Product identification detection method and system, electronic equipment and storage medium

Abstract

The invention provides a product identification detection method and system, an electronic device and a storage medium, the method is applied to a detection system, the detection system comprises a product detection device controlled by a PLC and an image recognition device supporting a PLC communication protocol, and the method comprises the steps that after the product detection device detects that a to-be-detected product exists in a detection station of the product detection device, the to-be-detected product is detected; a trigger signal is sent to an image recognition device through a PLC communication protocol; after receiving the trigger signal, the image recognition equipment performs image recognition on the to-be-detected product to obtain a detection result in a structured character form, and transmits the detection result back to the product detection equipment through a PLC (Programmable Logic Controller) communication protocol; and after receiving the detection result, the product detection equipment performs corresponding processing according to the detection result. According to the invention, the architecture of the product identification detection system is simplified, and the real-time performance of detection triggering and result feedback is improved; and data conversion errors possibly caused by transfer processing of the industrial personal computer are avoided, and the reliability of a product identification detection result is improved.

Description

TECHNICAL FIELD

[0001] One or more embodiments of the present disclosure relate to the technical field of visual detection and processing, and in particular to a product identification detection method and system, an electronic device, and a storage medium. BACKGROUND

[0002] In the global production scenario of battery packs, the configuration of nameplates of battery packs of different specifications has significant differences. Taking domestic and foreign markets as examples, overseas models of battery packs need to be additionally attached with nameplates and recyclable certification nameplates, while domestic models do not need such identification. Such differences lead to the need to dynamically switch the nameplate mounting scheme on the production line, and if not properly controlled, it is easy to cause quality risks such as misplacement and omission, directly affecting product compliance.

[0003] To address the above problems, the related technology uses an industrial CCD (Charge Coupled Device) camera to complete image acquisition of the nameplate, and then transmits the image data to an industrial computer for feature recognition. The industrial computer then converts the processing result into a protocol format that can be parsed by the PLC and sends it to the PLC. Finally, the PLC determines the correctness of the nameplate mounting. Although this scheme can achieve image-level recognition, the image data needs to be converted by the industrial computer and then transmitted to the PLC, resulting in a long signal link and transmission delay that slows down the production line rhythm. In addition, the industrial CCD camera and the PLC use heterogeneous protocols, and a customized protocol conversion middleware needs to be developed, which prolongs the development cycle and increases maintenance costs.

[0004] Another technology uses a PLC to directly control a basic color sensor to achieve simple differentiation by detecting the color block of the nameplate (such as the color difference between a red nameplate and a black barcode). Although this scheme simplifies the communication architecture, it cannot parse text and numerical information because the sensor can only recognize color blocks, making it difficult to meet high-reliability production requirements. SUMMARY

[0005] Therefore, the present disclosure provides a product identification detection method. The method is applied to a detection system, which includes a product detection device controlled by a PLC and an image recognition device supporting a PLC communication protocol. The method includes the following steps: The product detection device sends a trigger signal to the image recognition device through the PLC communication protocol after detecting that a detection station of the product detection device has a product to be detected; The image recognition device performs image recognition on the product to be detected after receiving the trigger signal, obtains a detection result in the form of structured characters, and returns the detection result to the product detection device through the PLC communication protocol; The product detection device performs corresponding processing according to the detection result after receiving the detection result.

[0006] Optionally, the product detection device predefines a work step execution logic, and after detecting that the detection station of the product detection device has the product to be detected, the product detection device sends a trigger signal to the image recognition device through the PLC communication protocol, including: After detecting that the detection station of the product detection device has the product to be detected, the product detection device performs work step counting, and sends an enable signal to the image recognition device through the PLC communication protocol. After receiving the enable signal, the image recognition device performs state preparation, and returns state ready information to the product detection device after preparation is completed. After running to a preset trigger work step and receiving the state ready information, the product detection device sends a trigger signal to the image recognition device through the PLC communication protocol.

[0007] Optionally, the product detection device includes a code scanning gun, and the method further includes: After detecting that the detection station of the product detection device has the product to be detected, the product detection device scans the barcode of the product to be detected through the code scanning gun to determine the product type of the product to be detected according to the barcode. After receiving the detection result, the product detection device performs corresponding processing according to the detection result, including: After running to a preset judgment work step and receiving the detection result, the product detection device performs corresponding processing according to the product type of the product to be detected and the detection result.

[0008] Optionally, after running to a preset judgment work step and receiving the detection result, the product detection device performs corresponding processing according to the product type of the product to be detected and the detection result, including: After running to a preset judgment work step and receiving the detection result, the product detection device determines whether the target mark is detected according to the detection result. If the target mark is detected and the product type of the product to be detected is a first type, or the target mark is not detected and the product type of the product to be detected is a second type, it is determined that the product mark of the product to be detected is qualified. Otherwise, it is determined that the product mark of the product to be detected is unqualified.

[0009] Optionally, the product to be detected is transported to the detection station by a transportation device, and the method further includes: If the product mark of the product to be detected is qualified, the product detection device sends a prompt signal to the transportation device to remove the product to be detected from the detection station. If the product identification of the product to be detected is unqualified, the product detection device issues an alarm.

[0010] Optionally, the target identification is multiple, and each target identification corresponds to a detection area of the product to be detected. According to the detection result, it is determined whether the target identification is detected in each detection area. If the target identification is detected in each detection area, it is determined that the target identification is detected. If the target identification is not detected in any detection area, it is determined that the target identification is not detected.

[0011] Optionally, the trigger mode of the image recognition device is preset as external triggering, the communication source of the image recognition device is preset as communication triggering, and the detection area of the image recognition device is preset as the identification area of the reference picture of the product to be detected.

[0012] The present disclosure also provides a product identification detection system, which comprises: A product detection device controlled by a PLC, which is used to send a trigger signal to an image recognition device through a PLC communication protocol after detecting that a detection station of itself has a product to be detected; An image recognition device supporting a PLC communication protocol, which is used to perform image recognition on the product to be detected after receiving the trigger signal, obtain a detection result in the form of structured character, and return the detection result to the product detection device through the PLC communication protocol; The product detection device is also used to perform corresponding processing according to the detection result after receiving the detection result.

[0013] The present disclosure also provides an electronic device, which comprises a communication interface, a processor, a memory and a bus, and the communication interface, the processor and the memory are connected with each other through the bus. The memory stores machine readable instructions, and the processor executes the above method by calling the machine readable instructions.

[0014] The present disclosure also provides a machine readable storage medium, which stores machine readable instructions, and the machine readable instructions realize the above method when called and executed by a processor.

[0015] It can be seen that in the technical solution of the present disclosure, when the product detection equipment detects that the station thereof has a product to be detected, a trigger signal is sent to the image recognition equipment through the PLC communication protocol. After receiving the signal, the image recognition equipment performs image recognition on the product to be detected, converts the identification information (such as letters, numbers, graphics, etc.) of the recognized image into structured character data as a detection result, and returns the result to the product detection equipment through the same PLC communication protocol. After receiving the structured detection result, the product detection equipment automatically performs subsequent processing actions according to the preset logic (such as judging whether the identification matches the product type, etc.), such as releasing qualified products, rejecting unqualified products, or triggering an alarm.

[0016] In the above manner, the technical solution of the present disclosure has the following advantages. On the one hand, by using the image recognition equipment supporting the PLC communication protocol to directly communicate with the product detection equipment controlled by the PLC in a high-efficiency and low-latency manner, without the need for a work station computer for transfer or additional protocol conversion middleware, the architecture of the product identification detection system is simplified, the integration difficulty and cost are reduced, and the real-time performance of detection triggering and result feedback is ensured. On the other hand, since the image recognition equipment integrates image processing and recognition functions, the collected image content can be directly processed into a structured character form of the detection result and returned through the PLC protocol, so that the result can be directly understood and processed by the product detection equipment, avoiding data conversion errors that may be caused by the work station computer in the traditional scheme, thereby improving the reliability and accuracy of the product identification detection result. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments described in the present disclosure, and other drawings can also be obtained by those skilled in the art without creative labor.

[0018] Figure 1 is a flowchart of a product identification detection method according to an exemplary embodiment; Figure 2 is a schematic diagram of a product identification detection device installation method according to an exemplary embodiment; Figure 3 is a schematic diagram of configuring an intelligent camera in a PLC according to an exemplary embodiment; Figure 4 is a schematic diagram of configuring a camera in a host computer of a product detection equipment according to an exemplary embodiment; Figure 5 is a schematic diagram of another product identification detection method according to an exemplary embodiment; Figure 6 Fig. 1 is a hardware structure diagram of an electronic device according to an example embodiment; Figure 7 Fig. 2 is a block diagram of a product identification detection system according to an example embodiment. DETAILED DESCRIPTION

[0019] In order to enable persons skilled in the art to better understand the technical solutions in the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by persons skilled in the art without creative labor should fall within the protection scope of the present disclosure.

[0020] It should be noted that: in other embodiments, the steps of the corresponding method are not necessarily performed in the order shown and described in the present disclosure. In some other embodiments, the steps included in the method thereof can be more or less than described in the present disclosure. In addition, a single step described in the present disclosure can be divided into multiple steps for description in other embodiments; and multiple steps described in the present disclosure can also be combined into a single step for description in other embodiments.

[0021] In the global production scenario of battery packs, the configuration of nameplates of battery packs of different specifications has significant differences. Taking domestic and foreign markets as examples, overseas models of battery packs need to be additionally attached with nameplates and recyclable certification nameplates, while domestic models do not need such identification. Such differences lead to the need to dynamically switch the nameplate mounting scheme on the production line, and if not properly controlled, it is easy to cause quality risks such as misplacement and omission, directly affecting product compliance.

[0022] To address the above problems, the related art uses an industrial CCD (Charge Coupled Device) camera to complete the image acquisition of the nameplate, and then transmits the image data to an industrial computer for feature recognition. The industrial computer then converts the processing result into a protocol format that can be parsed by the PLC and sends it to the PLC, and finally the PLC determines the correctness of the nameplate mounting. Although this scheme can achieve image-level recognition, the image data needs to be converted from the industrial computer to the PLC, and the signal link is long, which slows down the production line rhythm due to transmission delay. In addition, the industrial CCD camera and the PLC use heterogeneous protocols, and a customized protocol conversion middleware must be developed, which prolongs the development cycle and increases maintenance costs.

[0023] Another technology directly controls the base color sensor by PLC, and realizes simple distinction by detecting the color block of the nameplate (such as the color difference between the red nameplate and the black barcode). Although this scheme simplifies the communication architecture, the sensor can only identify the color block and cannot parse the text and digital information, so it is difficult to meet the high reliability production demand.

[0024] Therefore, the present disclosure aims to provide a technical solution for directly communicating between an image recognition device and a product detection device controlled by a PLC to complete product identification detection.

[0025] The technical solution is applied to a detection system, which includes a product detection device controlled by a PLC and an image recognition device supporting a PLC communication protocol. First, the product detection device sends a trigger signal to the image recognition device through the PLC communication protocol after detecting that the detection station of itself exists a product to be detected. Further, the image recognition device performs image recognition on the product to be detected after receiving the trigger signal, obtains a detection result in the form of structured characters, and returns the detection result to the product detection device through the PLC communication protocol. Finally, the product detection device performs corresponding processing according to the detection result after receiving the detection result.

[0026] For example, in a battery pack production line, the product detection device is an existing automated device (controlled by PLC to run logic) responsible for battery pack profile detection in the factory, and the image recognition device is a smart camera originally integrated with a PLC communication protocol (such as Profinet). When a battery pack is sent to the detection station of the product detection device by an automatic guided vehicle, the photoelectric sensor of the product detection device located at the detection station detects the battery pack to be detected, and the product detection device directly sends a trigger signal to the smart camera through the Profinet protocol to instruct it to start shooting. After receiving the signal, the smart camera immediately captures the nameplate area on the side of the battery pack, converts the character identification and graphic information on the nameplate into a detection result in the form of structured characters through the built-in OCR recognition algorithm, and returns the detection result to the product detection device through the Profinet protocol. After receiving the detection result, the product detection device automatically performs subsequent processing actions according to the preset logic (such as judging whether the identification matches the product type), such as releasing qualified products, rejecting unqualified products, or triggering an alarm.

[0027] It can be seen that in the technical solution of the disclosure, when the product detection equipment detects that the station thereof has a product to be detected, a trigger signal is sent to the image recognition equipment through the PLC communication protocol. After the image recognition equipment receives the signal, image recognition is performed on the product to be detected, the identification information (such as letters, numbers, graphics, etc.) of the recognized image is converted into structured character data as a detection result, and the result is returned to the product detection equipment through the same PLC communication protocol. After receiving the structured detection result, the product detection equipment automatically performs subsequent processing actions according to the preset logic (such as judging whether the identification matches the product type, etc.), such as releasing qualified products, rejecting unqualified products, or triggering an alarm.

[0028] In the above manner, the technical solution of the disclosure has the following effects. On the one hand, by using the image recognition equipment supporting the PLC communication protocol to directly communicate with the product detection equipment controlled by the PLC in a high-efficiency and low-latency manner, without the need for a work station to transfer, and without the need for additional custom protocol conversion middleware, the architecture of the product identification detection system is simplified, the integration difficulty and cost are reduced, and the real-time performance of detection triggering and result feedback is ensured. On the other hand, since the image recognition equipment integrates image processing and recognition functions, the collected image content can be directly processed into a structured character form of the detection result and returned through the PLC protocol, so that the result can be directly understood and processed by the product detection equipment, avoiding data conversion errors that may be caused by the work station in the traditional scheme, thereby improving the reliability and accuracy of the product identification detection result.

[0029] It should be noted that in the disclosure, the product detection equipment can be an original equipment of a factory responsible for product profile detection, product testing equipment, product sorting equipment, etc., the image recognition equipment can be an intelligent camera, a vision system, a vision unit, etc. natively integrated with a PLC protocol stack, and the product can be a battery pack, an industrial part, etc. The disclosure does not limit this.

[0030] The disclosure will be described below in conjunction with specific application scenarios through specific embodiments.

[0031] Please refer to Figure 1 , Figure 1 is a flowchart of a product identification detection method according to an exemplary embodiment. The method is applied to a detection system including a product detection equipment controlled by a PLC and an image recognition equipment supporting a PLC communication protocol. The method can perform the following steps: Step 102: After detecting that the detection station thereof has a product to be detected, the product detection equipment sends a trigger signal to the image recognition equipment through the PLC communication protocol.

[0032] For example, in a battery pack production line, the product detection equipment is an automated equipment (its operation logic is controlled by PLC) that the factory already has for battery pack profile detection, and the image recognition equipment is a smart camera that natively integrates a PLC communication protocol (such as Profinet). When a certain battery pack is sent to the detection station of the product detection equipment by an automated guided vehicle, after the photoelectric sensor of the product detection equipment at the detection station detects the battery pack to be detected, the product detection equipment directly sends a trigger signal to the smart camera through the Profinet protocol, instructing the smart camera to start photographing.

[0033] The PLC communication protocol is a standard protocol used in the field of industrial automation for data exchange between PLC and other devices, and common ones include Profinet, EtherNet / IP, etc. The image recognition equipment that natively integrates the PLC communication protocol can seamlessly access the industrial network dominated by PLC, realize efficient, low-latency, and high-reliability bidirectional data communication, and does not need an additional protocol conversion gateway or host computer as an intermediary. It only needs to import the GSDML configuration file of the image recognition equipment (such as a smart camera) into the PLC, so as to configure the image recognition equipment in the PLC and set the communication, triggering mode, etc. of the image recognition equipment.

[0034] Step 104: After receiving the trigger signal, the image recognition equipment performs image recognition on the product to be detected, obtains a detection result in the form of structured characters, and returns the detection result to the product detection equipment through the PLC communication protocol.

[0035] For example, after receiving the trigger signal, the smart camera immediately photographs the nameplate area on the side of the battery pack, converts the character and graphic information on the nameplate into a detection result in the form of structured characters through the built-in OCR recognition algorithm, and returns the detection result to the product detection equipment through the Profinet protocol.

[0036] The sending of the trigger signal is realized through data exchange at the network level by the PLC communication protocol. When the sensor of the product detection equipment detects that the product is in place, the PLC program of the product detection equipment sends a pre-defined data packet (i.e. the “trigger signal”) to the IP address or device node address of the image recognition equipment through the communication module. Taking the Profinet protocol as an example, the PLC of the product detection equipment will write a specific Boolean value to a certain input register address pre-configured by the image recognition equipment. The image recognition equipment continuously monitors this address, and as soon as it detects a change in the value of this address, it determines that it has received the trigger signal and immediately starts its internal image acquisition and recognition process.

[0037] The image recognition device recognizes letters, numbers or symbols in the image through an optical character recognition (OCR) algorithm; uses a decoding or template matching algorithm to recognize graphical information to obtain a recognition result in the form of structured characters, which is text data with clear meaning and format, such as JSON strings or key-value pairs, etc., to facilitate direct parsing and use by the PLC program. The image recognition device writes the recognition result to a specific address of the output register preset in its external communication interface. The PLC of the product detection device periodically reads data from the specific address through the cyclic data exchange mechanism of the PLC communication protocol. Once the image recognition is completed, the result data is written to the address, and the next cycle of the PLC reading can obtain the latest detection result.

[0038] Step 106: The product detection device processes according to the detection result after receiving the detection result.

[0039] For example, after the product detection device receives the detection result, it automatically performs subsequent processing actions according to the preset logic (such as judging whether the identification matches the product type, etc.), such as releasing qualified products, rejecting unqualified products, or triggering an alarm.

[0040] The preset logic is a set of judgment rules pre-configured in the product detection device, which is used to associate the structured detection result with the production requirements to form a "result-action" correspondence. A common way is to compare parameters based on the structured detection result: through the PLC program, compare the key data in the detection result (such as the battery pack identification recognized by the intelligent camera) with the preset qualified parameter library in real time, if they are consistent, it is determined to be qualified, if they are not consistent, it is determined to be unqualified. Releasing qualified products is that the product detection device drives the actuator to complete the action through the PLC output control signal. Rejecting unqualified products is based on the reverse control of the actuator by the PLC, such as driving the sorting action, locking the work station, triggering the alarm, etc.

[0041] To help those skilled in the art understand the technical solutions of the present disclosure intuitively, the following will combine the technical solutions of the present disclosure with Figures 2-3 The technical solutions of the present disclosure are further described.

[0042] Please refer to Figure 2 , Figure 2 is an exemplary embodiment showing a product identification detection device installation method schematic diagram. As Figure 2As shown, the product to be detected is located at the detection station of the product detection device. In order to facilitate the detection of the product to be detected, an intelligent camera is installed at the left side of the product entering direction at a height level. A length appropriate profile is fixed in the product detection device station, and the intelligent camera is fixedly installed on the profile, and the installation height is the same as the position of the product to be detected, so as to ensure that it can be directly and accurately shot. The PLC is placed in the product detection device control cabinet, and communicates with the intelligent camera through the Profinet protocol.

[0043] Please refer to Figure 3 , Figure 3 is an example embodiment showing a schematic diagram of configuring an intelligent camera in a PLC. As shown in Figure 3 , an industrial automation control system architecture based on a Profinet network is shown, and the core is Figure 3 “PACK2_PLC” in the upper left corner, which is a product detection device controller (PLC). The PLC communicates and controls multiple devices through the Profinet bus. Figure 3 “MV-Iseries” in the lower right corner is a camera configuration module. After importing the GSDML file of the intelligent camera for the PLC, the intelligent camera is configured, and communication with the intelligent camera is realized. The green check pattern in the upper left corner of the icon represents successful communication. The Profinet network represented by the lines in the whole system realizes data exchange and real-time control, ensuring efficient cooperation between various components, and is suitable for modern industrial automation production lines.

[0044] In an embodiment shown, the trigger mode of the image recognition device is preset as external trigger, the communication source of the image recognition device is preset as communication trigger, and the detection area of the image recognition device is preset as the identification area of the reference picture of the product to be detected.

[0045] For example, please refer to Figure 4 , Figure 4 is an example embodiment showing a schematic diagram of configuring a camera in the upper computer of the product detection device. As shown in Figure 4 , in order to configure the intelligent camera detection function, the camera software needs to be installed in the upper computer of the product detection device, and the communication mode needs to be set in the software, such as selecting Profinet communication mode. Since this scheme triggers the camera to take pictures by PLC, the trigger mode and trigger source of the intelligent camera are set to “external trigger” and “communication trigger” respectively. In order to help the intelligent camera determine the detection area, several reference pictures need to be provided manually, which contain the product identification of the product to be detected. By selecting the positioning reference point (thunderbolt icon in the center position of the interface on the right side in Figure 4 ) and the identification area actually needed to be detected (the area surrounded by the dotted line in Figure 4The intelligent camera is configured to detect the actual identification area to be detected of the product to be detected.

[0046] Wherein, external trigger refers to that the image recognition device is triggered by external signal when taking a picture or starting the recognition operation, instead of internal timer or other mechanism. Communication trigger refers to that the trigger source of the image recognition device is based on the communication connection with PLC or other control system, which means that the image recognition device needs to be pre-configured to listen to the data changes of specific communication address or port, and the data from these addresses is regarded as trigger instruction. The identification area of the reference picture refers to the reference area defined in advance to ensure that the image recognition device can accurately identify and locate the key information of the product to be detected. This area usually contains product identification, serial number and other important information, which is the target of image recognition. In specific implementation, first, several reference pictures with clear product identification are provided, and then the positioning reference points in the identification area and the actual identification area to be analyzed are manually selected through the software interface. These selected information will be saved as a template and used in the subsequent actual detection process, so that the image recognition device can quickly and accurately find and process the same type of identification.

[0047] In one embodiment shown, the target identification is multiple, and each target identification corresponds to a detection area of the product to be detected. The determination of whether the target identification is detected according to the detection result includes: determining whether the target identification is detected in each detection area according to the detection result; if the target identification is detected in each detection area, it is determined that the target identification is detected; if the target identification is not detected in any detection area, it is determined that the target identification is not detected.

[0048] For example, the battery pack to be detected contains two key nameplate identifications: one is the product name identification, and the other is the recyclable certification identification. In order to ensure the integrity and traceability of product information, the system needs to verify whether the two identifications exist at the same time. After the battery pack to be detected reaches the detection station and triggers the intelligent camera to take a picture, the intelligent camera processes the collected image and detects two areas at the same time. Only when the intelligent camera successfully detects the corresponding identification in the two detection areas respectively, it is determined that the target identification is detected, and the product detection device controls the battery pack to be detected to enter the next process. If the identification of any area fails (such as not detecting the corresponding identification), it is determined that the target identification is not detected, and the product detection device controls the battery pack to be detected to be processed separately.

[0049] In order to realize the above-mentioned embodiments, the intelligent camera needs to be pre-configured to detect multiple areas simultaneously, take or logic of multiple detection areas in the reference map, and output configuration to the intelligent camera. When any area in the multiple detection areas does not detect the corresponding identification, it is determined that the target identification is not detected and the corresponding data character is output. The reference map is a standard image template used by the intelligent camera to compare whether the target identification exists in the detection area. By pre-storing the feature information of the qualified identification, the intelligent camera provides a judgment basis for real-time detection.

[0050] In some embodiments, the intelligent camera can be configured in a more compatible mode. The camera can shield the interference points of the non-detection area and the detection area by itself. For the case that the nameplate identification in the to-be-detected area is skewed or has stains, the detection result is not affected, thereby improving the robustness and anti-interference ability of the detection.

[0051] In one embodiment shown, the product detection device predefines the execution logic of the work step. After detecting that the detection work station of the product detection device has a product to be detected, the product detection device sends a trigger signal to the image recognition device through the PLC communication protocol. The product detection device detects that the detection work station has a product to be detected, performs work step counting, and sends an enable signal to the image recognition device through the PLC communication protocol. After receiving the enable signal, the image recognition device prepares for the state, and returns the state ready information to the product detection device after preparation. The product detection device sends a trigger signal to the image recognition device through the PLC communication protocol after running to the preset trigger work step and receiving the state ready information.

[0052] For example, in the battery module assembly line, the product detection equipment predefines the execution logic of the work step containing multiple steps. When the automated guided vehicle sends the battery pack to be detected into the detection station, the photoelectric sensor on the detection station is triggered. After the PLC of the product detection equipment detects this signal, it increments the internal work step counter. Then, the product detection equipment sends an "enable signal" to the intelligent camera through the Profinet protocol (i.e. writes a Boolean value "1" to a specific input register of the intelligent camera). After receiving the enable signal, the intelligent camera starts the internal self-check, checks whether the camera lens is clean, whether the light source brightness is normal, whether the communication link is stable, and loads the identification program for this type of module. When all checks pass and are ready, the intelligent camera writes its internal "status ready" flag (a Boolean value "1") to the input register address preset by the product detection equipment PLC through Profinet. In the subsequent execution of the work step, when the work step counter reaches 120 work steps (i.e. the preset "trigger work step") and the intelligent camera status ready information has been received, the product detection equipment sends a "trigger signal" to the intelligent camera through Profinet (writes another specific instruction value), instructing it to take a photo immediately for identification.

[0053] In this embodiment, by sending an enable signal to the camera first and a trigger signal after the camera is ready, it is ensured that the intelligent camera performs photo detection in a ready state under high-speed production rhythm, avoiding false triggering or identification failure due to the intelligent camera not being ready.

[0054] In actual application, the number of work steps corresponding to the trigger work step can be determined according to the operation of the product detection equipment or the actual needs of the user. In this embodiment, when the product detection equipment is running to 120 work steps, the light controlled by the product detection equipment is just above the battery pack to be detected, so it is more appropriate to trigger the intelligent camera for detection at this time. Therefore, the intelligent camera is triggered for detection when the product detection equipment runs to the preset trigger work step, thereby improving the detection accuracy.

[0055] Wherein, the working step execution logic is an ordered operation sequence preset in the PLC program of the product detection device for controlling the entire automation process. Each "working step" represents a specific stage or action node in the process, for example, working step 100 can be "product entry", working step 120 can be "visual detection", working step 200 can be "result judgment", etc. The working step count is a technical means for the PLC to track the current execution progress through internal counters or state machine variables, enabling the product detection device to accurately execute specific instructions at preset time points. The enable signal is a pre-trigger signal in the form of a specific data value (such as a Boolean value) written through the PLC communication protocol, which serves to advance the notification of the image recognition device to perform "state preparation" work, ensuring that the intelligent camera can respond immediately upon receiving the trigger signal, avoiding delays due to initialization time. The state ready information is a confirmation signal returned by the image recognition device to the product detection device after completing all preparation actions through the PLC communication protocol, which is usually a Boolean value written to a preset register, constituting a handshaking mechanism and achieving bidirectional state confirmation between devices.

[0056] In one embodiment shown, the product detection device includes a code scanning gun, and the method further comprises: the product detection device scans the barcode of the product to be detected through the code scanning gun after detecting that the detection station of the product detection device has a product to be detected, to determine the product type of the product to be detected according to the barcode; and the product detection device performs corresponding processing according to the detection result after receiving the detection result, including: the product detection device performs corresponding processing according to the product type of the product to be detected and the detection result after running to a preset judgment working step and having received the detection result.

[0057] For example, please refer to Figure 5 , Figure 5 is another product identification detection method shown in an exemplary embodiment. As shown in Figure 5 , in a mixed production line producing domestic and overseas model battery packs at the same time, the product detection device integrates a code scanning gun. When the battery pack to be detected is sent to the detection station, the product detection device first scans the barcode on it through the code scanning gun. If the scanned barcode is "DOM-2025-001", the product detection device identifies that the product is a domestic model, and if the scanned barcode is "OVS-2025-001", the product detection device identifies that the product is an overseas model. Subsequently, the product detection device sends a trigger signal to the intelligent camera at working step 120 according to the preset logic to make it take a photo for recognition. The intelligent camera returns the detection result (whether the target mark is detected) after recognition. The product detection device determines whether the battery pack to be detected is qualified or unqualified by jointly judging the detection result and the product type when running to the preset working step 200 (i.e. the preset "judgment working step").

[0058] Among them, the product inspection equipment performs differentiated processing actions (such as release or alarm) according to the combination of "product type-test result", which can achieve accurate and adaptive quality control for mixed-line production scenarios, effectively avoiding the problem of inconsistent identification standards caused by model confusion, which leads to reduced identification accuracy, and improves the intelligence level and applicability of the inspection method.

[0059] In one embodiment shown, after the product inspection device runs to a preset judgment step and has received the detection result, it performs corresponding processing according to the product type of the product to be inspected and the detection result, including: after the product inspection device runs to a preset judgment step and has received the detection result, it determines whether the target identifier is detected according to the detection result; if the target identifier is detected and the product type of the product to be inspected is the first type, or the target identifier is not detected and the product type of the product to be inspected is the second type, then it is determined that the product identifier of the product to be inspected is qualified; otherwise, it is determined that the product identifier of the product to be inspected is unqualified.

[0060] For example, after the product inspection equipment runs to the preset 200 steps (i.e., the preset "judgment step") and receives the product type of the product to be inspected, it performs a joint judgment: if the battery pack to be inspected is an overseas version battery pack and the target mark is detected, it is judged to be qualified and the product is allowed to enter the next process; if the battery pack to be inspected is a domestic version battery pack and the target mark is not detected, it is judged to be qualified and the product is allowed to enter the next process; if the battery pack to be inspected is an overseas version battery pack and the target mark is not detected, it is judged to be unqualified (nameplate is missing) and corresponding processing is performed; if the battery pack to be inspected is a domestic version battery pack and the target mark is detected, it is judged to be unqualified (nameplate is wrongly affixed) and corresponding processing is performed.

[0061] Among them, after the battery pack to be inspected is judged to be unqualified, the corresponding processing method may include triggering a workstation alarm, pausing the conveyor line, waiting for manual intervention, etc. For domestic version battery packs, there should be no recyclable and battery name plates on the side. For overseas version battery packs, there should be recyclable and battery name plates on the side. In order to achieve different standards for result judgment of two types of products, this embodiment uses a composite judgment rule based on Boolean logic, takes "product type" and "visual inspection result" as two input variables, and judges whether the final product identification is qualified through a specific logical relationship.

[0062] In an embodiment shown, the product to be detected is carried to the detection station by a transport device, and the method further comprises: if the product identification of the product to be detected is qualified, the product detection device sends a prompt signal to the transport device to make the transport device remove the product to be detected from the detection station; if the product identification of the product to be detected is unqualified, the product detection device sends an alarm.

[0063] For example, in a battery pack production line, the battery pack to be detected is carried to the detection station of the product detection device by an automated guided vehicle. After the product detection device completes all detection processes (including scanning code to identify the product type and receiving the intelligent camera vision detection result), if it is confirmed based on the judgment logic that the product identification of the battery pack is qualified, the PLC of the product detection device will send a prompt signal to the automated guided vehicle through a communication interface. After receiving the signal, the automated guided vehicle knows that the detection station has been processed, and automatically starts and carries the battery pack to be detected to the next process. On the contrary, if it is judged that the product identification is unqualified, the PLC of the product detection device will not send a removal signal, but will immediately trigger an audible and light alarm to alert the on-site personnel to intervene, while keeping the station locked to prevent the automated guided vehicle from taking away the unqualified product.

[0064] Among them, the transport device refers to an automated device responsible for carrying the product to be detected between stations on the production line, and common forms include automated guided vehicles, conveyors, mechanical arms or track trolleys. The "prompt signal" is an instruction signal sent by the product detection device to the transport device, indicating that it can take away the product. Its form can be a data message transmitted through an industrial communication protocol, or a simple digital output. After the product detection device processes all processes about the battery pack to be detected, it resets the process and waits for the transport device to send the next battery pack to be detected to the detection station before restarting the process.

[0065] Corresponding to the above-mentioned embodiments of the product identification detection method, the present disclosure also provides an embodiment of a product identification detection system.

[0066] Please refer to Figure 6 , Figure 6Figure 1 is an exemplary embodiment illustrating a hardware structure diagram of an electronic device. At the hardware level, the device includes a processor 602, an internal bus 604, a network interface 606, a memory 608, and a non-volatile memory 610, and can also include other required hardware. One or more embodiments of the present disclosure can be implemented in a software manner, such as by the processor 602 reading a corresponding computer program from the non-volatile memory 610 into the memory 608 and then running. Of course, in addition to the software implementation, one or more embodiments of the present disclosure do not exclude other implementation manners, such as a logic device or a combination of software and hardware, and the like, that is, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or a logic device.

[0067] Figure 2 is an exemplary embodiment illustrating a product identification detection system block diagram. The product identification detection system 700 can be applied to an electronic device as shown in Figure 7 , Figure 7 Figure 3 is an exemplary embodiment illustrating a product identification detection system block diagram. The product identification detection system 700 can be applied to an electronic device as shown in Figure 6 Figure 4 is an exemplary embodiment illustrating a product identification detection system block diagram. The product identification detection system 700 can be applied to an electronic device as shown in The product detection device 702 is controlled by a PLC, and is configured to send a trigger signal to the image recognition device through the PLC communication protocol after detecting that the detection station of the product detection device itself has a product to be detected. The image recognition device 704 supports the PLC communication protocol, and is configured to perform image recognition on the product to be detected after receiving the trigger signal, obtain a detection result in the form of structured characters, and return the detection result to the product detection device through the PLC communication protocol. The product detection device 702 is further configured to perform corresponding processing according to the detection result after receiving the detection result.

[0068] In some embodiments, the product detection device predefines a work step execution logic, and the product detection device sends a trigger signal to the image recognition device through the PLC communication protocol after detecting that the detection station of the product detection device itself has a product to be detected, including: The product detection device performs work step counting after detecting that the detection station of the product detection device itself has a product to be detected, and sends an enable signal to the image recognition device through the PLC communication protocol. The image recognition device performs state preparation after receiving the enable signal, and returns state ready information to the product detection device after preparation is completed. The product detection device sends a trigger signal to the image recognition device through the PLC communication protocol after running to a preset trigger work step and receiving the state ready information.

[0069] In some embodiments, the product detection device comprises a code scanning gun, and the product detection device is further configured to: after detecting that the detection station itself has the product to be detected, scanning a barcode of the product to be detected by using the code scanning gun to determine a product type of the product to be detected according to the barcode; after receiving the detection result, the product detection device performs corresponding processing according to the detection result, including: after running to a preset judgment step and receiving the detection result, the product detection device performs corresponding processing according to the product type of the product to be detected and the detection result.

[0070] In some embodiments, after running to a preset judgment step and receiving the detection result, the product detection device performs corresponding processing according to the product type of the product to be detected and the detection result, including: after running to a preset judgment step and receiving the detection result, the product detection device determines whether the target mark is detected according to the detection result; if the target mark is detected and the product type of the product to be detected is a first type, or if the target mark is not detected and the product type of the product to be detected is a second type, it is determined that the product mark of the product to be detected is qualified; otherwise, it is determined that the product mark of the product to be detected is unqualified.

[0071] In some embodiments, the product to be detected is transported to the detection station by a transportation device, and the product detection device is further configured to: if the product mark of the product to be detected is qualified, a prompt signal is sent to the transportation device to make the transportation device remove the product to be detected from the detection station; if the product mark of the product to be detected is unqualified, an alarm is issued.

[0072] In some embodiments, the target mark is a plurality of target marks, each target mark corresponding to a detection area of the product to be detected, and the determination of whether the target mark is detected according to the detection result includes: determining whether the target mark is detected in each detection area according to the detection result; if the target mark is detected in each detection area, it is determined that the target mark is detected; if the target mark is not detected in any detection area, it is determined that the target mark is not detected.

[0073] In some embodiments, the trigger mode of the image recognition device is preset as an external trigger, the communication source of the image recognition device is preset as a communication trigger, and the detection area of the image recognition device is preset as an identification area of the reference picture of the product to be detected.

[0074] The implementation process of the functions and roles of the units in the above device is specifically described in the implementation process of the corresponding steps in the above method, which will not be repeated here.

[0075] For the device embodiment, since it basically corresponds to the method embodiment, the relevant part can be referred to the part of the method embodiment. The device embodiments described above are only illustrative, and the units described as separate components can or can not be physically separated, and the components displayed as units can or can not be physical units, that is, they can be located in one place, or they can be distributed on multiple network units. According to actual needs, some or all of the modules can be selected to achieve the purpose of the present disclosure. Those skilled in the art can understand and implement it without creative labor.

[0076] The system, device, module or unit illustrated in the above embodiments can be specifically implemented by a computer chip or entity, or by a product with certain functions. A typical implementation device is a computer, and the specific form of the computer can be a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email transceiver device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0077] In a typical configuration, the computer includes one or more processors (CPUs), input / output interfaces, network interfaces, and memories.

[0078] The memory can include non-persistent memory in computer readable medium, random access memory (RAM), and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM). The memory is an example of computer readable media.

[0079] Computer-readable media includes permanent and non-permanent, removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage, quantum memory, graphene-based storage media, or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to computing devices. According to the definition herein, computer-readable media does not include transitory media such as modulated data signals and carriers.

[0080] The user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present disclosure are information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation portal for user to choose authorization or refusal.

[0081] It should also be noted that the terms "comprising", "including", or any other variant thereof are intended to cover non-exclusive inclusion, so that processes, methods, articles or devices including a series of elements not only include those elements, but also include other elements not explicitly listed or inherent to such processes, methods, articles or devices. Without more limitations, the element defined by the statement "including a" does not exclude the presence of another identical element in the process, method, article or device including the element.

[0082] The above describes specific embodiments of the present disclosure. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different than the order in the embodiments and still achieve the desired result. In addition, the processes depicted in the figures do not necessarily require the particular order shown or sequential order to achieve the desired results. In certain implementations, multi-task processing and parallel processing are possible or can be advantageous.

[0083] The terminology used in this disclosure one or more embodiments is for the purpose of describing particular embodiments only and is not intended to be limiting of this disclosure one or more embodiments. As used in this disclosure one or more embodiments and the accompanying claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0084] It is to be understood that the terms first, second, third, etc. can be employed merely for distinguishing between similar information, and do not imply a relationship or hierarchy between the information so distinguished. For example, a first information can be termed a second information, and, similarly, a second information can be termed a first information, without departing from the scope of this disclosure one or more embodiments. As used herein, the term "if' can be construed to mean "when" or "upon" or "in response to determining" or "in response to a determination" depending on the context.

[0085] The foregoing is merely illustrative of the principles of this disclosure one or more embodiments and various modifications can be made by persons skilled in the art without departing from the scope and nature of the disclosure one or more embodiments as disclosed in the specification and their equivalent.

Claims

1. A product identification detection method, characterized in that: The method is applied to a detection system, wherein the detection system includes a product detection device controlled by a PLC and an image recognition device supporting a PLC communication protocol, and the method includes: After the product inspection device detects that there is a product to be inspected at its own inspection station, the product inspection device sends a trigger signal to the image recognition device through the PLC communication protocol; After receiving the trigger signal, the image recognition device performs image recognition on the product to be inspected, obtains a detection result in the form of structured characters, and transmits the detection result back to the product inspection device via the PLC communication protocol; After receiving the test results, the product testing device performs corresponding processing according to the test results.

2. The method according to claim 1, characterized in that The product inspection device predefines a work step execution logic. After detecting that there is a product to be inspected at its own inspection station, the product inspection device sends a trigger signal to the image recognition device through the PLC communication protocol, including: The product inspection device counts the steps after detecting the presence of the product to be inspected at its inspection station; and sends an enable signal to the image recognition device through the PLC communication protocol; After receiving the enable signal, the image recognition device performs state preparation and returns state readiness information to the product detection device after being ready; After the product inspection device runs to a preset triggering step and has received the status ready information, it sends a trigger signal to the image recognition device through the PLC communication protocol.

3. The method according to claim 2, characterized in that The product detection device includes a barcode scanner, and the method further includes: After the product inspection device detects that there is a product to be inspected at its own inspection station, it scans the barcode of the product to be inspected by the barcode scanner to determine the product type of the product to be inspected based on the barcode; After receiving the test result, the product testing device performs corresponding processing according to the test result, including: After the product inspection device has run to the preset judgment step and has received the inspection result, it performs corresponding processing according to the product type of the product to be inspected and the inspection result.

4. The method according to claim 3, characterized in that After the product inspection device reaches the preset judgment step and has received the inspection result, it performs corresponding processing according to the product type of the product to be inspected and the inspection result, including: After the product inspection device reaches a preset judgment step and has received the inspection result, it determines whether the target identifier is detected according to the inspection result; If the target identifier is detected and the product type of the product to be detected is the first type, or if the target identifier is not detected and the product type of the product to be detected is the second type, then determining that the product identifier of the product to be detected is qualified; Otherwise, it is determined that the product identification of the product to be tested is unqualified.

5. The method according to claim 4, characterized in that The product to be inspected is transported to the inspection station by a transport device, and the method further includes: If the product identification of the product to be inspected is qualified, the product inspection device sends a prompt signal to the transport device, so that the transport device removes the product to be inspected from the inspection station; If the product identification of the product to be tested is unqualified, the product testing equipment will issue an alarm.

6. The method according to claim 4, characterized in that There are multiple target identifiers, each target identifier corresponds to a detection area of ​​the product to be detected, and determining whether the target identifier is detected according to the detection result includes: Determining whether the target identifier is detected in each detection area according to the detection result; If the target identifier is detected in each detection area, it is determined that the target identifier is detected; If the target marker is not detected in any detection area, it is determined that the target marker is not detected.

7. The method according to claim 1, characterized in that The trigger mode of the image recognition device is preset to external trigger, the communication source of the image recognition device is preset to communication trigger, and the detection area of ​​the image recognition device is preset to the identification area of ​​the reference image of the product to be detected.

8. A product identification detection system, characterized in that: The system comprises: Product inspection equipment, the product inspection equipment is controlled by a PLC and is used to send a trigger signal to the image recognition device through the PLC communication protocol after detecting the presence of a product to be inspected at its own inspection station; An image recognition device, the image recognition device supporting the PLC communication protocol, configured to, upon receiving the trigger signal, perform image recognition on the product to be inspected, obtain a detection result in the form of structured characters, and transmit the detection result back to the product inspection device via the PLC communication protocol; The product testing device is further configured to perform corresponding processing according to the test results after receiving the test results.

9. An electronic device, characterized in that: It includes a communication interface, a processor, a memory and a bus, wherein the communication interface, the processor and the memory are interconnected via the bus; The memory stores machine-readable instructions, and the processor executes the method according to any one of claims 1 to 7 by calling the machine-readable instructions.

10. A machine-readable storage medium, characterized in that The machine-readable storage medium stores machine-readable instructions, and when the machine-readable instructions are called and executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images