A method and device for predicting the quality of cotton dyeing effluent and application thereof

Abstract

The application provides a cotton dyeing effluent water quality prediction method and device and application, belongs to the printing and dyeing technical field, can predict the cotton dyeing effluent water quality, obtains effluent water quality parameters of multiple sections of the cotton dyeing process to be operated in a future period of time, so that the cotton dyeing effluent can be classified and treated, the requirements of each process link on the water quality of recycled water are met, the treatment efficiency of the cotton dyeing process effluent is improved, and the recycling cost is reduced. The method inputs process parameters and dye parameters of the cotton dyeing process to be operated into an effluent water quality prediction model, and the effluent water quality prediction model outputs effluent water quality parameters of the cotton dyeing process to be operated.

Description

Technical Field

[0001] This invention relates to the field of dyeing and printing technology, and in particular to a method, apparatus and application for predicting the quality of effluent from cotton dyeing. Background Technology

[0002] The printing and dyeing industry is a typical industry with high pollution discharge and high water consumption. Among them, cotton dyeing process is the most important production unit and pollution discharge unit in the printing and dyeing industry.

[0003] The cotton dyeing process can be divided into two stages: dyeing and washing. In the dyeing stage, the woven cotton fabric and reactive dye solution are first placed into a dye bath. Heating promotes the diffusion of the reactive dye. Once a suitable temperature is reached, a neutral electrolyte is added to promote the adsorption of the reactive dye by the fibers. After a certain time, an alkali is added to promote the covalent bonding of the reactive dye with the cotton fibers, and the reaction continues until the set time. In the washing stage, a first wash, a soap wash, and a second wash are performed sequentially to remove residual chemicals. The wastewater generated in the dyeing stage is called dyeing wastewater, which contains some residual reactive dyes and neutral electrolytes, and is difficult to effectively degrade using conventional biochemical processes. The wastewater generated in the washing stage is called finishing wastewater, which has a lower pollutant load than dyeing wastewater. Both dyeing and finishing wastewater are considered effluent from the cotton dyeing process.

[0004] Existing treatment methods for the effluent from the cotton dyeing process include: a mixed-flow treatment method that mixes dyeing wastewater and finishing wastewater for unified treatment, and then reuses a portion of the treated wastewater; and an empirically-based classification and reuse method that separates dyeing wastewater and finishing wastewater into clear wastewater and turbid wastewater for separate treatment, reusing the treated clear wastewater. However, in actual production, the requirements for the quality of reused water vary at different process stages. Existing treatment methods for cotton dyeing effluent are too simplistic and cannot meet the specific quality requirements of each process stage, necessitating further treatment. This results in low treatment efficiency and high reuse costs for the cotton dyeing effluent. Summary of the Invention

[0005] This invention proposes a method, device, and application for predicting the effluent quality of cotton dyeing. It can predict the effluent quality of cotton dyeing and obtain the effluent quality parameters of multiple stages of the cotton dyeing process to be operated in the future. This facilitates the classification and treatment of cotton dyeing effluent to meet the requirements of each process stage for reclaimed water quality, improves the treatment efficiency of cotton dyeing process effluent, and reduces reuse costs.

[0006] To achieve the above objectives, the present invention adopts the following technical solution:

[0007] In a first aspect, the present invention provides a method for predicting the effluent quality of cotton dyeing, comprising: acquiring process parameters and dye parameters for multiple stages of a cotton dyeing process to be operated; the process parameters including dye dosage, salt dosage, and soda ash dosage; and the dye parameters including the topological polar surface area, octanol-water partition ratio, number of oxidizable atoms, and number of unsaturated bonds of the dye used in the cotton dyeing process to be operated. The process parameters and dye parameters for the multiple stages of the cotton dyeing process to be operated are input into an effluent quality prediction model. The effluent quality prediction model predicts the input process parameters and dye parameters of the cotton dyeing process to be operated, and outputs the effluent quality parameters for the multiple stages of the cotton dyeing process to be operated over a future period; the effluent quality parameters include chemical oxygen demand (COD) and conductivity.

[0008] The method for predicting the effluent quality of cotton dyeing provided by this invention uses the amount of dye, salt, and soda ash added as process parameters. The topological polarity surface area, octanol-water partition ratio, number of oxidizable atoms, and number of unsaturated bonds of the dye used in the cotton dyeing process to be operated are used as dye parameters. The process parameters and dye parameters are predicted using an effluent quality prediction model to obtain the effluent quality parameters for multiple stages of the cotton dyeing process to be operated within a certain period. This facilitates the classification and treatment of cotton dyeing effluent to meet the requirements of each process stage for reclaimed water quality, improves the treatment efficiency of cotton dyeing process effluent, and reduces reuse costs.

[0009] Secondly, this invention provides a device for predicting the effluent quality of cotton dyeing, comprising a parameter determination module, a parameter input module, and a prediction result output module. The parameter determination module is used to acquire the process parameters and dye parameters of the cotton dyeing process to be run. The process parameters include the amount of dye added, the amount of salt added, and the amount of soda ash added. The dye parameters include the topological polar surface area, octanol-water partition ratio, number of oxidizable atoms, and number of unsaturated bonds of the dye used in the cotton dyeing process to be run. The parameter input module is used to input the process parameters and dye parameters of the cotton dyeing process to be run into the effluent quality prediction model. The prediction result output module is used for the effluent quality prediction model to predict the effluent quality parameters of multiple stages of the cotton dyeing process to be run over a future period based on the input process parameters and dye parameters of the cotton dyeing process to be run; the effluent quality parameters include chemical oxygen demand (COD) and conductivity.

[0010] In one implementation of the second aspect, the prediction device further includes an optimization module. The optimization module is used to optimize the effluent water quality prediction model.

[0011] In one implementation of the first and second aspects, the effluent water quality prediction model is constructed based on a random forest model.

[0012] In one implementation of the first and second aspects, the effluent water quality prediction model includes an input terminal, multiple decision trees connected to the input terminal via a root node, a combiner connected to the leaf nodes of the multiple decision trees, and an output terminal connected to the combiner.

[0013] In one implementation of the first and second aspects, the training process of the effluent water quality prediction model includes: obtaining a training set for the effluent water quality prediction model, the training set including: data samples and labels for the data samples, wherein the data samples include process parameters and dye parameters of multiple cotton dyeing processes, and the labels for the data samples include effluent water quality parameters of multiple sections of the multiple cotton dyeing processes corresponding to the process parameters and dye parameters of the multiple cotton dyeing processes. Multiple sub-training sets are constructed based on the training set, each sub-training set being used to train a decision tree. Multiple decision trees are constructed based on hyperparameters and the training set. Multiple decision trees are trained using the multiple sub-training sets. For each decision tree, the error between the output parameters of the decision tree and the corresponding effluent water quality parameter samples is minimized, allowing the decision tree to be further expanded until the decision tree reaches a preset stopping condition, thus obtaining the effluent water quality prediction model.

[0014] In one implementation of the first and second aspects, the hyperparameters include the number of decision trees, the maximum tree depth, and the minimum number of samples per leaf node; the preset stopping conditions include the decision tree reaching its maximum depth, the decision tree reaching its maximum number of features, the decision tree reaching its maximum number of leaf nodes, the decision tree reaching its minimum leaf node impurity, and / or the decision tree reaching its minimum sample weight.

[0015] In one implementation of the first and second aspects, the training process of the effluent water quality prediction model also includes: optimizing the hyperparameters using a grid search method.

[0016] In one implementation of the first and second aspects, each point in the hyperparameter grid corresponds to a set of hyperparameters for the effluent water quality prediction model.

[0017] In one implementation of the first and second aspects, the process parameters also include the bath ratio, cloth weight, water volume, reaction temperature, and heat preservation time.

[0018] Thirdly, the present invention provides an electronic device including a processor and a memory coupled to the processor; the memory is used to store computer instructions, and when the electronic device is running, the processor executes the computer instructions stored in the memory to cause the electronic device to perform the method as described in the first aspect above or any implementation thereof.

[0019] Fourthly, the present invention provides a computer-readable storage medium including computer program instructions that, when executed by a computer, cause the computer to perform the method as described in the first aspect above or any implementation thereof.

[0020] Fifthly, the present invention provides a computer program product, including computer program instructions, which, when executed on a computer, cause the computer to perform the method as described in the first aspect above or any of its implementations.

[0021] Sixthly, the present invention provides an application of a method for predicting the quality of effluent from cotton dyeing. Based on the above-mentioned method for predicting the quality of effluent from cotton dyeing, the method is characterized in that, based on the prediction results of the effluent quality prediction model, the effluent from multiple stages of the cotton dyeing process is classified, treated, and reused.

[0022] The technical effects of the second to sixth aspects and their possible implementations can be referred to the above description of the technical effects of the first aspect and its possible implementations, and will not be repeated here. Attached Figure Description

[0023] Figure 1 This is one of the schematic diagrams of a method for predicting the effluent quality of cotton dyeing provided in the embodiments of this application;

[0024] Figure 2 This is a schematic diagram of the effluent water quality prediction model provided in the embodiments of this application;

[0025] Figure 3 This is a second schematic diagram of a method for predicting the effluent quality of cotton dyeing provided in the embodiments of this application;

[0026] Figure 4 This is one of the structural schematic diagrams of a device for measuring the effluent quality of cotton dyeing provided in the embodiments of this application;

[0027] Figure 5 This is the second schematic diagram of a device for measuring the quality of water from cotton dyeing, provided in an embodiment of this application. Detailed Implementation

[0028] In the specification and claims of this invention, the terms "first" and "second," etc., are used to distinguish different objects, rather than to describe a specific order of objects.

[0029] In the embodiments of this application, "and / or" indicates a relationship between objects. For example, A and / or B can represent the following three situations: A exists alone, B exists alone, and A and B exist simultaneously.

[0030] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0031] In the description of this invention, unless otherwise stated, "multiple" means two or more. For example, multiple decision trees means two or more decision trees.

[0032] The method and apparatus provided in this application relate to the prediction of effluent water quality in cotton dyeing. Specifically, an effluent water quality prediction model is used to predict the effluent water quality parameters of multiple sections of the cotton dyeing process to be operated within a certain period of time, based on the process parameters and dye parameters of the cotton dyeing process to be operated.

[0033] To address the shortcomings of existing cotton dyeing effluent treatment methods, which offer simplistic classification and fail to meet the water quality requirements of various process stages, necessitating further treatment and resulting in low treatment efficiency and high reuse costs, this application provides a method, apparatus, and application for predicting cotton dyeing effluent quality. The method uses dye dosage, salt dosage, and soda ash dosage as process parameters, and the dye parameters (topological polarity surface area, octanol-water partition ratio, number of oxidizable atoms, and number of unsaturated bonds) as dye parameters for the cotton dyeing process to be operated. By using an effluent quality prediction model to predict the process and dye parameters, the effluent quality parameters for multiple stages of the cotton dyeing process to be operated within a future period are obtained. This facilitates the classification and treatment of cotton dyeing effluent to meet the water quality requirements of each process stage, thereby improving the treatment efficiency of cotton dyeing effluent and reducing reuse costs.

[0034] For example, the method for predicting the quality of cotton dyeing effluent provided in this embodiment of the invention can be executed by an electronic device with processing capabilities, such as a computer or server. Taking a computer as an example, the hardware components of the computer may include: a processor, memory, a network interface, a user interface, a communication bus, etc.

[0035] The processor controls the electronic equipment to perform related processing and calculation tasks, such as acquiring process parameters and dye parameters, and predicting effluent quality parameters using an effluent quality prediction model. The processor may include a central processing unit (CPU) or other processors, and may be single-core or multi-core; for example, a processor may include multiple CPUs.

[0036] The memory is used to store computer instructions and related data, such as process parameters, dye parameters, effluent quality prediction models, and effluent quality parameters. The memory can be random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical storage, disk storage media, or other magnetic storage devices, or any other medium capable of storing program code or data accessible by a computer. Optionally, the memory can be integrated into the processor, or it can be independent of the processor.

[0037] A network interface is used for communication between a computer and other devices or communication networks. A network interface can be a transceiver with transmit and receive capabilities. Optionally, a network interface may include standard wired interfaces or wireless interfaces (such as Wi-Fi interfaces, Bluetooth interfaces, and 5G interfaces).

[0038] The communication bus is used to enable communication between different components. For example, the processor, memory, network interface and user interface mentioned above can be interconnected through the communication bus.

[0039] The user interface may include a display screen and an input unit (such as a keyboard). Optionally, the user interface may also include a standard wired interface or a wireless interface.

[0040] Those skilled in the art will understand that the computer described above may include more or fewer components, or combine certain components, or have different component arrangements; the embodiments of this application do not limit this.

[0041] like Figure 1 As shown, the method for predicting the quality of cotton dyeing effluent provided in this application includes S101-S103.

[0042] S101. Obtain the process parameters and dye parameters of multiple sections of the cotton dyeing process to be run.

[0043] In this embodiment of the application, the above process parameters include the amount of dye added, the amount of salt added, and the amount of soda ash added. The dye parameters include the topological polar surface area, octanol-water partition ratio, number of oxidizable atoms, and number of unsaturated bonds of the dye used in the cotton dyeing process to be run.

[0044] In the process parameters, dye dosage refers to the amount of dye added to the dyeing medium during the cotton dyeing process; salt dosage refers to the amount of salts added to the dyeing medium during the cotton dyeing process; and soda ash dosage refers to the amount of soda ash (Na2CO3) added to the dyeing medium during the cotton dyeing process. The units for dye dosage, salt dosage, and soda ash dosage are usually mass or volume.

[0045] In some cases, reactive dyes may be included, such as Reactive Yellow K-6G (Chemical Abstracts Service Number, CAS No. 50662-99-2), Reactive Red 195 (CAS No. 93050-79-4), and Reactive Yellow 145 (CAS No. 93050-80-7). Salts may include sodium chloride or sodium sulfate.

[0046] In the dye parameters,

[0047] Topological polar surface area (TPSA) is a parameter used in computational chemistry to characterize molecular polarity. TPSA represents the total surface area of ​​polar regions within a molecule.

[0048] Octanol-Water Partition Ratio (OWR) refers to the ratio of the concentration of a substance in the octanol phase to the concentration in the aqueous phase when equilibrium is reached under specific conditions. OWR is an important chemical parameter used to describe the hydrophobicity or hydrophilicity of a substance and its distribution behavior in the environment.

[0049] The number of oxidizable atoms refers to the number of atoms in a molecule that can participate in redox reactions;

[0050] The number of unsaturated bonds refers to the total number of chemical bonds in an organic molecule that do not contain single bonds. The number of unsaturated bonds is an important parameter for measuring the number of multiple bonds and rings in a molecule, reflecting its structural characteristics and potential reactivity.

[0051] Optionally, the process parameters also include the liquor ratio, cloth weight, water volume, reaction temperature, and heat preservation time.

[0052] Among them, the liquor ratio refers to the ratio of the mass of the material being dyed to the mass of the dye liquor prepared during immersion or exhaustion dyeing; the fabric weight refers to the weight in grams (g / m²) of cotton fabric per square meter after dyeing. 2 ).

[0053] In some application scenarios, the cotton dyeing process to be run includes multiple stages: feeding stage (adding cotton fiber fabric and reactive dye into the dyeing vat), heating stage (heating the dyeing vat to promote dye diffusion), salting stage (adding neutral electrolyte to promote dye adsorption), alkaliing stage (adding alkali to promote covalent bonding between dye and cotton fiber), drainage stage (discharging dyeing wastewater), and washing / soaping stage (discharging washing wastewater).

[0054] S102. Input the process parameters and dye parameters of multiple sections of the cotton dyeing process to be run into the effluent water quality prediction model.

[0055] In this embodiment of the application, the above-mentioned effluent water quality prediction model is constructed based on the random forest model.

[0056] refer to Figure 2 The effluent water quality prediction model includes an input terminal, multiple decision trees connected to the root node and the input terminal, a combiner connected to the leaf nodes of the multiple decision trees, and an output terminal connected to the combiner.

[0057] Continue to refer to Figure 2 The structure of a decision tree includes: a root node (the starting point of the decision tree, containing all samples to be classified), internal nodes connected to the root node (also called split nodes, used to divide samples according to feature values, each internal node corresponding to a feature), branches connecting two nodes (representing the corresponding feature values), and leaf nodes (the terminating node of the decision tree, representing the prediction result of the decision tree).

[0058] In one implementation, the training process of the effluent water quality prediction model includes:

[0059] S1. Obtain the training set of the effluent water quality prediction model. The training set includes: data samples and labels of the data samples. The data samples include process parameters and dye parameters of multiple cotton dyeing processes. The labels of the data samples include effluent water quality parameters of multiple sections of multiple cotton dyeing processes corresponding to the process parameters and dye parameters of the multiple cotton dyeing processes.

[0060] It is understandable that the effluent water quality parameter samples of the multiple sections of the above-mentioned multiple sets of cotton dyeing processes, as well as the process parameters and dye parameters of the cotton dyeing process corresponding to the effluent water quality parameter samples of the multiple sections of the multiple sets of cotton dyeing processes, are derived from historical data of the multiple sections of the cotton dyeing process.

[0061] S2. Construct multiple sub-training sets based on the training set. Each sub-training set in the multiple sub-training sets is used to train a decision tree.

[0062] The aforementioned sub-training sets can be obtained by performing bootstrap sampling on the training set. Bootstrap sampling refers to sampling with replacement. It can be understood that each data sample in the sub-training set corresponds to a set of process parameters and dye parameters for a cotton dyeing process, and the labels of the data samples correspond to the effluent water quality parameters of multiple stages in a cotton dyeing process.

[0063] S3. Construct multiple decision trees based on hyperparameters, process parameters in the training set, and dye parameters.

[0064] In the above process, hyperparameters may include the number of decision trees, the maximum tree depth, and the minimum number of samples per leaf node.

[0065] For example, the splitting criterion mentioned above can be information gain or Gini impurity, etc.; the termination condition mentioned above can be that the decision tree reaches a set depth, or that the number of nodes in the decision tree reaches the minimum number of samples per node.

[0066] Optionally, the above termination conditions may also be that the decision tree reaches the maximum number of features, the decision tree reaches the maximum number of leaf nodes, the decision tree reaches the minimum impurity of leaf nodes, and / or the decision tree reaches the minimum sample weight.

[0067] S4. Train multiple decision trees using multiple sub-training sets. For each decision tree, minimize the error between the output parameters of the decision tree and the corresponding effluent water quality parameter samples to further expand the decision tree until it reaches the preset stopping condition, thus obtaining the effluent water quality prediction model.

[0068] The process of constructing and training a decision tree is as follows.

[0069] 1. Initialize the tree structure

[0070] Initialize the root node of the decision tree. The root node includes all training data samples and their labels in the sub-training set.

[0071] 2. Select the optimal split point

[0072] Calculate the split point: For all features of the current node, calculate the split criterion value corresponding to the possible split points, such as the mean squared error (MSE) value (the mean squared error between the actual label values ​​of all samples in the split child nodes and the average label value of the current node). Each split point is a threshold value for a feature, dividing the data samples of the current node into two parts. For each possible split point, calculate the MSE of the two child nodes after the split, and then take the weighted average. Select the split point that minimizes the weighted average MSE value as the split point of the current node.

[0073] 3. Perform a split

[0074] Based on the selected optimal split point, the data of the current node is divided into two subsets, and a new child node is created for each subset.

[0075] 4. Recursive splitting

[0076] Repeat the above steps for each newly created child node until the stopping condition is met.

[0077] 5. Generate the final decision tree

[0078] The training process of the decision tree ends when all nodes meet the stopping condition, generating the final decision tree. This model consists of individual nodes and their split points. Each leaf node contains the average label value of the training samples within that node, which is the predicted value of that leaf node.

[0079] During the training of multiple decision trees using multiple sub-training sets, each decision tree can randomly select different subsets of input features (i.e., input features selected from process parameters and dye parameters). When each decision tree performs node splitting, it selects features from the corresponding feature subset as the splitting point and calculates the splitting criterion value. This enhances the model's generalization ability.

[0080] Optionally, the preset stopping condition in S4 can be that the depth of the decision tree reaches the maximum depth of the tree.

[0081] In one application scenario, the training process of the effluent water quality prediction model also includes optimizing the hyperparameters using a grid search method.

[0082] Specifically, multiple sets of hyperparameters are selected, and a hyperparameter grid is constructed based on these sets of hyperparameters. Each point in the hyperparameter grid corresponds to a set of hyperparameters for the effluent water quality prediction model. The hyperparameters include the number of decision trees, the maximum tree depth, and the minimum number of samples per leaf node.

[0083] Furthermore, based on multiple sets of hyperparameters corresponding to multiple points in the hyperparameter grid, multiple models are constructed and trained, and the hyperparameters of the model with the best prediction performance are taken as the optimal hyperparameters.

[0084] Optionally, the above-mentioned effluent water quality prediction model can also be constructed based on the extreme gradient boosting model, or it can be constructed using neural network algorithms, such as Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), and Fully Connected Neural Network.

[0085] S103, the effluent water quality prediction model predicts the process parameters and dye parameters of the cotton dyeing process to be run, and outputs the effluent water quality parameters of multiple sections of the cotton dyeing process to be run in the future.

[0086] Among them, the effluent water quality parameters include chemical oxygen demand and electrical conductivity.

[0087] In this embodiment, after the process parameters and dye parameters of the cotton dyeing process to be run are input into the effluent water quality prediction model, the input process parameters and dye parameters are entered into multiple decision trees of the effluent water quality prediction model through the input terminal. The output results of the leaf nodes of the multiple decision trees are input to the connector. After the connector processes the output results of the multiple decision trees, it outputs the prediction result of the effluent water quality prediction model through the output terminal.

[0088] In one implementation, the combiner processes the outputs of multiple decision trees using a weighted average method, where the average method satisfies the following formula:

[0089]

[0090] In the above formula, H (x) The output of the combiner is given by T, where T is the number of decision trees and w is the number of trees. i h represents the weighting coefficients for the i-th decision tree. i (x) represents the output of the i-th decision tree.

[0091] It should be noted that the chemical oxygen demand (COD) in the effluent water quality prediction model is strongly correlated with the dye parameters input into the effluent water quality prediction model.

[0092] Specifically, the COD (Chemical Oxygen Demand) in the effluent from cotton dyeing processes mainly originates from residual reactive dyes. Different types of reactive dyes, due to variations in topological polarity surface area, octanol-water partition ratio, number of oxidizable atoms, and number of unsaturated bonds (i.e., dye parameters), will produce different COD concentrations even at the same concentration. Therefore, using these dye parameters to predict the COD in the effluent water quality parameters is quite effective.

[0093] Furthermore, the conductivity among the aforementioned effluent water quality parameters is strongly correlated with the process parameters input into the effluent water quality prediction model.

[0094] Specifically, conductivity is strongly correlated with the amount of salt added in multiple stages of the cotton dyeing process. The higher the amount of dye, salt, and soda ash added (i.e., the process parameters), the higher the conductivity. Therefore, the conductivity of effluent water quality parameters can be well predicted using the above process parameters.

[0095] As is understandable, COD refers to the amount of oxidant consumed when treating a water sample with a certain strong oxidant under specific conditions. It is an indicator of the amount of reducing substances in water. The higher the COD value of wastewater, the more severe the water pollution. The COD of the effluent from the cotton dyeing process can reflect the degree of water pollution. The conductivity of the effluent from the cotton dyeing process is a measure of the ion migration capacity in water, reflecting the content of inorganic salts and other soluble substances. Therefore, the effluent quality parameters of the effluent quality prediction model can effectively reflect the pollution status of the effluent from the cotton dyeing process.

[0096] In summary, if the effluent quality prediction model can predict the effluent quality parameters well through dye parameters and process parameters, and the effluent quality parameters can well reflect the pollution status of the effluent from the cotton dyeing process, then the effluent quality prediction model can predict the effluent quality of the cotton dyeing process effectively.

[0097] In the prediction method provided in this application, the dye dosage, salt dosage, and soda ash dosage are used as process parameters. The topological polar surface area, octanol-water partition ratio, number of oxidizable atoms, and number of unsaturated bonds of the dye used in the cotton dyeing process to be operated are used as dye parameters. The process parameters and dye parameters are predicted using an effluent quality prediction model to obtain the effluent quality parameters for multiple stages of the cotton dyeing process to be operated within a future period. This facilitates the classification and treatment of cotton dyeing effluent to meet the requirements of each process stage for reclaimed water quality, improves the treatment efficiency of cotton dyeing process effluent, and reduces reuse costs.

[0098] In some application scenarios, combined with Figure 1 ,like Figure 3 As shown, the method for predicting the effluent quality of cotton dyeing provided in this application embodiment further includes: S104, optimizing the effluent quality prediction model.

[0099] Optionally, historical data with low prediction accuracy of the effluent water quality prediction model can be obtained and used to form a new training set. A new decision tree can then be built and trained based on the new training set.

[0100] The above process not only improves the prediction accuracy under new process scenarios, but also maintains the understanding of old process scenarios, enabling the model to continuously self-optimize.

[0101] Accordingly, this application provides an application of the above-mentioned method for predicting the effluent quality of cotton dyeing. Based on the prediction results of the effluent quality prediction model, the effluent from multiple stages of the cotton dyeing process is classified, treated, and reused.

[0102] The application of the above-mentioned method for predicting the quality of effluent from cotton dyeing is described in detail below.

[0103] Based on the prediction results of the effluent quality prediction model obtained from the cotton dyeing effluent quality prediction method and the water demand of the target reuse section, the effluent from multiple sections of the cotton dyeing process to be operated is classified into four levels as shown in the table below.

[0104] Table 1. Classification of Effluent

[0105] Wastewater Classification and Destination COD (mg / L) Electrical conductivity (μS / cm) Direct reuse ≤120 ≤6000 Simple processing and reuse ≤350 ≤12000 Deep processing reuse ≤1000 ≤25000 Treatment to meet emission standards ＞1000 ＞25000

[0106] After obtaining the classification results, treatment equipment is set up at the outlets of multiple work sections according to the classification results to realize the treatment and reuse of cotton dyeing effluent.

[0107] Understandably, during cotton dyeing, wastewater COD, conductivity, color, hardness, and iron / manganese ion concentration have a significant impact on product quality. Since no new hardness or iron / manganese ions are introduced during dyeing and wastewater treatment, the hardness and iron / manganese ion concentrations in each stage originate from the initial fresh water and do not affect wastewater reuse. Furthermore, after wastewater is treated separately, the dye molecules that produce the water's color are largely destroyed, thus only affecting direct reuse. In practice, only wastewater from the same batch of orders being dyed again, and lighter shades of the same color from the same process, are directly reused. This can be achieved through manual judgment.

[0108] Accordingly, embodiments of this application provide a device for predicting the quality of cotton dyeing effluent, such as... Figure 4 As shown, it includes a parameter determination module 501, a parameter input module 502, and a prediction result output module 503.

[0109] The parameter determination module 501 is used to obtain the process parameters and dye parameters of the cotton dyeing process to be run. The process parameters include the amount of dye added, the amount of salt added, and the amount of soda ash added. The dye parameters include the topological polar surface area, octanol-water partition ratio, number of oxidizable atoms, and number of unsaturated bonds of the dye used in the cotton dyeing process to be run. For example, the parameter determination module 501 is used to implement S101 of the above prediction method.

[0110] The parameter input module 502 is used to input the process parameters and dye parameters of the cotton dyeing process to be run into the effluent water quality prediction model. For example, the parameter input module 502 is used to implement S102 of the above prediction method.

[0111] The prediction result output module 503 is used by the effluent water quality prediction model to predict the process parameters and dye parameters of the cotton dyeing process to be operated, and output the effluent water quality parameters of multiple sections of the cotton dyeing process to be operated in the future; the effluent water quality parameters include chemical oxygen demand and conductivity. For example, the prediction result output module 503 is used to implement S103 of the above prediction method.

[0112] Optionally, combined Figure 4 ,like Figure 5 As shown, the prediction device further includes an optimization module 504. For example, the optimization module 504 is used to implement step S104 of the prediction method described above.

[0113] The optimization module 504 is used to optimize the effluent water quality prediction model.

[0114] Each module of the above-mentioned cotton dyeing effluent water quality prediction device can also be used to perform other steps in the above method embodiments. All relevant contents involved in the above method embodiments can be referred to the functional description of the corresponding functional module, and will not be repeated here.

[0115] This application also provides an electronic device, including: a processor and a memory coupled to the processor; the memory is used to store computer instructions, and when the electronic device is running, the processor executes the computer instructions stored in the memory to cause the electronic device to perform the methods described in the above embodiments. The processor can implement the parameter determination module 501, the parameter input module 502, and the prediction result output module 503; the memory can also be used to store process parameters, dye parameters, effluent water quality prediction models, and effluent water quality parameters, etc.

[0116] This application also provides a computer-readable storage medium including a computer program that, when run on a computer, performs the methods described in the above embodiments.

[0117] This application also provides a computer program product, which includes computer program instructions that, when run on a computer, execute the methods described in the above embodiments.

[0118] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0119] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method of predicting the effluent quality of cotton dyeing, characterized by, The method comprises the following steps: obtaining process parameters and dye parameters of multiple sections of a cotton dyeing process to be run, the process parameters comprising dye dosage, salt dosage and soda dosage, and the dye parameters comprising topological polarity surface area, octanol-water partition ratio, oxidizable atom number and unsaturated bond number of a dye used in the cotton dyeing process to be run; inputting the process parameters and dye parameters of the multiple sections of the cotton dyeing process to be run into an effluent water quality prediction model; the effluent water quality prediction model predicts the input process parameters and dye parameters of the cotton dyeing process to be run, and outputs effluent water quality parameters of the multiple sections of the cotton dyeing process to be run in a future period of time; the effluent water quality parameters comprise chemical oxygen demand and conductivity.

2. The method of claim 1, wherein, The effluent water quality prediction model is constructed based on a random forest model.

3. The method of claim 2, wherein, The effluent water quality prediction model comprises an input end, multiple decision trees connected to the input end, a combiner connected to leaf nodes of the multiple decision trees, and an output end connected to the combiner.

4. The method of claim 1 or 3, wherein, The training process of the effluent water quality prediction model comprises the following steps: obtaining a training set of the effluent water quality prediction model, the training set comprising data samples and labels of the data samples, wherein the data samples comprise multiple groups of process parameters and dye parameters of cotton dyeing processes, and the labels of the data samples comprise multiple groups of effluent water quality parameters of multiple sections of the multiple groups of cotton dyeing processes corresponding to the process parameters and dye parameters of the multiple groups of cotton dyeing processes; constructing multiple sub-training sets based on the training set, each of the multiple sub-training sets being used for training a decision tree; constructing multiple decision trees based on hyperparameters and the training set; training the multiple decision trees through the multiple sub-training sets, for each of the multiple decision trees, minimizing errors between an output parameter of the decision tree and a corresponding effluent water quality parameter sample of the decision tree, so that the decision tree is further expanded until the decision tree reaches a preset stopping condition, and the effluent water quality prediction model is obtained.

5. The method of claim 4, wherein, The hyperparameters comprise a number of decision trees, a maximum depth of a tree and a minimum number of leaf nodes; and the preset stopping condition comprises that a depth of a decision tree reaches a maximum depth of a tree, the decision tree reaches a maximum number of features, the decision tree reaches a maximum number of leaf nodes, the decision tree reaches a minimum impurity of a leaf node and / or the decision tree reaches a minimum sample weight.

6. The method of claim 4, wherein, The training process of the effluent water quality prediction model further comprises: optimizing the hyperparameters through a grid search method.

7. The method of claim 6, wherein, Each point in a hyperparameter grid corresponds to a group of hyperparameters of the effluent water quality prediction model.

8. The method of claim 1, wherein, The process parameters further comprise bath ratio, fabric weight, water quantity, reaction temperature and holding time.

9. A device for predicting the effluent quality of cotton dyeing, characterized by, The method comprises a parameter determination module, a parameter input module and a prediction result output module. The parameter determination module is configured to obtain process parameters and dye parameters of a cotton dyeing process to be run, the process parameters comprising dye dosage, salt dosage and soda dosage, and the dye parameters comprising topological polarity surface area, octanol-water partition ratio, oxidizable atom number and unsaturated bond number of a dye used in the cotton dyeing process to be run; The parameter input module is configured to input process parameters of a cotton dyeing process to be run and dye parameters into the effluent water quality prediction model. The prediction result output module is configured to cause the effluent water quality prediction model to predict the input process parameters of the cotton dyeing process to be run and the dye parameters, and output effluent water quality parameters of multiple sections of the cotton dyeing process to be run in a future period of time; the effluent water quality parameters include chemical oxygen demand and conductivity.

10. Use of a method for the prediction of the effluent quality of a cotton dyeing process, based on the method according to any one of claims 1 to 8, characterized in that, Based on the prediction result of the effluent water quality prediction model, the effluent water of the multiple sections of the cotton dyeing process is classified and reused.

Images