Petroleum coke blending uniform stirring system

Abstract

The present application relates to the technical field of petroleum chemical industry, and discloses a petroleum coke blending uniform stirring system, which comprises a parameter setting module, a process control module, a uniformity evaluation module, an optimization decision module, a self-adaptive optimization module and a report generation module. The parameter setting module dynamically generates optimized blending parameters and outputs setting data. The process control module is called to execute stirring actions and real-time monitor the mixing state, and output process data. The uniformity evaluation module constructs an evaluation matrix, analyzes the blending uniformity level and outputs evaluation results. The optimization decision module matches a historical database to generate decision instructions and feedback adjustment parameters. The self-adaptive optimization module analyzes the system performance profile, identifies weak points and generates optimization instructions. The report generation module integrates and outputs uniformity reports. The present application ensures the uniformity of petroleum coke distribution, improves the reliability and self-adaptive control capability of the stirring process.

Description

Technical Field

[0001] This invention relates to the field of petrochemical technology, specifically to a petroleum coke blending and uniform stirring system. Background Technology

[0002] Petrochemical industry, or petrochemical industry for short, generally refers to the chemical industry that uses petroleum and natural gas as raw materials. It has a wide scope and many products. Crude oil is cracked, reformed and separated to provide basic raw materials such as ethylene, propylene, butene, butadiene, benzene, toluene, xylene, naphthalene and so on.

[0003] Currently, due to the characteristics of raw materials and fluctuations in operating conditions during the blending and mixing process of petroleum coke, traditional systems rely on fixed thresholds when setting parameters, which cannot detect the gradual trend of blending parameters deviating from standard operating conditions in real time. When the parameter settings deviate from the actual situation, it will lead to inaccurate blending ratios and affect the uniformity of subsequent mixing.

[0004] Therefore, a petroleum coke blending and uniform mixing system is proposed to solve the above problems. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides a petroleum coke blending and uniform stirring system, which solves the problem mentioned in the background art of being unable to detect the gradual trend of blending parameters deviating from standard operating conditions in real time, and the problem that this leads to inaccurate blending ratios.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a petroleum coke blending and uniform stirring system, comprising: The parameter setting module generates blending parameters using the blending ratio calculation unit, sets operating procedures through the rule configuration unit, and outputs setting data through the environmental factors unit. The process control module receives the set data, collects real-time data through the sensor data acquisition unit, executes the stirring action using the stirring control unit, and outputs process data through the uniformity detection unit. The uniformity evaluation module receives the process data, constructs an evaluation matrix through the data acquisition unit, outputs the evaluation results through the evaluation calculation unit, and provides adjustment feedback through the feedback unit. The optimization decision module receives the evaluation results, generates decision instructions by calling the database through the feature extraction unit and the matching unit, and feeds them back to the parameter setting module through the inference unit to adjust the parameters. The adaptive optimization module receives the evaluation results output by the uniformity evaluation module, analyzes the system performance through the performance profile construction unit, identifies problem points through the weakness analysis unit, and generates optimization instructions through the parameter control unit. The report generation module integrates the evaluation results with system data and generates a uniformity report through the indicator fusion unit and weight calculation unit.

[0007] Preferably, the process of generating blending parameters using the blending ratio calculation unit in the parameter setting module specifically includes: Set key operating parameters for petroleum coke blending, including raw material ratio, stirring speed, and time threshold; Calculate the degree of deviation of the current blending parameters from the standard operating condition range. If the deviation is greater than zero, trigger the parameter adjustment mechanism. Based on historical blending data and environmental factors, optimization parameters are dynamically generated through the proportion calculation unit and output to the process control module.

[0008] Preferably, the process of calculating the degree of deviation specifically includes: The real-time blending parameter values ​​are obtained and compared with the preset standard range to determine the deviation. When the deviation exceeds the tolerance threshold, the adjustment unit of the parameter setting module is activated to recalculate the blending ratio. By integrating external conditions, including temperature and humidity, through the environmental factors unit, the parameter settings are ensured to meet the actual working conditions.

[0009] Preferably, the process of receiving the set data in the process control module, acquiring real-time data through the sensor data acquisition unit, executing the stirring action using the stirring control unit, and outputting process data through the uniformity detection unit specifically includes: Initialize the operating parameters of the mixing equipment based on the setting data output by the parameter setting module; The mixing state of petroleum coke, including viscosity, density, and distribution uniformity, is monitored in real time through a sensor data acquisition unit. The stirring control unit is used to adjust the speed and direction of the stirrer to ensure that the blended materials are mixed evenly; The homogeneity detection unit performs real-time analysis on the mixed sample and calculates the homogeneity index using the following formula: ; in, The coefficient of variation is 1. The standard deviation of the sample parameter, The mean of the sample parameters is used to output process data to the uniformity evaluation module.

[0010] Preferably, the analysis process of the uniformity detection unit specifically includes: Collect multi-point sample data during the stirring process and construct a time series curve; Calculate the standard deviation and coefficient of variation of the sample parameters to assess the level of homogeneity; When the uniformity is below the set threshold, a feedback mechanism is triggered to notify the process control module to adjust the stirring parameters.

[0011] Preferably, the process of receiving the process data in the uniformity evaluation module, constructing an evaluation matrix through the data acquisition unit, outputting the evaluation result through the evaluation calculation unit, and providing adjustment feedback through the feedback unit specifically includes: Key indicators in the integration process data include mixing uniformity and blending consistency; The indicators are organized into a multi-dimensional matrix through the data collection unit, with each dimension representing an evaluation factor. The evaluation calculation unit uses a weighted algorithm to process matrix data and calculates the overall score using the following formula: ; in, Based on the overall score, Let be the weight coefficient of the i-th indicator. Let i be the standardized value of the i-th indicator. The total number of indicators; The feedback unit provides real-time adjustment suggestions to the optimization decision-making module based on the priority of the results.

[0012] Preferably, the weighted algorithm process of the evaluation calculation unit specifically includes: Each evaluation factor is assigned a weight coefficient, which is dynamically adjusted based on historical data and the learning model. Calculate a comprehensive score, and if the score is lower than the safety threshold, it is marked as requiring emergency intervention; The feedback unit maps the scores into specific operation instructions to ensure timely system response.

[0013] Preferably, the process in the optimization decision module that receives the evaluation result, generates a decision instruction by calling the database through the feature extraction unit and the matching unit, and feeds it back to the parameter setting module through the inference unit to adjust the parameters specifically includes: Receive the evaluation results from the uniformity evaluation module and extract key features including uniformity trends and deviation patterns; Similar cases are identified by matching the feature extraction unit with the historical database; The matching unit calculates the similarity, selects the optimal decision scheme, and feeds back the simulation effect to the parameter setting module after the deduction unit. The simulation unit takes into account production plans and resource constraints to ensure the feasibility of decisions.

[0014] Preferably, the simulation process of the inference unit specifically includes: Based on the current system status and decision-making scheme, a virtual blending scenario is constructed; Run simulations to predict uniformity changes after parameter adjustments; If the prediction result is better than the threshold, the decision instruction is confirmed; otherwise, the database is re-matched to generate a new solution.

[0015] Preferably, the process by which the adaptive optimization module receives the evaluation results output by the uniformity evaluation module, analyzes the system performance through the performance profiling unit, identifies problem points through the weakness analysis unit, and generates optimization instructions through the parameter control unit specifically includes: By analyzing historical operational data through performance profiling building units, a system health status profile is generated. The weakness analysis unit identifies common problems in the blending and mixing process, including equipment wear and raw material variations; The parameter control unit dynamically adjusts and optimizes instructions based on the profile and problem points, enabling the system to learn and optimize itself. The optimized instructions are integrated into the report generation module to enable long-term performance tracking.

[0016] Compared with the prior art, the present invention provides a petroleum coke blending and uniform stirring system, which has the following beneficial effects: 1. In this invention, the deviation trend of petroleum coke blending parameters from standard operating conditions is monitored in real time by the parameter setting module, the blending ratio calculation unit dynamically generates optimized blending parameters, the operation specifications are set by the rule configuration unit, and the set data output by the environmental factors unit is combined to sense the gradual deviation of parameters, adjust the blending ratio in time, avoid the problem of ratio inaccuracy caused by fixed threshold setting, ensure the accuracy and stability of the blending process, and improve the system response sensitivity and blending quality consistency.

[0017] 2. In this invention, the process control module integrates a sensor data acquisition unit to collect stirring data in real time, the stirring control unit executes the stirring action, and the uniformity detection unit analyzes the mixing state in real time and outputs process data. This enables the system to comprehensively track changes in the mixing state of materials, dynamically adjust stirring parameters, and immediately correct any abnormalities in uniformity through a feedback mechanism. This solves the monitoring blind spots in traditional control, ensures the uniformity of petroleum coke distribution, and improves the reliability and adaptive control capability of the stirring process.

[0018] 3. In this invention, a multi-dimensional evaluation matrix is ​​constructed through the data acquisition unit of the uniformity evaluation module, and the quantitative evaluation results are output by the evaluation calculation unit. Historical data is matched by the feature extraction unit of the optimization decision module, and decision instructions are generated by the deduction unit and fed back to the parameter setting module. This enables a multi-dimensional comprehensive analysis of blending uniformity, identifies deviation patterns and forms a closed-loop optimization, improves the scientificity and accuracy of system decision-making, and ensures stable control of blending quality and continuous optimization of system performance. Attached Figure Description

[0019] Figure 1 This is a schematic diagram of the structure of a petroleum coke blending and uniform stirring system according to the present invention. Detailed Implementation

[0020] 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.

[0021] Please see Figure 1 The specific implementation of a petroleum coke blending and uniform stirring system is as follows, including: The parameter setting module generates blending parameters using the blending ratio calculation unit, sets operating procedures through the rule configuration unit, and outputs setting data through the environmental factors unit. The process control module receives set data, collects real-time data through the sensor data acquisition unit, executes stirring actions using the stirring control unit, and outputs process data through the uniformity detection unit. The uniformity assessment module receives process data, constructs an assessment matrix through the data acquisition unit, outputs the assessment results through the assessment calculation unit, and provides adjustment feedback through the feedback unit. The optimization decision module receives the evaluation results, generates decision instructions by calling the database through the feature extraction unit and the matching unit, and feeds them back to the parameter setting module through the inference unit to adjust the parameters. The adaptive optimization module receives the evaluation results output by the uniformity evaluation module, analyzes the system performance through the performance profile building unit, identifies problem points through the weakness analysis unit, and generates optimization instructions through the parameter control unit. The report generation module integrates the evaluation results with system data and generates a uniformity report through the indicator fusion unit and weight calculation unit.

[0022] The process of generating blending parameters using the blending ratio calculation unit in the parameter setting module specifically includes: Set key operating parameters for petroleum coke blending, including raw material ratio, stirring speed, and time threshold; The blending ratio calculation unit calculates the optimal blending ratio based on the carbon content and volatile matter content of the raw materials. The calculation formula is as follows: ; in, To optimize the blending ratio, For standard blending ratio, and These are the correction factors for carbon content and volatile matter content, respectively. and These represent the actual carbon content and volatile matter content of the current batch of raw materials, respectively. and These are the target carbon content and volatile matter content, respectively. The specific operation includes: using a near-infrared spectrometer and an industrial analyzer to detect the actual carbon content of the current batch of petroleum coke raw materials in real time. and volatile matter content Retrieve the target carbon content from the pre-stored raw material standard database. and target volatile content Correction factor and The regression analysis, conducted using historical production data and employing a multiple linear regression method, used data from the past 100 production batches as the training set. The least squares method was used to fit the coefficients, ensuring the minimum sum of squared residuals. The model was updated quarterly and stored in the system parameter library. To enable real-time adjustment of the raw material ratio fed into the mixer; Calculate the degree of deviation of the current blending parameters from the standard operating condition range. If the deviation is greater than zero, trigger the parameter adjustment mechanism. Based on historical blending data and environmental factors, optimization parameters are dynamically generated through the proportion calculation unit and output to the process control module; The process of setting operation specifications through the rule configuration unit in the parameter setting module specifically includes: Based on preset production process standards, equipment operation manuals and safety production procedures, a complete knowledge base of blending and mixing operation rules is constructed and stored. Through the rule configuration unit, the operation specifications that match the current production task are called from the knowledge base. The specifications specifically include the allowable fluctuation range of the raw material blending ratio, the safe operating range of the stirring equipment speed, the time threshold of each process stage, and the corresponding parameter standards for products of different quality grades. The invoked operation specifications are converted into logical instructions and parameter constraints that the system can recognize and execute, and loaded into the process control module as the benchmark and boundary conditions for its execution of stirring actions; The process of outputting setting data through the environmental factors unit in the parameter setting module specifically includes: Temperature and humidity sensors deployed at the raw material silo, conveyor belt and mixer inlet are used to collect ambient temperature and raw material apparent humidity data in real time. The environmental factors unit receives real-time environmental data and calculates environmental correction factors based on the pre-established working condition influence model. The model quantifies the actual impact of changes in environmental temperature and humidity on the flowability, adhesion, and target blending ratio of raw materials. The calculated environmental correction factor is fused and verified with the optimized blending parameters generated by the blending ratio calculation unit and the operating specifications set by the rule configuration unit to generate the final executable setting data package, which is then output to the process control module.

[0023] The process of calculating the degree of deviation specifically includes: The real-time blending parameter values ​​are obtained and compared with the preset standard range to obtain the deviation. The formula for calculating the deviation D is: ; in, For the comprehensive deviation, The number of blending parameters, For the actual value of the j-th parameter, Let j be the standard value of the j-th parameter. Let be the weight factor of the j-th parameter; Its specific operations include: real-time data collection by the system. Actual value of each blending parameter This includes, but is not limited to, the flow rate of the main raw material, the rate of addition of auxiliary materials, and the current of the mixer. Compared with the preset standard value Comparison of the weighting factors of each parameter Based on the importance of this parameter to the final product quality, the comprehensive deviation was calculated using the analytic hierarchy process (AHP) with pre-defined parameters. With the set tolerance threshold Compare; When the deviation exceeds the tolerance threshold, the adjustment unit of the parameter setting module is activated to recalculate the blending ratio. By integrating external conditions, including temperature and humidity, through the environmental factors unit, the parameter settings are ensured to meet the actual working conditions.

[0024] The process control module receives set data, acquires real-time data through the sensor data acquisition unit, executes stirring actions using the stirring control unit, and outputs process data through the uniformity detection unit. Specifically, this process includes: Initialize the operating parameters of the mixing equipment based on the setting data output by the parameter setting module; The mixing state of petroleum coke, including viscosity, density, and distribution uniformity, is monitored in real time through a sensor data acquisition unit. The stirring control unit is used to adjust the speed and direction of the stirrer to ensure that the blended materials are mixed evenly; The homogeneity detection unit performs real-time analysis on the mixed sample and calculates the homogeneity index using the following formula: ; in, The coefficient of variation is 1. The standard deviation of the sample parameter, The mean of the sample parameters is used to output process data to the uniformity evaluation module.

[0025] The analysis process of the uniformity detection unit specifically includes: Collect multi-point sample data during the stirring process and construct a time series curve; Calculate the standard deviation and coefficient of variation of the sample parameters, assess the level of homogeneity, and determine the level of homogeneity. Compare the target value using the following formula:

[0026] in, It is an index of uniformity level. The preset target coefficient of variation threshold; The specific operation includes: installing an online particle size analyzer and sampling device at the mixer outlet, collecting samples periodically, and measuring key indicators including particle size distribution and the standard deviation of true density. and mean Calculate the coefficient of variation ,Will Compared with the ideal coefficient of variation predetermined according to product quality standards To make a comparison, The closer the value is to 1, the better the uniformity. When the uniformity level index If the value falls below the set threshold, a feedback mechanism is triggered, notifying the process control module to adjust the stirring parameters.

[0027] The uniformity assessment module receives process data, constructs an assessment matrix through a data acquisition unit, outputs assessment results through an assessment calculation unit, and provides adjustment feedback through a feedback unit. The specific process includes: Key indicators in the integration process data include mixing uniformity and blending consistency; The indicators are organized into a multi-dimensional matrix through the data collection unit, with each dimension representing an evaluation factor. The evaluation calculation unit uses a weighted algorithm to process matrix data and calculates the overall score using the following formula: ; in, Based on the overall score, Let be the weight coefficient of the i-th indicator. Let i be the standardized value of the i-th indicator. The total number of indicators; The feedback unit provides real-time adjustment suggestions to the optimization decision-making module based on the priority of the results.

[0028] The weighted algorithm process for evaluating computational units specifically includes: Each evaluation factor is assigned a weight coefficient, which is dynamically adjusted based on historical data and the learning model. The iterative update formula is: ; in, and These are the weight coefficients for the k-th and (k+1)-th iterations, respectively. For learning rate, To assess error Weights The partial derivatives; Its specific operation includes: the system records the overall score for each evaluation. Product quality score compared with actual testing Error between Gradient descent is used for weight optimization, and the learning rate is... The initial value is set to 0.01, and the value is dynamically adjusted according to the convergence of the loss function, including halving it when the rate of change of the loss function is lower than 0.001. The maximum number of iterations is 1000 to ensure stability. This process is performed automatically after each production batch to achieve adaptive optimization of the evaluation model. Calculate a comprehensive score, and if the score is lower than the safety threshold, it is marked as requiring emergency intervention; The feedback unit maps the scores into specific operation instructions to ensure timely system response.

[0029] The process of receiving evaluation results in the optimization decision-making module, generating decision instructions by calling the database through the feature extraction and matching units, and then feeding them back to the parameter setting module via the inference unit to adjust the parameters specifically includes: Receive the evaluation results from the uniformity evaluation module and extract key features including uniformity trends and deviation patterns; By matching the feature extraction unit with a historical database, similar cases are identified, and the similarity of the matches is determined. Calculated using the following cosine similarity formula: ; in, and These are the current feature vector and the historical case feature vector, respectively. and For the first in the vector 1 eigenvalue, For feature dimensions; The specific operations include: identifying the key characteristics of the current production batch, including the overall deviation. Uniformity level The main deviation parameter types are constructed into 3D feature vector The similar features of each case in the historical case library are constructed into vectors. ,calculate With each cosine similarity The top K most similar historical cases are selected as decision-making references; The matching unit calculates the similarity, selects the optimal decision scheme, and feeds back the simulation effect to the parameter setting module after the deduction unit. The simulation unit takes into account production plans and resource constraints to ensure the feasibility of decisions.

[0030] The simulation process of the deduction unit specifically includes: Based on the current system status and decision-making scheme, a virtual blending scenario is constructed; The simulation is run to predict the uniformity change after parameter adjustment. The prediction model for the uniformity change trend ΔU is as follows: ; in, The predicted change in the uniformity index. For constant terms, For the h-th adjustment parameter The regression coefficients, To adjust the number of parameters; Its specific operations include: the predictive model is developed by adjusting a large amount of historical data, and the adjustment amount... and the resulting uniformity change The dataset was trained using multiple linear regression, containing 500 historical samples. Five-fold cross-validation was used to prevent overfitting. The regression coefficients were calculated using the normal equation method and fine-tuned periodically with new data. Adjustment parameters This may include adjustments to stirring speed, blending ratio, and mixing time, as well as regression coefficients. , ,..., This is determined and solidified in the system during the model training phase to achieve rapid prediction; If the prediction result is better than the threshold, the decision instruction is confirmed; otherwise, the database is re-matched to generate a new solution.

[0031] The adaptive optimization module receives the evaluation results output by the uniformity evaluation module, analyzes the system performance through the performance profiling unit, identifies problem points through the weakness analysis unit, and generates optimization instructions through the parameter control unit. The specific process includes: By analyzing historical operational data through performance profiling building units, a system health status profile is generated. The weakness analysis unit identifies common problems in the blending and mixing process, including equipment wear and raw material variations; The parameter control unit dynamically adjusts and optimizes instructions based on the profile and problem points, enabling the system to learn and optimize itself. Optimize instructions and integrate them into the report generation module to enable long-term performance tracking; The process of integrating evaluation results and system data in the report generation module, and generating a uniformity report through the indicator fusion unit and weight calculation unit, specifically includes: The indicator fusion unit first receives the evaluation results from the uniformity evaluation module. The evaluation results include quantitative indicators such as mixing uniformity and blending consistency. At the same time, the unit also collects real-time data during system operation, including equipment operation status logs, environmental sensor readings, production batch information and other system data. Through data preprocessing steps, the multi-source heterogeneous data is cleaned, denoised and normalized. The evaluation results and system data are converted into a unified standardized indicator set to ensure that the data format is consistent and comparable. The weight calculation unit dynamically assigns weight coefficients to each indicator based on a preset weight allocation strategy. The weight allocation strategy can be dynamically adjusted based on the importance analysis of indicators in historical data, expert experience rules, and machine learning models. Key indicators, including the evenness level index, are given higher weights, while auxiliary indicators, including ambient temperature, have relatively lower weights. The weight calculation process also considers the correlation between indicators to avoid duplicate calculations and ensures that the total weight is 1 through normalization. Finally, the report generation module uses a weighted fusion algorithm to linearly weight and sum the standardized indicators with their corresponding weights to calculate the comprehensive uniformity score. Based on the score, a structured uniformity report is automatically generated, which includes a text summary, data tables, trend charts, and improvement suggestions. It also supports exporting to common formats such as PDF and Excel, facilitating decision analysis and long-term archiving for users. The entire process achieves seamless integration of evaluation results and system data, enhancing the credibility and usability of the report.

[0032] The operating steps of a petroleum coke blending and uniform mixing system are as follows: Step 1: Intelligent setting and dynamic adjustment of operating parameters: During the system initialization phase, the parameter setting module begins operation. The blending ratio calculation unit first determines the basic parameters for petroleum coke blending based on the operating specifications set by the preset rule configuration unit, including the raw material ratio, stirring speed, and time threshold. The environmental factors unit simultaneously collects external condition data such as on-site temperature and humidity. The core operation is that this module calculates the deviation of the current blending parameters from the standard operating condition range in real time. When a deviation is detected, the parameter adjustment mechanism is immediately triggered. The blending ratio calculation unit dynamically generates optimized blending parameters based on historical blending data and real-time environmental factors, forming the set data and outputting it to the process control module to provide initial settings for the entire stirring process.

[0033] Step 2: Multi-parameter coordinated control and real-time monitoring of the stirring process: After receiving the set data, the process control module starts the mixing process. The sensor data acquisition unit begins to continuously monitor the mixing state of the materials in the mixer. Key parameters include viscosity, density, and distribution uniformity. Based on this real-time data, the mixing control unit dynamically adjusts the speed and direction of the mixer to ensure that the blended materials achieve initial mixing. The uniformity detection unit performs online analysis on the mixed sample, calculates uniformity indicators such as the coefficient of variation, quantitatively evaluates the mixing effect, and outputs the real-time process data to the uniformity evaluation module to achieve closed-loop control of the entire mixing process.

[0034] Step 3: Multi-dimensional quantitative assessment and status feedback of uniformity: The uniformity assessment module performs in-depth processing on the received process data. Its data acquisition unit integrates key indicators such as mixing uniformity and blending consistency to construct a multi-dimensional assessment matrix. The assessment calculation unit uses a weighted algorithm to process the matrix and calculate a comprehensive score, thereby quantitatively assessing the uniformity of the current stirring state. The feedback unit generates specific adjustment suggestions based on the priority of the assessment results and sends the assessment results and adjustment feedback to the optimization decision module simultaneously to provide data support for decision-making.

[0035] Step 4: Optimization decision generation based on historical case matching: After receiving the evaluation results, the optimization decision-making module begins operation. The feature extraction unit first extracts key features from the evaluation results, including the uniformity trend and the main deviation patterns. Then, the matching unit performs similarity calculation and matching on these features with cases in the historical database, identifying the most similar historical cases. Based on the matching results, the inference unit simulates the implementation effects of different decision-making schemes, comprehensively considers the current production plan and resource constraints, generates the optimal decision instruction, and feeds the instruction back to the parameter setting module to initiate parameter adjustment.

[0036] Step 5: System performance self-learning and parameter adaptive optimization: The adaptive optimization module is responsible for the continuous improvement of the system. The performance profile building unit generates a health status profile of the system by analyzing long-term historical operating data. The weakness analysis unit then identifies common problems and performance bottlenecks in the blending and mixing process based on this profile. The parameter control unit dynamically adjusts the system's optimization instructions according to the identified problems, realizing the self-correction of parameters and the self-learning optimization of strategies, so that the system can continuously adapt to new working conditions and raw material characteristics.

[0037] Step Six: Comprehensive Data Fusion and Visualization Report Generation: The report generation module, as the system output terminal, integrates the evaluation results from the uniformity assessment module and the system's own operating data. The index fusion unit fuses the multi-source data, and the weight calculation unit assigns appropriate weights to different indicators. Finally, the module generates a comprehensive and visualized uniformity report, clearly showing the overall performance of the blending and mixing process, the achievement of key indicators, and historical trends, providing an intuitive basis for production management and decision-making.

[0038] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0039] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A petroleum coke blending and uniform mixing system, characterized in that, include: The parameter setting module generates blending parameters using the blending ratio calculation unit, sets operating procedures through the rule configuration unit, and outputs setting data through the environmental factors unit. The process control module receives the set data, collects real-time data through the sensor data acquisition unit, executes the stirring action using the stirring control unit, and outputs process data through the uniformity detection unit. The uniformity evaluation module receives the process data, constructs an evaluation matrix through the data acquisition unit, outputs the evaluation results through the evaluation calculation unit, and provides adjustment feedback through the feedback unit. The optimization decision module receives the evaluation results, generates decision instructions by calling the database through the feature extraction unit and the matching unit, and feeds them back to the parameter setting module through the inference unit to adjust the parameters. The adaptive optimization module receives the evaluation results output by the uniformity evaluation module, analyzes the system performance through the performance profile construction unit, identifies problem points through the weakness analysis unit, and generates optimization instructions through the parameter control unit. The report generation module integrates the evaluation results with system data and generates a uniformity report through the indicator fusion unit and weight calculation unit.

2. The petroleum coke blending and uniform stirring system according to claim 1, characterized in that, The process of generating blending parameters using the blending ratio calculation unit in the parameter setting module specifically includes: Set key operating parameters for petroleum coke blending, including raw material ratio, stirring speed, and time threshold; Calculate the degree of deviation of the current blending parameters from the standard operating condition range. If the deviation is greater than zero, trigger the parameter adjustment mechanism. Based on historical blending data and environmental factors, optimization parameters are dynamically generated through the proportion calculation unit and output to the process control module.

3. The petroleum coke blending and uniform stirring system according to claim 2, characterized in that, The process of calculating the degree of deviation specifically includes: The real-time blending parameter values ​​are obtained and compared with the preset standard range to determine the deviation. When the deviation exceeds the tolerance threshold, the adjustment unit of the parameter setting module is activated to recalculate the blending ratio. By integrating external conditions, including temperature and humidity, through the environmental factors unit, the parameter settings are ensured to meet the actual working conditions.

4. The petroleum coke blending and uniform stirring system according to claim 1, characterized in that, The process control module receives the set data, acquires real-time data through the sensor data acquisition unit, executes the stirring action using the stirring control unit, and outputs process data through the uniformity detection unit. Specifically, this process includes: Initialize the operating parameters of the mixing equipment based on the setting data output by the parameter setting module; The mixing state of petroleum coke, including viscosity, density, and distribution uniformity, is monitored in real time through a sensor data acquisition unit. The stirring control unit is used to adjust the speed and direction of the stirrer to ensure that the blended materials are mixed evenly; The homogeneity detection unit performs real-time analysis on the mixed sample and calculates the homogeneity index using the following formula: ； in, The coefficient of variation is 1. The standard deviation of the sample parameter, The mean of the sample parameters is used to output process data to the uniformity evaluation module.

5. The petroleum coke blending and uniform stirring system according to claim 4, characterized in that, The analysis process of the uniformity detection unit specifically includes: Collect multi-point sample data during the stirring process and construct a time series curve; Calculate the standard deviation and coefficient of variation of the sample parameters to assess the level of homogeneity; When the uniformity is below the set threshold, a feedback mechanism is triggered to notify the process control module to adjust the stirring parameters.

6. The petroleum coke blending and uniform stirring system according to claim 1, characterized in that, The process of receiving process data in the uniformity evaluation module, constructing an evaluation matrix through a data acquisition unit, outputting evaluation results through an evaluation calculation unit, and providing adjustment feedback through a feedback unit specifically includes: Key indicators in the integration process data include mixing uniformity and blending consistency; The indicators are organized into a multi-dimensional matrix through the data collection unit, with each dimension representing an evaluation factor. The evaluation calculation unit uses a weighted algorithm to process matrix data and calculates the overall score using the following formula: ； in, Based on the overall score, Let be the weight coefficient of the i-th indicator. Let i be the standardized value of the i-th indicator. The total number of indicators; The feedback unit provides real-time adjustment suggestions to the optimization decision-making module based on the priority of the results.

7. The petroleum coke blending and uniform stirring system according to claim 6, characterized in that, The weighted algorithm process of the evaluation calculation unit specifically includes: Each evaluation factor is assigned a weight coefficient, which is dynamically adjusted based on historical data and the learning model. Calculate a comprehensive score, and if the score is lower than the safety threshold, it is marked as requiring emergency intervention; The feedback unit maps the scores into specific operation instructions to ensure timely system response.

8. The petroleum coke blending and uniform stirring system according to claim 1, characterized in that, The process by which the optimization decision module receives the evaluation results, generates decision instructions by calling the database through the feature extraction unit and the matching unit, and then feeds them back to the parameter setting module through the inference unit to adjust the parameters specifically includes: Receive the evaluation results from the uniformity evaluation module and extract key features such as uniformity trends and deviation patterns; Similar cases are identified by matching the feature extraction unit with the historical database; The matching unit calculates the similarity, selects the optimal decision scheme, and feeds back the simulation effect to the parameter setting module after the deduction unit. The simulation unit takes into account production plans and resource constraints to ensure the feasibility of decisions.

9. A petroleum coke blending and uniform stirring system according to claim 8, characterized in that, The simulation process of the inference unit specifically includes: Based on the current system status and decision-making scheme, a virtual blending scenario is constructed; Run simulations to predict uniformity changes after parameter adjustments; If the prediction result is better than the threshold, the decision instruction is confirmed; otherwise, the database is re-matched to generate a new solution.

10. A petroleum coke blending and uniform stirring system according to claim 1, characterized in that, The adaptive optimization module receives the evaluation results output by the uniformity evaluation module, analyzes the system performance through the performance profiling unit, identifies problem points through the weakness analysis unit, and generates optimization instructions through the parameter control unit. The specific process includes: By analyzing historical operational data through performance profiling building units, a system health status profile is generated. The weakness analysis unit identifies common problems in the blending and mixing process, including equipment wear and raw material variations; The parameter control unit dynamically adjusts and optimizes instructions based on the profile and problem points, enabling the system to learn and optimize itself. The optimized instructions are integrated into the report generation module to enable long-term performance tracking.

Images