Methods, systems, devices, and media for monitoring an alloy production process

Abstract

This invention discloses a method, system, computer equipment, and medium for monitoring alloy production processes. The method includes: collecting production process data and alloy composition data from the alloy production line; processing the production process data and alloy composition data; predicting alloy properties based on the processed production process data and alloy composition data to obtain performance prediction results; and monitoring and issuing early warnings based on the performance prediction results. The proposed solution can detect abnormal trends during production, allowing operators to intervene promptly and avoid continuous scrap. Furthermore, by quantifying uncertainty, it accurately identifies high-risk batches for focused testing, reducing redundant testing costs for high-reliability batches. Finally, the system can automatically record the entire lifecycle data of each steel coil, providing complete data support for subsequent quality dispute handling and process optimization.

Description

Technical Field

[0001] This invention relates to the field of iron and steel metallurgy, and more specifically to a method, system, equipment, and medium for monitoring alloy production processes. Background Technology

[0002] Gear steel, as a core basic material for high-end equipment such as automobiles, high-speed trains, and wind power, has extremely high requirements for purity, hardenability bandwidth, and mechanical property stability. Current production quality control mainly faces the following challenges: 1. Significant feedback lag: In the traditional model, steel properties must be obtained after production by sampling and cutting for destructive physical experiments (such as end-quenching and tensile testing), which takes as long as 24-48 hours. Once a quality defect is discovered, the entire batch of steel has already been produced, resulting in huge economic losses.

[0003] 2. Process Black Box: Although there are numerous sensors on the production line, there is a lack of a correlation model between the data and the final quality. Operators find it difficult to determine the specific impact of current temperature fluctuations or component fine-tuning on the final performance.

[0004] 3. Lack of early warning mechanism: Existing monitoring systems are mostly based on upper and lower limit alarms of single parameters (such as high temperature alarms), which cannot provide comprehensive early warning for quality fluctuations caused by the coupling of multiple parameters.

[0005] Therefore, there is an urgent need for a solution that can use real-time data to predict product quality online and identify potential risks in advance during the production process. Summary of the Invention

[0006] In view of this, in order to overcome at least one aspect of the above-mentioned problems, embodiments of the present invention provide a method for monitoring an alloy production process, comprising the following steps: Collect production process data and alloy composition data from the alloy production line; The production process data and the alloy composition data are processed; Based on the processed production process data and alloy composition data, the alloy properties are predicted to obtain performance prediction results. Monitoring and early warning are conducted based on the performance prediction results.

[0007] In some embodiments, collecting production process data and alloy composition data from the alloy production line further includes: Collect heating temperature, initial rolling temperature, final rolling temperature, cooling rate, pulling speed, and rolling force on the alloy production line; Collect alloy composition data after each process on the alloy production line.

[0008] In some embodiments, processing the production process data and the alloy composition data further includes: The production process data and alloy composition data are subjected to protocol parsing, time alignment, and data cleaning preprocessing.

[0009] In some embodiments, protocol parsing of the production process data and the alloy composition data further includes: The proprietary protocols corresponding to the collected production process data and alloy composition data are converted into standard MQTT or OPC UA protocols.

[0010] In some embodiments, time alignment of the production process data and the alloy composition data further includes: The alloy composition data collected at different time points were matched with the production process data.

[0011] In some embodiments, monitoring and early warning based on the performance prediction results further include: A Level 1 warning is triggered in response to the performance prediction result not falling within the preset acceptable range; When the performance prediction result is within a preset acceptable range, but the standard deviation of the performance prediction result exceeds a safety threshold, a level two warning is triggered.

[0012] In some embodiments, the method further includes: Based on the first-level or second-level early warning signal, process parameter adjustment suggestions are generated and fed back to the production line control system to correct subsequent production processes.

[0013] Based on the same inventive concept, according to another aspect of the present invention, embodiments of the present invention also provide a system for monitoring an alloy production process, comprising: The data sensing module is configured to collect production process parameters and raw material composition data on the gear steel production line; The edge computing module is configured to process the production process parameters and raw material composition data collected by the data sensing module; The intelligent analysis module is configured to predict the performance of the current batch of gear steel based on the data processed by the edge computing module. The monitoring and early warning module is configured to perform monitoring and early warning based on the performance prediction results output by the intelligent analysis module.

[0014] Based on the same inventive concept, according to another aspect of the present invention, embodiments of the present invention also provide a computer device, comprising: At least one processor; and The memory stores a computer program that can run on the processor, which, when executing the program, performs the steps of any of the methods described above for monitoring the alloy production process.

[0015] Based on the same inventive concept, according to another aspect of the present invention, embodiments of the present invention also provide a computer-readable storage medium storing a computer program that, when executed by a processor, performs the steps of any of the methods for monitoring an alloy production process as described above.

[0016] This invention offers one of the following beneficial technical effects: The proposed solution can detect abnormal trends during the production process, allowing operators to intervene promptly and preventing continuous scrap. Furthermore, by quantifying uncertainty, it accurately identifies high-risk batches for focused inspection, reducing redundant inspection costs for high-reliability batches. Finally, the system automatically records the entire lifecycle data of each steel coil, providing comprehensive data support for subsequent quality dispute handling and process optimization. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other embodiments can be obtained based on these drawings without creative effort.

[0018] Figure 1 A schematic flowchart of a method for monitoring an alloy production process provided for an embodiment of the present invention; Figure 2 A schematic diagram of a system for monitoring the alloy production process provided in an embodiment of the present invention; Figure 3 A schematic diagram of the structure of a computer device provided for an embodiment of the present invention; Figure 4 A schematic diagram of the structure of a computer-readable storage medium provided for an embodiment of the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the present invention clearer, the embodiments of the present invention will be further described in detail below with reference to specific examples and the accompanying drawings.

[0020] It should be noted that all uses of "first" and "second" in the embodiments of the present invention are for the purpose of distinguishing two entities or parameters with the same name but different names. It is clear that "first" and "second" are only for the convenience of expression and should not be construed as limiting the embodiments of the present invention. Subsequent embodiments will not explain this in detail.

[0021] According to one aspect of the present invention, embodiments of the present invention provide a method for monitoring alloy production processes, such as... Figure 1 As shown, it may include the following steps: S1, collect production process data and alloy composition data from the alloy production line; S2, Process the production process data and the alloy composition data; S3, Based on the processed production process data and the alloy composition data, the alloy properties are predicted to obtain the performance prediction results; S4. Monitor and issue early warnings based on the performance prediction results.

[0022] The proposed solution can detect abnormal trends during the production process, allowing operators to intervene promptly and prevent continuous scrap. Furthermore, by quantifying uncertainty, it accurately identifies high-risk batches for focused inspection, reducing redundant testing costs for high-reliability batches. Finally, the system automatically records the entire lifecycle data for each steel coil, providing comprehensive data support for subsequent quality dispute resolution and process optimization.

[0023] In some embodiments, collecting production process data and alloy composition data from the alloy production line further includes: Collect heating temperature, initial rolling temperature, final rolling temperature, cooling rate, pulling speed, and rolling force on the alloy production line; Collect alloy composition data after each process on the alloy production line.

[0024] Specifically, the data sensing layer is used for data collection, which is responsible for obtaining raw data from the production site, including process data and alloy composition data after each process.

[0025] The process data includes heating temperature, initial rolling temperature, final rolling temperature, cooling rate, casting speed, and rolling force, such as high-frequency time-series data in the L1 / L2 level automation system, including continuous casting casting speed, secondary cooling water flow rate, heating furnace section temperature, roughing / finishing mill inlet temperature, rolling force, and post-rolling cooling rate.

[0026] Alloy composition data includes the content of alloying elements such as C, Si, Mn, Cr, Mo, S, and P. For example, data on the smelting composition after ladle refining (C, Si, Mn, P, S, Cr, Ni, Mo, Al, etc.) can be collected.

[0027] In some embodiments, processing the production process data and the alloy composition data further includes: The production process data and alloy composition data are subjected to protocol parsing, time alignment, and data cleaning preprocessing.

[0028] In some embodiments, protocol parsing of the production process data and the alloy composition data further includes: The proprietary protocols corresponding to the collected production process data and alloy composition data are converted into standard MQTT or OPC UA protocols. In some embodiments, time alignment of the production process data and the alloy composition data further includes: The alloy composition data collected at different time points were matched with the production process data.

[0029] Specifically, the edge computing layer deployed on the edge gateway at the workshop side can be used to perform protocol parsing, time alignment, and data cleaning preprocessing on the collected production process data and alloy composition data.

[0030] Protocol conversion involves converting the proprietary protocol of the device used to collect data into a standard protocol, such as converting the proprietary protocol of Siemens / Schneider PLC into the standard MQTT or OPC UA protocol.

[0031] Data alignment is based on material tracking ID, matching component data collected at different time points with rolling process data to form a complete "furnace-sample" dataset.

[0032] Adaptive preprocessing can clean outliers, correct skewed data, and ensure the quality of data uploaded to the cloud.

[0033] In some embodiments, adaptive preprocessing can be: 1. First, check the standard deviation σ. If σ = 0 (or less than the machine precision ε), it means that the feature has the same value in all samples and contains no information. The processing strategy is to avoid performing division operations, that is, to directly set all values ​​in the feature column to 0. This eliminates division-by-zero errors at the source and enhances the stability of the algorithm when running unattended.

[0034] 2. If the standard deviation is not equal to 0, the processing strategy is determined based on the skewness, kurtosis, and extreme value range, and the corresponding set is processed according to the processing strategy.

[0035] If the kurtosis is greater than the first threshold, it indicates that the data conforms to a long-tailed / outlier distribution. In this case, the median (Q2) and interquartile range (Q1, Q3) can be used instead of the mean and variance for data standardization. x' = (x - Q2) / (Q3 - Q1) Where x represents the original data.

[0036] If the kurtosis is greater than the first threshold and the absolute value of the skewness is less than the second threshold, then the data conforms to an approximately normal distribution, and standard Z-score can be used for data standardization. x' = (x - μ) / σ Where σ is the standard deviation and μ is the mean.

[0037] If the kurtosis is greater than the first threshold and the absolute value of the skewness is not less than the second threshold, it indicates that the data conforms to a skewed distribution. In this case, log smoothing can be performed on the data in the corresponding set, and then data standardization can be performed based on the mean and standard deviation of the log smoothed data. This effectively stretches dense intervals and compresses long-tail intervals, making it closer to a normal distribution. X log = ln(x + c) x' = (X log - μ log ) / σ log Where, μ log For multiple X log The mean, σ log For multiple X log The standard deviation, where c is a constant (e.g., 10). -6 ).

[0038] If the data exhibits characteristics of a strictly limited known range of values, then Min-Max normalization can be used for standardization, i.e.: x' = (x - X_min) / (X_max - X_min) In some embodiments, S3, based on the processed production process data and the alloy composition data, the alloy performance is predicted to obtain a performance prediction result. Specifically, an intelligent analysis layer can be deployed on a private cloud or industrial server, and its core components are: Performance prediction engine: Loads a pre-trained alloy performance prediction model based on ensemble learning. Inputs real-time process parameters and outputs predicted end hardenability (Jominy value), tensile strength, yield strength, and other indicators in milliseconds.

[0039] Uncertainty assessment unit: Calculates the confidence interval of the prediction results. If the model determines that the current operating condition belongs to the "unknown domain" (i.e., the prediction variance is large), then the batch is marked as high risk.

[0040] In some embodiments, monitoring and early warning based on the performance prediction results further include: A Level 1 warning is triggered in response to the performance prediction result not falling within the preset acceptable range; When the performance prediction result is within a preset acceptable range, but the standard deviation of the performance prediction result exceeds a safety threshold, a level two warning is triggered.

[0041] In some embodiments, the method further includes: Based on the first-level or second-level early warning signal, process parameter adjustment suggestions are generated and fed back to the production line control system to correct subsequent production processes.

[0042] Specifically, the monitoring and early warning system can be used to display the predicted performance curve of the current furnace batch and the national standard bandwidth in real time at the application layer, and a tiered early warning mechanism can be provided: Red light alarm: Predictive performance is unqualified. It is recommended to stop the machine immediately or scrap it.

[0043] Yellow light warning: The prediction performance is acceptable but the confidence level is low (high model uncertainty), or the performance is on the verge of being acceptable. It is recommended to sample and retest or fine-tune the process.

[0044] Parameter recommendations: Based on the backpropagation algorithm, we provide optimized suggested values ​​for process parameters (such as tempering temperature).

[0045] Example 1: Real-time monitoring of a 20CrMnTiH gear steel production line This embodiment is deployed on a special steel gear steel production line, with the goal of real-time monitoring of the end hardenability J9 point hardness of the gear steel (standard requirement: 30-43 HRC).

[0046] 1. Hardware deployment and data access Sensing layer: It connects to the Siemens S7-1500 PLC via the OPC UA protocol to collect the final rolling temperature (target 850℃) of the finishing mill and the cooling rate of the Steyrmo air-cooled line; it also connects to the LIMS database via the ODBC interface to read the smelting composition.

[0047] Edge layer: Using an industrial edge gateway, process data is collected once per second, and the composition data is aligned with the temperature data when passing through the finishing mill based on the billet tracking ID to form a complete feature vector.

[0048] 2. The intelligent analysis and prediction system loads a pre-trained XGBoost and random forest ensemble model.

[0049] Scenario A: Normal production (green light) Data collected: C=0.20%, Cr=1.10%, final rolling temperature=852℃.

[0050] Model output: Predicted mean μ = 33.5 HRC, predicted standard deviation σ = 0.2.

[0051] The system determines that 33.5 is within the range of [30, 36] and σ < 0.5 (high confidence).

[0052] Action: The interface displays a green light and records data, requiring no manual intervention.

[0053] Scenario B: Quality Anomaly Alarm (Red Light - Level 1 Warning) Data collected: Due to a heating furnace malfunction, the final rolling temperature of a certain batch dropped to 810℃.

[0054] Model output: Predicted mean μ = 28.5 HRC, predicted standard deviation σ = 0.3.

[0055] The system determined that 28.5 < 30 (below the lower limit of the national standard).

[0056] Action: Triggering a Level 1 warning, the on-site alarm light turns red, and the system automatically sends a command to the PLC to mark the reel as "defective" and automatically divert it to the scrap area at the offline point.

[0057] Scenario C: High-risk warning (yellow light - Level 2 warning) Data collected: A certain batch used a new manufacturer's ferromolybdenum alloy, which caused fluctuations in the trace element Mo content, and the data distribution differed significantly from historical training data.

[0058] Model output: Predicted mean μ = 32.0 HRC (acceptable), but predicted standard deviation σ = 1.5 (high uncertainty).

[0059] The system determines that although the predicted value is acceptable, σ > 1.0 (threshold).

[0060] Action: A level-two warning is triggered, a yellow alert is displayed on the interface, and a pop-up window prompts "Model confidence is low, it is recommended to take samples for retesting." The quality inspector receives a text message notification and, after this batch leaves the production line, takes a sample section and sends it to the laboratory for physical end-quenching experiments to ensure everything is in perfect working order.

[0061] 3. Feedback control: In response to the low temperature problem in scenario B, the feedback control module calculates a compensation strategy and suggests that the furnace outlet temperature of the next steel billet be increased by 15°C. This set value is then recommended to the operator for confirmation, thereby achieving closed-loop control.

[0062] The proposed solution can detect abnormal trends during the production process, allowing operators to intervene promptly and prevent continuous scrap. Furthermore, by quantifying uncertainty, it accurately identifies high-risk batches for focused inspection, reducing redundant testing costs for high-reliability batches. Finally, the system automatically records the entire lifecycle data for each steel coil, providing comprehensive data support for subsequent quality dispute resolution and process optimization.

[0063] Based on the same inventive concept, according to another aspect of the present invention, embodiments of the present invention also provide a system 400 for monitoring an alloy production process, such as... Figure 2 As shown, it includes: Data sensing module 401 is configured to collect production process parameters and raw material composition data on the gear steel production line; Edge computing module 402 is configured to process the production process parameters and raw material composition data collected by the data sensing module; The intelligent analysis module 403 is configured to predict the performance of the current batch of gear steel based on the data processed by the edge computing module. The monitoring and early warning module 404 is configured to perform monitoring and early warning based on the performance prediction results output by the intelligent analysis module.

[0064] In some embodiments, collecting production process data and alloy composition data from the alloy production line further includes: Collect heating temperature, initial rolling temperature, final rolling temperature, cooling rate, pulling speed, and rolling force on the alloy production line; Collect alloy composition data after each process on the alloy production line.

[0065] In some embodiments, processing the production process data and the alloy composition data further includes: The production process data and alloy composition data are subjected to protocol parsing, time alignment, and data cleaning preprocessing.

[0066] In some embodiments, protocol parsing of the production process data and the alloy composition data further includes: The proprietary protocols corresponding to the collected production process data and alloy composition data are converted into standard MQTT or OPC UA protocols. In some embodiments, time alignment of the production process data and the alloy composition data further includes: The alloy composition data collected at different time points were matched with the production process data.

[0067] In some embodiments, monitoring and early warning based on the performance prediction results further include: A Level 1 warning is triggered in response to the performance prediction result not falling within the preset acceptable range; When the performance prediction result is within a preset acceptable range, but the standard deviation of the performance prediction result exceeds a safety threshold, a level two warning is triggered.

[0068] In some embodiments, a feedback control module is further included, configured to: Based on the first-level or second-level early warning signal, process parameter adjustment suggestions are generated and fed back to the production line control system to correct subsequent production processes.

[0069] Based on the same inventive concept, according to another aspect of the present invention, such as Figure 3 As shown, embodiments of the present invention also provide a computer device 501, comprising: At least one processor 520; and The memory 510 stores a computer program 511 that can run on a processor. When the processor 520 executes the program, it performs the steps of any of the methods described above for monitoring the alloy production process.

[0070] Based on the same inventive concept, according to another aspect of the present invention, such as Figure 4 As shown, embodiments of the present invention also provide a computer-readable storage medium 601, which stores a computer program 610. When executed by a processor, the computer program 610 performs the steps of any of the methods described above for monitoring the alloy production process.

[0071] Finally, it should be noted that those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods.

[0072] Furthermore, it should be understood that the computer-readable storage medium (e.g., memory) described herein may be volatile memory or non-volatile memory, or may include both volatile memory and non-volatile memory.

[0073] Those skilled in the art will also understand that the various exemplary logic blocks, modules, circuits, and algorithm steps described in conjunction with the disclosure herein can be implemented as electronic hardware, computer software, or a combination of both. To clearly illustrate this interchangeability between hardware and software, the functionality of various illustrative components, modules, circuits, and steps has been generally described. Whether this functionality is implemented as software or as hardware depends on the specific application and the design constraints imposed on the system as a whole. Those skilled in the art can implement the functionality in various ways for each specific application, but such implementation decisions should not be construed as departing from the scope of the embodiments disclosed herein.

[0074] The above are exemplary embodiments disclosed in this invention. However, it should be noted that various changes and modifications can be made without departing from the scope of the embodiments of this invention as defined by the claims. The functions, steps, and / or actions of the methods according to the disclosed embodiments described herein do not need to be performed in any particular order. Furthermore, although the elements disclosed in the embodiments of this invention may be described or claimed individually, they may be understood as multiple unless explicitly limited to a singular number.

[0075] It should be understood that, as used herein, the singular form “a” is intended to include the plural form as well, unless the context clearly supports an exception. It should also be understood that, as used herein, “and / or” refers to any and all possible combinations of one or more of the associated listed items.

[0076] The embodiment numbers disclosed in the above embodiments of the present invention are merely for description and do not represent the superiority or inferiority of the embodiments.

[0077] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0078] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of the invention (including the claims) is limited to these examples. Within the framework of the invention, technical features of the above embodiments or different embodiments can be combined, and many other variations of different aspects of the invention exist, which are not provided in the details for the sake of brevity. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the invention should be included within the protection scope of the invention.

Claims

1. A method for monitoring an alloy production process, characterized in that, include: Collect production process data and alloy composition data from the alloy production line; The production process data and the alloy composition data are processed; Based on the processed production process data and alloy composition data, the alloy properties are predicted to obtain performance prediction results. Monitoring and early warning are conducted based on the performance prediction results.

2. The method as described in claim 1, characterized in that, Collect production process data and alloy composition data from the alloy production line, further including: Collect heating temperature, initial rolling temperature, final rolling temperature, cooling rate, pulling speed, and rolling force on the alloy production line; Collect alloy composition data after each process on the alloy production line.

3. The method as described in claim 1, characterized in that, Processing the production process data and the alloy composition data further includes: The production process data and alloy composition data are subjected to protocol parsing, time alignment, and data cleaning preprocessing.

4. The method as described in claim 3, characterized in that, The protocol parsing of the production process data and the alloy composition data further includes: The proprietary protocols corresponding to the collected production process data and alloy composition data are converted into standard MQTT or OPC UA protocols.

5. The method as described in claim 3, characterized in that, Time alignment of the production process data and the alloy composition data further includes: The alloy composition data collected at different time points were matched with the production process data.

6. The method as described in claim 1, characterized in that, Monitoring and early warning based on the performance prediction results further include: A Level 1 warning is triggered in response to the performance prediction result not falling within the preset acceptable range; When the performance prediction result is within a preset acceptable range, but the standard deviation of the performance prediction result exceeds a safety threshold, a level two warning is triggered.

7. The method as described in claim 6, characterized in that, Also includes: Based on the first-level or second-level early warning signal, process parameter adjustment suggestions are generated and fed back to the production line control system to correct subsequent production processes.

8. A system for monitoring an alloy production process, characterized in that, include The data sensing module is configured to collect production process parameters and raw material composition data on the gear steel production line; The edge computing module is configured to process the production process parameters and raw material composition data collected by the data sensing module; The intelligent analysis module is configured to predict the performance of the current batch of gear steel based on the data processed by the edge computing module. The monitoring and early warning module is configured to perform monitoring and early warning based on the performance prediction results output by the intelligent analysis module.

9. A computer device, comprising: At least one processor; as well as A memory storing a computer program executable on the processor, characterized in that the processor executes the program by performing the steps of the method as described in any one of claims 1-7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it performs the steps of the method as described in any one of claims 1-7.

Images