Information monitoring device and method for storage tool magazine multi-motor system

By integrating multi-motor drive control, integrated sensors, edge computing and communication optimization systems in the multi-motor system of the warehouse tool magazine, the problems of limited monitoring range and slow response speed are solved, and the system is comprehensive, real-time monitoring and efficient management are achieved, improving the system's improvement Failure prediction accuracy and maintenance efficiency.

CN119065257APending Publication Date: 2024-12-03OKADA SEIKI DANYANG CO LTD

Patent Information

Application Number
CN202411566556.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-11-05
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

The existing multi-motor system monitoring methods in the warehouse tool magazine have problems such as limited monitoring range, slow response speed, and insufficient data utilization, making it difficult to comprehensively and in real time to grasp the system operation status and deal with faults in a timely manner.

Method used

Adopt multi-motor drive control system, integrated sensor system, edge computing and data processing system, communication and network system, intelligent prediction and maintenance system and communication optimization system, through real-time monitoring of multiple sensor data, in-depth analysis of machine learning algorithms, encrypted data transmission, Remote diagnosis and optimization of communication strategies to achieve comprehensive, real-time monitoring and efficient management of multi-motor systems in the warehouse tool magazine.

Benefits of technology

It realizes comprehensive, real-time monitoring and efficient management of multi-motor systems in the storage tool magazine, improves data processing speed and fault prediction accuracy, and ensures stable operation and preventive maintenance of the system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119065257A_ABST
    Figure CN119065257A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of tool magazine monitoring, in particular to an information monitoring device and method for a multi-motor system of a storage tool magazine, and the method comprises the steps: starting and controlling a plurality of motors to carry out the rotation, tool grabbing and replacement of the storage tool magazine; monitoring and collecting various parameter data of the storage tool magazine multi-motor system in real time; carrying out preprocessing and preliminary analysis on the collected data, and carrying out deep analysis by using a machine learning algorithm to generate an operation state report; data are encrypted and transmitted, various parameter data are monitored in real time, intelligent analysis is carried out, and operation parameters of the multi-motor system are adjusted. According to the invention, the problems of limited monitoring range, slow response speed and insufficient data utilization in the existing monitoring method are effectively solved, comprehensive and real-time monitoring and efficient management of the storage tool magazine multi-motor system are realized, and the data processing speed and the fault prediction accuracy are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of tool magazine monitoring, and in particular to an information monitoring device and method for a multi-motor system of a storage tool magazine. Background Art

[0002] In modern manufacturing, the tool magazine multi-motor system is an important part of CNC machine tools. It uses multiple motors to independently control the rotation of the tool magazine, the grabbing and replacement of tools, and realizes the rapid and accurate replacement of tools, thereby significantly improving processing efficiency and flexibility. However, with the increase in system complexity, it becomes particularly important to effectively monitor and manage the tool magazine multi-motor system.

[0003] During the operation of the multi-motor system of the tool storage magazine, it is necessary to monitor the tool status, motor working parameters, tool magazine position and other information in real time, and transmit the data to the central control system through the communication network for analysis and processing. The existing monitoring methods mainly rely on manual inspection and simple sensor monitoring, which have the problems of limited monitoring range, slow response speed and insufficient data utilization. It is difficult to fully and real-time grasp the operation of the system and deal with system failures in a timely manner.

[0004] The information disclosed in this background technology section is only intended to deepen the understanding of the overall background technology of the present disclosure, and should not be regarded as acknowledging or suggesting in any form that the information constitutes the prior art known to those skilled in the art. Summary of the invention

[0005] The present invention provides an information monitoring device and system for a multi-motor system of a tool storage magazine, thereby effectively solving the problems pointed out in the background technology.

[0006] In order to achieve the above object, the technical solution adopted by the present invention is: The information monitoring device of the multi-motor system of the storage tool magazine includes: Multi-motor drive control system, including multiple motors and their drive controllers, used to independently control the rotation of the storage tool magazine, the grabbing and changing operations of the tool; Comprehensive sensor system, integrating multiple sensors, for real-time monitoring of various parameters of the multi-motor system of the storage tool magazine; Edge computing and data processing system, including edge computing module and intelligent analysis module. The edge computing module performs data preprocessing and preliminary analysis on the device side. The intelligent analysis module performs in-depth analysis by integrating multiple sensor data and machine learning algorithms and generates an operation status report. The communication and network system includes an IoT gateway, a secure communication module and a remote monitoring module. The IoT gateway transmits sensor data and control instructions through a variety of communication protocols, and interconnects various systems for data exchange and collaborative work. The secure communication module uses encryption technology to process data transmission encryption and performs access control through an identity authentication mechanism. The remote monitoring module performs remote system status viewing and control through a secure channel, monitors equipment operation, and sends alarms and notifications when an abnormality is detected, and performs remote diagnosis and maintenance together with the secure communication module. The central control system is used to coordinate the operation of each system and perform real-time monitoring and intelligent analysis of sensor data.

[0007] Furthermore, it also includes an intelligent predictive maintenance system, the intelligent predictive maintenance system including: A historical data storage module, through which the historical operation data of the system is acquired and stored; A data analysis and model training module, which analyzes the historical operation data, identifies failure modes, and trains a failure prediction model using a machine learning platform; The data collection and prediction module collects system operation data in real time, uses the trained fault prediction model to perform real-time prediction, and obtains fault prediction results; The maintenance suggestion generation module analyzes and generates maintenance suggestions through a rule engine based on the fault prediction results to perform preventive maintenance.

[0008] Furthermore, the fault prediction model includes: The data input layer receives and processes multi-dimensional real-time data from the integrated sensor system and inputs it in parallel through multiple channels; The feature extraction layer uses convolutional neural networks to extract key features from the input data and captures spatial patterns and changing trends in sensor data through automated feature learning; The sequence processing layer uses a hybrid model combining a long short-term memory network and a gated recurrent unit to process time series data and analyze data changes at different time points during the operation of the tool. The long short-term memory network is used to capture the long-term dependencies generated during the operation of the warehouse tool magazine multi-motor system, and the gated recurrent unit is used to simplify the structure of the hybrid model and accelerate the training process to process short-term dependencies. The data fusion layer combines the features of multi-source data to fuse the features of different sensor data; The output layer generates the fault prediction result, which is a specific fault type; The loss function calculates the error between the fault prediction result and the actual situation through an adaptive weighted cross entropy loss function.

[0009] Furthermore, a communication optimization system is also included, and the communication optimization system includes: A historical data analysis module, which acquires historical communication data and sensor data, analyzes the correlation between the historical communication data and historical network performance, and obtains a first correlation result; A real-time data monitoring module obtains current communication status data and sensor real-time data, analyzes the correlation between current communication data and current network performance, and obtains a second correlation result; The communication optimization algorithm module optimizes the communication strategy and adjusts relevant communication parameters according to the first association result and the second association result to obtain the optimal performance of the communication network.

[0010] Furthermore, the communication optimization algorithm includes: Dynamic spectrum management algorithm, which uses artificial intelligence algorithms to monitor spectrum usage in real time, predict possible interference, and dynamically adjust spectrum allocation strategies; Intelligent routing optimization algorithm, which uses deep learning algorithm to optimize data transmission paths in real time and dynamically adjust routing strategies according to network load, transmission delay and bandwidth requirements; Traffic control and congestion management algorithms predict network traffic trends through machine learning models and dynamically adjust traffic control parameters to prevent and alleviate network congestion.

[0011] Furthermore, the intelligent predictive maintenance system and edge computing module are combined through distributed computing and collaborative analysis, including: The edge computing module processes sensor data in parallel on the device side and decomposes the preprocessing task into multiple subtasks; The edge computing module and the intelligent predictive maintenance system perform data synchronization, and the edge computing module transmits the processed data to the cloud in real time through the gateway; The intelligent predictive maintenance system processes preliminary analysis results from multiple edge computing modules in parallel in the cloud, and combines historical data with real-time data for in-depth analysis and model optimization; The intelligent predictive maintenance system dynamically adjusts the parameters of the fault prediction model according to the in-depth analysis results of the cloud. The optimized model parameters are synchronized to each edge computing module through the Internet of Things gateway, and the edge computing module applies the optimized model in real time to predict faults.

[0012] Furthermore, the intelligent predictive maintenance system processes preliminary analysis results from multiple edge computing modules in parallel in the cloud, combines historical data and real-time data for in-depth analysis and model optimization, including: Decompose the sensor data into hourly data blocks, and assign each hourly data block as a subtask to different cloud computing nodes for parallel processing; Use convolutional neural network models to process sensor data and identify abnormal patterns, and use long short-term memory network models to analyze time series data, capture time dependencies and predict future trends; The performance of each model was evaluated through cross-validation, and the hyperparameters of the long short-term memory network model were adjusted using Bayesian optimization to obtain the final fault prediction model.

[0013] The information monitoring method of the tool storage magazine multi-motor system adopts the information monitoring device of the tool storage magazine multi-motor system, comprising: Start and control multiple motors to rotate the storage tool magazine, grab and replace tools; Real-time monitoring and collection of various parameter data of the multi-motor system of the storage tool magazine; Preprocess and preliminarily analyze the collected data, and use machine learning algorithms for in-depth analysis to generate operating status reports; The data is encrypted for transmission, the parameter data are monitored in real time, and intelligent analysis is performed to adjust the operating parameters of the multi-motor system.

[0014] Furthermore, it also includes: Acquire and store historical operation data of the system; Analyze the historical operation data, identify failure modes, and train a failure prediction model using a machine learning platform; Collect system operation data in real time, use the trained fault prediction model to perform real-time prediction, and obtain fault prediction results; According to the fault prediction results, maintenance suggestions are generated through the rule engine to perform preventive maintenance.

[0015] Furthermore, it also includes: Acquire historical communication data and sensor data, analyze the correlation between the historical communication data and historical network performance, and obtain a first correlation result; Acquire current communication status data and sensor real-time data, analyze the correlation between current communication data and current network performance, and obtain a second correlation result; According to the first association result and the second association result, the communication strategy is optimized and the relevant communication parameters are adjusted to obtain the optimal performance of the communication network.

[0016] The technical solution of the present invention can achieve the following technical effects: The present invention effectively solves the problems of limited monitoring range, slow response speed and insufficient data utilization in existing monitoring methods, realizes comprehensive and real-time monitoring and efficient management of the multi-motor system of the storage tool magazine, and improves the data processing speed and the accuracy of fault prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 It is a framework diagram of the information monitoring device for the multi-motor system of the storage tool magazine; Figure 2 It is an optimized framework diagram of the information monitoring device for the multi-motor system of the storage tool magazine; Figure 3 A flow chart of an information monitoring method for a multi-motor system of a tool storage magazine; Figure 4 A schematic diagram of a process for intelligent predictive maintenance of device operation data; Figure 5 A schematic diagram of a process for communication optimization based on correlation analysis results. DETAILED DESCRIPTION

[0019] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0021] Embodiment 1 like Figure 1 As shown, the present invention provides an information monitoring device for a multi-motor system of a storage tool magazine, the device comprising: Multi-motor drive control system, including multiple motors and their drive controllers, used to independently control the rotation of the storage tool magazine, the grabbing and changing operations of the tool; Specifically, at the beginning of the operation, the central control system first sends control instructions to the multi-motor drive control system, which includes multiple motors and their drive controllers. These motors can independently control the rotation of the storage tool magazine, the grabbing and replacement operations of the tools, and each motor performs precise movements according to predetermined paths and parameters to ensure accurate grabbing and replacement of the tools. This process is closed-loop controlled by the instructions and real-time feedback of the central control system to ensure the accuracy and efficiency of the operation.

[0022] Comprehensive sensor system, integrating multiple sensors, for real-time monitoring of various parameters of the multi-motor system of the storage tool magazine; Specifically, the comprehensive sensor system integrates multiple sensors such as temperature sensors, vibration sensors, current sensors, etc. to monitor the various parameters of the multi-motor system of the storage tool magazine in real time. These sensors are distributed in key positions of the system and continuously collect real-time data during operation. For example, the temperature sensor monitors the operating temperature of the motor, the vibration sensor monitors the mechanical vibration state of the tool magazine, and the current sensor monitors the current consumption of each motor. The collected data is transmitted to the edge computing module through the communication interface for processing.

[0023] Edge computing and data processing system, including edge computing module and intelligent analysis module. The edge computing module performs data preprocessing and preliminary analysis on the device side, and the intelligent analysis module performs in-depth analysis by integrating multiple sensor data and machine learning algorithms and generates operation status reports. Specifically, after receiving the sensor data, the edge computing module first performs data preprocessing, which includes denoising, filtering and data aggregation to reduce data redundancy and improve data quality. The preprocessed data is transmitted to the intelligent analysis module, which uses the fusion of multiple sensor data and machine learning algorithms for in-depth analysis. This analysis can identify potential problems and anomalies in system operation and generate a detailed operation status report. The report content includes the system's health status, performance indicators and fault warning information, and these reports are transmitted to the central control system.

[0024] Communication and network systems, including IoT gateways, secure communication modules and remote monitoring modules. IoT gateways transmit sensor data and control instructions through multiple communication protocols, and interconnect various systems for data exchange and collaborative work. Secure communication modules use encryption technology to process data transmission encryption, and perform access control through identity authentication mechanisms. Remote monitoring modules view and control remote system status through secure channels, monitor equipment operation, and send alarms and notifications when abnormalities are detected. They work together with secure communication modules to perform remote diagnosis and maintenance. Specifically, the IoT gateway transmits sensor data and control instructions through a variety of communication protocols (such as Wi-Fi, Bluetooth, and Zigbee), interconnects various systems, and realizes data exchange and collaborative work. The gateway establishes a communication bridge between different sensors and control devices to ensure efficient data transmission and coordinated operation of the system; the secure communication module uses encryption technology (such as AES and TLS) to encrypt data transmission, and performs access control through identity authentication mechanisms (such as two-factor authentication) to ensure the security of data transmission and the reliability of device access. These security measures prevent unauthorized access and data leakage; the remote monitoring module uses a secure channel (such as VPN) to view and control the remote system status and monitor the equipment operation in real time. When an abnormality is detected, the system will immediately send an alarm and notification. The remote monitoring module works together with the secure communication module to perform remote diagnosis and maintenance to improve the reliability and maintenance efficiency of the system.

[0025] The central control system is used to coordinate the operation of each system and perform real-time monitoring and intelligent analysis of sensor data.

[0026] Specifically, the central control system integrates data from various subsystems, and performs real-time monitoring and intelligent analysis of sensor data. Based on the analysis results, the system dynamically adjusts the operating parameters of the multi-motor drive control system to ensure the stable operation of the multi-motor system in the storage tool magazine. The central control system is also responsible for coordinating the operation of various subsystems to ensure smooth data exchange and collaborative work between them. Through real-time monitoring and intelligent analysis, the central control system can promptly detect and resolve potential problems to maintain the efficiency and stability of the system.

[0027] As a preferred embodiment of the above, Figure 2 As shown, it also includes an intelligent predictive maintenance system, which includes: A historical data storage module, through which the historical operation data of the system is acquired and stored; Data analysis and model training module, which analyzes historical operation data, identifies failure modes, and trains failure prediction models using a machine learning platform; The data collection and prediction module collects system operation data in real time, uses the trained fault prediction model to make real-time predictions, and obtains fault prediction results; The maintenance suggestion generation module analyzes and generates maintenance suggestions based on the fault prediction results through the rule engine to perform preventive maintenance.

[0028] Specifically, the operation data of the equipment is first collected in real time through sensors, and the data is transmitted to the historical data storage module for recording; then, the data analysis and model training module cleans, extracts features and recognizes patterns of historical data, and trains the fault prediction model using machine learning algorithms; real-time data is input into the prediction model for real-time fault prediction, and the prediction results include the type of fault and the time when it may occur; the maintenance suggestion generation module generates detailed maintenance suggestions through the rule engine based on the prediction results, and preventive maintenance is carried out in advance. The rule engine first matches and judges the input data and analyzes it according to predefined rules. For example, the rule engine detects whether parameters such as motor temperature, vibration and current exceed the normal range. When real-time data is input into the system, the rule engine matches and judges these data according to predefined rules, identifies potential faults and maintenance needs, and generates specific maintenance suggestions based on the matching results, such as parts that need to be checked, parts that need to be replaced, and recommended maintenance time and steps. The intelligent predictive maintenance system can not only significantly improve the reliability and stability of equipment, reduce unplanned downtime, and reduce maintenance costs, but also extend the service life of equipment and improve production efficiency.

[0029] As a preferred embodiment of the above, the fault prediction model includes: The data input layer receives and processes multi-dimensional real-time data from the integrated sensor system and inputs it in parallel through multiple channels; The feature extraction layer uses convolutional neural networks to extract key features from the input data and captures spatial patterns and changing trends in sensor data through automated feature learning; The sequence processing layer uses a hybrid model that combines long short-term memory networks and gated recurrent units to process time series data and analyze data changes at different time points during tool operation. The long short-term memory network is used to capture the long-term dependencies generated by the multi-motor system of the storage tool magazine during operation. The gated recurrent unit is used to simplify the structure of the hybrid model and accelerate the training process to process short-term dependencies. The data fusion layer combines the features of multi-source data to fuse the features of different sensor data; The output layer generates fault prediction results, which are specific fault types; Loss function,The error between the fault prediction result and the actual situation is calculated through the adaptive weighted cross entropy loss function.

[0030] Specifically, the data input layer accepts and processes multi-dimensional real-time data from the integrated sensor system in parallel to ensure the diversity and real-time nature of the input data. The feature extraction layer uses a convolutional neural network (CNN) to extract key features from the input data and captures spatial patterns and change trends in sensor data through automated feature learning. The sequence processing layer uses a hybrid model that combines a long short-term memory network (LSTM) and a gated recurrent unit (GRU) to process time series data and analyze data changes at different time points during tool operation. LSTM is used to capture long-term dependencies, and GRU is used to simplify the model structure and accelerate the training process to process short-term dependencies. The data fusion layer combines multi-source data features to fuse features from different sensor data to generate a comprehensive feature vector. The output layer uses a fully connected layer and a Softmax function to generate specific fault prediction results and determine the fault type through probability distribution. The loss function uses an adaptive weighted cross entropy loss function to calculate the error between the fault prediction result and the actual situation, and adaptively adjusts the weights according to the imbalance of samples of different fault types to optimize the model training effect.

[0031] As a preferred embodiment of the above, Figure 2 As shown, a communication optimization system is also included, and the communication optimization system includes: A historical data analysis module, which obtains historical communication data and sensor data, analyzes the correlation between the historical communication data and historical network performance, and obtains a first correlation result; A real-time data monitoring module obtains current communication status data and sensor real-time data, analyzes the correlation between current communication data and current network performance, and obtains a second correlation result; The communication optimization algorithm module optimizes the communication strategy and adjusts relevant communication parameters according to the first correlation result and the second correlation result to obtain the optimal performance of the communication network.

[0032] Specifically, during operation, the system collects and records all historical communication data and sensor data. The historical data analysis module analyzes this data to identify the relationship between communication data and network performance. For example, through analysis, it can be found that certain communication parameters change the impact of network delay or throughput; the system collects current communication status data and sensor data in real time, and analyzes these data in real time. By comparing the current communication data with network performance, it can promptly discover changes in network performance and potential problems, and generate a second correlation result; the communication optimization algorithm module combines the historical data analysis results and real-time data monitoring results to dynamically adjust the communication strategy. For example, based on the current network load and communication needs, it optimizes spectrum allocation and routing paths to ensure efficient and stable data transmission. This module can optimize the performance of the entire communication network by adjusting the frequency allocation of the spectrum management unit and the path selection of the intelligent routing unit.

[0033] As a preferred embodiment of the above, the communication optimization algorithm includes: Dynamic spectrum management algorithm, which uses artificial intelligence algorithms to monitor spectrum usage in real time, predict possible interference, and dynamically adjust spectrum allocation strategies; Intelligent routing optimization algorithm, which uses deep learning algorithm to optimize data transmission paths in real time and dynamically adjust routing strategies according to network load, transmission delay and bandwidth requirements; Traffic control and congestion management algorithms predict network traffic trends through machine learning models and dynamically adjust traffic control parameters to prevent and alleviate network congestion.

[0034] Specifically, the dynamic spectrum management algorithm uses spectrum sensors to collect spectrum usage data, predicts the occurrence of interference events through machine learning models (such as support vector machines or random forests), and dynamically adjusts the spectrum allocation strategy through reinforcement learning (such as Q-learning) to maximize spectrum utilization and communication quality; the intelligent routing optimization algorithm collects network status data, uses convolutional neural networks (CNN) or graph neural networks (GNN) for real-time analysis, predicts the optimal transmission path, and dynamically adjusts routing selection through reinforcement learning (such as the DQN algorithm) to achieve network load balancing and maximize transmission efficiency; the flow control and congestion management algorithm first trains the long short-term memory network (LSTM) through historical traffic data to predict future traffic trends, and then adjusts the flow control parameters (such as window size, sending rate) according to the prediction results, and uses adaptive flow control algorithms (such as TCPBBR) to optimize data transmission to prevent and alleviate network congestion and ensure the stability and efficiency of data transmission.

[0035] As a preferred embodiment of the above, the intelligent predictive maintenance system and the edge computing module are combined through distributed computing and collaborative analysis, including: The edge computing module processes sensor data in parallel on the device side and decomposes the preprocessing task into multiple subtasks; Data synchronization is performed between the edge computing module and the intelligent predictive maintenance system. The edge computing module transmits the processed data to the cloud in real time through the gateway; The intelligent predictive maintenance system processes preliminary analysis results from multiple edge computing modules in parallel in the cloud, combining historical data and real-time data for in-depth analysis and model optimization; The intelligent predictive maintenance system dynamically adjusts the parameters of the fault prediction model based on the in-depth analysis results of the cloud. The optimized model parameters are synchronized to each edge computing module through the IoT gateway. The edge computing module applies the optimized model in real time to predict faults.

[0036] Specifically, the edge computing module uses the multi-core processing power of the device to process sensor data in real time, including data cleaning, standardization and feature extraction. Each subtask is executed independently, which improves the efficiency and real-time performance of data processing. Data synchronization is performed between the edge computing module and the intelligent predictive maintenance system. The edge computing module transmits the processed data to the cloud in real time through the IoT gateway. The IoT gateway ensures the timeliness and accuracy of data transmission, so that the cloud system can obtain the latest data on the device in a timely manner. The intelligent predictive maintenance system processes the preliminary analysis results from multiple edge computing modules in parallel on the cloud, and conducts in-depth analysis and model optimization based on historical data and real-time data. By decomposing tasks into multiple subtasks and assigning them to different computing nodes for parallel processing, the system can efficiently complete the analysis and processing of large-scale data and improve the accuracy of fault prediction using deep learning models. The intelligent predictive maintenance system dynamically adjusts the parameters of the fault prediction model based on the in-depth analysis results on the cloud. The optimized model parameters are synchronized to each edge computing module through the IoT gateway. The edge computing module applies the optimized model in real time to perform fault prediction. Through the collaborative work of the cloud and the device, efficient and accurate fault prediction and maintenance management are achieved.

[0037] As a preferred embodiment of the above, the intelligent predictive maintenance system processes preliminary analysis results from multiple edge computing modules in parallel on the cloud, combines historical data and real-time data for in-depth analysis and model optimization, including: Decompose sensor data into hourly data blocks, and assign each hourly data block as a subtask to different cloud computing nodes for parallel processing; Use convolutional neural network models to process sensor data and identify abnormal patterns, and use long short-term memory network models to analyze time series data, capture time dependencies and predict future trends; The performance of each model was evaluated through cross-validation, and the hyperparameters of the long short-term memory network model were adjusted using Bayesian optimization to obtain the final fault prediction model.

[0038] Specifically, first, the edge computing module collects sensor data in real time on the device side and decomposes the data into hourly data blocks. For example, 24 hours of data a day will be decomposed into 24 hourly data blocks. Then, each hourly data block is assigned as a subtask to different cloud computing nodes for parallel processing. This can make full use of cloud computing resources and improve the efficiency and real-time performance of data processing.

[0039] In the cloud, the CNN model is first used to process the sensor data in each hourly data block. Through multi-layer convolution and pooling operations, CNN extracts spatial features in the data and identifies abnormal patterns. Then, the LSTM model is used to analyze the time series data in each hourly data block. LSTM captures long-term dependencies in the data through its memory units and predicts future trends. For example, it can analyze current sensor data and predict future current fluctuation trends.

[0040] When optimizing models in the cloud, we first evaluate the performance of each model through cross-validation. Specifically, we divide the data into K subsets, use K-1 subsets for training each time, and use the remaining 1 subset for validation. This is repeated K times, and the average performance index is calculated. Through cross-validation, we can evaluate the generalization ability of the model and select the model with the best performance. Next, we use the Bayesian optimization method to adjust the hyperparameters of the LSTM model. Bayesian optimization builds a probabilistic model to predict the optimal parameter combination in the hyperparameter space and find the optimal hyperparameter settings with a smaller number of experiments, thereby improving the prediction accuracy and stability of the model.

[0041] Through the above steps, an optimized fault prediction model is finally obtained, which can accurately identify abnormal patterns in sensor data and predict future failure trends, thereby improving system reliability and maintenance efficiency.

[0042] Embodiment 2 like Figure 3 As shown, the present application provides an information monitoring method for a storage tool magazine multi-motor system, using the above-mentioned information monitoring device for the storage tool magazine multi-motor system, including: S1: Start and control multiple motors to rotate the storage tool magazine, grab and replace tools; S2: Real-time monitoring and collection of various parameter data of the multi-motor system of the storage tool magazine; S3: Preprocess and preliminarily analyze the collected data, and use machine learning algorithms for in-depth analysis to generate an operation status report; S4: Encrypt data transmission, monitor various parameter data in real time, conduct intelligent analysis and adjust the operating parameters of the multi-motor system.

[0043] As a preferred embodiment of the above, Figure 4 As shown, it also includes: A1: Obtain and store the historical operation data of the system; A2: Analyze historical operation data, identify failure modes, and use machine learning platforms to train failure prediction models; A3: Collect system operation data in real time, use the trained fault prediction model to make real-time predictions, and obtain fault prediction results; A4: Based on the fault prediction results, the rule engine is used to analyze and generate maintenance recommendations for preventive maintenance.

[0044] As a preferred embodiment of the above, Figure 5 As shown, it also includes: B1: Obtain historical communication data and sensor data, analyze the correlation between the historical communication data and historical network performance, and obtain a first correlation result; B2: obtaining current communication status data and sensor real-time data, analyzing the correlation between current communication data and current network performance, and obtaining a second correlation result; B3: Optimize the communication strategy and adjust relevant communication parameters according to the first association result and the second association result to obtain the optimal performance of the communication network.

[0045] The technical effects achieved by this embodiment are the same as those of the first embodiment and will not be described again here.

[0046] Although the present application has been described in conjunction with specific features and embodiments thereof, it is obvious that various modifications and combinations may be made thereto without departing from the spirit and scope of the present application. Accordingly, this specification and the accompanying drawings are merely exemplary illustrations of the present application as defined therein, and are deemed to have covered any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application is intended to include these modifications and variations.

Claims

1. The information monitoring device of the multi-motor system of the storage tool magazine is characterized by: include: Multi-motor drive control system, including multiple motors and their drive controllers, used to independently control the rotation of the storage tool magazine, the grabbing and changing operations of the tool; Comprehensive sensor system, integrating multiple sensors, for real-time monitoring of various parameters of the multi-motor system of the storage tool magazine; Edge computing and data processing system, including edge computing module and intelligent analysis module. The edge computing module performs data preprocessing and preliminary analysis on the device side. The intelligent analysis module performs in-depth analysis by integrating multiple sensor data and machine learning algorithms and generates an operation status report. The communication and network system includes an IoT gateway, a secure communication module and a remote monitoring module. The IoT gateway transmits sensor data and control instructions through a variety of communication protocols, and interconnects various systems for data exchange and collaborative work. The secure communication module uses encryption technology to process data transmission encryption and performs access control through an identity authentication mechanism. The remote monitoring module performs remote system status viewing and control through a secure channel, monitors equipment operation, and sends alarms and notifications when an abnormality is detected, and performs remote diagnosis and maintenance together with the secure communication module. The central control system is used to coordinate the operation of each system and perform real-time monitoring and intelligent analysis of sensor data.

2. The information monitoring device for the tool storage magazine multi-motor system according to claim 1 is characterized in that: It also includes an intelligent predictive maintenance system, the intelligent predictive maintenance system comprising: A historical data storage module, through which the historical operation data of the system is acquired and stored; A data analysis and model training module, which analyzes the historical operation data, identifies failure modes, and trains a failure prediction model using a machine learning platform; The data collection and prediction module collects system operation data in real time, uses the trained fault prediction model to perform real-time prediction, and obtains fault prediction results; The maintenance suggestion generation module analyzes and generates maintenance suggestions through a rule engine based on the fault prediction results to perform preventive maintenance.

3. The information monitoring device for the tool storage magazine multi-motor system according to claim 2 is characterized in that: The fault prediction model includes: The data input layer receives and processes multi-dimensional real-time data from the integrated sensor system and inputs it in parallel through multiple channels; The feature extraction layer uses convolutional neural networks to extract key features from the input data and captures spatial patterns and changing trends in sensor data through automated feature learning; The sequence processing layer uses a hybrid model combining a long short-term memory network and a gated recurrent unit to process time series data and analyze data changes at different time points during the operation of the tool. The long short-term memory network is used to capture the long-term dependencies generated during the operation of the warehouse tool magazine multi-motor system, and the gated recurrent unit is used to simplify the structure of the hybrid model and accelerate the training process to process short-term dependencies. The data fusion layer combines the features of multi-source data to fuse the features of different sensor data; The output layer generates the fault prediction result, which is a specific fault type; The loss function calculates the error between the fault prediction result and the actual situation through an adaptive weighted cross entropy loss function.

4. The information monitoring device for a tool storage magazine multi-motor system according to claim 1, characterized in that: Also included is a communication optimization system, the communication optimization system comprising: A historical data analysis module, which acquires historical communication data and sensor data, analyzes the correlation between the historical communication data and historical network performance, and obtains a first correlation result; A real-time data monitoring module obtains current communication status data and sensor real-time data, analyzes the correlation between current communication data and current network performance, and obtains a second correlation result; The communication optimization algorithm module optimizes the communication strategy and adjusts relevant communication parameters according to the first association result and the second association result to obtain the optimal performance of the communication network.

5. The information monitoring device for the tool storage magazine multi-motor system according to claim 4 is characterized in that: Communication optimization algorithms include: Dynamic spectrum management algorithm, which uses artificial intelligence algorithms to monitor spectrum usage in real time, predict possible interference, and dynamically adjust spectrum allocation strategies; Intelligent routing optimization algorithm, which uses deep learning algorithm to optimize data transmission paths in real time and dynamically adjust routing strategies according to network load, transmission delay and bandwidth requirements; The traffic control and congestion management algorithm predicts network traffic trends through machine learning models and dynamically adjusts traffic control parameters to prevent and alleviate network congestion.

6. The information monitoring device for a tool storage magazine multi-motor system according to claim 1, characterized in that: The intelligent predictive maintenance system and edge computing module are combined through distributed computing and collaborative analysis, including: The edge computing module processes sensor data in parallel on the device side and decomposes the preprocessing task into multiple subtasks; The edge computing module and the intelligent predictive maintenance system perform data synchronization, and the edge computing module transmits the processed data to the cloud in real time through the gateway; The intelligent predictive maintenance system processes preliminary analysis results from multiple edge computing modules in parallel in the cloud, and combines historical data with real-time data for in-depth analysis and model optimization; The intelligent predictive maintenance system dynamically adjusts the parameters of the fault prediction model according to the in-depth analysis results of the cloud. The optimized model parameters are synchronized to each edge computing module through the Internet of Things gateway, and the edge computing module applies the optimized model in real time to predict faults.

7. The information monitoring device for a tool storage magazine multi-motor system according to claim 6, characterized in that: The intelligent predictive maintenance system processes the preliminary analysis results from multiple edge computing modules in parallel in the cloud, combines historical data with real-time data for in-depth analysis and model optimization, including: Decompose the sensor data into hourly data blocks, and assign each hourly data block as a subtask to different cloud computing nodes for parallel processing; Use convolutional neural network models to process sensor data and identify abnormal patterns, and use long short-term memory network models to analyze time series data, capture time dependencies and predict future trends; The performance of each model was evaluated through cross-validation, and the hyperparameters of the long short-term memory network model were adjusted using Bayesian optimization to obtain the final fault prediction model.

8. The information monitoring method of the multi-motor system of the storage tool magazine is characterized in that: The information monitoring device used in the multi-motor system of the tool storage magazine as described in claims 1-7 comprises: Start and control multiple motors to rotate the storage tool magazine, grab and replace tools; Real-time monitoring and collection of various parameter data of the multi-motor system of the storage tool magazine; Preprocess and preliminarily analyze the collected data, and use machine learning algorithms for in-depth analysis to generate operating status reports; The data is encrypted for transmission, the parameter data are monitored in real time, and intelligent analysis is performed to adjust the operating parameters of the multi-motor system.

9. The information monitoring method of the tool storage magazine multi-motor system according to claim 8 is characterized in that: Also includes: Acquire and store historical operation data of the system; Analyze the historical operation data, identify failure modes, and train a failure prediction model using a machine learning platform; Collect system operation data in real time, use the trained fault prediction model to perform real-time prediction, and obtain fault prediction results; According to the fault prediction results, maintenance suggestions are generated through the rule engine to perform preventive maintenance.

10. The information monitoring method of the tool storage magazine multi-motor system according to claim 8, characterized in that: Also includes: Acquire historical communication data and sensor data, analyze the correlation between the historical communication data and historical network performance, and obtain a first correlation result; Acquire current communication status data and sensor real-time data, analyze the correlation between current communication data and current network performance, and obtain a second correlation result; According to the first association result and the second association result, the communication strategy is optimized and the relevant communication parameters are adjusted to obtain the optimal performance of the communication network.

Citation Information

Patent Citations

  • Communication transmission equipment data supervision method and system based on big data

    CN117498958A

  • Remote monitoring and fault prediction system for water chiller

    CN118194150A

  • New energy mine truck battery fault prediction method based on RNN recurrent neural network

    CN118519043A

  • Power equipment health monitoring system and method based on machine learning and edge computing

    CN118552178A

  • Automatic door operation state real-time monitoring and fault early warning management system

    CN118837133A

Cited By

  • Intelligent operation and maintenance monitoring system, method and equipment based on water pumping station

    CN119333373A

  • Machine tool management system based on big data analysis

    CN119863229A

  • Digital monitoring system of driving motor for logistics equipment

    CN121254764A

  • Marine surveying and mapping base station control system and method

    CN121397039A

  • Marine survey base station control system and method

    CN121397039B