Machine vision-based device and method for adding medicine powder into medicine adding room of water plant

Abstract

The invention discloses a water plant dosing room medicine powder dosing device and method based on machine vision, and relates to the field of medicine powder dosing. According to the device, an automatic control system controls an automatic tray conveyor to convey trays and medicine bags from a feeding station to a visual recognition station, and a material shortage signal is detected in real time; the upper computer system checks the material shortage signal to generate an authorization signal; the automatic control system controls the 3D visual camera to collect images at the visual identification station according to the authorization signal; the upper computer system determines grabbing coordinates according to the image; the automatic control system controls the robot to grab the medicine bags and transfer the grabbed medicine bags from the visual identification station to the bag breaking machine according to the grabbing coordinates, controls the bag breaking machine to break the grabbed medicine bags and store medicine powder in the medicine bags, and controls the material suction machine to suck the medicine powder and convey the medicine powder to the metering bin; and the metering bin is controlled to calculate the weight of the medicine powder and the medicine powder with the set weight is added into water. By means of the intelligent medicine powder adding process, the medicine powder adding process quality is improved.

Description

Technical Field

[0001] The present application relates to the field of water industry, and in particular to a device and method for adding powder in a water plant's dosing room based on machine vision. Background Art

[0002] In the operation process of the water plant's dosing room, the powder involved in water treatment is stored in a soft medicine bag before being added. At present, the drug bag still relies on manual labor from material collection and storage, bag breaking to powder addition to the warehouse. The manual operation method not only requires the operator's experience and judgment, but also poses a risk of occupational diseases (inhaled dust). At the same time, this operation is heavy physical labor, and the overall quality of the water production process may be affected due to human factors. It has become very necessary to improve the process quality of this link through intelligent transformation and eliminate the shortcomings of the current traditional dosing process. At the same time, this is also one of the ways for the water industry to move towards intelligence. Summary of the invention

[0003] The purpose of this application is to provide a device and method for adding powder in the dosing room of a water plant based on machine vision, so as to improve the process quality of powder adding through an intelligent powder adding process.

[0004] To achieve the above objectives, this application provides the following solutions:

[0005] In the first aspect, the present application provides a powder dosing device in a water plant dosing room based on machine vision, comprising: an automatic tray conveyor, a 3D vision camera, a robot, a bag breaker, a metering silo, a suction machine, an automatic control system, and a host computer system;

[0006] The automatic control system is in communication connection with the host computer system, the automatic pallet conveyor, the 3D visual camera, the robot, the bag breaking machine, the metering silo and the suction machine; the automatic control system is used to control the automatic pallet conveyor to convey the pallet and the medicine bag from the loading station to the visual recognition station, and to detect the shortage of material in real time and send the signal to the host computer system; the medicine bag is located on the pallet;

[0007] The host computer system is used to review the material shortage signal, generate an authorization signal, and send the authorization signal to the automatic control system;

[0008] The automatic control system is also used to control the 3D visual camera to collect images at the visual recognition station according to the authorization signal, and send them to the host computer system;

[0009] The host computer system is also used to determine the grabbing coordinates according to the image at the visual recognition station, and send the grabbing coordinates to the automatic control system;

[0010] The automatic control system is also used to control the robot to grab the medicine bag according to the grabbing coordinates and transfer the grabbed medicine bag from the visual recognition station to the bag breaking machine, control the bag breaking machine to break the grabbed medicine bag and store the medicine powder in the medicine bag, control the suction machine to absorb the medicine powder in the bag breaking machine and transfer it to the metering silo, control the metering silo to calculate the weight of the medicine powder and add the set weight of the medicine powder into the water.

[0011] In a second aspect, the present application provides a method for adding powder to a water plant's dosing room based on machine vision, comprising: the method for adding powder to a water plant's dosing room based on machine vision comprises:

[0012] The automatic pallet conveyor is controlled by the automatic control system to convey the pallet and the medicine package from the loading station to the visual recognition station, and the shortage signal is detected in real time and sent to the upper computer system; the medicine package is located on the pallet;

[0013] The upper computer system reviews the material shortage signal, generates an authorization signal, and sends the authorization signal to the automatic control system;

[0014] The automatic control system controls the 3D vision camera to collect images at the visual recognition station according to the authorization signal, and sends the images to the host computer system;

[0015] Determine the grabbing coordinates according to the image at the visual recognition station through the host computer system, and send the grabbing coordinates to the automatic control system;

[0016] The automatic control system controls the robot to grab the medicine bag according to the grabbing coordinates and transfer the grabbed medicine bag from the visual recognition station to the bag breaking machine, controls the bag breaking machine to break the grabbed medicine bag and store the medicine powder in the medicine bag, controls the suction machine to absorb the medicine powder in the bag breaking machine and transfer it to the metering silo, controls the metering silo to calculate the weight of the medicine powder and add the set weight of the medicine powder into the water.

[0017] According to the specific embodiments provided in this application, this application has the following technical effects:

[0018] The present application provides a device and method for adding powder in the medicine adding room of a water plant based on machine vision. Through the cooperation of the automatic control system and the host computer system, the automatic tray conveyor and the 3D visual camera are controlled to collect images of the tray and the medicine bag at the specified position, and the robot is controlled to transfer the medicine bag from the specified position to the bag breaking machine. The intelligent collection of images and transfer of medicine bags make the collected images more accurate, reduce manual errors, avoid heavy physical labor of workers, and reduce safety hazards. Secondly, the automatic control system controls the bag breaking machine to break the medicine bag, the suction machine to absorb the medicine powder, and the metering silo to add the set weight of medicine powder into the water. This process avoids the impact of artificial inhalation of medicine powder on health, and the use of the metering silo makes the powder addition more accurate, which increases the overall quality of the water production process. The entire intelligent powder addition process of the present application not only avoids manual work, reduces the impact of manpower on the powder addition, makes the powder addition more accurate, improves the process quality of the powder addition, but also ensures the health of workers. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1 This is a structural schematic diagram of a powder dosing device in a water plant dosing room based on machine vision in one embodiment of the present application;

[0021] Figure 2 A schematic diagram of a system module in a powder dosing device in a dosing room of a water plant based on machine vision provided in one embodiment of the present application;

[0022] Figure 3 A schematic flow chart of a method for adding powder to a dosing room in a water plant based on machine vision is provided as an embodiment of the present application.

[0023] Reference numerals:

[0024] Loading station—1, automatic pallet conveyor—2, visual recognition station—3, 3D visual camera—4, robot—5, waste bag recycling machine—6, bag breaking machine—7, suction machine—8, metering silo—9. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0026] In order to make the purpose, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0027] In an exemplary embodiment, Figure 1 As shown, a powder dosing device for a water plant dosing room based on machine vision is provided, and the powder dosing device for a water plant dosing room based on machine vision includes: an automatic tray conveyor 2, a 3D vision camera 4, a robot 5, a bag breaker 7, a metering silo 9, a suction machine 8, an automatic control system and a host computer system.

[0028] The automatic control system is communicatively connected with the host computer system, the automatic pallet conveyor 2, the 3D vision camera 4, the robot 5, the bag breaker 7, the metering silo 9 and the suction machine 8; the automatic control system is used to control the automatic pallet conveyor 2 to transfer the pallet and the medicine package from the loading station 1 to the visual recognition station 3, and detect the shortage of material signal in real time and send it to the host computer system; the medicine package is located on the pallet.

[0029] Specifically, when the powder supplier delivers the medicine packages, the forklift transfers the whole stack of medicine packages and the pallet from the transport vehicle to the loading station 1 of the pallet automatic conveyor 2, and the forklift puts down the pallet and then withdraws. The automatic control system senses that the pallet is put down, and after the forklift withdraws, it transfers the pallet and the whole stack of medicine packages. The visual recognition station 3 is also used to store medicine packages.

[0030] The host computer system is used to review the material shortage signal, generate an authorization signal, and send the authorization signal to the automatic control system.

[0031] The automatic control system is also used to control the 3D vision camera 4 to collect images at the visual recognition station 3 according to the authorization signal and send them to the host computer system. The 3D vision camera 4 is fixed at the center position just above the visual recognition station 3 to take pictures of the entire stack of medicine packages.

[0032] The host computer system is also used to determine the grabbing coordinates according to the image at the visual recognition station 3, and send the grabbing coordinates to the automatic control system.

[0033] The automatic control system is also used to control the robot 5 to grab the medicine bag according to the grabbing coordinates and transfer the grabbed medicine bag from the visual recognition station 3 to the bag breaking machine 7, control the bag breaking machine 7 to break the grabbed medicine bag and store the medicine powder in the medicine bag, control the suction machine 8 to absorb the medicine powder in the bag breaking machine 7 and transfer it to the metering silo 9, control the metering silo 9 to calculate the weight of the medicine powder and add the set weight of the medicine powder into the water. The robot 5 is a four-axis robot. The metering silo 9 is a precision metering silo.

[0034] Specifically, the robot 5 carries the medicine bag to the top of the bag breaker 7 for bag breaking, and the medicine powder falls into the bag breaker 7. The suction machine 8 generates negative pressure in the powder delivery pipeline, and the medicine powder is sucked into the metering silo 9. Multiple metering silos 9 can be set up to achieve the effect of sharing a set of equipment for multiple powder target dosing points. In addition, the powder delivery pipeline can be equipped according to the actual working conditions on site, so that the powder dosing device has certain flexibility. The metering silo 9 receives the medicine powder transported by the powder delivery pipeline, and relies on the weighing sensor to accurately measure the medicine powder entering the silo and the medicine powder added out of the silo.

[0035] In another exemplary embodiment of the present application, the bag breaking machine 7 specifically includes: a bag breaking tool and a material dropping chamber. The bag breaking tool is used to break the medicine bag under the control of the automatic control system. The material dropping chamber is used to store the medicine powder in the medicine bag.

[0036] In another exemplary embodiment of the present application, the machine vision-based powder dosing device in the water plant dosing room also includes: a waste bag recycling machine 6, and the automatic control system is also used to control the waste bag recycling machine 6 to recycle the medicine bags in the medicine bag grabbed by the robot 5. The medicine bags in the medicine bag are transferred by the robot 5 to the waste bag recycling machine 6 for recycling. The waste bag recycling machine 6 compresses the medicine bags inside the equipment. When the empty bags in the waste bag recycling machine 6 are full, an alarm will be issued to inform the staff to perform the recycling operation. The staff can perform this operation without entering the safety fence, ensuring the safety of the personnel.

[0037] In another exemplary embodiment of the present application, the machine vision-based powder dosing device in the water plant dosing room also includes: a tray centering and locking mechanism and a tray automatic ejection mechanism; the tray centering and locking mechanism and the tray automatic ejection mechanism are both located at the visual recognition station 3.

[0038] The automatic control system is also used to control the pallet centering and locking mechanism to center and lock the pallet at the visual recognition station 3.

[0039] The automatic control system is also used to control the automatic tray pushing mechanism to push out the tray at the visual recognition station 3.

[0040] When the visual recognition station 3 recognizes the pallet, the pallet centering and locking mechanism will center and lock the pallet, waiting for the out-of-material signal. When the automatic control system detects the out-of-material signal, the 3D visual camera 4 starts to collect the image at the visual recognition station 3 according to the control of the automatic control system, and sends it to the host computer system. The host computer system determines whether there is a medicine package based on the image at the visual recognition station 3. If so, it determines the grabbing coordinates of the medicine package and sends them to the automatic control system. The automatic control system controls the robot 5 to perform the medicine package grabbing operation according to the grabbing coordinates (x, y, z) of the medicine package; if the host computer system does not recognize the medicine package based on the image at the visual recognition station 3, the pallet centering and locking mechanism will be unlocked, and the pallet will be pushed out of the visual recognition station 3 by the automatic pallet pushing mechanism.

[0041] In another exemplary embodiment of the present application, Figure 2 As shown in the figure, the powder dosing device in the water plant dosing room based on machine vision mainly includes an automatic control system (Programmable Logic Controller, PLC), an edge manufacturing execution system (Manufacturing Execution System, MES) and a visual recognition model. The edge manufacturing execution system and the visual recognition model are pre-stored in the upper computer system, and the data is interoperable with the lower computer automatic control system to ensure that the powder dosing device is safe, efficient and controllable. As shown in Tables 1, 2 and 3 below.

[0042] Table 1 Interaction data between automatic control system and visual recognition model

[0043]

[0044] Table 2 Interaction data between the automatic control system and the edge manufacturing execution system

[0045]

[0046] Table 3 Interaction data between visual recognition model and edge manufacturing execution system

[0047]

[0048] Among them, the automatic control system includes the human machine interface (HMI) subsystem, the robot subsystem, the sensor subsystem, and the safety circuit subsystem. Among them, the HMI subsystem provides a way for human-machine interaction for the production site. The robot subsystem stores multiple task programs and corrects the grasping position according to the calculation results of the visual recognition model in the host computer system. The sensor subsystem includes functions such as material transmission perception, equipment fault detection, and precise measurement of powder. The safety circuit subsystem is composed of safety equipment such as emergency stop buttons, safety light curtains, safety door locks, and safety programmable controllers, which are set according to the on-site working conditions.

[0049] The edge manufacturing execution system reviews the material shortage signal, generates an authorization signal, and sends the authorization signal to the automatic control system. The edge manufacturing execution system is a workshop-level information management and control platform, which is mainly composed of an inventory management module, an equipment management module, a data analysis module, and a data visualization module. It can be directly connected to the powder dosing device, and can also be connected to the information of the production workshop where the powder dosing device is located. The inventory management module records various material information in the workshop where the powder dosing device is located. The equipment management module manages various production equipment in the workshop where the powder dosing device is located, including equipment start and stop, equipment status monitoring, and production capacity configuration. The data analysis module conducts multi-dimensional analysis of the real-time data of the automatic control system, the edge MES storage data, and the calculation results of the visual recognition model, generates production reports, and proposes production optimization plans. The data visualization module displays the on-site equipment status information in three dimensions to reduce the difficulty of personnel management.

[0050] Based on the images captured by the 3D vision camera 4, the automatic control system automatically calls the visual recognition model in the host computer system to analyze the current working conditions. The relevant visual recognition models include the three-dimensional visual recognition model for soft package unpalletizing, the model for the recognition of the presence or absence of a pallet, the model for the recognition of abnormal workstations, and the model for the recognition of damaged medicine packages. The three visual models of the model for the recognition of the presence or absence of a pallet, the model for the recognition of abnormal workstations, and the model for the recognition of damaged medicine packages complete the task objectives through the methods of image acquisition, image processing, feature extraction, detection and judgment, and output results, ensuring the stable operation of the entire device.

[0051] The production process of this application is fully automated, and the process quality is guaranteed; the edge MES records the data of drug packages in and out of the warehouse, and generates a replenishment plan in time according to the material consumption; the drug powder addition data is accurately measured; the bag breaking process is automatically grasped by the visually guided robot 5, and the drug powder remaining in the drug bag after bag breaking is ≤0.1%; the automatic control system automatically determines the replenishment position and autonomously triggers the drug feeding process.

[0052] Based on the same inventive concept, Figure 3 As shown, the embodiment of the present application also provides a method for adding powder in a water plant dosing room based on machine vision. The method for adding powder in a water plant dosing room based on machine vision includes steps 101 to 105.

[0053] Step 101, control the automatic tray conveyor 2 through the automatic control system to convey the tray and the medicine package from the loading station 1 to the visual recognition station 3, and detect the shortage signal in real time and send it to the upper computer system; the medicine package is located on the tray.

[0054] Step 102, the upper computer system reviews the material shortage signal, generates an authorization signal, and sends the authorization signal to the automatic control system.

[0055] Step 103, the automatic control system controls the 3D vision camera 4 according to the authorization signal to collect the image at the visual recognition station 3, and sends it to the host computer system.

[0056] Step 104 , determining the grabbing coordinates according to the image at the visual recognition station 3 by the host computer system, and sending the grabbing coordinates to the automatic control system.

[0057] Step 105, controlling the robot 5 to grab the medicine bag according to the grabbing coordinates through the automatic control system and transferring the grabbed medicine bag from the visual recognition station 3 to the bag breaking machine 7, controlling the bag breaking machine 7 to break the grabbed medicine bag and store the medicine powder in the medicine bag, controlling the suction machine 8 to absorb the medicine powder in the bag breaking machine 7 and transfer it to the metering silo 9, controlling the metering silo 9 to calculate the weight of the medicine powder and add the set weight of the medicine powder into the water.

[0058] As an optional embodiment, after the automatic pallet conveyor 2 is controlled by the automatic control system to transfer the pallet and the medicine package from the loading station 1 to the visual recognition station 3, it also includes: controlling the pallet centering locking mechanism by the automatic control system to lock the pallet at the visual recognition station 3.

[0059] As an optional implementation, the host computer system determines the grasping coordinates based on the image at the visual recognition station 3, specifically including: the host computer system determines the grasping coordinates based on the image at the visual recognition station 3 by using a sampling consistency algorithm and a spatial clustering algorithm.

[0060] As an optional implementation, the host computer system uses a sampling consistency algorithm and a density space clustering algorithm according to the image at the visual recognition station 3 to determine the grabbing coordinates, specifically including:

[0061] The point cloud data is acquired by the host computer system based on the image at the visual recognition station 3.

[0062] Based on the point cloud data, a sampling consistency algorithm is used to segment the planar point cloud data.

[0063] The density space clustering algorithm is used to cluster the non-planar point cloud data.

[0064] Determine the grabbing coordinates based on the clustered point cloud data.

[0065] Specifically, the random sample consensus algorithm (RANSAC) is first used to segment the plane from the point cloud data generated by the camera, and then the density-based spatial clustering algorithm (DBSCAN) is used to cluster the non-planar point cloud. Finally, the coordinates of all point clouds belonging to the same cluster are averaged in each dimension (x, y, z) to obtain a coordinate point representing the center position of the cluster, which is output as the grasping coordinate and sent to the robot 5. After receiving the grasping coordinate, the robot 5 automatically adjusts the movement trajectory to grasp the medicine package.

[0066] As an optional implementation, after the bag breaking machine 7 is controlled by the automatic control system to break the grabbed medicine bag and store the medicine powder in the medicine bag, it also includes: controlling the robot 5 by the automatic control system to transfer the medicine bag in the grabbed medicine bag to the waste bag recycling machine 6, and controlling the waste bag recycling machine 6 to recycle the medicine bag.

[0067] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0068] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0069] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0070] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0071] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A powder dosing device for a water plant dosing room based on machine vision, characterized in that: The powder dosing device in the water plant dosing room based on machine vision includes: an automatic tray conveyor, a 3D vision camera, a robot, a bag breaker, a metering silo, a suction machine, an automatic control system and a host computer system; The automatic control system is in communication connection with the host computer system, the automatic pallet conveyor, the 3D visual camera, the robot, the bag breaking machine, the metering silo and the suction machine; the automatic control system is used to control the automatic pallet conveyor to convey the pallet and the medicine bag from the loading station to the visual recognition station, and to detect the shortage of material in real time and send the signal to the host computer system; the medicine bag is located on the pallet; The host computer system is used to review the material shortage signal, generate an authorization signal, and send the authorization signal to the automatic control system; The automatic control system is also used to control the 3D visual camera to collect images at the visual recognition station according to the authorization signal, and send the images to the host computer system; The host computer system is also used to determine the grabbing coordinates according to the image at the visual recognition station, and send the grabbing coordinates to the automatic control system; The automatic control system is also used to control the robot to grab the medicine bag according to the grabbing coordinates and transfer the grabbed medicine bag from the visual recognition station to the bag breaking machine, control the bag breaking machine to break the grabbed medicine bag and store the medicine powder in the medicine bag, control the suction machine to absorb the medicine powder in the bag breaking machine and transfer it to the metering silo, control the metering silo to calculate the weight of the medicine powder and add the set weight of the medicine powder into the water.

2. The device for adding powder in the water plant dosing room based on machine vision according to claim 1 is characterized in that: The machine vision-based powder dosing device for the water plant dosing room also includes: a waste bag recycling machine; The automatic control system is also used to control the waste bag recycling machine to recycle the medicine bags in the medicine packages grabbed by the robot.

3. The device for adding powder in the water plant dosing room based on machine vision according to claim 1 is characterized in that: The bag breaking machine comprises: A bag breaking tool, used for breaking the medicine bag under the control of the automatic control system; The blanking cavity is used to store the medicine powder in the medicine bag.

4. The device for adding powder in the water plant dosing room based on machine vision according to claim 1 is characterized in that: The machine vision-based powder dosing device for the water plant dosing room also includes: a tray centering and locking mechanism; the tray centering and locking mechanism is located at the visual recognition station; The automatic control system is also used to control the pallet centering and locking mechanism to center and lock the pallet at the visual recognition station.

5. The device for adding powder in the water plant dosing room based on machine vision according to claim 1 is characterized in that: The machine vision-based powder dosing device for the water plant dosing room also includes: an automatic tray push-out mechanism, which is located at a visual recognition station; The automatic control system is also used to control the automatic tray pushing mechanism to push out the tray at the visual recognition station.

6. A method for adding powder in a water plant's dosing room based on machine vision, using the device for adding powder in a water plant's dosing room based on machine vision as claimed in any one of claims 1 to 5, characterized in that: The method for adding powder in the water plant dosing room based on machine vision includes: The automatic pallet conveyor is controlled by the automatic control system to convey the pallet and the medicine package from the loading station to the visual recognition station, and the shortage signal is detected in real time and sent to the upper computer system; the medicine package is located on the pallet; The upper computer system reviews the material shortage signal, generates an authorization signal, and sends the authorization signal to the automatic control system; The automatic control system controls the 3D vision camera to collect images at the visual recognition station according to the authorization signal, and sends the images to the host computer system; Determine the grabbing coordinates according to the image at the visual recognition station through the host computer system, and send the grabbing coordinates to the automatic control system; The automatic control system controls the robot to grab the medicine bag according to the grabbing coordinates and transfer the grabbed medicine bag from the visual recognition station to the bag breaking machine, controls the bag breaking machine to break the grabbed medicine bag and store the medicine powder in the medicine bag, controls the suction machine to absorb the medicine powder in the bag breaking machine and transfer it to the metering silo, controls the metering silo to calculate the weight of the medicine powder and add the set weight of the medicine powder into the water.

7. The method for adding powder in the water plant dosing room based on machine vision according to claim 6 is characterized in that: After the automatic pallet conveyor is controlled by the automatic control system to convey the pallet and the medicine package from the loading station to the visual recognition station, the method further includes: controlling the pallet centering locking mechanism by the automatic control system to lock the pallet at the visual recognition station.

8. The method for adding powder in the water plant dosing room based on machine vision according to claim 6 is characterized in that: The host computer system determines the grabbing coordinates according to the image at the visual recognition station, specifically including: The host computer system determines the grabbing coordinates based on the image at the visual recognition station by using a sampling consistency algorithm and a spatial clustering algorithm.

9. The method for adding powder in the water plant dosing room based on machine vision according to claim 8, characterized in that: The host computer system uses a sampling consistency algorithm and a density space clustering algorithm according to the image at the visual recognition station to determine the grabbing coordinates, specifically including: Acquiring point cloud data according to the image at the visual recognition station through the host computer system; Based on the point cloud data, a sampling consistency algorithm is used to segment the plane point cloud data; The density space clustering algorithm is used to cluster the non-planar point cloud data; Determine the grabbing coordinates based on the clustered point cloud data.

10. The method for adding powder in the water plant dosing room based on machine vision according to claim 6, characterized in that: After the bag breaking machine is controlled by the automatic control system to break the grabbed medicine bag and store the medicine powder in the medicine bag, it also includes: controlling the robot by the automatic control system to transfer the medicine bag in the grabbed medicine bag to the waste bag recycling machine, and controlling the waste bag recycling machine to recycle the medicine bag.

Images