A method for stacking monitoring and residual material calculation based on multi-dimensional data linkage processing

Abstract

This application relates to a multi-dimensional data linkage processing method for stacking monitoring and surplus material calculation, comprising the following steps: environmental assessment and requirements definition: assessing the stacking area and customizing the sensor layout and data acquisition scheme; sensor network deployment and calibration: deploying sensors, RFID tag readers, and 3D scanners according to the design scheme; data interface and fusion platform construction; three-dimensional stacking model construction; intelligent analysis algorithm development and testing: developing machine learning-based intelligent analysis algorithms, training and testing the algorithms, and optimizing algorithm performance; dynamic monitoring and anomaly detection mechanism establishment: implementing a dynamic monitoring system to continuously track changes in stacking status, developing anomaly detection algorithms to identify safety hazards in real time and trigger early warning mechanisms; surplus material calculation and optimization suggestion generation: performing detailed surplus material calculations to provide accurate information on remaining material quantities; system integration and on-site debugging.

Description

Technical Field

[0001] This application relates to the field of material management technology, specifically to a method for stacking monitoring and surplus material calculation with multi-dimensional data linkage processing. Background Technology

[0002] In modern warehousing and logistics, efficient material management is crucial for improving operational efficiency, reducing waste, and ensuring safety. Traditional manual inventory and management methods are not only time-consuming and labor-intensive but also prone to errors, making it difficult to meet increasingly complex and dynamically changing inventory demands. With the development of Internet of Things (IoT), big data, and artificial intelligence (AI) technologies, intelligent material management systems are gradually becoming key to improving warehouse management. However, existing technologies still have shortcomings in real-time monitoring, accurate measurement, intelligent analysis, and space optimization, especially lacking a comprehensive system that integrates multiple sensing technologies, can dynamically model, and provide optimization strategies. Although some automated systems have attempted to manage through sensors and computer assistance, these systems are mostly limited to single-dimensional data collection and analysis, failing to comprehensively consider the dynamic interaction of multiple factors such as spatial layout, material attributes, and time series, resulting in low monitoring accuracy and inaccurate surplus material calculations. Summary of the Invention

[0003] This application provides a stacking monitoring and surplus material calculation method with multi-dimensional data linkage processing. Through comprehensive analysis of multi-dimensional data, this stacking monitoring and surplus material calculation method can achieve accurate monitoring of stacked materials and efficient calculation of surplus material quantity, thereby improving the automation level and accuracy of inventory management.

[0004] The multi-dimensional data linkage processing method for stacking monitoring and surplus material calculation provided in this application includes the following steps:

[0005] S1, Environmental Assessment and Requirements Definition: Assess the storage area and, based on the assessment results, customize the sensor layout and data acquisition scheme.

[0006] S2, Sensor Network Deployment and Calibration: Deploy sensors, RFID tag readers, and 3D scanners according to the design plan. The deployment must ensure full coverage of the stacking area. After deployment, perform precise calibration of the sensors.

[0007] S3, Data Interface and Fusion Platform Construction: Develop data receiving and processing interfaces to ensure seamless access of various sensor data to the central processing system; build a data fusion platform to achieve standardized processing and integration of multi-source data and form a unified data model.

[0008] S4, 3D stacking model construction: Using 3D scanning and image recognition technology, combined with weight and size data, a 3D model of the stacked materials is dynamically constructed. The 3D model must be able to reflect changes in the stacking status in real time, including material addition, removal and position adjustment.

[0009] S5, Intelligent Analysis Algorithm Development and Testing: Develop machine learning-based intelligent analysis algorithms to predict material consumption trends, optimize stacking layout, and calculate residual material. Train and test the algorithms using historical data to continuously optimize their performance.

[0010] S6, Establishment of dynamic monitoring and anomaly detection mechanism: Implement a dynamic monitoring system to continuously track changes in stacking status, develop anomaly detection algorithms to identify safety hazards in real time and trigger early warning mechanisms;

[0011] S7, Calculation and Optimization Suggestion Generation for Residual Material: Combining the real-time stacking model and material attributes, the system performs detailed calculations of residual material, providing accurate information on the amount of material remaining. Based on the calculation results, the system automatically generates stacking optimization suggestions to guide inventory management and space utilization.

[0012] S8, System Integration and On-site Debugging: Integrate all modules into a unified management system, perform on-site installation and debugging to ensure smooth operation of the entire system and timely and accurate data processing and feedback.

[0013] In an alternative approach, step S2 can employ a genetic algorithm to optimize sensor placement during sensor deployment, as briefly described below:

[0014] ;

[0015] In the formula, For the fitness function, The coverage ratio is used to measure the completeness of the monitoring range. For total cost, This is a redundancy index. , ,and These are weighting factors adjusted based on actual circumstances. Reflecting economic considerations, This ensures system reliability; through iterative optimization, the optimal sensor deployment strategy is found.

[0016] During deployment, the data acquisition frequency and accuracy requirements of various sensors are dynamically adjusted by intelligent algorithms. A Kalman filter is used to fuse and reduce noise in the sensor data. The simplified formula is as follows:

[0017] ;

[0018] ;

[0019] ;

[0020] ;

[0021] ;

[0022] In the formula, represent State estimation at time 10:00 for Time-varying covariance matrix for Kalman gain at time step and It is the system transition matrix. and These are the covariance matrices of process noise and measurement noise, respectively. For measured values, This is the observation model matrix.

[0023] In one alternative, in step S2, the deployed sensor includes a weight sensor, which is installed on the support structure or handling equipment to directly measure the weight change of the stacked material.

[0024] RFID tag readers can attach RFID tags to each batch or important individual material. Fixed or mobile readers can be deployed at the entrance and exit channels and the edge of the stacking area to realize material identification and location tracking. The reading range and recognition rate can be tested, and the antenna angle and power can be adjusted to ensure stable reading of all tags within the specified area.

[0025] 3D scanners can periodically or on demand scan stacked areas to build and update three-dimensional models of stacked materials, accurately recording their shape, volume, and stacking structure.

[0026] In one alternative approach, step S3 specifically includes the following steps:

[0027] Design and implement a data receiving service, employing a high-concurrency processing framework to ensure low-latency data transmission and buffering;

[0028] The received data undergoes preliminary cleaning and format verification to remove invalid or erroneous data. If a measurement value outside the normal range is detected, it is processed using data smoothing or outlier detection algorithms.

[0029] Standardize the preprocessed data to ensure that data from different sensors are comparable under the same unit of measurement;

[0030] By employing a data fusion algorithm that integrates time series analysis and spatial information, a comprehensive and accurate description of the stacked materials is generated. For the fusion of stack height and weight, the following weighted fusion formula can be used:

[0031] ;

[0032] In the formula, For the integrated comprehensive indicators, and These are measurements of height and weight, respectively. and These are weighting coefficients set according to the application scenario.

[0033] In one alternative approach, step S4 specifically includes the following steps:

[0034] The stacking area is scanned regularly or as needed to obtain three-dimensional point cloud data of the material stacking. High-resolution cameras are used in conjunction with image recognition algorithms to identify material types, boundaries and identification information, thereby enhancing the detail accuracy of the model.

[0035] By integrating material location information read from weight sensors and RFID tags, as well as data from environmental sensors, a comprehensive database of material properties is formed.

[0036] The original point cloud data is denoised and downsampled, and then converted into a triangular mesh model through a 3D reconstruction algorithm to form a preliminary 3D stacking model.

[0037] Based on image recognition technology, each batch or single piece of material is identified, and combined with RFID tag data, the correct material properties and weight information are assigned to model elements.

[0038] The real-time data from the weight sensor is correlated with the materials in the model, and the model is adjusted in real time through interpolation or shape deformation algorithms to ensure that the model can reflect the weight changes, additions, removals and position adjustments of the stacked materials.

[0039] Based on the dynamically updated 3D model, mechanical analysis algorithms are applied to evaluate the stability of the stacking structure, calculate parameters such as center of gravity offset and stacking pressure distribution, and compare them with preset safety thresholds. When the threshold is exceeded, an early warning is triggered.

[0040] The dynamically updated 3D model is displayed through a graphical user interface and allows for interactive browsing.

[0041] In one alternative embodiment, step S5 specifically includes the following steps:

[0042] Cross-validation was used to evaluate the model's generalization ability, and hyperparameter tuning was performed using grid search and random search methods to find the optimal model configuration. The model formula for predicting material consumption trends can be abstractly expressed as follows:

[0043] ;

[0044] ;

[0045] In the formula, In hidden state, For the current input, , This is the weight matrix. , For bias terms, , The activation function is used to adjust its parameters through backpropagation and optimization algorithms.

[0046] In one alternative embodiment, step S6 specifically includes the following steps:

[0047] Thresholds are set based on the normal state of material stacking. Any situation exceeding these thresholds is considered abnormal. Supervised or unsupervised learning algorithms are used to train a model on historical data to identify normal and abnormal patterns. Combining 3D model data, weight data, and environmental parameters, a multimodal anomaly detection method is used to comprehensively judge the abnormal state and improve the detection accuracy.

[0048] Threshold Setting and Dynamic Adjustment: Based on historical data and business logic, early warning thresholds for key indicators are set. An adaptive threshold algorithm is used to automatically adjust the thresholds according to real-time supply and demand changes, avoiding false alarms and missed alarms. The conditions for triggering an early warning are as follows:

[0049] ;

[0050] In the formula, This indicates the current indicator value; Indicates the historical average; Indicates standard deviation; Indicates the threshold coefficient;

[0051] Anomaly detection algorithm: Introduces machine learning methods to perform real-time analysis of data streams, identify abnormal changes in stacking patterns, and issue early warning signals in a timely manner;

[0052] Anomaly score in model output Represented as: ;

[0053] In the formula, This is the prediction function of the anomaly detection model. Given the input feature vector, the higher the output anomaly score, the more the current state deviates from the normal pattern.

[0054] In one alternative approach, step S7 specifically includes the following steps:

[0055] Real-time stacking model update: Based on the latest stacking status data obtained from the dynamic monitoring system, including stacking length, width, depth, and the distribution of materials in each layer, the 3D stacking model is updated. If this process involves 3D reconstruction, ray casting or voxelization algorithms are used for 3D reconstruction. The simplified formula is as follows:

[0056] ;

[0057] In the formula, Indicates the stacking volume. This represents the length of the i-th layer. Indicates the width of the i-th layer. Indicates the height of the i-th layer;

[0058] Precise calculation of remaining materials: By applying density mapping technology and volumetric weight conversion, and combining the density information of each material, the total volume and weight of the remaining materials are accurately calculated. The calculation formula is as follows:

[0059] ;

[0060] In the formula, Indicates the weight of the remaining material; Indicates the stacking volume; The average density is calculated by considering the average mixing value of the materials in the stockpile. This represents the cumulative weight of materials removed from the initial state to the current time point.

[0061] In one alternative approach, the algorithm for generating stacking optimization suggestions in step S7 includes:

[0062] Maximizing space utilization: Using heuristic algorithms such as genetic algorithms or particle swarm optimization, the optimal stacking layout is searched for based on the current stacking state and remaining materials. The objective function can be defined as minimizing the unused space volume, while also considering the ease of material retrieval. The simplified formula is as follows:

[0063] ;

[0064] In the formula, Let be the objective function. This represents the total free volume. As an adjustment factor, it balances space utilization and operational efficiency. For ease of operation;

[0065] Inventory Management Recommendations: Based on the surplus material calculation results, use predictive models to analyze future demand trends and provide replenishment or allocation suggestions to reduce inventory costs. The formula is as follows:

[0066] ;

[0067] In the formula, Indicates the replenishment quantity. This indicates the predicted demand. This indicates the current remaining material quantity. The safety stock factor reflects the need to buffer against market fluctuations. This indicates the safety stock level.

[0068] In one alternative approach, step S1, assessing the storage area, includes: measuring the dimensions of the storage area, assessing the ground's load-bearing capacity, analyzing lighting conditions, and considering ventilation and fire protection requirements; meticulously classifying the types of materials, recording the physical and chemical properties of each material, and ensuring the targeted and safe implementation of subsequent management measures.

[0069] The requirements definition includes: covering basic inventory tracking and safety management, while also delving into advanced goals such as improving operational efficiency, energy conservation and emission reduction, and cost control; if flammable materials are stored, the system needs to be highly sensitive to changes in temperature and humidity; if the materials are time-sensitive, the focus is on automating the first-in, first-out (FIFO) principle.

[0070] The beneficial effects of this application are as follows:

[0071] The stacking monitoring and surplus material calculation method in this application integrates sensors, RFID technology, 3D scanning, and data analysis algorithms to achieve comprehensive and refined management of material stacking. It can automatically monitor the stacking status of materials, calculate surplus material in real time, predict demand trends, and propose stacking layout adjustments based on optimization algorithms, effectively avoiding overloading, reducing space waste, and enhancing safety and response speed.

[0072] It should be understood that the foregoing general description and the following detailed description are merely illustrative and are not restrictive of the present application. Attached Figure Description

[0073] Figure 1 This is a flowchart illustrating the stacking monitoring and surplus material calculation method provided in this application.

[0074] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. Detailed Implementation

[0075] To better understand the technical solution of this application, the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0076] It should be understood that the described embodiments are merely some, not all, of the embodiments in this application. All other embodiments obtained by those skilled in the art based on the embodiments in this application without inventive effort are within the scope of protection of this application.

[0077] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. The singular forms “a,” “the,” and “the” used in the embodiments of this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0078] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0079] like Figure 1 As shown, this application provides a multi-dimensional data linkage processing method for stacking monitoring and surplus material calculation, which includes the following steps:

[0080] S1, Environmental Assessment and Requirements Definition: Assess the storage area and, based on the assessment results, customize the sensor layout and data acquisition scheme.

[0081] Specifically, this step begins with a thorough environmental assessment. This detailed and systematic process aims to comprehensively understand the specific conditions of the storage area, including, but not limited to, measuring the dimensions of the storage area, assessing the ground's load-bearing capacity, analyzing lighting conditions, and considering ventilation and fire protection requirements. Simultaneously, the materials are meticulously categorized, and the physical properties (such as density, shape, stacking stability, and flammability / explosiveness) and chemical properties (such as corrosivity and reactivity) of each material are recorded to ensure the appropriateness and safety of subsequent management measures.

[0082] Based on this information, requirements are defined. Requirements analysis not only covers basic inventory tracking and safety management, but also delves into advanced goals such as improving operational efficiency, energy conservation and emission reduction, and cost control. For example, if flammable materials are stored, the system needs to be highly sensitive to changes in temperature and humidity; if the materials are time-sensitive, the automated execution of the first-in, first-out principle needs to be considered.

[0083] S2, Sensor Network Deployment and Calibration: Deploy sensors, RFID tag readers, and 3D scanners according to the design plan. The deployment must ensure full coverage of the stacking area. After deployment, perform precise calibration of the sensors.

[0084] Specifically, this stage introduces the design concept of intelligent early warning algorithms to ensure efficient and accurate data collection. The sensor deployment strategy combines coverage, detection accuracy, and cost-effectiveness analysis, employing optimization algorithms to determine the optimal deployment scheme. For example, a Genetic Algorithm (GA) can be used to optimize sensor placement, with the objective function potentially including minimizing blind spots and maximizing information acquisition efficiency. The GA formula is briefly described below:

[0085] ;

[0086] In the formula, For the fitness function, The coverage ratio is used to measure the completeness of the monitoring range. For total cost, This is a redundancy index. , ,and These are weighting factors adjusted based on actual circumstances. Reflecting economic considerations, This ensures the reliability of the system; through iterative optimization, the optimal sensor deployment strategy is found.

[0087] In this step, the deployment and calibration of the sensor network are fundamental to ensuring the efficient operation of the system. The deployment process requires meticulous planning. Based on the environmental assessment and requirements definition results from the first step, appropriate sensor types and quantities should be selected and scientifically distributed at key locations within the stacking area. The specific deployment is as follows:

[0088] 1. Weight Sensors: Installed on the supporting structure or handling equipment, these sensors directly measure changes in the weight of the stacked materials. For dynamically stacked areas, ensure that the sensor layout covers all possible loading and unloading points.

[0089] Calibration was performed using a standard with known mass. The zero-point offset under no-load conditions and the linearity, repeatability, and other indicators after loading were recorded. The least squares method was used for linear fitting correction.

[0090] ;

[0091] In the formula, For measured values, For the true value, The slope The intercept is used to adjust the correction coefficients through fitting.

[0092] 2. RFID Tags and Readers: Attach RFID tags to each batch or important individual material, and deploy fixed or mobile readers at the entrance and exit channels and the edges of the stacking area to achieve material identification and location tracking.

[0093] Test the reading range and recognition rate, and adjust the antenna angle and power to ensure stable reading of all tags within the specified area.

[0094] 3. 3D Scanner: Using a fixed or drone-mounted 3D laser scanner, the stacking area is scanned periodically or as needed to build and update a three-dimensional model of the stacked materials, accurately recording their shape, volume, and stacking structure.

[0095] Spatial calibration is performed using standard geometry, and the scanned data and model data are registered using the Iterative Closest Point (ICP) algorithm to eliminate systematic biases and ensure the accuracy of 3D reconstruction.

[0096] The data acquisition solution is customized based on material characteristics and management needs, integrating multiple technologies such as weight sensors, RFID tags, infrared thermal imagers, and 3D scanners. The data acquisition frequency and accuracy requirements for each type of sensor are dynamically adjusted by intelligent algorithms to ensure that monitoring needs are met while minimizing unnecessary resource consumption. For example, a Kalman filter is used to fuse and reduce noise in the sensor data; the simplified formula is as follows:

[0097] ;

[0098] ;

[0099] ;

[0100] ;

[0101] ;

[0102] In the formula, represent State estimation at time 10:00 for Time-varying covariance matrix for Kalman gain at time step and It is the system transition matrix. and These are the covariance matrices of process noise and measurement noise, respectively. For measured values, This represents the observation model matrix. This algorithm can accurately estimate material states even in noisy environments, laying a solid foundation for subsequent intelligent early warning and decision support.

[0103] S3, Data Interface and Fusion Platform Construction: Develop data receiving and processing interfaces to ensure seamless access of various sensor data to the central processing system; build a data fusion platform to achieve standardized processing and integration of multi-source data and form a unified data model.

[0104] In this step, the establishment of the data interface and fusion platform is a crucial step in achieving multi-dimensional data linkage processing. It ensures that the large amounts of heterogeneous data collected from different sensors can be efficiently integrated, processed, and transformed into valuable information that can be used for stockpiling monitoring and surplus material calculation. Specific implementation details are as follows:

[0105] Define a common data transmission protocol (such as MQTT, HTTP / RESTful, etc.) for all sensors to ensure consistency in data format and communication method. The output data of each sensor is encapsulated in the format specified by the protocol, including basic information such as timestamp, sensor ID, and measurement value.

[0106] Design and implement a data receiving service that monitors sensor data streams and employs high-concurrency processing frameworks (such as Apache Kafka and RabbitMQ) to ensure low-latency data transmission and buffering, preventing data loss or congestion.

[0107] The received data undergoes preliminary cleaning and format verification to remove invalid or erroneous data. If a measurement value outside the normal range is detected, it is processed using data smoothing or outlier detection algorithms (such as Grubbs' Test).

[0108] The preprocessed data is standardized to ensure that data from different sensors are comparable under the same unit of measurement. For example, weight data is standardized to tons, location coordinates are unified to the same coordinate system, and timestamps are synchronized to the server time.

[0109] Data fusion algorithms, such as weighted averaging, Kalman filtering, or deep learning fusion networks, are employed to integrate time series analysis and spatial information, resulting in a comprehensive and accurate description of stacked materials. For example, the following simple weighted fusion formula can be used to fuse stack height and weight:

[0110] ;

[0111] In the formula, For the integrated comprehensive indicators, and These are measurements of height and weight, respectively. and These are weighting coefficients set according to the application scenario.

[0112] Based on the fused data, a three-dimensional stacking model is constructed, and a dynamically updated material stacking database is formed by combining material attributes (such as density and stacking limits). The model includes not only static stacking layout, but also dynamically changing information such as remaining material quantity and stacking safety status, providing a foundation for subsequent intelligent analysis.

[0113] S4, 3D stacking model construction: Using 3D scanning and image recognition technology, combined with weight and size data, a 3D model of the stacked materials is dynamically constructed. The 3D model must be able to reflect changes in the stacking status in real time, including material addition, removal and position adjustment.

[0114] Specifically, in the process of constructing the three-dimensional stacking model, 3D scanning, image recognition technology, and real-time sensor data are comprehensively used to dynamically reproduce the actual situation of the stacking site, enabling precise management and early warning response of the stacked materials. The specific implementation details are as follows:

[0115] Fixed or mobile 3D laser scanners are used to scan the stacking area periodically or as needed to obtain three-dimensional point cloud data of the material stacking; at the same time, high-resolution cameras are used in conjunction with image recognition algorithms to identify material types, boundaries and marking information, thereby enhancing the detail accuracy of the model.

[0116] By integrating material location information from weight sensors and RFID tags, along with data from environmental sensors, a comprehensive database of material properties is created. This data serves as a crucial supplement to the model, ensuring that the model's physical properties match the actual situation. Point cloud processing algorithms (such as Voxel Grid Downsampling and Statistical Outlier Removal from the PCL library) are used to denoise and downsample the original point cloud data. Then, 3D reconstruction algorithms (such as the Marching Cubes algorithm for surface reconstruction) are applied to convert it into a triangular mesh model, forming a preliminary 3D stacking model.

[0117] Based on image recognition technology, each batch or individual material is identified. Combined with RFID tag data, the correct material properties and weight information are assigned to each model element. Real-time data from weight sensors is correlated with the materials in the model, and the model is adjusted in real time through interpolation or shape deformation algorithms (such as Free-Form Deformation, FFD) to ensure that the model can reflect changes in the weight, addition, removal, and repositioning of stacked materials.

[0118] Based on a dynamically updated 3D model, mechanical analysis algorithms (such as finite element analysis, FEM) are applied to evaluate the stability of the stacking structure, calculate parameters such as center of gravity offset and stacking pressure distribution, and compare them with preset safety thresholds. When the threshold is exceeded, an early warning is triggered.

[0119] A fuzzy logic controller (FLC) is used to assess the stacking risk level. Fuzzy sets and membership functions are set based on factors such as stacking height, weight distribution, and support conditions. The risk level is output through fuzzy rule inference. Example formula:

[0120] ;

[0121] In the formula, Represents the fuzzy membership function. Risk level, , , These represent input variables such as stacking height, weight distribution uniformity, and support stability.

[0122] The dynamically updated 3D model is displayed through a graphical user interface, using technologies such as OpenGL or Unity for interactive browsing. Users can rotate and zoom the model to view stacking details and warning information. When the intelligent warning algorithm identifies a potential risk, the system not only provides visual (e.g., color-coded unstable areas) and audible (alarm sounds) alerts, but also provides detailed explanations of the warning reasons and suggested measures through interface pop-ups, supporting real-time user intervention.

[0123] S5, Intelligent Analysis Algorithm Development and Testing: Develop machine learning-based intelligent analysis algorithms to predict material consumption trends, optimize stacking layout, and calculate surplus material. Train and test the algorithms using historical data to continuously optimize their performance.

[0124] In this step, we will delve into the development and testing process of machine learning-based intelligent analysis algorithms, with a particular emphasis on how these algorithms can predict material consumption trends, optimize stacking layouts, and accurately calculate surplus material quantities. At the same time, we will continuously optimize algorithm performance using historical data to ensure the accuracy and effectiveness of intelligent early warnings.

[0125] Based on the requirements, select appropriate machine learning models, such as time series analysis (ARIMA, LSTM), cluster analysis (K-means, DBSCAN), regression analysis (random forest, gradient boosting tree), optimization algorithms (genetic algorithm, particle swarm optimization), etc.

[0126] Based on business understanding, key features that aid in prediction and optimization are extracted, such as daily consumption, stacking density, material category, and seasonality. Appropriate machine learning models are built using Python libraries such as scikit-learn, TensorFlow, and PyTorch, depending on the chosen library.

[0127] Cross-validation (such as K-fold cross-validation) is used to evaluate the model's generalization ability, and hyperparameter tuning is performed using methods such as grid search and random search to find the optimal model configuration. Taking LSTM as an example to predict material consumption trends, the model formula can be abstractly expressed as:

[0128] ;

[0129] ;

[0130] In the formula, In hidden state, For the current input, , This is the weight matrix. , For bias terms, , The activation function is adjusted using backpropagation and optimization algorithms such as Adam.

[0131] S6. Establishment of dynamic monitoring and anomaly detection mechanism: Implement a dynamic monitoring system to continuously track changes in stacking status, develop anomaly detection algorithms to identify safety hazards in real time and trigger early warning mechanisms.

[0132] In this step, dynamic monitoring and anomaly detection mechanisms are crucial to ensuring the safe and efficient operation of the stacking system. Through real-time data acquisition and intelligent algorithm analysis, the system can quickly identify potential risks and take action. Specific implementation details are as follows:

[0133] Thresholds are set based on the normal stacking conditions of materials, such as maximum load capacity and tilt angle thresholds. Any situation exceeding these thresholds is considered abnormal. Supervised or unsupervised learning algorithms, such as One-Class SVM, IsolationForest, or Autoencoder, are used to train a model on historical data to identify normal and abnormal patterns. An example of anomaly score calculation formula (using One-Class SVM as an example):

[0134] ;

[0135] In the formula, For the input data points, Represents support vectors, This represents the distance from the data point to the support vector. A higher anomaly score indicates that the data point deviates more from the normal range, and an alert is triggered when the score reaches a preset threshold.

[0136] By combining 3D model data, weight data, environmental parameters, and other data, a multimodal anomaly detection method, such as a deep neural network fusion model, is adopted to comprehensively judge the abnormal state and improve the detection accuracy.

[0137] Threshold setting and dynamic adjustment: Based on historical data and business logic, early warning thresholds are set for key indicators such as material inventory and stacking safety factor. An adaptive threshold algorithm is adopted to automatically adjust the thresholds according to real-time supply and demand changes, avoiding false alarms and missed alarms.

[0138] The conditions for triggering the warning are:

[0139] ;

[0140] In the formula, This indicates the current indicator value. Indicates the historical average. Indicates standard deviation, This represents the threshold coefficient.

[0141] Anomaly detection algorithm: Introduce machine learning methods, such as Isolation Forest or One-Class SVM, to perform real-time analysis of the data stream, identify abnormal changes in stacking patterns, and issue early warning signals in a timely manner.

[0142] ;

[0143] In the formula, This is the prediction function of the anomaly detection model. The input feature vector, This is the anomaly score output by the model. The higher the anomaly score, the more the current state deviates from the normal pattern.

[0144] S7, Calculation and Optimization Suggestion Generation for Residual Material: Combining the real-time stacking model with material attributes, the system performs detailed calculations of residual material, providing accurate information on the remaining amount of material. Based on the calculation results, the system automatically generates stacking optimization suggestions to guide inventory management and space utilization.

[0145] In this step, the system utilizes advanced algorithms to perform in-depth analysis of real-time stacking data to achieve accurate calculation of remaining material and propose efficient stacking optimization suggestions. The specific operation process is as follows:

[0146] 1. Real-time Stacking Model Update: First, based on the latest stacking status data obtained from the dynamic monitoring system, including but not limited to stacking length, width, depth, and the distribution of materials in each layer, the 3D stacking model is updated. This process may involve 3D reconstruction techniques, using algorithms such as ray casting or voxelization. The simplified formula is as follows:

[0147] ;

[0148] In the formula, Indicates the stacking volume. This represents the length of the i-th layer. Indicates the width of the i-th layer. This represents the height of the i-th layer.

[0149] 2. Precise Calculation of Residual Material: Applying density mapping technology and volumetric weight conversion, combined with the density information of each material, the total volume and weight of the remaining material are accurately calculated. The calculation formula is as follows:

[0150]

[0151] In the formula, Indicates the weight of remaining material. Indicates the stacking volume. The average density is calculated by considering the average mixing value of the materials in the stockpile; while This represents the cumulative weight of materials removed from the initial state to the current time point.

[0152] 3. Optimization Suggestion Generation Algorithm: Maximizing Space Utilization: Using heuristic algorithms such as genetic algorithms or particle swarm optimization (PSO), the optimal stacking layout is searched based on the current stacking state and remaining materials. The objective function may be defined as minimizing the unused space volume while considering the ease of material retrieval. The simplified formula is as follows:

[0153] ;

[0154] In the formula, Let be the objective function. This represents the total free volume. As an adjustment factor, it balances space utilization and operational efficiency; For ease of operation.

[0155] Inventory Management Recommendations: Based on the surplus material calculation results, use predictive models (such as ARIMA, Random Forest) to analyze future demand trends and provide replenishment or allocation suggestions to reduce inventory costs. Example formula:

[0156] ;

[0157] In the formula, Indicates the replenishment quantity. This indicates the predicted demand. This indicates the current remaining material quantity. The safety stock factor reflects the need to buffer against market fluctuations. This indicates the safety stock level.

[0158] S8, System Integration and On-site Debugging: Integrate all modules into a unified management system, perform on-site installation and debugging to ensure smooth system operation and timely and accurate data processing and feedback. Run the system officially, continuously collect feedback data, and monitor system performance. Based on performance in actual applications, continuously adjust algorithm parameters and optimize data processing flows to improve the overall system accuracy and usability. Simultaneously, establish a regular maintenance and upgrade mechanism to ensure long-term stable and efficient system operation.

[0159] The above are merely preferred embodiments of this application and are not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for stacking monitoring and surplus material calculation using multi-dimensional data linkage processing, characterized in that, Includes the following steps: S1, Environmental Assessment and Requirements Definition: Assess the storage area and, based on the assessment results, customize the sensor layout and data acquisition scheme. S2, Sensor Network Deployment and Calibration: Deploy sensors, RFID tag readers, and 3D scanners according to the design plan. The deployment must ensure full coverage of the stacking area. After deployment, perform precise calibration of the sensors. S3, Data Interface and Fusion Platform Construction: Develop data receiving and processing interfaces to ensure seamless access of various sensor data to the central processing system; build a data fusion platform to achieve standardized processing and integration of multi-source data and form a unified data model. S4, 3D stacking model construction: Using 3D scanning and image recognition technology, combined with weight and size data, a 3D model of the stacked materials is dynamically constructed. The 3D model must be able to reflect changes in the stacking status in real time, including material addition, removal and position adjustment. S5, Intelligent Analysis Algorithm Development and Testing: Develop machine learning-based intelligent analysis algorithms to predict material consumption trends, optimize stacking layout, and calculate residual material. Train and test the algorithms using historical data to continuously optimize their performance. S6, Establishment of dynamic monitoring and anomaly detection mechanism: Implement a dynamic monitoring system to continuously track changes in stacking status, develop anomaly detection algorithms to identify safety hazards in real time and trigger early warning mechanisms; S7, Calculation and Optimization Suggestion Generation for Residual Material: Combining the real-time stacking model and material attributes, the system performs detailed calculations of residual material, providing accurate information on the amount of material remaining. Based on the calculation results, the system automatically generates stacking optimization suggestions to guide inventory management and space utilization. S8, System Integration and On-site Debugging: Integrate all modules into a unified management system, perform on-site installation and debugging to ensure smooth operation of the entire system and timely and accurate data processing and feedback; Step S7 specifically includes the following steps: Real-time stacking model update: Based on the latest stacking status data obtained from the dynamic monitoring system, including stacking length, width, depth, and the distribution of materials in each layer, the 3D stacking model is updated. If this process involves 3D reconstruction, ray casting or voxelization algorithms are used for 3D reconstruction. The simplified formula is as follows: ； In the formula, Indicates the stacking volume. This represents the length of the i-th layer. Indicates the width of the i-th layer. Indicates the height of the i-th layer; Precise calculation of remaining materials: By applying density mapping technology and volumetric weight conversion, and combining the density information of each material, the total volume and weight of the remaining materials are accurately calculated. The calculation formula is as follows: ； In the formula, Indicates the weight of the remaining material; Indicates the stacking volume; The average density is calculated by considering the average mixing value of the materials in the stockpile. This represents the cumulative weight of materials removed from the initial state to the current time point; In step S7, the algorithm for generating stacking optimization suggestions includes: Maximizing space utilization: Using heuristic algorithms such as genetic algorithms or particle swarm optimization, the optimal stacking layout is searched for based on the current stacking state and remaining materials. The objective function can be defined as minimizing the unused space volume, while also considering the ease of material retrieval. The simplified formula is as follows: ； In the formula, Let be the objective function. This represents the total free volume. As an adjustment factor, it balances space utilization and operational efficiency. For ease of operation; Inventory Management Recommendations: Based on the surplus material calculation results, use predictive models to analyze future demand trends and provide replenishment or allocation suggestions to reduce inventory costs. The formula is as follows: ； In the formula, Indicates the replenishment quantity. This indicates the predicted demand. This indicates the current remaining material quantity. The safety stock factor reflects the need to buffer against market fluctuations. This indicates the safety stock level.

2. The stacking monitoring and surplus material calculation method for multi-dimensional data linkage processing according to claim 1, characterized in that, In step S2, a genetic algorithm can be used to optimize the sensor location during sensor deployment. The formula is briefly described below: ； In the formula, For the fitness function, The coverage ratio is used to measure the completeness of the monitoring range. For total cost, This is a redundancy index. , ,and These are weighting factors adjusted based on actual circumstances. Reflecting economic considerations, This ensures system reliability; through iterative optimization, the optimal sensor deployment strategy is found. During deployment, the data acquisition frequency and accuracy requirements of various sensors are dynamically adjusted by intelligent algorithms. A Kalman filter is used to fuse and reduce noise in the sensor data. The simplified formula is as follows: ； ； ； ； ； In the formula, represent State estimation at time 10:00 for Time-varying covariance matrix for Kalman gain at time step and It is the system transition matrix. and These are the covariance matrices of process noise and measurement noise, respectively. For measured values, This is the observation model matrix.

3. The stacking monitoring and surplus material calculation method for multi-dimensional data linkage processing according to claim 2, characterized in that, In step S2, the deployed sensors include weight sensors, which are installed on the support structure or handling equipment to directly measure the weight change of the stacked materials. RFID tag readers can attach RFID tags to each batch or important individual material. Fixed or mobile readers can be deployed at the entrance and exit channels and the edge of the stacking area to realize material identification and location tracking. The reading range and recognition rate can be tested, and the antenna angle and power can be adjusted to ensure stable reading of all tags within the specified area. 3D scanners can periodically or on demand scan stacked areas to build and update three-dimensional models of stacked materials, accurately recording their shape, volume, and stacking structure.

4. The method for stacking monitoring and surplus material calculation based on multi-dimensional data linkage processing according to any one of claims 1-3, characterized in that, Step S3 specifically includes the following steps: Design and implement a data receiving service, employing a high-concurrency processing framework to ensure low-latency data transmission and buffering; The received data undergoes preliminary cleaning and format verification to remove invalid or erroneous data. If a measurement value outside the normal range is detected, it is processed using data smoothing or outlier detection algorithms. Standardize the preprocessed data to ensure that data from different sensors are comparable under the same unit of measurement; By employing a data fusion algorithm that integrates time series analysis and spatial information, a comprehensive and accurate description of the stacked materials is generated. For the fusion of stack height and weight, the following weighted fusion formula can be used: ； In the formula, For the integrated comprehensive indicators, and These are measurements of height and weight, respectively. and These are weighting coefficients set according to the application scenario.

5. The stacking monitoring and surplus material calculation method for multi-dimensional data linkage processing according to claim 4, characterized in that, Step S4 specifically includes the following steps: The stacking area is scanned regularly or as needed to obtain three-dimensional point cloud data of the material stacking. High-resolution cameras are used in conjunction with image recognition algorithms to identify material types, boundaries and identification information, thereby enhancing the detail accuracy of the model. By integrating material location information read from weight sensors and RFID tags, as well as data from environmental sensors, a comprehensive database of material properties is formed. The original point cloud data is denoised and downsampled, and then converted into a triangular mesh model through a 3D reconstruction algorithm to form a preliminary 3D stacking model. Based on image recognition technology, each batch or single piece of material is identified, and combined with RFID tag data, the correct material properties and weight information are assigned to model elements. The real-time data from the weight sensor is correlated with the materials in the model, and the model is adjusted in real time through interpolation or shape deformation algorithms to ensure that the model can reflect the weight changes, additions, removals and position adjustments of the stacked materials. Based on the dynamically updated 3D model, mechanical analysis algorithms are applied to evaluate the stability of the stacking structure, calculate parameters such as center of gravity offset and stacking pressure distribution, and compare them with preset safety thresholds. When the threshold is exceeded, an early warning is triggered. The dynamically updated 3D model is displayed through a graphical user interface and allows for interactive browsing.

6. The stacking monitoring and surplus material calculation method for multi-dimensional data linkage processing according to claim 4, characterized in that, Step S5 specifically includes the following steps: Cross-validation was used to evaluate the model's generalization ability, and hyperparameter tuning was performed using grid search and random search methods to find the optimal model configuration. The model formula for predicting material consumption trends can be abstractly expressed as follows: ； ； In the formula, In hidden state, For the current input, , This is the weight matrix. , For bias terms, , The activation function is used to adjust its parameters through backpropagation and optimization algorithms.

7. The method for stacking monitoring and surplus material calculation based on multi-dimensional data linkage processing according to any one of claims 1-3 or 5-6, characterized in that, Step S6 specifically includes the following steps: Thresholds are set based on the normal state of material stacking. Any situation exceeding these thresholds is considered abnormal. Supervised or unsupervised learning algorithms are used to train a model on historical data to identify normal and abnormal patterns. Combining 3D model data, weight data, and environmental parameters, a multimodal anomaly detection method is used to comprehensively judge the abnormal state and improve the detection accuracy. Threshold Setting and Dynamic Adjustment: Based on historical data and business logic, early warning thresholds for key indicators are set. An adaptive threshold algorithm is used to automatically adjust the thresholds according to real-time supply and demand changes, avoiding false alarms and missed alarms. The conditions for triggering an early warning are as follows: ； In the formula, This indicates the current indicator value; Indicates the historical average; Indicates standard deviation; Indicates the threshold coefficient; Anomaly detection algorithm: Introduces machine learning methods to perform real-time analysis of data streams, identify abnormal changes in stacking patterns, and issue early warning signals in a timely manner; Anomaly score in model output Represented as: ; In the formula, This is the prediction function of the anomaly detection model. Given the input feature vector, the higher the output anomaly score, the more the current state deviates from the normal pattern.

8. The method for stacking monitoring and surplus material calculation based on multi-dimensional data linkage processing according to any one of claims 1-3 or 5-6, characterized in that, In step S1, the assessment of the storage area includes: measuring the size of the storage area, assessing the ground bearing capacity, analyzing lighting conditions, and considering ventilation and fire protection requirements; and meticulously classifying the types of materials, recording the physical and chemical properties of each material to ensure the targeted and safe nature of subsequent management measures. The requirements definition includes: covering basic inventory tracking and safety management, while also delving into advanced goals such as improving operational efficiency, energy conservation and emission reduction, and cost control; if flammable materials are stored, the system needs to be highly sensitive to changes in temperature and humidity; if the materials are time-sensitive, the focus is on automating the first-in, first-out (FIFO) principle.

Images