficiency requirement of the modern manufacturing industry is met.
It should be appreciated that the test data analysis can help identify any anomalies or defects in the encoder board during the burn-in and test process, thereby ensuring that each product meets predetermined quality standards. However, conventional analysis of test data is typically accomplished by manual or simple analysis methods. In particular, conventional methods typically rely on manual inspection and recording of test data, and comparison of standard values piece by piece, which is time consuming and laborious, particularly when handling large amounts of data, is very inefficient, and may also lead to human error. In addition, when test data involves multiple variables and dimensions, traditional analysis methods have difficulty capturing complex relationships between the variables comprehensively, which may result in insufficient understanding of the test results, missing important correlations, and thus reducing the accuracy of the test results.
Therefore, in the process of analyzing the test data by using the upper computer to obtain a test result, the technical concept of the application is to perform embedded coding on each test result item in the test data by adopting an artificial intelligence-based data processing and analyzing algorithm, and perform global semantic association and local semantic association on the embedded coded test result respectively, so that the test result is automatically obtained according to the obvious fusion characteristic between the global semantic characteristic and the local semantic characteristic of the test result. Thus, the efficiency of processing a large amount of measured data is improved, and the time and error rate of manual operation are reduced. Meanwhile, complex relations among variables can be comprehensively captured, deeper test result understanding is provided, and test data processing is more intelligent.
FIG. 2 is a flowchart showing a step S107 of a single turn magnetic encoder automated test fixture according to the embodiment shown in FIG. 1. As shown in fig. 2, step S107, the upper computer analyzes the test data to obtain a test result, including: step S1071, performing embedded coding on each test result item in the test data by using the test embedded coding matrix to obtain a set of test result item embedded coding vectors.
Step S1072, the test result item is embedded into a set of coding vectors and input into a global semantic association coder between test results based on a converter structure to obtain the global semantic coding feature vectors of the test results.
Step S1073, the test result item is embedded into a set of coding vectors and input into a local semantic association encoder between test results to obtain the test result local semantic coding feature vector.
And step S1074, inputting the global semantic coding feature vector of the test result and the local semantic coding feature vector of the test result into a significant fusion network based on feature principal component query matching to obtain a multi-scale sparse fusion representation vector of the test result.
Step S1075, obtaining the test result based on the multi-scale sparse fusion expression vector of the test result.
Specifically, considering that each test result item in the test data generally contains a large number of data dimensions, if the direct processing calculation amount of the data is large, and each data item contains key data item information, in the technical scheme of the application, each test result item in the test data is embedded and encoded by using a test embedded encoding matrix to obtain a set of test result item embedded encoding vectors, that is, the test embedded encoding matrix can map high-dimensional data to a low-dimensional space, reduce calculation complexity, and simultaneously retain intrinsic meaning and semantic information in the data, so that richer data support is provided for subsequent data processing.
Next, considering that there is a semantic correlation and impact between individual test result item embedded encoding vectors in the set of test result item embedded encoding vectors, the core of the converter structure is a Self-Attention (Self-Attention) mechanism that is capable of capturing semantic relationships between different elements in the input sequence, which is critical to understanding the global semantic correlation between test result items. Based on the above, in the technical scheme of the application, the set of the test result item embedded coding vectors is input into the global semantic association encoder between test results based on the converter structure so as to capture and mine semantic association between each vector to obtain the global semantic coding feature vector of the test result.
Then, considering that the set of test result item embedded encoding vectors also has local semantic based relevance in a local scope, the 1D-CNN is able to capture local features in the sequence data through a convolution layer, which is very useful for identifying local semantic associations between test result items. Therefore, in the technical scheme of the application, the set of the embedded encoding vectors of the test result items is input into the inter-test result local semantic association encoder based on the 1D-CNN model to obtain the test result local semantic encoding feature vector. That is, the 1D-CNN model uses a convolution layer to process an input set of embedded encoded vectors, the convolution layer moving in sequence through a sliding window (convolution kernel), extracting local semantic features in the embedded encoded vectors.
In one embodiment of the present application, the embedding the test result item into the set of encoding vectors is input into the inter-test result local semantic association encoder to obtain a test result local semantic encoding feature vector, including: and embedding the test result items into a set of coding vectors, and inputting the set of the test result items into a 1D-CNN model-based inter-test result local semantic association encoder to obtain the test result local semantic coding feature vectors.
Further, considering that the global semantic coding feature vector of the test result and the local semantic coding feature vector of the test result capture different layers of information of the test result respectively. And there are significant semantic features between both information. In order to more comprehensively capture the complexity and multidimensional information of the test data and accurately judge the test result, in the technical scheme of the application, the global semantic coding feature vector of the test result and the local semantic coding feature vector of the test result are input into a significant fusion network which is based on feature principal component query matching to obtain a multi-scale sparse fusion representation vector of the test result. Particularly, the salient fusion network based on feature principal component query matching utilizes feature sparsification, principal component analysis and key salient feature integration technology to create a feature extraction and fusion method, and aims to construct sparse and key association mapping between feature vectors. In detail, firstly, the global semantic coding feature vector of the test result and the local semantic coding feature vector of the test result are standardized so as to eliminate the influence of different feature vectors caused by different dimensions, so that the features are comparable, and the global semantic coding feature vector of the standardized test result and the local semantic coding feature vector of the standardized test result are obtained. And then, calculating covariance matrixes of the standardized test result global semantic coding feature vectors and the standardized test result local semantic coding feature vectors to obtain a test result global semantic sample covariance matrix and a test result local semantic sample covariance matrix. And then, extracting eigenvectors based on matrix decomposition from the covariance matrix to obtain a set of overall semantic principal component eigenvectors of the test result and a set of local semantic principal component eigenvectors of the test result. In particular, the feature vector extraction based on matrix decomposition is to utilize a principal component analysis algorithm to carry out sparse processing on the normalized vector, so that the principal component features which can most represent the semantics of the test result can be extracted from the global and local layers while the data dimension is reduced. And then, carrying out maximum approximate query matching based on the feature vectors on the two groups of vectors, and carrying out the query matching of the most relevant semantics by calculating the cosine similarity between each feature so as to find the optimal matching pair. Furthermore, the optimal matching pair of each group is subjected to fine-granularity semantic joint processing by using a gating mechanism so as to capture and extract multi-dimensional principal component associated information between the global feature of the test result and the data feature, so that the model can more finely understand and process the semantic information, the grasping of semantic content by the model is enhanced, and the collection of the local semantic principal component fusion feature vectors of the test result global-test result is obtained. Finally, the set of principal component fusion feature vectors is subjected to cascading processing to further integrate and optimize the feature vectors so as to obtain feature representations containing global and local rich semantic information of the test result, and therefore a multi-scale sparse fusion representation vector of the test result is generated.
In one embodiment of the present application, inputting the test result global semantic coding feature vector and the test result local semantic coding feature vector into a salient fusion network based on feature principal component query matching to obtain a test result multi-scale sparse fusion representation vector includes: carrying out standardized processing on the global semantic coding feature vector of the test result and the local semantic coding feature vector of the test result to obtain a global semantic coding feature vector of the standardized test result and a local semantic coding feature vector of the standardized test result; calculating a sample covariance matrix of the standardized test result global semantic coding feature vector and the standardized test result local semantic coding feature vector to obtain a test result global semantic sample covariance matrix and a test result local semantic sample covariance matrix; extracting feature vectors based on matrix decomposition from the test result global semantic sample covariance matrix and the test result local semantic sample covariance matrix to obtain a set of test result global semantic principal component feature vectors and a set of test result local semantic principal component feature vectors; inputting the set of the global semantic principal component feature vectors of the test result and the set of the local semantic principal component feature vectors of the test result into a maximum approximate query matching network to obtain a set of best matching pairs of the global semantic principal component feature vectors of the test result and the local semantic principal component feature vectors of the test result; inputting the optimal matched pairs of the global semantic principal component feature vector of the test result and the local semantic principal component feature vector of the test result into a semantic fine granularity gating joint module to obtain a set of global semantic principal component fusion feature vectors of the test result and a set of local semantic principal component fusion feature vectors of the test result; and cascading the set of the test result global-test result local semantic principal component fusion feature vectors to obtain the test result multi-scale sparse fusion representation vector.
Further, in an embodiment of the present application, the normalizing process is performed on the test result global semantic coding feature vector and the test result local semantic coding feature vector to obtain a normalized test result global semantic coding feature vector and a normalized test result local semantic coding feature vector, including: respectively calculating the mean value and standard deviation of the global semantic coding feature vector of the test result to obtain the mean value of the global semantic coding feature of the test result and the standard deviation of the global semantic coding feature of the test result; position-based division is carried out on the test result global semantic coding feature vector and the test result global semantic coding feature mean value to obtain a position-based division of the obtained test result global semantic offset vector and the test result global semantic coding feature standard deviation so as to obtain the standardized test result global semantic coding feature vector; respectively calculating the mean value and standard deviation of the local semantic coding feature vector of the test result to obtain the mean value of the local semantic coding feature of the test result and the standard deviation of the local semantic coding feature of the test result; and carrying out position-by-position subtraction on the test result local semantic coding feature vector and the test result local semantic coding feature mean value, and carrying out position-by-position division on the obtained test result local semantic offset vector and the test result local semantic coding feature standard deviation to obtain the standardized test result local semantic coding feature vector.
Further, in an embodiment of the present application, calculating a sample covariance matrix of the normalized test result global semantic coding feature vector and the normalized test result local semantic coding feature vector to obtain a test result global semantic sample covariance matrix and a test result local semantic sample covariance matrix includes: multiplying the transpose vector of the standardized test result global semantic coding feature vector with the standardized test result global semantic coding feature vector, and then dividing the obtained standardized test result global semantic association matrix with a numerical value obtained by subtracting one from the length of the standardized test result global semantic coding feature vector by positions to obtain the test result global semantic sample covariance matrix; multiplying the transpose vector of the normalized test result local semantic coding feature vector with the normalized test result local semantic coding feature vector, and then dividing the obtained normalized test result local semantic association matrix by a value obtained by subtracting one from the length of the normalized test result local semantic coding feature vector according to positions to obtain the test result local semantic sample covariance matrix.
Still further, in one embodiment of the present application, inputting the set of test result global semantic principal component feature vectors and the set of test result local semantic principal component feature vectors into a maximum approximation query matching network to obtain a set of best matching pairs of test result global semantic principal component feature vectors and test result local semantic principal component feature vectors, comprising: extracting a preset test result global semantic principal component feature vector in the test result global semantic principal component feature vector set; calculating cosine similarity between the preset test result global semantic principal component feature vector and each test result local semantic principal component feature vector in the test result local semantic principal component feature vector set to obtain a matched query similarity set; and taking the test result local semantic principal component feature vector corresponding to the largest matching query similarity in the set of matching query similarities and the preset test result global semantic principal component feature vector as the optimal matching pair of the preset test result global semantic principal component feature vector and the test result local semantic principal component feature vector.
Still further, in an embodiment of the present application, inputting each of the sets of best matched pairs of test result global semantic principal component feature vectors and test result local semantic principal component feature vectors into a semantic fine granularity gating joint module to obtain a set of test result global-test result local semantic principal component fusion feature vectors, comprising: respectively calculating the position-by-position difference value, the position-by-position point multiplication and the position-by-position addition between the best matching pair of the test result global semantic principal component feature vector and the test result local semantic principal component feature vector to obtain a test result global-local semantic principal component difference vector, a test result global-local semantic principal component point multiplication vector and a test result global-local semantic principal component addition vector; cascading the test result global-local semantic principal component differential vector, the test result global-local semantic principal component dot product vector and the test result global-local semantic principal component addition vector, and then carrying out one-dimensional convolution coding to obtain a test result global-local semantic principal component multidimensional fusion vector; and carrying out maximum pooling processing based on a local window on the test result global-local semantic principal component multi-dimensional fusion vector to obtain the test result global-test result local semantic principal component fusion feature vector.
Specifically, inputting the global semantic coding feature vector of the test result and the local semantic coding feature vector of the test result into a salient fusion network based on feature principal component query matching, and processing the salient fusion network by using the following salient fusion formula to obtain a multi-scale sparse fusion representation vector of the test result; wherein, the obvious fusion formula is as follows: ; wherein, AndRespectively representing the global semantic coding feature vector of the test result and the local semantic coding feature vector of the test result,AndRespectively the average value of the global semantic coding feature vector of the test result and the local semantic coding feature vector of the test result,AndStandard deviations of the test result global semantic coding feature vector and the test result local semantic coding feature vector are respectively determined,AndThe normalized test result global semantic coding feature vector and the normalized test result local semantic coding feature vector are respectively,AndRespectively isAndIs used to determine the transposed vector of (c),AndThe lengths of the normalized test result global semantic coding feature vector and the normalized test result local semantic coding feature vector are respectively,AndThe test result global semantic sample covariance matrix and the test result local semantic sample covariance matrix are respectively,AndThe test result global semantic principal component orthogonal matrix and the test result local semantic principal component orthogonal matrix are respectively,AndA global semantic diagonal matrix of the test result and a local semantic diagonal matrix of the test result are respectively provided,For elements on diagonal in the matrixIs a global semantic diagonal matrix of test results of (a),The weight values of the feature vectors of the global semantic principal components of each test result are respectively,For elements on diagonal in the matrixIs a local semantic diagonal matrix of the test results of (a),The weight values of the feature vectors of the local semantic principal components of each test result are respectively,AndRespectively isAndIs used to determine the transposed matrix of (a),Global semantic principal component feature vectors for each test result in the set of test result global semantic principal component feature vectors,For each test result local semantic principal component feature vector in the set of test result local semantic principal component feature vectors,To calculate theAndThe inner product of the vectors between them,In order to calculate a norm of the vector,For returning to maximum valueThe value of the sum of the values,Is the maximum approximate match value and,、AndRespectively the difference value according to the position, the multiplication according to the position point and the addition according to the position,In the case of a cascade of processes,Is a one-dimensional convolutional encoding operation,Is the operation of the maximum pooling,Is the first in the set of the test result global-test result local semantic principal component fusion feature vectorsIndividual test result global-test result local semantic principal component fusion feature vectors,Is the number of feature vectors in the set of feature vectors fused by the test result global-test result local semantic principal components,Is the multi-scale sparse fusion expression vector of the test result.
And then, inputting the test result multi-scale sparse fusion representation vector into a classifier-based test result generator to obtain the test result. The test result is automatically obtained by performing classification processing by using the test result multiscale sparse fusion expression vector obtained after the test result global semantic coding feature vector and the test result local semantic coding feature vector are subjected to significance fusion. Thus, the efficiency of processing a large amount of measured data is improved, and the time and error rate of manual operation are reduced. Meanwhile, complex relations among variables can be comprehensively captured, deeper test result understanding is provided, and test data processing is more intelligent.
After all the coded main boards are tested, the PC upper computer needs to display a final test result PASS/NG', wherein the PASS indicates that the main boards PASS all the test standards and requirements, which means that the functions, performances and quality of the main boards meet the design specifications and manufacturing standards, and when the PC upper computer displays the PASS, the main boards can enter the next production stage, such as packaging and shipping. NG indicates that the motherboard fails the test, there are some non-standard issues that may be due to hardware defects, software errors, or other manufacturing issues, and when "NG" is displayed, the motherboard requires further inspection and repair, or may require reworking or scrapping.
In one embodiment of the present application, obtaining the test result based on the test result multi-scale sparse fusion representation vector includes: inputting the test result multi-scale sparse fusion representation vector into a classifier-based test result generator to obtain the test result.
Preferably, considering that the global semantic coding feature vector of the test result and the local semantic coding feature vector of the test result respectively represent the associated feature based on the embedded representation context and the local associated feature of the embedded representation context of each test result item, when the feature principal component query matching is obviously fused, the feature principal component query matching significance difference caused by the embedded representation association dimension difference can cause the embedded semantic aggregation fine granularity alignment conflict, thereby causing the aggregation key information to be lost and influencing the expression effect of the multi-scale sparse fusion representation vector of the test result.
Based on this, in the preferred example, when the test result multi-scale sparse fusion representation vector is input to a classifier-based test result generator to obtain the test result, the test result multi-scale sparse fusion representation vector is optimized, specifically, the optimization process includes the steps of: clustering all feature values of the test result multi-scale sparse fusion representation vector based on feature value intervals, such as difference absolute value distances, and determining a proportion value of the feature number of clustered features relative to the feature number of the test result multi-scale sparse fusion representation vector; arranging the clustering features into test result multi-scale sparse fusion clustering vectors, and dividing the two norms of the test result multi-scale sparse fusion clustering vectors by the two norms of the test result multi-scale sparse fusion representation vectors to obtain a first test result multi-scale sparse fusion clustering related weight value; dividing a first power value of a norm of the test result multi-scale sparse fusion cluster vector with the ratio value as an index by a second power value of a norm of the test result multi-scale sparse fusion representation vector with the ratio value as an index to obtain a second test result multi-scale sparse fusion cluster related weight value; multiplying each characteristic value of the test result multi-scale sparse fusion cluster vector by the reciprocal of the difference between the related weight values of the first and second test result multi-scale sparse fusion clusters to obtain an optimized characteristic value of the test result multi-scale sparse fusion cluster vector; for each feature value except the clusters in the test result multi-scale sparse fusion representation vector, multiplying the feature value by the reciprocal of the sum of the related weight values of the first and second test result multi-scale sparse fusion clusters to obtain an optimized extrageneric feature value of the test result multi-scale sparse fusion representation vector; and forming an optimized test result multi-scale sparse fusion representation vector by the optimized characteristic value of the test result multi-scale sparse fusion clustering vector and the optimized extrageneric characteristic value of the test result multi-scale sparse fusion representation vector.
That is, the optimization process is expressed as:； Is the test result multi-scale sparse fusion representation vector, e.g. denoted as Is used for the number of features of a (c),Is the test result multi-scale sparse fusion cluster vector, for example, marked asIs used for the number of features of a (c),Representing a cluster feature set corresponding to the test result multi-scale sparse fusion cluster vector,AndRepresenting the two and one norms of the vector, respectivelyTo the power of the two,Is the value of the proportion of the total weight of the product,Is the multi-scale sparse fusion representation vector of the test result,Is the multi-scale sparse fusion cluster vector of the test result,Is the characteristic value of each position of the multi-scale sparse fusion cluster vector of the test result,The feature values of all positions of the optimized test result multi-scale sparse fusion expression vector are composed of the optimized out-of-class feature values.
Here, in order to avoid that the test result multiscale sparse fusion representation vector is based on aggregation features, key suffix semantic information relative to the whole original feature set is lost due to aggregation conflict, clustering proportion of the feature number of the test result multiscale sparse fusion cluster vector relative to the feature number of the test result multiscale sparse fusion representation vector is used as a judgment function to conduct countermeasure judgment of the test result multiscale sparse fusion cluster vector and one-norm aggregate absolute representation of the test result multiscale sparse fusion representation vector, positive and negative interactions are conducted on clustering intrinsic conflict representations of two norms of the test result multiscale sparse fusion representation vector and the test result multiscale sparse fusion representation vector respectively, and firm alignment guardrails of the optimized test result multiscale sparse fusion representation vector based on aggregation features and the whole original feature set are constructed, so that harmful information loss alleviation intention of the optimized test result multiscale sparse fusion representation vector based on aggregation risk migration is achieved, the expression effect of the optimized test result multiscale sparse fusion representation vector is improved, and the test result multiscale fusion representation generator input test result classification accuracy based on the test result input classifier is improved. Thus, the efficiency of processing a large amount of measured data is improved, and the time and error rate of manual operation are reduced. Meanwhile, complex relations among variables can be comprehensively captured, deeper test result understanding is provided, and test data processing is more intelligent.
In summary, by adopting the above scheme, each test result item in the test data is embedded and encoded by adopting the data processing and analysis algorithm based on artificial intelligence, and the embedded and encoded test result is respectively subjected to global semantic association and local semantic association, so that the test result is automatically obtained according to the obvious fusion characteristics between the global semantic characteristics and the local semantic characteristics of the test result. Thus, the efficiency of processing a large amount of measured data is improved, and the time and error rate of manual operation are reduced. Meanwhile, complex relations among variables can be comprehensively captured, deeper test result understanding is provided, and test data processing is more intelligent.
Referring now to fig. 3, a schematic diagram of an electronic device 600 suitable for use in implementing embodiments of the present application is shown. The terminal device in the embodiment of the present application may include, but is not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), car terminals (e.g., car navigation terminals), and the like, and stationary terminals such as digital TVs, desktop computers, and the like. The electronic device shown in fig. 3 is only an example and should not be construed as limiting the functionality and scope of use of the embodiments of the application.
As shown in fig. 3, the electronic device 600 may include a processing means (e.g., a central processing unit, a graphics processor, etc.) 601, which may perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 602 or a program loaded from a storage means 608 into a Random Access Memory (RAM) 603. In the RAM603, various programs and data required for the operation of the electronic apparatus 600 are also stored. The processing device 601, the ROM602, and the RAM603 are connected to each other through a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
In general, the following devices may be connected to the I/O interface 605: input devices 606 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, and the like; an output device 607 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 608 including, for example, magnetic tape, hard disk, etc.; and a communication device 609. The communication means 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. While fig. 3 shows an electronic device 600 having various means, it is to be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may be implemented or provided instead.
In particular, according to embodiments of the present application, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present application include a computer program product comprising a computer program embodied on a non-transitory computer readable medium, the computer program comprising program code for performing the method shown in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via communication means 609, or from storage means 608, or from ROM 602. The above-described functions defined in the method of the embodiment of the present application are performed when the computer program is executed by the processing means 601.
The computer readable medium of the present application may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present application, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.
In some embodiments, the clients, servers may communicate using any currently known or future developed network protocol, such as HTTP (HyperText TransferProtocol ), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the internet (e.g., the internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed networks.
The computer readable medium may be contained in the electronic device; or may exist alone without being incorporated into the electronic device.
Computer program code for carrying out operations of the present application may be written in one or more programming languages, including, but not limited to, an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules involved in the embodiments of the present application may be implemented in software or in hardware. The name of the module is not limited to the module itself in some cases, and for example, the test parameter obtaining module may also be described as "a module for obtaining the device test parameter corresponding to the target device".
The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: a Field Programmable Gate Array (FPGA), an Application Specific Integrated Circuit (ASIC), an Application Specific Standard Product (ASSP), a system on a chip (SOC), a Complex Programmable Logic Device (CPLD), and the like.
In the context of the present application, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
FIG. 4 is an application scenario diagram of a single turn magnetic encoder automated test fixture, according to an example embodiment. As shown in fig. 4, in the application scenario, first, test data is collected by a lower computer (e.g., C as illustrated in fig. 4); the acquired test data is then input into a server (e.g., S as illustrated in fig. 4) deployed with a single-turn magnetic encoder automated test tooling algorithm, wherein the server is capable of processing the test data based on the single-turn magnetic encoder automated test tooling algorithm to obtain the test result.
The above description is only illustrative of the preferred embodiments of the present application and of the principles of the technology employed. It will be appreciated by persons skilled in the art that the scope of the disclosure referred to in the present application is not limited to the specific combinations of technical features described above, but also covers other technical features formed by any combination of the technical features described above or their equivalents without departing from the spirit of the disclosure. Such as the above-mentioned features and the technical features disclosed in the present application (but not limited to) having similar functions are replaced with each other.
Moreover, although operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order. In certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the application. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination.
Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are exemplary forms of implementing the claims. The specific manner in which the various modules perform the operations in the apparatus of the above embodiments have been described in detail in connection with the embodiments of the method, and will not be described in detail herein.

Claims (8)

1. Automatic test fixture of single circle magnetic encoder, its characterized in that includes: the upper computer and the lower computer, wherein, the working process of upper computer with the lower computer includes: starting the upper computer; selecting an encoder main board to be tested and corresponding firmware data; the upper computer communicates with the lower computer through RS-485 to send a burning instruction and the firmware data; the lower computer selects a correct encoder main board through an FPGA chip, and downloads the firmware data to an editor chip of the encoder main board through an ISP download protocol; after the burning is finished, the lower computer reads the encoder data according to the multi-Moire encoder protocol to check the working state of the encoder main board; collecting test data through the lower computer and sending the test data to the upper computer; the upper computer analyzes the test data to obtain a test result;
The upper computer analyzes the test data to obtain a test result, and the method comprises the following steps: performing embedded coding on each test result item in the test data by using a test embedded coding matrix to obtain a set of test result item embedded coding vectors; the test result item is embedded into a set of coding vectors and input into a global semantic association coder between test results based on a converter structure to obtain a test result global semantic coding feature vector; embedding the test result item into a set of coding vectors and inputting the set of the test result item into a local semantic association coder among test results to obtain a test result local semantic coding feature vector; inputting the test result global semantic coding feature vector and the test result local semantic coding feature vector into a significant fusion network based on feature principal component query matching to obtain a test result multi-scale sparse fusion representation vector; and obtaining the test result based on the test result multi-scale sparse fusion expression vector.
2. The automated single turn magnetic encoder test fixture of claim 1, wherein embedding the set of test result items into the inter-test result local semantic association encoder for the set of test result embedded encoding vectors to obtain the test result local semantic encoding feature vectors comprises: and embedding the test result items into a set of coding vectors, and inputting the set of the test result items into a 1D-CNN model-based inter-test result local semantic association encoder to obtain the test result local semantic coding feature vectors.
3. The automated single-turn magnetic encoder test fixture of claim 2, wherein inputting the test result global semantic coding feature vector and the test result local semantic coding feature vector into a salient fusion network based on feature principal component query matching to obtain a test result multi-scale sparse fusion representation vector, comprises: carrying out standardized processing on the global semantic coding feature vector of the test result and the local semantic coding feature vector of the test result to obtain a global semantic coding feature vector of the standardized test result and a local semantic coding feature vector of the standardized test result; calculating a sample covariance matrix of the standardized test result global semantic coding feature vector and the standardized test result local semantic coding feature vector to obtain a test result global semantic sample covariance matrix and a test result local semantic sample covariance matrix; extracting feature vectors based on matrix decomposition from the test result global semantic sample covariance matrix and the test result local semantic sample covariance matrix to obtain a set of test result global semantic principal component feature vectors and a set of test result local semantic principal component feature vectors; inputting the set of the global semantic principal component feature vectors of the test result and the set of the local semantic principal component feature vectors of the test result into a maximum approximate query matching network to obtain a set of best matching pairs of the global semantic principal component feature vectors of the test result and the local semantic principal component feature vectors of the test result; inputting the optimal matched pairs of the global semantic principal component feature vector of the test result and the local semantic principal component feature vector of the test result into a semantic fine granularity gating joint module to obtain a set of global semantic principal component fusion feature vectors of the test result and a set of local semantic principal component fusion feature vectors of the test result; and cascading the set of the test result global-test result local semantic principal component fusion feature vectors to obtain the test result multi-scale sparse fusion representation vector.
4. The automated single-turn magnetic encoder test fixture of claim 3, wherein normalizing the test result global semantic coding feature vector and the test result local semantic coding feature vector to obtain a normalized test result global semantic coding feature vector and a normalized test result local semantic coding feature vector comprises: respectively calculating the mean value and standard deviation of the global semantic coding feature vector of the test result to obtain the mean value of the global semantic coding feature of the test result and the standard deviation of the global semantic coding feature of the test result; position-based division is carried out on the test result global semantic coding feature vector and the test result global semantic coding feature mean value to obtain a position-based division of the obtained test result global semantic offset vector and the test result global semantic coding feature standard deviation so as to obtain the standardized test result global semantic coding feature vector; respectively calculating the mean value and standard deviation of the local semantic coding feature vector of the test result to obtain the mean value of the local semantic coding feature of the test result and the standard deviation of the local semantic coding feature of the test result; and carrying out position-by-position subtraction on the test result local semantic coding feature vector and the test result local semantic coding feature mean value, and carrying out position-by-position division on the obtained test result local semantic offset vector and the test result local semantic coding feature standard deviation to obtain the standardized test result local semantic coding feature vector.
5. The automated single turn magnetic encoder test fixture of claim 4, wherein calculating the sample covariance matrices of the normalized test result global semantic encoding feature vectors and the normalized test result local semantic encoding feature vectors to obtain a test result global semantic sample covariance matrix and a test result local semantic sample covariance matrix comprises: multiplying the transpose vector of the standardized test result global semantic coding feature vector with the standardized test result global semantic coding feature vector, and then dividing the obtained standardized test result global semantic association matrix with a numerical value obtained by subtracting one from the length of the standardized test result global semantic coding feature vector by positions to obtain the test result global semantic sample covariance matrix; multiplying the transpose vector of the normalized test result local semantic coding feature vector with the normalized test result local semantic coding feature vector, and then dividing the obtained normalized test result local semantic association matrix by a value obtained by subtracting one from the length of the normalized test result local semantic coding feature vector according to positions to obtain the test result local semantic sample covariance matrix.
6. The automated single turn magnetic encoder test fixture of claim 5, wherein inputting the set of test result global semantic principal component feature vectors and the set of test result local semantic principal component feature vectors into a maximum approximation query matching network to obtain a set of best matching pairs of test result global semantic principal component feature vectors and test result local semantic principal component feature vectors, comprises: extracting a preset test result global semantic principal component feature vector in the test result global semantic principal component feature vector set; calculating cosine similarity between the preset test result global semantic principal component feature vector and each test result local semantic principal component feature vector in the test result local semantic principal component feature vector set to obtain a matched query similarity set; and taking the test result local semantic principal component feature vector corresponding to the largest matching query similarity in the set of matching query similarities and the preset test result global semantic principal component feature vector as the optimal matching pair of the preset test result global semantic principal component feature vector and the test result local semantic principal component feature vector.
7. The automated single-turn magnetic encoder test fixture of claim 6, wherein inputting each of the set of best matched pairs of test result global semantic principal component feature vectors and test result local semantic principal component feature vectors into a semantic fine granularity gating joint module to obtain a set of test result global-test result local semantic principal component fusion feature vectors, comprising: respectively calculating the position-by-position difference value, the position-by-position point multiplication and the position-by-position addition between the best matching pair of the test result global semantic principal component feature vector and the test result local semantic principal component feature vector to obtain a test result global-local semantic principal component difference vector, a test result global-local semantic principal component point multiplication vector and a test result global-local semantic principal component addition vector; cascading the test result global-local semantic principal component differential vector, the test result global-local semantic principal component dot product vector and the test result global-local semantic principal component addition vector, and then carrying out one-dimensional convolution coding to obtain a test result global-local semantic principal component multidimensional fusion vector; and carrying out maximum pooling processing based on a local window on the test result global-local semantic principal component multi-dimensional fusion vector to obtain the test result global-test result local semantic principal component fusion feature vector.
8. The automated single-turn magnetic encoder test fixture of claim 7, wherein obtaining the test result based on the test result multi-scale sparse fusion representation vector comprises: inputting the test result multi-scale sparse fusion representation vector into a classifier-based test result generator to obtain the test result.
CN202411307111.7A 2024-09-19 2024-09-19 Automatic test fixture for single-coil magnetic encoder Active CN118818273B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202411307111.7A CN118818273B (en) 2024-09-19 2024-09-19 Automatic test fixture for single-coil magnetic encoder

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202411307111.7A CN118818273B (en) 2024-09-19 2024-09-19 Automatic test fixture for single-coil magnetic encoder

Publications (2)

Publication Number Publication Date
CN118818273A CN118818273A (en) 2024-10-22
CN118818273B true CN118818273B (en) 2024-11-26

Family

ID=93071074

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202411307111.7A Active CN118818273B (en) 2024-09-19 2024-09-19 Automatic test fixture for single-coil magnetic encoder

Country Status (1)

Country Link
CN (1) CN118818273B (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109323716A (en) * 2018-11-01 2019-02-12 上海开通数控有限公司 The serial absolute type encoder of servo drive system detects debugging apparatus
CN114623855A (en) * 2021-10-21 2022-06-14 杭州欣扬风电技术有限公司 Encoder testing method and servo turntable control system

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115359383B (en) * 2022-07-07 2023-07-25 北京百度网讯科技有限公司 Cross-modal feature extraction, retrieval and model training method, device and medium
CN116679192A (en) * 2023-06-29 2023-09-01 福建海睿达科技有限公司 Self-checking device and self-checking method for circuit board of magneto-electric encoder

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109323716A (en) * 2018-11-01 2019-02-12 上海开通数控有限公司 The serial absolute type encoder of servo drive system detects debugging apparatus
CN114623855A (en) * 2021-10-21 2022-06-14 杭州欣扬风电技术有限公司 Encoder testing method and servo turntable control system

Also Published As

Publication number Publication date
CN118818273A (en) 2024-10-22

Similar Documents

Publication Publication Date Title
US11651014B2 (en) Source code retrieval
US11995543B2 (en) Wafer processing method and apparatus, storage medium and electronic device
CN110489345A (en) A kind of collapse polymerization, device, medium and equipment
CN113139617A (en) Power transmission line autonomous positioning method and device and terminal equipment
CN116559619A (en) Semiconductor device testing method and related device
CN118789779B (en) Automatic die changing control system of injection molding machine
CN115905284A (en) A data processing method, device, equipment and storage medium
Xiong A design of bare printed circuit board defect detection system based on YOLOv8
CN115543339A (en) Code conversion method and device, computer equipment and storage medium
CN118818273B (en) Automatic test fixture for single-coil magnetic encoder
CN120892321B (en) Software defect processing method, electronic device, storage medium, and program product
CN117574962A (en) Semiconductor chip detection method, device and storage medium based on transfer learning
CN115952879A (en) A link prediction method and device based on symbolic graph neural network
CN115146394A (en) Decision control model simulation data generation method, device, device and storage medium
CN118823686B (en) Automatic warehouse logistics distribution system and method
CN120411477A (en) Model training method, industrial target detection method, device, equipment and storage medium
CN119648701A (en) A method and system for automatically detecting and evaluating insulating sheets
CN112650477A (en) Project data batch transfer method and device and electronic equipment
CN116016692B (en) Protocol description text construction method, device, equipment and storage medium
CN115718727B (en) An artificial intelligence-based project completion file archiving method and cloud platform
CN111400644B (en) Calculation processing method for laboratory analysis sample
CN118032160A (en) A method, system, electronic device and storage medium for wireless temperature measurement of transformer
CN116841846A (en) Real-time log abnormality detection method, device, equipment and storage medium thereof
CN115062705A (en) Data verification method, data verification device, electronic equipment and storage medium
EP4492261A1 (en) Apparatus and method for aligning scientific instrument metadata to a semantic model

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