Ladle temperature tracking and scheduling system and method based on AI data acquisition

Abstract

The invention belongs to the technical field of steel production, and discloses a ladle temperature tracking and scheduling system and method based on AI data acquisition, and the system comprises a data acquisition module, a data transmission module, a data processing and analysis module, an intelligent scheduling execution module, and a monitoring and management module. Non-contact and real-time monitoring of the temperature of the hot metal ladle is achieved by means of the infrared camera, the change trend of the temperature of the hot metal ladle in a period of time in the future can be accurately predicted in cooperation with the temperature prediction model, and compared with a traditional single-point temperature measurement or regular sampling inspection mode, the system can obtain continuous change data of the temperature of the hot metal ladle, and the accuracy of temperature measurement is improved. The situation that the steelmaking process is affected by too low molten iron temperature due to untimely or inaccurate temperature monitoring is avoided, the transportation path and the transportation speed can be adjusted in time or heat preservation measures are taken by predicting temperature changes in advance, it is ensured that molten iron enters the steelmaking link at the proper temperature, the quality stability of molten steel is effectively improved, the defective rate is reduced, and the product percent of pass is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of steel production, and specifically relates to a ladle temperature tracking and scheduling system and method based on AI data acquisition. Background Art

[0002] In modern steel production, the ladle serves as a critical transport vehicle connecting blast furnace ironmaking and converter steelmaking. Its temperature and dispatch efficiency have a decisive impact on steel production quality, energy consumption, and capacity. Traditional ladle management relies primarily on manual experience and simple automated equipment, resulting in numerous technical bottlenecks that urgently need to be addressed.

[0003] From a temperature management perspective, molten iron experiences significant temperature drops during transportation and waiting due to factors such as thermal radiation and convection. Failure to accurately monitor ladle temperature fluctuations can easily lead to excessively low temperatures, impacting the stability of subsequent steelmaking processes and product quality. Existing technologies often rely on single-point temperature measurement or scheduled spot checks. These methods not only fail to provide real-time, comprehensive monitoring of ladle temperature, but also make it difficult to accurately predict temperature trends, failing to provide reliable temperature data support for production scheduling.

[0004] In terms of scheduling management, traditional scheduling methods are often based on static production plans and fixed transportation routes, lacking the ability to quickly respond to unexpected production situations (such as equipment failures and production plan changes). Ladle scheduling often relies on manual coordination, which can easily lead to problems such as duplicate transportation routes, high idle equipment rates, and excessive waiting times. This results in low ladle turnover efficiency and insufficient utilization of transportation equipment, which in turn increases energy consumption and production costs.

[0005] Furthermore, as ladles are subject to long-term exposure to high temperatures, heavy loads, and highly corrosive environments, managing their service life and failure risks is crucial. Existing technologies make it difficult to effectively assess and predict the health of ladles, and repairs are typically performed only after a failure has occurred. This not only impacts production continuity but can also lead to safety accidents caused by sudden equipment failures.

[0006] With the advancement of intelligent upgrading in the steel industry, higher requirements are being placed on the real-time and accuracy of ladle temperature tracking, as well as the intelligent and dynamic scheduling management. There is an urgent need for systems and methods that integrate advanced data acquisition technology and artificial intelligence algorithms to achieve accurate tracking of ladle temperature and intelligent optimization of scheduling plans, while improving the full life cycle management level of ladle equipment, thereby effectively solving the problems of low efficiency, high cost, and high risk in the traditional ladle management model. Summary of the invention The purpose of the present invention is to provide a ladle temperature tracking and scheduling system and method based on AI data acquisition to solve the problems raised in the above background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions: A hot metal ladle temperature tracking and scheduling system and method based on AI data collection, including a data collection module, a data transmission module, a data processing and analysis module, an intelligent scheduling execution module, and a monitoring and management module. The data collection module includes an RFID reader for reading the ID of the hot metal ladle; an infrared camera for collecting the temperature of the hot metal; a travel encoder for obtaining the position distance; a weighing device for collecting weight data; a limit switch for detecting the lid state. The data transmission module transmits the data collected by the data collection module to the data processing and analysis module. The data processing and analysis module is provided with a temperature prediction model for predicting the temperature change trend; a life and failure prediction unit for predicting the service life and failure probability of the hot metal ladle; a scheduling algorithm module for generating a scheduling plan. The intelligent scheduling execution module includes controlling the transportation equipment to execute the scheduling and monitoring and anti-collision warning during the transportation process. The monitoring and management module is used to display the equipment operation status and query production data and generate reports.

[0008] Preferably, the RFID reader adopts high-frequency RFID technology, with a working frequency of 860 - 960 MHz and an identification distance of 0.1 - 10 meters, which can quickly and accurately read the RFID tag information pasted on the surface of the hot metal ladle to realize the automatic identification of the hot metal ladle ID.

[0009] Preferably, the infrared camera is a non-contact temperature measurement camera, with a temperature measurement range of 600 - 1600 °C and an accuracy of ±2 °C, which can collect the surface temperature of the hot metal in the hot metal ladle in real time.

[0010] Preferably, the travel encoder is an absolute encoder with a resolution of 0.1 mm, which cooperates with the induction device on the transportation track to accurately obtain the position distance information of the hot metal ladle on the transportation track.

[0011] Preferably, the weighing device is a high-precision pressure sensor with a range of 0 - 100 tons and an accuracy of 0.1% FS. It is installed on the bearing device of the hot metal ladle to collect the weight data of the hot metal ladle in real time and perform dynamic calibration. It has an automatic tare function and can accurately collect the weight data of the hot metal ladle in real time. When the weighing exceeds the range, the power supply is automatically cut off and the work stops, and an overload alarm is sent to the monitoring and management module. The limit switch has a double-contact design, which is respectively used to detect the opening and closing states of the ladle lid, and there is electrical isolation between the two contacts to prevent signal interference and improve the detection accuracy.

[0012] Preferably, the temperature prediction model is constructed based on a deep learning algorithm, and the inputs include parameters such as the initial temperature of molten iron, ambient temperature, transportation time, and the material of the ladle, to predict the change trend of the molten iron temperature in the ladle in the future; the life and fault prediction unit uses a machine learning algorithm, combined with the usage duration of the ladle, working environment parameters, weight change data, etc., to predict the remaining service life and the probability of fault occurrence of the ladle.

[0013] Preferably, the monitoring and management module has a permission management function, and the ranges of device operation status information, production data query, and report generation functions that users with different permissions can view and operate are different.

[0014] Preferably, the scheduling algorithm module supports dynamic adjustment of the scheduling plan. When receiving real-time event information such as production plan changes and sudden equipment failures, it can regenerate an optimized plan within a short time; the control transportation equipment execution scheduling function module has two control modes, remote and local, and can be switched through the monitoring and management module; the transportation process monitoring and anti-collision warning function module uses a fusion technology of lidar and image recognition to monitor obstacles on the transportation path in real time and issue a warning signal when the distance to the obstacle reaches the warning distance.

[0015] The method for tracking and scheduling the temperature of the ladle based on AI data collection includes the following steps: Data collection step: Real-time collection of ladle-related data through the RFID reader, infrared camera, travel encoder, weighing device, and limit switch in the data collection module.

[0016] Data transmission step: Use the data transmission module to transmit the collected data to the data processing and analysis module.

[0017] Data processing and analysis step: In the data processing and analysis module, the temperature prediction model predicts the temperature change trend; the life and fault prediction unit predicts the service life and fault probability of the ladle; the scheduling algorithm module generates a scheduling plan based on the above data and factors such as the status of transportation equipment and production plan.

[0018] Intelligent scheduling execution step: The intelligent scheduling execution module receives the scheduling plan, controls the transportation equipment to execute the scheduling, and monitors and provides anti-collision warning during the transportation process.

[0019] Monitoring and management step: The monitoring and management module displays the device operation status in real time and provides production data query and report generation services.

[0020] Preferably, in the data processing and analysis step, the scheduling algorithm module takes the shortest transportation path, the least transportation time, and the least equipment loss as the optimization objectives, and generates an efficient scheduling plan in combination with the real-time data of the ladle and the resource configuration of the transportation equipment. The beneficial effects of the present invention are as follows: 1. The present invention realizes non-contact and real-time monitoring of the temperature of the ladle with the help of an infrared camera. Combined with the temperature prediction model, it can accurately predict the temperature change trend of the molten iron in the next period of time. Compared with the traditional single-point temperature measurement or regular sampling inspection method, this system can obtain continuous change data of the ladle temperature, avoiding the problem that the temperature of the molten iron is too low due to untimely or inaccurate temperature monitoring, which affects the steelmaking process. By predicting the temperature change in advance, the transportation path, transportation speed or heat preservation measures can be adjusted in time to ensure that the molten iron enters the steelmaking process at an appropriate temperature, effectively improving the quality stability of the molten steel, reducing the defective rate and increasing the product qualification rate.

[0021] 2. Through the scheduling algorithm module, the present invention can optimize the transportation path to be the shortest, the transportation time to be the least, and the equipment loss to be the smallest. Combining the real-time data of the ladle and the transportation equipment resource configuration, it can generate an efficient scheduling plan and support dynamic adjustment. In case of sudden situations such as production plan changes and sudden equipment failures, it can regenerate an optimized plan in a very short time. Compared with the traditional scheduling method based on static plans and manual coordination, this system can effectively avoid problems such as repeated transportation paths and empty running of equipment, significantly improve the turnover efficiency of the ladle and the utilization rate of transportation equipment, and thus greatly improve the overall efficiency of steel production and increase production capacity.

[0022] 3. Due to the design of the life and fault prediction unit, the present invention can accurately predict the remaining service life and the probability of failure of the ladle by analyzing multi-dimensional information such as the service duration, loading times, temperature cycle data, and maintenance records of the ladle, changing the traditional after-fact maintenance mode and realizing preventive maintenance of the ladle. By planning the maintenance plan in advance, it can reduce the production interruption time caused by sudden equipment failures, reduce the maintenance cost and the equipment replacement frequency. At the same time, the monitoring of the operating status and loss analysis of the transportation equipment also helps to reasonably arrange equipment maintenance and prolong the service life of the equipment, further reducing the equipment operation and maintenance cost of the enterprise.

[0023] 4. Due to the design of the transportation process monitoring and anti-collision warning function module, the present invention can monitor the obstacles on the transportation path in real time, send a warning signal when the distance to the obstacle reaches the warning distance, and automatically adjust the operating status of the transportation equipment, effectively avoiding the occurrence of collision accidents. The intelligent warning system of the monitoring and management module monitors the abnormal temperature of the ladle, transportation equipment failures, scheduling timeouts and other situations in real time, and pushes the warning information in multiple levels through various methods, enabling the operator to take measures in time to deal with emergencies.

[0024] 5. Due to the design of the monitoring and management module in the present invention, information such as the running track, temperature change, and equipment status of the molten iron ladle can be visually presented. Operators can view detailed operation parameters in all directions, changing the abstraction and unintuitiveness of traditional data display, reducing the work difficulty and information acquisition cost of operators, providing data support and visual analysis reports for decisions such as production plan adjustment, equipment maintenance arrangement, and scheduling strategy optimization, assisting management personnel in making scientific decisions, avoiding the limitations and subjectivity of relying on manual experience in traditional management models, and enhancing the intelligent and scientific level of enterprise production management. Brief Description of the Drawings

[0025] Figure 1 It is a structural block diagram of the present invention.

[0026] In the figure: 1. Data acquisition module; 2. Data transmission module; 3. Data processing and analysis module; 4. Intelligent scheduling execution module; 5. Monitoring and management module; 6. RFID reader / writer; 7. Infrared camera; 8. Travel encoder; 9. Weighing device; 10. Limit switch; 11. Temperature prediction model; 12. Life and fault prediction unit; 13. Scheduling algorithm module; 14. Control the transportation equipment to execute scheduling; 15. Monitor the transportation process and anti-collision warning; 16. Display the equipment operation status; 17. Query production data and generate reports. Detailed Embodiment

[0027] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0028] Such as Figure 1As shown in the figure, the present invention provides a ladle temperature tracking and scheduling system and method based on AI data collection, including a data collection module 1, a data transmission module 2, a data processing and analysis module 3, an intelligent scheduling execution module 4, and a monitoring and management module 5. The data collection module 1 includes an RFID reader 6 for reading the ladle ID; an infrared camera 7 for collecting the ladle temperature; a travel encoder 8 for obtaining the position distance; a weighing device 9 for collecting weight data; a limit switch 10 for detecting the lid state. The data transmission module 2 transmits the data collected by the data collection module 1 to the data processing and analysis module 3. The data processing and analysis module 3 is provided with a temperature prediction model 11 for predicting the temperature change trend; a life and fault prediction unit 12 for predicting the service life and the probability of fault occurrence of the ladle; a scheduling algorithm module 13 for generating a scheduling plan. The intelligent scheduling execution module 4 includes controlling the transportation equipment to execute the scheduling 14 and monitoring and anti-collision warning during the transportation process 15. The monitoring and management module 5 is used to display the equipment operation status 16 and query production data and generate reports 17.

[0029] This claim is a general definition of the overall architecture and core functions of the ladle temperature tracking and intelligent scheduling optimization system based on AI and data collection. By clarifying the five core modules of the data collection module 1, the data transmission module 2, the data processing and analysis module 3, the intelligent scheduling execution module 4, and the monitoring and management module 5, as well as the functions of the key components within each module, a complete system solution is constructed. The RFID reader 6, infrared camera 7, travel encoder 8, weighing device 9, and limit switch 10 in the data collection module 1 realize the all-round data perception of the ladle operation status from the dimensions of ladle identity recognition, temperature collection, position tracking, weight monitoring, and lid state detection, providing accurate and real-time basic data for subsequent data processing and analysis. The data transmission module 2 ensures that this data can be stably and efficiently transmitted to the data processing and analysis module 3, ensuring the timeliness and integrity of the data. The data processing and analysis module 3, as the "brain" of the system, through the temperature prediction model 11, life and fault prediction unit 12, and scheduling algorithm module 13, uses artificial intelligence algorithms to deeply mine and analyze the collected data, realizing temperature change trend prediction, equipment life and fault estimation, and scheduling plan generation. The intelligent scheduling execution module 4 is responsible for putting the generated scheduling plan into practice, ensuring the high efficiency and safety of the ladle transportation process through controlling the transportation equipment to execute the scheduling 14 and monitoring and anti-collision warning during the transportation process 15. The monitoring and management module 5 provides the functions of visualizing the equipment operation status display 16 and querying production data and generating reports 17 for operators and managers, facilitating the real-time monitoring of the entire production process and management decision-making. This claim covers the core technical points of the entire process from data collection to final management decision-making, laying the foundation framework of the entire patent technology.

[0030] Among them, it is characterized in that: the RFID reader / writer 6 adopts high-frequency RFID technology, with a working frequency of 860 - 960 MHz and an identification distance of 0.1 - 10 meters. It can quickly and accurately read the RFID tag information pasted on the surface of the ladle, realizing the automatic identification of the ladle ID.

[0031] This claim makes specific technical feature limitations on the RFID reader / writer 6 in claim 1. By adopting high-frequency RFID technology and setting the working frequency in the range of 860 - 960 MHz, this frequency band has characteristics such as a moderate identification distance of 0.1 - 10 meters, fast reading speed, and strong anti-interference ability, which can meet the requirements for fast and accurate identification of the ladle ID in the complex environment of steel production sites. By reading the RFID tag information pasted on the surface of the ladle, the automatic identification of the ladle ID is realized. Compared with traditional manual identification or other identification methods, it greatly improves the identification efficiency and accuracy, avoids errors that may occur in manual operations, provides a reliable identity identification basis for the whole-process tracking and management of the ladle, ensures the traceability of information for each ladle during the production process, and also provides an accurate object identification for subsequent data processing and scheduling decisions.

[0032] Among them, the infrared camera 7 is a non-contact temperature measurement camera, with a temperature measurement range of 600 - 1600 °C and an accuracy of ±2 °C. It can collect the surface temperature of the molten iron in the ladle in real time.

[0033] This claim further clarifies the technical parameters and functional characteristics of the infrared camera 7. As a non-contact temperature measurement camera, its temperature measurement range is set at 600 - 1600 °C, and the accuracy reaches ±2 °C. This parameter range fully covers the temperature range of molten iron during production and transportation, and can collect the surface temperature of the molten iron in the ladle in real time and accurately. The non-contact measurement method avoids equipment damage and measurement errors that may be caused by contacting high-temperature molten iron, improves the reliability of temperature measurement and the service life of the equipment. By accurately obtaining the molten iron temperature data, it provides accurate input information for the temperature prediction model 11, enabling the system to timely grasp the change of molten iron temperature, and then taking corresponding measures to ensure that the molten iron enters the steelmaking process at an appropriate temperature, ensuring the stability of molten steel quality. At the same time, it also provides an important temperature reference basis for the formulation of the scheduling plan, avoiding the impact on production efficiency and product quality due to abnormal temperature.

[0034] Among them, the travel encoder 8 is an absolute encoder with a resolution of 0.1 mm. By cooperating with the induction device on the transportation track, it accurately obtains the position and distance information of the ladle on the transportation track.

[0035] This claim details the travel encoder 8. An absolute encoder is adopted, with a resolution as high as 0.1 mm. By cooperating with the induction device on the transport track, it can accurately obtain the position and distance information of the ladle on the transport track. Compared with incremental encoders, absolute encoders have a power-off memory function, which can directly obtain the accurate position of the ladle after the system restarts without recalibration, improving the stability and reliability of position information acquisition. The high resolution of 0.1 mm ensures the accuracy of ladle position tracking, enabling the system to grasp the specific position of the ladle during transportation in real time, providing accurate position data support for the scheduling algorithm module 13 to formulate reasonable transportation routes and scheduling plans. At the same time, it also helps to realize the functions of transportation process monitoring and anti-collision warning 15, timely detecting and avoiding collisions between the ladle and other equipment or obstacles during transportation, and ensuring transportation safety.

[0036] Among them, the weighing device 9 is a high-precision pressure sensor with a measuring range of 0 - 100 tons and an accuracy of 0.1% FS. It is installed on the loading device of the ladle to collect the weight data of the ladle in real time and perform dynamic calibration. It has an automatic tare function and can accurately collect the weight data of the ladle in real time. When the weighing exceeds the range, it automatically cuts off the power supply and stops working, and sends an overload alarm to the monitoring and management module 5. The limit switch 10 has a dual-contact design, which is used to detect the opening and closing states of the ladle cover respectively, and there is electrical isolation between the two contacts to prevent signal interference and improve the accuracy of detection.

[0037] This claim also supplements the technical features of the weighing device 9 and the limit switch 10. As a high-precision pressure sensor, the weighing device 9 has a measuring range of 0 - 100 tons and an accuracy of 0.1% FS, which can meet the weight measurement requirements of the ladle under different loading conditions. It is installed on the loading device of the ladle to collect the weight data of the ladle in real time. Its dynamic calibration and automatic tare functions effectively improve the accuracy and stability of weight measurement, and can eliminate measurement errors caused by the self-weight of the loading device, environmental factors, etc. When the weighing exceeds the range, it automatically cuts off the power supply and stops working, and sends an overload alarm to the monitoring and management module 5. This design not only protects the weighing device itself, but also timely reminds the operator to take corresponding measures to avoid equipment damage and safety accidents caused by overload. The dual-contact design and electrical isolation characteristics of the limit switch 10 are used to detect the opening and closing states of the ladle cover respectively, effectively preventing signal interference and improving the accuracy of ladle cover state detection, ensuring that the system can grasp the ladle cover state in real time and providing guarantee for production safety and process requirements. For example, when the ladle cover is not closed, the ladle transportation is prohibited to avoid safety hazards such as molten iron spilling.

[0038] Among them, the temperature prediction model 11 is constructed based on a deep learning algorithm. The inputs include parameters such as the initial temperature of molten iron, ambient temperature, transportation time, and the material of the ladle, and it predicts the changing trend of the temperature of molten iron in the ladle in the future; the life and fault prediction unit 12 uses a machine learning algorithm, combines information such as the service life of the ladle, working environment parameters, and weight change data, and predicts the remaining service life and the probability of fault occurrence of the ladle.

[0039] This claim focuses on the technical implementation methods of the temperature prediction model 11 and the life and fault prediction unit 12 in the data processing and analysis module 3. The temperature prediction model 11 is constructed based on a deep learning algorithm. By inputting multi-dimensional parameters such as the initial temperature of molten iron, ambient temperature, transportation time, and the material of the ladle, and using the powerful data analysis and pattern recognition capabilities of deep learning, it accurately predicts the changing trend of the temperature of molten iron in the ladle in the future. Compared with traditional temperature prediction methods, the deep learning algorithm can better handle complex non-linear relationships, adapt to the influence of various uncertain factors on the temperature of molten iron in the steel production process, provide more accurate temperature prediction information for production scheduling and process control, so as to take heat preservation or cooling measures in advance to ensure that the temperature of molten iron meets the requirements of the steelmaking process. The life and fault prediction unit 12 uses a machine learning algorithm, combines various information such as the service life of the ladle, working environment parameters, and weight change data, and establishes a life prediction and fault diagnosis model for the ladle, which can accurately predict the remaining service life and the probability of fault occurrence of the ladle. This prediction method realizes the transformation from traditional after-fact maintenance to preventive maintenance, helps enterprises plan the equipment maintenance plan in advance, reduces the production interruption time caused by sudden equipment failures, reduces the maintenance cost and the equipment replacement frequency, and improves the equipment utilization rate and production continuity.

[0040] Among them, the monitoring and management module 5 has a permission management function, and users with different permissions can view and operate different ranges of equipment operation status information, production data query, and report generation functions.

[0041] This claim emphasizes the permission management function of the monitoring and management module 5. In iron and steel production enterprises, the requirements and operation permissions of personnel in different positions for equipment operation status information, production data query, and report generation functions vary. By setting up the permission management function, the system can allocate different operation permissions according to the positions and responsibilities of users, ensuring that only personnel with corresponding permissions can view and operate specific function modules and data information. For example, ordinary operators can only view the equipment operation status and basic production data, while managers can perform operations such as production data query, report generation, and adjustment of scheduling plans. This permission management mechanism not only improves the security of the system, preventing data leakage and misoperations, but also optimizes the work process, enabling personnel in different positions to focus on the work within their respective responsibilities, improving work efficiency, and meeting the requirements of enterprise production management standardization and informatization at the same time.

[0042] Among them, the scheduling algorithm module 13 supports dynamic adjustment of the scheduling plan. When receiving real-time event information such as production plan changes and sudden equipment failures, it can regenerate an optimized plan within a short time; the control of transportation equipment to execute the scheduling 14 function module has both remote and local control modes, which can be switched through the monitoring and management module 5; the transportation process monitoring and anti-collision warning 15 function module uses the fusion technology of lidar and image recognition to monitor obstacles on the transportation path in real time and issue a warning signal when the distance to the obstacle reaches the warning distance.

[0043] This claim supplements the key features of the scheduling algorithm module 13, the control of transportation equipment to execute the scheduling 14 function module, and the transportation process monitoring and anti-collision warning 15 function module. The scheduling algorithm module 13 supports dynamic adjustment of the scheduling plan. When receiving real-time event information such as production plan changes and sudden equipment failures, it can regenerate an optimized plan within a short time. This feature enables the system to quickly adapt to various changes in the production process, ensuring that the ladle scheduling is always in an optimal state and avoiding production chaos and efficiency reduction caused by sudden situations. The control of transportation equipment to execute the scheduling 14 function module has both remote and local control modes and can be switched through the monitoring and management module 5. This design increases the flexibility and convenience of system operation. Under normal production conditions, the remote control mode can be used to achieve automated scheduling and improve production efficiency; when equipment debugging or failure requires manual intervention, it can be switched to the local control mode, facilitating on-site operation and maintenance by technicians. The transportation process monitoring and anti-collision warning 15 function module uses the fusion technology of lidar and image recognition to monitor obstacles on the transportation path in real time and issue a warning signal when the distance to the obstacle reaches the warning distance. Through the complementary advantages of the two technologies, it can more accurately detect the position, shape, and movement state of obstacles, timely remind the transportation equipment to take measures such as deceleration and avoidance, effectively avoid the occurrence of collision accidents, and ensure the safety and reliability of the ladle transportation process.

[0044] A method for tracking and scheduling the temperature of a hot metal ladle based on AI data collection, comprising the following steps: Data collection step: The RFID reader 6, infrared camera 7, travel encoder 8, weighing device 9, and limit switch 10 in the data collection module 1 are used to collect the relevant data of the hot metal ladle in real time.

[0045] Data transmission step: The collected data is transmitted to the data processing and analysis module 3 by using the data transmission module 2.

[0046] Data processing and analysis step: In the data processing and analysis module 3, the temperature prediction model 11 predicts the temperature change trend; the life and fault prediction unit 12 predicts the service life and fault probability of the hot metal ladle; the scheduling algorithm module 13 generates a scheduling plan according to the above data and factors such as the state of the transportation equipment and the production plan.

[0047] Intelligent scheduling execution step: The intelligent scheduling execution module 4 receives the scheduling plan, controls the transportation equipment to execute the scheduling 14, and monitors and provides anti-collision warning 15 during the transportation process.

[0048] Monitoring and management step: The monitoring and management module 5 displays the running state of the equipment 16 in real time, and provides services for querying production data and generating reports 17.

[0049] This claim proposes an optimization method for temperature tracking and intelligent scheduling of a hot metal ladle based on the system of claims 1-8, and elaborates in detail the specific step process of the system from data collection to the final realization of intelligent scheduling and monitoring management. In the data collection step, the relevant data of the hot metal ladle is collected in real time by each sensor in the data collection module 1, providing basic information for the operation of the system; in the data transmission step, the collected data is accurately transmitted to the data processing and analysis module 3 by using the data transmission module 2 to ensure the timely transmission of data; in the data processing and analysis step, in the data processing and analysis module 3, the data is deeply processed and analyzed through the temperature prediction model 11, the life and fault prediction unit 12, and the scheduling algorithm module 13 to generate key prediction information and scheduling plans; in the intelligent scheduling execution step, the intelligent scheduling execution module 4 receives the scheduling plan and controls the transportation equipment to execute the scheduling 14, while monitoring the transportation process and providing anti-collision warning 15 to realize the actual transportation and safety guarantee of the hot metal ladle; in the monitoring and management step, the monitoring and management module 5 displays the running state of the equipment 16 in real time and provides services for querying production data and generating reports 17, facilitating the operators and managers to monitor the entire production process in real time and make management decisions. These steps are closely linked to form a complete closed-loop process, ensuring that the system can operate efficiently and stably, and achieving the goal of temperature tracking and intelligent scheduling optimization of the hot metal ladle.

[0050] Among them, in the data processing and analysis step, the scheduling algorithm module 13 takes the shortest transportation path, the least transportation time, and the minimum equipment loss as the optimization objectives, and combines the real-time data of the ladle and the transportation equipment resource allocation situation to generate an efficient scheduling plan. The claims further clarify the optimization objectives and basis for the scheduling algorithm module 13 to generate a scheduling plan in the data processing and analysis step of claim 9. The scheduling algorithm module 13 takes the shortest transportation path, the least transportation time, and the minimum equipment loss as the optimization objectives, comprehensively considers the real-time data of the ladle such as temperature, weight, and position, and the transportation equipment resource allocation situation such as equipment status and available quantity, and uses optimization algorithms such as heuristic algorithms. Through continuous search and iteration, an efficient scheduling plan is generated. Taking the shortest transportation path and the least transportation time as the objectives can improve the turnover efficiency of the ladle, reduce the temperature drop of the molten iron during transportation, ensure that the molten iron enters the steelmaking process in a timely manner at an appropriate temperature, and improve production efficiency; taking the minimum equipment loss as the objective helps to extend the service life of the transportation equipment, reduce equipment maintenance costs, and improve equipment utilization. By combining the real-time data of the ladle and the transportation equipment, the scheduling plan can be dynamically adjusted according to the actual production situation, adapt to various changes in the production process, realize the intelligentization and scientific management of ladle scheduling, and improve the economic benefits and management level of the entire steel production process.

[0051] Working principle and usage process: I. Working principle The data acquisition module 1, as the "perception layer" of the system, uses a variety of sensors to achieve real-time acquisition of multi-dimensional data of the ladle. The RFID reader 6, based on radio frequency identification technology, communicates with the electronic tag on the ladle by emitting radio frequency signals, quickly and accurately reads the ladle ID, and realizes the unique identification and identity confirmation of the ladle; the infrared camera 7, based on Planck's radiation law, captures the infrared radiation energy on the surface of the molten iron, converts it into an electrical signal, and obtains the molten iron temperature data after algorithm processing, which can realize non-contact and real-time temperature measurement; the travel encoder 8 is connected to the transmission mechanism of the transportation equipment, converts the mechanical displacement of the equipment into a pulse signal, and obtains the position and distance information of the ladle after counting and conversion; the weighing device 9, based on the principle of a pressure sensor, converts the pressure generated by the weight of the ladle into an electrical signal, and obtains accurate weight data after amplification, filtering, etc.; the limit switch 10 uses an induction or mechanical trigger method. When the lid state of the ladle changes, the switch is triggered to act and outputs a corresponding electrical signal to realize the detection of the lid opening or closing state. The data transmission module 2 transmits the collected data to the data processing and analysis module 3. As the "brain" of the system, this module uses a variety of artificial intelligence algorithms to deeply mine and analyze the data. The temperature prediction model 11 learns from multi-dimensional data such as historical temperature data, ambient temperature, transportation time, and ladle status, and establishes a temperature change trend prediction model to predict the temperature change of hot metal in the next period of time. The life and fault prediction unit 12 uses information such as the service life, loading times, temperature cycle data, and maintenance records of the ladle to construct a ladle life prediction model and a fault diagnosis model to evaluate the remaining service life and the probability of fault occurrence of the ladle. The scheduling algorithm module 13 takes the shortest transportation path, the least transportation time, and the least equipment loss as the optimization objectives, and comprehensively considers factors such as the real-time data of the ladle temperature, weight, position, transportation equipment resource configuration, equipment status, available quantity, and production plan requirements to generate an optimal scheduling plan. The intelligent scheduling execution module 4 receives the scheduling plan generated by the scheduling algorithm module 13 and realizes the automatic execution of the ladle transportation task by controlling the transportation equipment to execute the scheduling 14 function. This module communicates with the control system of the transportation equipment, sends operation instructions such as start, stop, acceleration, deceleration, and steering, and controls the transportation equipment to transport the ladle according to the predetermined path and time requirements. During the transportation process, the transportation process monitoring and anti-collision warning 15 function module uses the fusion technology of lidar and image recognition to real-time monitor the obstacles on the transportation path. When the distance to the obstacle reaches the warning distance, a warning signal is issued, and the operation state of the transportation equipment is automatically adjusted according to the situation, such as deceleration, parking, and re-planning the path, to ensure the safety of the transportation process. The monitoring and management module 5, as the "human-computer interaction layer" of the system, provides operators with comprehensive equipment operation status monitoring and production management functions, intuitively presenting information such as the operation trajectory, temperature change, and equipment status of the ladle. Operators can view detailed operation parameters in all directions. The intelligent alarm system monitors in real-time situations such as abnormal ladle temperature, transportation equipment failure, and scheduling timeout according to preset thresholds and rules. When an abnormality occurs, alarm information is pushed in multiple ways such as sound and light, text message, and email at different levels.

[0052] II. Usage Process Before the system is put into use, initialization settings need to be carried out. First, configure and calibrate the parameters of each sensor in the data acquisition module 1 to ensure the measurement accuracy and reliability of devices such as the RFID reader 6, infrared camera 7, travel encoder 8, weighing device 9, limit switch 10, etc.; Second, in the data processing and analysis module 3, import basic data such as ladle historical data, transportation equipment parameters, production process requirements, etc., and perform initialization training on the temperature prediction model 11, life and fault prediction unit 12, and scheduling algorithm module 13; Finally, in the monitoring and management module 5, set system parameters such as user permissions, alarm thresholds, data storage periods, etc. to complete the system initialization. After the system starts, each sensor in the data acquisition module 1 starts to collect ladle data in real time. The RFID reader 6 periodically reads the ladle ID, the infrared camera 7 continuously monitors the ladle temperature, the travel encoder 8 records the position distance in real time, the weighing device 9 dynamically collects weight data, and the limit switch 10 detects the lid status in real time. The collected data is transmitted to the data processing and analysis module 3 through the data transmission module 2 in a wired or wireless communication manner such as Ethernet or 5G.

[0053] After receiving the data, the data processing and analysis module 3 first preprocesses the data, including data filtering, outlier detection and correction, to improve the data quality. Then, the temperature prediction model 11 analyzes the ladle temperature data to predict the temperature change trend in the next period of time; the life and fault prediction unit 12 combines the ladle usage data to evaluate its remaining service life and the probability of failure; the scheduling algorithm module 13 generates an optimal scheduling plan using heuristic algorithms based on information such as ladle real-time data, transportation equipment status, and production plans. After receiving the scheduling plan, the intelligent scheduling execution module 4 controls the transportation equipment to execute the scheduling 14 function, sends operation instructions to the transportation equipment, and starts the ladle transportation task. During the transportation process, the transportation process monitoring and anti-collision warning 15 function module monitors the transportation environment in real time to ensure transportation safety. In case of emergencies such as equipment failures or production plan changes, the scheduling algorithm module 13 supports dynamic adjustment of the scheduling plan, and the intelligent scheduling execution module 4 controls the transportation equipment to execute the task again according to the new plan. The monitoring and management module 5 receives and displays the system operation data in real time. Operators can intuitively view the ladle operation status, and the intelligent alarm system issues alarm notifications in a timely manner when abnormalities occur. At the same time, managers can use the production data query and report generation 17 function to statistically analyze the production data and optimize and adjust production plans, equipment maintenance, etc. During the operation of the system, through the feedback evaluation mechanism, the results of the actual scheduling executed by the transportation equipment are compared and analyzed with the expected goals of the scheduling plan to evaluate the execution effect of the scheduling plan, and the evaluation results are fed back to the data processing and analysis module 3 for further optimizing the scheduling algorithm module 13. At the same time, each module of the system is maintained regularly to check the sensor performance, software running status, data storage conditions, etc., to ensure the stable and reliable operation of the system. It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device.

[0054] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A hot metal ladle temperature tracking and scheduling system based on AI data collection, comprising a data collection module (1), a data transmission module (2), a data processing and analysis module (3), an intelligent scheduling execution module (4), and a monitoring and management module (5), characterized in that: The data acquisition module (1) includes an RFID reader / writer (6) for reading the ladle ID, an infrared camera (7) for collecting the molten iron temperature, an incremental encoder (8) for obtaining the position distance, a weighing device (9) for collecting weight data, and a limit switch (10) for detecting the ladle cover status. The data transmission module (2) transmits the data collected by the data acquisition module (1) to the data processing and analysis module (3). The data processing and analysis module (3) is provided with a temperature prediction model (11) for predicting the temperature change trend, a service life and fault prediction unit (12) for predicting the service life and fault occurrence probability of the ladle, and a scheduling algorithm module (13) for generating a scheduling plan. The intelligent scheduling execution module (4) includes controlling the transportation equipment to execute the scheduling (14) and monitoring and anti-collision warning during the transportation process (15). The monitoring and management module (5) is used to display the equipment operation status (16) and query production data and generate reports (17).

2. The hot metal ladle temperature tracking and scheduling system based on AI data collection according to claim 1, characterized in that: The RFID reader / writer (6) adopts high-frequency RFID technology, with a working frequency of 860 - 960 MHz and an identification distance of 0.1 - 10 meters. It can quickly and accurately read the RFID tag information pasted on the surface of the ladle, realizing the automatic identification of the ladle ID.

3. The molten iron ladle temperature tracking and scheduling system based on AI data collection according to claim 1, wherein: The infrared camera (7) is a non-contact temperature measurement camera, with a temperature measurement range of 600 - 1600 °C and an accuracy of ±2 °C. It can collect the surface temperature of the molten iron in the ladle in real time.

4. The molten iron ladle temperature tracking and scheduling system based on AI data collection according to claim 1, characterized in that: The incremental encoder (8) is an absolute encoder with a resolution of 0.1 mm. By cooperating with the induction device on the transportation track, it accurately obtains the position distance information of the ladle on the transportation track.

5. The molten iron ladle temperature tracking and scheduling system based on AI data collection according to claim 1, characterized in that: The weighing device (9) is a high-precision pressure sensor with a range of 0 - 100 tons and an accuracy of 0.1% FS. It is installed on the bearing device of the ladle, collects the weight data of the ladle in real time, and performs dynamic calibration. It has an automatic tare function and can accurately collect the weight data of the ladle in real time. When the weighing exceeds the range, it automatically cuts off the power supply and stops working, and sends an overload alarm to the monitoring and management module (5). The limit switch (10) has a double-contact design, which is respectively used to detect the opening and closing states of the ladle cover, and there is electrical isolation between the two contacts to prevent signal interference and improve the detection accuracy.

6. The molten iron ladle temperature tracking and scheduling system based on AI data collection according to claim 1, characterized in that: The temperature prediction model (11) is constructed based on a deep learning algorithm. The inputs include parameters such as the initial temperature of the molten iron, the ambient temperature, the transportation time, and the ladle material, and it predicts the future temperature change trend of the molten iron in the ladle. The service life and fault prediction unit (12) adopts a machine learning algorithm, combines the usage duration of the ladle, the working environment parameters, the weight change data, etc., and predicts the remaining service life and fault occurrence probability of the ladle.

7. The molten iron ladle temperature tracking and scheduling system based on AI data collection according to claim 1, characterized in that: The monitoring and management module (5) has a permission management function. Users with different permissions can view and operate different ranges of equipment operation status information, production data query, and report generation functions.

8. The hot metal ladle temperature tracking and scheduling system based on AI data collection according to claim 1, characterized in that: The scheduling algorithm module (13) supports dynamic adjustment of the scheduling plan. When receiving real-time event information such as production plan changes and sudden equipment failures, it can regenerate an optimized plan within a short time. The control transportation equipment execution scheduling (14) function module has two control modes: remote and local, and can be switched through the monitoring and management module (5). The transportation process monitoring and anti-collision warning (15) function module uses the fusion technology of lidar and image recognition to monitor obstacles on the transportation path in real time and issue a warning signal when the distance to the obstacle reaches the warning distance.

9. A hot metal ladle temperature tracking and scheduling method based on AI data collection, applied to the system according to any one of claims 1-8, characterized in that, The method includes the following steps: Data acquisition step: The RFID reader (6), infrared camera (7), travel encoder (8), weighing device (9), and limit switch (10) in the data acquisition module (1) are used to acquire the relevant data of the hot metal ladle in real time. Data transmission step: The data transmission module (2) is used to transmit the acquired data to the data processing and analysis module (3). Data processing and analysis step: In the data processing and analysis module (3), the temperature prediction model (11) predicts the temperature change trend; the life and failure prediction unit (12) predicts the service life and failure probability of the hot metal ladle; the scheduling algorithm module (13) generates a scheduling plan based on the above data and factors such as the status of transportation equipment and production plan. Intelligent scheduling execution step: The intelligent scheduling execution module (4) receives the scheduling plan, controls the transportation equipment to execute the scheduling (14), and monitors and warns of anti-collision during transportation (15). Monitoring and management step: The monitoring and management module (5) displays the equipment operation status (16) in real time and provides services for production data query and report generation (17).

10. The method for tracking and scheduling the temperature of a ladle based on AI data collection according to claim 9, wherein: In the data processing and analysis step, the scheduling algorithm module (13) takes the shortest transportation path, the least transportation time, and the minimum equipment loss as the optimization objectives, and generates an efficient scheduling plan in combination with the real-time data of the hot metal ladle and the resource allocation of transportation equipment.

Images