MABR film processing production line supervision control system based on Internet of Things

Abstract

The invention belongs to the technical field of production line control, and particularly relates to an Internet of Things-based MABR film processing production line supervision control system, which comprises a multi-dimensional Internet of Things sensing module, a parameter real-time detection output module, an automatic compensation control module, a production stability decision module and a production line supervision center, a parameter real-time detection output module is used for rapidly identifying parameters needing to be compensated, an automatic compensation control module is used for automatically repairing the parameters needing to be compensated, continuous and stable operation of a production line is guaranteed, and a production stability decision-making module is used for comprehensively analyzing the control stability of the production line based on multi-dimensional indexes. Quantitative evaluation analysis is carried out on the finished product quality when the stability qualification signal is generated, whether the raw material quality is related to the finished product quality abnormity or not is accurately judged when the quality control abnormity signal is generated, quality problem repetition is timely blocked from the raw material source, the operation stability and the automation level of an MABR film processing production line are remarkably improved, and the finished product quality of the MABR film is guaranteed.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of production line control, and in particular to an MABR membrane processing production line supervision control system based on Internet of Things. BACKGROUND

[0002] MABR (membrane aeration biological reactor) membrane is the core carrier of membrane aeration biological treatment technology, and the processing quality directly determines the biological membrane adhesion performance, oxygen mass transfer efficiency and service life. Precise supervision and dynamic control of the running state of the MABR membrane processing production line are the key to guaranteeing the quality of the MABR membrane product.

[0003] Current technical research in the field of MABR membrane manufacturing focuses on material formula optimization and preparation process improvement, but there is generally a lack of a whole-process closed-loop supervision system for the processing production line, resulting in insufficient production stability and quality controllability.

[0004] For example, the Chinese patent with the publication number CN120094412A discloses a MABR hollow fiber composite membrane and a preparation method and application thereof. The application technology optimizes the mechanical strength and aging resistance of the membrane by adding reinforcing agents and modifiers, and clearly defines the preparation steps such as raw material kneading and slurry coating. However, it only focuses on the static setting of material formula and molding process parameters, and does not involve real-time monitoring and self-adaptive adjustment of parameter fluctuations during production line operation. When parameter abnormalities occur, it cannot respond and correct in a timely manner, which easily leads to membrane structure defects and performance fluctuations.

[0005] Furthermore, the above-mentioned technical solutions of the application are difficult to realize abnormal capture and self-adaptive adjustment and repair of related parameters during the running of the MABR membrane processing production line, and are also difficult to perform progressive and reasonable analysis on the running stability of the MABR membrane processing production line, product quality control performance and raw material factor correlation and accurately output early warning. Therefore, a solution is proposed. SUMMARY

[0006] The purpose of the present application is to provide an MABR membrane processing production line supervision control system based on Internet of Things to solve the technical defects proposed in the background art.

[0007] To achieve the above-mentioned purpose, the present application provides the following technical solution: an MABR membrane processing production line supervision control system based on Internet of Things, comprising a multi-dimensional Internet of Things sensing module, a parameter real-time detection output module, an automatic compensation control module, a production stability decision module and a production line supervision center.

[0008] The multi-dimensional Internet of Things sensing module acquires real-time values of multi-dimensional parameters of the MABR membrane processing production line in real time through deployment of Internet of Things sensing terminals and sends them to the parameter real-time detection output module.

[0009] The parameter real-time detection output module marks a parameter as a compensation-required parameter if a deviation value of a real-time value of the parameter compared to a corresponding standard value exceeds a corresponding deviation threshold value, and sends the compensation-required parameter to the automatic compensation control module;

[0010] The automatic compensation control module adjusts the MABR membrane processing after receiving the compensation-required parameter to restore the compensation-required parameter to a normal state.

[0011] The production stability decision module analyzes the production automation control stability performance of the MABR membrane processing production line, generates a stability qualified signal or a stability abnormal signal through analysis, and sends the stability qualified signal or the stability abnormal signal to the production line supervision center.

[0012] Further, the specific analysis process of the production stability decision module includes:

[0013] The number of times that the corresponding parameter is marked as a compensation-required parameter in a detection period is obtained and defined as a compensation warning value, the average of all compensation recovery time lengths for the corresponding parameter in the detection period is calculated to obtain a compensation recovery time value, and the number of times that the corresponding parameter is marked as a compensation-required parameter and fails to recover to a normal state within a corresponding specified time length is marked as a compensation recovery abnormal frequency value.

[0014] The parameter control feature value is calculated by weighted summation of the compensation warning value, the compensation recovery time value, and the compensation recovery abnormal frequency value, the parameter control feature value is compared with a preset parameter control feature threshold value, if the parameter control feature value exceeds the corresponding preset parameter control feature threshold value, the corresponding parameter is defined as a blacklist parameter, and if there is a blacklist parameter in the detection period, a stability abnormal signal is generated.

[0015] Further, if there is no blacklist parameter in the detection period, the deviation value of the real-time value of the corresponding parameter compared to the corresponding standard value is obtained, a set of preset weight values corresponding to each parameter is set in advance, the corresponding deviation value is multiplied by the corresponding preset weight value to obtain a parameter condition feature value, and the sum of the parameter condition feature values of all parameters is calculated to obtain a production line real-time value.

[0016] The production line control feature value is calculated by averaging all production line real-time values in the detection period, the number of times that the production line time value exceeds the preset production line time threshold value is marked as a production line control abnormal frequency value, the production line control abnormal frequency value and the production line control feature value are compared with the preset production line control abnormal frequency threshold value and the preset production line control feature threshold value, respectively, if the production line control abnormal frequency value or the production line control feature value exceeds the corresponding preset threshold value, a stability abnormal signal is generated, and if the production line control abnormal frequency value and the production line control feature value do not exceed the corresponding preset threshold value, a stability qualified signal is generated.

[0017] Further, the production stability decision module is communicatively connected to the quality multi-index quantitative evaluation module, the production stability decision module sends a stability qualified signal to the quality multi-index quantitative evaluation module, the quality multi-index quantitative evaluation module analyzes the finished product quality control performance of the MABR membrane processing production line when receiving the stability qualified signal, generates a quality control qualified signal or a quality control abnormal signal through analysis, and sends the quality control qualified signal or the quality control abnormal signal to the production line supervision center.

[0018] Further, the specific analysis process of the quality multi-index quantitative evaluation module is as follows:

[0019] The membrane quality coefficient is obtained through the membrane quality comprehensive evaluation analysis, the membrane quality control table coefficient is obtained by performing mean value calculation on the membrane quality coefficients in the detection period, and the membrane quality abnormal occupancy coefficient is obtained by performing ratio calculation on the number of times that the membrane quality coefficient does not exceed the preset membrane quality coefficient threshold and the total number of detections in the detection period. If the membrane quality control table coefficient does not exceed the preset membrane quality control table coefficient threshold or the membrane quality abnormal occupancy coefficient exceeds the preset membrane quality abnormal occupancy coefficient threshold, a quality control abnormal signal is generated; otherwise, a quality control qualified signal is generated.

[0020] Further, the specific analysis process of the membrane quality comprehensive evaluation analysis is as follows:

[0021] The actual average pore diameter, actual porosity, and actual breaking strength of the finished MABR membrane are collected by the aperture analyzer and the tensile testing machine, the thickness of the finished MABR membrane at several positions is collected by the laser thickness gauge, the average value of the thicknesses of all positions is compared with the deviation value of the standard thickness to mark the membrane thickness deviation coefficient, and the thicknesses of all positions are subjected to variance calculation to obtain the membrane thickness uniformity coefficient. The membrane quality coefficient is calculated through the multi-index quantitative evaluation formula.

[0022] Further, the quality multi-index quantitative evaluation module is communicatively connected to the raw material dynamic supervision analysis module, the quality multi-index quantitative evaluation module sends a quality control abnormal signal to the raw material dynamic supervision analysis module, the raw material dynamic supervision analysis module analyzes the raw material preparation condition of the MABR membrane processing production line when receiving the quality control abnormal signal, judges whether to generate a raw material high correlation signal through analysis, and sends the raw material high correlation signal to the production line supervision center when the raw material high correlation signal is generated.

[0023] Further, the specific analysis process of the raw material dynamic supervision analysis module is as follows:

[0024] The raw material state coefficient is obtained through real-time detection and analysis of the raw material state. The raw material state coefficient is compared with a preset raw material state coefficient threshold. If the raw material state coefficient exceeds the preset raw material state coefficient threshold, the corresponding raw material state coefficient is marked as a high-impact coefficient. The number of high-impact coefficients of raw materials during the detection period is obtained and the ratio is calculated with the total number of raw material state coefficients to obtain the high-impact detection value of raw materials. The high-impact detection value of raw materials is compared with a preset high-impact detection threshold. If the high-impact detection value of raw materials exceeds the preset high-impact detection threshold, a high-correlation signal of raw materials is generated.

[0025] Furthermore, if the high impact detection value of the raw material does not exceed the preset high impact detection threshold, the average value of the state coefficients of all raw materials during the detection period is calculated to obtain the raw material state performance value, and the raw material state coefficient with the largest value during the detection period is marked as the raw material state performance value.

[0026] The raw material dynamic monitoring coefficient is calculated by weighting and summing the raw material high-impact detection value, raw material state performance value, and raw material state amplitude value. The raw material dynamic monitoring coefficient is then compared with a preset raw material dynamic monitoring coefficient threshold. If the raw material dynamic monitoring coefficient exceeds the preset raw material dynamic monitoring coefficient threshold, a raw material high correlation signal is generated.

[0027] Furthermore, the specific analysis process for real-time monitoring and analysis of raw material status is as follows:

[0028] The actual concentrations of each component in the raw material are collected, and a viscometer and a laser particle size analyzer are installed at the outlet of the mixing tank to collect the overall actual viscosity and overall actual particle size of the raw material. The raw material state coefficient is calculated using the real-time state analysis formula of the raw material.

[0029] Compared with the prior art, the beneficial effects of the present invention are:

[0030] 1. In this invention, by comprehensively capturing the key parameters of the MABR membrane processing production line and quickly identifying the parameters that need compensation, the accumulation of abnormalities can be avoided from affecting the operation of the production line or the quality of the products. The automated compensation control module realizes the automatic repair of the parameters that need compensation, which significantly improves the intelligence and automation level of the production line, ensures the continuous and stable operation of the production line, and comprehensively analyzes the stability of the production line control based on multi-dimensional indicators. It can accurately identify potential operational problems and trigger early warnings in a timely manner, which is conducive to ensuring the reliability of the production line operation.

[0031] 2. In this invention, by quantitatively evaluating and analyzing the quality of the finished product when a stability qualified signal is generated, production line supervision is strengthened in a timely manner and the cause is investigated. Furthermore, when a quality control abnormal signal is generated, it is possible to accurately determine whether the quality of raw materials is related to the abnormal quality of the finished product. This fills the gap in the traditional correlation analysis between abnormal quality of finished products and raw materials, effectively reduces the control difficulty of the MABR membrane processing production line, significantly improves the stability and automation level of the production line operation, and helps to ensure the quality of the MABR membrane finished product. Attached Figure Description

[0032] To facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings;

[0033] Figure 1 This is a system block diagram of Embodiment 1 of the present invention;

[0034] Figure 2 This is a system block diagram of Embodiments 2 and 3 of the present invention. Detailed Implementation

[0035] 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.

[0036] Example 1: As Figure 1 As shown, the IoT-based MABR membrane processing production line monitoring and control system proposed in this invention includes a multi-dimensional IoT sensing module, a real-time parameter detection and output module, an automated compensation control module, a production stability decision module, and a production line monitoring center.

[0037] The multi-dimensional IoT sensing module, by deploying IoT sensing terminals (i.e., several types of sensors), collects real-time values ​​of multi-dimensional parameters (such as curing temperature and curing humidity in the curing process) of the MABR membrane processing production line. It then sends the real-time values ​​of each parameter to the parameter real-time detection and output module via the Internet of Things. This enables the comprehensive capture of key parameter information during the operation of the MABR membrane processing production line, breaking the limitations of traditional single parameter acquisition and laying a solid data foundation for effective supervision of the production line.

[0038] The real-time parameter detection and output module compares the deviation of the real-time value from the corresponding standard value with the corresponding preset deviation threshold. It also marks parameters whose deviation exceeds the corresponding deviation threshold as parameters that need compensation and sends these parameters to the automated compensation control module, the production stability decision module, and the production line monitoring center. This allows for the rapid identification of parameters that need compensation during the operation of the MABR membrane processing production line, preventing abnormal parameters from accumulating due to undetected issues, which could affect the continuous operation of the production line or lead to product quality problems. This improves the timeliness of the MABR membrane processing production line's response to parameter anomalies and the targeted nature of subsequent processing.

[0039] After receiving the parameters requiring compensation, the automated compensation control module adjusts the MABR membrane processing accordingly to restore the parameters to normal. It also sends the compensation control information to the production stability decision module and the production line monitoring center, enabling automated repair of abnormal production line parameters. This significantly reduces reliance on manual intervention, greatly improves the intelligence and automation level of the MABR membrane processing production line, and effectively reduces the operational difficulty and errors of manual control. In addition, rapid automated compensation can shorten the duration of parameter anomalies, reduce production line downtime, production interruptions, or the production of unqualified products caused by parameter anomalies, ensure the continuous and stable operation of the production line, and indirectly improve production efficiency and product qualification rate.

[0040] The production stability decision module analyzes the stability performance of the automated control system in the MABR membrane processing production line. This analysis generates either a stability pass / fail signal or a stability anomaly signal, which is then sent to the production line monitoring center. Upon receiving an anomaly signal, the monitoring center issues a corresponding warning. This system scientifically assesses production line stability from two dimensions: parameter compensation effectiveness and overall production line operating status. It effectively identifies potential operational control risks and prompts monitoring personnel to quickly investigate the causes and take appropriate corrective measures. This avoids production line failures or product quality fluctuations caused by stability issues, ensuring the stability and reliability of production line operation. This provides a fundamental guarantee for the quality of finished MABR membranes and further reduces the difficulty of operating and managing the MABR membrane processing production line. The specific analysis process is as follows:

[0041] The number of times a corresponding parameter is marked as a parameter requiring compensation during the detection period is obtained and defined as a compensation warning value. The average of all compensation recovery times for the corresponding parameter during the detection period is calculated to obtain the compensation recovery status value. The number of times a corresponding parameter is marked as a parameter requiring compensation during the detection period but fails to return to its normal state within the corresponding specified time is marked as a compensation recovery frequency value.

[0042] The parameter control characteristic value is obtained by weighted summation of the compensation warning value, compensation recovery time status value, and compensation recovery frequency value. Specifically, the compensation warning value, compensation recovery time status value, and compensation recovery frequency value are each assigned a corresponding preset weight coefficient, and the compensation warning value, compensation recovery time status value, and compensation recovery frequency value are each multiplied by the corresponding preset weight coefficient. The sum of the three sets of product results is marked as the parameter control characteristic value.

[0043] It should be noted that the larger the value of the parameter control characteristic, the worse the overall control performance of the corresponding parameter during the detection period. The parameter control characteristic value is compared with the preset parameter control characteristic threshold. If the parameter control characteristic value exceeds the corresponding preset parameter control characteristic threshold, it indicates that the overall control performance of the corresponding parameter during the detection period is poor, and the corresponding parameter is defined as a blacklist parameter. If a blacklist parameter exists during the detection period, it indicates that there is a hidden danger in the operation control during the detection period, which is not conducive to ensuring the stable operation of the MABR membrane processing production line, and a stability abnormality signal is generated.

[0044] Furthermore, if there are no blacklist parameters during the detection period, the deviation value of the real-time value of the corresponding parameter compared with the corresponding standard value is obtained. Each parameter is pre-set to correspond to a set of preset weight values. The corresponding deviation value is multiplied by the corresponding preset weight value to obtain the parameter characteristic value. The parameter characteristic values ​​of all parameters are summed to obtain the production line real-time value.

[0045] All production line real-time values ​​within the detection period are obtained and their average values ​​are calculated to obtain the production line control characteristic value. The number of times the production line real-time value exceeds the preset production line real-time threshold is marked as the production line control frequency value. The production line control frequency value and the production line control characteristic value are compared with the preset production line control frequency threshold and the preset production line control characteristic threshold, respectively.

[0046] If the abnormal frequency value or characteristic value of the production line control exceeds the corresponding preset threshold, it indicates that the operation stability and control reliability of the MABR membrane processing production line are poor during the detection period, and a stability abnormality signal is generated; if neither the abnormal frequency value nor the characteristic value of the production line control exceeds the corresponding preset threshold, it indicates that the operation stability and control reliability of the MABR membrane processing production line are good during the detection period, and a stability qualified signal is generated.

[0047] Example 2: Figure 2 As shown, the difference between this embodiment and Embodiment 1 is that the production stability decision module is connected to the quality multi-index quantitative evaluation module. The production stability decision module sends the stability qualified signal to the quality multi-index quantitative evaluation module. When the quality multi-index quantitative evaluation module receives the stability qualified signal, it analyzes the finished product quality control performance of the MABR membrane processing production line and generates a quality control qualified signal or a quality control abnormal signal through analysis.

[0048] Furthermore, the system sends either a quality control pass signal or a quality control anomaly signal to the production line monitoring center. Upon receiving a quality control anomaly signal, the production line monitoring center issues a corresponding warning. This breaks through the limitations of traditional single-indicator quality assessment, enabling multi-dimensional quantitative assessment of MABR membrane finished product quality. It improves the comprehensiveness and accuracy of quality assessment, allowing for timely strengthening of production line monitoring and root cause investigation, thus ensuring the quality of the produced MABR membrane finished products. The specific analysis process of the multi-indicator quantitative quality assessment module is as follows:

[0049] The actual average pore size, actual porosity, and actual tensile strength of the finished MABR membrane were collected using a pore size analyzer and a tensile testing machine. The thickness of the finished MABR membrane at several locations was collected using a laser thickness gauge. The deviation of the average thickness at all locations from the standard thickness was marked as the membrane thickness deviation coefficient. The variance of the thickness at all locations was calculated to obtain the membrane thickness uniformity coefficient. The membrane quality coefficient was calculated using a multi-index quantitative evaluation formula, the specific formula of which is as follows:

[0050] ;

[0051] Where QI is the membrane quality coefficient;

[0052] d represents the actual average pore size of the finished MABR membrane; d0 represents the standard pore size of the finished MABR membrane.

[0053] Δh is the film thickness deviation coefficient; Δh0 is the standard value of film thickness deviation;

[0054] Hp is the film thickness uniformity coefficient; Hp is the standard value for film thickness uniformity.

[0055] ε represents the actual porosity of the finished MABR membrane; ε0 represents the standard porosity of the finished MABR membrane.

[0056] σ represents the actual tensile strength of the finished MABR membrane; σ0 represents the standard tensile strength of the finished MABR membrane.

[0057] The membrane quality control coefficient is calculated by averaging the membrane quality coefficients of several quality tests within the testing period. The membrane quality anomaly coefficient is calculated by the ratio of the number of times the membrane quality coefficient did not exceed the preset membrane quality coefficient threshold to the total number of tests within the testing period. The membrane quality control coefficient and the membrane quality anomaly coefficient are then compared with the preset membrane quality control coefficient threshold and the preset membrane quality anomaly coefficient threshold, respectively.

[0058] If the membrane quality control coefficient does not exceed the preset membrane quality control coefficient threshold or the membrane quality anomaly coefficient exceeds the preset membrane quality anomaly coefficient threshold, it indicates that the quality of the MABR membrane products produced during the testing period is poor, requiring strengthened production line supervision and cause investigation, thus generating a quality control abnormality signal; if the membrane quality control coefficient exceeds the preset membrane quality control coefficient threshold or the membrane quality anomaly coefficient does not exceed the preset membrane quality anomaly coefficient threshold, it indicates that the quality of the MABR membrane products produced during the testing period is good, thus generating a quality control qualified signal.

[0059] Example 3: Figure 2 As shown, the difference between this embodiment and Embodiments 1 and 2 is that the quality multi-index quantitative evaluation module is connected to the raw material dynamic monitoring and analysis module. The quality multi-index quantitative evaluation module sends the quality control abnormal signal to the raw material dynamic monitoring and analysis module. When the raw material dynamic monitoring and analysis module receives the quality control abnormal signal, it analyzes the raw material preparation status of the MABR membrane processing production line. Through analysis, it determines whether a high correlation signal of raw materials is generated, filling the gap in the correlation analysis between quality abnormalities and raw materials in traditional production lines. It scientifically evaluates the quality status of raw materials from multiple dimensions such as raw material component concentration and physical properties, accurately determines whether the raw materials are the key factors causing the quality abnormality of the finished product, realizes the automatic investigation and diagnosis of the cause of the quality status of the MABR membrane finished product, and avoids repeated quality abnormalities due to blind investigation of raw materials or ignoring raw material problems.

[0060] Furthermore, when a high correlation signal for raw materials is generated, it is sent to the production line monitoring center. Upon receiving the high correlation signal, the production line monitoring center issues a corresponding warning, prompting the monitoring center to promptly strengthen the supervision of raw material preparation, realize the automatic investigation and diagnosis of the causes of quality anomalies, prevent the continued occurrence of quality problems from the source of raw materials, further improve the control precision of MABR membrane finished product quality, and ensure that the production line outputs stable and qualified products. The specific analysis process of the raw material dynamic monitoring and analysis module is as follows:

[0061] The actual concentrations of each component in the raw material (such as polymers, pore-forming agents, solvents, etc.) were collected. A viscometer and laser particle size analyzer were installed at the mixing tank outlet to collect the overall actual viscosity and overall actual particle size of the raw material. The raw material state coefficient was calculated using the real-time state analysis formula. The real-time state analysis formula is as follows:

[0062] ;

[0063] Where S represents the raw material state coefficient; n represents the number of different types of components in the raw material;

[0064] Ci represents the actual concentration of the i-th component in the raw material;

[0065] C0i represents the standard concentration of the i-th component in the raw material;

[0066] Wi represents the preset influence factor of the i-th component in the raw material, and the sum of the preset influence factors of all components is 1;

[0067] μ represents the overall actual viscosity of the raw material; μ0 represents the overall standard viscosity of the raw material.

[0068] D represents the overall actual particle size of the raw material; D0 represents the overall standard particle size of the raw material.

[0069] Wc, Wμ, and Wd are preset weighting coefficients, and Wc + Wμ + Wd = 1;

[0070] The raw material state coefficient is compared with the preset raw material state coefficient threshold. If the raw material state coefficient exceeds the preset raw material state coefficient threshold, it indicates that the real-time quality of the raw material is poor. The corresponding raw material state coefficient is then marked as the raw material high impact coefficient. The number of raw material high impact coefficients during the detection period is obtained and the ratio is calculated with the total number of raw material state coefficients to obtain the raw material high impact detection value. The raw material high impact detection value is then compared with the preset raw material high impact detection threshold.

[0071] If the raw material high-impact detection value exceeds the preset raw material high-impact detection threshold, it indicates that the quality of the raw materials used in the MABR membrane processing production line during the detection period is poor, and the probability of poor quality of the finished MABR membrane due to raw material factors is high, thus generating a raw material high-correlation signal.

[0072] Furthermore, if the high impact detection value of the raw material does not exceed the preset high impact detection threshold, the average value of the state coefficients of all raw materials during the detection period is calculated to obtain the raw material state performance value, and the raw material state coefficient with the largest value during the detection period is marked as the raw material state performance value.

[0073] The raw material dynamic supervision coefficient is obtained by weighting and summing the raw material high impact detection value, raw material state performance value, and raw material state amplitude value. Specifically, the raw material high impact detection value, raw material state performance value, and raw material state amplitude value are each assigned a corresponding preset weight coefficient, and the raw material high impact detection value, raw material state performance value, and raw material state amplitude value are multiplied by the corresponding preset weight coefficients. The sum of the three sets of product results is marked as the raw material dynamic supervision coefficient.

[0074] It should be noted that the higher the value of the raw material dynamic monitoring coefficient, the worse the overall quality of the raw materials used in the MABR membrane processing production line during the testing period. The raw material dynamic monitoring coefficient is compared with the preset raw material dynamic monitoring coefficient threshold. If the raw material dynamic monitoring coefficient exceeds the preset raw material dynamic monitoring coefficient threshold, it indicates that the overall quality of the raw materials used in the MABR membrane processing production line during the testing period is poor. The probability of poor quality of the finished MABR membrane due to raw material factors is high, and a high correlation signal for raw materials is generated.

[0075] The working principle of this invention is as follows: During use, the multi-dimensional IoT sensing module comprehensively captures key parameters of the MABR membrane processing production line. The real-time parameter detection and output module quickly identifies parameters that need compensation, avoiding the accumulation of anomalies that could affect production line operation or product quality. The automated compensation control module realizes the automatic repair of parameters that need compensation, significantly reducing reliance on manual intervention, significantly improving the intelligence and automation level of the production line, and ensuring the continuous and stable operation of the production line. The production stability decision module comprehensively analyzes the stability of production line control based on multi-dimensional indicators, accurately identifies potential operational hazards and triggers early warnings in a timely manner, ensuring the reliability of production line operation, significantly improving the stability and automation level of production line operation, ensuring the quality of MABR membrane products, and reducing the difficulty of production line management.

[0076] In this invention, the threshold, preset value, or preset range settings are for result comparison and analysis to determine whether the result is good or bad. The magnitude of these values ​​is determined by a combination of large-scale model analysis of sample data and human experience, and can also be appropriately adjusted based on seasonal or common-sense influence conditions. Similarly, the preset weight coefficients and influence factors are assigned specific values ​​based on the magnitude of each parameter's influence on the result, ultimately reflecting the impact on the result. These settings are also determined by a combination of large-scale model analysis of sample data and human experience, and can also be appropriately adjusted based on seasonal or common-sense influence conditions.

[0077] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to any specific implementation. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, enabling those skilled in the art to better understand and utilize it. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. An Internet of Things based MABR membrane processing line supervisory control system, characterized in that, The multi-dimensional Internet of Things perception module, the parameter real-time detection output module, the automatic compensation control module, the production stability decision module and the production line supervision center are included. The multi-dimensional Internet of Things perception module collects real-time values of multi-dimensional parameters of the MABR membrane processing production line and sends them to the parameter real-time detection output module. The parameter real-time detection output module marks the parameters whose deviation values from the corresponding standard values exceed the corresponding deviation threshold values as compensation-required parameters. The automatic compensation control module adjusts the MABR membrane processing accordingly after receiving the compensation-required parameters to restore the compensation-required parameters to normal state. The production stability decision module analyzes the production automation control stability performance of the MABR membrane processing production line, generates a stability qualified signal or a stability abnormal signal through analysis, and sends the stability qualified signal or the stability abnormal signal to the production line supervision center.

2. The IoT-based MABR membrane processing skid control system of claim 1, wherein, The specific analysis process of the production stability decision module includes: calculating the parameter control characteristic value by weighted summation of the compensation warning value, the compensation recovery time value and the compensation recovery abnormal frequency value, defining the corresponding parameter as a blacklist parameter if the parameter control characteristic value exceeds the corresponding preset parameter control characteristic threshold value, and generating a stability abnormal signal if there is a blacklist parameter in the detection period.

3. The IoT-based MABR membrane processing skid monitoring and control system of claim 2, wherein, If there is no blacklist parameter in the detection period, the sum of the parameter condition characteristic values of all parameters is calculated to obtain the production line real-time value, all production line real-time values in the detection period are obtained and the mean value is calculated to obtain the production line control characteristic value, the number of times that the production line time value exceeds the preset production line time threshold value is marked as the production line control abnormal frequency value, and a stability abnormal signal is generated if the production line control abnormal frequency value or the production line control characteristic value exceeds the corresponding preset threshold value; otherwise, a stability qualified signal is generated.

4. The IoT-based MABR membrane processing skid control system of claim 2, wherein, The production stability decision module is communicatively connected to the quality multi-index quantitative evaluation module, the quality multi-index quantitative evaluation module analyzes the finished product quality control performance of the MABR membrane processing production line when receiving the stability qualified signal, generates a quality control qualified signal or a quality control abnormal signal through analysis, and sends the quality control qualified signal or the quality control abnormal signal to the production line supervision center.

5. The IoT-based MABR membrane processing line supervisory control system of claim 4, wherein, The specific analysis process of the quality multi-index quantitative evaluation module is as follows: the membrane quality coefficient is obtained through membrane quality comprehensive evaluation analysis, the membrane quality control table coefficient is obtained by averaging the membrane quality coefficients of several quality detections in the detection period, and the membrane quality abnormal occupancy coefficient is obtained by ratio calculation of the number of times that the membrane quality coefficient does not exceed the preset membrane quality coefficient threshold value and the total number of detections in the detection period; if the membrane quality control table coefficient does not exceed the preset membrane quality control table coefficient threshold value or the membrane quality abnormal occupancy coefficient exceeds the preset membrane quality abnormal occupancy coefficient threshold value, a quality control abnormal signal is generated; Otherwise, a quality control qualified signal is generated.

6. The IoT-based MABR membrane processing skid control system of claim 5, wherein, The specific analysis process of the membrane quality comprehensive evaluation analysis is as follows: The actual average pore size, actual porosity, and actual breaking strength of the finished MABR membrane are collected, and the thickness of the finished MABR membrane at several positions is collected, the average value of the thickness at all positions is compared with the deviation value of the standard thickness, and the deviation coefficient of the membrane thickness is marked, and the thickness uniformity coefficient of the membrane thickness is calculated by variance calculation; The membrane quality coefficient is calculated by the multi-index quantitative evaluation formula.

7. The IoT-based MABR membrane processing skid monitoring and control system of claim 4, wherein, The quality multi-index quantitative evaluation module is in communication connection with the raw material dynamic supervision analysis module, and when the quality control abnormal signal is received, the raw material preparation condition of the MABR membrane processing production line is analyzed, whether the raw material high correlation signal is generated is judged through the analysis, and when the raw material high correlation signal is generated, it is sent to the production line supervision center.

8. The IoT-based MABR membrane processing skid monitoring and control system of claim 7, wherein, The specific analysis process of the raw material dynamic supervision analysis module is: obtaining the raw material state coefficient through real-time detection and analysis of the raw material state, if the raw material state coefficient exceeds the preset raw material state coefficient threshold, the corresponding raw material state coefficient is marked as the raw material high influence coefficient; the number of raw material high influence coefficients in the detection period is obtained and the ratio calculation is performed with the total number of raw material state coefficients to obtain the raw material high influence detection value, if the raw material high influence detection value exceeds the preset raw material high influence detection threshold, the raw material high correlation signal is generated.

9. The IoT-based MABR membrane processing skid monitoring and control system of claim 8, wherein, If the raw material high influence detection value does not exceed the preset raw material high influence detection threshold, the raw material dynamic supervision coefficient is calculated by weighted summation of the raw material high influence detection value, the raw material state performance value and the raw material state table value, if the raw material dynamic supervision coefficient exceeds the preset raw material dynamic supervision coefficient threshold, the raw material high correlation signal is generated.

10. The IoT-based MABR membrane processing skid monitoring and control system of claim 8, wherein, The specific process of real-time detection and analysis of the raw material state is: collecting the actual concentration of each component in the raw material, and installing a viscometer and a laser particle size instrument at the outlet of the mixing tank to collect the overall actual viscosity and overall actual particle size of the raw material, and calculating the raw material state coefficient by the raw material real-time state analysis formula.

Images