Efficient assembly line packaging system based on Internet of Things

Abstract

The invention discloses an efficient assembly line packaging system based on the Internet of Things. According to the system, through cooperative work of the sensor module, the actuator module and the controller module, automatic identification, carrying and packaging of goods are achieved, manual intervention is greatly reduced, and the operation speed and efficiency of a production line are improved. The artificial intelligence and optimization module can analyze and process data in real time and make decisions quickly, so that the whole system can respond to changes of production requirements quickly. And the artificial intelligence and optimization module can make a more intelligent decision through deep learning and an optimization algorithm, so that the automation level of the system is improved. The model training module can continuously learn, and as time goes on, the system can better adapt to different production environments and requirements. The sorting optimization strategy sub-module can optimize the process according to the production data, reduces unnecessary steps, improves the overall efficiency, and provides powerful support for modern industrial production.

Description

Technical Field

[0001] The present invention belongs to the technical field of assembly line packaging, and in particular relates to a high-efficiency assembly line packaging system based on the Internet of Things. Background Art

[0002] Assembly line packaging is an efficient operation method in modern industrial production. It realizes the automation and continuity of packaging operations by breaking down the packaging process into multiple links and laying them out according to the order of product flow. Assembly line packaging mainly includes product preparation, packaging material supply, product filling, sealing, inspection and handling. Its purpose is to improve packaging efficiency, reduce labor costs, and ensure the safety and beauty of products during transportation and storage. Assembly line packaging is widely used in the production process of food, medicine, daily chemicals, electronics and other industries. With the advancement of science and technology, assembly line packaging equipment and technology are also constantly optimized and upgraded. In short, assembly line packaging plays an important role in modern industrial production.

[0003] However, traditional assembly line packaging systems often rely on manual operations, which are inefficient and prone to errors. At the same time, the system lacks intelligent analysis capabilities, cannot make quick decisions based on real-time data, and cannot optimize the production process, thus affecting the overall packaging efficiency. Summary of the invention

[0004] The purpose of the present invention is to provide an efficient assembly line packaging system based on the Internet of Things in order to solve the above-mentioned problems.

[0005] The technical solution adopted by the present invention is as follows: an efficient assembly line packaging system based on the Internet of Things, the system comprising: a sensor module, a packaging actuator module, a controller module, a communication module, a data processing and storage module, an artificial intelligence and optimization module and a signal processing module;

[0006] The artificial intelligence and optimization module is internally provided with a data processing module, a feature extraction module, a model training module, a sorting optimization strategy submodule and a result output submodule;

[0007] The sensor module is connected to the signal processing module: the raw data collected by the sensor module needs to be filtered, amplified, and converted by the signal processing module to obtain an accurate and stable signal;

[0008] The sensor module is connected to the controller module: the processed signal is sent to the controller module for further data analysis and instruction issuance;

[0009] The sensor module packaging actuator module is connected to the controller module: the controller module sends a control signal to the actuator module according to the processed data and the preset program to drive the actuator to perform a specific packaging operation;

[0010] The controller module receives signals from the sensor module, performs logical judgment and decision-making, and sends control instructions to the packaging actuator module;

[0011] The controller module is connected to the communication module: data is exchanged with other systems or cloud platforms through the communication module;

[0012] The controller module is connected to the data processing and storage module: the processed data is sent to the data processing and storage module for storage and analysis;

[0013] The communication module is connected to the controller module: responsible for sending the controller's instructions to the external system or receiving instructions from the external system;

[0014] The communication module is connected with the data processing and storage module to realize remote transmission and backup of data;

[0015] The data processing and storage module is connected to the controller module: receiving data from the controller, storing and pre-processing;

[0016] The data processing and storage module is connected to the artificial intelligence and optimization module to provide the artificial intelligence module with data required for training and reasoning;

[0017] The data processing and storage module is connected to the communication module to realize remote storage and access of data;

[0018] The artificial intelligence and optimization module is connected to the data processing and storage module: the processed and stored data are used for model training and optimization;

[0019] The artificial intelligence and optimization module is connected to the controller module: the optimized control strategy or decision is fed back to the controller to guide the actuator operation;

[0020] The signal processing module is connected to the sensor module to process the signal collected by the sensor to meet the system requirements.

[0021] In a preferred embodiment, the sensor module is provided with:

[0022] Cargo identification sensors: including barcode scanners and RFID readers, used to read information on cargo labels;

[0023] Position sensor: photoelectric sensor, proximity sensor, used to detect the position of goods on the assembly line;

[0024] Load cells, used to measure the weight of goods;

[0025] Includes encoder to monitor the conveyor belt's running speed;

[0026] The sensor module monitors various parameters of the goods in real time through physical contact or non-contact methods; when the goods pass through the sensor, the sensor converts the physical signal into an electrical signal, which is further processed by the signal processing module.

[0027] In a preferred embodiment, the package executor module includes:

[0028] Conveyor belt: used to transport goods to the packaging area;

[0029] Robotics: Collaborative robots or Delta robots for picking, carrying and placing goods;

[0030] Packaging equipment Sealing machines and heat shrink machines are used to package goods;

[0031] Sorting equipment: Slider sorter or conveyor chain sorter, used to sort the packaged goods to the designated area;

[0032] The actuator module receives instructions from the controller module and drives the corresponding mechanical components to complete the operation; when the goods arrive at the packaging position, the robot grabs the goods according to the preset program and places them on the packaging equipment for packaging.

[0033] In a preferred embodiment, the controller module is responsible for processing sensor data and controlling the actuator module;

[0034] The controller module receives the input signal from the sensor module, processes it according to the preset program logic, and then outputs a control signal to the actuator module; when the weight sensor detects that the weight of the cargo exceeds the preset range, the controller will send a signal to the robot to adjust the gripping force.

[0035] In a preferred embodiment, the communication module sends and receives data by wired or wireless means; uploads the data of the controller module to a cloud server via an Ethernet connection, or exchanges data with a mobile device via a Bluetooth connection;

[0036] The data processing unit of the data processing and storage module performs data cleaning and data fusion operations; the data storage unit of the data processing and storage module includes a local database and a cloud database; the data processing unit preprocesses the data collected by the sensor, including removing outliers and standardizing the data; the processed data is stored in the database to perform historical data analysis or provide training data for the artificial intelligence module.

[0037] In a preferred embodiment, the data processing module is responsible for cleaning the data, removing invalid or erroneous data, standardizing and normalizing the data, as well as possible feature fusion and data dimension reduction, in preparation for subsequent efficient pipeline packaging data feature extraction;

[0038] The feature extraction module converts the preprocessed pipeline packaging data into a form that can be used for machine learning models; including selecting and extracting the most informative features for intrusion detection tasks, which may include statistical information of CAN messages, pipeline packaging time series features, and pipeline packaging communication modes.

[0039] In a preferred embodiment, the model training module includes:

[0040] 1 Initialize model parameters: randomly initialize the weights and biases of the pipeline packaged data;

[0041] 2 Forward propagation: Input the characteristic parameters of the pipeline packaged data, calculate the activation values ​​of the hidden layer and the output layer, and the formula for forward propagation is:

[0042]

[0043] Among them, a j l is the activation value of the jth neuron in the llth layer, w ij l is the weight from the i-th neuron in the l-1th layer to the j-th neuron in the lth layer, b j l is the bias of the jth neuron in the lth layer, σ is the activation function, and nl-1 is the number of neurons in the l-1th layer;

[0044] 3. Calculate the loss function of the pipeline packaged data: compare the difference between the activation value of the output layer and the actual fault type; the formula for calculating the loss function is:

[0045]

[0046] Among them, L(y,y^) is the loss function, is the independent code of the actual fault type of the ith sample, is the activation value of the output layer of the i-th sample, mm is the number of samples, and nout is the number of neurons in the output layer;

[0047] 4 Back propagation: Calculate the gradient of the loss function of the pipeline packaged data to the weights and biases, and update the weights and biases. The formula for back propagation is:

[0048] in, is the loss function for weight w ij l The gradient of j l is the error of the jth neuron in the llth layer, a j l-1 is the activation value of the jth neuron in the l-1th layer.

[0049] In a preferred embodiment, when the sorting optimization strategy submodule is started, the optimization strategy submodule initializes the optimization algorithm according to preset parameters or historical data; these parameters may include learning rate, regularization coefficient, and number of iterations;

[0050] Data reception: The submodule receives input data from the data processing and storage module. This data is usually pre-processed and ready for model training or optimization.

[0051] Model training: The optimization strategy submodule uses a machine learning algorithm to train the model; during the training process, the optimization algorithm adjusts the weights and biases of the model to minimize the loss function;

[0052] Parameter adjustment:

[0053] Learning rate scheduling: Automatically adjust the learning rate based on the training progress or the performance of the validation set to prevent slow convergence or overfitting during training;

[0054] Regularization: Apply L1 or L2 regularization to reduce model complexity and prevent overfitting;

[0055] Dropout: Randomly discard some neurons in the network during training to enhance the generalization ability of the model;

[0056] Performance evaluation: After each iteration, the submodule will evaluate the performance of the model, usually using a validation set; if the performance does not improve or degrades, the submodule may adjust the optimization strategy;

[0057] Strategy update: Based on the evaluation results, the optimization strategy submodule updates the parameters of the optimization algorithm;

[0058] Output: When the model training reaches the preset number of iterations or performance standards, the optimization strategy submodule will output the final optimized model parameters for use by other parts of the artificial intelligence and optimization modules.

[0059] In a preferred embodiment, the operation method of the result output submodule is as follows:

[0060] Receive prediction results: The submodule receives the final prediction results from the artificial intelligence and optimization module. These results may be classification labels, regression values, or optimized packaging solutions.

[0061] Processing prediction results:

[0062] Confidence calculation: For classification problems, the softmax function is used to calculate the predicted probability of each category, that is, the confidence;

[0063] Result formatting: convert the prediction results into an easy-to-understand format and convert the classification labels into corresponding product names;

[0064] Result validation: Before output, the submodule may validate the results to ensure that they meet the business logic and system requirements;

[0065] Visualization: The results are visualized through the monitoring interface, including cargo type, packaging plan, and confidence information;

[0066] Data storage: The prediction results and related information are stored in the database of the data processing and storage module for historical record query and subsequent analysis;

[0067] Feedback mechanism: Based on the prediction results and the actual operation effects, the submodule may provide feedback to the artificial intelligence and optimization module to further adjust and optimize the model;

[0068] Output instructions: Finally, the submodule outputs the prediction results or optimization solutions to the controller module in the form of instructions, and the controller module controls the packaging executor module to perform specific packaging tasks accordingly.

[0069] In a preferred embodiment, the signal processing module first filters and amplifies the analog signal output by the sensor, and then converts the analog signal into a digital signal through an analog-to-digital converter (ADC) so that the controller module can perform further processing; the analog signal of the weighing sensor is converted into a digital signal to accurately measure the weight of the cargo.

[0070] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0071] 1. In the present invention, the automatic identification, handling and packaging of goods are realized through the coordinated work of the sensor module, the actuator module and the controller module, which greatly reduces manual intervention and improves the running speed and efficiency of the production line. The artificial intelligence and optimization module can analyze and process data in real time and make decisions quickly, so that the entire system can respond quickly to changes in production needs. The artificial intelligence and optimization module can make more intelligent decisions through deep learning and optimization algorithms, and improve the automation level of the system. The model training module can learn continuously, and the system can better adapt to different production environments and needs over time. The sorting optimization strategy submodule can optimize the process according to production data, reduce unnecessary steps, and improve overall efficiency. Through the analysis of data, the artificial intelligence and optimization module can predict potential equipment failures, perform maintenance in advance, and reduce downtime. The system can automatically adjust the packaging strategy according to different cargo characteristics and provide more personalized services. The contribution of the artificial intelligence and optimization module to the entire system is that it improves the intelligence level of the system and enhances the adaptive ability of the system, thereby playing a key role in improving production efficiency, reducing error rates, saving costs and improving product quality. By integrating artificial intelligence technology, the system can better adapt to complex and changeable production environments and provide strong support for modern industrial production.

[0072] 2. In the present invention, the automated packaging process reduces the reliance on manpower, especially in terms of high-intensity, repetitive labor, saving labor costs. By precisely controlling the packaging process, the risk of material waste and product damage is reduced, thereby reducing costs. Artificial intelligence and optimization modules ensure that the packaging quality of each package is consistent, improving the standardization of products. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] Figure 1 is the overall system block diagram of the present invention;

[0074] Figure 2 It is the artificial intelligence and optimization module in the present invention. DETAILED DESCRIPTION

[0075] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0076] Reference Figure 1-2 ,

[0077] Example:

[0078] An efficient assembly line packaging system based on the Internet of Things, the system includes: a sensor module, a packaging actuator module, a controller module, a communication module, a data processing and storage module, an artificial intelligence and optimization module and a signal processing module;

[0079] The artificial intelligence and optimization module is internally provided with a data processing module, a feature extraction module, a model training module, a sorting optimization strategy submodule and a result output submodule;

[0080] The sensor module is connected to the signal processing module: the raw data collected by the sensor module needs to be filtered, amplified, converted, etc. through the signal processing module to obtain accurate and stable signals.

[0081] The sensor module is connected to the controller module: the processed signal is sent to the controller module for further data analysis and instruction issuance.

[0082] The sensor module packaging actuator module is connected to the controller module: the controller module sends a control signal to the actuator module according to the processed data and the preset program to drive the actuator to perform specific packaging operations.

[0083] The controller module receives signals from the sensor module, performs logical judgment and decision-making, and sends control instructions to the packaged actuator module.

[0084] The controller module is connected to the communication module: data is exchanged with other systems or cloud platforms through the communication module.

[0085] The controller module is connected to the data processing and storage module: the processed data is sent to the data processing and storage module for storage and analysis.

[0086] The communication module is connected to the controller module: it is responsible for sending the controller's instructions to the external system or receiving instructions from the external system.

[0087] The communication module is connected with the data processing and storage module to realize the remote transmission and backup of data.

[0088] The data processing and storage module is connected to the controller module: it receives data from the controller and performs storage and pre-processing.

[0089] The data processing and storage module is connected to the artificial intelligence and optimization module: providing the artificial intelligence module with the data required for training and reasoning.

[0090] The data processing and storage module is connected to the communication module to realize remote storage and access of data.

[0091] The AI ​​and Optimization module is connected to the Data Processing and Storage module: the processed and stored data is used for model training and optimization.

[0092] The artificial intelligence and optimization module is connected to the controller module: the optimized control strategy or decision is fed back to the controller to guide the actuator operation.

[0093] The signal processing module is connected to the sensor module: the signal collected by the sensor is processed to meet the system requirements.

[0094] The internal configuration of the sensor module includes:

[0095] Cargo identification sensors: such as barcode scanners, RFID readers, etc., used to read information on cargo labels.

[0096] Position sensor: Photoelectric sensor, proximity sensor, used to detect the position of goods on the assembly line.

[0097] Load cells are used to measure the weight of goods.

[0098] Such as encoders, which are used to monitor the running speed of conveyor belts;

[0099] The sensor module monitors various parameters of the goods in real time through physical contact or non-contact methods. When the goods pass through the sensor, the sensor converts the physical signal into an electrical signal, which is further processed by the signal processing module. The barcode scanner emits a beam when the goods pass by, reads the barcode information and converts it into electronic data.

[0100] Packaged executor modules include:

[0101] Conveyor belt: used to transport goods to the packaging area.

[0102] Robotics: Collaborative robots or Delta robots for picking, carrying and placing goods.

[0103] Packaging equipment such as sealing machines and heat shrink machines are used to package goods.

[0104] Sorting equipment: Slider sorter or conveyor chain sorter, used to sort the packaged goods to the designated area;

[0105] The actuator module receives instructions from the controller module and drives the corresponding mechanical components to complete the operation. When the goods arrive at the packaging location, the robot grabs the goods according to the preset program and places them on the packaging equipment for packaging.

[0106] The controller module is responsible for processing sensor data and controlling the actuator modules;

[0107] The controller module receives the input signal from the sensor module, processes it according to the preset program logic, and then outputs the control signal to the actuator module. When the weight sensor detects that the weight of the cargo exceeds the preset range, the controller will send a signal to the robot to adjust the gripping force.

[0108] The communication module sends and receives data via wired or wireless means. The data of the controller module is uploaded to the cloud server via Ethernet connection, or data is exchanged with mobile devices via Bluetooth connection;

[0109] The data processing unit of the data processing and storage module: performs data cleaning, data fusion and other operations. The data storage unit of the data processing and storage module: includes a local database and a cloud database; the data processing unit pre-processes the data collected by the sensor, such as removing outliers, standardizing data, etc. The processed data is stored in the database for historical data analysis or to provide training data for the artificial intelligence module.

[0110] The data processing module is responsible for cleaning data, removing invalid or erroneous data, standardizing and normalizing data, as well as possible feature fusion and data dimension reduction, in preparation for subsequent efficient pipeline packaging data feature extraction;

[0111] The feature extraction module converts the preprocessed pipeline packaging data into a form that can be used for machine learning models; it includes selecting and extracting the most informative features for intrusion detection tasks, which may include statistical information of CAN messages, pipeline packaging time series features, and pipeline packaging communication modes.

[0112] The model training module includes the following steps in the process of using the training model:

[0113] 1 Initialize model parameters: randomly initialize the weights and biases of the pipeline packaged data;

[0114] 2 Forward propagation: Input the characteristic parameters of the pipeline packaged data, calculate the activation values ​​of the hidden layer and the output layer, and the formula for forward propagation is:

[0115] Among them, a j l is the activation value of the jth neuron in the llth layer, w ij l is the weight from the i-th neuron in the l-1th layer to the j-th neuron in the lth layer, b j l is the bias of the jth neuron in the llth layer, σ is the activation function, n l-1 is the number of neurons in the l-1th layer;

[0116] 3. Calculate the loss function of the pipeline packaged data: compare the difference between the activation value of the output layer and the actual fault type; the formula for calculating the loss function is:

[0117] Where L(y,y^) is the loss function, yj(i) is the independent encoding of the actual fault type of the i-th sample, y^ji is the activation value of the output layer of the i-th sample, mm is the number of samples, and nout is the number of neurons in the output layer;

[0118] 4 Back propagation: Calculate the gradient of the loss function of the pipeline packaged data to the weights and biases, and update the weights and biases. The formula for back propagation is:

[0119] in, is the loss function for weight w ij l The gradient of

[0120] δ j l is the error of the jth neuron in the llth layer, a j l-1 is the activation value of the jth neuron in the l-1th layer.

[0121] When the sorting optimization strategy submodule is started, the optimization strategy submodule will initialize the optimization algorithm according to preset parameters or historical data. These parameters may include learning rate, regularization coefficient, number of iterations, etc.

[0122] Data reception: The submodule receives input data from the data processing and storage module. This data is usually pre-processed and ready for model training or optimization.

[0123] Model training: The optimization strategy submodule uses a machine learning algorithm to train the model. During the training process, the optimization algorithm adjusts the weights and biases of the model to minimize the loss function.

[0124] Parameter adjustment:

[0125] Learning rate scheduling: Automatically adjust the learning rate based on the training progress or the performance of the validation set to prevent slow convergence or overfitting during training.

[0126] Regularization: Apply L1 or L2 regularization to reduce model complexity and prevent overfitting.

[0127] Dropout: Randomly discard some neurons in the network during training to enhance the generalization ability of the model.

[0128] Performance evaluation: After each iteration, the submodule evaluates the performance of the model, usually using a validation set. If the performance does not improve or degrades, the submodule may adjust the optimization strategy.

[0129] Strategy update: Based on the evaluation results, the optimization strategy submodule updates the parameters of the optimization algorithm, such as changing the learning rate, adjusting the regularization coefficient, etc.

[0130] Output: When the model training reaches the preset number of iterations or performance standards, the optimization strategy submodule will output the final optimized model parameters for use by other parts of the artificial intelligence and optimization modules.

[0131] The operation method flow of the result output submodule is as follows:

[0132] Receive prediction results: The submodule receives the final prediction results from the artificial intelligence and optimization module, which may be classification labels, regression values, or optimized packaging solutions.

[0133] Processing prediction results:

[0134] Confidence calculation: For classification problems, the softmax function is used to calculate the predicted probability of each category, that is, the confidence.

[0135] Result formatting: Convert the prediction results into an easy-to-understand format, such as converting classification labels into corresponding product names.

[0136] Result validation: Before output, submodules may validate the results to ensure that they comply with business logic and system requirements.

[0137] Visualization: The results are visualized through the monitoring interface, including information such as cargo type, packaging plan, and confidence level.

[0138] Data storage: The prediction results and related information are stored in the database of the data processing and storage module for historical record query and subsequent analysis.

[0139] Feedback mechanism: Based on the prediction results and the effects of actual operations, the sub-module may provide feedback to the artificial intelligence and optimization module to further adjust and optimize the model.

[0140] Output instructions: Finally, the submodule outputs the prediction results or optimization solutions to the controller module in the form of instructions, and the controller module controls the packaging executor module to perform specific packaging tasks accordingly.

[0141] The signal processing module first filters and amplifies the analog signal output by the sensor, and then converts the analog signal into a digital signal through an analog-to-digital converter (ADC) for further processing by the controller module. The analog signal of the weighing sensor is converted into a digital signal to accurately measure the weight of the goods.

[0142] In the present invention, the automatic identification, handling and packaging of goods are realized through the coordinated work of the sensor module, the actuator module and the controller module, which greatly reduces manual intervention and improves the running speed and efficiency of the production line. The artificial intelligence and optimization module can analyze and process data in real time and make decisions quickly, so that the entire system can respond quickly to changes in production needs. The artificial intelligence and optimization module can make more intelligent decisions through deep learning and optimization algorithms, and improve the automation level of the system. The model training module can learn continuously, and the system can better adapt to different production environments and needs over time. The sorting optimization strategy submodule can optimize the process according to production data, reduce unnecessary steps, and improve overall efficiency. Through the analysis of data, the artificial intelligence and optimization module can predict potential equipment failures, perform maintenance in advance, and reduce downtime. The system can automatically adjust the packaging strategy according to different cargo characteristics and provide more personalized services. The contribution of the artificial intelligence and optimization module to the entire system is that it improves the intelligence level of the system and enhances the adaptive ability of the system, thereby playing a key role in improving production efficiency, reducing error rates, saving costs and improving product quality. By integrating artificial intelligence technology, the system can better adapt to complex and changeable production environments and provide strong support for modern industrial production.

[0143] In the present invention, the automated packaging process reduces the reliance on manpower, especially in terms of high-intensity, repetitive labor, saving labor costs. By precisely controlling the packaging process, the risk of material waste and product damage is reduced, thereby reducing costs. Artificial intelligence and optimization modules ensure that the packaging quality of each package is consistent, improving the standardization of products.

[0144] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the term "comprises" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0145] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An efficient assembly line packaging system based on the Internet of Things, characterized by: The system includes: a sensor module, a packaged actuator module, a controller module, a communication module, a data processing and storage module, an artificial intelligence and optimization module, and a signal processing module; The artificial intelligence and optimization module is internally provided with a data processing module, a feature extraction module, a model training module, a sorting optimization strategy submodule and a result output submodule; The sensor module is connected to the signal processing module: the raw data collected by the sensor module needs to be filtered, amplified, and converted by the signal processing module to obtain an accurate and stable signal; The sensor module is connected to the controller module: the processed signal is sent to the controller module for further data analysis and instruction issuance; The sensor module packaging actuator module is connected to the controller module: the controller module sends a control signal to the actuator module according to the processed data and the preset program to drive the actuator to perform a specific packaging operation; The controller module receives signals from the sensor module, performs logical judgment and decision-making, and sends control instructions to the packaging actuator module; The controller module is connected to the communication module: data is exchanged with other systems or cloud platforms through the communication module; The controller module is connected to the data processing and storage module: the processed data is sent to the data processing and storage module for storage and analysis; The communication module is connected to the controller module: responsible for sending the controller's instructions to the external system or receiving instructions from the external system; The communication module is connected with the data processing and storage module to realize remote transmission and backup of data; The data processing and storage module is connected to the controller module: receiving data from the controller, storing and pre-processing; The data processing and storage module is connected to the artificial intelligence and optimization module to provide the artificial intelligence module with data required for training and reasoning; The data processing and storage module is connected to the communication module to realize remote storage and access of data; The artificial intelligence and optimization module is connected to the data processing and storage module: the processed and stored data are used for model training and optimization; The artificial intelligence and optimization module is connected to the controller module: the optimized control strategy or decision is fed back to the controller to guide the actuator operation; The signal processing module is connected to the sensor module to process the signal collected by the sensor to meet the system requirements.

2. The efficient assembly line packaging system based on the Internet of Things as claimed in claim 1, characterized in that: The sensor module is internally provided with: Cargo identification sensors: including barcode scanners and RFID readers, used to read information on cargo labels; Position sensor: photoelectric sensor, proximity sensor, used to detect the position of goods on the assembly line; Load cells, used to measure the weight of goods; Includes encoder to monitor the conveyor belt's running speed; The sensor module monitors various parameters of the goods in real time through physical contact or non-contact methods; when the goods pass through the sensor, the sensor converts the physical signal into an electrical signal, which is further processed by the signal processing module.

3. The efficient assembly line packaging system based on the Internet of Things as claimed in claim 1, characterized in that: The package executor module includes: Conveyor belt: used to transport goods to the packaging area; Robotics: Collaborative robots or Delta robots for picking, carrying and placing goods; Packaging equipment Sealing machines and heat shrink machines are used to package goods; Sorting equipment: Slider sorter or conveyor chain sorter, used to sort the packaged goods to the designated area; The actuator module receives instructions from the controller module and drives the corresponding mechanical components to complete the operation; when the goods arrive at the packaging position, the robot grabs the goods according to the preset program and places them on the packaging equipment for packaging.

4. The efficient assembly line packaging system based on the Internet of Things as claimed in claim 1, characterized in that: The controller module is responsible for processing sensor data and controlling the actuator module; The controller module receives the input signal from the sensor module, processes it according to the preset program logic, and then outputs a control signal to the actuator module; when the weight sensor detects that the weight of the cargo exceeds the preset range, the controller will send a signal to the robot to adjust the gripping force.

5. The efficient assembly line packaging system based on the Internet of Things as claimed in claim 1, characterized in that: The communication module sends and receives data by wired or wireless means; uploads the data of the controller module to the cloud server via Ethernet connection, or exchanges data with mobile devices via Bluetooth connection; The data processing unit of the data processing and storage module performs data cleaning and data fusion operations; the data storage unit of the data processing and storage module includes a local database and a cloud database; the data processing unit preprocesses the data collected by the sensor, including removing outliers and standardizing data; The processed data is stored in a database for historical data analysis or to provide training data for artificial intelligence modules.

6. The efficient assembly line packaging system based on the Internet of Things as claimed in claim 1, characterized in that: The data processing module is responsible for cleaning data, removing invalid or erroneous data, standardizing and normalizing data, as well as possible feature fusion and data dimension reduction, in preparation for subsequent efficient pipeline packaging data feature extraction; The feature extraction module converts the preprocessed pipeline packaged data into a form that can be used for a machine learning model; It includes selecting and extracting the most informative features for intrusion detection tasks, which may include statistical information of CAN messages, pipeline packaging time series characteristics, and pipeline packaging communication patterns.

7. The efficient assembly line packaging system based on the Internet of Things as claimed in claim 1, characterized in that: The model training module includes the following steps in the process of using the training model: 1 Initialize model parameters: randomly initialize the weights and biases of the pipeline packaged data; 2 Forward propagation: Input the characteristic parameters of the pipeline packaged data, calculate the activation values ​​of the hidden layer and the output layer, and the formula for forward propagation is: Among them, a j l is the activation value of the jth neuron in the llth layer, w ij l is the weight from the i-th neuron in the l-1th layer to the j-th neuron in the lth layer, b j l is the bias of the jth neuron in the llth layer, σ is the activation function, n l-1 is the number of neurons in the l-1th layer; 3. Calculate the loss function of the pipeline packaged data: compare the difference between the activation value of the output layer and the actual fault type; the formula for calculating the loss function is: Where L(y,y^) is the loss function, yj(i) is the independent encoding of the actual fault type of the i-th sample, y^ji is the activation value of the output layer of the i-th sample, mm is the number of samples, and nout is the number of neurons in the output layer; 4 Back propagation: Calculate the gradient of the loss function of the pipeline packaged data to the weights and biases, and update the weights and biases. The formula for back propagation is: in, is the loss function for weight w ij l The gradient of δ j l is the error of the jth neuron in the llth layer, a j l-1 is the activation value of the jth neuron in the l-1th layer.

8. The efficient assembly line packaging system based on the Internet of Things as claimed in claim 1, characterized in that: When the sorting optimization strategy submodule is started, the optimization strategy submodule will initialize the optimization algorithm according to preset parameters or historical data; these parameters may include learning rate, regularization coefficient, and number of iterations; Data reception: The submodule receives input data from the data processing and storage module. This data is usually pre-processed and ready for model training or optimization. Model training: The optimization strategy submodule uses a machine learning algorithm to train the model; during the training process, the optimization algorithm adjusts the weights and biases of the model to minimize the loss function; Parameter adjustment: Learning rate scheduling: Automatically adjust the learning rate based on the training progress or the performance of the validation set to prevent slow convergence or overfitting during training; Regularization: Apply L1 or L2 regularization to reduce model complexity and prevent overfitting; Dropout: Randomly discard some neurons in the network during training to enhance the generalization ability of the model; Performance evaluation: After each iteration, the submodule evaluates the performance of the model, usually using a validation set; If the performance does not improve or degrades, the submodule may adjust the optimization strategy; Strategy update: Based on the evaluation results, the optimization strategy submodule updates the parameters of the optimization algorithm; Output: When the model training reaches the preset number of iterations or performance standards, the optimization strategy submodule will output the final optimized model parameters for use by other parts of the artificial intelligence and optimization modules.

9. The efficient assembly line packaging system based on the Internet of Things as claimed in claim 1, characterized in that: The operation method flow of the result output submodule is as follows: Receive prediction results: The submodule receives the final prediction results from the artificial intelligence and optimization module. These results may be classification labels, regression values, or optimized packaging solutions. Processing prediction results: Confidence calculation: For classification problems, the softmax function is used to calculate the predicted probability of each category, that is, the confidence; Result formatting: convert the prediction results into an easy-to-understand format and convert the classification labels into corresponding product names; Result validation: Before output, the submodule may validate the results to ensure that they meet the business logic and system requirements; Visualization: The results are visualized through the monitoring interface, including cargo type, packaging plan, and confidence information; Data storage: The prediction results and related information are stored in the database of the data processing and storage module for historical record query and subsequent analysis; Feedback mechanism: Based on the prediction results and the actual operation effects, the submodule may provide feedback to the artificial intelligence and optimization module to further adjust and optimize the model; Output instructions: Finally, the submodule outputs the prediction results or optimization solutions to the controller module in the form of instructions, and the controller module controls the packaging executor module to perform specific packaging tasks accordingly.

10. The efficient assembly line packaging system based on the Internet of Things as claimed in claim 1, characterized in that: The signal processing module first filters and amplifies the analog signal output by the sensor, and then converts the analog signal into a digital signal through an analog-to-digital converter (ADC) so that the controller module can further process it; the analog signal of the weighing sensor is converted into a digital signal to accurately measure the weight of the goods.

Images