Logistics conveying line integrated control system based on modularized intelligent driving card

Abstract

The invention belongs to the technical field of logistics automation, and discloses a logistics conveying line integrated control system based on a modular intelligent driving card. Comprising a modularized intelligent driving card, a conveying line section, a main control unit and a service host. According to the system, operation parameters and state data of an equipment object are collected through a modular intelligent driving card, and operation feature vectors are generated; performing operation state classification by using a dynamic clustering algorithm; generating running trend prediction data through the prediction model in combination with high-level service logic of the service host; generating and issuing an optimization control instruction based on the prediction data; a dynamic handover strategy is generated through the network communication module, and product handover between adjacent conveying line sections is coordinated; and dynamically binding the product tracking data with the physical product position through a virtual mapping mechanism. According to the invention, the efficient integrated control of the logistics conveying line is realized, the response speed and the processing capability of the system are improved, the energy utilization is optimized, and the product tracking precision is enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of logistics automation, and more particularly to a logistics conveyor line integrated control system based on modular intelligent drive cards. Background Art

[0002] With the rapid development of e-commerce and intelligent manufacturing, modern logistics systems are facing unprecedented challenges and opportunities. As a core component of logistics conveyor lines, the advancement of their control technology directly impacts the efficiency and reliability of the entire logistics system. In recent years, logistics conveyor line control systems have evolved from traditional mechanical control to electrical automation control and then to information-based intelligent control.

[0003] Traditional logistics conveyor line control systems primarily utilize a PLC (Programmable Logic Controller)-based control architecture, connecting control units in various sections via a fieldbus to achieve basic conveying functions. This control approach works well in simple logistics scenarios, but its limitations become increasingly apparent as logistics scale expands and processing requirements become more complex.

[0004] Traditional systems generally employ a decentralized architecture, with independent control units and a lack of a unified integration framework. This results in poor coordination between system components and an inability to achieve globally optimized control. In high-speed logistics distribution centers, large quantities of items must be sorted and delivered within a short period of time. However, existing systems suffer from lengthy data transmission links and significant delays in issuing control commands, failing to meet millisecond-level response requirements, leading to item backlogs and delivery delays. The product handover process between adjacent conveyor line sections lacks an intelligent scheduling mechanism, relying solely on a simple fixed priority strategy that is unable to cope with dynamically changing handover demands. This often leads to problems such as congestion at handover points and product damage caused by collisions. Furthermore, traditional systems employ a fixed power allocation scheme, unable to dynamically adjust power supply strategies based on conveyor line loads. This leads to power shortages during peak periods and energy waste during off-peak periods, significantly increasing operating costs. The system lacks the ability to predict and analyze equipment operating trends, effectively responding to existing failures and failing to provide early warnings and preventative measures, resulting in frequent unplanned equipment downtime. Traditional product tracking systems rely on discrete detection points, making it impossible to continuously monitor the position of items on conveyor lines. As logistics density increases, problems such as item identity confusion and tracking loss can easily occur, seriously impacting the accuracy and reliability of logistics management. Furthermore, these systems generally lack environmental adaptability and are unable to automatically adjust control parameters based on factors such as temperature and humidity fluctuations and equipment aging. This results in unstable performance under varying operating conditions and high maintenance costs.

[0005] In view of this, the present invention proposes a logistics conveyor line integrated control system based on modular intelligent drive cards to solve the above problems. Summary of the Invention

[0006] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned purpose, the present invention provides the following technical solution: a logistics conveyor line integrated control system based on a modular intelligent drive card, comprising:

[0007] At least one modular intelligent drive card, at least one conveyor line section, at least one main control unit and at least one service host;

[0008] The modular intelligent driver card includes a power management module and a network communication module. The power management module is used to provide power supply, perform dynamic power distribution and collect operating status data. The network communication module is used to realize multi-protocol data communication and real-time handover control.

[0009] The conveyor line section includes at least one equipment object, and the equipment object includes a drive motor, a sensor, and an actuator;

[0010] The main control unit is used to communicate with the modular intelligent drive card and perform real-time control of the conveyor line section through a standardized communication interface;

[0011] The business host is used to execute high-level business logic, including logistics task scheduling, data storage and product tracking;

[0012] The system implements integrated control of the logistics conveyor line through the following steps:

[0013] Obtaining the operating parameters and status data of each equipment object in the conveyor line section, and generating a corresponding operating feature vector through the modular intelligent drive card;

[0014] Based on the operation feature vector, the operation status of the conveyor line section is classified by a dynamic clustering algorithm to generate a classified operation status set;

[0015] Generate operation trend prediction data of the conveyor line section through a prediction model according to the operation status set and the high-level business logic of the business host;

[0016] Based on the operation trend prediction data, generating and issuing optimization control instructions through the standardized communication interface to adjust the operation parameters of the device object;

[0017] generating a dynamic handover strategy through the network communication module according to product handover requirements between the conveyor line sections, and coordinating product handover between adjacent conveyor line sections based on the dynamic handover strategy;

[0018] Product tracking data is generated according to the high-level business logic of the business host, and the product tracking data is dynamically bound to the physical product location in the conveyor line section through a virtual mapping mechanism.

[0019] The technical effects and advantages of the integrated control system for logistics conveyor lines based on modular intelligent drive cards of the present invention are as follows:

[0020] This invention improves logistics processing efficiency, making the sorting and delivery process smoother and more efficient, effectively alleviating peak logistics pressures. In practical applications, item transport speeds have been significantly increased, waiting times have been significantly shortened, and logistics congestion has been effectively controlled. The system optimizes the item handover process between adjacent sections, making the handover process smoother, reducing item damage and delivery delays caused by poor handovers, and enhancing the safety and reliability of the logistics system. In terms of energy utilization, the system achieves optimal resource allocation, significantly reducing energy consumption while ensuring normal operation, creating considerable economic benefits for enterprises. Through advanced fault prediction capabilities, the system significantly reduces unplanned equipment downtime, extends equipment life, and reduces maintenance costs. High-precision item tracking ensures that each item is precisely located during transportation, effectively eliminating the risk of item loss and misdelivery, and improving customer satisfaction. The system's adaptive nature enables stable and efficient operation in diverse environmental conditions, eliminating the need for frequent manual intervention and reducing the workload of operations and maintenance personnel. Furthermore, the system's flexible scalability enables logistics companies to easily upgrade according to business development needs, avoiding the enormous costs and risks associated with a complete system replacement. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 Schematic diagram of the integrated control system for logistics conveyor lines based on modular intelligent drive cards of the present invention;

[0022] Figure 2 This is a schematic diagram of the integrated control logic of the logistics conveyor line implemented by the present invention. DETAILED DESCRIPTION

[0023] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0024] This application provides an integrated control system for a logistics conveyor line based on a modular intelligent driver card. The execution entities of the integrated control system for a logistics conveyor line based on a modular intelligent driver card include, but are not limited to, the following: a logistics control center, a conveyor line management system, an intelligent warehousing system, an equipment monitoring platform, an operation optimization system, etc., which can be regarded as general computing nodes of this application. The data processing platform includes, but is not limited to, at least one of an equipment status monitoring system, an operation characteristic analysis system, and a handover control system.

[0025] See also Figure 1 The present invention provides a logistics conveyor line integrated control system based on a modular intelligent driver card, comprising at least one modular intelligent driver card, at least one conveyor line section, at least one main control unit and at least one business host. The modular intelligent driver card comprises a power management module and a network communication module. The power management module is used to provide power supply, perform dynamic power distribution and collect operating status data. The network communication module is used to implement multi-protocol data communication and real-time handover control. The conveyor line section comprises at least one device object, which comprises a drive motor, a sensor and an actuator. The main control unit is used to communicate with the modular intelligent driver card and to perform real-time control of the conveyor line section through a standardized communication interface. The business host is used to execute high-level business logic, including logistics task scheduling, data storage and product tracking.

[0026] The present invention realizes intelligent control of logistics conveyor lines through modular design, constructs equipment object operation feature vectors to provide a data basis for subsequent analysis, and performs dynamic clustering and state classification based on the operation feature vectors to make the control adaptive. The dynamic clustering algorithm can identify changes in operation modes under different working conditions. Trend prediction combined with the high-level business logic of the business host improves the foresight of control, optimizes the generation and issuance of control instructions to ensure the real-time response capability of the system, and realizes dynamic handover between adjacent conveyor line sections through the network communication module to solve the coordination problem of the handover link in the traditional conveying system. The dynamic binding of product tracking data and physical product location ensures the visualization and traceability of the logistics process. The virtual mapping mechanism enhances the accuracy and real-time performance of product positioning.

[0027] See also Figure 2 , which is a schematic diagram of the integrated control logic of the logistics conveyor line implemented in this application. In the embodiment of the present invention, the system implements the integrated control of the logistics conveyor line through the following steps:

[0028] Step 1: Obtain the operating parameters and status data of each equipment object in the conveyor line section, and generate the corresponding operating feature vector through the modular intelligent driver card;

[0029] Step 2: Based on the operation feature vector, the operation status of the conveyor line section is classified by a dynamic clustering algorithm to generate a classified operation status set;

[0030] Step 3: Generate operation trend prediction data of the conveyor line section through the prediction model based on the operation status set and the high-level business logic of the business host;

[0031] Step 4: Based on the operation trend prediction data, generate and issue optimization control instructions through the standardized communication interface to adjust the operation parameters of the equipment object;

[0032] Step 5: Generate a dynamic handover strategy based on the product handover requirements between conveyor line sections through the network communication module, and coordinate the product handover between adjacent conveyor line sections based on the dynamic handover strategy;

[0033] Step 6: Generate product tracking data based on the high-level business logic of the business host, and dynamically bind the product tracking data to the physical product location in the conveyor line section through a virtual mapping mechanism.

[0034] In this embodiment, the operating parameters of each device object are first obtained from the conveyor line section, including parameters such as the speed, current, and temperature of the drive motor, data such as the position detection value, pressure value, and photoelectric status of the sensor, as well as information such as the action status, response time, and torque output of the actuator, to form a device operating parameter set. At the same time, the status data of the device object is collected, including information such as the working status (normal / abnormal / fault), cumulative operating time, and maintenance records, to form a device status data set. The collected operating parameters and status data are preliminarily processed by the data processing unit built into the modular intelligent driver card, including data normalization, outlier filtering, signal smoothing, and other operations to ensure data quality. The processed data is feature extracted according to a predefined feature extraction algorithm (such as time domain statistical features, frequency domain transformation features, time-frequency joint analysis features, etc.) to generate a feature vector that can characterize the operating status of the device. The feature vector contains multiple dimensions, such as stability index, energy efficiency index, responsiveness index, synchronization index, etc., which comprehensively characterize the operating characteristics of the device and form an operating feature vector.

[0035] Based on the operational feature vectors, a dynamic clustering algorithm is then used to classify the operating status of the conveyor line sections. Unlike traditional static clustering methods, this dynamic clustering algorithm can adaptively adjust cluster centers and category boundaries to accommodate dynamic changes in the conveyor line's operating status. The algorithm first initializes cluster centers. Initial cluster centers can be set based on historical data or expert experience, such as typical categories such as normal operating status, minor abnormality, and severe abnormality. The similarity (e.g., Euclidean distance, Mahalanobis distance, cosine similarity, etc.) between the operational feature vectors within each time window and each cluster center is calculated, and the feature vector is assigned to the most similar cluster category. As new data is generated, the location of the cluster centers and the number of clusters are dynamically adjusted, ensuring that the clustering results reflect real-time changes in the conveyor line's operating status. The algorithm employs an adaptive threshold mechanism. When the sample variability within a category exceeds a threshold, the category is split to form a new category. When the distance between two category centers is less than a threshold, the categories are merged. Through this dynamic adjustment mechanism, the operating status of the conveyor line can be accurately classified to form a classified operating status set, such as normal operation, low energy efficiency, fault precursor, equipment aging and other status categories.

[0036] Then, based on the classified operating status set and the high-level business logic provided by the business host (such as logistics task planning, product priority, production capacity requirements, etc.), the prediction model generates the operation trend prediction data of the conveyor line section. The prediction model adopts a deep learning architecture, such as the long short-term memory network (LSTM), the gated recurrent unit (GRU) or the temporal convolutional network (TCN), which can capture the temporal dependency of the conveyor line operation data. During the model training process, historical operation data and current business needs are taken into account at the same time to achieve modeling of multiple prediction targets, such as equipment status trend prediction (predicting when the equipment may fail), efficiency trend prediction (predicting changes in transportation efficiency in future time periods), energy consumption trend prediction (predicting fluctuations in energy consumption), etc. The prediction results are given in the form of a time series, including the predicted value, confidence interval and multiple possible development paths, forming operation trend prediction data, which provides a scientific basis for subsequent control optimization.

[0037] Based on operational trend forecast data, optimized control instructions are generated and issued through standardized communication interfaces. The generation process of optimized control instructions utilizes advanced control methods such as model predictive control (MPC) or reinforcement learning (RL) to optimize control objectives (such as maximizing energy efficiency, minimizing product damage, and optimizing handover time) while satisfying system constraints. Control instructions are issued to equipment objects in each conveyor line section through standardized communication interfaces, enabling precise adjustment of operating parameters such as drive motor speed, actuator action timing, and sensor sensitivity. The execution effect of control instructions is monitored in real time through a feedback mechanism, forming a closed-loop control system to ensure stable and efficient system operation.

[0038] According to the product handover requirements between the conveying line sections (such as product arrival time, product characteristics, handover priority, etc.), a dynamic handover strategy is generated through the network communication module. The handover strategy generation process considers multiple factors, such as the output capacity of the upstream conveying line, the receiving capacity of the downstream conveying line, product backlog status, physical limitations of the handover point, etc. Through game theory or multi-agent collaborative decision-making methods, optimal handover parameters such as handover time window, handover speed matching, product interval control, etc. are calculated to form a dynamic handover strategy. Based on the generated handover strategy, the product handover process between adjacent conveying line sections is coordinated to achieve seamless handover and smooth transmission, avoiding congestion, collision or product damage, etc.

[0039] Finally, according to the high-level business logic of the business host (such as order information, product attributes, delivery requirements, etc.), product tracking data is generated, including product unique identifier, current location, historical trajectory, estimated arrival time, etc. Through a virtual mapping mechanism, product tracking data is dynamically bound to the physical product location in the conveying line section. The virtual mapping mechanism is based on a sensor network and a location calculation algorithm to update the accurate location of the product on the conveying line in real time, and synchronizes with the tracking database to ensure the accuracy and real-time nature of the tracking data. Through this binding mechanism, visual monitoring and accurate tracking of the entire product are achieved, improving the transparency and management efficiency of the logistics system.

[0040] In the embodiment of the present application, the standardized communication interface includes a vertical interface and a horizontal interface, wherein:

[0041] The vertical interface includes a control interface and a reporting interface, the control interface is used to issue optimization control instructions from the master control unit to the modular intelligent drive card, and the reporting interface is used to upload running state data and running feature vectors from the modular intelligent drive card to the master control unit;

[0042] The horizontal interface includes a dynamic handover interface, the dynamic handover interface is used to define a product handover protocol between adjacent conveying line sections, the product handover protocol includes a dynamic request signal, a dynamic response signal, a handover priority signal and an extended auxiliary signal;

[0043] The data format of the dynamic handover interface adopts a variable length data frame structure, which is used to carry product handover information, product tracking data and priority information of the dynamic handover strategy.

[0044] In this embodiment, the standardized communication interface adopts a hierarchical design, dividing the communication functions into two categories: vertical interface and horizontal interface. The vertical interface is responsible for data exchange between the upper and lower levels, including two sub-interfaces: the control interface and the reporting interface. The control interface adopts a command-response mode and defines a set of standardized instruction sets, including basic control instructions (such as start, stop, speed regulation), parameter setting instructions (such as modifying operating parameters, updating thresholds), mode switching instructions (such as switching to manual mode, diagnostic mode), etc. The instruction format is unified, including fields such as instruction header, target address, instruction code, parameter domain and check code to ensure the reliability and accuracy of instruction transmission. The main control unit sends optimized control instructions to the modular intelligent drive card through the control interface to achieve precise control of the conveyor line equipment. The reporting interface adopts a publish-subscribe mode, and the modular intelligent drive card uploads operating status data and operating feature vectors to the main control unit periodically or event-triggered. Different priorities and frequencies can be set for data upload, such as high-priority real-time upload of critical status data and low-priority batch upload of ordinary monitoring data. The report data uses a structured format that includes fields such as timestamp, device ID, data type, data value, and quality tag, which facilitates data processing and analysis by the main control unit.

[0045] The horizontal interface is mainly responsible for the collaborative communication between devices of the same level, and the core component is the dynamic handover interface. The dynamic handover interface defines the product handover protocol between adjacent conveyor line sections to achieve seamless collaboration between devices. The product handover protocol contains four key signals: a dynamic request signal, which is sent by the upstream device and contains the product information requested for handover (such as size, weight, arrival time, etc.) and the expected handover parameters (such as speed, interval, etc.); a dynamic response signal, which is replied by the downstream device and contains the receiving capability status (such as receivable, delayed reception, refused reception, etc.) and the recommended handover parameters; a handover priority signal, which is used to determine the processing order when multiple handover requests conflict. The priority is dynamically calculated based on product attributes (such as urgency, value, etc.) and system status; an extended auxiliary signal, which is used to transmit additional handover-related information, such as special handling requirements, product tracking data, quality inspection results, etc. These signals together constitute a complete handover protocol framework that supports flexible and diverse handover scenarios.

[0046] The data format of the dynamic handover interface adopts a variable-length data frame structure, which not only ensures the complete transmission of necessary information, but also avoids the waste of bandwidth caused by fixed-length frames. The data frame is composed of a frame header (including a synchronization word, frame length, frame type, etc.), a frame body (including handover information, tracking data, priority information, etc.), and a frame tail (including a check code, an end marker, etc.). The frame body part adopts a TLV (Type-Length-Value) encoding method, which can flexibly add or delete information fields to adapt to the needs of different handover scenarios. The priority information is encoded in a specific field to guide the priority order of network transmission and reception processing, ensuring that important handover information will not be delayed due to network congestion. The entire data frame structure design takes into account real-time performance, reliability, and scalability, providing a reliable communication foundation for product handover.

[0047] In the embodiment of the application, the generation method of the operation feature vector comprises:

[0048] Obtaining operation parameters of each device object in the conveying line section, the operation parameters including motor speed, sensor readings and actuator state;

[0049] Normalizing the operation parameters to generate a normalized operation parameter set;

[0050] Extracting operation fluctuation features of the device object within a preset time window according to the normalized operation parameter set, the operation fluctuation features including variance, frequency distribution and peak change rate of the operation parameters;

[0051] Fusing the operation fluctuation features with the state data to generate an operation feature vector of the device object.

[0052] In the embodiment, first, detailed operation parameters are collected from each device object of the conveying line section. For the driving motor, the speed (RPM value), phase current (A value), phase voltage (V value), output torque (N·m value), coil temperature (℃ value), vibration intensity (mm / s value), etc. are collected; for the sensor, the coordinate value (mm value) of the position sensor, the trigger state (on / off) of the photoelectric sensor, the pressure value (Pa value) of the pressure sensor, the temperature value (℃ value) of the temperature sensor, the speed value (m / s value) of the speed sensor, etc. are collected; for the actuator, the extension position (mm value) of the cylinder, the on / off state of the electromagnetic valve (on / off), the angle value (° value) of the steering engine, the action state (working / standby) of the sorting mechanism, etc. are collected. These parameters are obtained in real time through the data acquisition interface of the modular intelligent drive card, and the sampling frequency is dynamically adjusted according to the importance and change rate of the parameters, such as high-frequency sampling (such as 100Hz) for key parameters and low-frequency sampling (such as 10Hz) for general parameters.

[0053] Normalize the acquired operating parameters to eliminate dimensional differences and numerical ranges between parameters, making subsequent analysis more objective and accurate. Normalization methods include minimum-maximum normalization, which maps parameter values ​​to the interval [0, 1], converting the parameters into a distribution with a mean of 0 and a standard deviation of 1. For example, logarithmic transformation is used to compress the range of parameters with large variations. Different normalization methods may be used for different parameters; select the method that best suits the distribution characteristics of the parameter. All normalized parameters constitute the normalized operating parameter set, providing a standardized data foundation for subsequent feature extraction.

[0054] Based on a set of normalized operating parameters, the operational fluctuation characteristics of the equipment object are extracted within a preset time window (such as 5 minutes, 30 minutes, or longer). The operational fluctuation characteristics reflect the variation patterns of the parameters in the time domain, including: variance characteristics, which calculate the statistical variance of the parameters within the window and reflect the severity of the parameter fluctuations; frequency distribution characteristics, which convert the time domain signal to the frequency domain through fast Fourier transform (FFT) or wavelet transform to extract spectral characteristics such as the main frequency component and energy distribution; peak change rate, which calculates the frequency of parameter peaks and the rate of change between adjacent peaks, reflecting the stability of the system response. These fluctuation characteristics can capture the dynamic characteristics of equipment operation and are highly sensitive to abnormal conditions.

[0055] Finally, the extracted operational fluctuation features are fused with the equipment's status data (such as operating mode, fault records, maintenance cycles, etc.), and a feature fusion algorithm (such as feature-level fusion or decision-level fusion) is used to generate a comprehensive operational feature vector. The feature vector dimension is dynamically adjusted according to application requirements and computing resources, and usually contains 10-50 feature dimensions, each of which represents a specific aspect of the equipment's operational status. To improve the expressive power of the feature vector, dimensionality reduction techniques (such as principal component analysis (PCA) and linear discriminant analysis (LDA)) can be used to remove redundant information, or feature enhancement techniques (such as constructing combined features) can be used to enhance key information. The final generated operational feature vector is a high-dimensional abstract expression of the equipment's operational status, which can comprehensively and accurately characterize the equipment's health status and performance level, providing strong support for subsequent status classification and trend prediction.

[0056] In an embodiment of the present invention, a method for generating a dynamic handover strategy includes:

[0057] Acquiring output status data of a first conveyor line section and input status data of a second conveyor line section, where the first conveyor line section and the second conveyor line section are adjacent conveyor line sections;

[0058] Calculating a handover conflict probability between the first conveyor line section and the second conveyor line section based on the output state data and the input state data;

[0059] Based on the handover conflict probability, the handover priority between the first conveyor line section and the second conveyor line section is generated through a game model;

[0060] Generate a dynamic handover strategy based on the handover priority and the high-level business logic of the service host. The dynamic handover strategy includes the handover time window, handover speed, and handover path selection.

[0061] In this embodiment, the status data of adjacent conveyor line sections are first obtained in real time. For the first conveyor line section (upstream), its output status data is obtained, including: the status of the output end product queue (such as the number of products waiting for handover, product type, product size, etc.), the output rate (such as the current number of products output per minute), the output end device status (such as the driving device operation status, sensor detection status, etc.), product attributes (such as weight, shape, fragility, etc.), the time series of expected arrival at the handover point, etc. For the second conveyor line section (downstream), its input status data is obtained, including: the input end buffer status (such as current occupancy rate, remaining capacity, etc.), the input rate (such as the current number of products that can be received per minute), the input end device status (such as the receiving device preparation status, sensor ready status, etc.), the processing capacity constraint (such as the maximum processable product size, weight limit, etc.), the current processing task priority, etc. The status data is collected and updated in real time through the network communication module to ensure that the decision is based on the latest information.

[0062] Based on the acquired output state data and input state data, the probability of possible handover conflicts between the first conveyor line section and the second conveyor line section is calculated. Conflict types include: time conflicts (such as multiple products arriving at the handover point at the same time), capacity conflicts (such as product parameters exceeding the downstream processing capacity), rate conflicts (such as upstream output rate is greater than downstream receiving rate), etc. The conflict probability calculation adopts a probabilistic model, such as a Bayesian network or a Markov model, to consider various possible state combinations and their probabilities of occurrence. For example, the probability of time conflict can be expressed as: P (time conflict) = P (|T1-T2| < Δt), where T1 and T2 are the times when the two products arrive at the handover point, and Δt is the safe time interval. The model parameters trained by historical data are combined with the current state data to calculate the real-time handover conflict probability matrix to quantify the possibility of different types of conflicts.

[0063] Based on the probability of handover conflict, a game model is used to calculate the handover priority of the first conveyor line section and the second conveyor line section. The game model regards the handover process as a strategic interaction of multiple participants. Each conveyor line section selects the optimal strategy based on its own status and goals (such as maximizing throughput, minimizing waiting time, optimizing energy consumption, etc.). The model adopts a non-cooperative game framework and solves the optimal strategy combination through Nash equilibrium. The priority calculation takes into account various factors, such as product urgency (based on delivery time), product value (based on product type and customer level), system load (based on current processing volume), etc. The priority is expressed in numerical form, and the higher the value, the higher the priority. In the event of a conflict, high-priority handover requests will be given priority, and low-priority requests may be delayed or rescheduled.

[0064] A complete dynamic handover strategy is generated based on the calculated handover priority and the high-level business logic provided by the business host (such as order priority, delivery time requirements, and capacity balancing strategies). The handover strategy consists of three key components: the handover time window, which clearly defines the optimal handover time period for each product, including the start time, end time, and optimal handover moment, reducing conflicts through time staggering; the handover speed, which specifies the optimal operating speed for upstream and downstream equipment to achieve speed matching and smooth transition, avoiding product backlogs or equipment idling due to speed mismatches; and the handover path selection, which specifies the optimal handover path in a multi-path handover system, taking into account factors such as path load, distance, and equipment status to achieve load balancing and optimal resource utilization. The dynamic handover strategy is distributed to the relevant conveyor line sections via the network communication module to guide the actual execution of the handover process. The effectiveness of the strategy execution is evaluated in real time through a feedback mechanism. Deviations trigger strategy adjustments, forming a closed-loop control system to ensure the stability and efficiency of the handover process.

[0065] In an embodiment of the present invention, a method for dynamically binding product tracking data to a physical product location includes:

[0066] Obtaining an identification code for each physical product in the conveyor line section, the identification code is used to uniquely identify the physical product;

[0067] Generate a virtual position mapping table of the physical product based on the real-time position data of the physical product in the conveyor line section collected by the sensor;

[0068] Based on the virtual position mapping table, the continuous position trajectory of the physical product in the conveyor line section is predicted through the interpolation algorithm;

[0069] Bind the identification code to the continuous location track to generate product tracking data;

[0070] The product tracking data is stored in a distributed tracking database, which uses a sharded storage structure to partition the product tracking data according to the geographical location of the conveyor line section.

[0071] In this embodiment, each physical product in the conveyor line section is first uniquely identified. Identification methods include: barcode labels, which are attached to the surface of the product and read by a barcode scanner; RFID tags, which are built-in or attached to the product and are identified contactlessly by an RFID reader; QR code labels, which are printed or attached to the product and read by an image recognition device; and visual feature recognition, which uses the product's own appearance features (such as shape, color, texture, etc.) to identify the product through a machine vision system. The identification process is automatically completed when the product enters the conveyor system, and each product is assigned a unique identification code, such as a UUID (universally unique identifier), serial number, or order number. The identification code is associated with the product's business attributes (such as category, specification, order information, etc.) and stored in the system database, providing a basis for subsequent tracking.

[0072] The physical location of products on the conveyor line is determined in real time based on data collected by various sensors distributed throughout the conveyor line segment. Sensor types include: photoelectric sensors, which detect when a product passes a specific point; visual sensors, which determine product location through image analysis; RFID readers, which identify product positions within their read range; and laser rangefinders, which accurately measure the distance between a product and a reference point. These sensors are distributed at regular intervals along the conveyor line, forming a sensor network. When a product passes through a sensor coverage area, the sensor triggers and records the product ID and timestamp, which are then uploaded to the control system. The system integrates the data from each sensor to construct a set of discrete product locations on the conveyor line. This system, combined with the conveyor line's topology and coordinate system, generates a virtual location map for each product. The map is a dynamically updated data structure containing information such as product ID, timestamp, coordinate location, and movement status, providing real-time information on the distribution of products in physical space.

[0073] Based on the discrete position data in the virtual position mapping table, the continuous position trajectory of the product in the conveying line section is predicted by an interpolation algorithm. The interpolation algorithm types include: linear interpolation, suitable for simple scenarios with constant speed movement; spline interpolation, suitable for scenarios with smooth speed changes, generating smooth curves; Bezier curve interpolation, suitable for accurate description of complex paths; Kalman filtering, combining motion model and measurement data, suitable for trajectory prediction in noisy environment. The algorithm selection is dynamically determined according to the characteristics of the conveying line and the accuracy requirements. The interpolation process considers the physical constraints of the conveying line (such as speed limit, acceleration limit, path constraint, etc.) and real-time running parameters (such as current speed, equipment state, etc.), ensuring the physical feasibility of the predicted trajectory. The prediction result is a continuous function of time-position, which can calculate the expected position of the product at any time, making up for the gap in position information caused by discrete sampling of sensors, and realizing continuous tracking of the product position.

[0074] The product identification code is bound to the predicted continuous position trajectory to generate complete product tracking data. The tracking data is a multi-dimensional data structure, including: product basic information (such as ID, type, specification, etc.), position trajectory information (such as current position, historical trajectory, predicted trajectory, etc.), time information (such as entry time, estimated completion time, node passing time, etc.), state information (such as normal movement, pause, abnormality, etc.), business information (such as order, priority, destination, etc.). These information is organized through association relationship to form a complete product digital mapping, supporting all-round product tracking and monitoring.

[0075] The generated product tracking data is stored in a distributed tracking database to ensure high availability and query efficiency of the data. The database uses a sharded storage structure to manage tracking data by geographical location of the conveying line section. Each physical area corresponds to a data shard, managed by the nearest server node, reducing data transmission delay. The shards maintain data consistency through synchronization mechanism, ensuring the continuity of tracking data when the product moves across regions. The database supports multiple query modes, such as querying by product ID, querying by location area, querying by time range, etc., meeting the needs of different business scenarios. At the same time, data lifecycle management is implemented to archive or clean up historical data, maintaining efficient system operation. Through this distributed architecture, efficient storage and fast access of product tracking data are realized, providing reliable data support for upper-layer applications.

[0076] In the embodiment of the application, the generation method of the prediction model comprises:

[0077] Obtain historical running data and historical state data of the conveying line section, the historical running data including running parameters of the device object, and the historical state data including fault records and handover records of the device object;

[0078] Based on historical operation data and historical state data, a time series data set is constructed;

[0079] Feature extraction is performed on the time series data set to generate a prediction feature set, which includes trend features, periodic features and abnormal features of the operation parameters;

[0080] Based on the prediction feature set, a prediction model is trained through a long short-term memory network to generate operation trend prediction data.

[0081] In this embodiment, first, comprehensive historical data of the conveying line section is obtained from the system historical database. The historical operation data includes various parameter records in the long-term operation process of the equipment object, such as the speed history curve of the driving motor, the current change record, the temperature fluctuation data, the historical readings of the sensor, the trigger record, the sensitivity change, the action timing record of the actuator, the response time statistics, the torque output history, etc. The historical state data includes fault records of the equipment object, such as fault type, occurrence time, duration, severity, handling method, etc.; handover records, such as handover time point, handover product type, handover success rate, handover abnormal type, etc.; and maintenance records, warning records and other auxiliary information. Quality assessment is performed during data acquisition, and the data integrity, accuracy and consistency are checked to eliminate or repair low-quality data and ensure the reliability of subsequent analysis.

[0082] Based on the obtained historical operation data and historical state data, a standardized time series data set is constructed. The data set is organized in a multi-dimensional time series format, with each time point corresponding to multiple feature dimensions, including original operation parameters, state markers and derived indicators. Data preprocessing includes: time alignment, which unifies data from different sources and different sampling rates to the same time scale using interpolation or downsampling methods; missing value processing, which uses forward filling, mean filling or model prediction filling to ensure data continuity; outlier processing, which identifies and processes outliers in the data to avoid their negative impact on model training; and data standardization, which normalizes parameters of different dimensions to make them suitable for model training. The processed data set is arranged in chronological order and divided into training set, validation set and test set for model training and evaluation.

[0083] Feature extraction is performed on the constructed time series dataset to uncover patterns and regularities within the data and generate a predictive feature set. Feature extraction focuses on three key features: trend features, which reflect the long-term direction of parameter changes, such as linear trend coefficients, exponential smoothing values, and moving averages, capturing the gradual evolution of parameters; periodic features, which reflect the cyclical variation of parameters, such as Fourier transform coefficients, wavelet transform features, and autocorrelation coefficients, identifying periodic patterns in the data; and anomaly features, which reflect unusual fluctuations in parameters, such as mutation detection indicators, entropy changes, and outlier metrics, identifying potential precursors to anomalies. The feature extraction process utilizes a sliding window mechanism, calculating feature values ​​at different time scales to capture short-term, medium-term, and long-term data characteristics. Furthermore, interaction terms and derived features between features, such as correlation coefficients, ratios, and composite indices, are introduced to enhance the expressive power of the features. After importance assessment and redundancy analysis, the extracted features are screened for the most predictive subset, which forms the final predictive feature set.

[0084] Based on the prediction feature set, a prediction model is constructed using a long short-term memory (LSTM) network from deep learning. The LSTM network architecture includes: an input layer, which receives feature vectors from the prediction feature set; an LSTM layer, consisting of multiple LSTM units, each with an input gate, a forget gate, and an output gate, enabling the learning of long-term dependencies; an attention mechanism layer, which focuses on key time points and features to improve prediction accuracy; a fully connected layer, which maps the output of the LSTM layer to the prediction target space; and an output layer, which generates the final prediction results. The network is trained using the backpropagation algorithm, with the mean squared error (MSE) or mean absolute error (MAE) loss function, Adam or RMSprop as the optimizer, and a dynamic learning rate adjustment strategy. To prevent overfitting, the model incorporates regularization techniques such as L2 regularization and dropout. During model training, model performance is evaluated on a validation set, and hyperparameters such as the number of hidden layers, units, and learning rate are dynamically adjusted to find the optimal configuration. After training, the model is evaluated on a test set to ensure good generalization.

[0085] The trained LSTM prediction model can generate operational trend forecasts for conveyor line sections based on current and historical operational data. This forecast includes multiple dimensions: equipment performance trends, which predict future performance curves for equipment, such as efficiency, energy consumption, and response time; failure risk prediction, which assesses the probability and potential time windows for various equipment failures; transfer capacity prediction, which predicts the maximum transfer capacity and potential bottlenecks in future periods; and resource demand prediction, which estimates the energy and maintenance resources required for future operations. The forecast results are presented as a time series, including predicted values, confidence intervals, and possible scenario branches, providing multi-dimensional reference information for system control decisions. After the model is deployed, an online learning mechanism is implemented to continuously absorb new operational data and continuously optimize model parameters to maintain the accuracy and timeliness of the forecasts and adapt to the dynamic changes in the conveyor system.

[0086] In an embodiment of the present invention, a dynamic power allocation method of a power management module of a modular intelligent driver card includes:

[0087] Get the real-time power demand of each equipment object in the transmission line section;

[0088] Based on the real-time power demand, the power demand peak of the transmission line section in the future time window is predicted through the power prediction algorithm;

[0089] Based on the peak power demand, the power allocation ratio of the power management module is dynamically adjusted to generate a power allocation strategy;

[0090] According to the power allocation strategy, the power management module is controlled to provide differentiated power output to the device objects.

[0091] In this embodiment, the power demand data of each equipment object in the transmission line section is first obtained in real time. For the drive motor, the real-time current, voltage and power factor are measured, and the active power, reactive power and apparent power are calculated; for the sensor, the supply voltage and working current are recorded, and the power consumption level is calculated; for the actuator, the instantaneous power and average power during the action are monitored. Power data acquisition uses a high-precision power parameter measurement circuit, which supports a wide range of power monitoring (such as 0.1W to several kW) and fast response (such as millisecond sampling rate). During the data acquisition process, the working status and load conditions of the equipment are recorded at the same time, and a mapping relationship between power demand and working status is established to provide a basis for subsequent predictions. After preliminary processing (such as filtering and calibration), all power data forms a real-time power demand data stream and is input into the power management system.

[0092] Based on the acquired real-time power demand data, a power prediction algorithm is applied to predict the power demand changes, especially the power peaks, of the conveyor line section within a future time window (such as the next 5 minutes, 15 minutes, 30 minutes, etc.). The prediction algorithm comprehensively uses multiple technologies: time series prediction methods such as autoregressive moving average model (ARIMA), exponential smoothing method, etc., based on the time regularity of historical power data for prediction; machine learning methods such as support vector regression (SVR), random forest, etc., using multi-dimensional features (including current power, equipment status, product characteristics, etc.) to predict future power; deep learning methods such as recurrent neural network (RNN), long short-term memory network (LSTM), etc., to capture complex nonlinear patterns of power changes. The prediction process takes into account business planning factors such as the product queue to be processed, planned speed adjustments, etc., to enhance the forward-looking nature of the prediction. The algorithm output includes expected power values at different time points, power change curves, peak occurrence time and duration, and predicted confidence intervals, fully describing the characteristics of future power demand.

[0093] Based on the power demand prediction results, especially the predicted power demand peaks, the power distribution strategy of the power management module is dynamically adjusted. The strategy-making process takes into account multiple factors: total power constraint, setting the upper limit of power distribution according to the total capacity of the power supply system; device priority, determining the power supply priority according to the importance of the device and the degree of business impact; energy efficiency optimization, pursuing the maximization of the overall energy utilization efficiency of the system; peak smoothing, balancing power peaks and valleys through pre-distribution and delayed power supply. The strategy is represented as a set of power distribution proportion coefficients, which define the percentage of power that each device category or functional unit should obtain under different load conditions. The distribution strategy is adaptive and can be dynamically adjusted according to real-time load changes and prediction results, ensuring that the system can maintain stable operation and optimal performance under various working conditions.

[0094] According to the generated power distribution strategy, the power management module controls the differentiated power supply output to each device object in real time. The control methods include: voltage regulation, dynamically adjusting the output voltage through an efficient voltage stabilizing circuit to meet the voltage requirements of different devices; current limiting, limiting the output current of each channel through an accurate current control circuit to avoid overload; power modulation, adjusting the power output through pulse width modulation (PWM) or phase control technology to achieve accurate power distribution; timing control, controlling the power-on time and sequence of each device through an intelligent timing circuit to avoid power peaks caused by simultaneous startup. The power supply control has high precision (such as power control accuracy better than 1%) and fast response characteristics (such as millisecond-level adjustment speed), which can adapt to rapidly changing load conditions. At the same time, the control system continuously monitors the power supply state and device response to form a closed-loop control, ensuring the effective implementation of the power distribution strategy. In extreme cases (such as total power demand exceeding system capacity), automatic protection mechanisms are activated, such as power-off by priority, load degradation operation, etc., to protect system safety. Through this intelligent dynamic power management, the system can achieve optimal energy distribution under limited power resources, improve energy utilization efficiency, reduce operating costs, while ensuring the reliable operation of critical devices and improving the overall performance of the system.

[0095] In the embodiment of the present application, the system further comprises an adaptive configuration unit, which is used to realize adaptive configuration of parameters through a network interface. The method for adaptive configuration of parameters comprises:

[0096] The hardware parameters of the modular intelligent drive card and the operation parameters of the conveying line section are obtained.

[0097] Based on the hardware parameters and the operation parameters, an environmental perception algorithm is used to identify the operation environment characteristics of the conveying line section, which include temperature, humidity, load change rate and equipment aging degree.

[0098] According to the operation environment characteristics, an adaptive parameter configuration strategy is generated through a reinforcement learning model.

[0099] Based on the adaptive parameter configuration strategy, the operation parameters of the modular intelligent drive card and the master control unit are updated, and the update results are displayed through the network interface.

[0100] In this embodiment, the adaptive configuration unit as the core configuration management component of the system, first through the system bus and network interface to obtain the hardware parameters of the modular intelligent drive card and the running parameters of the conveying line section. The hardware parameters include: processor specifications (such as model, frequency, core number, etc.), memory capacity, communication interface type (such as RS485, CAN, Ethernet, etc.), power supply specifications (such as input voltage range, maximum power, etc.), expansion capability (such as I / O point number, module slot, etc.), hardware version number, etc. The running parameters include: processor load rate, memory usage, communication bandwidth occupation, power output, I / O response time, module temperature, etc. Real-time performance indicators. The parameter acquisition process adopts a combination of polling and event triggering mechanism to ensure that the data is comprehensive and timely. After preprocessing (such as denoising, formatting), the obtained parameters form a structured parameter data set, providing a basis for subsequent analysis.

[0101] Based on the obtained hardware parameters and running parameters, the running environment characteristics of the conveying line section are identified through the environment perception algorithm. The environment perception algorithm integrates multi-source data, including: direct environment sensing data, such as temperature, humidity, dust concentration, vibration intensity, etc. Physical environment parameters collected through built-in or external sensors; indirect inference data, such as environmental factors inferred from changes in device running characteristics, such as power fluctuations, communication quality changes, etc.; historical comparison data, comparing the current running parameters with the historical baseline to identify abnormal change patterns. The algorithm uses multi-modal data fusion technology to integrate and analyze data from different sources and forms, extracting environmental characteristics. Key environmental characteristics include: temperature characteristics, including average temperature, temperature fluctuation range, temperature gradient, etc., affecting the reliability and life of electronic components; humidity characteristics, including relative humidity, humidity change rate, etc., affecting insulation performance and electrical safety; load change rate, representing the dynamic characteristics of system load, such as peak-to-valley ratio, change frequency, mutation amplitude, etc., affecting system resource allocation strategy; device aging degree, quantified by performance degradation curve, error growth rate, response delay, etc. Reflecting the health status and remaining life of the device. These characteristics comprehensively reflect the running environment of the conveying line section, providing decision basis for parameter adaptive configuration.

[0102] Based on the identified operating environment characteristics, a reinforcement learning model is used to generate an adaptive parameter configuration strategy. This reinforcement learning model models the parameter configuration problem as a Markov decision process (MDP), comprising: a state space defined by the operating environment characteristics and the current system state; an action space consisting of the range of values ​​and adjustment steps for each adjustable parameter; a reward function designed based on system performance metrics (such as processing efficiency, energy consumption, and failure rate) to quantify the effects of parameter adjustments; and a state transition model describing the mechanism by which parameter adjustments affect the system state. The model employs advanced reinforcement learning algorithms, such as the Deep Q-Network (DQN), the Policy Gradient method, or the Actor-Critic architecture, to learn the optimal parameter configuration strategy through interaction with the environment. During the learning process, the model gradually explores the parameter space, discovers the optimal parameter combination under different environmental conditions, and establishes a mapping between environmental characteristics and parameter configurations. Model training utilizes a combination of online and offline learning, utilizing historical data for basic training while enabling continuous optimization based on real-time feedback to adapt to dynamic environmental changes. The learning result is an adaptive parameter configuration strategy that can automatically recommend the optimal parameter settings based on the characteristics of the current operating environment, thereby achieving environmental adaptation of system performance.

[0103] Based on the generated adaptive parameter configuration strategy, the operating parameters of the modular intelligent drive card and main control unit are updated. The parameter update process includes parameter verification, which checks the validity and security of recommended parameters to ensure they are within a safe range; progressive updates, which employ a gradual adjustment strategy for key parameters to avoid system instability caused by sudden changes; a rollback mechanism, which sets a monitoring window for parameter updates and enables a rapid rollback to the previous stable configuration if performance anomalies are detected; and version management, which records historical parameter updates and supports configuration comparison and rollback. After the parameter update, the system visually displays the update results through a web interface. This includes a parameter change list, which clearly displays a comparison of parameters before and after the adjustment; a performance impact analysis, which quantifies the expected impact of the parameter adjustment on various system performance indicators; an environmental adaptability score, which assesses the adaptability of the current configuration to the current environment; and optimization suggestions, which provide directions and potential for further optimization. The web interface adopts a responsive design and supports access from a variety of terminal devices (such as PCs, tablets, and mobile devices). Interface elements include data tables, trend charts, and parameter relationship network diagrams, providing a comprehensive and intuitive presentation of configuration information. Through this adaptive parameter configuration mechanism, the system can actively adjust operating parameters according to environmental changes, maintain optimal operating status, improve the system's adaptability and reliability in complex and changing environments, and reduce the workload and error risks of manual configuration.

[0104] In an embodiment of the present invention, a method for generating a game model includes:

[0105] A game objective function is constructed, which takes minimization of handover conflict probability as an optimization objective and takes task priority of high-level business logic of the business host as a constraint condition;

[0106] A strategy model of handover behavior of the first and second conveying line sections is established to generate a handover strategy set;

[0107] Based on the game objective function and the handover strategy set, the handover priority is solved by a Nash equilibrium algorithm.

[0108] In this embodiment, first, a game objective function of the handover process is constructed as a core evaluation standard of the game model. The objective function is designed based on two key factors: one is minimization of handover conflict probability, which takes the occurrence probability of various conflicts (such as time conflict, capability conflict, rate conflict, etc.) as the main optimization objective, and pursues minimization of the overall conflict rate of the system; the other is the task priority in the high-level business logic provided by the business host as a constraint condition, which ensures that high-priority tasks are given priority. The mathematical expression form of the objective function is a multi-objective optimization function, which can be expressed as:

[0109] F(x)=α·P_conflict(x)+β·∑ i w_i·V_i(x);

[0110] Wherein, P_conflict(x) represents the overall conflict probability under the strategy x; V_i(x) represents the influence value (such as delay, cost, etc.) of the strategy x on the task with priority i; w_i represents the weight coefficient of the priority i; and α and β are balance coefficients for adjusting the balance relationship between conflict minimization and priority guarantee. The objective function can also include other constraint terms, such as energy consumption limit, device load balancing, etc., to form a complete multi-objective optimization problem.

[0111] The handover behavior of the first conveying line section and the second conveying line section is modeled by strategy, and the actions and decisions that each participant can take are abstracted into a strategy space. The strategy space of the first conveying line section (upstream) includes: output rate adjustment strategies such as maintaining the current rate, increasing the rate, decreasing the rate, etc.; product sorting strategies such as sorting by product priority, sorting by product attribute, sorting by destination, etc.; buffer management strategies such as active buffering, direct output, conditional buffering, etc.; handover request strategies such as immediate request, delayed request, batch request, etc. The strategy space of the second conveying line section (downstream) includes: receiving rate adjustment strategies such as matching the upstream rate, fixed rate, dynamically adjusting the rate, etc.; admission control strategies such as receiving all, conditionally receiving, rejecting receiving, etc.; buffer management strategies such as reserved buffer, dynamic allocation, priority buffer, etc.; handover response strategies such as immediate response, delayed response, conditional response, etc. These strategies can be combined to form composite strategies, constituting a complete strategy set. The strategy modeling process takes into account device physical constraints, control precision limitations, and response time characteristics to ensure the practical feasibility of the model.

[0112] Based on the constructed game objective function and the handover strategy set, a Nash equilibrium algorithm is applied to solve the handover priority. The solving process first establishes a payment matrix of strategy combinations, and the matrix elements represent the benefits (or costs) of each participant under a certain strategy combination, such as the degree of conflict probability reduction, the efficiency of task completion improvement, etc. The payment matrix can be high-dimensional, containing multiple strategy combinations and multiple participants. The Nash equilibrium solving uses iterative methods such as Best Response Dynamics, Pseudo-gradient Descent, or Evolutionary Game Algorithms, etc. Constraints such as physical feasibility constraints, resource limitation constraints, etc. are considered in the solving process to ensure that the results are executable in the actual system. The algorithm outputs multiple possible equilibrium points, each corresponding to a set of handover strategy combinations and the corresponding priority allocation scheme. By evaluating the performance indicators (such as conflict probability, system throughput, task delay, etc.) of each equilibrium point, the optimal equilibrium solution is selected as the final handover priority scheme. The scheme represents the priority order of each handover request in numerical form, such as priority scores based on 0-1 normalization, facilitating system execution of priority judgment and resource allocation. The handover priority solving process is dynamic, updating in real time as the system state and business demand change, ensuring that the priority always reflects the current optimal decision.

[0113] In the embodiment of the application, the method for predicting the continuous position trajectory of the physical product in the conveying line section by the interpolation algorithm comprises:

[0114] Obtaining discrete location data of the physical product in the virtual location mapping table, where the discrete location data includes a timestamp and corresponding virtual location coordinates;

[0115] Based on the virtual position mapping table, the position change characteristics of the physical product in the conveyor line section are extracted. The position change characteristics include the discrete time intervals and position offsets of the position coordinates.

[0116] Based on the position change characteristics, a dynamic position distribution model of the physical product in the conveyor line section is constructed. The dynamic position distribution model is used to characterize the position distribution probability of the physical product in different time periods.

[0117] Based on the dynamic position distribution model, the discrete position data is interpolated by the probability weighted interpolation algorithm to generate the preliminary continuous position trajectory of the physical product in the conveyor line section;

[0118] Obtaining the operating status data of the equipment objects in the conveyor line section, including the speed fluctuation of the drive motor and the detection error of the sensor;

[0119] Based on the operating status data, the preliminary continuous position trajectory is corrected to generate a corrected continuous position trajectory, wherein the correction includes adjusting the smoothness of the position trajectory based on the speed fluctuation and adjusting the offset of the position trajectory based on the detection error;

[0120] The corrected continuous position trajectory and the virtual position mapping table are dynamically updated to ensure that the virtual position mapping table is consistent with the actual position of the physical product.

[0121] In this embodiment, the discrete position data of the physical product is first extracted from the virtual position mapping table. The position mapping table is a dynamic data structure maintained by the system, which records the movement trajectory points of each product on the conveyor line. The discrete position data contains two key elements: a timestamp, which accurately records the moment when the product is detected, usually with an accuracy of milliseconds; and a virtual position coordinate, which records the position of the product in a virtual coordinate system. The coordinate system can be one-dimensional (such as the distance value on a straight conveyor line), two-dimensional (such as the (x, y) coordinates in a plane conveyor system), or three-dimensional (such as the (x, y, z) coordinates in a stereoscopic conveyor system). The data extraction process performs a data quality check, filters out outliers (such as points that significantly deviate from a reasonable trajectory) and redundant data (such as repeated sampling points with too short time intervals), and ensures the data quality of subsequent analysis. The extracted discrete position data forms a time-position sequence, which provides a basis for trajectory prediction.

[0122] Based on the historical data in the virtual position mapping table, the position change characteristics of the physical product in the conveying line section are extracted. The position change characteristics include two core dimensions: the discrete time interval of the position coordinates, which reflects the frequency and regularity of position sampling, and the statistical distribution of the time interval (such as mean, standard deviation, distribution shape, etc.), which identifies the pattern and anomaly of time sampling; the position offset, which represents the position change between adjacent sampling points, and the vector characteristics (such as size, direction) and statistical characteristics (such as average speed, acceleration, turning frequency, etc.) of the offset. The feature extraction process uses time series analysis methods such as sliding window statistics, change rate calculation, pattern recognition, etc., to mine the motion rules from discrete data. In addition, context-related features are also extracted, such as behavior characteristics in specific areas (such as turns, intersections, transfer points, etc.), motion characteristics under specific conditions (such as high load, high speed operation, etc.). These position change characteristics comprehensively describe the motion characteristics of the product on the conveying line, providing a basis for subsequent modeling.

[0123] According to the extracted position change characteristics, a dynamic position distribution model of the physical product in the conveying line section is constructed. The model is a probabilistic description of the change of product position over time, which can represent the possible position distribution of the product at any time. The model construction uses probability and statistics methods such as Gaussian Process, Hidden Markov Model or Bayesian Network, etc. The model parameters are obtained by training with historical data, which can capture the regularity and randomness of product motion. The model characteristics include: time-varying, the model parameters are dynamically adjusted with time, adapting to the change of system state; spatial correlation, considering the correlation structure between positions, such as path constraints, velocity continuity, etc.; multi-modal, which can handle multiple possible motion patterns, such as uniform motion, acceleration motion, pause, etc. The model output is the position distribution probability density function of the product in different time periods, which can not only give the most likely position point, but also quantify the uncertainty of position prediction.

[0124] Based on the constructed dynamic position distribution model, a probability-weighted interpolation algorithm is applied to interpolate discrete position data to generate a preliminary continuous position trajectory. Unlike traditional deterministic interpolation methods (such as linear interpolation and spline interpolation), the probability-weighted interpolation algorithm considers the probability distribution of position predictions and can more accurately reflect the uncertainty of product movement. The algorithm process includes: for each time point to be interpolated, the probability distribution of possible positions is calculated based on the dynamic position distribution model; multiple possible positions are sampled from the probability distribution; the sampled points are weighted averaged, with weights based on the position probability and physical feasibility; and a smooth trajectory is generated that meets physical constraints (such as speed limits, acceleration limits, and path constraints). The interpolation process considers the topology of the conveyor line, such as straight segments, curved segments, and intersections, to ensure that the generated trajectory meets physical path constraints. The algorithm output is a time-continuous position trajectory function that can calculate the expected position at any time, bridging the time gaps in the original discrete data.

[0125] Real-time operating status data of equipment objects in the conveyor line section is acquired to provide a basis for trajectory correction. Operating status data includes two key types of information: the speed fluctuation of the drive motor, which reflects the changes in the conveyor line speed, including real-time speed value, speed fluctuation range, acceleration and deceleration characteristics, etc.; and the detection error of the sensor, which quantifies the uncertainty of position detection, including systematic errors (such as sensor position offset and signal delay) and random errors (such as noise interference and environmental influences). Status data is collected in real time through the monitoring interface of the modular intelligent drive card. After data preprocessing (such as filtering and calibration), it forms a structured status data set for trajectory correction.

[0126] Based on the acquired device operating status data, the preliminary continuous position trajectory is corrected to generate a more accurate continuous position trajectory. The correction process involves two key steps: 1. Adjusting the trajectory smoothness based on drive motor speed fluctuations. Actual motor speed changes (such as fluctuations, jitter, and transients) are mapped onto the position trajectory, ensuring the trajectory more accurately reflects the product's actual motion. For example, the trajectory slows down during motor deceleration and steepens during acceleration. 2. Adjusting the trajectory offset based on sensor detection errors. The trajectory is compensated based on sensor error characteristics (such as systematic bias and random noise) to correct for position offsets caused by detection errors. Correction utilizes filtering algorithms such as Kalman filters or particle filters to fuse the preliminary trajectory with status data. This method preserves trajectory continuity and smoothness while enhancing trajectory accuracy and reliability. The correction process is dynamic; as new status data is generated, the trajectory is continuously updated and optimized to maintain consistency with the actual product position.

[0127] The corrected continuous location trajectory and the virtual location mapping table are dynamically updated to ensure that the location data in the system always reflects the actual location of the product. The update process utilizes an incremental update strategy, updating only the changed parts to reduce system overhead. Updates include: fine-tuning of historical trajectory points based on newly acquired information to improve the accuracy of historical data; precise positioning of the current location, calculating the product's current location in real time to support real-time monitoring and interaction; and updating of future trajectory predictions, adjusting future trajectory predictions based on the latest data to improve prediction accuracy. Data consistency checks are implemented during the update process to ensure that the updated data meets physical and logical constraints, such as velocity continuity and location boundary limits. Through this dynamic update mechanism, the virtual location mapping table can be continuously optimized, continuously improving the accuracy and timeliness of product location representation, providing reliable location data support for product tracking and system control.

[0128] Through the description of the above specific implementation methods, the logistics conveyor line integrated control system based on modular intelligent drive cards of the present invention realizes real-time collection and analysis of equipment object operating parameters, dynamic classification and prediction of operating status, seamless handover and coordination between adjacent conveyor line sections, and accurate tracking and mapping of product locations, which significantly improves the intelligence level, operating efficiency and reliability of the logistics conveying system.

[0129] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art will be able to modify the technical solutions described in the foregoing embodiments or to substitute equivalents for some of the technical features. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

[0130] The formulas in this manual are all dimensionless and calculated using numerical values. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters and thresholds in the formulas are set by technicians in this field based on actual conditions.

[0131] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to the embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the claims and their equivalents.

Claims

1. The integrated control system of logistics conveyor line based on modular intelligent drive card is characterized by: include: At least one modular intelligent drive card, at least one conveyor line section, at least one main control unit and at least one service host; The modular intelligent driver card includes a power management module and a network communication module. The power management module is used to provide power supply, perform dynamic power distribution and collect operating status data. The network communication module is used to realize multi-protocol data communication and real-time handover control. The conveyor line section includes at least one equipment object, and the equipment object includes a drive motor, a sensor, and an actuator; The main control unit is used to communicate with the modular intelligent drive card and perform real-time control of the conveyor line section through a standardized communication interface; The business host is used to execute high-level business logic, including logistics task scheduling, data storage and product tracking; The system implements integrated control of the logistics conveyor line through the following steps: Obtaining the operating parameters and status data of each equipment object in the conveyor line section, and generating a corresponding operating feature vector through the modular intelligent drive card; Based on the operation feature vector, the operation status of the conveyor line section is classified by a dynamic clustering algorithm to generate a classified operation status set; Generate operation trend prediction data of the conveyor line section through a prediction model according to the operation status set and the high-level business logic of the business host; Based on the operation trend prediction data, generating and issuing optimization control instructions through the standardized communication interface to adjust the operation parameters of the device object; generating a dynamic handover strategy through the network communication module according to product handover requirements between the conveyor line sections, and coordinating product handover between adjacent conveyor line sections based on the dynamic handover strategy; Product tracking data is generated according to the high-level business logic of the business host, and the product tracking data is dynamically bound to the physical product location in the conveyor line section through a virtual mapping mechanism.

2. The integrated control system for logistics conveyor lines based on modular intelligent driver cards according to claim 1, characterized in that: The standardized communication interface includes a vertical interface and a horizontal interface, wherein: The vertical interface includes a control interface and a reporting interface, wherein the control interface is used to send the optimization control instruction from the main control unit to the modular intelligent driver card, and the reporting interface is used to upload the operating status data and the operating feature vector from the modular intelligent driver card to the main control unit; The horizontal interface includes a dynamic handover interface, which is used to define a product handover protocol between adjacent conveyor line sections. The product handover protocol includes a dynamic request signal, a dynamic response signal, a handover priority signal, and an extended auxiliary signal. The data format of the dynamic handover interface adopts a variable-length data frame structure, and the variable-length data frame structure is used to carry the product handover information, the product tracking data and the priority information of the dynamic handover strategy.

3. The integrated control system for logistics conveyor lines based on modular intelligent driver cards according to claim 1 is characterized in that: The method for generating the running characteristic vector includes: Obtaining operating parameters of each equipment object in the conveyor line section, the operating parameters including motor speed, sensor reading, and actuator status; Normalizing the operating parameters to generate a normalized operating parameter set; Extracting, based on the normalized operating parameter set, operating fluctuation characteristics of the device object within a preset time window, the operating fluctuation characteristics including variance, frequency distribution, and peak change rate of the operating parameters; The operation fluctuation feature is fused with the state data to generate an operation feature vector of the device object.

4. The integrated control system for logistics conveyor lines based on modular intelligent driver cards according to claim 1, characterized in that: The method for generating the dynamic handover strategy includes: Acquiring output status data of a first conveyor line section and input status data of a second conveyor line section, wherein the first conveyor line section and the second conveyor line section are adjacent conveyor line sections; Calculating a handover conflict probability between the first conveyor line section and the second conveyor line section based on the output state data and the input state data; Based on the handover conflict probability, generating a handover priority between the first conveyor line section and the second conveyor line section through a game model; The dynamic handover strategy is generated according to the handover priority and the high-level service logic of the service host. The dynamic handover strategy includes a handover time window, a handover speed, and a handover path selection.

5. The integrated control system for logistics conveyor lines based on modular intelligent driver cards according to claim 1, characterized in that: The method for dynamically binding the product tracking data to the physical product location includes: Obtaining an identification code for each physical product in the conveyor line section, wherein the identification code is used to uniquely identify the physical product; generating a virtual position mapping table of the physical product according to the real-time position data of the physical product in the conveyor line section collected by the sensor; Based on the virtual position mapping table, predicting the continuous position trajectory of the physical product in the conveyor line section by an interpolation algorithm; Binding the identification code to the continuous location track to generate the product tracking data; The product tracking data is stored in a distributed tracking database, which adopts a shard storage structure and performs partition management on the product tracking data according to the geographical location of the conveyor line section.

6. The integrated control system for logistics conveyor lines based on modular intelligent driver cards according to claim 1, characterized in that: The method for generating the prediction model includes: Acquire historical operation data and historical status data of the conveyor line section, wherein the historical operation data includes operation parameters of the equipment object, and the historical status data includes fault records and handover records of the equipment object; constructing a time series data set based on the historical operation data and the historical status data; Extracting features from the time series data set to generate a prediction feature set, wherein the prediction feature set includes trend features, period features, and abnormal features of the operating parameters; Based on the prediction feature set, the prediction model is trained through a long short-term memory network to generate the operation trend prediction data.

7. The integrated control system for logistics conveyor lines based on modular intelligent driver cards according to claim 1, characterized in that: The dynamic power distribution method of the power management module of the modular intelligent driver card includes: Obtaining real-time power requirements of each equipment object in the transmission line section; According to the real-time power demand, a power forecasting algorithm is used to forecast the peak power demand of the transmission line section in a future time window; Based on the power demand peak, dynamically adjust the power allocation ratio of the power management module to generate a power allocation strategy; According to the power allocation strategy, the power management module is controlled to provide differentiated power outputs to the device objects.

8. The integrated control system for logistics conveyor lines based on modular intelligent driver cards according to claim 1, characterized in that: The system further includes an adaptive configuration unit, which is configured to implement adaptive configuration of parameters through a network interface. The method for adaptive configuration of parameters includes: Obtaining hardware parameters of the modular intelligent drive card and operating parameters of the conveyor line section; Based on the hardware parameters and the operating parameters, identifying operating environment characteristics of the conveyor line section through an environmental perception algorithm, the operating environment characteristics including temperature, humidity, load change rate, and equipment aging degree; Generating an adaptive parameter configuration strategy through a reinforcement learning model according to the operating environment characteristics; Based on the adaptive parameter configuration strategy, the operating parameters of the modular intelligent drive card and the main control unit are updated, and the update results are displayed through the network interface.

9. The integrated control system for logistics conveyor lines based on modular intelligent driver cards according to claim 4, characterized in that: The method for generating the game model includes: Constructing a game objective function, wherein the game objective function takes minimizing the handover conflict probability as an optimization goal and takes the task priority of the high-level business logic of the business host as a constraint condition; Performing strategy modeling on the handover behavior between the first conveyor line section and the second conveyor line section to generate a handover strategy set; Based on the game objective function and the handover strategy set, the handover priority is solved by a Nash equilibrium algorithm.

10. The integrated control system for logistics conveyor lines based on modular intelligent driver cards according to claim 1, characterized in that: The method for predicting the continuous position trajectory of the physical product in the conveyor line section by an interpolation algorithm includes: Obtaining discrete location data of the physical product in the virtual location mapping table, the discrete location data including a timestamp and corresponding virtual location coordinates; Extracting position change characteristics of the physical product in the conveyor line section based on the virtual position mapping table, the position change characteristics including discrete time intervals and position offsets of position coordinates; Constructing a dynamic position distribution model of the physical product in the conveyor line section according to the position change characteristics; Based on the dynamic position distribution model, the discrete position data is interpolated by a probability weighted interpolation algorithm to generate a preliminary continuous position trajectory of the physical product in the conveyor line section; Acquiring operating status data of the equipment object in the conveyor line section, the operating status data including speed fluctuation of the drive motor and detection error of the sensor; Correcting the preliminary continuous position trajectory based on the operating status data to generate a corrected continuous position trajectory, wherein the correction includes adjusting the smoothness of the position trajectory based on the speed fluctuation and adjusting the offset of the position trajectory based on the detection error; The corrected continuous position trajectory and the virtual position mapping table are dynamically updated to ensure that the virtual position mapping table is consistent with the actual position of the physical product.

Images