CN112070246A - Photovoltaic product defect detection algorithm deployment system - Google Patents
Photovoltaic product defect detection algorithm deployment systemDownload PDFInfo
- Publication number
- CN112070246A CN112070246ACN202010868972.8ACN202010868972ACN112070246ACN 112070246 ACN112070246 ACN 112070246ACN 202010868972 ACN202010868972 ACN 202010868972ACN 112070246 ACN112070246 ACN 112070246A
- Authority
- CN
- China
- Prior art keywords
- algorithm
- service
- photovoltaic
- detection algorithm
- task
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06316—Sequencing of tasks or work
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Operations Research (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Pathology (AREA)
- Immunology (AREA)
- Biochemistry (AREA)
- Analytical Chemistry (AREA)
- Computer Networks & Wireless Communication (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Chemical & Material Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Photovoltaic Devices (AREA)
Abstract
Description
Translated fromChinese技术领域technical field
本发明属于新能源技术领域，特别涉及一种光伏产品缺陷检测算法部署系统。The invention belongs to the technical field of new energy, and in particular relates to a photovoltaic product defect detection algorithm deployment system.
背景技术Background technique
光伏发电是目前应用最为广泛的新能源发电形式。太阳能电池板是光伏发电的核心器件，其生产、安装过程中不可避免产生的缺陷将严重影响发电效率。常见的产品缺陷有隐裂、虚焊、失效、断栅等，其中，隐裂是因碰撞按压出现在电池片主栅线或边缘的细线状裂纹；虚焊是焊接不良形成的矩形阴影；失效是明确形状边缘的深黑色块状；断栅是副栅线断裂形成的絮状或块状阴影。因此，太阳能电池板的缺陷检测是生产过程中必不可少的环节。然而，在电池板制造工厂生产过程中，大多采用人工目视进行缺陷检测。由于目视的方法具有很强的主观性，且人眼容易疲劳，检测可靠性和效率较低。Photovoltaic power generation is currently the most widely used form of new energy power generation. Solar panels are the core components of photovoltaic power generation, and the inevitable defects in the production and installation process will seriously affect the power generation efficiency. Common product defects include cracks, virtual welding, failure, broken grid, etc. Among them, cracks are thin linear cracks that appear on the busbar line or edge of the cell due to collision and pressing; virtual welding is a rectangular shadow formed by poor welding; Failures are dark black blocks with well-defined shape edges; broken grids are flocculent or blocky shadows formed by the fracture of secondary grid lines. Therefore, defect detection of solar panels is an essential part of the production process. However, in the production process of the panel manufacturing plant, human visual inspection is mostly used for defect detection. Because the visual method is highly subjective, and the human eye is easily fatigued, the detection reliability and efficiency are low.
发明内容SUMMARY OF THE INVENTION
本发明实施例提供了一种光伏产品缺陷检测算法部署系统，该部署系统包括，The embodiment of the present invention provides a photovoltaic product defect detection algorithm deployment system, the deployment system includes:
光伏产品产线机台，通过设于该机台的客户端获取光伏产品的照片，并将获取的光伏产品的照片发送至任务中心；Photovoltaic product production line machine, obtain photos of photovoltaic products through the client installed on the machine, and send the obtained photos of photovoltaic products to the task center;
任务中心，该任务中心的服务，接收由机台客户端发送的光伏产品照片，根据产品缺陷类型列入检测任务，将检测任务下发给算法服务器集群；The task center, the service of the task center, receives the photos of photovoltaic products sent by the machine client, lists the inspection tasks according to the product defect type, and sends the inspection tasks to the algorithm server cluster;
算法服务器集群，包括多个算法服务器，根据产品缺陷类型，每个算法服务器对应一个缺陷检测算法服务。The algorithm server cluster includes multiple algorithm servers. According to the product defect type, each algorithm server corresponds to a defect detection algorithm service.
本发明实施例有益效果之一，提高了光伏产品缺陷检测效率，降低了部署成本，增加了检测算法部署灵活性。One of the beneficial effects of the embodiments of the present invention is that the defect detection efficiency of photovoltaic products is improved, the deployment cost is reduced, and the deployment flexibility of the detection algorithm is increased.
附图说明Description of drawings
通过参考附图阅读下文的详细描述，本发明示例性实施方式的上述以及其他目的、特征和优点将变得易于理解。在附图中，以示例性而非限制性的方式示出了本发明的若干实施方式，其中：The above and other objects, features and advantages of exemplary embodiments of the present invention will become readily understood by reading the following detailed description with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present invention are shown by way of example and not limitation, wherein:
图1现有的光伏产品缺陷检测算法部署系统架构图。Figure 1 is an architecture diagram of an existing photovoltaic product defect detection algorithm deployment system.
图2根据本发明实施例之一的光伏产品缺陷检测算法部署系统架构图。FIG. 2 is an architecture diagram of a photovoltaic product defect detection algorithm deployment system according to one embodiment of the present invention.
具体实施方式Detailed ways
为提高太阳能电池板的缺陷检测可靠性和效率，主要的解决方案是采用基于图像识别、机器学习等各类视觉算法的检测方案。现有的一种算法部署方案，是基于B/S应用架构，将所有功能都开发和打包在一起，属于“单体应用”，整体架构如图1所示。其中多个服务器进行负载均衡，当用户访问量变大时服务器也能支撑；将静态文件独立出来，通过CDN等手段进行加速，可以提升应用的整体响应。CDN的全称是Content Delivery Network，即内容分发网络。CDN是构建在现有网络基础之上的智能虚拟网络，依靠部署在各地的边缘服务器，通过中心平台的负载均衡、内容分发、调度等功能模块，使用户就近获取所需内容，降低网络拥塞，提高用户访问响应速度和命中率。CDN的关键技术主要有内容存储和分发技术。In order to improve the reliability and efficiency of defect detection of solar panels, the main solution is to use detection schemes based on various visual algorithms such as image recognition and machine learning. An existing algorithm deployment scheme is based on the B/S application architecture, and all functions are developed and packaged together, which belongs to "single application". The overall architecture is shown in Figure 1. Among them, multiple servers perform load balancing, and the server can also support when the number of user visits increases; the static files are isolated and accelerated by means such as CDN, which can improve the overall response of the application. The full name of CDN is Content Delivery Network, that is, Content DeliveryNetwork . CDN is an intelligent virtual network built on the basis of the existing network, relying on edge servers deployed in various places, through the load balancing, content distribution, scheduling and other functional modules of the central platform, so that users can obtain the desired content nearby, reducing network congestion, Improve user access response speed and hit rate. The key technologies of CDN mainly include content storage and distribution technology.
单体应用一般在一个服务器上同时部署检测算法、数据库应用、web服务器等，以及一系列的定时任务。使用复杂脚本和手工流程进行应用的安装和升级。进程间的通信也是借助本地文件系统(比如在磁盘上放一个文件，另一个进程来读取)。使用本地文件系统来持久化存储，数据文件和应用的文件混合在一起。配置是存储在文件里的，通常散落在多个位置，并与应用的文件混在一起。实践中，光伏缺陷检测领域单体应用具有如下局限：Monolithic applications generally deploy detection algorithms, database applications, web servers, etc. on one server at the same time, as well as a series of timing tasks. Install and upgrade applications using complex scripts and manual processes. Communication between processes is also done by means of the local file system (for example, a file is placed on disk, and another process reads it). Using the local file system for persistent storage, data files are mixed with application files. Configurations are stored in files, usually scattered across multiple locations, and mixed with the application's files. In practice, the single application in the field of photovoltaic defect detection has the following limitations:
(1)代码臃肿，应用启动时间长。检测产品一般包括客户端、检测算法(图像识别、机器学习等)、数据库、web应用、MES对接、相关硬件操作等，将所有应用建立在一套代码中，代码逻辑复杂、耦合度高，应用启动时间长。(1) The code is bloated and the application startup time is long. Detection products generally include clients, detection algorithms (image recognition, machine learning, etc.), databases, web applications, MES docking, related hardware operations, etc., all applications are built in a set of codes, the code logic is complex, the coupling degree is high, and the application Long startup time.
(2)回归测试周期长，修复一个小小bug可能都需要对所有关键业务进行回归测试。所有应用整体打包，牵一发动全身。(2) The regression test cycle is long, and repairing a small bug may require regression testing of all key businesses. All applications are packaged as a whole, pulling the whole body.
(3)应用容错性差，任何一个部件出现某个小小的错误都有可能导致整个系统宕机。(3) The fault tolerance of the application is poor, and a small error in any component may cause the entire system to go down.
(4)伸缩困难，单体应用扩展性能时只能整个应用进行扩展，造成计算资源浪费。(4) Scaling is difficult. When a single application expands its performance, only the entire application can be expanded, resulting in a waste of computing resources.
(5)开发协作困难，一个大型应用系统，可能几十个甚至上百个开发人员，大家都在维护一套代码的话，代码merge复杂度急剧增加。(5) Development and collaboration are difficult. In a large-scale application system, there may be dozens or even hundreds of developers. If everyone maintains a set of codes, the complexity of code merge increases dramatically.
(6)自动化部署困难。开发环境和测试环境差异较大，导致一些生产环境问题不能在测试期间发现。(6) Difficulty in automated deployment. The development environment and the test environment are quite different, so some production environment problems cannot be discovered during the test.
根据一个或者多个实施例，光伏产品缺陷检测算法部署系统，基于docker容器化技术，将光伏检测产品中的各个模块服务化，通过容器化实现了服务化部署，从而解决单体应用部署模式存在的较多局限。According to one or more embodiments, the photovoltaic product defect detection algorithm deployment system, based on the docker containerization technology, serves each module in the photovoltaic detection product, and realizes the service-oriented deployment through containerization, thereby solving the existence of the single application deployment mode. more limitations.
光伏产品缺陷检测系统工作流程从产线机台开始，机台上装有定制化的客户端程序，用于拍摄显示光伏产品EL照片以及配置缺陷检测项。客户端将需要检测的照片统一回传到任务中心，也被称为中台(英文名称Mission Hub)中，由中台(Mission Hub)把检测任务下发给算法服务器，并整理好服务器给出的检测结果，然后写入数据库。The workflow of the photovoltaic product defect detection system starts from the production line machine. The machine is equipped with a customized client program, which is used to take and display the EL photos of photovoltaic products and configure defect detection items. The client sends the photos that need to be detected back to the task center, also known as the middle platform (English name Mission Hub). The detection results are then written to the database.
光伏EL智能缺陷检测系统在架构上主要由2部分组成，分别是任务中心和算法服务器集群。Mission hub是负责收集缺陷照片和整理缺陷结果的模块，以及用于接收暂存来自客户端的缺陷识别任务，而该缺陷识别任务由客户端发起的，并对有处理任务能力的算法服务器进行认证管理；算法服务器负责从照片中识别缺陷。算法服务器集群业务上识别不同缺陷类型(不同的AI模型)，进而划分为多种算法服务。The photovoltaic EL intelligent defect detection system is mainly composed of two parts in architecture, namely the task center and the algorithm server cluster. Mission hub is a module responsible for collecting defect photos and sorting defect results, and for receiving and temporarily storing defect identification tasks from clients, which are initiated by clients and authenticate and manage the algorithm server capable of processing tasks. ; the algorithm server is responsible for identifying defects from photos. The algorithm server cluster business identifies different defect types (different AI models), and then divides them into multiple algorithm services.
中台Mission hub中包含的微服务有：The microservices included in the mission hub of the middle platform are:
a.数据库：用于存放每个EL照片的算法检测结果，如车间信息(车间号、产线号、机台号)、组件自身属性(如ID号、行列数、电池片类型等)、缺陷信息(如是否有缺陷、缺陷类型、缺陷大小、缺陷所在行列号等)。除了AI检测结果外，如果产线工人对判别结果进行了增删或修正，数据库中也会存放工人的判别结果。a. Database: used to store the algorithm detection results of each EL photo, such as workshop information (shop number, production line number, machine number), component attributes (such as ID number, row number, cell type, etc.), defects Information (such as whether there is a defect, the type of defect, the size of the defect, the row and column number of the defect, etc.). In addition to the AI detection results, if the production line workers add, delete or modify the discrimination results, the discrimination results of the workers will also be stored in the database.
b.任务队列：任务队列本质上是一组键值对(key-value)。正常流程中，Missionhub和算法服务器约定每组键值对与检测缺陷的对应关系，每个键(key)就是一类缺陷检测，例如隐裂、虚焊等，值(value)则是需要检测的照片信息所组成的队列，例如图中的img1、img2、img3、……。Mission hub收集到需要检测的照片后，将照片信息写入到多个缺陷检测键值对中。算法服务器则会到其检测缺陷类型对应的任务队列中取出照片信息进行检测。b. Task queue: A task queue is essentially a set of key-value pairs. In the normal process, Missionhub and the algorithm server agree on the corresponding relationship between each set of key-value pairs and detection defects. Each key (key) is a type of defect detection, such as cracks, virtual welding, etc., and the value (value) needs to be detected. A queue composed of photo information, such as img1, img2, img3, ... in the figure. After the Mission hub collects the photos to be inspected, the photo information is written into multiple defect inspection key-value pairs. The algorithm server will retrieve the photo information from the task queue corresponding to the detection defect type for detection.
c.Web应用：web端与数据库相连接，可以显示每个车间各个机台的稼动率、生产状态等，方便管理者远程监控。另外，基于数据库中存放的历史检测结果，web端提供了一系列数据挖掘工具，如对各个时间段各个缺陷的检测数量、出现的频率、出现的位置偏好进行统计，从而实现质量追溯。c. Web application: The web terminal is connected to the database, which can display the utilization rate and production status of each machine in each workshop, which is convenient for managers to monitor remotely. In addition, based on the historical detection results stored in the database, the web terminal provides a series of data mining tools, such as statistics on the detection quantity, frequency of occurrence, and location preference of each defect in each time period, so as to achieve quality traceability.
算法服务器集群包含各种缺陷类型的算法检测服务，如隐裂、虚焊、断栅等检测服务，除了兼容不同缺陷类型外，算法服务也兼容不同类型的电池片。The algorithm server cluster includes algorithm detection services for various defect types, such as detection services for cracks, virtual welding, and broken gates. In addition to being compatible with different defect types, the algorithm service is also compatible with different types of cells.
本发明实施例的有益效果包括：The beneficial effects of the embodiments of the present invention include:
(1)提高灵活性和可移植性。系统通过容器化实现了服务化部署，可以实现本地化和云端部署两种方式，提高部署效率、降低成本(1) Improve flexibility and portability. The system realizes service-oriented deployment through containerization, which can realize localization and cloud deployment to improve deployment efficiency and reduce costs.
(2)通过容器化部署方式，降低系统使用过程中的安全风险，且部署速度快，降低运维成本(2) Through the containerized deployment method, the security risks during the use of the system are reduced, the deployment speed is fast, and the operation and maintenance costs are reduced
(3)系统可扩展性强，增加新的任务键就能扩展新的业务类型的算法服务(3) The system has strong scalability, adding new task keys can expand the algorithm services of new business types
(4)检测系统具有很大弹性，增加新的算法服务器并从对应任务队列取任务以快速提升已有算法服务的处理能力(4) The detection system has great flexibility, adding new algorithm servers and fetching tasks from the corresponding task queue to quickly improve the processing capacity of existing algorithm services
(5)检测系统安全性高，某一算法服务器异常不会影响Mission hub以及其他算法服务器的正常工作(5) The security of the detection system is high, and the abnormality of a certain algorithm server will not affect the normal operation of Mission hub and other algorithm servers
(6)降低人工成本。若采用过去的客户端与服务器直连模式，由人工完成所有客户端和服务器的配置任务，需消耗2人约2天时间完成所有的更新、匹配与测试。但通过当前的技术方案，可以完全实现自动切换，无需专人再去调整、测试和维护。(6) Reduce labor costs. If the direct connection mode between client and server is adopted in the past, all the configuration tasks of client and server are completed manually, and it takes two people about two days to complete all the updating, matching and testing. However, through the current technical solution, automatic switching can be fully realized, without the need for special personnel to adjust, test and maintain.
根据一个或者多个实施例，光伏产品缺陷检测算法部署系统，根据光伏缺陷检测产品的功能，整体系统可以划分为：任务中心(包括任务队列、数据库、web应用)，算法检测服务。利用docker容器，分别将Mission hub、算法检测服务进行打包成docker镜像。According to one or more embodiments, the photovoltaic product defect detection algorithm deployment system, according to the function of photovoltaic defect detection products, the overall system can be divided into: task center (including task queue, database, web application), algorithm detection service. Using the docker container, the Mission hub and the algorithm detection service are packaged into docker images respectively.
光伏EL智能缺陷检测系统中包含多个微服务，使用docker run的命令方式来启动各个微服务，并不能适应快速部署的需求。另外，各个服务之间可能存在依赖关系，部分应用也需要划分到一组网络中方便访问。为了保证安全，以及无关应用的隔离，降低维护的工作量，在实际使用过程中，使用Docker Compose进行容器的编排和管理。The photovoltaic EL intelligent defect detection system includes multiple microservices. The docker run command method is used to start each microservice, which cannot meet the needs of rapid deployment. In addition, there may be dependencies between various services, and some applications also need to be divided into a group of networks for easy access. In order to ensure security, isolate unrelated applications, and reduce maintenance workload, Docker Compose is used for container orchestration and management in actual use.
Mission hub编排的微服务包括：数据库、任务队列、Web应用等。算法服务器集群中编排的微服务包括5bb/9bb、单/多晶、全/半片，隐裂/虚焊/断栅等缺陷检测模型。在实际部署情况下，工厂产线可能会同时生产不同类型的光伏组件，如5bb多晶全片、9bb单晶半片等等。不同的组件类型，所需的检测模型也不同。因此，算法检测服务需要同时部署多个模型，才能满足生产需求。多个模型同时存在时，客户端送过来的检测任务，需要通过特定的路由方式才能查找到对应的检测服务。在使用Docker Compose进行服务编排时，我们对不同的算法服务使用不同的环境变量进行标记。如以下服务表示专门用于检测9bb、单晶、半片隐裂的服务。The microservices orchestrated by Mission Hub include: database, task queue, web application, etc. The microservices arranged in the algorithm server cluster include defect detection models such as 5bb/9bb, single/poly, full/half, crack/virtual solder/broken gate. In the actual deployment situation, the factory production line may produce different types of photovoltaic modules at the same time, such as 5bb polycrystalline full wafers, 9bb monocrystalline half wafers, and so on. Different component types require different detection models. Therefore, the algorithm detection service needs to deploy multiple models at the same time to meet production requirements. When multiple models exist at the same time, the detection task sent by the client needs to find the corresponding detection service through a specific routing method. When using Docker Compose for service orchestration, we mark different algorithm services with different environment variables. For example, the following services represent services specially used to detect 9bb, single crystal, and half-chip cracks.
在实际部署过程中，存在以下情况：算法检测服务中，没有与当前待检测光伏组件类型完全相匹配的检测服务。为解决上述问题，我们对不同的环境变量给予不同的权重，根据所有环境变量权重的加权和计算匹配度。匹配度最大的检测服务将获取数据并进行检测。In the actual deployment process, there are the following situations: In the algorithm detection service, there is no detection service that completely matches the type of PV modules to be detected. In order to solve the above problems, we give different weights to different environmental variables, and calculate the matching degree according to the weighted sum of the weights of all environmental variables. The detection service with the best match will take the data and perform the detection.
通过对不同的检测模型“打标签”，从而实现不同的检测任务自动路由至对应的检测服务上。By "labeling" different detection models, different detection tasks are automatically routed to corresponding detection services.
值得说明的是，虽然前述内容已经参考若干具体实施方式描述了本发明创造的精神和原理，但是应该理解，本发明并不限于所公开的具体实施方式，对各方面的划分也不意味着这些方面中的特征不能组合，这种划分仅是为了表述的方便。本发明旨在涵盖所附权利要求的精神和范围内所包括的各种修改和等同布置。It is worth noting that although the foregoing content has described the spirit and principle of the present invention with reference to several specific embodiments, it should be understood that the present invention is not limited to the disclosed specific embodiments, and the division of various aspects does not mean that these Features in aspects cannot be combined, this division is for convenience of presentation only. The invention is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.
Claims (6)
Translated fromChinesePriority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010868972.8ACN112070246A (en) | 2020-08-26 | 2020-08-26 | Photovoltaic product defect detection algorithm deployment system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010868972.8ACN112070246A (en) | 2020-08-26 | 2020-08-26 | Photovoltaic product defect detection algorithm deployment system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112070246Atrue CN112070246A (en) | 2020-12-11 |
Family
ID=73659404
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010868972.8APendingCN112070246A (en) | 2020-08-26 | 2020-08-26 | Photovoltaic product defect detection algorithm deployment system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112070246A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112908877A (en)* | 2021-01-19 | 2021-06-04 | 上海擎昆信息科技有限公司 | Photovoltaic cell detection method and system, electronic device and storage medium |
| CN115130863A (en)* | 2022-06-29 | 2022-09-30 | 上海洪朴信息科技有限公司 | Photovoltaic module production quality analysis method, system, storage medium and computing device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107018075A (en)* | 2017-04-06 | 2017-08-04 | 安徽国防科技职业学院 | A kind of integrated data processing server system |
| CN108564104A (en)* | 2018-01-09 | 2018-09-21 | 北京百度网讯科技有限公司 | Product defects detection method, device, system, server and storage medium |
| CN109309693A (en)* | 2017-07-26 | 2019-02-05 | 财付通支付科技有限公司 | Services system, dispositions method and device, equipment and storage medium based on docker |
| CN110070526A (en)* | 2019-04-18 | 2019-07-30 | 深圳市深视创新科技有限公司 | Defect inspection method based on the prediction of deep neural network temperature figure |
| CN111008961A (en)* | 2019-11-25 | 2020-04-14 | 深圳供电局有限公司 | A transmission line equipment defect detection method and system, equipment and medium thereof |
- 2020
- 2020-08-26CNCN202010868972.8Apatent/CN112070246A/enactivePending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107018075A (en)* | 2017-04-06 | 2017-08-04 | 安徽国防科技职业学院 | A kind of integrated data processing server system |
| CN109309693A (en)* | 2017-07-26 | 2019-02-05 | 财付通支付科技有限公司 | Services system, dispositions method and device, equipment and storage medium based on docker |
| CN108564104A (en)* | 2018-01-09 | 2018-09-21 | 北京百度网讯科技有限公司 | Product defects detection method, device, system, server and storage medium |
| CN110070526A (en)* | 2019-04-18 | 2019-07-30 | 深圳市深视创新科技有限公司 | Defect inspection method based on the prediction of deep neural network temperature figure |
| CN111008961A (en)* | 2019-11-25 | 2020-04-14 | 深圳供电局有限公司 | A transmission line equipment defect detection method and system, equipment and medium thereof |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112908877A (en)* | 2021-01-19 | 2021-06-04 | 上海擎昆信息科技有限公司 | Photovoltaic cell detection method and system, electronic device and storage medium |
| CN115130863A (en)* | 2022-06-29 | 2022-09-30 | 上海洪朴信息科技有限公司 | Photovoltaic module production quality analysis method, system, storage medium and computing device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110689223B (en) | Robot batch management system based on RPA control | |
| WO2023142054A1 (en) | Container microservice-oriented performance monitoring and alarm method and alarm system | |
| CN113406438B (en) | Intelligent fault diagnosis method suitable for low-voltage transformer area and operation and maintenance system thereof | |
| CN111949484B (en) | Information processing method, device, electronic equipment and medium | |
| CN109873499A (en) | Intelligent distribution station area management terminal | |
| CN110716875A (en) | Concurrency test method based on feedback mechanism in domestic office environment | |
| CN112070246A (en) | Photovoltaic product defect detection algorithm deployment system | |
| CN108710566A (en) | A kind of distribution scheduling station integration testing framework and method | |
| US20210351612A1 (en) | Solar inverter power output communications methods, and related computer program products | |
| CN118227271A (en) | Terminal all-in-one machine operation and maintenance method and device based on container cloud platform | |
| CN116192616A (en) | Micro-service-based power standby and regulation system processing method and device and computer equipment | |
| CN111404757A (en) | Cloud-based cross-network application integration system | |
| US20170244252A1 (en) | Autonomous Operational Platform for Micro-Grid Energy Management | |
| CN115277473A (en) | Remote operation and maintenance method and device for edge gateway, computer equipment and storage medium | |
| CN112256384B (en) | Service set processing method and device based on container technology and computer equipment | |
| CN117997715A (en) | Alarm processing method, device, equipment, storage medium and program product | |
| CN108173955A (en) | The system that a kind of cloud platform excludes server failure | |
| CN115577160A (en) | A production line data acquisition method, device, equipment and medium | |
| CN111427592B (en) | High-availability system for virtual deployment of mysql | |
| CN115473567A (en) | A system and method for comprehensive testing of spacecraft based on private cloud | |
| CN118863789B (en) | Campus big data comprehensive service system | |
| Reitze | Using commercial web services to build Automated Test Equipment cloud based applications | |
| Madathala | AI-Enhanced Disaster Recovery Strategies for SAP S/4HANA in the Cloud | |
| Li et al. | Node Resource Balance Scheduling Algorithm of Power Internet of Things Based on Big Data | |
| CN117877171A (en) | Self-service machine management method, device, computer equipment and storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication | Application publication date:20201211 | |
| RJ01 | Rejection of invention patent application after publication |