Intelligent sorting, disinfecting and packaging platform for medical waste

Abstract

An intelligent sorting, disinfecting and packaging platform for medical waste belongs to the field of waste treatment and comprises a machine vision module, an internet of things control module, a sorting module, a waste collection and storage module and a control power supply module. Through the automatic sorting, disinfecting and packaging processes, the manual operation time is shortened, and the overall efficiency of medical waste treatment is improved. The intelligent sorting system can effectively distinguish recoverable medical waste from unrecoverable medical waste, and resource reutilization is promoted. And through efficient disinfection and sealed packaging, harmful substances are prevented from leaking, and the environment is protected against pollution. The automatic operation reduces the dependence on manpower, and reduces the labor cost and management difficulty.

Description

Technical Field

[0001] The present invention belongs to the technical field of waste disposal, and more specifically, particularly relates to an intelligent sorting, disinfecting and packaging platform for medical waste. Background Art

[0002] In the context of the prosperous development of the Internet industry, the "Internet + Medical" model has developed rapidly, but the corresponding medical waste treatment mechanism has not yet been established. The "Work Plan for Comprehensive Management of Waste in Medical Institutions" and other policy documents clearly put forward relevant regulations and requirements for strengthening the management of medical waste under the "Internet + Medical" model to ensure the safety and effectiveness of medical waste during the treatment process. The introduction of these regulations and requirements provides support and guarantee for adapting to the new industrial development trend. The development of machine vision technology provides a new perspective for solving the above problems. As a widely used technology, it has penetrated into many fields such as agriculture, industry, national defense, medical care and daily life. Among them, multi-target recognition algorithms have a large number of successful application cases in industrial automation, military reconnaissance, medical assistance and transportation convenience. However, from the current research status at home and abroad, the application of intelligent garbage sorting technology based on machine vision to the medical subdivision field is still insufficient, there are few application cases of target detection of medical waste, and there are insufficient resources on medical waste in image recognition data sets such as ImageNet and COCO.

[0003] In this context, a more intelligent and efficient source classification and treatment method for medical waste and path tracking are urgently needed, which is of great significance to solving the global medical waste treatment problem and blocking the secondary spread of diseases. Therefore, this project intends to design an intelligent trash can with intelligent sensing devices, special compression and disinfection treatment devices, full load detection devices and leakage detection devices. Through machine vision technology and neural network models, the trash can can automatically identify and sort garbage, including masks, tablets and pills, medical supplies and other hazardous waste. At the same time, the trash can can upload full load alarms and damage alarms to Huawei Cloud and the manager's mobile phone APP in time, reminding the manager to clean and repair the trash can in time. After the garbage is full, it will be automatically packaged and disinfected inside the trash can. The packaged garbage will be sent to the centralized treatment point. After delivery, the manager will receive a message reminder that the delivery has been confirmed to ensure the safe treatment and harmless disposal of medical waste. Summary of the invention

[0004] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0005] In view of the above or existing problems of digital intelligent manufacturing platforms, the present invention is proposed.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] The embodiment of the present invention provides a digital intelligent manufacturing platform, including: a machine vision module, which is used to install a photosensitive sensor at a garbage throwing port to collect and identify garbage images; an Internet of Things control module, which is used to monitor the status of a garbage bin in real time by connecting sensors; a sorting module, which is used to control a mechanical arm or other execution devices according to the recognition result of the machine vision module to sort different types of garbage to corresponding collection and storage modules; a garbage collection and storage module, which is used to calculate the optimal moving path of the mechanical arm using a path planning algorithm, transport the garbage to the corresponding garbage bin, and use a loading optimization algorithm to allocate the position of the garbage in the garbage bin; and a power supply control module, which is used to supply power in sequence according to the startup sequence and power requirements of each module, and use a PID control algorithm to adjust the current and voltage in real time.

[0008] As a preferred solution of the digital intelligent manufacturing platform of the present invention, the photosensitive sensor is installed at the garbage throwing port to collect and identify garbage images, including:

[0009] When the throwing door is opened, the light becomes stronger and the camera is prohibited from taking pictures; when the throwing door is closed, the light becomes darker and the camera is triggered to take pictures.

[0010] As a preferred solution of the digital intelligent manufacturing platform of the present invention, wherein: the photosensitive sensor is installed at the garbage throwing port to collect and identify garbage images, and further includes:

[0011] Use the YOLOv5 algorithm to process the collected images, identify the types of garbage, perform data enhancement on the collected images, and normalize the image pixel values. The YOLOv5 algorithm formula is as follows:

[0012] Positioning loss:

[0013]

[0014] Among them, S c is the minimum enclosed area of ​​the predicted box and the true box, S u is the area of ​​the union of the two;

[0015] Confidence loss:

[0016] Loss conf =-[y·log(p)+(1-y)·log(1-p)]

[0017] Among them, y is the true label and p is the confidence of the prediction;

[0018] Classification loss:

[0019]

[0020] Among them, C is the number of categories, y c is the one-hot encoding of the true category, p c is the predicted class probability.

[0021] As a preferred solution of the digital intelligent manufacturing platform of the present invention, wherein: the real-time monitoring of the status of the trash can by connecting the sensor includes:

[0022] When the trash can is full, the room number and the category of the full trash classification bin will be sent to the manager's mobile APP; when the trash can is damaged, the room number and damage information will be sent to the manager's mobile APP to remind that repairs are needed.

[0023] As a preferred solution of the digital intelligent manufacturing platform of the present invention, wherein: the real-time monitoring of the status of the trash can by connecting the sensor also includes:

[0024] The ultrasonic sensor measures the distance d from the sensor to the surface of the garbage. If the total height of the garbage can is H, the filling height h of the garbage is:

[0025] h=Hd

[0026] Set a full load threshold height h threshold When the measured filling height h is greater than or equal to the threshold, the trash can is determined to be full.

[0027] As a preferred solution of the digital intelligent manufacturing platform of the present invention, the control of the mechanical arm or other execution device according to the recognition result of the machine vision module to sort different types of garbage to the corresponding collection and storage modules includes:

[0028] The visual algorithm is used to determine the position coordinates (x, y) of the garbage on the conveyor belt. According to the location of the garbage and the location of the target collection and storage module, the movement path of the robotic arm is planned, and the robotic arm is controlled to move along the planned path to grab the garbage and place it in the corresponding collection and storage module.

[0029] As a preferred solution of the digital intelligent manufacturing platform of the present invention, the method of calculating the optimal moving path of the robot arm by using a path planning algorithm to transport the garbage to the corresponding garbage bin includes:

[0030] Model the workspace of the robot arm, determine the location and shape of obstacles, and apply A *The algorithm searches for a collision-free path in the modeled space, optimizes the initial path, and converts the optimized path into the joint space trajectory of the robot arm for execution by the controller. * The algorithm formula is as follows:

[0031] f(n)=g(n)+h(n)

[0032] Among them, f(n) is the comprehensive cost of node n, g(n) is the actual cost from the starting point to node n, and h(n) is the heuristic estimated cost from node n to the goal.

[0033] As a preferred solution of the digital intelligent manufacturing platform of the present invention, wherein: the use of a loading optimization algorithm to allocate the position of garbage in the garbage bin includes:

[0034] Construct a mathematical model to maximize the utilization of the trash can, expressed as:

[0035]

[0036] Where n is the total number of garbage items, m is the total number of garbage bins, V i is the volume of the ith garbage item, C j is the capacity of the jth trash can, x ij Whether the i-th garbage item is put into the j-th garbage bin;

[0037] Each trash item can only be put into one trash can:

[0038]

[0039] The total amount of garbage in each trash can cannot exceed its capacity:

[0040]

[0041] As a preferred solution of the digital intelligent manufacturing platform of the present invention, the power supply is sequentially supplied according to the startup sequence and power requirements of each module, and the current and voltage are adjusted in real time using the PID control algorithm, including:

[0042] According to the power requirements of each module, the initial output voltage and current of the power module are set, and each module is started in turn according to the predetermined startup sequence. After each module is started, the PID control algorithm is used to monitor and adjust the power output in real time to ensure that each module obtains a stable power supply. The system operation status is continuously monitored, and the PID control parameters are adjusted according to the feedback. The output calculation formula of the PID controller is:

[0043]

[0044] Among them, u(t) is the controller output, e(t) is the current error, K p , K i , K d are the proportional, integral and derivative gains respectively.

[0045] As a preferred solution of the digital intelligent manufacturing platform of the present invention, the initial output voltage and current of the power module are set according to the power requirements of each module, including:

[0046] Set the output voltage of the power module to match the rated voltage of the device, that is, U set =U rated , set the output current limit of the power module higher than the rated current of the device to provide margin:

[0047] I set =I rated ×(1+margin factor)

[0048] The margin coefficient is between 10% and 20%.

[0049] The beneficial effects of the present invention are as follows: the present invention reduces manual operation time and improves the overall efficiency of medical waste treatment by automating the sorting, disinfection and packaging processes. The intelligent sorting system can effectively distinguish between recyclable and non-recyclable medical waste and promote the reuse of resources. Through efficient disinfection and sealed packaging, harmful substances are prevented from leaking and the environment is protected from pollution. Automated operation reduces dependence on manpower, reduces labor costs and management difficulty. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0051] Figure 1 A schematic diagram of the structure of a medical waste intelligent sorting, disinfection and packaging platform provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0052] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0053] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0054] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0055] Example

[0056] Reference below Figure 1 , which is an embodiment of the present invention.

[0057] S1: Machine vision module, used to install photosensitive sensors at the garbage disposal port to collect and identify garbage images.

[0058] Preferably, when the throwing door is opened, the light is enhanced and the camera is prohibited from taking pictures; when the throwing door is closed, the light becomes dim, triggering the camera to take pictures.

[0059] Preferably, the YOLOv5 algorithm is used to process the collected images, identify the types of garbage, perform data enhancement on the collected images, and normalize the image pixel values. The YOLOv5 algorithm formula is as follows:

[0060] Positioning loss:

[0061]

[0062] Among them, S c is the minimum enclosed area of ​​the predicted box and the true box, S u is the area of ​​the union of the two;

[0063] Confidence loss:

[0064] Loss conf =-[y·log(p)+(1-y)·log(1-p)]

[0065] Among them, y is the true label and p is the confidence of the prediction;

[0066] Classification loss:

[0067]

[0068] Among them, C is the number of categories, y c is the one-hot encoding of the true category, pc is the predicted class probability.

[0069] Furthermore, a light sensor is installed at a position where it can accurately sense changes in ambient light, and a throwing door status sensor is installed at an appropriate position of the throwing door to detect its open and closed status; the light sensor collects ambient light intensity data in real time, and converts it into an electrical signal and transmits it to the control unit; the throwing door status sensor monitors changes in the state of the door in real time, and transmits the status signal to the control unit; a logic program is written in the control unit to set a light intensity threshold (for example, setting the light intensity threshold to L_th); when the light sensor detects that the light intensity is higher than L_th and the throwing door status sensor indicates that the door is open, the control unit sends an instruction to prohibit the camera from taking pictures; when the light sensor detects that the light intensity is lower than L_th and the throwing door status sensor indicates that the door is closed, the control unit sends an instruction to trigger the camera to take pictures.

[0070] Furthermore, the preprocessed image is input into the YOLOv5 model and trained using the above loss function. The model parameters are optimized through back propagation and gradient descent algorithms so that it can accurately identify different types of medical waste. During the training process, the validation set is used to monitor the model performance to prevent overfitting, and the hyperparameters are adjusted according to the validation results. After the training is completed, an independent test set is used to evaluate the model's accuracy, recall rate, F1-score and other indicators to ensure that the model meets the actual application requirements. The trained YOLOv5 model is deployed to the medical waste intelligent sorting, disinfection and packaging platform to realize the identification of garbage types in real-time collected images. The recognition results are linked with the robotic arm or other actuators to sort the garbage into the corresponding collection and storage module according to the type of garbage to complete the intelligent sorting process.

[0071] S2: IoT control module, used to monitor the status of the trash can in real time by connecting sensors.

[0072] Preferably, when the trash can is full, the room number and the category of the full trash classification bin are sent to the manager's mobile phone APP; when the trash can is damaged, the room number and damage information are sent to the manager's mobile phone APP to remind that repairs are needed.

[0073] Preferably, the ultrasonic sensor measures the distance d from the sensor to the surface of the garbage. Assuming the total height of the garbage bin is H, the filling height h of the garbage is:

[0074] h=Hd

[0075] Set a full load threshold height h threshold When the measured filling height h is greater than or equal to the threshold, the trash can is determined to be full.

[0076] Furthermore, the ultrasonic sensor measures the distance d in real time and transmits the data to the control unit. The control unit calculates the current filling height h according to the formula h=Hd. The control unit compares the calculated filling height h with the set threshold h threshold Compare. If h≥h threshold , the trash can is determined to be full, and the control unit triggers the alarm device to remind the cleaning staff to clean it in time. After the trash can is emptied, the distance d measured by the ultrasonic sensor will be close to the total height H of the trash can, and the filling height h is close to zero. After the control unit detects this change, it resets the alarm device and the system returns to normal monitoring status.

[0077] S3: Sorting module, used to control the robotic arm or other execution devices to sort different types of garbage to corresponding collection and storage modules according to the recognition results of the machine vision module.

[0078] Preferably, the position coordinates (x, y) of the garbage on the conveyor belt are determined by a visual algorithm, and the movement path of the robotic arm is planned according to the position of the garbage and the position of the target collection and storage module. The robotic arm is controlled to move along the planned path, grab the garbage and place it in the corresponding collection and storage module.

[0079] Furthermore, the target detection algorithm is used to identify the location of garbage in the image, and the center coordinates (x, y) of each piece of garbage are determined through image processing. The deep learning model or stereo vision technology is used to estimate the distance between the garbage and the camera to obtain the three-dimensional coordinates (x, y, z).

[0080] The target location of each piece of garbage is determined based on the preset collection and storage module locations. The path planning algorithm is used to calculate the optimal path from the current garbage location to the target location, taking into account obstacles and the movement limitations of the robotic arm. Based on the path planning results, the movement instructions of the robotic arm are generated, and the robotic arm moves according to the instructions, grabs the garbage and places it in the corresponding collection and storage module.

[0081] S4: Garbage collection and storage module, which is used to calculate the optimal moving path of the robotic arm using the path planning algorithm, transport the garbage to the corresponding garbage bin, and use the loading optimization algorithm to allocate the position of the garbage in the garbage bin.

[0082] Preferably, the working space of the robot arm is modeled, the location and shape of the obstacles are determined, and A is applied * The algorithm searches for a collision-free path in the modeled space, optimizes the initial path, and converts the optimized path into the joint space trajectory of the robot arm for execution by the controller. * The algorithm formula is as follows:

[0083] f(n)=g(n)+h(n) where f(n) is the comprehensive cost of node n, g(n) is the actual cost from the starting point to node n, and h(n) is the heuristic estimated cost from node n to the target.

[0084] Preferably, a mathematical model is constructed to maximize the utilization of the trash can, which is expressed as:

[0085]

[0086] Where n is the total number of garbage items, m is the total number of garbage bins, V i is the volume of the ith garbage item, C j is the capacity of the jth trash can, x ij Whether the i-th garbage item is put into the j-th garbage bin;

[0087] Each trash item can only be put into one trash can:

[0088]

[0089] The total amount of garbage in each trash can cannot exceed its capacity:

[0090]

[0091] Furthermore, the volume of garbage items: V1=10L, V2=15L, V3=20L, V4=25L, V5=30L; the capacity of garbage bins: C1=50L, C2=60L, C3=70L; the above model is input into the integer programming solver to obtain the optimal solution.

[0092] Assume that the solution is: the first garbage item is placed in the first garbage bin, the second garbage item is placed in the second garbage bin, the third garbage item is placed in the third garbage bin, the fourth garbage item is placed in the first garbage bin, and the fifth garbage item is placed in the second garbage bin. At this time, the filling volume of each garbage bin is: the filling volume of the first garbage bin is 10+25=35L, the filling volume of the second garbage bin is 15+30=45L, and the filling volume of the third garbage bin is 20L.

[0093] The utilization rates of the trash cans are: 35 / 50 = 70% for the first trash can, 45 / 60 = 75% for the second trash can, and 20 / 70 = 28.57% for the third trash can. By adjusting the distribution of the trash items, the utilization rate of each trash can can be further optimized.

[0094] S5: Control the power supply module, which is used to supply power in sequence according to the startup sequence and power requirements of each module, and use the PID control algorithm to adjust the current and voltage in real time.

[0095] Preferably, according to the power requirements of each module, the initial output voltage and current of the power module are set, and each module is started in turn according to a predetermined startup sequence. After each module is started, the PID control algorithm is used to monitor and adjust the power output in real time to ensure that each module obtains a stable power supply, continuously monitor the system operation status, and adjust the PID control parameters according to feedback. The output calculation formula of the PID controller is:

[0096]

[0097] Among them, u(t) is the controller output, e(t) is the current error, K p , K i , K d are the proportional, integral and derivative gains respectively.

[0098] Preferably, the output voltage of the power module is set to match the rated voltage of the device, that is, U set =U rated , set the output current limit of the power module higher than the rated current of the device to provide margin:

[0099] I set =I rated ×(1+margin factor)

[0100] The margin coefficient is between 10% and 20%.

[0101] Furthermore, assuming that there are three main modules, the power demand of module 1 is P1=50W, the power demand of module 2 is P2=80W, and the power demand of module 3 is P3=60W. According to these requirements, the initial output voltage and current of the power module are first set. Assuming that the initial output voltage of the power module is U0=12V, the initial value of the current output by the power supply can be calculated based on the power demand:

[0102] Current I1=P1 / U0=50W / 12V=4.17A, current I2=P2 / U0=80W / 12V=6.67A, current I3=P3 / U0=60W / 12V=5A. Start each module in turn according to the power requirements and startup sequence of the module. Assume the startup sequence is as follows:

[0103] Start module 1 (current 4.17A, power 50W), start module 2 (current 6.67A, power 80W),

[0104] Start module 3 (current 5A, power 60W);

[0105] During the startup process, the output current and voltage of the power module need to be adjusted in real time to meet the needs of each module. We use the PID control algorithm to ensure the stability of the power output and adjust the output voltage and current in real time as the load changes (such as module power fluctuations).

[0106] When starting module 1, the power module provides 4.17A current (set value is I1) according to the preset value. When starting module 2, the power module provides 6.67A current (set value is I2). When starting module 3, the power module provides 5A current (set value is I3).

[0107] After the module is started, the system monitors the current and voltage status of each module in real time, obtains the actual value through the sensor, and calculates the current error:

[0108] e(t)=I actual (t)-I set (t) Where I actual(t) is the actual current, I set(t) is the target current;

[0109] The PID controller calculates the control quantity u(t) based on the error e(t) and adjusts the current output by the power supply: the power supply output is adjusted until the actual current is close to the target current. The system continuously adjusts the output to ensure stable operation of the power supply.

[0110] Assume that after starting module 1, the actual current of the power supply is 0.5A higher than the target value, that is, the error is e(t) = 0.5A. The PID controller will calculate according to the formula:

[0111]

[0112] Assume that the controller gain is Kp=1, Ki=0.1, Kd=0.05;

[0113] The output of the PID controller is:

[0114] u(t)=1·0.5+0.1·0.5·t+0.05·0=0.5+0.05t

[0115] Over time, the controller gradually adjusts the current to stabilize it at the target value.

[0116] Furthermore, assuming that the rated voltage of the equipment is U rated =12V, therefore, the output voltage U set is set to match the rated voltage of the device, U set =U rated =12V;

[0117] Assume that the rated current of the device is I rated=2A, according to the current margin factor, the output current of the power module can be set. For example, if the margin factor is selected as 15%:

[0118] I set =I rated ×(1+Margin Factor)

[0119] Among them, the margin factor is selected as 15%:

[0120] I set =2A×(1+0.15)=2A×1.15=2.3A

[0121] Therefore, the output current of the power module is set to I set =2.3A, which means a 15% margin is added to the rated current of the equipment.

[0122] Combined with the above settings, the initial output parameters of the power module are voltage Uset = 12V, current Iset = 2.3A,

[0123] After the power module is started, the output voltage is first set to the rated voltage U set =12V. Then, set the output current to I set = 2.3A, providing 15% margin for the device. The output current and voltage of the power module are monitored in real time through the current sensor and voltage sensor. If the power required by the device changes (for example, the load increases or decreases), the power module will adjust the output current in real time to ensure that it is always maintained at I set =2.3A. Assume that the equipment load changes and the current demand changes from I rated =2A increases to I rated =2.5A, the system can still adapt by adjusting the current output by the power module. At this time, the power module will make corresponding current output adjustments according to the new requirements to ensure that the power current is always maintained within the maximum carrying capacity of the power module.

[0124] If the current or voltage fluctuates greatly, or if the current fails to stabilize near the set value in time due to instantaneous load changes, the PID control algorithm can be used to adjust the output to ensure stable power supply. The PID controller calculates the error in real time and adjusts the output current to eliminate steady-state errors or oscillations.

[0125] In the description of the present invention, it should be noted that the terms “first”, “second” and “third” are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0126] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0127] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0128] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0129] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0130] Finally, it should be noted that the above-described embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

[0131] In addition, although the operations of the method of the present invention are described in a specific order in the drawings, this does not require or imply that the operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

Claims

1. A medical waste intelligent sorting, disinfection and packaging platform, characterized in that: include: Machine vision module, used to install photosensitive sensors at the garbage disposal port to collect and identify garbage images; The IoT control module is used to monitor the status of the trash can in real time by connecting sensors; A sorting module is used to control a robotic arm or other actuators to sort different types of garbage to corresponding collection and storage modules according to the recognition results of the machine vision module; The garbage collection and storage module is used to calculate the optimal movement path of the robot arm using the path planning algorithm, transport the garbage to the corresponding garbage bin, and use the loading optimization algorithm to allocate the position of the garbage in the garbage bin; The control power supply module is used to supply power in sequence according to the startup sequence and power requirements of each module, and use the PID control algorithm to adjust the current and voltage in real time.

2. The medical waste intelligent sorting, disinfection and packaging platform according to claim 1, characterized in that: The photosensitive sensor is installed at the garbage throwing port to collect and identify garbage images, including: When the throwing door is opened, the light becomes stronger and the camera is prohibited from taking pictures; when the throwing door is closed, the light becomes darker and the camera is triggered to take pictures.

3. The intelligent medical waste sorting, disinfection and packaging platform according to claim 1, characterized in that: The photosensitive sensor is installed at the garbage throwing port to collect and identify garbage images, and also includes: Use the YOLOv5 algorithm to process the collected images, identify the types of garbage, perform data enhancement on the collected images, and normalize the image pixel values. The YOLOv5 algorithm formula is as follows: Positioning loss: Among them, S c is the minimum enclosed area of ​​the predicted box and the true box, S u is the area of ​​the union of the two; Confidence loss: Loss conf =-[y·log(p)+(1-y)·log(1-p)] Among them, y is the true label and p is the confidence of the prediction; Classification loss: Among them, C is the number of categories, y c is the one-hot encoding of the true category, p c is the predicted class probability.

4. The medical waste intelligent sorting, disinfection and packaging platform according to claim 1, characterized in that: The real-time monitoring of the status of the trash can by connecting the sensor includes: When the trash can is full, the room number and the category of the full trash classification bin will be sent to the manager's mobile APP; when the trash can is damaged, the room number and damage information will be sent to the manager's mobile APP to remind that repairs are needed.

5. The medical waste intelligent sorting, disinfection and packaging platform according to claim 1, characterized in that: The real-time monitoring of the status of the trash can by connecting the sensor also includes: The ultrasonic sensor measures the distance d from the sensor to the surface of the garbage. If the total height of the garbage can is H, the filling height h of the garbage is: h=Hd Set a full load threshold height h threshold When the measured filling height h is greater than or equal to the threshold, the trash can is determined to be full.

6. The medical waste intelligent sorting, disinfection and packaging platform according to claim 1, characterized in that: According to the recognition result of the machine vision module, the robot arm or other execution device is controlled to sort different types of garbage to corresponding collection and storage modules, including: The visual algorithm is used to determine the position coordinates (x, y) of the garbage on the conveyor belt. According to the location of the garbage and the location of the target collection and storage module, the movement path of the robotic arm is planned, and the robotic arm is controlled to move along the planned path to grab the garbage and place it in the corresponding collection and storage module.

7. The medical waste intelligent sorting, disinfection and packaging platform according to claim 1, characterized in that: The method of calculating the optimal moving path of the robot arm by using a path planning algorithm to transport the garbage to the corresponding garbage bin includes: Model the workspace of the robot arm, determine the location and shape of obstacles, and apply A * The algorithm searches for a collision-free path in the modeled space, optimizes the initial path, and converts the optimized path into the joint space trajectory of the robot arm for execution by the controller. * The algorithm formula is as follows: f(n)=g(n)+h(n) Among them, f(n) is the comprehensive cost of node n, g(n) is the actual cost from the starting point to node n, and h(n) is the heuristic estimated cost from node n to the goal.

8. The medical waste intelligent sorting, disinfection and packaging platform according to claim 1, characterized in that: The method of using a loading optimization algorithm to allocate the position of garbage in the garbage bin includes: Construct a mathematical model to maximize the utilization of the trash can, expressed as: Where n is the total number of garbage items, m is the total number of garbage bins, V i is the volume of the ith garbage item, C j is the capacity of the jth trash can, x ij Whether the i-th garbage item is put into the j-th garbage bin; Each trash item can only be put into one trash can: The total amount of garbage in each trash can cannot exceed its capacity:

9. The medical waste intelligent sorting, disinfection and packaging platform according to claim 1, characterized in that: The method supplies power in sequence according to the startup sequence and power requirements of each module, and uses a PID control algorithm to adjust the current and voltage in real time, including: According to the power requirements of each module, the initial output voltage and current of the power module are set, and each module is started in turn according to the predetermined startup sequence. After each module is started, the PID control algorithm is used to monitor and adjust the power output in real time to ensure that each module obtains a stable power supply. The system operation status is continuously monitored, and the PID control parameters are adjusted according to the feedback. The output calculation formula of the PID controller is: Among them, u(t) is the controller output, e(t) is the current error, K p , K i , K d are the proportional, integral and derivative gains respectively.

10. The medical waste intelligent sorting, disinfection and packaging platform according to claim 9, characterized in that: The initial output voltage and current of the power module are set according to the power requirements of each module, including: Set the output voltage of the power module to match the rated voltage of the device, that is, U set =U rated , set the output current limit of the power module higher than the rated current of the device to provide margin: I set =I rated ×(1+margin factor) The margin coefficient is between 10% and 20%.

Images