Detection method and system for unattended screw ship unloader

Abstract

The invention discloses a detection method and system for an unattended screw ship unloader, and the system comprises a data collection module, a signal processing module, a fault recognition module, a decision output module, a data storage and retrieval module, a remote monitoring communication module, and a central processing module. The signal processing module is connected with the fault identification module, the remote monitoring communication module is connected with the central processing module, the central processing module is connected with the data storage retrieval module and the decision output module, and the fault identification module is connected with the decision output module and used for sending a fault diagnosis result to the decision output module. Therefore, the detection of the screw ship unloader is completed. According to the system, real-time monitoring and intelligent diagnosis of the running state of the spiral ship unloader are realized, the fault detection sensitivity and the diagnosis accuracy are greatly improved, and the fault response time is greatly shortened.

Description

Technical Field

[0001] This invention relates to the field of port automation machinery, specifically to a detection method and system for an unmanned screw unloader. Background Technology

[0002] As a key piece of equipment in port loading and unloading operations, the operational stability and reliability of screw unloaders directly affect the efficiency and safety of port operations. However, traditional manual inspection and fault diagnosis methods suffer from low efficiency, slow response, and low accuracy, making it difficult to meet the demands of modern ports for efficient and intelligent management. Summary of the Invention

[0003] (I) Purpose of the Invention

[0004] The purpose of this invention is to provide a detection method and system for an unattended spiral unloader. This method enables comprehensive monitoring and intelligent diagnosis of the spiral unloader's operating status, thereby improving the equipment's maintenance efficiency and operational safety.

[0005] (II) Technical Solution

[0006] To address the aforementioned problems, a first aspect of the present invention provides a detection system for an unattended screw unloader, comprising a data acquisition module, a signal processing module, a fault identification module, a decision output module, a data storage and retrieval module, a remote monitoring and communication module, and a central processing module, wherein...

[0007] The output terminal of the data acquisition module is connected to the input terminal of the signal processing module, and is used to send the acquired data to the signal processing module for processing;

[0008] The output of the signal processing module is connected to the input of the fault identification module, and is used to send the processed data to the fault identification module for fault diagnosis.

[0009] The remote monitoring communication module is connected to the central processing module and is used to send the received operation instructions from the external terminal to the central processing module. The external operation instructions include storage instructions and decision instructions.

[0010] The central processing module is connected to the data storage and retrieval module and the decision output module respectively, and is used to send the received storage instructions to the data storage and retrieval module and send the received decision instructions to the decision output module.

[0011] The data storage and retrieval module is used to execute corresponding data storage operations according to the received storage instructions, and at the same time to provide data reading services to the central processing module;

[0012] The output of the fault identification module is connected to the input of the decision output module, and is used to send the fault diagnosis results to the decision output module. The decision output module is used to generate and output an execution decision based on the received fault diagnosis results and decision instructions, so as to complete the detection of the screw unloader.

[0013] Preferably, the central processing module is further configured to send the various types of data read to the remote monitoring and communication module, and to perform real-time data monitoring of the various types of data through the remote monitoring and communication module.

[0014] Preferably, the data storage and retrieval module uses a distributed database to store the data.

[0015] Preferably, the signal processing module uses a finite impulse response filter to preprocess the original signal, then uses a denoising algorithm to denoise the preprocessed signal, and finally uses a feature extraction algorithm to extract features.

[0016] Preferably, the step of sending the processed data to the fault identification module for fault diagnosis includes:

[0017] Anomaly classification is performed on the processed data using vector machines and random forest learning algorithms.

[0018] The results of anomaly classification are judged and analyzed using convolutional neural networks to determine the fault type.

[0019] Preferably, the central processing module adopts a multi-core processor and hyper-threading technology, wherein the multi-core processor has ≥8 cores and a main frequency ≥2.5GHz.

[0020] Preferably, the central processing module, the data acquisition module, the signal processing module, and the fault identification module are all interconnected via a PCIe bus.

[0021] Preferably, the remote monitoring communication module communicates with external terminals in real time via TCP / IP network and MQTT communication protocol.

[0022] Preferably, the data acquisition module includes a vibration sensor, a temperature sensor, a pressure sensor, and a current sensor. The vibration sensor includes a piezoelectric sensor, and the temperature sensor includes a PT100 resistance temperature detector (RTD).

[0023] A second aspect of the present invention provides a method for detecting an unattended screw unloader, the method employing the detection system for an unattended screw unloader as described in any of the claims above, the method comprising:

[0024] S1: Transmit the real-time operating data of the spiral unloader collected by the data acquisition module to the signal processing module for preprocessing;

[0025] S2: Send the data processed by the signal processing module to the fault identification module for fault diagnosis;

[0026] S3: Send the operation instructions received by the remote monitoring and communication module from the external terminal to the central processing module. The external operation instructions include storage instructions and decision instructions.

[0027] S4: Send the storage instructions and decision instructions received by the central processing module to the data storage retrieval module and the decision output module, respectively;

[0028] S5: According to the storage instruction, the data storage retrieval module performs the corresponding data storage operation and provides data reading service to the central processing module.

[0029] S6: Receive the fault diagnosis results and decision instructions from the decision output module, generate an execution decision, and output it to complete the inspection of the screw unloader.

[0030] (III) Beneficial Effects

[0031] The above-mentioned technical solution of the present invention has the following beneficial technical effects: The present invention provides a detection method and system for an unmanned spiral unloader. Multiple modules in this system work collaboratively to solve the problem of low operating efficiency in traditional spiral unloaders. Specifically, the data acquisition module sends the acquired data to the signal processing module for processing, reducing the frequency and intensity of manual inspections and enabling more timely fault detection. The signal processing module sends the processed data to the fault identification module for fault diagnosis. The remote monitoring communication module is connected to the central processing module and sends the received operation instructions from the external terminal to the central processing module, realizing remote real-time monitoring and management, reducing the need for on-site inspections. The central processing module, as the core, is connected to the data storage and retrieval module and the decision output module, improving parallel processing capabilities and resource utilization. The data storage and retrieval module executes corresponding data storage operations according to the received storage instructions and provides data reading services to the central processing module, ensuring long-term efficient data storage and rapid retrieval. The decision output module generates and outputs execution decisions based on the received fault diagnosis results and decision instructions to complete the detection of the spiral unloader, achieving rapid fault response and processing, and reducing downtime. This invention enables real-time monitoring and intelligent diagnosis of the operating status of the spiral unloader, greatly improving the sensitivity of fault detection and the accuracy of diagnosis, and shortening the fault response time; at the same time, the automated fault detection and diagnosis system reduces the frequency and intensity of manual inspections, thus reducing labor costs. Attached Figure Description

[0032] Figure 1This is a schematic diagram of the detection system structure of the unmanned spiral unloader of the present invention;

[0033] Figure 2 This is a flowchart of the detection method for the unattended screw unloader of the present invention;

[0034] Figure 3 This is a specific embodiment of the detection method for the unattended spiral unloader of the present invention. Detailed Implementation

[0035] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments and the accompanying drawings. It should be understood that these descriptions are merely exemplary and not intended to limit the scope of the invention. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concept of the invention.

[0036] like Figure 1 As shown, the first aspect of the present invention provides a detection system for an unattended screw unloader, including a data acquisition module, a signal processing module, a fault identification module, a decision output module, a data storage and retrieval module, a remote monitoring and communication module, and a central processing module. The specific descriptions of each module are as follows:

[0037] The output of the data acquisition module is connected to the input of the signal processing module, and is used to send the acquired data to the signal processing module for processing. The data acquisition module integrates high-precision sensors to capture key parameters such as vibration, temperature, pressure, and current of the screw unloader in real time, providing a comprehensive and accurate data source for subsequent processing, thus reducing response delays and misjudgments caused by missing or incorrect data from the source. The data acquisition module is equipped with vibration sensors, temperature sensors, pressure sensors, and current sensors to collect real-time operating data of the screw unloader. The vibration sensor is a piezoelectric sensor with a measurement range of 0-20kHz and a sensitivity of not less than 10mV / g. The temperature sensor uses a PT100 resistance temperature detector (RTD) with a measurement accuracy of ±0.1℃. The pressure sensor has a range of 0.75 to 1.5 times the working pressure of the screw unloader and an accuracy of not less than 0.5%. The current sensor has a measurement range of 1 to 1.5 times the rated power of the motor being measured and an accuracy of not less than 1%. Through the integrated application of high-precision sensors, comprehensive monitoring of the operating status of the screw unloader is achieved, providing a rich and accurate data source for subsequent data processing and fault diagnosis.

[0038] The output of the signal processing module is connected to the input of the fault identification module, and is used to send the processed data to the fault identification module for fault diagnosis. The signal processing module uses a finite impulse response filter to preprocess the original signal, and then uses a denoising algorithm to denoise the preprocessed signal, and then uses a feature extraction algorithm to extract features. The process of sending the processed data to the fault identification module for fault diagnosis includes: (1) using vector machine and random forest learning algorithms to classify the processed data for anomalies; (2) using convolutional neural networks to judge and analyze the results of anomaly classification in order to determine the fault type. The signal processing module uses digital signal processing technology and has filtering, denoising, and feature extraction functions. It preprocesses the collected data, first using a finite impulse response filter, and then using wavelet transform and feature extraction algorithms to effectively extract key feature parameters that reflect the health status of the equipment. The preprocessed data is purer and more effective, providing a more reliable data foundation for subsequent fault identification and improving the accuracy and efficiency of fault identification.

[0039] The remote monitoring and communication module is connected to the central processing module and is used to send the received operation instructions from the external terminal to the central processing module. These external operation instructions include storage instructions and decision instructions. The remote monitoring and communication module (remote monitoring and communication module) communicates with the external terminal in real time via TCP / IP network and MQTT communication protocol. The remote monitoring and communication module supports multiple communication protocols to achieve remote monitoring of the system and communication with external systems. It supports TCP / IP and MQTT communication protocols to achieve real-time data transmission and instruction reception with the remote monitoring center. The module has a built-in security encryption mechanism to ensure the security of data transmission. It also supports mobile terminal access, allowing maintenance personnel to monitor equipment status anytime, anywhere. Through remote monitoring and communication functions, remote monitoring and real-time management of the spiral unloader is achieved, improving the overall operating efficiency and security of the system. Simultaneously, the mobile terminal access function further enhances the system's convenience and flexibility. The remote monitoring and communication module's support for real-time data transmission and mobile terminal access enables problems to be detected and handled remotely in an instant, further reducing response latency.

[0040] The central processing module is connected to the data storage and retrieval module and the decision output module, respectively. It sends received storage instructions to the data storage and retrieval module and receives decision instructions to the decision output module. The central processing module also sends various types of read data to the remote monitoring and communication module for real-time data monitoring. The central processing module employs a multi-core processor and hyper-threading technology, with the multi-core processor having at least 8 cores and a clock speed at least 2.5 GHz. The central processing module, data acquisition module, signal processing module, and fault identification module are all interconnected via a PCIe bus. As the core, the central processing module, relying on a high-performance multi-core processor, hyper-threading technology, and virtualization support, improves parallel processing capabilities and resource utilization. Simultaneously, the high-speed bus ensures efficient collaboration between modules, directly optimizing the overall system response speed. It employs a high-performance multi-core processor with 8 or more cores, each with a clock speed of no less than 2.5GHz, and supports Hyper-Threading technology to enhance parallel processing capabilities. The central processing module (CPU) is equipped with a large-capacity high-speed cache, with an L3 cache capacity of no less than 16MB, to reduce memory access latency. The CPU also supports virtualization technology, enabling the running of multiple operating systems or virtual machine instances, improving system flexibility and resource utilization. The application of the high-performance multi-core processor enhances the system's data processing and parallel processing capabilities. The support for Hyper-Threading and virtualization technologies further improves the system's flexibility and resource utilization. The CPU is responsible for coordinating database operations, including data reception, storage, index building, and query optimization, ensuring efficient database operation. The CPU has a built-in security unit supporting data encryption and access control functions, guaranteeing data security and privacy.

[0041] The data storage and retrieval module (data storage and retrieval module) is used to execute corresponding data storage operations according to received storage instructions, and also to provide data reading services to the central processing module. The data storage and retrieval module uses a distributed database to store data. The data storage and retrieval module employs distributed database technology and is tightly integrated with the central processing module, responsible for long-term data preservation and rapid retrieval. The data storage and retrieval module transmits data with the central processing module through a high-speed network interface. Through the application of the distributed database, long-term preservation and rapid retrieval of massive amounts of data are achieved. The distributed database is integrated within the data storage and retrieval module, serving as a part of the data storage and retrieval module, tightly connected to other modules, and playing a crucial role. The distributed database transmits data with the central processing module through a high-speed network interface, with the central processing module coordinating data reception, storage, index construction, and query optimization to ensure efficient data access. Simultaneously, the distributed database also receives pre-processed data from the data acquisition module after signal processing, enabling long-term preservation. For the remote monitoring and communication module, the distributed database provides historical and real-time data support to meet the needs of remote monitoring and data analysis, and responds to remote commands to execute query or update operations. Furthermore, when the decision output module generates maintenance suggestions or adjusts parameters, it relies on the historical and real-time data support provided by the distributed database to ensure decision accuracy. The roles of the distributed database in the system can be summarized as follows: First, the distributed architecture enables long-term storage of massive amounts of operational data, providing a data foundation for fault diagnosis and performance analysis. Second, through index building and query optimization techniques, it supports rapid retrieval, meeting real-time analysis needs. Third, it collaborates with the security unit of the central processing module to ensure data encryption and access control, preventing the leakage of sensitive information. Fourth, the distributed architecture supports system expansion, adapts to data growth, and is compatible with remote and mobile terminal access, improving flexibility. Finally, it provides data support for modules such as fault identification and decision output, improving overall system performance and diagnostic accuracy. These functions collectively ensure the efficiency and reliability of the system's real-time monitoring, fault diagnosis, and intelligent management.

[0042] The output of the fault identification module is connected to the input of the decision output module, and is used to send the fault diagnosis results to the decision output module. The decision output module is used to generate and output an execution decision based on the received fault diagnosis results and decision instructions to complete the inspection of the screw unloader. The fault identification module combines machine learning algorithms and deep learning models to automatically complete anomaly judgment and fault type localization, replacing the inefficient mode of traditional manual experience judgment, significantly shortening the diagnosis time and improving accuracy. The decision output module reduces manual intervention by automatically generating maintenance suggestions or adjusting control parameters, realizing rapid response and handling of faults. The fault identification module uses machine learning algorithms and deep learning models to initially judge whether there are anomalies based on the processed data, and conducts in-depth analysis of the identified anomalies to determine the fault type and location; support vector machine and random forest learning algorithms are used to classify the processed data; convolutional neural networks are used, combined with domain knowledge and historical fault cases, to conduct in-depth analysis of the identified anomalies to determine the specific type, location and possible cause of the fault. The decision output module generates maintenance suggestions or automatically adjusts control parameters based on diagnostic results. It automatically generates a maintenance suggestion report based on fault diagnosis results, including a fault description, suggested maintenance measures, a list of required spare parts, and estimated maintenance time. The module also has the function of automatically adjusting control parameters; for faults that can be corrected by software, adjustments can be implemented immediately to reduce downtime. The maintenance suggestion report includes information such as a fault description, suggested maintenance measures, a list of required spare parts, and estimated maintenance time. For faults that can be corrected by software, control parameters are directly adjusted to reduce downtime. By automatically generating maintenance suggestions or automatically adjusting control parameters, timely fault response and handling are achieved, effectively shortening downtime and improving equipment operating efficiency and production benefits.

[0043] Other examples Figure 2 As shown, a second aspect of the present invention provides a method for detecting an unattended screw unloader, the method employing the detection system for an unattended screw unloader as described in any of the claims above, the method comprising:

[0044] S1: Transmit the real-time operating data of the spiral unloader collected by the data acquisition module to the signal processing module for preprocessing;

[0045] S2: Send the data processed by the signal processing module to the fault identification module for fault diagnosis;

[0046] S3: Send the operation instructions received by the remote monitoring and communication module from the external terminal to the central processing module. The external operation instructions include storage instructions and decision instructions.

[0047] S4: Send the storage instructions and decision instructions received by the central processing module to the data storage retrieval module and the decision output module, respectively;

[0048] S5: According to the storage instruction, the data storage retrieval module performs the corresponding data storage operation and provides data reading service to the central processing module.

[0049] S6: Receive the fault diagnosis results and decision instructions from the decision output module, generate an execution decision, and output it to complete the inspection of the screw unloader.

[0050] Figure 3 This is a flowchart illustrating a specific embodiment of the detection method of the present invention. The method specifically includes:

[0051] (1) Install sensors for data acquisition modules in key parts of the spiral unloader to ensure comprehensive coverage of the equipment's operating status; connect each module to the central processing module via a high-speed PCIe bus to build a complete system architecture; configure a remote monitoring and communication module to achieve connection and data transmission with the remote monitoring center.

[0052] (2) The data acquisition module collects the operating data of the spiral unloader in real time, such as vibration, temperature, pressure and current; the signal processing module performs filtering, noise reduction and feature extraction on the collected raw data to remove noise and interference and extract key feature parameters that reflect the health status of the equipment.

[0053] (3) Based on the processed data, the fault identification module uses machine learning algorithms and deep learning models to make a preliminary judgment and identify possible anomalies. For the identified anomalies, the fault identification module conducts in-depth analysis to determine the specific type, location and possible cause of the fault.

[0054] (4) The decision output module automatically generates a maintenance suggestion report or adjusts the control parameters based on the fault diagnosis results. The maintenance suggestion report includes information such as fault description, suggested maintenance measures, required spare parts list and estimated maintenance time, and is sent to the remote monitoring center or on-site maintenance personnel through the remote monitoring and communication module. For faults that can be corrected by software, the decision output module automatically adjusts the control parameters to reduce downtime.

[0055] (5) All collected data and diagnostic results are stored in the data storage and retrieval module for subsequent analysis and query; maintenance personnel can access the database through the remote monitoring and communication module to query equipment historical data and fault records;

[0056] (6) Regularly calibrate and maintain the sensors of the data acquisition module to ensure the accuracy of the data; optimize and update the algorithms of the signal processing module and the fault identification module to improve the accuracy and real-time performance of fault diagnosis; regularly optimize and clean the data storage and retrieval module to ensure the system's operating efficiency; strengthen the system's network security protection, and regularly update security patches and configure firewall rules.

[0057] This invention provides a detection method and system for an unmanned spiral unloader. The system integrates multiple high-precision sensors and advanced intelligent algorithms. The signal processing module applies a finite impulse response filter algorithm and a wavelet transform denoising algorithm to filter and denoise the raw data, retaining effective signal components and extracting key feature parameters, providing a clean data source for subsequent analysis. The fault identification module combines machine learning algorithms such as support vector machines and random forests for anomaly classification and uses a convolutional neural network deep learning model to deeply analyze anomalies, determine the fault type and location, and improve diagnostic accuracy by incorporating historical cases. The decision output module automatically generates maintenance reports or adjusts equipment parameters based on the diagnostic results, reducing manual intervention. The data storage and retrieval module uses distributed database storage algorithms and index building and query optimization algorithms to ensure efficient data storage and rapid retrieval. The remote monitoring and communication module ensures data transmission security and enables real-time remote monitoring through data encryption algorithms and communication protocol encapsulation and parsing algorithms. The central processing module utilizes hyper-threading and virtualization technologies to improve parallel processing capabilities and resource utilization, supporting efficient collaboration among multiple modules. These algorithms function within their respective modules, collectively constructing an intelligent system capable of real-time monitoring, rapid response, and accurate diagnosis.

[0058] It should be understood that the specific embodiments described above are merely illustrative of the principles of the invention and do not constitute a limitation thereof. Therefore, any modifications, equivalent substitutions, or improvements made without departing from the spirit and scope of the invention should be included within the protection scope of the invention. Furthermore, the appended claims are intended to cover all variations and modifications falling within the scope and boundaries of the appended claims, or equivalent forms of such scope and boundaries. Those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it includes the flows of the embodiments of the methods described above. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc. The steps in the methods of the embodiments of the present invention can be adjusted, merged, or deleted according to actual needs. The modules in the system of the embodiments of the present invention can be merged, divided, or deleted according to actual needs.

Claims

1. A detection system for an unattended screw unloader, characterized in that, It includes a data acquisition module, a signal processing module, a fault identification module, a decision output module, a data storage and retrieval module, a remote monitoring and communication module, and a central processing module. The output terminal of the data acquisition module is connected to the input terminal of the signal processing module, and is used to send the acquired data to the signal processing module for processing; The output of the signal processing module is connected to the input of the fault identification module, and is used to send the processed data to the fault identification module for fault diagnosis. The remote monitoring communication module is connected to the central processing module and is used to send the received operation instructions from the external terminal to the central processing module. The external operation instructions include storage instructions and decision instructions. The central processing module is connected to the data storage and retrieval module and the decision output module respectively, and is used to send the received storage instructions to the data storage and retrieval module and send the received decision instructions to the decision output module. The data storage and retrieval module is used to execute corresponding data storage operations according to the received storage instructions, and at the same time provide data reading services to the central processing module; The output of the fault identification module is connected to the input of the decision output module, and is used to send the fault diagnosis results to the decision output module. The decision output module is used to generate and output an execution decision based on the received fault diagnosis results and decision instructions, so as to complete the detection of the screw unloader.

2. The detection system for the unmanned screw unloader according to claim 1, characterized in that, The central processing module is also used to send various types of data to the remote monitoring and communication module, and to perform real-time data monitoring of various types of data through the remote monitoring and communication module.

3. The detection system for the unmanned screw unloader according to claim 1, characterized in that, The data storage and retrieval module uses a distributed database to store the data.

4. The detection system for the unmanned screw unloader according to claim 1, characterized in that, The signal processing module uses a finite impulse response filter to preprocess the original signal, then uses a denoising algorithm to denoise the preprocessed signal, and finally uses a feature extraction algorithm to extract features.

5. The detection system for the unmanned screw unloader according to claim 1, characterized in that, The step of sending the processed data to the fault identification module for fault diagnosis includes: Anomaly classification is performed on the processed data using vector machines and random forest learning algorithms. The results of anomaly classification are judged and analyzed using convolutional neural networks to determine the fault type.

6. The detection system for the unmanned screw unloader according to claim 1, characterized in that, The central processing module adopts a multi-core processor and hyper-threading technology. The multi-core processor has ≥8 cores and a main frequency ≥2.5GHz.

7. The detection system for the unmanned screw unloader according to claim 1, characterized in that, The central processing module, the data acquisition module, the signal processing module, and the fault identification module are all interconnected via a PCIe bus.

8. The detection system for the unmanned screw unloader according to claim 1, characterized in that, The remote monitoring communication module communicates with external terminals in real time via TCP / IP network and MQTT communication protocol.

9. The detection system for the unmanned screw unloader according to claim 1, characterized in that, The data acquisition module is equipped with a vibration sensor, a temperature sensor, a pressure sensor, and a current sensor. The vibration sensor includes a piezoelectric sensor, and the temperature sensor includes a PT100 resistance temperature detector.

10. A detection method for an unattended screw unloader, characterized in that, The method employs the detection system for the unmanned screw unloader as described in any one of claims 1-9, and the method includes: S1: Transmit the real-time operating data of the spiral unloader collected by the data acquisition module to the signal processing module for preprocessing; S2: Send the data processed by the signal processing module to the fault identification module for fault diagnosis; S3: Send the operation instructions received by the remote monitoring and communication module from the external terminal to the central processing module. The external operation instructions include storage instructions and decision instructions. S4: Send the storage instructions and decision instructions received by the central processing module to the data storage retrieval module and the decision output module, respectively; S5: According to the storage instruction, the data storage retrieval module performs the corresponding data storage operation and provides data reading service to the central processing module. S6: Receive the fault diagnosis results and decision instructions from the decision output module, generate an execution decision, and output it to complete the inspection of the screw unloader.

Images