Intelligent cabinet industrial control data and management data fusion method

Abstract

The application provides an intelligent cabinet industrial control data and management data fusion method, and belongs to the technical field of intelligent cabinets. The intelligent cabinet industrial control data and management data fusion method comprises the following steps: data acquisition and preprocessing; data interface standardization; defining a unified data interface standard to ensure that the data of the industrial control layer (such as sensors and PLC data) and the management layer system (such as ERP and WMS) can be smoothly connected; real-time data acquisition; using IoT technology (such as the MQTT protocol) to collect the switch state, access record, environmental parameters and other control data of the intelligent cabinet in real time; defining a unified data interface standard to ensure the seamless connection of the data between the industrial control layer and the management layer system, breaking the data island, improving the data flow efficiency, and enabling the efficient integration of the real-time state of the equipment and enterprise management information.

Description

Technical Field

[0001] This invention belongs to the field of intelligent cabinet technology, specifically relating to a method for integrating industrial control data and management data of intelligent cabinets. Background Technology

[0002] Smart lockers, as automated storage and distribution devices, are widely used in various industries such as retail, logistics, and manufacturing. With the development of Internet of Things (IoT) technology, the intelligence level of smart lockers is constantly improving, but they also face challenges in data processing. Industrial control data, such as switch states, access records, and environmental parameters generated by sensors and programmable logic controllers (PLCs), is fragmented with management data provided by enterprise resource planning (ERP) systems and warehouse management systems (WMS). Industrial control data focuses on real-time equipment status monitoring, while management data focuses on inventory, orders, and user information. Insufficient integration between the two leads to inefficient decision-making and fails to fully realize the value of the data. Traditional data processing methods often analyze these two types of data independently, failing to fully utilize their potential correlations.

[0003] To address the aforementioned problems, this invention provides a composite drug screening device based on microfluidic technology. Summary of the Invention

[0004] The purpose of this invention is to provide a device for screening compound drugs using microfluidic technology, which aims to solve the problem of insufficient integration of industrial control data and management data in the prior art, overcome the limitations of low decision-making efficiency and inability to fully realize the value of data, and improve the intelligence level of smart cabinet operation by integrating and optimizing data processing processes.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] A method for fusing industrial control data and management data in intelligent cabinets includes the following steps:

[0007] Level 1: Data Acquisition and Preprocessing

[0008] Data interface standardization: Define a unified data interface standard to ensure smooth data exchange between the industrial control layer (such as sensor and PLC data) and the management layer systems (such as ERP and WMS);

[0009] Real-time data acquisition: Utilize IoT technologies (such as the MQTT protocol) to collect control data such as the smart cabinet's on / off status, access records, and environmental parameters in real time;

[0010] Management data integration: Integrate management information such as inventory information, user data, and order details from ERP and WMS, and achieve data synchronization through API interfaces or middleware;

[0011] Data preprocessing: cleaning, deduplication, format conversion, handling missing values, and data standardization to prepare for subsequent fusion;

[0012] Level Two: Application of Data Fusion Technology

[0013] Spatiotemporal data alignment: Aligning time-series control data with spatially relevant management data to ensure spatiotemporal consistency between data;

[0014] Feature extraction and mapping: Extract key features (such as usage frequency and fault warning signals) from control data and map and associate them with corresponding features in management data (such as inventory turnover rate and user preferences).

[0015] Multimodal fusion algorithm: This algorithm integrates data from different dimensions using data fusion algorithms (such as weighted average, Kalman filter, and deep learning fusion network) to form a unified data view;

[0016] Level 3: Intelligent Analysis and Decision Making

[0017] Real-time analysis and monitoring: Use real-time analysis tools to monitor the operation status of the smart cabinet and quickly respond to abnormal situations, such as automatic alarms and remote control adjustments;

[0018] Predictive maintenance: Based on fused data, predictive models are built to predict equipment failures, inventory shortages, etc., and maintenance plans and replenishment strategies are developed in advance.

[0019] Optimization strategy generation: Analyze data through machine learning algorithms to generate optimization suggestions, such as intelligent scheduling, inventory layout optimization, and user behavior analysis, to improve operational efficiency;

[0020] Level Four: Implementation and Feedback

[0021] Decision execution: Transforming analysis results into specific operational instructions, such as automatically adjusting inventory levels and optimizing the user interface;

[0022] Effectiveness evaluation and feedback: Regularly evaluate the effectiveness of the data fusion strategy, monitor system performance through KPIs (Key Performance Indicators), collect user feedback, and continuously optimize data fusion methods and strategies.

[0023] Compared with the prior art, the beneficial effects of the present invention are:

[0024] 1. This solution ensures seamless data integration between the industrial control layer and the management layer by defining a unified data interface standard. This breaks down data silos, improves data flow efficiency, and enables efficient integration of real-time equipment status and enterprise management information. It utilizes IoT technologies (such as the MQTT protocol) to collect control data in real time and integrates management information from ERP, WMS, and other systems, achieving instant data synchronization. This provides a data foundation for rapid response to market changes and customer needs. Preprocessing steps such as cleaning, deduplication, and format conversion improve data quality and usability, laying a solid foundation for subsequent analysis. The application of advanced denoising algorithms further enhances data purity and ensures the accuracy of analysis results.

[0025] 2. In this solution, precise alignment of time-series control data and spatial management data ensures spatiotemporal consistency in analysis, facilitating the discovery of more complex data relationships. The introduction of feature extraction and mapping techniques enables the effective correlation of key information extracted from different data sources, deepening the understanding of business scenarios. Employing multiple data fusion algorithms, such as weighted average, Kalman filtering, and deep learning networks, integrates data from different dimensions to form a unified data view. This not only enhances the depth and breadth of data fusion but also strengthens the model's ability to learn complex data patterns. Through real-time monitoring and analysis, combined with predictive maintenance models, issues such as equipment failures and inventory shortages can be detected and addressed in advance, reducing operational risks. Optimization strategies, such as intelligent scheduling and inventory layout optimization, significantly improve overall operational efficiency and enhance user experience. Attached Figure Description

[0026] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0027] Figure 1 This is a flowchart illustrating the process distribution of the intelligent cabinet industrial control data and management data fusion method of the present invention. Detailed Implementation

[0028] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0029] Example 1

[0030] Please see Figure 1 The present invention provides the following technical solutions:

[0031] A method for fusing industrial control data and management data in intelligent cabinets includes the following steps:

[0032] Level 1: Data Acquisition and Preprocessing

[0033] Data interface standardization: Define a unified data interface standard to ensure smooth data exchange between the industrial control layer (such as sensor and PLC data) and the management layer systems (such as ERP and WMS);

[0034] Real-time data acquisition: Utilize IoT technologies (such as the MQTT protocol) to collect control data such as the smart cabinet's on / off status, access records, and environmental parameters in real time;

[0035] Management data integration: Integrate management information such as inventory information, user data, and order details from ERP and WMS, and achieve data synchronization through API interfaces or middleware;

[0036] Data preprocessing: cleaning, deduplication, format conversion, handling missing values, and data standardization to prepare for subsequent fusion;

[0037] Level Two: Application of Data Fusion Technology

[0038] Spatiotemporal data alignment: Aligning time-series control data with spatially relevant management data to ensure spatiotemporal consistency between data;

[0039] Feature extraction and mapping: Extract key features (such as usage frequency and fault warning signals) from control data and map and associate them with corresponding features in management data (such as inventory turnover rate and user preferences).

[0040] Multimodal fusion algorithm: This algorithm integrates data from different dimensions using data fusion algorithms (such as weighted average, Kalman filter, and deep learning fusion network) to form a unified data view;

[0041] Level 3: Intelligent Analysis and Decision Making

[0042] Real-time analysis and monitoring: Use real-time analysis tools to monitor the operation status of the smart cabinet and quickly respond to abnormal situations, such as automatic alarms and remote control adjustments;

[0043] Predictive maintenance: Based on fused data, predictive models are built to predict equipment failures, inventory shortages, etc., and maintenance plans and replenishment strategies are developed in advance.

[0044] Optimization strategy generation: Analyze data through machine learning algorithms to generate optimization suggestions, such as intelligent scheduling, inventory layout optimization, and user behavior analysis, to improve operational efficiency;

[0045] Level Four: Implementation and Feedback

[0046] Decision execution: Transforming analysis results into specific operational instructions, such as automatically adjusting inventory levels and optimizing the user interface;

[0047] Effectiveness evaluation and feedback: Regularly evaluate the effectiveness of the data fusion strategy, monitor system performance through KPIs (Key Performance Indicators), collect user feedback, and continuously optimize data fusion methods and strategies.

[0048] In this embodiment: Level 1: In-depth explanation of data acquisition and preprocessing:

[0049] Data interface standardization:

[0050] Protocol selection and customization: In addition to defining common data exchange formats (such as JSON, XML), customized protocols may be required for specific scenarios to ensure that the protocol can effectively support the real-time control commands and status feedback of the smart cabinet, while being compatible with the business logic of ERP / WMS;

[0051] Security mechanisms: Encryption and authentication mechanisms, such as TLS / SSL, are added during data transmission to ensure data security and integrity;

[0052] Real-time data acquisition:

[0053] Edge computing: Deploy lightweight edge computing devices at the smart cabinet to perform preliminary data processing and filtering, reduce data transmission volume, and improve response speed;

[0054] Anomaly detection: Anomaly detection algorithms are integrated into the data acquisition process to promptly identify and mark abnormal data, reducing the burden of subsequent processing;

[0055] Management data integration:

[0056] Data lake architecture: Build a data lake to store various types of raw data, and use metadata management to make the data source, format and meaning transparent and traceable, which facilitates later analysis;

[0057] Data virtualization: Through data virtualization technology, a unified data access layer is provided for upper-layer applications, without needing to care about the specific storage location and format of the underlying data;

[0058] Data preprocessing:

[0059] Advanced denoising algorithms: Employ more advanced denoising algorithms (such as wavelet transform and adaptive filters) to remove and manage noise in control data, thereby improving data quality;

[0060] Feature engineering: Deep feature extraction of data, including periodic pattern recognition and trend analysis, to provide richer input for fusion algorithms;

[0061] Level Two: In-depth explanation of the application of data fusion technology:

[0062] Spatiotemporal data alignment:

[0063] Event-driven synchronization: Utilizing an event-driven model, when a key event is triggered (such as product retrieval or inventory reaching a threshold), the data synchronization process is automatically triggered to ensure the timeliness and consistency of the data;

[0064] Spatiotemporal index: Construct a spatiotemporal index structure to quickly locate and associate control and management data within a specific time and space, facilitating in-depth analysis;

[0065] Feature extraction and mapping:

[0066] Deep feature learning: Using deep learning models (such as Autoencoder and Transformer) to automatically extract high-order features that can better express the complex relationships between data;

[0067] Heterogeneous data fusion framework: Design a flexible framework that can handle different types of data (such as numerical, categorical, and time series data) and achieve effective mapping of cross-modal features;

[0068] Multimodal fusion algorithm:

[0069] Adaptive fusion strategy: Dynamically adjust the weight allocation of the fusion algorithm according to the characteristics of the data stream. For example, when device anomalies occur frequently, increase the fusion weight of control data.

[0070] Deep Neural Network Fusion: Using deep neural networks (such as multilayer perceptrons and attention mechanisms) for data fusion can not only integrate multi-source data, but also learn deeper-level correlation patterns, thereby improving the accuracy of prediction and decision-making.

[0071] Additional considerations:

[0072] Feedback loop and continuous optimization: Establish a closed-loop feedback mechanism to feed the integrated data analysis results back into the control strategy of the smart cabinet, forming a continuous iterative optimization process;

[0073] Visualization and Interaction: Develop user-friendly data visualization interfaces so that managers can intuitively understand the analysis results of integrated data and improve decision-making efficiency;

[0074] Level 3: Further Expansion of Intelligent Analysis and Decision-Making:

[0075] Real-time analysis and monitoring:

[0076] Dynamic threshold setting: Combine historical data and current operating conditions to dynamically set monitoring thresholds to adapt to operational needs in different time periods or under special conditions;

[0077] Root cause analysis: When an anomaly occurs, causal inference and association rule mining techniques are used to quickly locate the source of the problem and assist decision-makers in taking targeted measures.

[0078] Predictive maintenance:

[0079] Hybrid prediction models combine traditional statistical methods (such as ARIMA) with deep learning models (such as LSTM and GRU) to improve prediction accuracy and cover short-term fluctuations and long-term trends.

[0080] Health Index Construction: Based on multi-dimensional data, an equipment health index is constructed to quantify the equipment status and provide an intuitive basis for preventive maintenance;

[0081] Optimization strategy generation:

[0082] Reinforcement learning applications: Reinforcement learning algorithms are applied in fields such as inventory scheduling and user recommendation, allowing the system to learn from its environment and continuously optimize its strategies.

[0083] Collaborative optimization: Considering the overall collaboration between upstream and downstream of the supply chain, improve overall operational efficiency through cross-system data sharing and joint optimization models;

[0084] Level Four: In-depth Practice of Implementation and Feedback

[0085] Decision execution:

[0086] Automated workflows: Build an event-based automated workflow management system to ensure that analysis results can quickly trigger predetermined operation processes and reduce manual intervention;

[0087] Flexible configuration and testing: Provides an easy-to-configure decision execution platform, allowing for rapid adjustment of strategies based on actual conditions and preliminary testing and verification on a small scale;

[0088] Effect evaluation and feedback:

[0089] A / B testing: Conduct A / B testing to compare the actual effects of different data fusion strategies or optimization schemes to ensure the scientific and effective nature of decision-making;

[0090] Closed-loop feedback system: Establish a comprehensive closed-loop feedback mechanism, including data feedback, user feedback collection, and monitoring of changes in the external environment, to continuously iterate and optimize models and strategies in a data-driven manner;

[0091] Continuous learning and adaptation: Utilizing online learning technology, the system continuously absorbs new data during operation, automatically adjusts model parameters, adapts to market changes and business development, and maintains forward-looking and flexible decision-making.

[0092] Through the aforementioned in-depth practices, the operation of smart cabinets will achieve a high degree of intelligence and autonomy, which will not only effectively improve efficiency and user experience, but also significantly enhance the stability and resilience of the system, providing strong support for enterprises' digital transformation and intelligent upgrading.

[0093] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are 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 can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for integrating industrial control data and management data in intelligent cabinets, characterized in that, It includes the following steps: Level 1: Data Acquisition and Preprocessing Data interface standardization: Define a unified data interface standard to ensure smooth data exchange between the industrial control layer (such as sensor and PLC data) and the management layer systems (such as ERP and WMS); Real-time data acquisition: Utilize IoT technologies (such as the MQTT protocol) to collect control data such as the smart cabinet's on / off status, access records, and environmental parameters in real time; Management data integration: Integrate management information such as inventory information, user data, and order details from ERP and WMS, and achieve data synchronization through API interfaces or middleware; Data preprocessing: cleaning, deduplication, format conversion, handling missing values, and data standardization to prepare for subsequent fusion; Level Two: Application of Data Fusion Technology Spatiotemporal data alignment: Aligning time-series control data with spatially relevant management data to ensure spatiotemporal consistency between data; Feature extraction and mapping: Extract key features (such as usage frequency and fault warning signals) from control data and map and associate them with corresponding features in management data (such as inventory turnover rate and user preferences). Multimodal fusion algorithm: This algorithm integrates data from different dimensions using data fusion algorithms (such as weighted average, Kalman filter, and deep learning fusion network) to form a unified data view; Level 3: Intelligent Analysis and Decision Making Real-time analysis and monitoring: Use real-time analysis tools to monitor the operation status of the smart cabinet and quickly respond to abnormal situations, such as automatic alarms and remote control adjustments; Predictive maintenance: Based on fused data, predictive models are built to predict equipment failures, inventory shortages, etc., and maintenance plans and replenishment strategies are developed in advance. Optimization strategy generation: Analyze data through machine learning algorithms to generate optimization suggestions, such as intelligent scheduling, inventory layout optimization, and user behavior analysis, to improve operational efficiency; Level Four: Implementation and Feedback Decision execution: Transforming analysis results into specific operational instructions, such as automatically adjusting inventory levels and optimizing the user interface; Effectiveness evaluation and feedback: Regularly evaluate the effectiveness of the data fusion strategy, monitor system performance through KPIs (Key Performance Indicators), collect user feedback, and continuously optimize data fusion methods and strategies.

Images