Crane multidimensional data analysis system based on big data

Abstract

The invention discloses a crane multi-dimensional data analysis system based on big data, and relates to the technical field of crane monitoring, the crane multi-dimensional data analysis system comprises a data acquisition module, a data transmission module, a data storage module, a collaborative decision center and an analysis and application module, a full-link closed-loop architecture is formed, and the data acquisition module acquires crane mechanical, electrical and operation data, environment data and associated equipment data; the transmission module guarantees safe and real-time transmission of data through a hybrid architecture; the storage module carries out hierarchical storage on data and constructs a fault knowledge graph; the collaborative decision center integrates a data linkage analysis module; the analysis module realizes health assessment, fault root cause positioning, cross-device collaboration and adaptive optimization; and the application module performs visual display, performs multi-channel early warning and generates a decision report. The system solves the problems that traditional monitoring is isolated, fault root causes are difficult to find and the like, improves operation chain efficiency and reduces maintenance cost.

Description

Technical Field

[0001] This invention relates to the field of crane operation monitoring and data analysis technology, specifically a crane multi-dimensional data analysis system based on big data. Background Technology

[0002] As a core heavy equipment in industrial production and logistics transportation, the operational stability, efficiency, and safety performance of cranes directly determine the overall operational efficiency and cost of the production chain. With the large-scale development of the logistics industry and the increasing complexity of construction projects, traditional crane monitoring and data analysis technologies are no longer sufficient to meet the operational needs of "multi-equipment collaboration and diversified failure risks": Traditional systems only collect and analyze the mechanical and electrical parameters of a single crane, without establishing data linkage with transport vehicles and warehousing systems. This results in cranes often wasting time waiting for transport vehicles or idle cargo spaces, significantly reducing the efficiency of the overall operation chain and causing resource misallocation problems; Fault monitoring often relies on single parameter threshold judgments, which can only warn of fault phenomena but cannot trace the root cause. Maintenance personnel need to disassemble and troubleshoot on-site, which not only prolongs fault handling time and increases maintenance costs but may also cause secondary faults due to misjudgment; Health status assessment models rely on a large amount of historical fault data, making it difficult to identify new faults, and are easily affected by environmental interference such as strong winds and dust, leading to parameter distortion, frequent triggering of invalid warnings, and reducing staff's trust in warning information; Therefore, we propose a multi-dimensional data analysis system for cranes based on big data. Summary of the Invention

[0003] The purpose of this invention is to provide a crane multi-dimensional data analysis system based on big data, which solves the problems mentioned in the background art.

[0004] To achieve the above objectives, the present invention provides the following technical solution: a multi-dimensional data analysis system for cranes based on big data, characterized in that it includes a data acquisition module, a data transmission module, a big data storage module, a collaborative decision-making center, a data analysis module, and a data application module; after the data acquisition module collects data, it transmits the data to the big data storage module via the data transmission module; the collaborative decision-making center integrates the preprocessed data from the big data storage module and links with the data analysis module for analysis; the analysis results are displayed and applied through the data application module, forming a closed-loop architecture.

[0005] In a preferred embodiment of the present invention, the data acquisition module includes sensors deployed at key parts of the crane, environmental monitoring equipment in the work area, and interfaces for related equipment; the acquired data includes multi-dimensional crane operation data, environmental parameters, and related equipment data. The multi-dimensional crane operation data includes mechanical and electrical parameters, and the related equipment data includes the operation and status data of the transport vehicle and the warehousing system.

[0006] In a preferred embodiment of the present invention, the data transmission module adopts a hybrid transmission architecture that combines wireless transmission, wired transmission, and data federation; the wireless transmission uses 5G, WiFi, or Bluetooth, the wired transmission uses Ethernet or fiber optic, and the data federation channel achieves parameter sharing and encryption protection through federation learning nodes on each device; the data transmission module is equipped with a data caching and retransmission mechanism, which temporarily stores data when the network is interrupted and resumes transmission after the network is restored.

[0007] In a preferred embodiment of the present invention, the big data storage module adopts a hierarchical storage architecture, storing data on different storage media according to the data access frequency; it integrates relational databases, non-relational databases and graph databases to store structured data, unstructured data and crane fault knowledge graphs respectively; the big data storage module also includes a data preprocessing unit, which uses a distributed computing framework to perform data cleaning, deduplication, transformation and standardization.

[0008] As a preferred embodiment of the present invention, the collaborative decision-making center adopts a cloud-edge collaborative architecture. The cloud is deployed on an industrial cloud platform and managed using containerization, while the edge is deployed on the scheduling terminal of the crane and related equipment. Its functions include integrating full-dimensional data, issuing tasks to the data analysis module, pushing analysis results to the execution layer, updating the knowledge base and model parameters based on maintenance feedback, and communicating between the cloud and the edge through a lightweight Internet of Things protocol.

[0009] In a preferred embodiment of the present invention, the data analysis module includes a state assessment unit, a fault root cause localization unit, a fault early warning unit, a cross-device collaborative analysis unit, and an adaptive learning unit; the state assessment unit adopts a combined model, the fault early warning unit adopts a dual early warning mechanism, the cross-device collaborative analysis unit adopts a reinforcement learning algorithm, the fault root cause localization unit adopts parameter correlation analysis combined with knowledge graph, and the adaptive learning unit adopts a prototype network and incremental training mechanism.

[0010] As a preferred embodiment of the present invention, the workflow of the fault root cause localization unit includes: extracting multi-dimensional data before and after the fault anomaly, calculating parameter correlation, matching root causes, verifying root causes through image or maintenance detection, updating the root cause confidence of the knowledge graph, and outputting fault type, location, root cause and recommended maintenance plan.

[0011] As a preferred embodiment of the present invention, the collaborative scheduling model of the cross-device collaborative analysis unit takes the efficiency of the work chain and the equipment load as optimization objectives, generates scheduling strategies based on information such as equipment operation progress, location, and status, and adjusts the strategies in real time in combination with positioning data to avoid crane idleness; the adaptive learning unit constructs fault prototypes through small samples to identify new faults, adopts an attention mechanism to reduce environmental interference and misjudgment, and performs online updates through a lightweight model at the edge combined with manual annotation.

[0012] In a preferred embodiment of the present invention, the display unit of the data application module uses front-end technology to develop a visual interface to display the crane's real-time parameters, cross-device collaborative status, fault information, and historical data; the early warning notification unit pushes notifications through multiple channels according to the early warning level; and the decision support unit has the function of generating health status reports, fault analysis reports, and collaborative reports.

[0013] Compared with the prior art, the beneficial effects of the present invention are as follows: This invention effectively breaks down data silos between cranes, transport vehicles, and warehousing systems through a data federation and collaborative scheduling model, avoiding resource mismatch issues such as cranes waiting for transport vehicles and idle storage spaces, thus significantly improving the efficiency of the overall work chain. Relying on parameter correlation analysis and fault knowledge graph technology, it upgrades from simply issuing fault warnings to accurately locating the root cause, eliminating the need for maintenance personnel to disassemble and troubleshoot on-site, significantly shortening fault handling time, reducing maintenance costs, and preventing secondary faults caused by misjudgment of the root cause. The small-sample learning function of the adaptive learning unit can quickly identify new types of faults, while the anti-interference mechanism reduces invalid warnings caused by environmental factors such as strong winds, improving the model's generalization ability and staff's trust in the warning information. Furthermore, the hierarchical storage strategy effectively controls storage costs, and the combination of a hybrid transmission architecture with encryption mechanisms and cache retransmission functions ensures real-time data transmission, secure storage, and no data loss in network blind spots, fully meeting the reliability requirements of industrial scenarios. Attached Figure Description

[0014] Other features, objects, and advantages of the present invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings: Figure 1 This is a framework diagram of a crane multi-dimensional data analysis system based on big data according to the present invention. Detailed Implementation

[0015] To make the technical means, creative features, objectives and effects of this invention easier to understand, the invention will be further described below in conjunction with specific embodiments.

[0016] like Figure 1 As shown, a crane multi-dimensional data analysis system based on big data adopts a full-link architecture of "data acquisition-transmission-storage-collaborative decision-making-analysis-application". The core includes six functional modules: data acquisition module, data transmission module, big data storage module, collaborative decision-making center, data analysis module and data application module.

[0017] The system comprises several modules: a data acquisition module, a data processing module, and a data storage module. The data acquisition module collects mechanical, electrical, and operational data related to the crane's operation, as well as data from the working environment and related equipment such as transport vehicles and warehousing systems. The data transmission module transmits the collected data securely and stably to the storage module using a hybrid transmission method. The big data storage module preprocesses the data, stores it hierarchically according to data type and access frequency, and constructs a fault knowledge graph. The collaborative decision-making center, as the core of the system, integrates data from all dimensions, collaborates with the data analysis module to conduct analysis, and pushes the results to the execution layer. The data analysis module includes five units: status assessment, fault root cause localization, fault early warning, cross-device collaborative analysis, and adaptive learning, enabling crane health assessment, fault tracing, multi-device collaboration, and model optimization. The data application module provides operational and management support to staff through visualization, multi-channel early warning, and decision reports, forming a closed-loop operating system suitable for multi-device collaborative operation scenarios.

[0018] System Detailed Operation Process 1. Data Acquisition Phase The data acquisition module collects mechanical parameters (lifting capacity, lifting height, vibration amplitude, etc.) and electrical parameters (voltage, current, power, etc.) of the crane through sensors deployed at key parts of the crane; it also collects operational behavior data such as operation commands, operation duration, and operation videos through equipment in the control room; it collects environmental data such as temperature, humidity, wind speed, and visibility through environmental monitoring equipment in the work area; and it connects to the transport vehicle dispatching system and the warehouse management system through standard interfaces to collect real-time location, load status, and estimated arrival time of transport vehicles, as well as related equipment data such as the status of cargo locations and the progress of inventory preparation in the warehouse system, achieving comprehensive multi-dimensional data collection. 2. Data transmission stage The data transmission module employs a combined wireless and wired transmission channel. The wireless method adapts to mobile crane operation scenarios, while the wired method ensures stable transmission of core data. Simultaneously, through federated learning nodes deployed on each device, cross-device collaborative analysis and data transmission are achieved via parameter sharing, with encryption technology ensuring security. In the event of a network interruption (such as in signal blind spots during deep foundation pit operations), the transmission module's buffer unit temporarily stores the collected data. Once the network is restored, a breakpoint resumption mechanism is used to resume transmission, preventing data loss and ensuring real-time, stable data transmission to the big data storage module. 3. Data storage stage The preprocessing unit of the big data storage module cleans, deduplicates, transforms, and standardizes the transmitted data, removing invalid and abnormal data and unifying the data format. Subsequently, the data is stored in a hierarchical manner according to data type and access frequency: high-frequency access real-time data is stored on high-speed storage media, medium-frequency access short-term job data is stored on conventional hard drives, and long-term archive data is stored on low-cost storage media, reducing the overall storage cost. At the same time, different types of databases are used to store structured data (such as mechanical and electrical parameters), unstructured data (such as operation videos and environmental images), and fault knowledge graphs (including the correlation between fault phenomena, root causes, and maintenance plans), providing data support for subsequent analysis. 4. Collaborative Decision-Making and Data Analysis Phase The collaborative decision-making center integrates the preprocessed data from the storage module, synchronizes the status information of the crane, transport vehicle, and warehousing system in real time, and issues targeted analysis tasks to the data analysis module (such as focusing on monitoring the operating status of the hoisting mechanism). The status assessment unit adopts a combined model, inputs preprocessed data into the model, outputs the crane health status level, and combines the updated parameters of the adaptive learning unit to improve the ability to identify new faults and environmental interference. The fault early warning unit monitors data through a dual mechanism of threshold judgment and trend prediction. If an anomaly is detected, it immediately triggers the corresponding level of early warning (level 1, level 2, level 3) and links with the fault root cause location unit. The fault root cause localization unit extracts multi-dimensional data before and after the anomaly, calculates the correlation of parameters, matches the fault root cause with the fault knowledge graph, verifies the root cause through operation room images or maintenance detection, updates the confidence of the knowledge graph, and outputs the fault type, location, root cause and recommended maintenance plan. The cross-device collaborative analysis unit is based on a deep reinforcement learning model. It generates scheduling strategies by combining the status information of each device (such as adjusting the crane operation priority, the arrival time of the transport vehicle, and the order of warehouse inventory). It also adjusts these strategies in real time based on location data to avoid the crane from being idle. The adaptive learning unit constructs fault prototypes using small samples to identify novel faults, employs an attention mechanism to reduce misjudgments due to environmental interference, and continuously optimizes model performance by combining a lightweight model at the edge with manual annotation for online updates. 5. Data Application Stage The data application module enables the practical application of collaborative decision-making and analysis results: The data display unit uses a visual interface to show the crane's real-time operating parameters, cross-device collaboration status, fault warnings and root cause information in the form of curves, charts and maps. It also supports historical data queries, making it convenient for staff to keep track of the system status in real time. The early warning notification unit pushes early warning information to the corresponding personnel through multiple channels such as sound and light alarms, SMS, and telephone according to the early warning level (e.g., the maintenance supervisor is notified simultaneously for a level 1 early warning, and maintenance personnel are notified for a level 2 early warning), and records all early warning events for easy traceability; The decision support unit generates crane health status reports, fault analysis reports, and cross-equipment collaborative reports, providing data support for managers to formulate equipment maintenance plans and work scheduling schemes, thereby helping to improve overall operational efficiency and management level. 6. System Iterative Optimization Phase The collaborative decision-making center receives maintenance verification results and early warning processing information from the data application module, updates the fault knowledge graph and model parameters of the data analysis module, continuously optimizes the system's analysis accuracy and collaborative scheduling capabilities, and forms a closed-loop operation of "collection-transmission-storage-analysis-application-optimization" to continuously improve system performance and meet actual operational needs. In summary, this system, through a closed-loop architecture and collaborative operation of all modules, achieves comprehensive collection and efficient processing of multi-dimensional crane data. It overcomes the limitations of traditional monitoring methods that rely on isolated analysis of single devices, reducing crane idleness and resource mismatch through cross-device collaborative scheduling, thereby improving the overall operational efficiency. Furthermore, it accurately identifies the root causes of faults, provides early warnings of risks, shortens fault handling time, and reduces maintenance costs. Simultaneously, it continuously optimizes model performance through adaptive learning, reducing misjudgments and missed diagnoses caused by environmental interference and novel faults. Finally, it provides clear support to staff through visual displays and decision reports, facilitating scientific management decisions and ultimately providing strong assurance for the safe, stable operation and efficient management of cranes in various scenarios.

[0019] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or basic characteristics. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, it is intended that all variations falling within the meaning and scope of equivalents of the claims be included within the present invention.

[0020] Furthermore, it should be understood that although this specification describes embodiments, not every embodiment contains only one independent technical solution. This narrative style is merely for clarity. Those skilled in the art should consider the specification as a whole, and the technical solutions in each embodiment can also be appropriately combined to form other embodiments that can be understood by those skilled in the art.

Claims

1. A crane multi-dimensional data analysis system based on big data, characterized in that: It includes a data acquisition module, a data transmission module, a big data storage module, a collaborative decision-making center, a data analysis module, and a data application module. After the data acquisition module collects data, it transmits the data to the big data storage module via the data transmission module. The collaborative decision-making center integrates the preprocessed data from the big data storage module and links with the data analysis module for analysis. The analysis results are displayed and applied through the data application module, forming a closed-loop architecture.

2. The crane multi-dimensional data analysis system based on big data according to claim 1, characterized in that: The data acquisition module includes sensors deployed at key parts of the crane, environmental monitoring equipment in the work area, and interfaces for related equipment. The acquired data includes multi-dimensional crane operation data, environmental parameters, and related equipment data. The multi-dimensional crane operation data includes mechanical and electrical parameters, and the related equipment data includes the operation and status data of the transport vehicle and warehousing system.

3. The crane multi-dimensional data analysis system based on big data according to claim 1, characterized in that: The data transmission module adopts a hybrid transmission architecture that combines wireless transmission, wired transmission, and data federation. Wireless transmission uses 5G, WiFi, or Bluetooth, while wired transmission uses Ethernet or fiber optics. The data federation channel achieves parameter sharing through federation learning nodes on each device and is protected by encryption. The data transmission module is equipped with a data caching and retransmission mechanism, which temporarily stores data when the network is interrupted and resumes transmission after the network is restored.

4. The crane multi-dimensional data analysis system based on big data according to claim 1, characterized in that: The big data storage module adopts a hierarchical storage architecture, storing data on different storage media according to the frequency of data access; it integrates relational databases, non-relational databases, and graph databases to store structured data, unstructured data, and crane fault knowledge graphs respectively; the big data storage module also includes a data preprocessing unit, which uses a distributed computing framework to perform data cleaning, deduplication, transformation, and standardization.

5. The crane multi-dimensional data analysis system based on big data according to claim 1, characterized in that: The collaborative decision-making hub adopts a cloud-edge collaborative architecture. The cloud is deployed on an industrial cloud platform and managed using containerization, while the edge is deployed on the scheduling terminal of the crane and related equipment. Its functions include integrating full-dimensional data, issuing tasks to the data analysis module, pushing analysis results to the execution layer, updating the knowledge base and model parameters based on maintenance feedback, and communicating between the cloud and the edge through a lightweight IoT protocol.

6. The crane multi-dimensional data analysis system based on big data according to claim 1, characterized in that: The data analysis module includes a status assessment unit, a fault root cause localization unit, a fault early warning unit, a cross-device collaborative analysis unit, and an adaptive learning unit. The status assessment unit adopts a combined model, the fault early warning unit adopts a dual early warning mechanism, the cross-device collaborative analysis unit adopts a reinforcement learning algorithm, the fault root cause localization unit adopts parameter correlation analysis combined with knowledge graph, and the adaptive learning unit adopts a prototype network and incremental training mechanism.

7. The crane multi-dimensional data analysis system based on big data according to claim 6, characterized in that: The workflow of the fault root cause localization unit includes: extracting multi-dimensional data before and after the fault, calculating parameter correlation, matching root causes, verifying root causes through images or maintenance inspections, updating the root cause confidence of the knowledge graph, and outputting the fault type, location, root cause, and recommended maintenance plan.

8. The crane multi-dimensional data analysis system based on big data according to claim 1, characterized in that: The collaborative scheduling model of the cross-equipment collaborative analysis unit takes the efficiency of the work chain and the equipment load as optimization objectives. It generates scheduling strategies based on information such as equipment operation progress, location, and status, and adjusts the strategies in real time in combination with positioning data to avoid cranes being idle. The adaptive learning unit constructs fault prototypes through small samples to identify novel faults, adopts an attention mechanism to reduce misjudgments due to environmental interference, and performs online updates through a lightweight model at the edge combined with manual annotation.

9. A crane multi-dimensional data analysis system based on big data according to claim 1, characterized in that: The data application module's display unit uses front-end technology to develop a visual interface that displays the crane's real-time parameters, cross-device collaborative status, fault information, and historical data; the early warning notification unit pushes notifications through multiple channels according to the early warning level; and the decision support unit has the function of generating health status reports, fault analysis reports, and collaborative reports.

Images