Data self-acquisition system for pig casting machine and intelligent cast iron production line

Abstract

The invention discloses a data self-acquisition system for a pig casting machine and an intelligent cast iron production line, and relates to the technical field of intelligent cast iron production, the data self-acquisition system comprises a data acquisition module, an image acquisition module, an edge calculation module and an AI data analysis module, the data acquisition module and the image acquisition module are connected with the edge calculation module through a CAN bus, the edge calculation module is connected to the AI data analysis module through database sharing, and the AI data analysis module is used for carrying out production optimization control according to the collected production parameters. By installing the AI data analysis module, AI analysis and prediction functions of multi-dimensional production parameters of the pig casting machine are achieved, the problem that in traditional cast iron production, deep data analysis of production working conditions and equipment states is lacked is solved, manual judgment errors are reduced, the accuracy of the production process is improved, and the production efficiency and the product quality are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent cast iron production, and in particular to a data self-collection system for a cast iron machine and an intelligent cast iron production line. Background Art

[0002] In the production process of existing cast iron machines, due to incomplete data collection methods and untimely data processing, production efficiency is often low and product quality is unstable. Especially in complex environments such as high temperature and high pressure, traditional data collection methods are difficult to achieve comprehensive monitoring and efficient processing.

[0003] The traditional cast iron production process usually relies on manual monitoring and adjustment, which is easily affected by human factors, resulting in low production efficiency, unstable product quality and frequent equipment failures. With the development of Industry 4.0 and the popularization of intelligent manufacturing, there is an urgent need for an intelligent system that can monitor production data in real time, make automatic adjustments, predict equipment failures and ensure safe production.

[0004] Patent document CN101758172B discloses a high-efficiency, long-life, safe roller-fixed cast iron machine. The above patent achieves reduced energy consumption, high efficiency, and safe operation, and meets the requirements of "energy saving, environmental protection, high efficiency, and longevity" in the metallurgical industry. However, the above patent cannot realize the AI ​​analysis and prediction functions of the multi-dimensional parameters of cast iron machine production.

[0005] Patent document CN101758173B discloses a cast iron mold for a cast iron machine. The above patent achieves a service life increase of more than two times, significantly reduces the number of shutdowns for maintenance and replacement of cast iron molds, significantly improves the comprehensive production capacity of the cast iron machine, greatly reduces the equipment operating costs of manufacturers, and significantly improves economic benefits. However, the above patent cannot achieve the function of automatically monitoring and adjusting process parameters.

[0006] Patent document CN103204353B discloses a chain-belt tray conveyor system, which significantly improves the use effect and safety performance of the iron block, mineral or block material conveying system, prolongs the service life, and prevents the chain-belt tray conveyor from causing safety accidents due to chain breakage. The conveyor system is safe and reliable, with high production capacity and production efficiency, reaching 300 to 500 tons per hour and 4,000 to 10,000 tons per day, but the above patent cannot realize the fault monitoring and maintenance function of the equipment operation.

[0007] Patent document CN101775452B discloses a method for smelting pig iron for ultra-low sulfur, low silicon and low titanium grey ductile iron. The above patent realizes the production of large high-quality ductile iron parts that are particularly suitable for large cast ferritic ductile iron and wind power generation, nuclear fuel storage and transportation containers, etc., filling the gap in such products. However, the above patent cannot realize the monitoring and identification function of production safety.

[0008] In summary, the above patents cannot realize the AI ​​analysis and prediction functions of multi-dimensional parameters of cast iron machine production, the automatic monitoring and adjustment of process parameters, the fault monitoring and maintenance functions of equipment operation, and the monitoring and identification functions of production safety, resulting in low production efficiency, equipment failures cannot be promptly maintained, poor product quality, and great safety hazards; To this end, the present application proposes a data self-collection system and an intelligent cast iron production line for cast iron machines that can realize AI analysis and prediction functions of multi-dimensional parameters of cast iron machine production, automatic monitoring and adjustment of process parameters, fault monitoring and maintenance functions for equipment operation, and monitoring and identification functions for production safety. Summary of the invention

[0009] The purpose of the present invention is to provide a data self-collection system for a cast iron machine and an intelligent cast iron production line, so as to solve the technical problems proposed in the above background technology that the AI ​​analysis and prediction function of the multi-dimensional parameters of the cast iron machine production, the function of automatic monitoring and adjustment of the process parameters, the fault monitoring and maintenance function of the equipment operation and the monitoring and identification function of production safety cannot be realized, resulting in low production efficiency, no immediate maintenance of equipment failures, poor product quality and great safety hazards.

[0010] To achieve the above object, the present invention provides the following technical solutions: a data self-collection system for a cast iron machine, comprising a data acquisition module, an image acquisition module, an edge computing module and an AI data analysis module, wherein the data acquisition module and the image acquisition module are connected to the edge computing module via a CAN bus, the edge computing module is connected to the AI ​​data analysis module via database sharing, and the AI ​​data analysis module is used to perform production optimization control according to the collected production parameters; The AI ​​data analysis module includes: an AI prediction model unit, a deep learning optimization unit and an anomaly detection alarm unit; The AI ​​prediction model unit uses an AI model to train historical production data and real-time sensor data, and uses a prediction algorithm to predict faults in the iron casting process; The deep learning optimization unit optimizes the decision-making process through an adaptive learning algorithm, automatically adjusts the production parameters of the cast iron machine, and provides a customized optimization model to match each production equipment and production conditions; The anomaly detection alarm unit classifies the cast iron machine data through an AI anomaly detection algorithm, quickly identifies anomalies, and provides visual alarms, sound and light alarms, and SMS / email notifications.

[0011] Preferably, the data acquisition module is used to monitor and collect production parameters in the production process of the cast iron machine in real time; The data acquisition module includes: a temperature sensor unit, a pressure sensor unit and a vibration sensor unit; The temperature sensor unit is installed in the furnace, mold and cooling system. The thermocouple / infrared temperature sensor is used to collect temperature data in cast iron production in real time. The collection frequency is 1 second / time. It has an integrated self-calibration function and provides a data correction algorithm to deal with sensor drift. The pressure sensor unit is installed in the hydraulic system and casting molding cavity of the iron casting machine. The pressure sensor is used to detect the pressure changes inside the equipment and provide real-time feedback; The vibration sensor unit is deployed on the mold conveyor belt and feeding mechanism of the cast iron machine to detect mechanical vibration in real time. It adapts to multi-dimensional detection, namely the X / Y / Z axis direction, and uses the FFT algorithm to perform frequency domain analysis on the vibration signal to identify abnormal vibration frequencies and predict mechanical wear and failure.

[0012] Preferably, the image acquisition module is used to acquire real-time production images of the iron casting machine production process and the iron castings; The image acquisition module includes: industrial camera unit, infrared thermal imaging unit and AI image recognition unit; The industrial camera unit uses a CCD industrial camera, which automatically adjusts the focus and aperture through software control to adapt to light changes in different environments and ensure clear capture of the surface features of cast iron parts; The infrared thermal imaging unit covers the furnace area, cooling area and die-out area of ​​the cast iron machine to capture the temperature distribution. The thermal imaging data is linked with the temperature sensor data to improve the overall detection accuracy by comparing the temperature results of the two. The AI ​​image recognition unit uses a convolutional neural network to identify defects on the strip surface of castings, automatically identifying cracks, pores and shrinkage defects. The system automatically records and marks the defect location, generates a real-time alarm and prompts the operator to check.

[0013] Preferably, the edge computing module is used to process and transmit the data collected and transmitted by the data acquisition module and the image acquisition module in real time; The edge computing module includes: edge terminal equipment, edge computing algorithms, and edge-cloud dynamic switching; The edge terminal equipment uses an industrial-grade edge computing terminal with a quad-core CPU, supports industrial Ethernet communication, and has real-time data processing capabilities; The edge computing algorithm integrates the stream data processing framework, applies fast anomaly detection algorithm and real-time classification algorithm, analyzes edge data, adopts data filtering mechanism, removes redundant and abnormal data, transmits valid data to the cloud, and reduces transmission bandwidth pressure; The dynamic switching between edge and cloud is an intelligent transmission mechanism. The edge computing terminal automatically determines the amount of data and decides to upload the data to the cloud for in-depth analysis to optimize data transmission efficiency.

[0014] Preferably, the edge computing module further includes a data communication module, which is used to effectively transmit the collected production-related data; The data communication module includes: a wireless transmission unit, a wired transmission unit and a communication protocol conversion unit; The wireless transmission unit supports 5G high-speed transmission protocol, ensuring real-time transmission of high-definition images, videos and large-scale production data; The wired transmission unit is equipped with a Gigabit Ethernet interface, which is suitable for high-frequency data transmission and supports the network automatic switching mechanism to ensure that data transmission is not interrupted when the network fails; The communication protocol conversion unit supports a variety of industrial communication protocols to ensure seamless connection and data interoperability of various types of equipment.

[0015] Preferably, the AI ​​data analysis module is connected to an intelligent working condition adjustment module via a data communication module, and the intelligent working condition adjustment module is used to adjust the working condition by combining the data of the data acquisition module and the image acquisition module; The intelligent working condition adjustment module includes: an environmental monitoring unit, a dynamic working condition adjustment unit and an intelligent adjustment controller; The environmental monitoring unit arranges environmental sensors around the iron casting machine to collect external environmental data in real time and analyze the potential impact of the environment on the iron casting machine production; The dynamic working condition adjustment unit uses AI algorithms to adjust production process parameters in real time according to environmental monitoring data and the current working status of the cast iron machine to maintain the optimal working condition; The intelligent adjustment controller intelligently adjusts the apartment parameters of the cast iron machine according to the changes in materials and the degree of equipment wear to ensure stable product quality.

[0016] Preferably, the AI ​​data analysis module is connected to a remote fault prediction and maintenance module via a data communication module, and the remote fault prediction and maintenance module is used to perform remote fault prediction and maintenance on the cast iron machine; The remote fault prediction and maintenance module includes: remote monitoring platform, fault prediction algorithm and remote maintenance guidance unit; The remote monitoring platform combines cloud and edge computing to remotely monitor the real-time status of the cast iron machine and the operating data of key components; The fault prediction algorithm uses AI algorithms to analyze current data for anomalies based on big data and historical fault cases, predict potential equipment failures, issue alarms in advance, and propose recommended maintenance time windows; The remote maintenance guidance unit uses AR technology to remotely view the internal status of the equipment and obtain maintenance guidance suggestions. The system provides virtual maintenance operation instructions to reduce excessive reliance on manual professional skills.

[0017] Preferably, the AI ​​data analysis module is connected to an intelligent safety protection module via a data communication module, and the intelligent safety protection module is used to monitor dangerous situations in production in real time; The intelligent safety protection module includes: personnel detection unit, dynamic hazard prediction and emergency shutdown mechanism; The personnel detection unit, i.e. the system is equipped with intelligent cameras and AI algorithms, which monitor the range of operators’ activities in real time, determine if a person has entered a dangerous area, and automatically trigger safety alarms and emergency shutdown mechanisms; Dynamic hazard prediction uses AI algorithms to combine equipment status and environmental data to predict potential dangerous situations, including over-temperature and equipment abnormalities, and automatically implements protective measures, including reducing equipment operating speed and early warning prompts; The system has a built-in emergency stop control unit. When the danger persists, the system automatically executes the emergency stop mechanism to ensure the safety of equipment and personnel.

[0018] Preferably, the intelligent cast iron production line includes: an intelligent pouring module, an intelligent cooling module, an intelligent transmission logistics module, an automated detection module, an intelligent energy efficiency optimization module, a dynamic maintenance self-inspection module, a production line safety protection module and an intelligent production scheduling module. The intelligent pouring module, the intelligent cooling module and the intelligent transmission logistics module are all equipped with temperature sensor units, pressure sensor units and vibration sensor units, and pouring, cooling and material transmission are performed during the production process. The automated detection module is equipped with an industrial camera and an AI image recognition unit to automatically detect the quality of castings.

[0019] Preferably, the intelligent energy efficiency optimization module dynamically optimizes energy consumption through an internally installed intelligent working condition adjustment module, the dynamic maintenance self-inspection module performs dynamic maintenance of cast iron machine production in combination with the prediction results of the remote fault prediction and maintenance module, the production line safety protection module responds to sudden dangers through analysis by the intelligent safety protection module, and the intelligent production scheduling module uses the analysis results of the AI ​​data analysis module to intelligently schedule production tasks and automatically adjust production rhythm and resource allocation.

[0020] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention realizes the AI ​​analysis and prediction function of multi-dimensional parameters of cast iron machine production by installing an AI data analysis module, solves the problem of lack of in-depth data analysis of production conditions and equipment status in traditional cast iron production, reduces human judgment errors, improves the accuracy of the production process, prevents production fluctuations and equipment failures, and improves production efficiency and product quality; 2. The present invention realizes the function of automatically monitoring and adjusting the process parameters by installing an intelligent working condition adjustment module, solves the problem of unstable product quality caused by fluctuations in process parameters in the production line, reduces the error of manual adjustment, ensures the stability of the production line and the consistency of the products, and significantly improves the overall efficiency of the production line; 3. The present invention realizes the fault monitoring and maintenance function of equipment operation by installing a remote fault prediction and maintenance module, solves the problem of sudden fault downtime in traditional equipment maintenance methods, and reduces production interruptions and economic losses caused by equipment failures; 4. The present invention realizes the monitoring and identification function of production safety by installing an intelligent safety protection module, solves the problem of untimely and incomplete personnel safety protection in traditional production lines, and reduces the risk of safety accidents caused by operational errors or equipment failures. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a schematic diagram of the production line workflow of the present invention. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] See also Figure 1 , an embodiment provided by the present invention: a data self-collection system for a cast iron machine, comprising a data acquisition module, an image acquisition module, an edge computing module and an AI data analysis module, wherein the data acquisition module and the image acquisition module are connected to the edge computing module via a CAN bus, the edge computing module is connected to the AI ​​data analysis module via database sharing, and the AI ​​data analysis module is used to perform production optimization control according to the collected production parameters; The AI ​​data analysis module includes: an AI prediction model unit, a deep learning optimization unit and an anomaly detection alarm unit; The AI ​​prediction model unit uses an AI model to train historical production data and real-time sensor data, and uses a prediction algorithm to predict faults in the iron casting process; The deep learning optimization unit optimizes the decision-making process through an adaptive learning algorithm, automatically adjusts the production parameters of the cast iron machine, and provides a customized optimization model to match each production equipment and production conditions; The anomaly detection alarm unit uses an AI anomaly detection algorithm to classify the cast iron machine data, quickly identify anomalies, and provide visual alarms, sound and light alarms, and SMS / email notifications; Furthermore, the core algorithms of the AI ​​data analysis module are based on machine learning models and deep learning models, including regression analysis, which is used to analyze the historical trends of data such as temperature, pressure, and flow; classification algorithms compare the current status with historical data to determine whether the production line is in normal working condition; pattern recognition uses the trained AI model to identify specific patterns in the data, such as whether there are abnormal temperature fluctuations during cooling, abnormal pressure during pouring, etc.; The data collected by the data acquisition module and the image acquisition module are deeply analyzed to establish a change model of each parameter of the process flow and predict the future production status. The AI ​​analysis module identifies the trend of temperature changes in the normal production process based on the historical data of the temperature sensor on the production line, and compares it with the real-time temperature data to determine whether it is necessary to adjust the pouring speed or cooling speed of the intelligent pouring module and the intelligent cooling module. By analyzing the equipment vibration data, the normal vibration mode of the equipment operation is identified. When abnormal vibration is found, the system will issue an early warning to indicate possible equipment failure. After the AI ​​data analysis module analyzes the current data, it will make corresponding judgments and feed back to the production control system through the edge terminal or directly, triggering the automatic adjustment operation of the production line. The specific feedback and adjustment process includes: Process parameter optimization: The AI ​​analysis module automatically adjusts the operating parameters of the equipment according to the real-time changes in production conditions. For example, it adjusts the pouring speed, increases the water flow in the cooling section, optimizes the running speed of the conveyor belt, etc. Abnormal alarm: When the AI ​​analysis module analyzes potential problems (such as abnormal equipment vibration, high molten iron temperature or uneven cooling), the system will immediately alarm and push it to the operator's monitoring platform to ensure that the problem can be handled in a timely manner; Energy consumption optimization: By analyzing production energy consumption data (such as equipment power consumption and cooling water flow), the system can adjust the energy consumption mode of the equipment to optimize energy efficiency and reduce unnecessary energy waste.

[0024] See also Figure 1 , an embodiment provided by the present invention: a data self-collection system for an iron casting machine, wherein the data collection module is used for real-time monitoring and collection of production parameters in the production process of the iron casting machine; The data acquisition module includes: a temperature sensor unit, a pressure sensor unit and a vibration sensor unit; The temperature sensor unit is installed in the furnace, mold and cooling system. The thermocouple / infrared temperature sensor is used to collect temperature data in cast iron production in real time. The collection frequency is 1 second / time. It has an integrated self-calibration function and provides a data correction algorithm to deal with sensor drift. The pressure sensor unit is installed in the hydraulic system and casting molding cavity of the iron casting machine. The pressure sensor is used to detect the pressure changes inside the equipment and provide real-time feedback; The vibration sensor unit is deployed on the die conveyor belt and feeding mechanism of the cast iron machine to detect mechanical vibration in real time, adapt to multi-dimensional detection, i.e. X / Y / Z axis direction, use FFT algorithm to analyze the vibration signal in the frequency domain, identify abnormal vibration frequency, and predict mechanical wear and failure; The image acquisition module is used to acquire real-time production images of the iron casting machine production process and the iron castings; The image acquisition module includes: industrial camera unit, infrared thermal imaging unit and AI image recognition unit; The industrial camera unit uses a CCD industrial camera, which automatically adjusts the focus and aperture through software control to adapt to light changes in different environments and ensure clear capture of the surface features of cast iron parts; The infrared thermal imaging unit covers the furnace area, cooling area and die-out area of ​​the cast iron machine to capture the temperature distribution. The thermal imaging data is linked with the temperature sensor data to improve the overall detection accuracy by comparing the temperature results of the two. The AI ​​image recognition unit uses a convolutional neural network to identify defects on the casting strip surface, automatically identifying cracks, pores and shrinkage defects. The system automatically records and marks the defect location, generates a real-time alarm and prompts the operator to conduct an inspection; Furthermore, temperature sensors monitor the temperature of molten iron, cooling water and mold in the cast iron machine. Pressure sensors are installed in the pouring system and hydraulic system to monitor the pressure of the cast iron machine during operation. Vibration sensors are used to monitor the vibration of key equipment. Flow sensors monitor the water flow in the cooling system to ensure the stability of the cooling process. CCD industrial cameras are installed at several key locations of the cast iron production line, such as the molten iron pouring point, cooling section, casting outlet, etc., to ensure that the camera can clearly capture the flow of molten iron, the cooling state of the casting and the surface quality. The infrared thermal imaging unit covers the furnace area, cooling area and mold area of ​​the cast iron machine to capture the temperature distribution. The AI ​​image recognition system will conduct in-depth analysis of the image to identify whether there are abnormal conditions in the production process, such as molten iron overflow, surface defects (such as cracks, pores, etc.), casting deformation, etc. This process uses machine learning technology. The system learns the image features of normal and abnormal conditions through training samples, so as to identify abnormalities in time in actual production; The data from both are initially processed and transmitted through edge terminal devices, and enter the AI ​​data analysis module for in-depth analysis, thereby realizing intelligent monitoring and optimization of the entire cast iron production process.

[0025] See also Figure 1 , an embodiment provided by the present invention: a data self-collection system for a cast iron machine, wherein the edge computing module is used to perform real-time processing and transmission of data collected and transmitted by the data collection module and the image collection module; The edge computing module includes: edge terminal equipment, edge computing algorithms, and edge-cloud dynamic switching; The edge terminal equipment uses an industrial-grade edge computing terminal with a quad-core CPU, supports industrial Ethernet communication, and has real-time data processing capabilities; The edge computing algorithm integrates the stream data processing framework, applies fast anomaly detection algorithm and real-time classification algorithm, analyzes edge data, adopts data filtering mechanism, removes redundant and abnormal data, transmits valid data to the cloud, and reduces transmission bandwidth pressure; The dynamic switching between edge and cloud is an intelligent transmission mechanism. The edge computing terminal automatically determines the amount of data and decides to upload the data to the cloud for in-depth analysis to optimize data transmission efficiency. The edge computing module also includes a data communication module, which is used to effectively transmit the collected production-related data; The data communication module includes: a wireless transmission unit, a wired transmission unit and a communication protocol conversion unit; The wireless transmission unit supports 5G high-speed transmission protocol, ensuring real-time transmission of high-definition images, videos and large-scale production data; The wired transmission unit is equipped with a Gigabit Ethernet interface, which is suitable for high-frequency data transmission and supports the network automatic switching mechanism to ensure that data transmission is not interrupted when the network fails; The communication protocol conversion unit supports a variety of industrial communication protocols to ensure seamless connection and data intercommunication of various devices; Furthermore, the edge computing module receives data from the data acquisition module and the image acquisition module, including physical parameter data (such as temperature, pressure, flow) and image video data. For the data collected by the sensor, data filtering and denoising will be performed first. For image and video data, the edge computing module will use data compression technology to reduce the bandwidth and storage space occupied during transmission and storage. The edge computing module uses embedded computing units and algorithms to perform local calculations immediately after data access. For example, for trend analysis of real-time data such as temperature and pressure, when certain parameters are close to the set warning values, the edge computing module will immediately issue a local warning and respond quickly to avoid potential production accidents. The edge computing module pre-loads a trained AI model and can perform intelligent reasoning on image data. For example, the AI ​​model can be used to identify surface defects of castings and signs of equipment failure. By performing AI reasoning at the edge, real-time monitoring and optimization of the production process can be achieved; The data communication module is responsible for transmitting data to the central control system or the cloud. In wired transmission, the data communication module uses redundant link technology to ensure that when the main transmission channel fails, the backup channel can seamlessly take over to ensure the reliability of data transmission. In wireless transmission, the module has anti-interference ability to ensure signal stability in the working environment of the cast iron machine. In order to ensure the security of transmitted data, the data communication module uses AES encryption technology to encrypt the transmitted data to prevent data leakage or tampering during the transmission process. At the same time, the module supports identity authentication and access control, and only authorized devices and systems can access the transmitted data.

[0026] See also Figure 1 , an embodiment provided by the present invention: a data self-collection system for a cast iron machine, wherein the AI ​​data analysis module is connected to an intelligent working condition adjustment module through a data communication module, and the intelligent working condition adjustment module is used to adjust the working condition by combining the data of the data acquisition module and the image acquisition module; The intelligent working condition adjustment module includes: an environmental monitoring unit, a dynamic working condition adjustment unit and an intelligent adjustment controller; The environmental monitoring unit arranges environmental sensors around the iron casting machine to collect external environmental data in real time and analyze the potential impact of the environment on the iron casting machine production; The dynamic working condition adjustment unit uses AI algorithms to adjust production process parameters in real time according to environmental monitoring data and the current working status of the cast iron machine to maintain the optimal working condition; The intelligent control controller intelligently adjusts the parameters of the cast iron machine according to the changes in materials and the degree of equipment wear to ensure stable product quality; Furthermore, the module has built-in gas and dust sensors to continuously monitor the concentration of harmful gases and dust in the production environment. When a gas leak is detected or the dust concentration exceeds the standard, the system will automatically turn on the ventilation device or trigger an alarm, and record relevant data for subsequent analysis. The intelligent working condition adjustment module first monitors the key process parameters on the cast iron production line in real time through the data acquisition module and the image acquisition module, including furnace temperature, casting speed, cooling rate, mold status, etc. These data will be transmitted to the edge computing module or the central control system, and the AI ​​algorithm equipped in the module will perform real-time analysis based on historical production data and current working condition parameters. For example, by analyzing the trend of furnace temperature changes, it is predicted whether cast iron cooling will be abnormal. The algorithm will integrate multi-dimensional parameters and use machine learning models to analyze the current production conditions, identify parameter changes that may cause product quality fluctuations, and based on the analysis results, the intelligent working condition adjustment module will automatically adjust the operating parameters of the production equipment. For example, when it is detected that cast iron is cooling too fast, the module will instruct the cooling system to slow down the cooling rate or increase the flow of cooling water through the edge computing module to maintain the stability of casting quality. Through the feedback control loop, the module will continuously adjust the working conditions according to real-time data to ensure that the system is in the optimal operating state. The adjustment operation covers the power of the heater, the adjustment of the conveying speed, the optimization of the casting time, etc.

[0027] See also Figure 1 , an embodiment provided by the present invention: a data self-collection system for an iron casting machine, wherein the AI ​​data analysis module is connected to a remote fault prediction and maintenance module through a data communication module, and the remote fault prediction and maintenance module is used to perform remote fault prediction and maintenance on the iron casting machine; The remote fault prediction and maintenance module includes: remote monitoring platform, fault prediction algorithm and remote maintenance guidance unit; The remote monitoring platform combines cloud and edge computing to remotely monitor the real-time status of the cast iron machine and the operating data of key components; The fault prediction algorithm uses AI algorithms to analyze current data for anomalies based on big data and historical fault cases, predict potential equipment failures, issue alarms in advance, and propose recommended maintenance time windows; The remote maintenance guidance unit uses AR technology to remotely view the internal status of the equipment and obtain maintenance guidance suggestions. The system provides virtual maintenance operation instructions to reduce excessive reliance on manual professional skills. Furthermore, the remote fault prediction and maintenance module collects the operating status data of the production equipment in real time through equipment sensors (such as vibration sensors, temperature sensors, pressure sensors, etc.). Including the speed of the motor, the vibration frequency of the equipment, temperature changes, equipment workload, etc., the fault prediction algorithm establishes a fault prediction model based on a large amount of historical equipment operation data. These models can identify the characteristic signals of the equipment before the failure through machine learning and big data analysis. For example, by analyzing the changes in the vibration spectrum, the wear of the internal bearings of the equipment can be predicted, or signs of leakage in the pumping system can be found. When the system detects abnormal equipment status (such as continuous temperature increase or vibration beyond the normal range), the fault prediction module will issue an alarm and send the prediction results to the maintenance personnel or operator through the remote interface. The system will provide a detailed diagnostic report indicating the possible fault location and cause. At the same time, the module supports remote expert diagnosis function, allowing external technical experts to access the system through the network, view equipment operation data, and remotely assist on-site personnel in fault analysis and processing.

[0028] See also Figure 1 , an embodiment provided by the present invention: a data self-collection system for a cast iron machine, wherein the AI ​​data analysis module is connected to an intelligent safety protection module via a data communication module, and the intelligent safety protection module is used to monitor dangerous situations in production in real time; The intelligent safety protection module includes: personnel detection unit, dynamic hazard prediction and emergency shutdown mechanism; The personnel detection unit, i.e. the system is equipped with intelligent cameras and AI algorithms, which monitor the range of operators’ activities in real time, determine if a person has entered a dangerous area, and automatically trigger safety alarms and emergency shutdown mechanisms; Dynamic hazard prediction uses AI algorithms to combine equipment status and environmental data to predict potential dangerous situations, including over-temperature and equipment abnormalities, and automatically implements protective measures, including reducing equipment operating speed and early warning prompts; The system has a built-in emergency stop control unit. When the danger persists, the system automatically executes the emergency stop mechanism to ensure the safety of equipment and personnel; Furthermore, the intelligent safety protection module uses intelligent cameras and sensors to monitor the conditions of dangerous areas such as high-temperature areas and mechanical moving parts in the production line in real time. For example, when a person or other object approaches a dangerous area, the sensor will issue a warning signal, and the image captured by the camera will be transmitted to the edge computing module and the central control system for analysis in real time. Through the AI ​​algorithm, the module can identify whether the behavior of the on-site personnel poses a safety hazard. For example, when the AI ​​system detects that a worker has stayed in a dangerous area for too long or entered an unauthorized area, the system will immediately issue an audible and visual alarm and notify the safety manager to handle it. If the system detects a serious safety threat, such as equipment failure that may cause personal injury or abnormally high temperature, the module will automatically start the emergency shutdown mechanism and immediately stop the operation of the production equipment to ensure the safety of personnel. The intelligent safety protection module is linked with the protective equipment on the production line (such as safety barriers, emergency stop buttons, protective doors, etc.). When the system issues a safety alarm, these devices will respond immediately and take safety measures. If a worker mistakenly enters a dangerous area, the safety protection door will automatically close to prevent the worker from further contact with dangerous equipment.

[0029] Working principle: First, the data acquisition module and the image acquisition module are used to obtain multi-dimensional data of the production process in real time. These data include casting temperature, material quality, production speed, equipment status, etc. The edge computing module performs preliminary analysis and processing on these data to ensure fast local processing and response during the production process without transmitting all data to a remote server; The received data is further processed by the AI ​​data analysis module, which combines historical data and machine learning algorithms to conduct in-depth analysis and prediction of the current production line status. The intelligent working condition adjustment module automatically optimizes the process parameters of the production line based on these analysis results, adjusts the furnace temperature, cooling rate, etc., to ensure the stability of the production process. At the same time, the remote fault prediction and maintenance module monitors the operating status of the equipment, identifies potential faults in advance, and promptly initiates the remote maintenance process to ensure the continuous and stable operation of the production line; During the production process, the intelligent safety protection module continuously monitors the safety of the environment and equipment to ensure that workers and equipment operate within a safe range. If an abnormal situation is detected (such as dangerous behavior or equipment failure), the system will immediately activate the early warning mechanism or even automatically shut down the machine.

[0030] It will be apparent to those skilled in the art that the 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 the spirit or essential features of the invention. 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, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A data self-collection system for a cast iron machine, comprising a data acquisition module, an image acquisition module, an edge computing module and an AI data analysis module, characterized in that: The data acquisition module and the image acquisition module are connected to the edge computing module via a CAN bus, and the edge computing module is connected to the AI ​​data analysis module via database sharing, and the AI ​​data analysis module is used to perform production optimization control according to the collected production parameters; The AI ​​data analysis module includes: an AI prediction model unit, a deep learning optimization unit and an anomaly detection alarm unit; The AI ​​prediction model unit uses an AI model to train historical production data and real-time sensor data, and uses a prediction algorithm to predict faults in the iron casting process; The deep learning optimization unit optimizes the decision-making process through an adaptive learning algorithm, automatically adjusts the production parameters of the cast iron machine, and provides a customized optimization model to match each production equipment and production conditions; The anomaly detection alarm unit classifies the cast iron machine data through an AI anomaly detection algorithm, quickly identifies anomalies, and provides visual alarms, sound and light alarms, and SMS / email notifications.

2. The data self-collection system for an iron casting machine according to claim 1, characterized in that: The data acquisition module is used to monitor and collect production parameters in the production process of the cast iron machine in real time; The data acquisition module includes: a temperature sensor unit, a pressure sensor unit and a vibration sensor unit; The temperature sensor unit is installed in the furnace, mold and cooling system. It uses thermocouple / infrared temperature sensors to collect temperature data in cast iron production in real time. The collection frequency is 1 second / time. It has an integrated self-calibration function and provides a data correction algorithm to deal with sensor drift. The pressure sensor unit is installed in the hydraulic system and casting molding cavity of the iron casting machine. The pressure sensor is used to detect the pressure changes inside the equipment and provide real-time feedback; The vibration sensor unit is deployed on the mold conveyor belt and feeding mechanism of the cast iron machine to detect mechanical vibration in real time. It adapts to multi-dimensional detection, namely the X / Y / Z axis direction, and uses the FFT algorithm to perform frequency domain analysis on the vibration signal, identify abnormal vibration frequencies, and predict mechanical wear and failure.

3. The data self-collection system for an iron casting machine according to claim 1, characterized in that: The image acquisition module is used to acquire real-time production images of the iron casting machine production process and the iron castings; The image acquisition module includes: industrial camera unit, infrared thermal imaging unit and AI image recognition unit; The industrial camera unit uses a CCD industrial camera, which automatically adjusts the focus and aperture through software control to adapt to light changes in different environments and ensure clear capture of the surface features of cast iron parts; The infrared thermal imaging unit covers the furnace area, cooling area and die-out area of ​​the cast iron machine to capture the temperature distribution. The thermal imaging data is linked with the temperature sensor data to improve the overall detection accuracy by comparing the temperature results of the two. The AI ​​image recognition unit uses a convolutional neural network to identify defects on the strip surface of castings, automatically identifying cracks, pores and shrinkage defects. The system automatically records and marks the defect location, generates a real-time alarm and prompts the operator to conduct inspections.

4. The data self-collection system for an iron casting machine according to claim 1, characterized in that: The edge computing module is used to process and transmit the data collected and transmitted by the data acquisition module and the image acquisition module in real time; The edge computing module includes: edge terminal equipment, edge computing algorithms, and edge-cloud dynamic switching; The edge terminal equipment uses an industrial-grade edge computing terminal with a quad-core CPU, supports industrial Ethernet communication, and has real-time data processing capabilities; The edge computing algorithm integrates the stream data processing framework, applies fast anomaly detection algorithm and real-time classification algorithm, analyzes edge data, adopts data filtering mechanism, removes redundant and abnormal data, transmits valid data to the cloud, and reduces transmission bandwidth pressure; The dynamic switching between edge and cloud is an intelligent transmission mechanism. The edge computing terminal automatically determines the amount of data and decides to upload the data to the cloud for in-depth analysis to optimize data transmission efficiency.

5. The data self-collection system for an iron casting machine according to claim 1, characterized in that: The edge computing module also includes a data communication module, which is used to effectively transmit the collected production-related data; The data communication module includes: a wireless transmission unit, a wired transmission unit and a communication protocol conversion unit; The wireless transmission unit supports 5G high-speed transmission protocol, ensuring real-time transmission of high-definition images, videos and large-scale production data; The wired transmission unit is equipped with a Gigabit Ethernet interface, which is suitable for high-frequency data transmission and supports the network automatic switching mechanism to ensure that data transmission is not interrupted when the network fails; The communication protocol conversion unit supports a variety of industrial communication protocols to ensure seamless connection and data interoperability of various types of equipment.

6. The data self-collection system for an iron casting machine according to claim 1, characterized in that: The AI ​​data analysis module is connected to an intelligent working condition adjustment module through a data communication module, and the intelligent working condition adjustment module is used to adjust the working condition by combining the data of the data acquisition module and the image acquisition module; The intelligent working condition adjustment module includes: an environmental monitoring unit, a dynamic working condition adjustment unit and an intelligent adjustment controller; The environmental monitoring unit arranges environmental sensors around the iron casting machine to collect external environmental data in real time and analyze the potential impact of the environment on the iron casting machine production; The dynamic working condition adjustment unit uses AI algorithms to adjust production process parameters in real time according to environmental monitoring data and the current working status of the cast iron machine to maintain the optimal working condition; The intelligent adjustment controller intelligently adjusts the apartment parameters of the cast iron machine according to the changes in materials and the degree of equipment wear to ensure stable product quality.

7. The data self-collection system for an iron casting machine according to claim 1, characterized in that: The AI ​​data analysis module is connected to a remote fault prediction and maintenance module through a data communication module, and the remote fault prediction and maintenance module is used to perform remote fault prediction and maintenance on the cast iron machine; The remote fault prediction and maintenance module includes: remote monitoring platform, fault prediction algorithm and remote maintenance guidance unit; The remote monitoring platform combines cloud and edge computing to remotely monitor the real-time status of the cast iron machine and the operating data of key components; The fault prediction algorithm uses AI algorithms to analyze current data for anomalies based on big data and historical fault cases, predict potential equipment failures, issue alarms in advance, and propose recommended maintenance time windows; The remote maintenance guidance unit uses AR technology to remotely view the internal status of the equipment and obtain maintenance guidance suggestions. The system provides virtual maintenance operation instructions to reduce excessive reliance on manual professional skills.

8. The data self-collection system for an iron casting machine according to claim 1, characterized in that: The AI ​​data analysis module is connected to an intelligent safety protection module via a data communication module, and the intelligent safety protection module is used to monitor dangerous situations in production in real time; The intelligent safety protection module includes: personnel detection unit, dynamic hazard prediction and emergency shutdown mechanism; The personnel detection unit, i.e. the system is equipped with intelligent cameras and AI algorithms, which monitor the range of operators’ activities in real time, determine if a person has entered a dangerous area, and automatically trigger safety alarms and emergency shutdown mechanisms; Dynamic hazard prediction uses AI algorithms to combine equipment status and environmental data to predict potential dangerous situations, including over-temperature and equipment abnormalities, and automatically implements protective measures, including reducing equipment operating speed and early warning prompts; The system has a built-in emergency stop control unit. When the danger persists, the system automatically executes the emergency stop mechanism to ensure the safety of equipment and personnel.

9. An intelligent cast iron production line for a cast iron machine, applicable to the data self-collection system for a cast iron machine according to any one of claims 1 to 8, characterized in that: The intelligent cast iron production line includes: an intelligent pouring module, an intelligent cooling module, an intelligent transmission and logistics module, an automatic detection module, an intelligent energy efficiency optimization module, a dynamic maintenance self-inspection module, a production line safety protection module and an intelligent production scheduling module. The intelligent pouring module, the intelligent cooling module and the intelligent transmission and logistics module are all equipped with temperature sensor units, pressure sensor units and vibration sensor units, and pouring, cooling and material transmission are performed during the production process. The automatic detection module is equipped with an industrial camera and an AI image recognition unit to automatically detect the quality of castings.

10. The intelligent cast iron production line for a cast iron machine according to claim 9, characterized in that: The intelligent energy efficiency optimization module dynamically optimizes energy consumption through the internally installed intelligent working condition adjustment module. The dynamic maintenance self-inspection module performs dynamic maintenance of the cast iron machine production in combination with the prediction results of the remote fault prediction and maintenance module. The production line safety protection module responds to sudden dangers through the analysis of the intelligent safety protection module. The intelligent production scheduling module uses the analysis results of the AI ​​data analysis module to intelligently schedule production tasks and automatically adjust the production rhythm and resource allocation.

Images