Intelligent control method and system for vegetation water purification type ecological building block production line

Abstract

The invention discloses an intelligent control method and system for a vegetation water purification type ecological building block production line, and the method comprises the following steps: 1, carrying out the correlation analysis based on the production data of vegetation water purification type ecological building blocks in historical data and corresponding building block porosity data; according to the method, the parameters needing to be adjusted can be accurately determined by combining the optimization control parameter combination sorting table and the actual situation of the production control parameters, waste caused by blind adjustment is reduced, the optimal adjustment scheme can be formulated by analyzing the adjustment difficulty of the production control parameters and the porosity optimization degree, and the adjustment efficiency is improved. Therefore, the production efficiency and the product quality are improved, parameters which are large in porosity optimization degree and small in adjustment difficulty are adjusted, resources can be utilized to the maximum extent, the overall performance of a production line can be gradually improved, an adjustment scheme is determined through a scientific method, the production risk caused by improper parameter adjustment can be reduced, and the product quality is improved. And the production stability and reliability are ensured.

Description

Technical Field

[0001] The invention relates to the technical field of ecological building block production lines, and in particular to an intelligent control method and system for a plant-based water purification ecological building block production line. Background Art

[0002] Vegetative water purification ecological blocks are a type of blocks that are scientifically made with plants as the main body, supplemented with appropriate amounts of soil, organic fertilizers and other materials, and integrated with water purification function design. They are designed to protect river banks, improve water quality, and promote ecological restoration and biodiversity. These blocks usually have a porous structure that is conducive to plant growth, and achieve water purification through the synergistic effect of plant roots and microorganisms;

[0003] The original intention of designing the vegetation-based water-purification ecological blocks is to integrate the function of vegetation planting and provide the necessary space and nutrients for vegetation growth. Porosity, as an important indicator to measure the size of the internal space of the blocks, directly affects whether the roots of the vegetation can grow and expand smoothly in the blocks. In addition to providing plant growth space, the vegetation-based water-purification ecological blocks also have a water purification function. The pore structure inside the blocks can filter and purify rainwater, which helps to improve the quality of the urban water environment. The size and distribution of the porosity will directly affect the performance of this function. Therefore, the porosity needs to be monitored during the production process to ensure that the blocks have sufficient structural strength while meeting the ecological function. However, when the porosity is abnormal, the control parameters need to be adjusted, but there is a lack of basis for adjusting the control parameters. Blind adjustment causes waste of resources and it is difficult to formulate a better adjustment plan, which affects the improvement of production efficiency and product quality and increases the production risk caused by improper parameter adjustment. Summary of the invention

[0004] The object of the present invention is to provide an intelligent control method and system for a plant-based water-purifying ecological building block production line to solve at least one of the above-mentioned prior art problems.

[0005] In a first aspect, the present invention provides an intelligent control method for a plant-based water-purifying ecological building block production line, comprising the following steps:

[0006] Step 1: Based on the production data of the plant-based water purification ecological blocks in the historical data and the corresponding block porosity data, combined with correlation analysis, obtain the production control parameters with high impact on the block porosity;

[0007] Step 2: Based on the obtained production control parameters, a porosity model is established, and a combination ranking table of optimized control parameters is obtained using a particle swarm optimization algorithm;

[0008] Step 3: During the production process of the plant-based water purification ecological building blocks, the porosity of the ecological building blocks is tested, and the porosity data is deeply analyzed to obtain an abnormal evaluation value, and the abnormal evaluation threshold is judged to identify and output the porosity abnormality signal;

[0009] Step 4: Based on the abnormal porosity signal, analyze the optimization control parameter combination ranking table, the difficulty of production control parameter adjustment, and the porosity optimization degree to optimize the production control parameters;

[0010] Specifically, it includes: extracting the production control parameters corresponding to the abnormal signal of the control parameter generation, comparing them in the order of the optimized control parameter sorting table to obtain the overlap ratio value, and generating the sorting table to be optimized in combination with the overlap ratio value, calculating the optimization degree value and the mean of the number of steps for each sorted overlapping production control parameter, using the formula to calculate the adjustment judgment value, selecting the overlapping production control parameter combination corresponding to the maximum value for adjustment, and adjusting the overlapping production control parameters to the overlapping production control parameter standard values.

[0011] In a second aspect, the present invention provides an intelligent control system for a plant-based water-purifying ecological building block production line, the system comprising: a high-impact parameter acquisition module, an optimized parameter combination acquisition module, an anomaly detection module, a production optimization module and a cloud server;

[0012] High-impact parameter acquisition module: Based on the production data of plant-based water purification ecological blocks in historical data and the corresponding block porosity data, combined with correlation analysis, the production control parameters of high-impact block porosity are obtained;

[0013] Optimization parameter combination acquisition module: Based on the obtained production control parameters, a porosity model is established, and the particle swarm optimization algorithm is used to obtain the optimization control parameter combination ranking table;

[0014] Abnormal detection module: During the production process of the plant-based water purification ecological building blocks, the porosity of the ecological building blocks is detected, and the porosity data is deeply analyzed to obtain the abnormal evaluation value, and the abnormal evaluation threshold is judged to identify and output the abnormal porosity signal;

[0015] Production optimization module: Based on the abnormal porosity signal, combined with the optimization control parameter combination ranking table, the difficulty of production control parameter adjustment, and the porosity optimization degree, the production control parameters are optimized;

[0016] Specifically, it includes: extracting the production control parameters corresponding to the abnormal signal of the control parameter generation, comparing them in the order of the optimized control parameter sorting table to obtain the overlap ratio value, and generating the sorting table to be optimized in combination with the overlap ratio value, calculating the optimization degree value and the mean of the number of steps for each sorted overlapping production control parameter, using the formula to calculate the adjustment judgment value, selecting the overlapping production control parameter combination corresponding to the maximum value for adjustment, and adjusting the overlapping production control parameters to the overlapping production control parameter standard values.

[0017] Beneficial effects of the present invention:

[0018] 1. The present invention combines correlation analysis with a model optimization algorithm to screen out production control parameters that have a significant impact on the porosity of blocks, and establish an accurate porosity prediction model to guide the adjustment of production parameters, improve production efficiency and the accuracy of block quality, and optimize the production control parameters using a particle swarm optimization algorithm to obtain an optimized control parameter combination ranking table. By controlling the production parameters, the plant-based water purification ecological blocks can have a stable porosity, thereby improving the overall quality and performance of the product;

[0019] 2. The present invention can accurately determine the parameters that need to be adjusted by combining the optimization control parameter combination ranking table with the actual situation of the production control parameters, reduce the waste caused by blind adjustment, and formulate the optimal adjustment plan by analyzing the difficulty of adjusting the production control parameters and the degree of porosity optimization, thereby improving production efficiency and product quality. By adjusting the parameters with a high degree of porosity optimization and a low adjustment difficulty, resources can be utilized to the maximum extent, and the overall performance of the production line can be gradually improved. By determining the adjustment plan through scientific methods, the production risks caused by improper parameter adjustment can be reduced, thereby ensuring the stability and reliability of production. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 This is a flow chart of an intelligent control method for a production line of plant-based water-purifying ecological building blocks according to the present invention;

[0022] Figure 2 This is a structural schematic diagram of an intelligent control system for a plant-based water-purifying ecological building block production line of the present invention;

[0023] Figure 3 This is a structural schematic diagram of an intelligent control device for a plant-based water purification ecological building block production line according to the present invention.

[0024] In the figure: 3, computer device; 301, processor; 302, memory; 303, computer program; DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0026] Embodiment 1

[0027] Figure 1 The flowchart of the intelligent control method of a plant-based water-purifying ecological block production line provided in the first embodiment of the present invention, the embodiment of the present invention can be applied to the situation of monitoring and optimizing the porosity when producing plant-based water-purifying ecological blocks, the intelligent control method of the plant-based water-purifying ecological block production line can be executed by an intelligent control system of a plant-based water-purifying ecological block production line, the intelligent control system of the plant-based water-purifying ecological block production line can be implemented by software and / or hardware, and the intelligent control system of the plant-based water-purifying ecological block production line can be configured in an intelligent control device of a plant-based water-purifying ecological block production line. Optionally, the intelligent control device of a plant-based water-purifying ecological block production line can be an electronic device, which can be a notebook, a desktop computer, a smart tablet, etc., and the embodiment of the present invention does not limit this.

[0028] like Figure 1 As shown, an intelligent control method for a production line of a water-purifying eco-building block provided by an embodiment of the present invention specifically comprises the following steps:

[0029] Step 1: Based on the production data of the plant-based water purification ecological blocks in the historical data and the corresponding block porosity data, combined with correlation analysis, obtain the production control parameters with high impact on the block porosity;

[0030] In some embodiments, production data on plant-growing water purification ecological building blocks and corresponding building block porosity data are extracted from historical data, wherein the historical data is obtained from a production record system;

[0031] Production data includes but is not limited to raw material ratio, production process parameters (such as temperature, pressure, time, etc.), and equipment status;

[0032] The Spearman rank correlation analysis algorithm is used to analyze the correlation between porosity and any production data;

[0033] Take porosity as one variable and any production data as the other variable, (X, Y), sort the two variable data, and record the position after sorting (X′, Y′). The value of (X′, Y′) is called the rank. Calculate the difference in rank, i.e. d i =X′-Y′;

[0034] Among them, the calculation method of Spearman rank correlation is: Where n is the number of variables, i indicates that the variables are in order, and the Spearman rank correlation coefficient S is calculated using SPSS software Rho and P value;

[0035] The significance level is set to 0.05, and a correlation threshold is set at the same time, wherein the correlation threshold is set by a person skilled in the art based on a summary of multiple historical experimental data;

[0036] Take the absolute value of the Spearman rank correlation coefficient to obtain the absolute coefficient value, compare the P value with the significance level, and compare the absolute coefficient value with the correlation degree threshold. If the P value is less than the significance level and the absolute coefficient value is greater than the correlation degree threshold, it means that the porosity has a high correlation with the corresponding production data, and it is marked as a production control parameter with a high impact on the porosity of the block. Otherwise, it is marked as a production control parameter with a low impact on the porosity of the block.

[0037] It should be noted that the above-mentioned low impact includes low impact and no impact;

[0038] Step 2: Based on the obtained production control parameters, a porosity model is established, and a combination ranking table of optimized control parameters is obtained using a model optimization algorithm;

[0039] Among them, model optimization algorithms include but are not limited to: genetic algorithm, particle swarm optimization;

[0040] In some embodiments, based on the marked production control parameters with high impact on the porosity of the blocks, a porosity model is established by training a random forest model, and the specific process is as follows:

[0041] Extracting the marked production control parameter data with high impact on the porosity of masonry blocks and the corresponding porosity data from the historical data;

[0042] The acquired data is divided into a training set and a validation set in a ratio of 8:2 for training the random forest model;

[0043] The production control parameters that have been marked as high-impact are selected as features (independent variables) and porosity as the target variable (dependent variable);

[0044] Clean the data, remove outliers and missing values, and normalize or standardize the data if necessary to ensure that the weights of each feature in model training are relatively balanced;

[0045] Use the random forest algorithm for model training. Random forest is an ensemble learning method that improves the accuracy and robustness of the model by building multiple decision trees and combining their prediction results.

[0046] During the training process, the random forest randomly selects a subset of features to build each decision tree and uses a voting mechanism to determine the final prediction result;

[0047] Use cross-validation and other methods to evaluate the model to check the generalization ability of the model. Evaluation indicators include but are not limited to: accuracy, recall, and F1 score;

[0048] The model that meets the performance requirements after evaluation is the porosity model. The particle swarm optimization algorithm is used to obtain the optimization control parameter combination ranking table. The specific process is as follows:

[0049] Each particle represents a potential combination of production control parameters, and the particle's position (i.e., parameter value) and velocity (i.e., direction and magnitude of parameter adjustment) are its states in the search space;

[0050] Set a reasonable number of particles to ensure sufficient exploration of the search space;

[0051] According to the value range of the production control parameters, the position and speed of each particle are randomly initialized;

[0052] Using the trained random forest porosity model as the fitness function, for each particle (i.e., each combination of production control parameters), it is input into the model to obtain the predicted porosity;

[0053] Define the fitness value according to actual needs. For example, if the goal is to make the porosity within the porosity limit range, the fitness value can be the negative value of the error between the predicted porosity and the maximum or minimum value of the range.

[0054] Exemplarily, the following is a possible method for defining the fitness value: if the predicted porosity K is within the porosity limit range [KX, KD], the error can be defined as 0, indicating that the parameter combination has reached the target; if the predicted porosity K is lower than the minimum value KX of the porosity limit range, the error can be defined as a positive value of KX-K, indicating that the porosity is insufficient; if the predicted porosity is higher than the maximum value KD of the porosity limit range, the error can be defined as a positive value of K-KD, indicating that the porosity is too high; the fitness value SD can be defined as the negative value of the error, but it should be noted that since we want to maximize the fitness value (i.e., minimize the error), when the porosity is within the target range, a positive reward value (such as 0 or a small positive number) should be given, rather than simply 0 (because 0 may not be as superior as other positive numbers in comparison). For simplicity, a small positive number JL is selected as the reward value. When the porosity is within the target range, the fitness value is JL;

[0055] For each particle, record the best position it has found so far (i.e., the parameter combination that produces the highest fitness value), which is called the individual optimal position;

[0056] In the entire particle swarm, the best position found so far (i.e. the best among the individual optimal positions of all particles) is recorded, which is called the global optimal position.

[0057] According to the individual optimal and global optimal positions, as well as the current speed and position of the particle, the speed and position of the particle are adjusted according to the PSO update formula. The update formula usually includes inertia terms, cognitive terms, and social terms, which represent the ability of the particle to maintain the current motion trend, learn from the individual optimal, and learn from the global optimal.

[0058] Set a maximum number of iterations or a threshold value of fitness value change as the termination condition. When the maximum number of iterations is reached or the change in fitness value is less than the threshold, stop the iteration.

[0059] After the iteration is completed, a ranking table containing multiple optimal parameter combinations is output, which is the optimization control parameter combination ranking table. The optimization parameter combinations in the ranking table are sorted from high to low according to the fitness value;

[0060] The technical solution of this embodiment is: firstly, based on historical production data and porosity data, the production control parameters with high impact on the porosity of the blocks are screened out using the Spearman rank correlation analysis algorithm; based on these high-impact parameters, a porosity prediction model is established using the random forest algorithm; and the production control parameters are optimized using the particle swarm optimization algorithm, and finally an optimized control parameter combination ranking table is output to guide actual production;

[0061] In this way, the production control parameters that have a significant impact on the porosity of the blocks can be screened out, and an accurate porosity prediction model can be established to guide the adjustment of production parameters, improve production efficiency and the accuracy of block quality. By optimizing the production control parameters using the particle swarm optimization algorithm, the optimal or better parameter combination can be found. By controlling the production parameters, the plant-based water purification ecological blocks can have a stable porosity, thereby improving the overall quality and performance of the product.

[0062] Embodiment 2

[0063] Based on the above embodiments, Figure 1 As shown, an intelligent control method for a production line of a water-purifying eco-building block provided by an embodiment of the present invention specifically comprises the following steps:

[0064] Step 3: During the production process of the plant-based water purification ecological blocks, the porosity of the ecological blocks is tested, the porosity data is deeply analyzed, and the normal porosity signal or the abnormal porosity signal is identified and output;

[0065] In some embodiments, a monitoring period is set, and during the production process of the plant-based water-purifying ecological building blocks, random sampling and testing are performed on the plant-based water-purifying ecological building blocks produced within the monitoring period to obtain the porosity;

[0066] Among them, the porosity is obtained by image analysis method, and the specific process is as follows:

[0067] Use automated equipment (such as automatic cutting machines and automatic grinding machines) to cut or grind the blocks to prepare a smooth cross section. Use a digital camera to take photos of the cross section. Use image analysis software to process the photos, identify the pores, and measure the pore area and the total area of ​​the blocks. Use the formula Calculate porosity;

[0068] Setting a porosity threshold, and comparing the porosity with the porosity threshold, wherein the porosity is set by a person skilled in the art based on a summary of multiple historical experimental data and production standards;

[0069] If the porosity is less than or equal to the porosity threshold, it is marked as a standard block; if the porosity is greater than the porosity threshold, it is marked as a non-standard block;

[0070] Count the number of blocks that do not meet the standards and mark them as non-compliant blocks. Compare the non-compliant blocks with the total number of samples to obtain the non-compliant block ratio.

[0071] Obtain the porosity values ​​of the blocks that do not meet the standards, and perform difference calculations with the porosity thresholds to obtain deviation values, perform ratio calculations on the deviation values ​​and the porosity thresholds to obtain non-conformity values, and sum and average all non-conformity values ​​to obtain a non-conformity mean value;

[0072] The non-conformity ratio and the non-conformity degree mean are weighted and summed to obtain the abnormal assessment value, where the weight of the non-conformity ratio is 0.532 and the weight of the non-conformity degree mean is 0.468;

[0073] Setting an abnormality assessment threshold, and comparing the abnormality assessment value with the abnormality assessment threshold, wherein the abnormality assessment threshold is set by a person skilled in the art based on a summary of multiple historical laboratory data and the amount of sample for sampling and testing;

[0074] If the abnormal evaluation value is greater than the abnormal evaluation threshold, a porosity abnormal signal is generated; if the abnormal evaluation value is less than or equal to the abnormal evaluation threshold, a porosity normal signal is generated;

[0075] Step 4: Based on the abnormal porosity signal, analyze the optimization control parameter combination ranking table, the difficulty of production control parameter adjustment, and the porosity optimization degree to optimize the production control parameters;

[0076] In some embodiments, based on the porosity abnormality signal, a detection period corresponding to the generation of the porosity abnormality signal is obtained and marked as an abnormal detection period;

[0077] Acquire the production control parameters of the high-impact block porosity during the abnormal detection period, compare the production control parameters of the high-impact block porosity with the standard range of the production control parameters of the high-impact block porosity, and generate a normal control parameter signal if the production control parameters of the high-impact block porosity are within the standard range of the production control parameters of the high-impact block porosity; and generate an abnormal control parameter signal if the production control parameters of the high-impact block porosity are not within the standard range of the production control parameters of the high-impact block porosity;

[0078] Extracting the production control parameters corresponding to the production control parameter abnormal signals as the production control parameters to be analyzed, counting the number of the production control parameters to be analyzed, and obtaining the data of the production control parameters to be analyzed;

[0079] The production control parameters to be analyzed are compared in sequence according to the order of the optimization control parameter ranking table, and the overlapping production control parameters in the production control parameters corresponding to each ranking are obtained, and the ratio is calculated with the number of generated control parameters to be analyzed to obtain the ratio of the overlapping number;

[0080] Sort the overlap quantity ratio values ​​in descending order to obtain an overlap production control parameter sorting table;

[0081] According to the numbering sequence of the optimization control parameter sorting table, the corresponding sorting numbers in the optimization control parameter sorting table and the corresponding sorting numbers in the overlapping production control parameter sorting table are summed and averaged, and sorted in descending order to obtain a new sorting table, which is marked as the sorting table to be optimized;

[0082] It should be noted that if there are numbers that are the same after summing and averaging, they will be randomly sorted in order;

[0083] For example, assuming that the porosity abnormality signal occurs between 9 and 11 a.m. on a certain day, we extract the production control parameters to be analyzed during this period, which are raw material ratio, curing temperature, and molding pressure;

[0084] Assuming that the first-ranked parameter combination in the optimization control parameter ranking table includes raw material ratio, curing temperature and humidity, we only calculate the overlap ratio of raw material ratio and curing temperature with the parameters to be analyzed, which is 2 / 3. The second-ranked parameter combination includes curing temperature, humidity and time. We only calculate the overlap ratio of curing temperature with the parameters to be analyzed, which is 1 / 3. The third-ranked parameter combination includes raw material ratio, curing temperature and molding pressure, and the overlap ratio is 1.

[0085] Based on the fact that the ranking numbers of the above-mentioned optimization control parameter ranking table are 1, 2, and 3, and the numbers of the overlapping production control parameter ranking table are 3, 1, and 2, then according to the optimization control parameter ranking table, the corresponding ranking numbers in the optimization control parameter ranking table and the corresponding ranking numbers in the overlapping production control parameter ranking table are summed and averaged to obtain 1.5, 2.5, and 2, and the new ranking is 1, 3, and 2. The first ranking of the ranking table to be optimized is raw material ratio, curing temperature and humidity, the second is raw material ratio, curing temperature and molding pressure, and the third is curing temperature, humidity, and time;

[0086] Based on the order of the sorted table to be optimized;

[0087] For each ranked overlapping production control parameter, the standard value of the overlapping production control parameter is input into the porosity model, a porosity prediction value is output, a difference is calculated between the output porosity prediction value and the porosity threshold, and a ratio is calculated between the difference and the porosity threshold to obtain an optimization degree value;

[0088] For each production control parameter, an adjustment step size is set, wherein the adjustment step size is set by a person skilled in the art based on a summary of historical multiple experimental data and the difficulty of adjusting the gradient;

[0089] For each overlapping production control parameter in each sort, calculate the number of steps adjusted to the standard value of the corresponding production control parameter. The formula for calculating the number of steps BS is: SCC is the value of the production control parameter, SCB is the standard value of the production control parameter, and BC is the adjustment step. The number of steps of the overlapping production control parameters in each sort is summed and averaged to obtain the mean number of steps;

[0090] It should be noted that if the calculated number of steps is not an integer, the number of steps is obtained by rounding off;

[0091] Remove the production control parameter combinations corresponding to the optimization degree value less than or equal to 0, and substitute the remaining overlapping production control parameters into the formula TP = Ln (a1*YH+1.032) + a2*BJ -2 , calculate the adjustment judgment value TP, where YH is the optimization degree value, BJ is the mean value of the step number, a1 and a2 are preset proportional coefficients, the value of a1 is 1.364, and the value of a2 is 1.136;

[0092] Extract the maximum value of the adjustment judgment value, obtain the coincidence production control parameter combination corresponding to the maximum value, and adjust the coincidence production control parameter to the coincidence production control parameter standard value;

[0093] It should be noted that if there are adjustment judgment values ​​that are tied for the maximum, the combination of overlapping production control parameters with a higher optimization degree value is selected for adjustment;

[0094] The core technical solution of this implementation is: in the production process of plant-based water-purifying ecological blocks, set a monitoring period, conduct random sampling inspection on the produced blocks, obtain the porosity through image analysis, and compare it with the set porosity threshold to generate a normal or abnormal porosity signal. Based on the abnormal porosity signal, obtain the production control parameters of the high-impact block porosity during the abnormal detection period, and compare them with the standard range. Extract the production control parameters corresponding to the abnormal control parameter signal, compare them in the order of the optimized control parameter sorting table, generate a sorting table to be optimized, calculate the optimization degree value and the mean of the number of steps for each sorted overlapping production control parameter, use the formula to calculate the adjustment judgment value, and select the overlapping production control parameter combination corresponding to the maximum value for adjustment;

[0095] By combining the optimization control parameter combination ranking table with the actual situation of the production control parameters, the parameters that need to be adjusted can be accurately determined to avoid waste caused by blind adjustment. By analyzing the difficulty of adjusting the production control parameters and the degree of porosity optimization, the optimal adjustment plan can be formulated to improve production efficiency and product quality. Adjusting parameters that have a large impact on porosity and are easy to adjust can maximize the use of resources, reduce waste, and gradually improve the overall performance of the production line. Determining the adjustment plan through scientific methods can reduce production risks caused by improper parameter adjustment and ensure production stability and reliability.

[0096] Embodiment 3

[0097] Based on the above embodiments, Figure 2 As shown, the embodiment of the present invention provides an intelligent control system for a plant-based water-purifying ecological building block production line, which specifically includes: a high-impact parameter acquisition module, an optimized parameter combination acquisition module, an anomaly detection module, a production optimization module and a cloud server;

[0098] High-impact parameter acquisition module: Based on the production data of plant-based water purification ecological blocks in historical data and the corresponding block porosity data, combined with correlation analysis, the production control parameters of high-impact block porosity are obtained;

[0099] Optimization parameter combination acquisition module: Based on the obtained production control parameters, a porosity model is established, and the optimization control parameter combination ranking table is obtained using the model optimization algorithm;

[0100] Among them, model optimization algorithms include but are not limited to: genetic algorithm, particle swarm optimization;

[0101] Abnormal detection module: During the production process of the plant-based water purification ecological blocks, the porosity of the ecological blocks is detected, the porosity data is deeply analyzed, and the normal porosity signal or abnormal porosity signal is identified and output;

[0102] Production optimization module: Based on the abnormal porosity signal, combined with the optimization control parameter combination ranking table, the difficulty of production control parameter adjustment, and the porosity optimization degree, the production control parameters are optimized.

[0103] Embodiment 4

[0104] like Figure 3 As shown, an embodiment of the present invention further provides a computer device 3, comprising: a memory 302 and a processor 301 and a computer program 303 stored on the memory 302. When the computer program 303 is executed on the processor 301, an intelligent control method for a bio-based water-purifying ecological building block production line as described in any one of the above methods is implemented.

[0105] The computer device 3 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The computer device 3 may include, but is not limited to, a processor 301 and a memory 302. Those skilled in the art will appreciate that

[0106] Figure 3 It is only an example of computer device 3 and does not constitute a limitation on computer device 3. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components, for example, it may also include input and output devices, network access devices, etc.

[0107] The processor 301 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0108] In some embodiments, the memory 302 may be an internal storage unit of the computer device 3, such as a hard disk or memory of the computer device 3. In other embodiments, the memory 302 may also be an external storage device of the computer device 3, such as a plug-in hard disk, a smart memory card (SmartMediaCard, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the computer device 3. Further, the memory 302 may also include both an internal storage unit of the computer device 3 and an external storage device. The memory 302 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program. The memory 302 may also be used to temporarily store data that has been output or is to be output.

[0109] Embodiment 5

[0110] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, an intelligent control method for a bio-based water-purifying ecological building block production line as described in any one of the above methods is implemented.

[0111] In this embodiment, if the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0112] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0113] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0114] In the embodiments disclosed in the present application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0115] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0116] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0117] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. An intelligent control method for a production line of bio-water-purifying ecological building blocks, characterized in that: The following steps are involved: Step 1: Based on the production data of the plant-based water purification ecological blocks in the historical data and the corresponding block porosity data, combined with correlation analysis, obtain the production control parameters with high impact on the block porosity; Step 2: Based on the obtained production control parameters, a porosity model is established, and a combination ranking table of optimized control parameters is obtained using a particle swarm optimization algorithm; Step 3: During the production process of the plant-based water purification ecological building blocks, the porosity of the ecological building blocks is tested, and the porosity data is deeply analyzed to obtain an abnormal evaluation value, and the abnormal evaluation threshold is judged to identify and output the porosity abnormality signal; Step 4: Based on the abnormal porosity signal, analyze the optimization control parameter combination ranking table, the difficulty of production control parameter adjustment, and the porosity optimization degree to optimize the production control parameters; Specifically, it includes: extracting the production control parameters corresponding to the abnormal signal of the control parameter generation, comparing them in the order of the optimized control parameter sorting table to obtain the overlap ratio value, and generating the sorting table to be optimized in combination with the overlap ratio value, calculating the optimization degree value and the mean of the number of steps for each sorted overlapping production control parameter, using the formula to calculate the adjustment judgment value, selecting the overlapping production control parameter combination corresponding to the maximum value for adjustment, and adjusting the overlapping production control parameters to the overlapping production control parameter standard values.

2. According to claim 1, the intelligent control method of a plant-based water purification ecological block production line is characterized in that: The process of obtaining the production control parameters that have a great impact on the porosity of the blocks is as follows: Extract the production data of plant-based water purification ecological blocks and the corresponding block porosity data from historical data; The Spearman rank correlation analysis algorithm is used to analyze the correlation between porosity and any production data; Take porosity as one variable and any production data as the other variable, (X, Y), sort the two variable data, and record the position after sorting (X′, Y′). The value of (X′, Y′) is called the rank. Calculate the difference in rank, i.e. d i =X′-Y′; Among them, the calculation method of Spearman rank correlation is: Where n is the number of variables, i indicates that the variables are in order, and the Spearman rank correlation coefficient S is calculated using SPSS software Rho and P value; The significance level was set to 0.05, and the correlation threshold was set at the same time; Take the absolute value of the Spearman rank correlation coefficient to obtain the absolute coefficient value, compare the P value with the significance level, and compare the absolute coefficient value with the correlation degree threshold. If the P value is less than the significance level and the absolute coefficient value is greater than the correlation degree threshold, it is marked as a production control parameter with a high impact on the porosity of the masonry block.

3. The intelligent control method of a plant-based water purification ecological block production line according to claim 1 is characterized in that: The process of obtaining the porosity model is as follows: Based on the production control parameters of the marked high-impact block porosity, extracting the marked high-impact block porosity production control parameter data and the corresponding porosity data from the historical data; The acquired data is divided into a training set and a validation set in a ratio of 8:2 for training the random forest model; The production control parameters that have been marked as high-impact are selected as features, and porosity is used as the target variable; Clean the data to remove outliers and missing values; During the training process, the random forest randomly selects a subset of features to build each decision tree and uses a voting mechanism to determine the final prediction result; The model is evaluated using methods such as cross-validation, and the model that meets the performance requirements after evaluation is the porosity model.

4. The intelligent control method for a plant-based water purification ecological block production line according to claim 1 is characterized in that: The process of obtaining the optimization control parameter combination ranking table is as follows: Each particle represents a potential combination of production control parameters, and the position and velocity of the particle are its state in the search space; Set a reasonable number of particles to ensure sufficient exploration of the search space; According to the value range of the production control parameters, the position and speed of each particle are randomly initialized; Using the trained random forest porosity model as the fitness function, for each particle, it is input into the model to obtain the predicted porosity; Define the fitness value; For each particle, record the best position it has found so far, called the individual optimum; In the entire particle swarm, the best position found so far is recorded, which is called the global optimum; According to the individual optimal and global optimal positions, as well as the current speed and position of the particle, the speed and position of the particle are adjusted according to the PSO update formula; Set a maximum number of iterations or a threshold value of fitness value change as the termination condition. When the maximum number of iterations is reached or the change in fitness value is less than the threshold, stop the iteration. After the iteration is completed, a sorting table containing multiple optimal parameter combinations is output, which is the optimization control parameter combination sorting table. The optimization parameter combinations in the sorting table are sorted from high to low according to the fitness value.

5. The intelligent control method of a plant-based water purification ecological building block production line according to claim 1 is characterized in that: The process of outputting the abnormal porosity signal is as follows: Obtaining an anomaly assessment threshold, setting the anomaly assessment threshold, and comparing the anomaly assessment value with the anomaly assessment threshold; If the abnormality evaluation value is greater than the abnormality evaluation threshold, a porosity abnormality signal is generated.

6. The intelligent control method of a plant-based water purification ecological building block production line according to claim 1 is characterized in that: The process of obtaining the abnormal evaluation value is as follows: A monitoring period is set, and during the production process of the vegetation water purification type ecological building blocks, random sampling and testing are conducted on the vegetation water purification type ecological building blocks produced within the monitoring period to obtain the porosity; A porosity threshold is set, and the porosity is compared with the porosity threshold; If the porosity is greater than the porosity threshold, it is marked as a non-compliant masonry block; Count the number of blocks that do not meet the standards and mark them as non-compliant blocks. Compare the non-compliant blocks with the total number of samples to obtain the non-compliant block ratio. Obtain the porosity values ​​of the blocks that do not meet the standards, and perform difference calculations with the porosity thresholds to obtain deviation values, perform ratio calculations on the deviation values ​​and the porosity thresholds to obtain non-conformity values, and sum and average all non-conformity values ​​to obtain a non-conformity mean value; The weighted sum of the non-conformity ratio and the non-conformity degree average is calculated to obtain the abnormal assessment value.

7. The intelligent control method for a water-purifying eco-block production line according to claim 1 is characterized in that: The process of obtaining the adjustment judgment value is as follows: Get the optimization degree value and the average number of steps; Remove the production control parameter combinations corresponding to the optimization degree value less than or equal to 0, and substitute the remaining overlapping production control parameters into the formula TP = Ln (a1*YH+1.032) + a2*BJ -2 , the adjustment judgment value TP is calculated, where YH is the optimization degree value, BJ is the mean of the number of steps, and a1 and a2 are preset proportional coefficients.

8. The intelligent control method for a plant-based water purification ecological block production line according to claim 1 is characterized in that: The process of obtaining the optimization degree value and the mean value of the step number is as follows: Get the order of the sorted table to be optimized; For each ranked overlapping production control parameter, the standard value of the overlapping production control parameter is input into the porosity model, a porosity prediction value is output, a difference is calculated between the output porosity prediction value and the porosity threshold, and a ratio is calculated between the difference and the porosity threshold to obtain an optimization degree value; For each production control parameter, set the adjustment step size; For each overlapping production control parameter in each sort, calculate the number of steps to adjust to the standard value of the corresponding production control parameter. The formula for calculating the number of steps BS is: where SCC is the production control parameter value, SCB is the standard value of the production control parameter, and BC is the adjustment step. Sum and average the number of steps of the overlapping production control parameters in each sort to obtain the mean number of steps.

9. The intelligent control method for a plant-based water purification ecological block production line according to claim 1 is characterized in that: The process of obtaining the order of the sorting table to be optimized is as follows: Based on the porosity abnormality signal, a detection period corresponding to the generation of the porosity abnormality signal is obtained and marked as an abnormality detection period; Acquire the production control parameters of the high-impact block porosity during the abnormal detection period, compare the production control parameters of the high-impact block porosity with the standard range of the production control parameters of the high-impact block porosity, and generate a control parameter abnormality signal if the production control parameters of the high-impact block porosity are not within the standard range of the production control parameters of the high-impact block porosity; Extracting the production control parameters corresponding to the production control parameter abnormal signals as the production control parameters to be analyzed, counting the number of the production control parameters to be analyzed, and obtaining the data of the production control parameters to be analyzed; The production control parameters to be analyzed are compared in sequence according to the order of the optimization control parameter ranking table, and the overlapping production control parameters in the production control parameters corresponding to each ranking are obtained, and the ratio is calculated with the number of generated control parameters to be analyzed to obtain the ratio of the overlapping number; Sort the overlap quantity ratio values ​​in descending order to obtain an overlap production control parameter sorting table; According to the numbering order of the optimization control parameter sorting table, the corresponding sorting numbers in the optimization control parameter sorting table and the corresponding sorting numbers in the overlapping production control parameter sorting table are summed and averaged, and sorted in descending order to obtain a new sorting table, which is marked as the sorting table to be optimized.

10. An intelligent control system for a plant-based water purification ecological block production line, characterized in that: The system is used to execute the method described in any one of claims 1 to 9 above, and the system comprises: a high-impact parameter acquisition module, an optimization parameter combination acquisition module, an anomaly detection module, a production optimization module and a cloud server; High-impact parameter acquisition module: Based on the production data of plant-based water purification ecological blocks in historical data and the corresponding block porosity data, combined with correlation analysis, the production control parameters of high-impact block porosity are obtained; Optimization parameter combination acquisition module: Based on the obtained production control parameters, a porosity model is established, and the particle swarm optimization algorithm is used to obtain the optimization control parameter combination ranking table; Abnormal detection module: During the production process of the plant-based water purification ecological building blocks, the porosity of the ecological building blocks is detected, and the porosity data is deeply analyzed to obtain the abnormal evaluation value, and the abnormal evaluation threshold is judged to identify and output the abnormal porosity signal; Production optimization module: Based on the abnormal porosity signal, combined with the optimization control parameter combination ranking table, the difficulty of production control parameter adjustment, and the porosity optimization degree, the production control parameters are optimized; Specifically, it includes: extracting the production control parameters corresponding to the abnormal signal of the control parameter generation, comparing them in the order of the optimized control parameter sorting table to obtain the overlap ratio value, and generating the sorting table to be optimized in combination with the overlap ratio value, calculating the optimization degree value and the mean of the number of steps for each sorted overlapping production control parameter, using the formula to calculate the adjustment judgment value, selecting the overlapping production control parameter combination corresponding to the maximum value for adjustment, and adjusting the overlapping production control parameters to the overlapping production control parameter standard values.

Images