A method and system for evaluating the remaining life of a graphite guide nozzle protective sleeve of a copper molten converter

Abstract

The invention relates to the technical field of copper liquid transfer equipment detection, and in particular to a method and system for evaluating the remaining life of a graphite guide nozzle protective sleeve of a copper liquid converter, which can effectively solve the limitations of existing evaluation technologies and improve the reliability and safety of equipment. The method comprises: obtaining a guide nozzle protective sleeve wear feature set of each smelting operation and a copper liquid converter operating condition data set; performing weighted calculation on the guide nozzle protective sleeve wear feature set to obtain a decline in the guide nozzle protective sleeve wear failure index of the smelting operation; combining several guide nozzle protective sleeve wear failure index declines with their respective corresponding copper liquid converter operating condition data sets as training data, uploading them to a deep learning model training platform for correlation training, and constructing a guide nozzle protective sleeve wear analysis model; obtaining a guide nozzle protective sleeve wear feature set with critical requirements for the guide nozzle protective sleeve life, and performing weighted calculation on it to obtain a critical guide nozzle protective sleeve wear failure index.

Description

Technical Field

[0001] The invention relates to the technical field of copper liquid transfer equipment detection, and in particular to a method and system for evaluating the remaining life of a graphite guide nozzle protective sleeve of a copper liquid converter. Background Art

[0002] In the modern metallurgical industry, the copper molten converter is one of the key equipment, and its efficient and stable operation is crucial to ensure continuous production and product quality. One of the core components of the copper molten converter is the graphite guide nozzle protective sleeve, which not only undertakes the task of guiding the flow of high-temperature copper liquid, but also plays a role in protecting the converter lining from direct thermal shock and physical wear. However, working in a high-temperature environment for a long time, coupled with frequent contact with high-speed flowing copper liquid, the guide nozzle protective sleeve will gradually experience problems such as increased pores, decreased thermal conductivity, increased deformation and surface wear, which directly affect its service life and safety.

[0003] Most of the existing remaining life assessment technologies for the guide nozzle protective cover are based on simple statistical analysis of a single wear indicator or rely on empirical judgment, or formulate fixed-cycle preventive maintenance strategies. The above existing methods lack consideration of the comprehensive impact of multiple factors under complex working conditions, and cannot accurately predict the actual wear and tear of the guide nozzle protective cover, which can easily lead to waste of resources or sudden failures. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a method and system for evaluating the remaining life of a graphite guide nozzle protective sleeve of a copper molten converter, which can effectively solve the limitations of existing evaluation technologies and improve the reliability and safety of equipment.

[0005] In a first aspect, the present invention provides a method for evaluating the remaining life of a graphite guide nozzle protective sleeve of a copper molten converter, the method comprising:

[0006] Obtain the wear feature set of the nozzle protection sleeve and the operating condition data set of the copper liquid converter for each smelting operation;

[0007] Performing weighted calculation on the guide nozzle protective sleeve wear feature set to obtain a decline in the guide nozzle protective sleeve wear failure index of the smelting operation;

[0008] The declines in the wear failure index of the guide nozzle protective sleeve for several times are combined with the corresponding copper liquid converter operating condition data sets as training data, uploaded to the deep learning model training platform for correlation training, and a guide nozzle protective sleeve wear analysis model is constructed;

[0009] A guide nozzle protective sleeve wear feature set with critical life requirements is obtained, and a critical guide nozzle protective sleeve wear failure index is obtained by weighted calculation.

[0010] Based on the production plan, a set of copper molten converter operating condition data for several future smelting operations is obtained, and the data is sequentially input into the nozzle protection sleeve wear analysis model to obtain the decline in the nozzle protection sleeve wear failure index for several future smelting operations;

[0011] Obtaining the real-time guide nozzle protective sleeve wear failure index of the guide nozzle protective sleeve, and according to the time sequence of several future smelting operations, accumulating the real-time guide nozzle protective sleeve wear failure index and the decline of the guide nozzle protective sleeve wear failure index corresponding to several future smelting operations one by one, until the accumulated result is greater than the critical guide nozzle protective sleeve wear failure index;

[0012] The smelting operation corresponding to the last accumulated decline in the wear failure index of the guide nozzle protection sleeve is deleted, and the remaining smelting operations corresponding to the accumulated decline in the wear failure index of the guide nozzle protection sleeve are summarized to obtain a set of smelting operations for the effective life of the guide nozzle protection sleeve;

[0013] The production cycle of each smelting operation in the smelting operation set of the effective life of the guide nozzle protection sleeve is counted, and the remaining effective life of the guide nozzle protection sleeve is calculated.

[0014] Furthermore, the wear characteristic set of the guide nozzle protective sleeve includes porosity, thermal conductivity, deformation rate and surface wear.

[0015] Furthermore, the copper liquid converter operating condition data set includes converter operating temperature, copper liquid flow, production cycle and cooling water flow.

[0016] Furthermore, the method for constructing the wear analysis model of the guide nozzle protective sleeve includes:

[0017] Perform data cleaning on the wear characteristic drop data and the copper liquid converter operating condition data, including removing outliers and filling missing values, and standardizing the cleaned data;

[0018] A deep learning model is selected as the basic architecture of the nozzle protection sleeve wear analysis model, wherein the deep learning model includes a recurrent neural network, a long short-term memory, and a gated recursive unit;

[0019] Divide the declines in the wear failure index of the guide nozzle protection sleeve for several times and the corresponding data sets of the copper liquid converter operation conditions into a training set and a verification set;

[0020] The training set is used to train the nozzle protection sleeve wear analysis model; the validation set is used to evaluate the performance of the nozzle protection sleeve wear analysis model;

[0021] Deploy the trained nozzle protective sleeve wear analysis model into the system.

[0022] Furthermore, the method for obtaining the decline of the wear failure index of the guide nozzle protective sleeve includes:

[0023] Based on production planning, collect the operating data of several smelting operations expected to be carried out in the future;

[0024] The working condition data of each set of future smelting operations are used as input into the nozzle protection sleeve wear analysis model;

[0025] Through model calculation, the corresponding decline in the wear failure index of the nozzle protection sleeve is output for each future smelting operation.

[0026] Furthermore, the method for obtaining the effective life smelting operation set of the guide nozzle protection sleeve includes:

[0027] Get the smelting operation corresponding to the last accumulated decline in the wear failure index of the guide nozzle protection sleeve:

[0028] The smelting operation corresponding to the decline in the wear failure index of the guide nozzle protection sleeve that participated in the accumulation for the last time is deleted from the accumulation process;

[0029] After deleting the last smelting operation participating in the accumulation, the remaining smelting operations are aggregated to form a smelting operation set for the effective life of the guide nozzle protection sleeve.

[0030] Furthermore, the influence weights corresponding to the various parameters in the guide nozzle protective sleeve wear feature set are determined by experimental data analysis, expert experience evaluation, historical data analysis, theoretical analysis and simulation.

[0031] On the other hand, the present application also provides a system for assessing the remaining life of a graphite guide nozzle protective sleeve of a copper molten converter, the system comprising:

[0032] A data acquisition module is used to obtain a set of wear characteristics of the nozzle protection sleeve and a set of operating conditions data of the copper molten converter for each smelting operation; the set of wear characteristics of the nozzle protection sleeve includes porosity, thermal conductivity, deformation rate and surface wear; the set of operating conditions data of the copper molten converter includes converter operating temperature, copper molten flow, production cycle and cooling water flow;

[0033] A failure index calculation module performs weighted calculation on the wear feature set of the guide nozzle protective sleeve to obtain a decrease in the wear failure index of the guide nozzle protective sleeve of the smelting operation;

[0034] A model building module combines several declines in the wear failure index of the guide nozzle protective sleeve with the corresponding copper liquid converter operating condition data sets as training data, uploads them to the deep learning model training platform for correlation training, and builds a guide nozzle protective sleeve wear analysis model;

[0035] The critical state assessment module obtains the guide nozzle protective sleeve wear feature set with the critical life requirement of the guide nozzle protective sleeve, and performs weighted calculation on it to obtain the critical guide nozzle protective sleeve wear failure index;

[0036] The future operating condition prediction submodule obtains the copper molten converter operating condition data set for several future smelting operations based on the production plan, and inputs them into the guide nozzle protective sleeve wear analysis model in sequence to obtain the decline in the guide nozzle protective sleeve wear failure index for several future smelting operations;

[0037] The remaining life estimation submodule obtains the real-time nozzle protection sleeve wear and failure index of the nozzle protection sleeve, and according to the time sequence of several future smelting operations, successively accumulates the real-time nozzle protection sleeve wear and failure index and the nozzle protection sleeve wear and failure index decline corresponding to several future smelting operations, until the accumulated result is greater than the critical nozzle protection sleeve wear and failure index; deletes the smelting operation corresponding to the nozzle protection sleeve wear and failure index decline that participated in the last accumulation, and summarizes the smelting operations corresponding to the nozzle protection sleeve wear and failure index decline that participated in the accumulation, to obtain the effective life smelting operation set of the nozzle protection sleeve;

[0038] The life calculation module counts the production cycle of each smelting operation in the smelting operation set of the effective life of the guide nozzle protection sleeve, and calculates the remaining effective life of the guide nozzle protection sleeve.

[0039] In a third aspect, the present application provides an electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, and the computer program, when executed by the processor, implements the steps of any one of the above methods.

[0040] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps in any one of the above-mentioned methods when executed by a processor.

[0041] Compared with the prior art, the invention has the following beneficial effects: the method more comprehensively reflects the actual wear condition of the nozzle protective sleeve by comprehensively considering multiple wear characteristics such as porosity, thermal conductivity, deformation rate and surface wear, as well as operating parameters such as converter operating temperature, copper liquid flow, production cycle and cooling water flow;

[0042] Using deep learning models for correlation training can automatically learn and extract the nonlinear relationship between complex working conditions and wear, which improves the accuracy and reliability of predictions and helps to take preventive measures in advance. It can predict the wear of the nozzle protection sleeve under different working conditions according to future production plans, making maintenance plans more flexible and efficient, reducing unnecessary preventive replacements and avoiding waste of resources.

[0043] Through the cumulative calculation of the real-time wear status of the guide nozzle protective cover and the future predicted wear, the specific time point when the critical point of life is reached can be accurately determined, ensuring that the protective cover is replaced in time before failure, avoiding sudden failures and ensuring the continuity and safety of production;

[0044] The generated smelting operation set of the effective life of the nozzle protection cover and the statistics of the remaining effective life provide a direct basis for formulating maintenance plans, which helps to achieve more accurate maintenance management and cost control; through scientific evaluation and prediction of the life of the nozzle protection cover, the safety risks caused by sudden equipment failures are effectively reduced, which is of great significance to improving the overall production safety level and product quality;

[0045] In summary, this method has significant advantages in the field of copper liquid transfer equipment detection. It can effectively solve the limitations of existing evaluation technologies, improve the reliability and safety of equipment, and is also conducive to improving production efficiency and rational use of resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 is a logic flow chart of the present invention;

[0047] Figure 2 It is a flow chart of the method for constructing the wear analysis model of the guide nozzle protective sleeve;

[0048] Figure 3 The present invention is a structural diagram of a residual life assessment system for a graphite guide nozzle protective sleeve of a copper liquid converter. DETAILED DESCRIPTION

[0049] In the description of this application, those skilled in the art should know that this application can be implemented as a method, an apparatus, an electronic device, and a computer-readable storage medium. Therefore, this application can be specifically implemented in the following forms: complete hardware, complete software (including firmware, resident software, microcode, etc.), a combination of hardware and software. In addition, in some embodiments, this application can also be implemented in the form of a computer program product in one or more computer-readable storage media, and the computer-readable storage medium contains computer program code.

[0050] The above-mentioned computer-readable storage medium may adopt any combination of one or more computer-readable storage media. Computer-readable storage media include: electrical, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or devices, or any combination of the above. More specific examples of computer-readable storage media include: portable computer disks, hard disks, random access memories, read-only memories, erasable programmable read-only memories, flash memories, optical fibers, optical disc read-only memories, optical storage devices, magnetic storage devices, or any combination of the above. In the present application, computer-readable storage media can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or device.

[0051] The present application describes the provided methods, devices, and electronic devices through flowcharts and / or block diagrams.

[0052] It should be understood that each box in the flowchart and / or block diagram and the combination of boxes in the flowchart and / or block diagram can be implemented by computer-readable program instructions. These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine, and these computer-readable program instructions are executed by a computer or other programmable data processing device to produce a device that implements the functions / operations specified by the boxes in the flowchart and / or block diagram.

[0053] These computer-readable program instructions may also be stored in a computer-readable storage medium that enables a computer or other programmable data processing device to work in a specific manner. In this way, the instructions stored in the computer-readable storage medium produce an instruction device product including functions / operations specified in the blocks in the flowchart and / or block diagram.

[0054] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device, so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby enabling the instructions executed on the computer or other programmable data processing apparatus to provide a process for implementing the functions / operations specified in the blocks in the flowchart and / or block diagram.

[0055] The present application is described below in conjunction with the drawings in the present application.

[0056] Embodiment 1: Figure 1 to Figure 2 As shown, a method for evaluating the remaining life of a graphite guide nozzle protective sleeve of a copper molten converter of the present invention specifically comprises the following steps:

[0057] S1, obtaining a nozzle guide sleeve wear feature set and a copper molten converter operating condition data set for each smelting operation; the nozzle guide sleeve wear feature set includes porosity, thermal conductivity, deformation rate and surface wear; the copper molten converter operating condition data set includes converter operating temperature, copper molten flow, production cycle and cooling water flow;

[0058] The wear feature set of the guide nozzle protective sleeve includes:

[0059] Porosity, measuring the size and distribution of pores inside the protective cover to evaluate the density and corrosion resistance of the material;

[0060] Thermal conductivity, which measures the heat transfer efficiency of the protective cover under standard test conditions and reflects the thermal stability of the material in a high temperature environment;

[0061] Deformation rate, regularly monitor the shape changes of the protective cover and evaluate the structural stability under high temperature and mechanical stress;

[0062] Surface wear: observe and measure the changes in the microstructure of the protective cover surface, including wear depth, scratch length, etc., to evaluate the degree of physical wear;

[0063] The copper liquid converter operating condition data set includes:

[0064] The converter operating temperature is monitored in real time by the temperature sensor installed in the furnace;

[0065] The copper liquid flow rate is measured in the copper liquid pipeline using an electromagnetic flowmeter or an ultrasonic flowmeter;

[0066] Production cycle: the actual production cycle is calculated based on the start and end time of each batch of smelting operations recorded in the production log;

[0067] Cooling water flow: monitor the water flow of the cooling system through a flow meter to ensure the cooling effect of the converter;

[0068] Clean the collected data, remove outliers, fill in missing data, and ensure data quality;

[0069] Normalize each parameter to eliminate the dimension effect;

[0070] The wear characteristics of each test and the corresponding operating condition data are time-tagged to form an orderly historical record, providing a basis for establishing a wear analysis model.

[0071] In this step, by measuring multi-dimensional wear characteristics, the performance degradation of the nozzle protective cover under complex working conditions is fully covered. Compared with the evaluation of a single indicator, it is more accurate and comprehensive, and provides detailed data for a deep understanding of the actual wear mechanism of the protective cover. The operating condition data is collected so that the evaluation method can fully consider the impact of different operating conditions on the wear of the protective cover, which improves the adaptability and accuracy of the evaluation model under diverse working conditions.

[0072] Data cleaning and outlier processing were implemented to eliminate erroneous data that may mislead the analysis results, and missing values ​​were filled to ensure the integrity and reliability of the analysis data, laying a high-quality data foundation for subsequent statistical analysis and model training. By normalizing each parameter, the differences in different measurement units and magnitudes were eliminated, allowing direct comparison and comprehensive analysis of different features, simplifying the data analysis process, and improving processing efficiency and the accuracy of model training. By adding time tags to the wear characteristics and working condition data of each test, a continuous and orderly historical record was formed, which is not only conducive to tracking the degradation trend of the protective cover over time, but also provides time series data support for the dynamic analysis of the wear process and future trend prediction, enhancing the timeliness and practicality of the prediction model.

[0073] In summary, this step significantly improves the scientificity and practicality of the remaining life assessment of the graphite guide nozzle protective sleeve of the copper liquid converter through comprehensive data collection and preprocessing strategies, and provides strong data support for the accurate management of equipment status, optimization of maintenance strategies, and improvement of production efficiency and safety.

[0074] S2. Performing weighted calculation on the wear feature set of the guide nozzle protective sleeve to obtain a decline in the wear failure index of the guide nozzle protective sleeve of the smelting operation;

[0075] In step S2, the wear characteristics of the nozzle protection sleeve need to be quantified to ensure that all characteristics are comparable on the same scale;

[0076] Subsequently, a weight coefficient is assigned to each wear feature to reflect the importance of each wear feature on the overall performance of the guide nozzle protective cover; the weight coefficient is determined in the following manner:

[0077] Experimental data analysis: Through actual experimental data, the relationship between the changes in different parameters and the degree of wear of the nozzle protection sleeve is analyzed; through statistical analysis of the experimental results, the relative influence of various parameters on the wear of the nozzle protection sleeve can be determined;

[0078] Expert experience evaluation: Invite experts in the field to conduct evaluations and determine the weights of various parameters based on their experience and knowledge. Experts will consider the actual role of various parameters in the wear process of the nozzle protection sleeve and their contribution to the overall performance.

[0079] Theoretical analysis and simulation: With the help of modern simulation software, the wear process of the nozzle protection sleeve under different working conditions is simulated and analyzed; through theoretical analysis, the relative importance of various parameters in the wear of the nozzle protection sleeve can be derived, so as to determine their weights;

[0080] Historical data analysis: Analyze historical maintenance records and failure cases to find out which factors most often lead to protective cover replacement or failure.

[0081] In this step, the wear characteristics of the nozzle protective cover are quantified to ensure that different characteristics are comparable on the same scale, so as to more accurately describe the wear of the nozzle protective cover; the weight coefficient reflects the degree of wear influence: the weight coefficient is assigned to each wear characteristic, which can reflect the influence of each characteristic on the overall performance of the nozzle protective cover; it helps to determine which factors are more critical when evaluating the remaining life of the nozzle protective cover; through experimental data analysis, the relationship between different parameter changes and the wear of the nozzle protective cover can be directly observed, so as to determine the relative influence of various parameters on wear; expert experience evaluation can combine the experts in the field Practical experience and knowledge, taking into account the role and contribution of each parameter in actual work; such an evaluation can make up for the shortcomings of experimental data analysis and provide a more comprehensive perspective; theoretical analysis and simulation can provide important support when experimental data is limited or difficult to obtain, and can theoretically derive and simulate the wear process of the nozzle protective cover under different working conditions, so as to infer the relative importance of various parameters; analysis of historical maintenance records and failure cases can reveal which factors most often lead to the replacement or failure of the protective cover, providing an important reference for the determination of weight coefficients, and can more directly understand the influence of various parameters on the life of the protective cover;

[0082] In summary, the beneficial effects of step S2 include improving the quantitative description of wear characteristics, determining weight coefficients that reflect the degree of influence of various parameters, and the comprehensive use of multiple methods such as experiments, expert evaluation, theoretical analysis, and historical data analysis, thereby enhancing the understanding and credibility and accuracy of the evaluation of the wear condition of the guide nozzle protective sleeve.

[0083] S3, combining the declines in the wear failure index of the guide nozzle protective sleeve for several times with the corresponding copper liquid converter operating condition data sets as training data, uploading them to the deep learning model training platform for correlation training, and constructing a guide nozzle protective sleeve wear analysis model;

[0084] The input of the guide nozzle protective sleeve wear analysis model is the copper liquid converter operating condition data set, and the output is the decline in the guide nozzle protective sleeve wear failure index;

[0085] Step S3 involves constructing a wear analysis model for the nozzle protection sleeve, which mainly relies on the deep learning model training platform for correlation training to solve the problem that the existing evaluation method lacks consideration of the comprehensive impact of multiple factors under complex working conditions; the construction method of the nozzle protection sleeve wear analysis model includes:

[0086] S31. Clean the wear characteristic drop data and the copper liquid converter operation condition data, including removing abnormal values ​​and filling missing values, and standardizing the cleaned data;

[0087] S32, selecting a deep learning model as the basic architecture of the guide nozzle protective sleeve wear analysis model, wherein the deep learning model includes a recurrent neural network, a long short-term memory, and a gated recursive unit;

[0088] S33, dividing the declines in the wear failure index of the guide nozzle protection sleeve for several times and the corresponding copper liquid converter operation condition data sets into a training set and a verification set;

[0089] S34. Using the training set, the parameters of the nozzle protection sleeve wear analysis model are adjusted to reduce the prediction error through the back propagation and gradient descent optimization algorithms; and the performance of the nozzle protection sleeve wear analysis model is evaluated using the validation set;

[0090] S35. Bring the trained nozzle protection sleeve wear analysis model into the system, input the future copper liquid converter operating condition data into the model, and predict the corresponding nozzle protection sleeve wear failure index decline.

[0091] In this step, by performing correlation training on the decline of the wear failure index of the guide nozzle protective sleeve and the copper liquid converter operating condition data set, a deep learning model is constructed, which can comprehensively consider the influence of various factors on the wear of the guide nozzle protective sleeve, so as to more accurately evaluate its remaining life; through the analysis of historical data and model training, the correlation law between the wear of the guide nozzle protective sleeve and the operating conditions can be learned, so as to achieve accurate prediction of the decline of the wear failure index of the guide nozzle protective sleeve; it is helpful to discover potential wear problems in advance, take corresponding maintenance and repair measures, and avoid sudden failures and production interruptions caused by wear; accurately evaluate the remaining life of the guide nozzle protective sleeve, which is helpful to optimize production planning and scheduling, reasonably arrange maintenance cycles, avoid production interruptions caused by sudden failures, and improve production efficiency and continuity of production lines;

[0092] In summary, the beneficial effects of step S3 include improving evaluation accuracy, achieving precise prediction, optimizing maintenance strategies, and improving production efficiency, which helps to improve the stable operation and product quality of the copper liquid converter.

[0093] S4, obtaining a set of wear characteristics of the guide nozzle protective sleeve that meets the critical life requirement of the guide nozzle protective sleeve, and performing weighted calculation on the set of wear characteristics of the guide nozzle protective sleeve to obtain a critical guide nozzle protective sleeve wear failure index;

[0094] In step S4, in order to determine the critical life requirements of the nozzle protection cover, it is first necessary to define a critical value set of wear characteristics based on historical data, experimental research and industry standards, which is directly related to the safe use limit of the nozzle protection cover; the following is a detailed description of step S4:

[0095] Review the previous failed nozzle protection cases and record their porosity, thermal conductivity, deformation rate and surface wear parameters at the time of failure to define the limit state of wear characteristics;

[0096] Invite experts in the field to evaluate the collected data based on actual work experience and existing industry safety standards and set one or a group of critical wear thresholds;

[0097] According to the different contributions of each wear feature to the overall performance and safety of the nozzle protection cover, a weight coefficient is assigned to each feature; then, the measured value of each feature is multiplied by its corresponding weight and the sum is calculated to obtain a comprehensive wear failure index;

[0098] Based on the comprehensive wear failure index, a critical value is set as the standard for replacing the guide nozzle protective cover. The critical value ensures that the guide nozzle protective cover can be replaced in time before it reaches severe wear, thereby avoiding the occurrence of safety accidents.

[0099] In this step, the accuracy and reliability of the critical value of the wear characteristics are ensured through comprehensive analysis of historical data and experimental research; the formulated critical value is closer to the actual working situation, which improves the accurate judgment of the wear state of the nozzle protective cover; the setting of the critical value is directly related to the safe use limit of the equipment; by comprehensively considering wear characteristics such as porosity, thermal conductivity, deformation rate and surface wear, the wear condition of the nozzle protective cover can be more comprehensively evaluated, and safety hazards can be discovered and avoided in time, thereby enhancing the safety of the equipment; the measured value of each wear characteristic is multiplied by its corresponding weight and then summed to obtain a comprehensive wear failure index, which can more intuitively reflect the overall wear condition of the nozzle protective cover and provide a comprehensive evaluation indicator for decision-making; based on the set critical value, a more scientific and reasonable preventive maintenance strategy can be formulated, and the nozzle protective cover with severe wear can be replaced in time, reducing the risk of sudden equipment failure and improving production continuity and stability;

[0100] In summary, the beneficial effects of step S4 include improving the accuracy and reliability of the evaluation, enhancing the safety of the equipment, formulating comprehensive evaluation indicators, and improving the level of preventive maintenance.

[0101] S5. Based on the production plan, a set of copper molten converter operating condition data for several future smelting operations is obtained, and the data is sequentially input into the guide nozzle protective sleeve wear analysis model to obtain a decline in the guide nozzle protective sleeve wear failure index for several future smelting operations;

[0102] In step S5, in order to predict the wear trend of the nozzle protection sleeve in the future and arrange the maintenance plan accordingly, the core is to use the constructed deep learning model to analyze the future copper liquid converter operation conditions; the method for obtaining the decline of the nozzle protection sleeve wear failure index includes:

[0103] Based on production planning, collect and organize detailed working condition data of several smelting operations expected in the future; this information directly affects the working environment and stress conditions of the protective sleeve;

[0104] Each set of future smelting operation operating data is used as input into the nozzle protection sleeve wear analysis model; the model uses a deep learning algorithm to identify and learn the complex nonlinear relationship between different operating parameters and nozzle protection sleeve wear characteristics;

[0105] Through model calculation, the corresponding decline in the wear failure index of the nozzle protection sleeve is output for each future smelting operation.

[0106] In this step, the deep learning model can learn the relationship between complex operating parameters and the wear characteristics of the nozzle protection sleeve, so as to accurately predict the wear trend of the nozzle protection sleeve in the future; it is helpful to arrange maintenance plans in time to avoid equipment failure and production interruption caused by excessive wear; through wear analysis of several future smelting operations, it can provide guidance for the maintenance of the nozzle protection sleeve; according to the wear conditions output by the model, it can reasonably arrange maintenance strategies, extend the service life of the nozzle protection sleeve, and improve production efficiency and equipment reliability; by accurately predicting the wear conditions, it can avoid excessive maintenance or unnecessary replacement, thereby saving maintenance costs and improving resource utilization efficiency; by timely maintaining and replacing severely worn nozzle protection sleeves, it can ensure the efficient and stable operation of the copper liquid converter, ensure continuous production and product quality, while reducing the risk of equipment failure and improving production safety;

[0107] In summary, the implementation of step S5 helps to improve production efficiency, reduce maintenance costs, and improve equipment reliability and safety.

[0108] S6. Obtain the real-time guide nozzle protective sleeve wear failure index of the guide nozzle protective sleeve, and according to the time sequence of several future smelting operations, successively add the real-time guide nozzle protective sleeve wear failure index and the decline of the guide nozzle protective sleeve wear failure index corresponding to several future smelting operations one by one, until the accumulated result is greater than the critical guide nozzle protective sleeve wear failure index;

[0109] Step S6 involves real-time monitoring of equipment wear and dynamic evaluation of it; the following is a detailed description of this step:

[0110] During the operation of the copper liquid converter, it is necessary to use sensors or monitoring equipment to obtain the wear index of the guide nozzle protective cover in real time; the sensor is installed on the surface of the guide nozzle protective cover, and the wear condition is indirectly evaluated by measuring parameters such as temperature, pressure, vibration, etc., or the morphology and characteristics of the worn surface are directly measured;

[0111] According to the wear index of the nozzle protection sleeve monitored in real time, the wear analysis model constructed in advance is used to calculate and obtain the real-time nozzle protection sleeve wear failure index; this index reflects the current wear degree and failure risk of the nozzle protection sleeve and is used for real-time monitoring and early warning;

[0112] The real-time guide nozzle protective sleeve wear failure index and the wear index decline of several future smelting operations are gradually accumulated; the wear index decline of each smelting operation is considered one by one in chronological order, and accumulated with the real-time wear index until the accumulated result exceeds the critical guide nozzle protective sleeve wear failure index;

[0113] Through real-time monitoring and cumulative calculation, the prediction and maintenance strategy for the guide nozzle protective cover can be dynamically adjusted; once the real-time wear index reaches the warning threshold or the cumulative result is close to the critical value, maintenance measures can be taken in time to ensure the safe and stable operation of the equipment.

[0114] In this step, by real-time monitoring of the wear of the equipment and dynamically evaluating the wear index of the nozzle protective cover, the status and performance of the equipment can be understood in time, and the wear of the equipment can be instantly mastered; by real-time monitoring and early warning of the wear failure index of the nozzle protective cover, the wear trend and potential failure risk can be discovered in advance, and preventive measures can be taken in time to avoid equipment failure and production interruption caused by wear, so as to ensure the continuity and stability of production; according to the results of real-time monitoring, the prediction and maintenance strategy of the nozzle protective cover can be dynamically adjusted to make the maintenance more accurate and effective; not only can it reduce unnecessary maintenance and replacement frequency and reduce maintenance costs, but it can also maximize the service life of the equipment and improve the reliability and stability of the equipment; by accurately monitoring the wear and taking maintenance measures in time, it can avoid excessive maintenance or equipment damage caused by negligence, and realize the rational use of resources and effective control of costs; at the same time, by extending the service life of the equipment, it can also reduce the frequency of equipment replacement and maintenance, and further save costs;

[0115] In summary, the implementation of step S6 can effectively improve the monitoring accuracy and maintenance efficiency of the equipment, ensure the safe and stable operation of the copper liquid converter, and provide reliable guarantee for smelting production.

[0116] S7, deleting the smelting operation corresponding to the last accumulated decrease in the wear and failure index of the guide nozzle protection cover, and summing up the remaining smelting operations corresponding to the accumulated decrease in the wear and failure index of the guide nozzle protection cover to obtain a set of smelting operations for the effective life of the guide nozzle protection cover;

[0117] In step S7, it involves processing the smelting operations corresponding to the decline in the wear failure index of the guide nozzle protection sleeve to obtain a smelting operation set of the effective life of the guide nozzle protection sleeve; the method for obtaining the smelting operation set of the effective life of the guide nozzle protection sleeve includes:

[0118] Get the smelting operation corresponding to the last accumulated decline in the wear failure index of the guide nozzle protection sleeve:

[0119] Determine the smelting operation corresponding to the last drop in the wear failure index of the guide nozzle protective sleeve involved in the accumulation process; the smelting operation is the last operation that causes the accumulation result to exceed the critical wear failure index of the guide nozzle protective sleeve;

[0120] Delete the last smelting operation involved in the accumulation:

[0121] The smelting operation corresponding to the decline in the wear failure index of the guide nozzle protection sleeve that participated in the accumulation for the last time is deleted from the accumulation process;

[0122] Summarize the remaining smelting operations involved in the accumulation:

[0123] After deleting the last smelting operation involved in the accumulation, the remaining smelting operations are the smelting operation set of the effective life of the nozzle protection cover; these operations together lead to the accumulation of the decline in the wear failure index of the nozzle protection cover, but do not cause the accumulation result to exceed the critical value, so they are considered to be operations within the effective life range of the nozzle protection cover;

[0124] Get the effective life of the nozzle protection sleeve smelting operation collection:

[0125] These remaining smelting operations are aggregated to form a collection of smelting operations for the effective life of the nozzle protection sleeve.

[0126] In this step, by deleting the job that failed due to the last accumulation, it can be ensured that the last job will not affect the determination of the effective life; the effective life range of the nozzle protective cover can be accurately determined to avoid counting the failed jobs; after removing the last job, the remaining job set reflects the performance of the nozzle protective cover in actual production, reducing errors and uncertainties; it helps to improve the accuracy of the evaluation and make the prediction of the life of the nozzle protective cover more reliable; the effective life smelting job set provides a basis for formulating a more reasonable maintenance plan based on the characteristics of these jobs; through the analysis of these jobs, the maintenance interval, maintenance method, etc. can be determined to maximize the service life of the nozzle protective cover and ensure the continuity and stability of the production process; by accurately determining the smelting jobs within the effective life, unnecessary maintenance or replacement can be avoided, thereby saving maintenance costs and optimizing resource utilization; it helps to reduce production costs and improve production efficiency;

[0127] In summary, the execution of step S7 helps to accurately determine the effective life range of the nozzle protection cover, optimize maintenance planning, and maximize the use of resources, thereby improving production efficiency and equipment utilization.

[0128] S8. Count the production cycles of each smelting operation in the smelting operation set of the effective life of the guide nozzle protection sleeve, and calculate the remaining effective life of the guide nozzle protection sleeve;

[0129] In step S8, it is necessary to count the production cycles of each smelting operation in the effective life smelting operation set of the nozzle protection cover, and calculate the remaining effective life of the nozzle protection cover based on these data, which is related to the operation safety and production efficiency of the equipment; the following is a detailed introduction to step S8:

[0130] Collect the production cycle data of each smelting operation in the effective life smelting operation set of the nozzle protection sleeve; obtain it through the production record and equipment monitoring system, including the start time and end time of each smelting operation;

[0131] Based on the collected data, calculate the production cycle of each smelting operation; the production cycle refers to the time from the start to the end of a smelting operation;

[0132] Collect and sort out the production cycle data of all smelting operations to obtain a data set of a production cycle;

[0133] The remaining effective life of the nozzle protection cover is calculated based on the obtained production cycle data; the remaining effective life is the time during which the nozzle protection cover can continue to operate safely in the current use state.

[0134] In this step, by monitoring and calculating the remaining effective life of the nozzle protective cover, the use status of the equipment can be better evaluated; it is helpful to discover the problems and wear of the nozzle protective cover in advance, and then take corresponding maintenance measures to ensure the safety and stability of equipment operation; understanding the remaining effective life of the nozzle protective cover is helpful to reasonably arrange maintenance plans and production schedules; by predicting the life of the nozzle protective cover, production interruptions caused by sudden failures or untimely maintenance can be avoided, thereby improving production efficiency and continuous production capacity; by accurately evaluating the remaining effective life of the nozzle protective cover, unnecessary maintenance and replacement can be avoided, maintenance costs and equipment downtime can be reduced, thereby optimizing resource utilization and improving the overall economic benefits of the equipment; by collecting and analyzing the production cycle data of the nozzle protective cover, a data support system for equipment life and operating status can be established; these data can provide decision-making references for managers and help them formulate more scientific and reasonable maintenance strategies and equipment update plans;

[0135] In summary, the statistical and calculation process in step S8 helps to improve the safety of equipment operation, production efficiency and resource management level, and provides strong support for the sustainable development of the enterprise.

[0136] Embodiment 2: Figure 3 As shown, a system for assessing the remaining life of a graphite guide nozzle protective sleeve of a copper molten converter of the present invention specifically comprises the following modules;

[0137] A data acquisition module is used to obtain a set of wear characteristics of the nozzle protection sleeve and a set of operating conditions data of the copper molten converter for each smelting operation; the set of wear characteristics of the nozzle protection sleeve includes porosity, thermal conductivity, deformation rate and surface wear; the set of operating conditions data of the copper molten converter includes converter operating temperature, copper molten flow, production cycle and cooling water flow;

[0138] A failure index calculation module performs weighted calculation on the wear feature set of the guide nozzle protective sleeve to obtain a decrease in the wear failure index of the guide nozzle protective sleeve of the smelting operation;

[0139] A model building module combines several declines in the wear failure index of the guide nozzle protective sleeve with the corresponding copper liquid converter operating condition data sets as training data, uploads them to the deep learning model training platform for correlation training, and builds a guide nozzle protective sleeve wear analysis model;

[0140] The critical state assessment module obtains the guide nozzle protective sleeve wear feature set with the critical life requirement of the guide nozzle protective sleeve, and performs weighted calculation on it to obtain the critical guide nozzle protective sleeve wear failure index;

[0141] The future operating condition prediction submodule obtains the copper molten converter operating condition data set for several future smelting operations based on the production plan, and inputs them into the guide nozzle protective sleeve wear analysis model in sequence to obtain the decline in the guide nozzle protective sleeve wear failure index for several future smelting operations;

[0142] The remaining life estimation submodule obtains the real-time nozzle protection sleeve wear and failure index of the nozzle protection sleeve, and according to the time sequence of several future smelting operations, successively accumulates the real-time nozzle protection sleeve wear and failure index and the nozzle protection sleeve wear and failure index decline corresponding to several future smelting operations, until the accumulated result is greater than the critical nozzle protection sleeve wear and failure index; deletes the smelting operation corresponding to the nozzle protection sleeve wear and failure index decline that participated in the last accumulation, and summarizes the smelting operations corresponding to the nozzle protection sleeve wear and failure index decline that participated in the accumulation, to obtain the effective life smelting operation set of the nozzle protection sleeve;

[0143] The life calculation module counts the production cycle of each smelting operation in the smelting operation set of the effective life of the guide nozzle protection sleeve, and calculates the remaining effective life of the guide nozzle protection sleeve.

[0144] The system comprehensively considers the various wear characteristics of the nozzle protection sleeve and the operating conditions of the converter, abandons the limitations of single indicator evaluation, and more accurately reflects the actual wear situation; through the deep learning model to build wear analysis, it can learn and capture the nonlinear laws of wear behavior under complex conditions. Compared with empirical judgment and simple statistical analysis, it provides more accurate prediction capabilities and effectively avoids resource waste and production interruptions caused by sudden failures;

[0145] The system can predict future working conditions based on production planning, adjust the input of the evaluation model in real time, and dynamically predict the wear trend of the nozzle protection cover. This dynamic adaptability significantly improves the foresight and effectiveness of maintenance decisions. Through the refined remaining life estimation process, especially the method of gradually accumulating the expected decline in the wear failure index of future operations until it reaches the critical value, the system achieves fine management of the protection cover life, ensures the timeliness and economy of replacement and maintenance, and maximizes the efficiency of equipment use.

[0146] Automated data collection and intelligent analysis reduce errors introduced by human factors, improve the objectivity and consistency of evaluation, help formulate more scientific and reasonable maintenance strategies, and reduce maintenance costs; accurately predict the remaining life of the nozzle protection cover, plan the replacement time in advance, avoid safety accidents caused by sudden failure of components, and ensure the stability of continuous production, which is of great significance to improving product quality;

[0147] In summary, the system realizes the accurate prediction and management of the remaining life of the guide nozzle protective cover by integrating multi-source data and adopting advanced artificial intelligence technology, effectively solving the shortcomings of traditional methods and providing strong technical support for the safe production and efficient operation of the metallurgical industry.

[0148] The various variations and specific embodiments of the method for assessing the remaining life of a graphite guide nozzle protective sleeve for a copper-molten converter in the aforementioned embodiment 1 are also applicable to the system for assessing the remaining life of a graphite guide nozzle protective sleeve for a copper-molten converter in this embodiment. Through the aforementioned detailed description of the method for assessing the remaining life of a graphite guide nozzle protective sleeve for a copper-molten converter, those skilled in the art can clearly understand the implementation method of the system for assessing the remaining life of a graphite guide nozzle protective sleeve for a copper-molten converter in this embodiment. Therefore, for the sake of brevity of the specification, it will not be described in detail here.

[0149] In addition, the present application also provides an electronic device, including a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor. The transceiver, the memory, and the processor are respectively connected via a bus. When the computer program is executed by the processor, each process of the above-mentioned method for controlling output data is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0150] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for evaluating the remaining life of a graphite guide nozzle protective sleeve of a copper molten converter, characterized in that: The method comprises: Obtain the wear feature set of the nozzle protection sleeve and the operating condition data set of the copper liquid converter for each smelting operation; A weighted calculation is performed on the wear feature set of the guide nozzle protective cover, and the wear feature of the guide nozzle protective cover is quantified, and a weight coefficient is assigned to each wear feature of the guide nozzle protective cover, wherein the weight coefficient reflects the degree of wear influence, and the determination method of the weight coefficient includes: Through actual experimental data, the relationship between the changes in different parameters and the degree of wear of the nozzle protection sleeve is analyzed, and through statistical analysis of the experimental results, the relative influence of various parameters on the wear of the nozzle protection sleeve is determined, and the decline in the nozzle protection sleeve wear failure index of this smelting operation is obtained; The declines in the wear failure index of the guide nozzle protective sleeve for several times are combined with the corresponding copper liquid converter operating condition data sets as training data, uploaded to the deep learning model training platform for correlation training, and a guide nozzle protective sleeve wear analysis model is constructed; The method for constructing the wear analysis model of the guide nozzle protective sleeve includes: Perform data cleaning on the wear characteristic drop data and the copper liquid converter operating condition data, including removing outliers and filling missing values, and standardizing the cleaned data; A deep learning model is selected as the basic architecture of the nozzle protection sleeve wear analysis model, wherein the deep learning model includes a recurrent neural network, a long short-term memory, and a gated recursive unit; Divide the declines in the wear failure index of the guide nozzle protection sleeve for several times and the corresponding data sets of the copper liquid converter operation conditions into a training set and a verification set; The training set is used to train the nozzle protection sleeve wear analysis model; the validation set is used to evaluate the performance of the nozzle protection sleeve wear analysis model; Deploy the trained nozzle protection sleeve wear analysis model into the system; A guide nozzle protective sleeve wear feature set with critical life requirements is obtained, and a critical guide nozzle protective sleeve wear failure index is obtained by weighted calculation. The method for obtaining the decline of the wear failure index of the guide nozzle protective sleeve includes: Based on production planning, collect the operating data of several smelting operations expected to be carried out in the future; The working condition data of each set of future smelting operations are used as input into the nozzle protection sleeve wear analysis model; Through model calculation, the corresponding decline in the wear failure index of the nozzle protection sleeve is output for each future smelting operation; Based on the production plan, a set of copper molten converter operating condition data for several future smelting operations is obtained, and the data is sequentially input into the nozzle protection sleeve wear analysis model to obtain the decline in the nozzle protection sleeve wear failure index for several future smelting operations; Obtaining the real-time guide nozzle protective sleeve wear failure index of the guide nozzle protective sleeve, and according to the time sequence of several future smelting operations, accumulating the real-time guide nozzle protective sleeve wear failure index and the decline of the guide nozzle protective sleeve wear failure index corresponding to several future smelting operations one by one, until the accumulated result is greater than the critical guide nozzle protective sleeve wear failure index; Real-time monitoring of the wear of the guide nozzle protective sleeve and dynamic evaluation thereof, the method comprising: The wear index of the nozzle protective cover is obtained in real time by using sensors. The sensors are installed on the surface of the nozzle protective cover and the wear condition is evaluated by measuring temperature, pressure and vibration, or the morphology and characteristics of the worn surface are measured. According to the wear index of the nozzle protection sleeve monitored in real time, the wear analysis model constructed is used to calculate and obtain the real-time nozzle protection sleeve wear failure index, which reflects the wear degree and failure risk of the current nozzle protection sleeve. The real-time guide nozzle protective sleeve wear failure index and the wear index decline of several future smelting operations are gradually accumulated; the wear index decline of each smelting operation is considered one by one in chronological order, and accumulated with the real-time wear index until the accumulated result exceeds the critical guide nozzle protective sleeve wear failure index; Through real-time monitoring and cumulative calculation, the prediction and maintenance strategy of the nozzle protection sleeve is dynamically adjusted. Once the real-time wear index reaches the warning threshold or the cumulative result is close to the critical value, maintenance measures are taken in time; The smelting operation corresponding to the last accumulated decline in the wear failure index of the guide nozzle protection sleeve is deleted, and the remaining smelting operations corresponding to the accumulated decline in the wear failure index of the guide nozzle protection sleeve are summarized to obtain a set of smelting operations for the effective life of the guide nozzle protection sleeve; The method for obtaining the effective life smelting operation set of the guide nozzle protection sleeve includes: Get the smelting operation corresponding to the last accumulated decline in the wear failure index of the guide nozzle protection sleeve: The smelting operation corresponding to the decline in the wear failure index of the guide nozzle protection sleeve that participated in the accumulation for the last time is deleted from the accumulation process; After deleting the last smelting operation involved in the accumulation, the remaining smelting operations are aggregated to form a smelting operation set for the effective life of the guide nozzle protection sleeve; Count the production cycle of each smelting operation in the effective life smelting operation set of the guide nozzle protection cover, and collect the production cycle data of each smelting operation in the effective life smelting operation set of the guide nozzle protection cover; Obtained through production records and equipment monitoring systems, including the start and end times of each smelting operation; Based on the collected data, the production cycle of each smelting operation is calculated; Collect and sort out the production cycle data of all smelting operations to obtain a data set of a production cycle; The remaining useful life of the guide nozzle protective cover is calculated based on the obtained production cycle data. The remaining useful life is the time during which the guide nozzle protective cover can continue to operate safely in the current use state.

2. A method for evaluating the remaining life of a graphite guide nozzle protective sleeve of a copper molten converter as claimed in claim 1, characterized in that: The wear characteristic set of the guide nozzle protective sleeve includes porosity, thermal conductivity, deformation rate and surface wear.

3. The method for evaluating the remaining life of a graphite guide nozzle protective sleeve of a copper molten converter according to claim 1, characterized in that: The copper liquid converter operating condition data set includes converter operating temperature, copper liquid flow, production cycle and cooling water flow.

4. A system for assessing the remaining life of a graphite guide nozzle protective sleeve of a copper molten converter, characterized in that: The method for assessing the remaining life of a graphite guide nozzle protective sleeve of a copper molten converter as claimed in claim 1 is adopted, wherein the system comprises: A data acquisition module is used to obtain a set of wear characteristics of the nozzle protection sleeve and a set of operating conditions data of the copper molten converter for each smelting operation; the set of wear characteristics of the nozzle protection sleeve includes porosity, thermal conductivity, deformation rate and surface wear; the set of operating conditions data of the copper molten converter includes converter operating temperature, copper molten flow, production cycle and cooling water flow; A failure index calculation module performs weighted calculation on the wear feature set of the guide nozzle protective sleeve to obtain a decrease in the wear failure index of the guide nozzle protective sleeve of the smelting operation; A model building module combines several declines in the wear failure index of the guide nozzle protective sleeve with the corresponding copper liquid converter operating condition data sets as training data, uploads them to the deep learning model training platform for correlation training, and builds a guide nozzle protective sleeve wear analysis model; The critical state assessment module obtains the guide nozzle protective sleeve wear feature set with the critical life requirement of the guide nozzle protective sleeve, and performs weighted calculation on it to obtain the critical guide nozzle protective sleeve wear failure index; The future operating condition prediction submodule obtains the copper molten converter operating condition data set for several future smelting operations based on the production plan, and inputs them into the guide nozzle protective sleeve wear analysis model in sequence to obtain the decline in the guide nozzle protective sleeve wear failure index for several future smelting operations; The remaining life estimation submodule obtains the real-time nozzle protection sleeve wear failure index of the nozzle protection sleeve, and according to the time sequence of several future smelting operations, successively accumulates the real-time nozzle protection sleeve wear failure index and the nozzle protection sleeve wear failure index decline corresponding to several future smelting operations, until the accumulated result is greater than the critical nozzle protection sleeve wear failure index; The smelting operation corresponding to the last accumulated decline in the wear failure index of the guide nozzle protection sleeve is deleted, and the remaining smelting operations corresponding to the accumulated decline in the wear failure index of the guide nozzle protection sleeve are summarized to obtain a set of smelting operations for the effective life of the guide nozzle protection sleeve; The life calculation module counts the production cycle of each smelting operation in the smelting operation set of the effective life of the guide nozzle protection sleeve, and calculates the remaining effective life of the guide nozzle protection sleeve.

5. An electronic device for evaluating the remaining life of a graphite guide nozzle protective cover of a copper molten converter, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, and characterized in that: When the computer program is executed by the processor, the steps in the method according to any one of claims 1 to 3 are implemented.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps in the method according to any one of claims 1 to 3 are implemented.

Images