Steel analysis laboratory intelligent monitoring management system based on multi-source data fusion

Abstract

The invention belongs to the technical field of industrial automation and intelligent manufacturing, and particularly discloses a steel analysis laboratory intelligent monitoring management system based on multi-source data fusion, which comprises a parameter monitoring module, a process judgment module, a path decision module, a deviation analysis module, a deviation propagation judgment module and a health assessment module. According to the method, the equipment operation state parameters and the material quality parameters of the steel sample in each process are collected in real time, and the preset steel quality detection standard is combined to judge whether the current process is qualified or not, so that the problem that equipment monitoring and quality detection are mutually disjointed is solved; meanwhile, the state deviation degree of the previous procedure and the real-time monitoring parameters of the subsequent procedure are subjected to fusion analysis, cross-procedure quality influence evaluation is established, then the propagation path of the quality deviation between the procedures is dynamically tracked, the process set value of the subsequent procedure is accurately adjusted based on the deviation of the previous procedure, and the quality of the subsequent procedure is improved. And beforehand intervention on the quality risk is realized.

Description

Technical Field

[0001] This invention belongs to the field of industrial automation and intelligent manufacturing technology, and relates to an intelligent monitoring and management system for steel analysis laboratories based on multi-source data fusion. Background Technology

[0002] In the steel industry's production process, steel analysis laboratories play a crucial role in continuously monitoring and evaluating the performance indicators of steel samples at each processing stage. With the continuous development of intelligent manufacturing technology, traditional quality inspection and equipment monitoring methods are no longer sufficient to meet the high requirements for overall process quality stability and the predictability of equipment operating status.

[0003] Current steel analysis laboratories face the following technical limitations in monitoring process quality and equipment status: First, quality inspection data from each process are stored and processed independently, lacking effective data interaction and correlation analysis mechanisms. This makes it impossible to track and quantify the propagation path and impact of quality deviations from preceding processes in subsequent processes. Second, existing systems lack the ability to quantify quality fluctuations within acceptable ranges, failing to dynamically adjust subsequent process parameters based on deviations from preceding processes for proactive intervention. Furthermore, existing systems fail to integrate equipment operating status parameters with material quality parameters, making it difficult to accurately reflect overall equipment performance and resulting in a lack of predictability in equipment maintenance decisions.

[0004] Furthermore, in terms of planning the flow path of steel samples and handling process anomalies, existing technical solutions still mainly rely on the experience of operators to make judgments. They cannot comprehensively determine the flow path of steel samples based on real-time collected multi-source data and cross-process quality impacts, thus failing to guarantee the improvement of production efficiency and the consistency of quality control. Summary of the Invention

[0005] In view of this, in order to solve the problems mentioned in the background technology, an intelligent monitoring and management system for steel analysis laboratories based on multi-source data fusion is proposed.

[0006] The objective of this invention can be achieved through the following technical solution: This invention provides an intelligent monitoring and management system for steel analysis laboratories based on multi-source data fusion, including: a parameter monitoring module, which monitors in real time the equipment operating status parameters and material quality parameters of steel samples in the current process.

[0007] The process judgment module determines whether the current process is qualified based on the equipment operating status parameters and material quality parameters, combined with the preset steel quality inspection standards.

[0008] The path decision module determines whether the steel sample can continue to the subsequent process if the current process is unqualified. If it is determined that the process cannot continue, it triggers an equipment maintenance command; otherwise, it triggers the monitoring and analysis of the subsequent processes.

[0009] The deviation analysis module calculates the state deviation of the steel sample based on the material quality parameters and their potential impact on subsequent processes, if the current process is qualified.

[0010] The deviation propagation judgment module dynamically tracks the propagation path of quality deviations between processes based on the state deviation of steel samples, and comprehensively analyzes whether subsequent processes are qualified by combining real-time monitoring parameters of subsequent processes.

[0011] The health assessment module determines the operational qualification of equipment in each process based on the qualification results of each process and generates corresponding maintenance strategies.

[0012] Compared with the prior art, the beneficial effects of the present invention are as follows: (1) The present invention collects the equipment operation status parameters and material quality parameters of steel samples in each process in real time, and combines them with the preset steel quality inspection standards to determine whether the current process is qualified. This overcomes the problem of equipment monitoring and quality inspection being disconnected in the traditional system and realizes a comprehensive and accurate assessment of the process status.

[0013] (2) The present invention determines the flow path of steel samples based on the product characteristics qualification judgment results of the current process, thereby eliminating the reliance on manual experience, reducing the ineffective flow of unqualified products, and ensuring the smooth transfer of qualified steel samples in the production process, thus significantly improving production efficiency.

[0014] (3) By calculating the state deviation of steel samples based on the material quality parameters and their potential impact on subsequent processes, this invention realizes the quantitative analysis of quality fluctuations within the benchmark quality testing standard range, solves the current problem of lacking quantitative analysis of small deviations, and thus provides an accurate basis for subsequent identification of potential quality risks.

[0015] (4) This invention integrates the state deviation of steel samples with the real-time monitoring parameters of subsequent processes to establish a cross-process quality impact assessment, thereby dynamically tracking the propagation path of quality deviation between processes, and adjusting the process setting value of subsequent processes based on the deviation of the preceding processes, so as to realize the pre-intervention of quality risks and effectively ensure the quality stability of the whole process.

[0016] (5) This invention calculates the equipment operation qualification by comprehensively considering the process qualification ratio, quality failure rate and average inheritance deviation, and constructs a multi-dimensional equipment performance evaluation method, thereby overcoming the limitations of traditional single index evaluation and accurately reflecting the comprehensive performance of the equipment when processing samples in different states. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments 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 drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a schematic diagram showing the connections of the various modules in the system of the present invention.

[0019] Figure 2 This is a schematic diagram showing the connection steps for calculating the state deviation of the present invention.

[0020] Figure 3 This is a schematic diagram showing the connection steps for analyzing whether subsequent processes of the present invention are qualified. Detailed Implementation

[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] Please see Figure 1 As shown, the present invention provides an intelligent monitoring and management system for steel analysis laboratories based on multi-source data fusion. The system includes: a parameter monitoring module, a process judgment module, a path decision module, a deviation analysis module, a deviation propagation judgment module, and a health assessment module.

[0023] In the above, the process determination module is connected to the parameter monitoring module, the path decision module, and the deviation analysis module, respectively. The deviation analysis module is connected to the path decision module and the deviation propagation determination module, respectively. The deviation propagation determination module is also connected to the health assessment module.

[0024] The parameter monitoring module monitors the equipment operating status parameters and material quality parameters of the steel sample in the current process in real time.

[0025] It should be noted that the equipment operating status parameters include, but are not limited to, vibration amplitude, bearing temperature, and operating noise, while the material quality parameters include, but are not limited to, chemical composition, microstructure, and hardness.

[0026] The process determination module determines whether the current process is qualified based on the equipment operating status parameters and material quality parameters, combined with preset steel quality inspection standards.

[0027] For example, determining whether the current process is qualified includes: comparing the equipment operating status parameters of the steel sample in the current process with its reference equipment operating parameter range. When the equipment operating status parameters are all within its reference equipment operating parameter range, it indicates that the operating status of the equipment in the current process is stable, the key operating parameters are within the normal fluctuation range, and the equipment itself meets the processing requirements of the process. Therefore, the process conditions of the current process are determined to be qualified.

[0028] When the operating parameters of the equipment are not within the range of its baseline operating parameters, it indicates that the equipment may be in an abnormal state or there may be process fluctuations, which poses a risk to the stability and reliability of the processing. Therefore, the process conditions of the current process are deemed unqualified.

[0029] It should be noted that the reference equipment operating parameter range refers to the allowable fluctuation range of each operating parameter of the equipment under normal operating conditions. The reference equipment operating parameter range can be obtained through statistical analysis of long-term operating data of the equipment under normal production conditions.

[0030] Specifically, the baseline operating parameter range for the equipment can be established as follows: collect operating data of the equipment over at least one normal production cycle, calculate the average value and standard deviation of each operating parameter, and take the average value ± 3 times the standard deviation as the baseline operating parameter range for that parameter. Taking vibration amplitude as an example, if the statistically obtained average vibration amplitude is 30 μm and the standard deviation is 5 μm, then its baseline operating parameter range can be set to 15 μm to 45 μm.

[0031] The material quality parameters of the steel sample are compared with the corresponding benchmark quality test standard range in the steel quality test standard. When all material quality parameters are within the benchmark quality test standard range, it indicates that the chemical composition, microstructure, hardness and other material quality parameters of the steel sample meet the quality requirements after processing in the current process. Therefore, the product characteristics of the current process are deemed qualified.

[0032] When material quality parameters are outside the range of the benchmark quality inspection standard, it indicates that the steel sample has a quality deviation after processing in this process, and its material quality parameters exceed the allowable range, which may affect the quality of the final product. Therefore, the product characteristics of the current process are deemed unqualified.

[0033] It should be noted that the aforementioned steel quality testing standards are a collection of normative documents that specify the technical requirements and testing methods for steel products, and serve as the fundamental basis for determining whether steel quality is up to standard. These standards include, but are not limited to, national standards, industry standards, and international standards. These standards typically contain technical requirements for numerous material quality parameters of steel, such as chemical composition, microstructure, and hardness.

[0034] The specified range of the reference quality inspection standard specifically refers to the qualified threshold or allowable fluctuation range clearly defined for each specific material quality parameter in the steel material quality inspection standard. For example, for the carbon element content, its reference quality inspection standard may be specified as 0.15% to 0.25%. The system reads and analyzes the steel material quality inspection standard to obtain the reference values corresponding to each parameter, which are used as the direct comparison basis for process determination.

[0035] If both the process conditions and product characteristics of the current process are qualified, the current process is determined to be qualified; otherwise, the current process is determined to be unqualified.

[0036] The path decision module, if the current process is unqualified, determines whether the steel sample can continue with the subsequent processes. If it is determined that it cannot continue, an equipment maintenance instruction is triggered; otherwise, monitoring and analysis of the subsequent processes are triggered.

[0037] Exemplarily, determining whether the steel sample can continue with the subsequent processes includes: If the product characteristics of the current process are determined to be unqualified, it indicates that the material quality parameters of the steel sample have exceeded the reference quality inspection standard, and its product characteristics such as chemical composition, microstructure, or hardness cannot meet the quality requirements. Allowing the sample to continue to flow in this case will cause the quality defects to spread along the process chain, not only affecting the processing effect of the subsequent processes but also resulting in unqualified final product quality. Therefore, it is determined that the steel sample cannot continue with the subsequent processes.

[0038] If the product characteristics of the current process are determined to be qualified, it indicates that the material quality parameters of the steel sample all meet the requirements of the reference quality inspection standard, and its quality status meets the basic conditions for entering the next process. Even if there are fluctuations in the equipment operation state parameters, since the core product quality indicators are up to standard, to ensure production continuity and avoid excessive interruption, it is determined that the steel sample can continue with the subsequent processes.

[0039] The deviation analysis module, if the current process is qualified, calculates the state deviation degree of the steel sample based on the material quality parameters and their potential impact on the subsequent processes.

[0040] Please refer to Figure 2 As shown, exemplarily, calculating the state deviation degree of the steel sample includes: Q1. For each material quality parameter, compare its measured value with its reference quality inspection standard interval.

[0041] Q2. If the measured value is greater than the upper limit value of its reference quality inspection standard interval, calculate the ratio of the absolute value of the part by which the measured value exceeds the upper limit to the distance from the upper limit value to the central value of the reference quality inspection standard interval, and add the ratio to the preset penalty coefficient to obtain the parameter deviation value of the material quality parameter.

[0042] Preferably, when the measured value is greater than the upper limit of the reference interval, the parameter deviation is calculated according to the following formula: In the formula: Represents the measured values ​​of material quality parameters. This indicates the upper limit of the baseline quality testing standard range. This represents the center value of the reference quality testing standard range. The default penalty coefficient is , and The penalty coefficient The degree of impact of the out-of-limit parameters on the final product quality is set based on historical quality data statistics and expert scoring, with a specific value ranging from 0.5 to 2.0.

[0043] Calculated in this way, the ratio It quantifies the relative severity of measured values ​​exceeding the normal fluctuation range, while the penalty coefficient... The introduction of this ensures that the deviation value of any out-of-limit situation will be significantly greater than the maximum deviation within the acceptable range, thus enabling it to be effectively identified and amplified in subsequent fusion calculations.

[0044] Q3. If the measured value is less than the lower limit of its benchmark quality test standard range, calculate the ratio of the absolute value of the portion of the measured value below the lower limit to the distance from the center value of the benchmark quality test standard range to the lower limit value, and add the ratio to the preset penalty coefficient to obtain the parameter deviation value of the material quality parameter.

[0045] In a preferred embodiment, when the measured value is less than the lower limit of its reference quality test standard range, its parameter deviation value is calculated according to the following formula: In the formula This represents the lower limit of the benchmark quality testing standard range. This formula ensures that when the parameter value deviates negatively, it receives the same quantitative evaluation and penalty as a positive deviation.

[0046] Q4. If the measured value is within its reference quality test standard range, calculate the absolute value of the measured value deviating from the center value of the reference quality test standard range, and the ratio of this ratio to half the total width of the range. Use this ratio as the parameter deviation value of the material quality parameter.

[0047] In a preferred embodiment, when the measured value is within the reference quality inspection standard range, its parameter deviation value is calculated according to the following formula: , This represents the total width of the tolerance interval. This involves scaling the actual deviation to a scale corresponding to the total width. The parameter deviation value measures the proportion of the scaled-up deviation to the total width. When the parameter deviation value is 1, it indicates that the actual value has reached the specification limit. The parameter deviation value is... , or .

[0048] Q5. Based on the deviation direction of each material quality parameter, set the weighting coefficient of each material quality parameter.

[0049] Furthermore, the setting of the weight coefficients for each material quality parameter includes: Q5-1, obtaining the basic weight value of each material quality parameter based on the deviation direction of each material quality parameter through a preset deviation direction-basic weight mapping relationship.

[0050] It should be noted that the preset deviation direction-basic weight mapping relationship refers to the mapping relationship between the pre-set deviation direction of the material quality parameter and the corresponding basic weight value. The deviation direction represents the direction of deviation between the actual value and the target value of the material quality parameter, including both positive and negative deviations. The basic weight value is used to quantify the contribution of this deviation direction to the overall process anomaly; the higher the weight value, the more significant the impact of the deviation direction on the anomaly.

[0051] The method for obtaining this mapping relationship includes the following steps:

[0052] Based on historical process data, the correlation strength between the quality parameters of each material and process anomaly events under different deviation directions is statistically analyzed, and the correlation degree between each deviation direction and the frequency of anomaly occurrence is calculated through correlation analysis.

[0053] Based on the degree of correlation, the correlation is converted into initial weight values ​​through normalization, and the initial weight values ​​are then corrected based on expert experience to ensure the rationality and interpretability of the weight values.

[0054] The corrected weight values ​​are correlated with the deviation direction and stored as a mapping table to form a deviation direction-basic weight mapping relationship.

[0055] As a preferred implementation, the preset deviation direction-basic weight mapping relationship is established through the following steps:

[0056] Collect at least 200 sets of historical process data, statistically analyze the correlation strength between each material quality parameter and process anomaly events under different deviation directions, and calculate the correlation degree using the Pearson correlation coefficient method.

[0057] The correlation degree is mapped to the range [0,1] using a linear normalization method to obtain the initial weight value, which is then corrected based on expert experience.

[0058] Establish and store a mapping table between the corrected weight values ​​and the deviation direction.

[0059] Q5-2. Sum the basic weight values ​​of each material quality parameter to obtain the comprehensive basic weight value. Then, use the ratio of the basic weight value of each material quality parameter to the comprehensive basic weight value as the weight coefficient of each material quality parameter.

[0060] Q6. Based on the parameter deviation values ​​and weighting coefficients of each material quality parameter, the state deviation of the steel sample is obtained through weighted fusion calculation.

[0061] It should be noted that the formula for calculating the state deviation is as follows: In the formula For state deviation degree, Indicates the first The parameter deviation value of each material quality parameter. Indicates the first Weighting coefficients for each material quality parameter. , This represents the total number of material quality parameters.

[0062] By using weighted fusion to calculate the state deviation of steel samples, on the one hand, the weighting coefficients can reflect the relative importance of different material quality parameters to the state deviation, and reflect the different contributions of each parameter deviation to the overall degree of steel state abnormality. On the other hand, it can directly integrate the information of multiple material quality parameter deviation values, and comprehensively consider the influence of the synergistic effect of multiple parameters on the state deviation of steel.

[0063] The weighting coefficients can be obtained based on actual production experience. For example, first collect the deviation values ​​of each material quality parameter and their corresponding records of steel condition anomalies from historical production data, calculate the correlation coefficient between the deviation value of each parameter and the condition anomaly, determine the contribution of each parameter to the condition deviation through regression analysis, and after normalization, convert the contribution into the weighting coefficients of each material quality parameter, and the sum of the weighting coefficients is 1, so as to accurately quantify the condition deviation of the steel sample.

[0064] The deviation propagation determination module dynamically tracks the propagation path of quality deviation between processes based on the state deviation degree of the steel sample, and comprehensively analyzes whether the subsequent processes are qualified by combining real-time monitoring parameters of the subsequent processes.

[0065] Please see Figure 3 As shown, for example, the comprehensive analysis of whether the subsequent process is qualified includes: Y1, based on the state deviation degree, performing negative impact compensation on the process settings of the subsequent process to obtain dynamic setting values ​​of material characteristic parameters.

[0066] Furthermore, the calculation process of the dynamic setting value of the material characteristic parameter is as follows: Y1-1, multiply the state deviation degree by the preset process sensitivity coefficient to obtain the negative influence factor.

[0067] It should be noted that the preset process sensitivity coefficient is a process parameter used to quantify the current production process's tolerance and response to material condition deviations. This coefficient defines the amplification or reduction effect of the condition deviation degree on the required correction value of the material quality parameters, and its value directly reflects the necessity and urgency of parameter adjustment when a specific condition deviation occurs in the current process.

[0068] The method for obtaining the sensitivity coefficient of this process includes the following steps:

[0069] Extract the records of steel condition deviations at each stage of historical production data, as well as the actual parameter adjustments used in subsequent processes to correct these deviations.

[0070] A multiple linear regression model is used, with state deviation as the independent variable and the actual adjustment range for a specific material quality parameter, such as hardness, as the dependent variable, for fitting analysis. The process sensitivity coefficient is defined as the regression coefficient of state deviation in this regression model. For multiple material quality parameters, an independent regression model needs to be established for each parameter to obtain its corresponding process sensitivity coefficient.

[0071] As a preferred embodiment, the process sensitivity coefficient is obtained by collecting a preset number of historical production data sets, for example, no less than 100 sets, with the state deviation as the independent variable and the process adjustment amount of a specific material quality parameter as the dependent variable, and fitting a linear regression model using the least squares method. The regression coefficient is the process sensitivity coefficient.

[0072] Y1-2. Subtract the negative influence factor from the value 1 to obtain the correction coefficient.

[0073] Y1-3. Based on the preset process specifications, obtain the process setting reference values ​​for the material property parameters of subsequent processes.

[0074] Y1-4. Multiply the process setting benchmark value of the material property parameters by the correction coefficient to obtain the dynamic setting value of the material property parameters.

[0075] Y2. The equipment driving the subsequent processes processes the material based on the dynamically set values ​​of the material characteristic parameters, and monitors the actual material quality parameters of the processed steel sample.

[0076] Y3. Compare the actual material quality parameters with their benchmark quality inspection standards, and at the same time compare the equipment operating status parameters of the corresponding equipment in the subsequent processes with their benchmark equipment operating parameter range.

[0077] Y4. Based on the comparison results of the above two items, a comprehensive judgment is made as to whether the subsequent process is qualified. The specific logic of this judgment is consistent with the method of this invention for determining whether the current process is qualified, that is: when the process conditions and product characteristics of the subsequent process are both determined to be qualified, the subsequent process is comprehensively determined to be qualified. Otherwise, it is determined to be unqualified, which will not be repeated here.

[0078] The health assessment module determines the operational qualification of equipment in each process based on the qualification results of each process and generates corresponding maintenance strategies.

[0079] For example, determining the operational qualification of each process equipment includes: W1, based on the qualification judgment results of each process, selecting all qualified judgment records of process conditions within a preset statistical period to form a qualified process record set for each process.

[0080] It should be noted that if there are no records of qualified process conditions for a certain process within the preset statistical period, that is, the set of qualified process records is empty, the operation qualification of the equipment is directly determined to be 0, and the highest priority emergency maintenance strategy is generated without executing the subsequent W2 to W5 steps.

[0081] W2. Calculate the number of qualified process records in each process set, and use the ratio of this number to the total number of steel samples in the preset statistical period as the process qualification ratio of each process equipment.

[0082] W3. Based on the set of qualified process records, evaluate the quality failure rate of equipment in each process.

[0083] Furthermore, the evaluation of the quality failure rate of each process equipment includes: W3-1, traversing the qualified process record set, statistically analyzing the product characteristic judgment results, accumulating the number of records with unqualified product characteristics, recording them as the failure count, and counting the total number of records in the qualified process record set, recording them as the total number of qualified processes.

[0084] W3-2. Calculate the quality failure rate of each process by comparing the number of failures with the total number of successful processes. The quality failure rate is a value between 0 and 1, used to quantitatively characterize the frequency of quality defects in the produced steel samples under stable equipment operation.

[0085] W4. Based on the state deviation of each steel sample in each process within the qualified process record set, evaluate the average inherited deviation of the equipment in each process.

[0086] Furthermore, the evaluation of the average inherited deviation of each process equipment includes: W4-1, obtaining the state deviation of each steel sample in the qualified process record set when it enters the current process. For the steel sample in the first process, its state deviation upon entry is defined as a baseline value of 0. Here, the first process refers to the first processing step after the steel sample enters this monitoring and management system. It has not undergone any process processing within this system upon entry, so its state deviation is defined as a baseline value of 0.

[0087] W4-2. Sum all the obtained state deviations to obtain the total deviation.

[0088] W4-3. Divide the total deviation by the total number of records in the qualified process record set to calculate the average inherited deviation of each process equipment. The average inherited deviation is a value greater than or equal to 0, which is used to quantitatively characterize the average quality deviation level accumulated in the preceding process of the steel sample successfully processed by the equipment within the statistical period.

[0089] It should be further noted that, to ensure the robustness of the operational qualification calculation formula, the average inherited deviation needs to be normalized when the set of qualified process records is not empty. If there is insufficient historical data within the statistical period to obtain meaningful maximum and minimum values, the default value of the normalized average inherited deviation is set to 0.

[0090] W5. Calculate the operational qualification rate of each process equipment by multiplying the process qualification rate, quality failure rate and average inherited deviation of each process equipment.

[0091] It should be noted that the formula for calculating the operational qualification rate is as follows: In the formula For operational qualification, The process qualification ratio, For quality failure rate, This represents the average inheritance deviation after normalization.

[0092] It should be noted that this formula integrates key indicators from three dimensions through a product. The process pass rate is a positive indicator; the higher the value, the greater its contribution to operational pass rate. However, the quality failure rate and average inherited deviation are negative indicators; therefore, the formula uses... and This is transformed into a positive contribution factor. This allows the operational qualification rate to comprehensively and sensitively reflect the overall health status of the equipment.

[0093] To ensure dimensional consistency and calculation rationality, the average inheritance deviation needs to be normalized so that its value falls within a certain range. Within the interval. Normalization methods can perform a linear transformation based on the maximum and minimum values ​​of the historical data sequence, i.e. ,in For the average inheritance deviation, and These are the historical minimum and maximum values ​​of the inherited deviation within the preset statistical period, respectively.

[0094] The above formula can effectively characterize that a decline in performance in any dimension will lead to a significant reduction in operational qualification, thereby achieving a comprehensive and balanced assessment of the equipment's operating status, and providing accurate quantitative basis for predictive maintenance and process optimization.

[0095] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, in the form of a computer program product.

[0096] Those skilled in the art will recognize that the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0097] In addition, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0098] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0099] Finally, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A smart monitoring and management system for steel analysis laboratories based on multi-source data fusion, characterized in that: include: The parameter monitoring module monitors the equipment operating status parameters and material quality parameters of the steel sample in the current process in real time. The process judgment module determines whether the current process is qualified based on the equipment operating status parameters and material quality parameters, combined with the preset steel quality inspection standards. The path decision module determines whether the steel sample can continue to the subsequent process if the current process is unqualified. If it is determined that it cannot continue, it triggers the equipment maintenance instruction; otherwise, it triggers the monitoring and analysis of the subsequent process. The deviation analysis module calculates the state deviation of the steel sample based on the material quality parameters and their potential impact on subsequent processes, if the current process is qualified. The deviation propagation judgment module dynamically tracks the propagation path of quality deviation between processes based on the state deviation of steel samples, and comprehensively analyzes whether the subsequent processes are qualified by combining real-time monitoring parameters of the subsequent processes. The health assessment module determines the operational qualification of equipment in each process based on the qualification results of each process and generates corresponding maintenance strategies.

2. The intelligent monitoring and management system for steel analysis laboratories based on multi-source data fusion as described in claim 1, characterized in that: The determination of whether the current process is qualified includes: The operating status parameters of the corresponding equipment in the current process of the steel sample are compared with the range of its reference operating parameters. When all the operating status parameters are within the range of their reference operating parameters, the process conditions of the current process are deemed qualified. When the equipment operating status parameters are not within the range of its baseline equipment operating parameters, the process conditions of the current process are deemed unqualified. The material quality parameters of the steel sample are compared with the corresponding benchmark quality test standard range in the steel quality test standard. When all material quality parameters are within the benchmark quality test standard range, the product characteristics of the current process are deemed qualified. When material quality parameters are outside the range of their benchmark quality inspection standards, the product characteristics of the current process are deemed unqualified. If the process conditions and product characteristics of the current process are both qualified, the current process is deemed qualified; otherwise, the current process is deemed unqualified.

3. The intelligent monitoring and management system for steel analysis laboratories based on multi-source data fusion as described in claim 2, characterized in that: The determination of whether the steel sample can continue to perform subsequent processes includes: If the product characteristics of the current process are determined to be unqualified, then the steel sample cannot continue to perform subsequent processes. If the product characteristics of the current process are deemed qualified, then the steel sample is determined to be able to continue with the subsequent processes.

4. The intelligent monitoring and management system for steel analysis laboratories based on multi-source data fusion as described in claim 1, characterized in that: The calculation of the state deviation of the steel sample includes: Q1. For each material quality parameter, compare its measured value with its benchmark quality test standard range; Q2. If the measured value is greater than the upper limit of its benchmark quality test standard range, calculate the ratio of the absolute value of the measured value exceeding the upper limit to the distance from the upper limit of the benchmark quality test standard range to the center value, and add the ratio to the preset penalty coefficient to obtain the parameter deviation value of the material quality parameter. Q3. If the measured value is less than the lower limit of its benchmark quality test standard range, calculate the ratio of the absolute value of the portion of the measured value below the lower limit to the distance from the center value of the benchmark quality test standard range to the lower limit value, and add the ratio to the preset penalty coefficient to obtain the parameter deviation value of the material quality parameter. Q4. If the measured value is within its reference quality test standard range, calculate the absolute value of the measured value deviating from the center value of the reference quality test standard range, and the ratio of this ratio to half the total width of the range, and use this ratio as the parameter deviation value of the material quality parameter. Q5. Based on the deviation direction of each material quality parameter, set the weighting coefficient of each material quality parameter; Q6. Based on the parameter deviation values ​​and weighting coefficients of each material quality parameter, the state deviation of the steel sample is obtained through weighted fusion calculation.

5. The intelligent monitoring and management system for steel analysis laboratories based on multi-source data fusion as described in claim 4, characterized in that: The weighting coefficients for each material quality parameter include: Based on the deviation direction of each material quality parameter, the basic weight value of each material quality parameter is obtained through a preset deviation direction-basic weight mapping relationship. The basic weight values ​​of each material quality parameter are summed to obtain the comprehensive basic weight value. Then, the ratio of the basic weight value of each material quality parameter to the comprehensive basic weight value is used as the weight coefficient of each material quality parameter.

6. The intelligent monitoring and management system for steel analysis laboratories based on multi-source data fusion as described in claim 1, characterized in that: The comprehensive analysis of whether subsequent processes are qualified includes: Y1. Based on the state deviation, the process settings of subsequent processes are negatively affected and compensated to obtain dynamic setting values ​​of material property parameters. Y2. The equipment driving the subsequent processes processes the material based on the dynamically set values ​​of the material characteristic parameters, and monitors the actual material quality parameters of the processed steel sample. Y3. Compare the actual material quality parameters with its benchmark quality testing standards, and compare the equipment operating status parameters of the corresponding equipment in the subsequent processes with its benchmark equipment operating parameter range. Y4. Based on the comparison results of the above two items, determine whether the subsequent processes are qualified.

7. The intelligent monitoring and management system for steel analysis laboratories based on multi-source data fusion as described in claim 6, characterized in that: The calculation process for the dynamically set values ​​of the material property parameters is as follows: Multiply the state deviation by a preset process sensitivity coefficient to obtain a negative influence factor; Subtract the negative influence factor from the value of 1 to obtain the correction coefficient; Based on the preset process specifications, obtain the process setting reference values ​​for the material property parameters of subsequent processes; The material property parameter process setting baseline value is multiplied by the correction coefficient to obtain the dynamic setting value of the material property parameter.

8. The intelligent monitoring and management system for steel analysis laboratories based on multi-source data fusion as described in claim 1, characterized in that: Determining the operational qualification of equipment in each process includes: W1. Based on the qualification judgment results of each process, select all qualified judgment records of process conditions within the preset statistical period to form a qualified process record set for each process. W2. Calculate the number of qualified process records in each process set, and use the ratio of the number of qualified process records to the total number of steel samples in the preset statistical period as the process qualification ratio of each process equipment. W3. Based on the set of qualified process records, evaluate the quality failure rate of equipment in each process. W4. Based on the state deviation of each steel sample in each process within the qualified process record set, evaluate the average inherited deviation of the equipment in each process. W5. Calculate the operational qualification rate of each process equipment by multiplying the process qualification rate, quality failure rate and average inherited deviation of each process equipment.

9. The intelligent monitoring and management system for steel analysis laboratories based on multi-source data fusion as described in claim 8, characterized in that: The assessment of the quality failure rate of equipment in each process includes: Traverse the set of qualified process records, count the product characteristic judgment results, accumulate the number of records with unqualified product characteristics, and record them as the number of failures. Also count the total number of records in the set of qualified process records, and record it as the total number of qualified processes. The quality failure rate of each process equipment is calculated by comparing the number of failures with the total number of successful processes.

10. The intelligent monitoring and management system for steel analysis laboratories based on multi-source data fusion according to claim 8, characterized in that: The evaluation of the average inheritance deviation of equipment in each process includes: Obtain the state deviation degree of each steel sample in the qualified process record set when it enters the current process; for the steel sample of the first process, its state deviation degree when it enters is defined as the reference value of zero; The total deviation is obtained by summing up all the obtained state deviations. The average inherited deviation of each process equipment is calculated by dividing the total deviation by the total number of records in the qualified process record set.

Images