An adaptive water purification method and apparatus

Abstract

The application discloses a kind of self-adapting water purification device and method, the device includes: environmental detection module, water quality monitoring module, filter module group, water purification module group and resource control module group;The water quality monitoring module is connected with the environmental detection module, for measuring water quality, obtain water quality parameter information set, the environmental monitoring data set and water quality parameter information set are evaluated and handled, obtain water purification demand information;The resource control module group is used to process the water purification demand information, obtain filter module switch instruction information and water purification module switch instruction information;Filter the raw water using the corresponding filter module of the electric switch;Open the water purification module switch instruction information corresponding electric switch, using the water purification module corresponding to the electric switch, the effluent of the filter module is purified.

Description

Technical Field

[0001] This invention relates to the fields of water purification technology, intelligent control and strategy optimization technology, and specifically to an adaptive water purification method and apparatus. Background Technology

[0002] As people's living standards improve, their requirements for drinking water quality are also increasing. Traditional water purification devices typically employ fixed filtration and purification processes, failing to adapt to varying water quality and environmental conditions. This fixed-mode approach to water purification presents the following technical problems:

[0003] First, traditional water purification devices cannot monitor the impact of environmental factors on water quality in real time. For example, changes in environmental parameters such as air pressure, temperature, and humidity can indirectly affect the water quality characteristics of the source water, but traditional water purification devices ignore these factors, resulting in the purification effect not reaching the optimal state.

[0004] Secondly, traditional water purification devices cannot flexibly adjust the combination and operating mode of filtration and purification modules when dealing with water of different pollution levels. They use the same treatment process for both high-turbidity and low-chlorine water, which may lead to low purification efficiency and wasted resources.

[0005] Furthermore, traditional water purification devices lack effective resource control mechanisms when multiple modules work together. Dynamic connection and switching between the filtration and purification modules are not possible, resulting in poor flexibility and adaptability of the entire water purification system.

[0006] Finally, traditional water purification devices are relatively simple in terms of data processing, and cannot classify, analyze, and accurately evaluate complex water quality data, making it difficult to dynamically adjust water purification strategies according to actual needs. Summary of the Invention

[0007] This invention primarily addresses the problem that traditional water purification devices are relatively simple in data processing, unable to classify, analyze, and accurately evaluate complex water quality data, and difficult to dynamically adjust water purification strategies according to actual needs. This invention discloses an adaptive water purification method and device.

[0008] In a first aspect, the present invention discloses an adaptive water purification device, comprising: an environmental detection module, a water quality monitoring module, a filtration module group, a water purification module group, and a resource control module group;

[0009] The environmental monitoring module is used to collect environmental monitoring datasets; the environmental monitoring datasets include air pressure sequences, PM2.5 content sequences, temperature sequences, humidity sequences, and oxygen content sequences.

[0010] The water quality monitoring module is connected to the environmental detection module and is used to measure water quality, obtain a set of water quality parameter information, evaluate and process the environmental monitoring dataset and the set of water quality parameter information to obtain water purification demand information; the set of water quality parameter information includes pH value sequence, dissolved oxygen value sequence, turbidity value sequence, conductivity value sequence and residual chlorine content sequence;

[0011] The filter module group includes several types of filter modules and an electric switch connected to each filter module;

[0012] The water purification module group includes several types of water purification modules and an electric switch connected to each water purification module;

[0013] The resource control module group is connected to the water quality monitoring module, the filtration module group, and the water purification module group, respectively. It processes the water purification demand information to obtain filtration module switch command information and water purification module switch command information. Based on the filtration module switch command information, it turns on the corresponding electric switch, using the filtration module corresponding to the electric switch to filter the raw water. Based on the water purification module switch command information, it turns on the corresponding electric switch, using the water purification module corresponding to the electric switch to purify the water output from the filtration module.

[0014] The water quality monitoring module includes a pH sensor, a dissolved oxygen sensor, a turbidity sensor, a conductivity sensor, a residual chlorine sensor, and a data processing submodule.

[0015] The pH sensor, dissolved oxygen sensor, turbidity sensor, conductivity sensor, and residual chlorine sensor are used to collect pH value sequences, dissolved oxygen value sequences, turbidity value sequences, conductivity value sequences, and residual chlorine content sequences, respectively.

[0016] The data processing submodule is used to evaluate and process the environmental monitoring dataset and water quality parameter information set to obtain water purification demand information.

[0017] A second aspect of this invention discloses an adaptive water purification method, implemented using the aforementioned adaptive water purification device, comprising:

[0018] S1, using the environmental detection module, an environmental monitoring dataset is collected;

[0019] S2, using the water quality monitoring module, the water quality is measured to obtain a set of water quality parameter information. The environmental monitoring dataset and the set of water quality parameter information are evaluated and processed to obtain water purification demand information.

[0020] S3, using the resource control module group, the water purification demand information is processed to obtain filter module switch command information and water purification module switch command information;

[0021] S4, according to the filter module switch instruction information, turn on the electric switch corresponding to the filter module switch instruction information, and use the filter module corresponding to the electric switch to filter the raw water; according to the water purification module switch instruction information, turn on the electric switch corresponding to the water purification module switch instruction information, and use the water purification module corresponding to the electric switch to purify the water output from the filter module.

[0022] The process of evaluating and processing the environmental monitoring dataset and water quality parameter information set to obtain clean water demand information includes:

[0023] S21, perform classification analysis on the environmental monitoring dataset and water quality parameter information set to obtain water quality datasets of each type;

[0024] S22, evaluate and process each type of water quality dataset to obtain an evaluation sub-value for each type;

[0025] S23, each type of evaluation sub-value is used as a demand component to construct water purification demand information; the categories of the demand components include filtration demand components and water purification demand components.

[0026] The environmental monitoring dataset and water quality parameter information set are classified and analyzed to obtain water quality datasets of each type, including:

[0027] S211, represent all sequences in the environmental monitoring dataset as a first matrix; the row vectors of the first matrix include air pressure sequence, PM2.5 content sequence, temperature sequence, humidity sequence, and oxygen content sequence;

[0028] S212, normalize each row vector of the first matrix;

[0029] S213, using all column vectors of the first matrix as variables to be classified, perform classification processing on the variables to be classified to obtain type information and the column vectors contained in each type;

[0030] S214, For all column vectors of the same type, perform classification matrix estimation and boundary estimation respectively to obtain the intermediate matrix and edge quantity corresponding to the type;

[0031] S215, using all types of intermediate matrices and marginal quantities, a water quality classification model is constructed;

[0032] S216. Using a water quality classification model, the water quality parameter information set is processed to obtain water quality datasets for each type.

[0033] The expression for the classification matrix estimation is:

[0034]

[0035] Among them, a i,kj β is the j-th element of the k-th column vector contained in the i-th type. ij Let ω1 and ω2 be the elements in the i-th row and j-th column of the intermediate matrix, respectively, where ω1 and ω2 are the preset first and second weighting factors, P is the number of types, and K is the total number of vectors contained in a type. Let be the mean of the k-th column vector contained in the i-th type. The mean of the j-th element of all column vectors of type i;

[0036] The expression for the boundary estimation is:

[0037]

[0038] Where J is the number of elements in a column vector, δ i μ is the largest eigenvalue of the type matrix constructed from all column vectors contained in the i-th type. i,kj The j-th element of the k-th eigenvector of the type matrix constructed from all column vectors contained in the i-th type, γ i Let be the edge quantity of the i-th type; the column vector of the type matrix is ​​all the column vectors contained in a type.

[0039] The discriminant expression for the i-th type of the water quality classification model is:

[0040]

[0041] Where, φ j Let J be the j-th element of the water quality parameter vector to be classified, where J is the number of elements in the water quality parameter vector; the water quality parameter vector is constructed using the collected values ​​of all sequences in the water quality parameter information set at the same time.

[0042] The evaluation process for each type of water quality dataset yields an evaluation sub-value for each type, including:

[0043] S221, obtain the standard values ​​of pH, dissolved oxygen, turbidity, conductivity, and residual chlorine content;

[0044] S222, for each type of water quality dataset, subtract the corresponding standard value from each element of the water quality parameter vector, and use all the subtraction results for each type to construct the difference vector of that type;

[0045] S223, perform a fusion evaluation calculation on all difference vectors for each type to obtain the evaluation sub-value for each type;

[0046] The expression for the fusion evaluation calculation is as follows:

[0047]

[0048] Where pgr is an evaluator of a type. and z represents the i-th element of the first characteristic vector and the second characteristic vector, respectively. ij Let N be the j-th element of the i-th difference vector of a type, N be the number of elements in the difference vector, and M be the number of difference vectors contained in a type.

[0049] A third aspect of the present invention discloses an adaptive water purification device, the device comprising:

[0050] Memory containing executable program code;

[0051] A processor coupled to the memory;

[0052] The processor calls the executable program code stored in the memory to execute the adaptive water purification method.

[0053] In a fourth aspect of this invention, a computer-storeable medium is disclosed, the computer-storeable medium storing computer instructions, which, when invoked by a computer, are used to execute the adaptive water purification method.

[0054] In a fifth aspect of this invention, an information data processing terminal is disclosed, which is used to implement the adaptive water purification method described above.

[0055] The beneficial effects of this invention are as follows:

[0056] This invention provides an adaptive water purification device that, through the coordinated operation of an environmental detection module and a water quality monitoring module, can collect real-time environmental monitoring data such as air pressure, PM2.5 content, temperature, humidity, and oxygen content, as well as water quality parameters such as pH value, dissolved oxygen, turbidity, conductivity, and residual chlorine content. This comprehensive monitoring method allows the water purification device to fully understand the impact of the external environment on water quality, thereby providing data support for accurate assessment of water purification needs.

[0057] This invention classifies, analyzes, and evaluates environmental monitoring data and water quality parameters through a data processing submodule, constructing a water quality classification model. Based on the water purification demand information output by the model, it dynamically adjusts the operating status of the filtration and purification modules. This adaptive processing method can flexibly select appropriate combinations of filtration and purification modules according to different water quality conditions, improving water purification efficiency and resource utilization.

[0058] The filter module group and water purification module group of this invention are connected to the resource control module group via branch switches, realizing dynamic connection and switching between modules. The flexible and controllable switching design of the filter module group and water purification module group ensures the stability and reliability of the entire water purification system, while improving the system's flexibility and adaptability. This modular design not only facilitates maintenance and upgrades but also allows for flexible expansion of system functions according to actual needs. Attached Figure Description

[0059] Figure 1 This is a flowchart illustrating the implementation of the method of the present invention;

[0060] Figure 2 This is a diagram showing the composition of the device of the present invention. Detailed Implementation

[0061] To better understand the content of this invention, an embodiment is provided here.

[0062] Figure 1 This is a flowchart illustrating the implementation of the method of the present invention. Figure 2 This is a diagram showing the composition of the device of the present invention.

[0063] In a first aspect, the present invention discloses an adaptive water purification device, comprising: an environmental detection module, a water quality monitoring module, a filtration module group, a water purification module group, and a resource control module group;

[0064] The environmental monitoring module is used to collect environmental monitoring datasets; the environmental monitoring datasets include air pressure sequences, PM2.5 content sequences, temperature sequences, humidity sequences, and oxygen content sequences.

[0065] The water quality monitoring module is connected to the environmental detection module and is used to measure water quality, obtain a set of water quality parameter information, evaluate and process the environmental monitoring dataset and the set of water quality parameter information to obtain water purification demand information; the set of water quality parameter information includes pH value sequence, dissolved oxygen value sequence, turbidity value sequence, conductivity value sequence and residual chlorine content sequence;

[0066] The filter module group includes several types of filter modules and an electric switch connected to each filter module;

[0067] The water purification module group includes several types of water purification modules and an electric switch connected to each water purification module;

[0068] The resource control module group is connected to the water quality monitoring module, the filtration module group, and the water purification module group respectively. It is used to process the water purification demand information to obtain filtration module switch command information and water purification module switch command information. Based on the filtration module switch command information, it turns on the corresponding electric switch, using the filtration module corresponding to the electric switch to filter the raw water. Based on the water purification module switch command information, it turns on the corresponding electric switch, using the water purification module corresponding to the electric switch to purify the water output from the filtration module.

[0069] The filter module group is connected to the water purification module group. Specifically, the filter module group and the water purification module are connected through a branch switch; the branch switch is kept in a connected state; the electric switch connected to each filter module is connected to the branch switch, and the electric switch connected to each water purification module is connected to the branch switch.

[0070] The water quality monitoring module includes a pH sensor, a dissolved oxygen sensor, a turbidity sensor, a conductivity sensor, a residual chlorine sensor, and a data processing submodule.

[0071] The pH sensor, dissolved oxygen sensor, turbidity sensor, conductivity sensor, and residual chlorine sensor are used to collect pH value sequences, dissolved oxygen value sequences, turbidity value sequences, conductivity value sequences, and residual chlorine content sequences, respectively.

[0072] The data processing submodule is used to evaluate and process the environmental monitoring dataset and water quality parameter information set to obtain water purification demand information.

[0073] The data processing submodule evaluates and processes the environmental monitoring dataset and water quality parameter information set to obtain water purification demand information, including:

[0074] The data processing submodule performs classification analysis on the environmental monitoring dataset and the water quality parameter information set to obtain water quality datasets of each type.

[0075] Each type of water quality dataset is evaluated to obtain an evaluation sub-value for each type.

[0076] Each type of evaluation sub-value is used as a demand component to construct water purification demand information; the categories of the demand components include filtration demand components and water purification demand components.

[0077] The environmental monitoring dataset and water quality parameter information set are classified and analyzed to obtain water quality datasets of each type, including:

[0078] All sequences in the environmental monitoring dataset are represented as a first matrix; the row vectors of the first matrix include air pressure sequence, PM2.5 content sequence, temperature sequence, humidity sequence, and oxygen content sequence.

[0079] For each row vector of the first matrix, normalization is performed separately;

[0080] Using all column vectors of the first matrix as variables to be classified, classify the variables to be classified to obtain type information and the column vectors contained in each type;

[0081] For all column vectors of the same type, perform classification matrix estimation and boundary estimation respectively to obtain the intermediate matrix and edge quantity corresponding to the type;

[0082] A water quality classification model is constructed using all types of intermediate matrices and marginal quantities;

[0083] By using a water quality classification model, the set of water quality parameter information is processed to obtain water quality datasets for each type.

[0084] The normalization process involves dividing each element in the vector by the maximum value of the elements in the vector.

[0085] The expression for the classification matrix estimation is:

[0086]

[0087] Among them, a i,kj β is the j-th element of the k-th column vector contained in the i-th type. ij Let ω1 and ω2 be the elements in the i-th row and j-th column of the intermediate matrix, respectively, where ω1 and ω2 are the preset first and second weighting factors, P is the number of types, and K is the total number of vectors contained in a type. Let be the mean of the k-th column vector contained in the i-th type. It is the mean of the j-th element of all column vectors of type i.

[0088] The expression for estimating the classification matrix comprehensively considers the logarithmic proportions and sinusoidal variation characteristics of the data. Logarithmic operations effectively highlight the relative differences between data points and capture the details of data changes; the sinusoidal function further explores the periodic or fluctuating characteristics of the data. This allows for a more comprehensive and detailed description of the characteristics of different types of water quality data when classifying and analyzing environmental monitoring datasets and water quality parameter information sets, avoiding the omission of important information. The expression introduces a preset first weighting factor ω1 and a second weighting factor ω2. By reasonably adjusting these two parameters, the weights of different calculation components can be flexibly assigned according to the actual application scenario and data characteristics. For example, when environmental factors have a significant impact on water quality, the weight of ω1 can be appropriately increased, allowing the calculation of the logarithmic proportions to play a greater role in the classification, thereby more accurately classifying the water quality data and improving the accuracy and adaptability of the classification.

[0089] The expression fully considers factors such as the number of data types P in the dataset and the total number of vectors K contained in a single type, enabling it to adapt to water quality data of different scales and structures. Whether processing small amounts of water quality data samples or large, complex datasets, it can stably perform classification analysis, laying a solid foundation for subsequent determination of water purification needs based on different water quality types.

[0090] The expression for the boundary estimation is:

[0091]

[0092] Where J is the number of elements in a column vector, δ i μ is the largest eigenvalue of the type matrix constructed from all column vectors contained in the i-th type. i,kj The j-th element of the k-th eigenvector of the type matrix constructed from all column vectors contained in the i-th type, γ i Let be the edge quantity of the i-th type; the column vector of the type matrix is ​​all the column vectors contained in a type;

[0093] The expression for the boundary estimation is derived by introducing the maximum eigenvalue δ of the type matrix. i , eigenvector elements μ ikjBy analyzing parameters such as matrix characteristics, this method can accurately estimate the boundary conditions of each type of water quality dataset. Accurate boundary estimation helps clarify the range of different water quality types, thus better determining whether the water quality data is within the normal or abnormal range, providing a reliable basis for timely adjustments to water purification strategies. By comprehensively considering factors such as the minimum and maximum values ​​of the data, it can effectively address fluctuations that may occur in water quality data during actual collection. When water quality data fluctuates due to environmental factors or other disturbances, this boundary estimation method can stably determine the data boundaries, avoiding misjudgments of water quality types due to data fluctuations, and enhancing the adaptability and robustness of water purification devices to complex water quality changes.

[0094] The discriminant expression for the i-th type of the water quality classification model is:

[0095]

[0096] Where, φ j Let J be the j-th element of the water quality parameter vector to be classified, where J is the number of elements in the water quality parameter vector; the water quality parameter vector is constructed using the collected values ​​of all sequences in the water quality parameter information set at the same time.

[0097] The evaluation process for each type of water quality dataset yields an evaluation sub-value for each type, including:

[0098] Obtain standard values ​​for pH, dissolved oxygen, turbidity, conductivity, and residual chlorine content;

[0099] For each type of water quality dataset, the elements of the water quality parameter vector are subtracted from the corresponding standard values. The difference vector is then constructed using all the subtraction results.

[0100] For all difference vectors of each type, perform a fusion evaluation calculation to obtain the evaluation sub-value for each type;

[0101] The expression for the fusion evaluation calculation is as follows:

[0102]

[0103] Where pgr is an evaluator of a type. and z represents the i-th element of the first characteristic vector and the second characteristic vector, respectively. ij Let N be the j-th element of the i-th difference vector of a type, N be the number of elements in the difference vector, and M be the number of difference vectors contained in a type.

[0104] The expression for the fusion assessment is calculated based on the difference vector obtained by subtracting the standard value from each type of water quality dataset. This comprehensively considers the differences between water quality parameters and standard values ​​across multiple dimensions (such as pH, dissolved oxygen, and turbidity). By fusing these difference vectors, the one-sidedness of single-parameter assessment is avoided, and the overall degree of difference between water quality and standards is more realistically reflected, thus providing a more accurate quantitative indicator for determining water purification needs.

[0105] The expression used in the fusion assessment calculation utilizes the properties of sine and logarithmic functions to highlight key features in the data. The sine function is highly sensitive to data trends and can capture data fluctuations; the logarithmic function amplifies the degree of data variation, allowing even small differences to be reflected in the assessment. Combining these two methods can more effectively uncover important hidden information in water quality data, improving the sensitivity and accuracy of the assessment.

[0106] The resource control module group processes the water purification demand information to obtain filter module switch command information and water purification module switch command information, including:

[0107] Obtain the filtering capacity value sequence of each filtering module in the filtering module group; each filtering capacity value in the filtering capacity value sequence has a corresponding filtering requirement component;

[0108] Obtain the water purification capacity value sequence of each water purification module in the water purification module group; each water purification capacity value in the water purification capacity value sequence has a corresponding water purification demand component;

[0109] All filtration requirement components are extracted from the water purification requirement information, and a filtration requirement vector is constructed.

[0110] All water purification demand components are extracted from the water purification demand information, and a water purification demand vector is constructed.

[0111] For each filter module in the filter module group, the filter capacity value sequence is calculated with the filter demand vector using Euclidean distance. The filter module with the smallest Euclidean distance is obtained, and the information of the electric switch connected to the filter module with the smallest Euclidean distance is determined as the filter module switch command information.

[0112] For each water purification module in the water purification module group, the water purification capacity value sequence is calculated with the water purification demand vector using Euclidean distance. The water purification module with the smallest Euclidean distance is obtained, and the information of the electric switch connected to the water purification module with the smallest Euclidean distance is determined as the water purification module switch command information.

[0113] The water quality classification model is used to process the water quality parameter information set to obtain water quality datasets for each type, including:

[0114] When a water quality parameter vector to be classified satisfies a discriminant expression for a type, it is determined that the water quality parameter vector to be classified belongs to the corresponding type.

[0115] By using water quality parameter vectors of the same type, a water quality dataset of the corresponding type can be constructed.

[0116] The eigenvalues ​​of a matrix are obtained using an eigenvalue solving algorithm.

[0117] The elements of the water quality parameter vector are the collected values ​​of the pH value sequence, dissolved oxygen value sequence, turbidity value sequence, and conductivity value sequence at a certain moment.

[0118] The water quality parameter vector has the same number of elements as the column vector of the first matrix, which is 5.

[0119] The filtration module group includes several filtration units; each filtration unit primarily utilizes ceramic membrane water purification technology and consists of a circulation pump, a ceramic membrane module, a backwash water tank, and an air compressor. The circulation pump, ceramic membrane module, backwash water tank, and air compressor are connected sequentially.

[0120] The filtration performance indicators of each filtration unit are different. The ceramic membrane has a pore size of 50nm, which can greatly reduce the turbidity, suspended solids, bacteria and viruses in the water, and reduce the working pressure on the downstream RO membrane.

[0121] The working principle of ceramic membranes: Ceramic membranes use static pressure difference as the driving force and utilize the "sieving" effect of the sieve-like filter medium to achieve membrane separation. Ceramic membranes employ a cross-flow filtration method. Driven by a pump, raw water flows parallel to the surface of the ceramic membrane within the membrane pores. The water that passes through the ceramic membrane is purified water, while the concentrated water is discharged from the other end of the membrane channels. The shear force generated when the water flows across the surface of the ceramic membrane carries away some of the impurities trapped on the membrane surface, thereby mitigating membrane surface fouling and maintaining a relatively thin fouling layer.

[0122] The backwash tank has a stainless steel shell and an air valve on the top that connects to an air compressor. When backwashing is required, the air valve opens, and the clean water in the tank enters the ceramic membrane module under air pressure, thus completing the backwashing process.

[0123] The water purification module employs an RO membrane assembly. The RO membrane uses an aromatic polyamide composite membrane material, which offers advantages such as low operating pressure, strong acid and alkali resistance, high water production, high desalination rate, and enhanced chemical stability. The selected LP series membrane elements are suitable for surface water with a salinity of approximately 10,000 ppm or less. The high-pressure pump is a key component of the RO system, providing a stable, uninterrupted flow rate and suitable pressure to the membrane assembly.

[0124] The water purification performance indicators of each water purification module are different;

[0125] The beneficial effects of this invention are mainly reflected in the following aspects: First, it improves the self-adaptability of the water purification device, enabling it to dynamically adjust the water purification strategy according to environmental and water quality conditions; second, it improves water purification efficiency and resource utilization through precise water quality assessment and modular design; third, it enhances the flexibility and reliability of the system, facilitating maintenance and expansion; and fourth, it achieves classification analysis and precise assessment of complex water quality data through advanced data processing technology, providing technical support for intelligent water purification.

[0126] A second aspect of this invention discloses an adaptive water purification method, implemented using the aforementioned adaptive water purification device, comprising:

[0127] S1, using the environmental detection module, an environmental monitoring dataset is collected;

[0128] S2, using the water quality monitoring module, the water quality is measured to obtain a set of water quality parameter information. The environmental monitoring dataset and the set of water quality parameter information are evaluated and processed to obtain water purification demand information.

[0129] S3, using the resource control module group, the water purification demand information is processed to obtain filter module switch command information and water purification module switch command information;

[0130] S4, according to the filter module switch instruction information, turn on the electric switch corresponding to the filter module switch instruction information, and use the filter module corresponding to the electric switch to filter the raw water; according to the water purification module switch instruction information, turn on the electric switch corresponding to the water purification module switch instruction information, and use the water purification module corresponding to the electric switch to purify the water output from the filter module.

[0131] The process of evaluating and processing the environmental monitoring dataset and water quality parameter information set to obtain clean water demand information includes:

[0132] S21, perform classification analysis on the environmental monitoring dataset and water quality parameter information set to obtain water quality datasets of each type;

[0133] S22, evaluate and process each type of water quality dataset to obtain an evaluation sub-value for each type;

[0134] S23, each type of evaluation sub-value is used as a demand component to construct water purification demand information; the categories of the demand components include filtration demand components and water purification demand components.

[0135] The environmental monitoring dataset and water quality parameter information set are classified and analyzed to obtain water quality datasets of each type, including:

[0136] S211, represent all sequences in the environmental monitoring dataset as a first matrix; the row vectors of the first matrix include air pressure sequence, PM2.5 content sequence, temperature sequence, humidity sequence, and oxygen content sequence;

[0137] S212, normalize each row vector of the first matrix;

[0138] S213, using all column vectors of the first matrix as variables to be classified, perform classification processing on the variables to be classified to obtain type information and the column vectors contained in each type;

[0139] S214, For all column vectors of the same type, perform classification matrix estimation and boundary estimation respectively to obtain the intermediate matrix and edge quantity corresponding to the type;

[0140] S215, using all types of intermediate matrices and marginal quantities, a water quality classification model is constructed;

[0141] S216 uses a water quality classification model to process the set of water quality parameter information to obtain water quality datasets for each type.

[0142] The normalization process involves dividing each element in the vector by the maximum value of the elements in the vector.

[0143] The expression for the classification matrix estimation is:

[0144]

[0145] Among them, a i,kj β is the j-th element of the k-th column vector contained in the i-th type. ij Let ω1 and ω2 be the elements in the i-th row and j-th column of the intermediate matrix, respectively, where ω1 and ω2 are the preset first and second weighting factors, P is the number of types, and K is the total number of vectors contained in a type. Let be the mean of the k-th column vector contained in the i-th type. It is the mean of the j-th element of all column vectors of type i.

[0146] The expression for the boundary estimation is:

[0147]

[0148] Where J is the number of elements in a column vector, δ iμ is the largest eigenvalue of the type matrix constructed from all column vectors contained in the i-th type. i,kj The j-th element of the k-th eigenvector of the type matrix constructed from all column vectors contained in the i-th type, γ i Let be the edge quantity of the i-th type; the column vector of the type matrix is ​​all the column vectors contained in a type;

[0149] The classification of the variables to be classified can be performed using principal component analysis or K-means algorithm.

[0150] The discriminant expression for the i-th type of the water quality classification model is:

[0151]

[0152] Where, φ j Let J be the j-th element of the water quality parameter vector to be classified, where J is the number of elements in the water quality parameter vector; the water quality parameter vector is constructed using the collected values ​​of all sequences in the water quality parameter information set at the same time.

[0153] The evaluation process for each type of water quality dataset yields an evaluation sub-value for each type, including:

[0154] S221, obtain the standard values ​​of pH, dissolved oxygen, turbidity, conductivity and residual chlorine content;

[0155] S222, for each type of water quality dataset, subtract the corresponding standard value from each element of the water quality parameter vector, and use all the subtraction results to construct the difference vector;

[0156] S223, perform a fusion evaluation calculation on all difference vectors for each type to obtain the evaluation sub-value for each type;

[0157] The expression for the fusion evaluation calculation is as follows:

[0158]

[0159] Where pgr is an evaluator of a type. and z represents the i-th element of the first characteristic vector and the second characteristic vector, respectively. ij Let N be the j-th element of the i-th difference vector of a type, N be the number of elements in the difference vector, and M be the number of difference vectors contained in a type.

[0160] The process of processing the water purification demand information to obtain filter module switch command information and water purification module switch command information includes:

[0161] S31, obtain the filtering capacity value sequence of each filtering module in the filtering module group; each filtering capacity value in the filtering capacity value sequence has a corresponding filtering requirement component.

[0162] S32, obtain the water purification capacity value sequence of each water purification module in the water purification module group; each water purification capacity value in the water purification capacity value sequence has a corresponding water purification demand component;

[0163] S33, extract all filtration requirement components from the water purification requirement information and construct a filtration requirement vector;

[0164] S34, extract all water purification demand components from the water purification demand information and construct a water purification demand vector;

[0165] S35, calculate the Euclidean distance between the filter capability value sequence of each filter module in the filter module group and the filter demand vector to obtain the filter module with the smallest Euclidean distance, and determine the information of the electric switch connected to the filter module with the smallest Euclidean distance as the filter module switch command information.

[0166] S36, For the water purification capacity value sequence of each water purification module in the water purification module group, calculate the Euclidean distance with the water purification demand vector to obtain the water purification module with the smallest Euclidean distance, and determine the information of the electric switch connected to the water purification module with the smallest Euclidean distance, which is the water purification module switch command information.

[0167] The water quality classification model is used to process the water quality parameter information set to obtain water quality datasets for each type, including:

[0168] When a water quality parameter vector to be classified satisfies a discriminant expression for a type, it is determined that the water quality parameter vector to be classified belongs to the corresponding type.

[0169] By using water quality parameter vectors of the same type, a water quality dataset of the corresponding type can be constructed.

[0170] The eigenvalues ​​of a matrix are obtained using an eigenvalue solving algorithm.

[0171] The elements of the water quality parameter vector are the collected values ​​of the pH value sequence, dissolved oxygen value sequence, turbidity value sequence, and conductivity value sequence at a certain moment.

[0172] The water quality parameter vector has the same number of elements as the column vector of the first matrix, which is 5.

[0173] A third aspect of the present invention discloses an adaptive water purification device, the device comprising:

[0174] Memory containing executable program code;

[0175] A processor coupled to the memory;

[0176] The processor calls the executable program code stored in the memory to execute the adaptive water purification method.

[0177] In a fourth aspect of this invention, a computer-storeable medium is disclosed, the computer-storeable medium storing computer instructions, which, when invoked by a computer, are used to execute the adaptive water purification method.

[0178] In a fifth aspect of this invention, an information data processing terminal is disclosed, which is used to implement the adaptive water purification method described above.

[0179] The above description is merely an embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of the present invention should be included within the scope of the claims of the present invention.

Claims

1. An adaptive water purification method, characterized in that, This is achieved using an adaptive water purification device, which includes: an environmental detection module, a water quality monitoring module, a filtration module group, a water purification module group, and a resource control module group. The environmental monitoring module is used to collect environmental monitoring datasets; the environmental monitoring datasets include air pressure sequences, PM2.5 content sequences, temperature sequences, humidity sequences, and oxygen content sequences. The water quality monitoring module is connected to the environmental detection module and is used to measure water quality, obtain a set of water quality parameter information, evaluate and process the environmental monitoring dataset and the set of water quality parameter information to obtain water purification demand information; the set of water quality parameter information includes pH value sequence, dissolved oxygen value sequence, turbidity value sequence, conductivity value sequence and residual chlorine content sequence; The filter module group includes several types of filter modules and an electric switch connected to each filter module; the filter module includes several filter units; the filter unit consists of a circulating pump, a ceramic membrane module, a backwash water tank, and an air compressor; the circulating pump, ceramic membrane module, backwash water tank, and air compressor are connected in sequence. The water purification module group includes several types of water purification modules and an electric switch connected to each water purification module; the water purification module is implemented using an RO membrane assembly; the RO membrane uses an aromatic polyamide composite membrane material. The resource control module group is connected to the water quality monitoring module, the filtration module group, and the water purification module group respectively. It is used to process the water purification demand information to obtain filtration module switch command information and water purification module switch command information. Based on the filtration module switch command information, it turns on the corresponding electric switch, using the filtration module corresponding to the electric switch to filter the raw water. Based on the water purification module switch command information, it turns on the corresponding electric switch, using the water purification module corresponding to the electric switch to purify the water output from the filtration module. The water purification method includes: S1, using the environmental detection module, an environmental monitoring dataset is collected; S2, using the water quality monitoring module, water quality is measured to obtain a set of water quality parameter information. The environmental monitoring dataset and the water quality parameter information set are evaluated and processed to obtain clean water demand information, including: S21, perform classification analysis on the environmental monitoring dataset and water quality parameter information set to obtain water quality datasets of each type; S22, evaluate and process each type of water quality dataset to obtain an evaluation sub-value for each type; S23, each type of evaluation sub-value is used as a demand component to construct water purification demand information; the categories of the demand components include filtration demand components and water purification demand components. S3, using the resource control module group, the water purification demand information is processed to obtain filter module switch command information and water purification module switch command information; S4, according to the filter module switch instruction information, turn on the electric switch corresponding to the filter module switch instruction information, and use the filter module corresponding to the electric switch to filter the raw water; according to the water purification module switch instruction information, turn on the electric switch corresponding to the water purification module switch instruction information, and use the water purification module corresponding to the electric switch to purify the water output from the filter module.

2. The adaptive water purification method as described in claim 1, characterized in that, The environmental monitoring dataset and water quality parameter information set are classified and analyzed to obtain water quality datasets of each type, including: S211, represent all sequences in the environmental monitoring dataset as a first matrix; the row vectors of the first matrix include air pressure sequence, PM2.5 content sequence, temperature sequence, humidity sequence, and oxygen content sequence; S212, normalize each row vector of the first matrix; S213, using all column vectors of the first matrix as variables to be classified, perform classification processing on the variables to be classified to obtain type information and the column vectors contained in each type; S214, For all column vectors of the same type, perform classification matrix estimation and boundary estimation respectively to obtain the intermediate matrix and edge quantity corresponding to the type; S215, using all types of intermediate matrices and marginal quantities, a water quality classification model is constructed; S216. Using a water quality classification model, the water quality parameter information set is processed to obtain water quality datasets for each type. The expression for the classification matrix estimation is: ， in, Let j be the j-th element of the k-th column vector contained in the i-th type. Let be the element in the i-th row and j-th column of the intermediate matrix. and These are the preset first and second weighting factors, respectively. P is the number of types, and K is the total number of vectors contained in a type. Let be the mean of the k-th column vector contained in the i-th type. The mean of the j-th element of all column vectors of type i; The expression for the boundary estimation is: ， Where J is the number of elements contained in a column vector. The largest eigenvalue of the type matrix constructed from all column vectors contained in the i-th type. The j-th element of the k-th eigenvector of the type matrix constructed from all column vectors contained in the i-th type. Let be the edge quantity of the i-th type; the column vector of the type matrix is ​​all the column vectors contained in a type.

3. The adaptive water purification method as described in claim 2, characterized in that, The discriminant expression for the i-th type of the water quality classification model is: ， in, Let J be the j-th element of the water quality parameter vector to be classified, where J is the number of elements in the water quality parameter vector. The water quality parameter vector is constructed using the collected values ​​of all sequences in the water quality parameter information set at the same time.

4. The adaptive water purification method as described in claim 1, characterized in that, The evaluation process for each type of water quality dataset yields an evaluation sub-value for each type, including: S221, obtain the standard values ​​of pH, dissolved oxygen, turbidity, conductivity and residual chlorine content; S222, for each type of water quality dataset, subtract the corresponding standard value from each element of the water quality parameter vector, and use all the subtraction results for each type to construct the difference vector of that type; S223, perform a fusion evaluation calculation on all difference vectors for each type to obtain the evaluation sub-value for each type; The expression for the fusion evaluation calculation is as follows: ， ， ， in, pgr For an evaluation subvalue of a type, and These are the i-th elements of the first characteristic vector and the second characteristic vector, respectively. Let N be the j-th element of the i-th difference vector of a type, N be the number of elements in the difference vector, and M be the number of difference vectors contained in a type.

5. The adaptive water purification method as described in claim 1, characterized in that, The water quality monitoring module includes a pH sensor, a dissolved oxygen sensor, a turbidity sensor, a conductivity sensor, a residual chlorine sensor, and a data processing submodule. The pH sensor, dissolved oxygen sensor, turbidity sensor, conductivity sensor, and residual chlorine sensor are used to collect pH value sequences, dissolved oxygen value sequences, turbidity value sequences, conductivity value sequences, and residual chlorine content sequences, respectively. The data processing submodule is used to evaluate and process the environmental monitoring dataset and water quality parameter information set to obtain water purification demand information.

6. A computer-storable medium, characterized in that, The computer storage medium stores computer instructions, which, when invoked by the computer, are used to execute the adaptive water purification method as described in any one of claims 1 to 5.

Images