Fusion test system and test method of laser radar component

Abstract

The invention discloses a fusion test system and test method of a laser radar component, and relates to the technical field of laser radars, the system comprises a data mobile acquisition platform and a test data analysis terminal; the data mobile acquisition platform comprises optical detection equipment and a signal processing card; the data mobile acquisition platform is connected with the test data analysis terminal; wherein the data mobile acquisition platform is used for being in butt joint with a to-be-tested laser radar component; the optical detection equipment is used for carrying out optical test on the to-be-tested laser radar component to obtain optical test data; the signal processing card is used for carrying out an electrical test on the to-be-tested laser radar component to obtain electrical test data; and the test data analysis terminal is used for performing analysis according to the optical test data and the electrical test data. According to the invention, optical test data and electrical test data are simultaneously acquired through the data mobile acquisition platform, so that the test of the laser radar component is realized.

Description

Technical Field

[0001] The present application relates to the field of laser radar technology, and more specifically, to a fusion test system and test method for laser radar components. Background Art

[0002] The technical route of LiDAR is a complex system involving multidisciplinary intersection and multi-technical integration. From light source generation to beam control, to signal reception and processing, and finally to data analysis and application, each link is crucial and together constitutes a complete system of LiDAR technology. Therefore, the testing of LiDAR components also requires the processing of multiple information.

[0003] The laser radar component testing system in the prior art generally has a trigger unit, which drives the signal generator in response to receiving the signal of the laser radar sensor to be tested, so that the signal generation unit of the signal generator outputs the recorded light signal, and then powers on to test the electrical signal in the laser radar component.

[0004] However, when testing LiDAR components, the existing technology requires separate testing for each detection item of the LiDAR components, and the LiDAR components need to be installed repeatedly, resulting in low test efficiency and discretization of test data, which is not conducive to large-scale production and iterative optimization of LiDAR. Summary of the invention

[0005] In response to at least one defect or improvement need in the prior art, the present invention provides a fusion test system and test method for laser radar components, which are used to solve the problem in the prior art that each detection item of the laser radar component needs to be tested separately, and the laser radar component needs to be installed repeatedly, resulting in low test efficiency and discretization of test data, which is not conducive to large-scale production and iterative optimization of laser radar.

[0006] To achieve the above-mentioned object, according to a first aspect of the present invention, a fusion test system for a laser radar component is provided, comprising: a data mobile acquisition platform and a test data analysis terminal; the data mobile acquisition platform comprises an optical detection device and a signal processing card; the data mobile acquisition platform is connected to the test data analysis terminal;

[0007] Among them, the data mobile acquisition platform is used to connect with the laser radar components to be tested;

[0008] The optical detection equipment is used to perform optical tests on the laser radar components to be tested and obtain optical test data;

[0009] The signal processing card is used to perform electrical tests on the laser radar components to be tested and obtain electrical test data;

[0010] The test data analysis terminal is used to perform analysis based on the optical test data and the electrical test data.

[0011] In a possible implementation, the optical detection device also includes: a photodetector; the photodetector is used to detect the light output power of the laser radar component to be tested.

[0012] In a possible implementation, the optical detection device also includes: an industrial camera; the industrial camera is used to obtain image information of the laser radar component to be tested.

[0013] In a possible implementation, it also includes: an information transmission terminal; the information transmission terminal is connected to the test data analysis terminal and is used for the test data analysis terminal to exchange data with an external device.

[0014] In a possible implementation, the information transmission end includes a switch; the switch is used to establish a local area network for the test data analysis terminal to exchange data with an external device.

[0015] In a possible implementation, the information transmission end includes a router; the router is used to establish a wide area network for the test data analysis terminal to exchange data with an external device.

[0016] In a possible implementation, it also includes: a database server; the database server is connected to the information transmission end; and the database server is used to store data sent by the information transmission end.

[0017] According to a second aspect of the present invention, a fusion test method for a laser radar component is also provided, based on any possible implementation as described above, including:

[0018] Acquire optical test data of the laser radar component to be tested by optical detection equipment;

[0019] Obtain electrical test data of the laser radar component to be tested through the signal processing card;

[0020] The laser radar component to be tested is subjected to fusion analysis based on the optical test data and the electrical test data. In a possible implementation, the laser radar component to be tested is subjected to fusion analysis based on the optical test data and the electrical test data, including:

[0021] Perform fuzzy logic reasoning on optical test data and electrical test data to obtain multi-modal test data;

[0022] The initial convolutional neural network is trained using historical test data to obtain a fully trained target convolutional neural network;

[0023] The multimodal test data is input into the target convolutional neural network for testing to obtain the test results.

[0024] In one possible implementation, the initial convolutional neural network is trained using historical test data to obtain a fully trained target convolutional neural network, including:

[0025] Extract feature information of LiDAR components from historical test data through feature selection and extraction mechanisms;

[0026] Execute multiple convolutional neural network operators in parallel to configure neural network parameters based on feature information of the lidar components;

[0027] Test the historical test data according to the neural network parameters and calculate the accuracy of the test results;

[0028] The convolutional neural network is trained cyclically until the test result accuracy exceeds the preset test accuracy threshold.

[0029] In general, the above technical solutions conceived by the present invention can achieve the following beneficial effects compared with the prior art:

[0030] (1) The present invention provides a fusion test system for laser radar components, which combines optical detection equipment and signal processing cards, and can simultaneously perform optical and electrical tests on the laser radar components to be tested, ensuring a comprehensive evaluation of the laser radar components on multiple key performance indicators and improving the accuracy and completeness of the test. The data mobile acquisition platform can collect optical and electrical test data in real time, and through connection with the test data analysis terminal, it can achieve rapid data transmission and analysis, shorten the test cycle, and improve test efficiency. The data mobile acquisition platform enables it to easily connect with different types of laser radar components to meet the testing requirements of different models and specifications. By integrating optical and electrical test functions into one system, the need to use multiple independent test equipment is avoided, which not only reduces equipment investment costs, but also reduces maintenance and operating costs during the test process.

[0031] (2) The present invention provides a fusion test method for laser radar components. By simultaneously acquiring optical test data and electrical test data of the laser radar components, the method can provide a more comprehensive performance evaluation. Optical test data can reflect the optical performance of the laser radar, such as emission, reception, and scanning, while electrical test data can reflect its performance in circuits, signal processing, and other aspects. Fusion analysis of optical test data and electrical test data can make full use of the complementarity of the two types of data to reveal potential problems in the performance and function of the laser radar components, help to discover defects or anomalies that may not be detected by a single data type, and improve the accuracy of the analysis results. The configuration of the optical detection equipment, signal processing card, and convolutional neural network can be easily adjusted to meet new testing requirements. At the same time, this method can also be combined with other testing technologies to form a more complete testing system. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0033] Figure 1 A schematic structural diagram of an embodiment of a fusion test system for laser radar components provided by the present invention;

[0034] Figure 2 A schematic diagram of a flow chart of an embodiment of a fusion test method for a laser radar component provided by the present invention;

[0035] Figure 3 The present invention provides Figure 2 A schematic diagram of a flow chart of an embodiment of step S203;

[0036] Figure 4 The present invention provides Figure 3 FIG. 5 is a flow chart of an embodiment of step S302 in FIG. DETAILED DESCRIPTION

[0037] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0038] The terms "first", "second", "third", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0039] The present invention provides a fusion test system and test method for laser radar components, which are described below respectively.

[0040] See also Figure 1 , Figure 1The present invention is a structural schematic diagram of an embodiment of a fusion test system for a laser radar component provided by the present invention. In a specific embodiment of the present invention, a fusion test system 100 for a laser radar component is disclosed, including: a data mobile acquisition platform 110 and a test data analysis terminal 120; the data mobile acquisition platform 110 includes an optical detection device 111 and a signal processing card 112; the data mobile acquisition platform 110 and the test data analysis terminal 120 are connected;

[0041] The data mobile acquisition platform 110 is used to connect with the laser radar component to be tested;

[0042] The optical detection device 111 is used to perform optical testing on the laser radar component to be tested and obtain optical testing data;

[0043] The signal processing card 112 is used to perform electrical testing on the laser radar component to be tested and obtain electrical test data;

[0044] The test data analysis terminal 120 is used to perform analysis based on the optical test data and the electrical test data.

[0045] In the above embodiment, the data mobile acquisition platform 110 is responsible for docking with the laser radar component to be tested. The data mobile acquisition platform 110 integrates a variety of advanced testing equipment to achieve multi-dimensional testing of the laser radar component. Among them, the optical detection device 111 is an important part of the test system. It uses precision optical components and detection technology to perform optical performance tests on the laser radar component to be tested. Through the optical detection device 111, various optical parameters of the laser radar component when transmitting and receiving optical signals can be obtained, such as light intensity, spot size, beam divergence angle, etc. These parameters are crucial for evaluating the optical performance of the laser radar component.

[0046] In addition to optical testing, the data mobile acquisition platform 110 is also equipped with a signal processing card 112 for performing electrical performance testing on the laser radar component to be tested. The signal processing card 112 is capable of receiving and processing electrical signals from the laser radar component, such as current, voltage, etc., and extracting electrical parameters related to the performance of the laser radar component through a built-in signal processing algorithm. These electrical parameters can be used to understand the working status of the laser radar component, evaluate its performance stability, and discover potential fault points.

[0047] After completing the optical and electrical tests, the data mobile acquisition platform 110 will transmit the collected test data to the test data analysis terminal 120. The test data analysis terminal 120 is the back end of the entire test system. It is responsible for receiving and processing the test data from the data mobile acquisition platform 110. By using advanced algorithms and data analysis technology, the test data analysis terminal 120 can conduct in-depth analysis and mining of optical test data and electrical test data, and extract key information related to the performance of the LiDAR components. This information can further fully understand the performance characteristics of the LiDAR components, discover potential performance bottlenecks, and provide strong data support for subsequent improvements and optimizations.

[0048] In addition, the fusion test system is highly flexible and scalable. The design of the data mobile acquisition platform 110 enables it to easily adapt to the testing requirements of lidar components of different models and specifications, while the test data analysis terminal 120 can expand its functions by upgrading software or adding new analysis modules. This flexibility and scalability enables the test system to continuously adapt to the development of lidar technology and meet higher levels of testing requirements in the future.

[0049] Compared with the prior art, the present embodiment provides a fusion test system 100 for laser radar components, which combines an optical detection device 111 and a signal processing card 112, and can simultaneously perform optical and electrical tests on the laser radar components to be tested, thereby ensuring a comprehensive evaluation of the laser radar components on multiple key performance indicators and improving the accuracy and completeness of the test. The data mobile acquisition platform 110 can collect optical and electrical test data in real time, and through connection with the test data analysis terminal 120, it can realize rapid data transmission and analysis, shorten the test cycle, and improve test efficiency. The data mobile acquisition platform 110 enables it to easily connect with different types of laser radar components to meet the testing requirements of different models and specifications. By integrating optical and electrical test functions into one system, the need to use multiple independent test equipment is avoided, which not only reduces the equipment investment cost, but also reduces the maintenance and operating costs during the test process.

[0050] In some embodiments of the present invention, the optical detection device 111 further includes: a photodetector; the photodetector is used to detect the light output power of the laser radar component to be tested.

[0051] In the above embodiment, the optical detection device 111 has been further improved, not only including the original detection function, but also adding new components to improve the comprehensiveness and accuracy of the test. Specifically, the optical detection device 111 is equipped with a photodetector, which can accurately detect the optical output power of the laser radar component to be tested. The optical output power is one of the important indicators for measuring the performance of the laser radar component. It is directly related to the detection distance and accuracy of the laser radar. Through the test of the laser radar component to be tested by the photodetector, the optical output power data of the laser radar component under different working conditions can be obtained, which provides strong support for subsequent performance evaluation and optimization.

[0052] In some embodiments of the present invention, the optical detection device 111 further includes: an industrial camera; the industrial camera is used to obtain image information of the laser radar component to be tested.

[0053] In the above embodiment, in order to more intuitively understand the appearance and structural features of the laser radar components, the optical detection device 111 is also equipped with an industrial camera. The industrial camera has high resolution and stable imaging performance, and can clearly capture the image information of the laser radar components to be tested. This information is of great significance for analyzing the assembly quality of the laser radar components, identifying potential structural defects, and evaluating their appearance consistency.

[0054] In some embodiments of the present invention, the signal processing card 112 further includes: a signal generating card; the signal generating card is used to obtain an analog signal of the laser radar component to be tested.

[0055] In the above embodiment, a signal generating card is added to the signal processing card 112. The signal generating card can simulate and generate analog signals related to the laser radar component to be tested. By inputting these analog signals into the laser radar component, its response can be observed, thereby evaluating the signal processing capability and stability of the laser radar component to be tested. This function is of great significance for discovering and solving potential problems in the signal processing of the laser radar component.

[0056] In some embodiments of the present invention, the signal processing card 112 further includes: a signal acquisition card; the signal acquisition card is used to acquire analog signals of the laser radar component to be tested and convert the analog signals into digital signals.

[0057] In the above embodiment, the signal processing card 112 is also equipped with a signal acquisition card for collecting analog signals output by the laser radar component to be tested and converting them into digital signals for subsequent processing and analysis. The signal acquisition card has the ability of high-precision and high-speed acquisition, which can ensure that the collected signal data is accurate and complete. Through the conversion of the signal acquisition card, the analog signal can be converted into a digital signal that can be recognized by the computer, which facilitates the subsequent data analysis and processing.

[0058] In some embodiments of the present invention, it further includes: an information transmission terminal 130; the information transmission terminal 130 is connected to the test data analysis terminal 120, and is used for the test data analysis terminal 120 to exchange data with an external device.

[0059] In the above embodiments, in order to further improve the data exchange capability of the test system, some embodiments of the present invention further add an information transmission terminal 130, which is connected to the test data analysis terminal 120, for realizing data exchange between the test data analysis terminal 120 and an external device, so that the fusion test system of the lidar component can be seamlessly connected with other systems or devices to realize data sharing and interaction.

[0060] In some embodiments of the present invention, the information transmission terminal 130 includes a switch 131; the switch 131 is used to establish a local area network for the test data analysis terminal 120 to exchange data with external devices.

[0061] In the above embodiment, a switch 131 is used to establish a local area network to provide a high-speed and stable data exchange channel for the test data analysis terminal 120 and external devices. The switch 131 has the capabilities of high-speed forwarding and intelligent routing, which can ensure the rapid transmission and efficient exchange of data within the local area network.

[0062] In some embodiments of the present invention, the information transmission terminal 130 includes a router 132; the router 132 is used to establish a wide area network for the test data analysis terminal 120 to exchange data with external devices.

[0063] In the above embodiment, a router 132 is used to establish a wide area network to provide cross-regional data exchange capabilities for the test data analysis terminal 120 and external devices. The router 132 has powerful network interconnection and routing selection functions, which can ensure the safe and reliable transmission of data within the wide area network.

[0064] In some embodiments of the present invention, it further includes: a database server 140; the database server 140 is connected to the information transmission terminal 130; and the database server 140 is used to store data sent by the information transmission terminal 130.

[0065] In the above embodiments, in order to achieve long-term storage and management of test data, some embodiments of the present invention further add a database server 140, which is connected to the information transmission terminal 130 and is used to store data sent by the information transmission terminal 130. The database server 140 has the ability of large-capacity storage and efficient data retrieval, and can ensure the integrity and security of the test data. With the support of the database server 140, the test data can be easily queried, analyzed and utilized, providing strong support for subsequent research and development and optimization.

[0066] See also Figure 2 , Figure 2 A flow chart of an embodiment of a fusion test method for a laser radar component provided by the present invention. According to a second aspect of the present invention, a fusion test method for a laser radar component is also provided, based on any one of the above embodiments, including:

[0067] S201, obtaining optical test data of the laser radar component to be tested through an optical detection device;

[0068] S202, obtaining electrical test data of the laser radar component to be tested through a signal processing card;

[0069] S203, performing fusion analysis on the laser radar component to be tested according to the optical test data and the electrical test data.

[0070] In the above embodiment, the optical test data of the laser radar component to be tested is obtained through the optical detection device 111, and the components such as the photoelectric detector in the optical detection device 111 are used to perform an accurate optical performance test on the laser radar component to be tested. During the test, the optical detection device 111 will capture the optical signals emitted and received by the laser radar component and convert them into optical test data that can be subsequently analyzed. These optical test data contain the key optical performance parameters of the laser radar component, such as light intensity, spot size, beam divergence angle, and light output power.

[0071] The electrical test data of the laser radar component to be tested is obtained through the signal processing card 112. The signal generation card in the signal processing card 112 can simulate and generate analog signals related to the laser radar component and observe its response. At the same time, the signal acquisition card will collect the analog signals output by the laser radar component and convert them into digital signals for subsequent analysis, which can comprehensively evaluate the electrical performance of the laser radar component, including signal processing speed, stability, and conversion accuracy of analog signals.

[0072] After obtaining the optical and electrical test data, the next step is to analyze the test data. First, the binding accuracy of the optical devices of the lidar component to be tested is analyzed based on the optical test data. Binding accuracy is an important indicator for measuring the assembly quality of optical devices in lidar components. By analyzing the light intensity distribution, spot shape and other parameters in the optical test data, it can be inferred whether the binding between the optical devices is tight and the position is accurate, thereby evaluating its binding accuracy.

[0073] The welding quality of the electrical components of the LiDAR components to be tested is analyzed based on the electrical test data. The welding quality is one of the key factors affecting the electrical performance of LiDAR components. By analyzing the current, voltage and other parameters in the electrical test data, it is possible to determine whether the welding between the electrical components is firm and the contact is good, thereby evaluating the welding quality.

[0074] It should be noted that the analysis method in the prior art can be used when analyzing the optical test data and the electrical test data. In the lidar test, there are related algorithms that can be used directly, and the present invention will not go into details about this.

[0075] See also Figure 3 , Figure 3 The present invention provides Figure 2 FIG. 1 is a flow chart of an embodiment of step S203 in FIG. 1 . In some embodiments of the present invention, a fusion analysis is performed on the laser radar component to be tested according to the optical test data and the electrical test data, including:

[0076] S301, performing fuzzy logic reasoning on optical test data and electrical test data to obtain multimodal test data;

[0077] S302, using historical test data to train the initial convolutional neural network to obtain a fully trained target convolutional neural network;

[0078] S303: Input the multimodal test data into the target convolutional neural network for testing to obtain test results.

[0079] In the above embodiment, the optical test data and electrical test data of the laser radar component are first integrated. The optical test data may include parameters such as light intensity, spot shape, scattering characteristics, etc., while the electrical test data may cover performance indicators such as current, voltage, power consumption, etc. In order to more comprehensively reflect the working status of the laser radar component, the fuzzy logic reasoning method is used to process these original test data.

[0080] Fuzzy logic reasoning is a reasoning method that can handle uncertain information. It allows decision-making in the case of incomplete certainty. By fuzzifying the optical and electrical test data, more abstract and comprehensive feature information can be extracted to form multimodal test data. These data not only contain the direct information of the original test data, but also incorporate the indirect information obtained through fuzzy reasoning, providing richer input for subsequent convolutional neural network testing.

[0081] Use historical test data to train an initial convolutional neural network (CNN). This historical data should include the test results of multiple lidar components under different conditions, as well as the corresponding label information (such as whether the component is qualified, performance level, etc.).

[0082] During the training process, the weights and bias parameters of CNN are constantly adjusted to minimize the error between the prediction results and the label information. As the training progresses, CNN gradually learns how to extract key features from the input multimodal test data and make accurate classification or regression predictions based on these features. When the training reaches the preset stop condition (such as error convergence, the number of iterations reaches the upper limit, etc.), a fully trained target convolutional neural network is obtained.

[0083] The multimodal test data of the lidar component to be tested is input into the fully trained target convolutional neural network. The convolutional neural network will process the input multimodal data according to the learned feature extraction and classification / regression rules, and output the corresponding test results.

[0084] The test results may include key information such as the performance level of the LiDAR components and whether they are qualified. These results not only provide an important basis for the quality control and performance evaluation of LiDAR components, but can also be used to guide subsequent improvement and optimization work.

[0085] See also Figure 4 , Figure 4 The present invention provides Figure 3 In some embodiments of the present invention, the initial convolutional neural network is trained using historical test data to obtain a fully trained target convolutional neural network, including:

[0086] S401, extracting feature information of laser radar components from historical test data through a feature selection and extraction mechanism;

[0087] S402, executing multiple convolutional neural network operators in parallel to configure neural network parameters based on feature information of the laser radar component;

[0088] S403, testing the historical test data according to the neural network parameters, and calculating the accuracy of the test results;

[0089] S404, performing cyclic training on the convolutional neural network until the test result accuracy exceeds a preset test accuracy threshold.

[0090] In the above embodiment, it is first necessary to extract the key feature information of the LiDAR components from the historical test data. This feature information may include optical properties (such as light intensity distribution, spot shape), electrical properties (such as current, voltage, power consumption) and other parameters related to the performance of the LiDAR components. In order to effectively extract these features, feature selection and extraction mechanisms such as principal component analysis (PCA), linear discriminant analysis (LDA) or deep learning-based methods (such as autoencoders) can be used. Through these methods, the most representative features can be screened out from the historical test data, providing strong support for the subsequent training of convolutional neural networks.

[0091] After extracting the characteristic information of the LiDAR components, it is necessary to use these features to configure the parameters of the convolutional neural network and execute multiple convolutional neural network operators in parallel, such as convolution layers, pooling layers, and fully connected layers, to build the basic architecture of the neural network. At the same time, according to the characteristics of the characteristic information, adjust the parameters of each operator (such as convolution kernel size, step size, padding method, etc.) to ensure that the neural network can accurately capture the key details in the characteristic information. Executing multiple operators in parallel can accelerate the training process of the neural network and improve training efficiency.

[0092] During model inference, different convolutional neural network (CNN) operators can be executed in parallel. This means that if the model contains multiple independent calculation steps (such as convolution, pooling, activation, etc.), these steps can be run simultaneously on different processing units instead of sequentially. By executing these operators in parallel, the system can use computing resources more efficiently, thereby achieving a 1.1 to 1.5 times acceleration of inference. This acceleration effect directly improves the processing speed of the model, allowing the automatic test terminal to output results faster.

[0093] The processing task can be broken down into multiple stages, each of which is responsible for processing a part of the task, which helps to better manage the complexity and computing requirements of the task. Different processing units (such as CPU, GPU, etc.) are assigned to different task stages, ensuring that each stage can get appropriate computing resources and avoiding idle or overloaded resources. Since the task is broken down into multiple stages and executed in parallel on different processing units, the parallel processing capability of the overall task is significantly improved, which not only speeds up the processing speed of the task, but also improves the throughput and operating efficiency of the system.

[0094] The GPU built into the automatic test terminal is good at handling large-scale parallel computing tasks, especially in processing image and video data. Multimodal test data (such as images, sounds, etc.) can be processed synchronously immediately after entering the terminal. The GPU built into the automatic test terminal allows multiple data streams to be processed at the same time. Due to the efficient parallel processing capabilities of the GPU, the inference time of multimodal test data has been significantly shortened, allowing the automatic test terminal to respond to test requests more quickly and improve the overall performance of the system.

[0095] After configuring the neural network parameters, you need to use historical test data to test the neural network to evaluate its performance. Input the historical test data into the neural network and calculate the error between the output of the neural network and the true label. By calculating the accuracy of the test results (such as accuracy, recall, F1 score, etc.), you can understand the performance of the neural network under the current parameter configuration.

[0096] Finally, the convolutional neural network is trained in a loop to continuously optimize its parameter configuration. In each loop, the parameters of the neural network are adjusted according to the accuracy of the test results obtained in the previous step. If the test result accuracy is lower than the preset test accuracy threshold, the neural network will continue to be trained; if the test result accuracy exceeds the preset test accuracy threshold, the neural network is considered to have been fully trained, and the training can be stopped and the final neural network model can be saved.

[0097] In summary, the present invention provides a fusion test system 100 for laser radar components, which combines an optical detection device 111 and a signal processing card 112, and can simultaneously perform optical and electrical tests on the laser radar components to be tested, thereby ensuring a comprehensive evaluation of the laser radar components on multiple key performance indicators and improving the accuracy and completeness of the test. The data mobile acquisition platform 110 can collect optical and electrical test data in real time, and through the connection with the test data analysis terminal 120, it can realize rapid data transmission and analysis, shorten the test cycle, and improve the test efficiency. The data mobile acquisition platform 110 enables it to easily connect with different types of laser radar components to meet the testing requirements of different models and specifications. By integrating optical and electrical test functions into one system, the need to use multiple independent test equipment is avoided, which not only reduces the equipment investment cost, but also reduces the maintenance and operating costs during the test process.

[0098] The present application also provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the steps of the above method are implemented. The computer-readable storage medium may include, but is not limited to, any type of disk, including a floppy disk, an optical disk, a DVD, a CD-ROM, a micro drive, and a magneto-optical disk, a ROM, a RAM, an EPROM, an EEPROM, a DRAM, a VRAM, a flash memory device, a magnetic card or an optical card, a nanosystem (including a molecular memory IC), or any type of medium or device suitable for storing instructions and / or data.

[0099] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0100] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0101] In the several embodiments provided in the present application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0102] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0103] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0104] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, disk or optical disk and other media that can store program code.

[0105] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, which can include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0106] The above is only an exemplary embodiment of the present disclosure, and the scope of the present disclosure cannot be limited thereto. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the specification and practicing the disclosure here, those skilled in the art will easily think of the implementation scheme of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the technical field not recorded in the present disclosure. The description and examples are regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

[0107] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0108] It will be easily understood by those skilled in the art that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A fusion test system for laser radar components, characterized in that: include: A data mobile acquisition platform and a test data analysis terminal; the data mobile acquisition platform includes an optical detection device and a signal processing card; the data mobile acquisition platform is connected to the test data analysis terminal; Wherein, the data mobile acquisition platform is used to connect with the laser radar component to be tested; The optical detection device is used to perform optical testing on the laser radar component to be tested and obtain optical test data; The signal processing card is used to perform electrical testing on the laser radar component to be tested and obtain electrical testing data; The test data analysis terminal is used to perform analysis based on the optical test data and the electrical test data.

2. The fusion test system of laser radar components according to claim 1, characterized in that: The optical detection device also includes: a photoelectric detector; the photoelectric detector is used to detect the light output power of the laser radar component to be tested.

3. The fusion test system of laser radar components according to claim 1, characterized in that: The optical detection equipment also includes: an industrial camera; the industrial camera is used to obtain image information of the laser radar component to be tested.

4. The fusion test system of laser radar components according to claim 1, characterized in that: Also includes: Information transmission end; The information transmission end is connected to the test data analysis terminal and is used for the test data analysis terminal to exchange data with an external device.

5. The fusion test system of laser radar components as claimed in claim 4, characterized in that: The information transmission end includes a switch; the switch is used to establish a local area network for the test data analysis terminal to exchange data with external devices.

6. The fusion test system of laser radar components as claimed in claim 4, characterized in that: The information transmission end includes a router; the router is used to establish a wide area network for the test data analysis terminal to exchange data with external devices.

7. The fusion test system of laser radar components as claimed in claim 4, characterized in that: It also includes: a database server; the database server is connected to the information transmission end; the database server is used to store the data sent by the information transmission end.

8. A fusion test method for a laser radar component, based on the fusion test system for a laser radar component as described in any one of claims 1 to 7, characterized in that: include: Acquiring optical test data of the laser radar component to be tested by the optical detection device; Acquiring electrical test data of the laser radar component to be tested through the signal processing card; The laser radar component to be tested is subjected to a fusion analysis based on the optical test data and the electrical test data.

9. The fusion test method of laser radar components according to claim 8, characterized in that: The performing fusion analysis on the laser radar component to be tested according to the optical test data and the electrical test data includes: Performing fuzzy logic reasoning on the optical test data and the electrical test data to obtain multimodal test data; The initial convolutional neural network is trained using historical test data to obtain a fully trained target convolutional neural network; The multimodal test data is input into the target convolutional neural network for testing to obtain a test result.

10. The fusion test method of laser radar components according to claim 9, characterized in that: The method of using historical test data to train the initial convolutional neural network to obtain a fully trained target convolutional neural network includes: Extracting feature information of the laser radar component from the historical test data through a feature selection and extraction mechanism; Executing multiple convolutional neural network operators in parallel to configure neural network parameters based on feature information of the laser radar component; Testing the historical test data according to the neural network parameters, and calculating the accuracy of the test results; The convolutional neural network is trained cyclically until the accuracy of the test result exceeds a preset test accuracy threshold.

Images