Intelligent reclaimed water treatment method

Abstract

The invention relates to the technical field of reclaimed water treatment, and discloses an intelligent reclaimed water treatment method which comprises the following steps: acquiring real-time water quality data and historical water quality data of to-be-treated reclaimed water; establishing a water quality scoring model according to the historical water quality data, inputting the real-time water quality data into the water quality scoring model, and outputting multiple influence factor scores of the water quality; generating a comprehensive score of the to-be-treated reclaimed water through scores of various influence factors of the water quality; establishing a reclaimed water treatment model library, selecting a corresponding reclaimed water treatment model in the reclaimed water treatment model library through the comprehensive score of the to-be-treated reclaimed water, and generating a reclaimed water treatment strategy; and executing the reclaimed water treatment strategy, detecting the reclaimed water treatment process, and updating the reclaimed water treatment model library according to a detection result. Through real-time monitoring and automatic adjustment of processing parameters, the automation level of the processing process is improved; therefore, manual intervention is reduced, water quality changes can be quickly responded, and the stability of the treatment effect is kept.

Description

Technical Field

[0001] The present invention relates to the technical field of reclaimed water treatment, and in particular to an intelligent reclaimed water treatment method. Background Art

[0002] At present, greywater treatment technology has become an important part of urban water management. Continuous innovation and optimization of technology have made greywater treatment more efficient, economical, and applicable to a variety of scenarios, including residential areas, commercial buildings, industrial parks, etc. Greywater reuse not only improves the recycling rate of water resources, but also contributes to ecological environmental protection and urban sustainable development.

[0003] Recycled water treatment technology is of great significance for alleviating water shortage, protecting the ecological environment, and promoting sustainable economic and social development. With the popularization of technology and policy support, recycled water reuse is expected to play a role in more areas and become an indispensable part of water resource management. In addition, the progress of recycled water treatment technology can also help to raise public awareness of the importance of water resource protection and recycling, and promote the green development concept of the entire society. Summary of the invention

[0004] The purpose of the present invention is to obtain real-time parameters of the reclaimed water to be treated by setting monitoring time nodes, generate the current comprehensive score of the reclaimed water through the evaluation model, dynamically adjust the reclaimed water treatment strategy, and realize efficient optimization and dynamic adaptation of the reclaimed water treatment process.

[0005] In order to achieve the above object, the present invention provides an intelligent reclaimed water treatment method, comprising:

[0006] Establish a water index evaluation model based on historical data;

[0007] Establish multiple monitoring time nodes, obtain the real-time parameters of the reclaimed water to be treated at the current monitoring time node, and generate the comprehensive score of the reclaimed water at the current monitoring time node based on the reclaimed water index evaluation model;

[0008] According to the comprehensive score of the reclaimed water at the current monitoring time node, the current reclaimed water treatment strategy and the current reclaimed water monitoring cycle are set.

[0009] In some embodiments of the present application, when establishing a water index evaluation model based on historical data, it includes:

[0010] Obtain historical water quality data D, D = [G, S, P, O];

[0011] The historical water quality data D contains multiple types of sub-data sets, among which G represents the particle size data set in the reclaimed water, S represents the salt content data set in the reclaimed water, P represents the pH value data set in the reclaimed water, and O represents the oxygen content data set in the reclaimed water;

[0012] G=[g1,g2…gi…gn]; S=[s1,s2…si…sn]; P=[p1,p2…pi…pn];

[0013] O=[o1,o2…oi…on];

[0014] gi represents the particle size data measured in the water for the i-th time, si represents the salt content data measured in the water for the i-th time, pi represents the pH value data measured in the water for the i-th time, oi represents the oxygen content data measured in the water for the i-th time, and n represents the total number of sampling times;

[0015] Based on the historical water quality data D, the values ​​of each type of sub-data are divided into intervals to generate multiple interval gradients, and the multiple interval gradients are assigned values ​​to obtain the evaluation value Z of each type of water index, Z = (Z G ,Z S ,Z P ,Z O );

[0016] Among them, Z G Score the particle size data in water, Z S Score the indicator for the salinity data in water, Z P The indicator score for the pH value data in water is Z O Score the indicator data for oxygen content in water.

[0017] In some embodiments of the present application, the generating of the comprehensive score of reclaimed water at the current monitoring time node includes:

[0018] Construct the historical water quality data matrix A[a ij ] n×4 ;

[0019] a ij It represents the score of the jth data indicator of the i-th sampling;

[0020] By a ij Calculate the weight p of the jth data index of the i-th sampling ij :

[0021]

[0022] Calculate the entropy weight e of the jth data indicator j :

[0023]

[0024] Calculate the coefficient of variation g of the jth data indicator j :

[0025] g j =1-e j(j=1,2,3,4);

[0026] Calculate the weight w of the jth data indicator j :

[0027]

[0028] Through the water quality scoring model, the scores Z of various data indicators of the reclaimed water to be treated are obtained, and the comprehensive score TS of the reclaimed water to be treated is calculated based on the scores Z of various data indicators of the reclaimed water;

[0029] TS=W1*Z G +W2*Z S +W3*Z P +W4*Z O ;

[0030] Among them, W1 is the weight of the particle size data in the water, W2 is the weight of the salt content data in the water, W3 is the weight of the pH value data in the water, and W4 is the weight of the oxygen content data in the water.

[0031] In some embodiments of the present application, the setting of the current grey water treatment strategy and the current grey water monitoring cycle includes:

[0032] According to the comprehensive score TS of the reclaimed water, the water quality status of the reclaimed water to be treated is judged, the corresponding monitoring cycle is set, and the time interval from the current monitoring time node to the next time node is determined;

[0033] Get the index score Z of the particle size data in the water at the current monitoring time node G and water salinity data index score Z S ;

[0034] If the index score of the particle size data in water is Z G and water salinity data index score Z S If they all reach their respective set thresholds, they enter the deep processing stage;

[0035] The pretreatment stage includes: removing particulate impurities from the reclaimed water and desalting the reclaimed water;

[0036] Obtain the particle size data change ΔZ during the removal of reclaimed water particles G And the salt content data ΔZ during the desalination process of reclaimed water S ;

[0037] Generate the particle size correction value Z in water G ', Z G '=(Z G -ΔZ G );

[0038] Correction value Z of salt content data in water desalination process S ', Z S '=(Z S -ΔZ S );

[0039] Based on the change of particle size data ΔZ G And the salt content data ΔZ S , generate water quality correction parameter B;

[0040] Based on the water quality correction parameter B, generate the pH correction value Z in the water P ' and the oxygen content correction value Z in water O ';

[0041] The deep processing stage includes:

[0042] Perform water quality acid-base balance treatment based on the corrected pH value of the water;

[0043] Deoxygenation treatment is performed based on the corrected oxygen content in the water.

[0044] In some embodiments of the present application, the setting of the corresponding monitoring period includes:

[0045] Generate the average value μ of the comprehensive score TS of the reclaimed water through historical data, and the standard deviation σ of the comprehensive score TS of the reclaimed water in the historical data;

[0046] Based on the average value μ and the standard deviation σ, the water quality status is divided, and according to the division of water quality status, the update time node of the comprehensive score of reclaimed water is formulated;

[0047] Based on the water purification test, determine the adjustment range of the sampling frequency (u min ,u max );

[0048] u min is the minimum scale factor of the sampling frequency, u max is the maximum scaling factor of the sampling frequency;

[0049] If TS∈(μ-σ,μ+σ), the current reclaimed water to be tested is defined as primary reclaimed water, the current water quality sampling frequency T0 is maintained, and the remaining amount of the primary acid-base reagent of the deoxidizer is predicted;

[0050] If TS∈(0,μ-σ), the current water to be tested is defined as secondary water, and the sampling frequency T of the current water quality is corrected.

[0051]

[0052] m is the current water quality sampling frequency proportional factor,

[0053] T = T0 / (1+m);

[0054] If TS∈(μ+σ,+∞), the current water to be tested is defined as third-grade water, and the sampling frequency T of the current water quality is corrected.

[0055] T = T0 / (1-m).

[0056] In some embodiments of the present application, the step of removing the water particle impurities includes:

[0057] Set the index threshold Z of the particle size data in water based on the water use index G (min);

[0058] And based on the index score Z of the current water particle size data G , calculate the amount of coagulant input;

[0059] Real-time monitoring of particle size data changes ΔZ during water particle impurity removal G ; When the index score of the particle size data in water is Z G When the index threshold is reached, the remaining colloids and suspended matter are removed by filtration;

[0060] Get the particle size data change ΔZ at this time G (max).

[0061] In some embodiments of the present application, the calculation of the input amount of the coagulant includes:

[0062] The coagulant input test was conducted to obtain the coagulant unit volume input coefficient k0;

[0063] Calculate the amount of coagulant input Q;

[0064] Q=k0*Z G *V;

[0065] V is the volume of the water to be treated.

[0066] In some embodiments of the present application, the desalination of the reclaimed water includes:

[0067] Set the salt content threshold Z of water based on water use indicators S (min);

[0068] The indicator score Z is calculated based on the current water salinity data. S , calculate the time for water desalination in reverse osmosis;

[0069] Real-time monitoring of salt content data changes ΔZ during the desalination process of reclaimed water S ; When the indicator score of the water salt content data is Z S When the indicator threshold is reached, obtain the granularity data change ΔZ at this timeS (max).

[0070] In some embodiments of the present application, the pH correction value Z in water is generated. P ' and the oxygen content correction value Z in water O ', including:

[0071] Based on the change of particle size data ΔZ G And the salt content data ΔZ S , generate the water quality correction parameter B in the deep treatment stage, B = (B1, B2);

[0072] B1=k1*ΔZ G +k2*ΔZ S ;

[0073] B2=k3*ΔZ G +k4*ΔZ S ;

[0074] k1 is the correction constant of the change of particle size data to pH value, k2 is the correction constant of the change of salt content data to pH value, k3 is the correction constant of the change of particle size data to oxygen content, k4 is the correction constant of salt content data to k2 to oxygen content;

[0075] Generate pH correction value Z in water P ', Z P '=Z P -B1;

[0076] And the oxygen content correction value Z in water O ', Z O '=Z O -B2;

[0077] Among them, B1 is the correction parameter for pH value in the pretreatment stage, and B2 is the correction parameter for oxygen content in water in the pretreatment stage.

[0078] In some embodiments of the present application, the deep processing stage includes:

[0079] Calculate the minimum index score Z of the pH value data in the water at the current monitoring time P (min)

[0080] Z P (min) = Z P -B1=Z P -(k1*ΔZ G (max)+k2*ΔZ S (max));

[0081] Calculate the minimum index score Z of the oxygen content data in the water at the current monitoring time O (min)

[0082] Z O (min) = Z O -B2=Z O -(k3*ΔZ G (max)+k4*ΔZ S (max));

[0083] The minimum index score Z according to the pH value data of water P (min), add acid and alkali reagents to adjust the pH value in the water to the target value;

[0084] The minimum index score Z based on the oxygen content data in the water O (min), add deoxidizer to control the oxygen content in water to the target content.

[0085] Compared with the prior art, the intelligent water treatment method according to the embodiment of the present invention has the following beneficial effects:

[0086] A water quality scoring model is established to quickly and accurately assess water quality conditions; the water quality scoring model not only provides a quantitative water quality assessment tool, but also provides strong support for subsequent reclaimed water treatment decisions.

[0087] By analyzing historical water quality data, a water quality scoring model is established to quantitatively evaluate water quality conditions; the calculation of the comprehensive score takes into account the weights and coefficients of variation of multiple water quality parameters, making the score more comprehensive and objective.

[0088] By analyzing the comprehensive score TS, the water quality status can be divided more accurately, so that corresponding monitoring and treatment strategies can be implemented for different grades of reclaimed water; this hierarchical management helps to solve water quality problems in a targeted manner and improve the overall treatment effect.

[0089] By dynamically adjusting the sampling frequency to ensure the accuracy of monitoring and the timeliness of processing, it is also possible to rationally plan the use of reagents and achieve the goal of optimizing resource allocation.

[0090] By updating the grey water treatment model library and providing feedback on the differences between treatment results and expectations, the model library can continue to evolve to ensure the long-term effectiveness and adaptability of grey water treatment. BRIEF DESCRIPTION OF THE DRAWINGS

[0091] Figure 1 It is a flow chart of an intelligent reclaimed water treatment method disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0092] The specific implementation of the present invention is further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0093] In the description of the present application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0094] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0095] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0096] like Figure 1 As shown, the embodiment of the present invention discloses an intelligent reclaimed water treatment method, including:

[0097] Establish a water index evaluation model based on historical data;

[0098] Establish multiple monitoring time nodes, obtain the real-time parameters of the reclaimed water to be treated at the current monitoring time node, and generate the comprehensive score of the reclaimed water at the current monitoring time node based on the reclaimed water index evaluation model;

[0099] According to the comprehensive score of the reclaimed water at the current monitoring time node, the current reclaimed water treatment strategy and the current reclaimed water monitoring cycle are set.

[0100] Embodiment 1:

[0101] When establishing a water index evaluation model based on historical data, it includes:

[0102] Obtain historical water quality data D, D = [G, S, P, O];

[0103] The historical water quality data D contains multiple types of sub-data sets, among which G represents the particle size data set in the reclaimed water, S represents the salt content data set in the reclaimed water, P represents the pH value data set in the reclaimed water, and O represents the oxygen content data set in the reclaimed water;

[0104] G=[g1,g2…gi…gn]; S=[s1,s2…si…sn]; P=[p1,p2…pi…pn];

[0105] O=[o1,o2…oi…on];

[0106] gi represents the particle size data measured in the water for the i-th time, si represents the salt content data measured in the water for the i-th time, pi represents the pH value data measured in the water for the i-th time, oi represents the oxygen content data measured in the water for the i-th time, and n represents the total number of sampling times;

[0107] Based on the historical water quality data D, the values ​​of each type of sub-data are divided into intervals to generate multiple interval gradients, and the multiple interval gradients are assigned values ​​to obtain the evaluation value Z of each type of water index, Z = (Z G ,Z S ,Z P ,Z O );

[0108] Among them, Z G Score the particle size data in water, Z S Score the indicator for the salinity data in water, Z P The indicator score for the pH value data in water is Z O Score the indicator data for oxygen content in water.

[0109] In this embodiment, a water quality scoring model is established to quickly and accurately evaluate water quality conditions.

[0110] Data preparation: Daily water quality test data for the past year were collected, covering four key indicators: salinity (S), particle size (G), pH value (P) and dissolved oxygen (O). Each indicator has more than 365 independent samples.

[0111] Score interpretation: A lower score (close to 0) indicates that the indicator deviates far from the average level, suggesting that there may be problems with water quality. Conversely, a high score (close to 1) means that the water quality is good or stable.

[0112] Real-time monitoring and early warning: By comparing newly collected data with the results of the scoring model in real time, the system can quickly identify sudden deterioration of water quality and facilitate immediate response measures, such as increasing the intensity of chemical treatment or adjusting the physical filtration program.

[0113] Long-term trend analysis: Continuously recorded scores of various indicators help to observe seasonal fluctuations in water quality or the degree of influence of external factors, thereby optimizing the overall greywater treatment strategy.

[0114] Through this detailed implementation process, the water quality scoring model not only provides a quantitative water quality assessment tool, but also provides strong support for subsequent greywater treatment decisions.

[0115] Embodiment 2:

[0116] When generating the comprehensive score of reclaimed water at the current monitoring time node, it includes:

[0117] Construct the historical water quality data matrix A[a ij ] n×4 ;

[0118] a ij It represents the score of the jth data indicator of the i-th sampling;

[0119] By a ij Calculate the weight p of the jth data index of the i-th sampling ij :

[0120]

[0121] Calculate the entropy weight e of the jth data indicator j :

[0122]

[0123] Calculate the coefficient of variation g of the jth data indicator j :

[0124] g j =1-e j (j=1,2,3,4);

[0125] Calculate the weight w of the jth data indicator j :

[0126]

[0127] Through the water quality scoring model, the scores Z of various data indicators of the reclaimed water to be treated are obtained, and the comprehensive score TS of the reclaimed water to be treated is calculated based on the scores Z of various data indicators of the reclaimed water;

[0128] TS=W1*Z G +W2*Z S +W3*Z P +W4*Z O ;

[0129] Among them, W1 is the weight of the particle size data in the water, W2 is the weight of the salt content data in the water, W3 is the weight of the pH value data in the water, and W4 is the weight of the oxygen content data in the water.

[0130] In this embodiment, by analyzing historical water quality data, a water quality scoring model is established to quantitatively evaluate water quality and provide a scientific basis for reclaimed water treatment. This model can help operators more accurately understand the multi-dimensional influencing factors of water quality, thereby optimizing treatment strategies;

[0131] The calculation of the composite score takes into account the weights and coefficients of variation of multiple water quality parameters, making the score more comprehensive and objective. This approach helps identify key issues in water quality and provides guidance for resource allocation and priority setting.

[0132] Establishment and update of model library: The establishment of the water treatment model library allows the selection of appropriate treatment models based on real-time water quality scores, and updates the model library based on treatment effects. This dynamic adjustment mechanism ensures treatment efficiency and water quality safety;

[0133] Intelligent treatment methods improve the automation level of the treatment process by real-time monitoring and automatic adjustment of treatment parameters. This not only reduces manual intervention, but also helps to quickly respond to changes in water quality and maintain the stability of treatment effects.

[0134] Embodiment 3:

[0135] The setting of the current grey water treatment strategy and the current grey water monitoring cycle includes:

[0136] According to the comprehensive score TS of the reclaimed water, the water quality status of the reclaimed water to be treated is judged, the corresponding monitoring cycle is set, and the time interval from the current monitoring time node to the next time node is determined;

[0137] Get the index score Z of the particle size data in the water at the current monitoring time node G and water salinity data index score Z S ;

[0138] If the index score of the particle size data in water is Z G and water salinity data index score Z S If they all reach their respective set thresholds, they enter the deep processing stage;

[0139] The pretreatment stage includes: removing particulate impurities from the reclaimed water and desalting the reclaimed water;

[0140] Obtain the particle size data change ΔZ during the removal of reclaimed water particles G And the salt content data ΔZ during the desalination process of reclaimed water S ;

[0141] Generate the particle size correction value Z in water G ', Z G '=(Z G -ΔZ G );

[0142] Correction value Z of salt content data in water desalination process S ', Z S '=(Z S -ΔZ S );

[0143] Based on the change of particle size data ΔZ G And the salt content data ΔZ S , generate water quality correction parameter B;

[0144] Based on the water quality correction parameter B, generate the pH correction value Z in the water P ' and the oxygen content correction value Z in water O ';

[0145] The deep processing stage includes:

[0146] Perform water quality acid-base balance treatment based on the corrected pH value of the water;

[0147] Deoxygenation treatment is performed based on the corrected oxygen content in the water.

[0148] Embodiment 4:

[0149] The setting of the corresponding monitoring period includes:

[0150] Generate the average value μ of the comprehensive score TS of the reclaimed water through historical data, and the standard deviation σ of the comprehensive score TS of the reclaimed water in the historical data;

[0151] Based on the average value μ and the standard deviation σ, the water quality status is divided, and according to the division of water quality status, the update time node of the comprehensive score of reclaimed water is formulated;

[0152] Based on the water purification test, determine the adjustment range of the sampling frequency (u min ,u max );

[0153] u min is the minimum scale factor of the sampling frequency, u max is the maximum scaling factor of the sampling frequency;

[0154] If TS∈(μ-σ,μ+σ), the current reclaimed water to be tested is defined as primary reclaimed water, the current water quality sampling frequency T0 is maintained, and the remaining amount of the primary acid-base reagent of the deoxidizer is predicted;

[0155] If TS∈(0,μ-σ), the current water to be tested is defined as secondary water, and the sampling frequency T of the current water quality is corrected.

[0156]

[0157] m is the current water quality sampling frequency proportional factor,

[0158] T = T0 / (1+m);

[0159] If TS∈(μ+σ,+∞), the current water to be tested is defined as third-grade water, and the sampling frequency T of the current water quality is corrected.

[0160] T = T0 / (1-m).

[0161] In this embodiment, not only can the sampling frequency be dynamically adjusted according to the real-time score of the reclaimed water quality to ensure the accuracy of monitoring and the timeliness of treatment, but also the reagent usage can be reasonably planned to achieve the purpose of optimizing resource allocation. This hierarchical monitoring and treatment strategy provides a strong guarantee for the efficient and stable operation of the reclaimed water treatment system.

[0162] In this embodiment, by statistically analyzing the average value μ and standard deviation σ of the comprehensive score TS, the water quality state can be more accurately divided, so that corresponding monitoring and treatment strategies can be implemented for different levels of reclaimed water. This hierarchical management helps to solve water quality problems in a targeted manner and improve the overall treatment effect.

[0163] Optimize resource allocation and treatment efficiency: According to the different levels of water quality scores, monitoring and treatment resources can be reasonably allocated to avoid using the same standard for all reclaimed water, thereby improving resource utilization efficiency and processing speed.

[0164] Strengthen early warning and emergency response capabilities: Through real-time monitoring and data analysis, digital twin technology can promptly detect water quality anomalies and trigger early warning mechanisms, which helps to quickly respond to potential water quality problems and reduce the impact of pollution incidents.

[0165] Promoting scientific and intelligent decision-making: The establishment and updating of the model library, combined with data assimilation technology and simulation prediction, provides decision-making support and makes management measures more accurate and effective. This helps to achieve the maximum utilization of water resources and sustainable development.

[0166] Improve the automation and intelligence level of the system: The intelligent greywater treatment method improves the automation level of water quality management by integrating advanced data analysis technology, automatic control and intelligent algorithms, reduces manual intervention and ensures the stability of treatment effects.

[0167] Embodiment 5:

[0168] The method of removing particulate impurities from the reclaimed water comprises:

[0169] Set the index threshold Z of the particle size data in water based on the water use index G (min);

[0170] And based on the index score Z of the current water particle size data G , calculate the amount of coagulant input;

[0171] Real-time monitoring of particle size data changes ΔZ during water particle impurity removal G ; When the index score of the particle size data in water is Z G When the index threshold is reached, the remaining colloids and suspended matter are removed by filtration;

[0172] Get the particle size data change ΔZ at this time G (max).

[0173] Embodiment 6:

[0174] The calculation of the amount of coagulant input includes:

[0175] The coagulant input test was conducted to obtain the coagulant unit volume input coefficient k0;

[0176] Calculate the amount of coagulant input Q;

[0177] Q=k0*Z G *V;

[0178] V is the volume of the water to be treated.

[0179] In this embodiment, the strategy overview

[0180] The strategy for removing particulate impurities from reclaimed water aims to effectively reduce the content of colloids and suspended matter in water by combining coagulant addition with subsequent filtration. The core of this strategy is to accurately calculate the amount of coagulant input based on the water quality characteristic parameter (ZG) to ensure effective removal of impurities while avoiding waste of reagents.

[0181] Calculation process of coagulant input

[0182] Determination of coagulant unit volume input coefficient (k)

[0183] Implement a coagulant input test and determine through a series of experiments the unit volume input (k) required for a specific type of coagulant and its optimal flocculation effect under target water quality conditions, that is, the amount of coagulant required per cubic meter (m3) of water to be treated (g / m3).

[0184] Calculate the amount of coagulant input (Q)

[0185] According to the measured coagulant unit volume input coefficient (k), combined with the volume of the treated water (V) and the water quality characteristic parameters (ZG), the total coagulant input (Q) is calculated.

[0186] Coagulation and sedimentation process

[0187] The calculated coagulant is added into the water to be treated in a predetermined amount, and is evenly dispersed under stirring to promote the formation of larger flocs and sedimentation and separation of particulate matter.

[0188] Monitor whether the effluent turbidity after coagulation is lower than the preset threshold to ensure that the initial treatment meets the standards.

[0189] Deep filtration stage

[0190] If the turbidity of the effluent after coagulation meets the standard, it will be further sent to the filter tank for deep filtration to remove residual micro-colloids and suspended matter.

[0191] The selection and design of filter media should ensure that smaller particles can be effectively retained to ensure that the effluent quality meets the standards.

[0192] Embodiment 7:

[0193] The desalination of the reclaimed water comprises:

[0194] Set the salt content threshold Z of water based on water use indicators S (min);

[0195] The indicator score Z is calculated based on the current water salinity data. S , calculate the time for water desalination in reverse osmosis;

[0196] Real-time monitoring of salt content data changes ΔZ during the desalination process of reclaimed water S ; When the indicator score of the water salt content data is Z S When the indicator threshold is reached, obtain the granularity data change ΔZ at this time S (max).

[0197] Embodiment 8:

[0198] Generate pH correction value Z in water P ' and the oxygen content correction value Z in water O ', including:

[0199] Based on the change of particle size data ΔZ G And the salt content data ΔZ S , generate the water quality correction parameter B in the deep treatment stage, B = (B1, B2);

[0200] B1=k1*ΔZ G +k2*ΔZ S ;

[0201] B2=k3*ΔZ G +k4*ΔZ S ;

[0202] k1 is the correction constant of the change of particle size data to pH value, k2 is the correction constant of the change of salt content data to pH value, k3 is the correction constant of the change of particle size data to oxygen content, k4 is the correction constant of salt content data to k2 to oxygen content;

[0203] Generate pH correction value Z in water P ', Z P '=Z P -B1;

[0204] And the oxygen content correction value Z in water O ', Z O '=Z O -B2;

[0205] Among them, B1 is the correction parameter for pH value in the pretreatment stage, and B2 is the correction parameter for oxygen content in water in the pretreatment stage.

[0206] In this embodiment, the desalination process of reclaimed water: First, the salt content index threshold ZS (min) is set according to the water use index. Then, the desalination time of the water in the reverse osmosis method is calculated through real-time monitoring and data analysis. During the desalination process, the salt content data change △ ZS is monitored in real time, and when the salt content index score ZS reaches the threshold, the particle size data change △ ZS (max) is recorded.

[0207] Water quality correction in the deep treatment stage: Based on the changes in particle size data and salt content data, the water quality correction parameter B in the deep treatment stage is generated. This parameter is used to calculate the pH correction value ZP' and the oxygen content correction value ZO'. Through these correction values, the pH value and oxygen content in the water can be adjusted to the target values.

[0208] Deep treatment stage: After the pretreatment stage, the comprehensive score TS'' of the reclaimed water is calculated, and based on the minimum index score of the corrected pH value and oxygen content data, acid and alkali reagents and deoxidizers are added to achieve the predetermined water quality standards.

[0209] In practical applications, these steps can be automated through integrated control systems and intelligent algorithms. For example, IoT technology can be used to monitor water quality parameters in real time, big data analysis can be used to optimize the treatment process, and cloud computing platforms can be used to centrally manage and analyze data. In addition, a virtual model of the greywater treatment system can be created through digital twin technology to achieve more accurate prediction and control.

[0210] Example 9

[0211] The deep processing stage includes:

[0212] Calculate the minimum index score Z of the pH value data in the water at the current monitoring time P (min)

[0213] Z P (min) = Z P -B1=Z P -(k1*ΔZ G (max)+k2*ΔZ S (max));

[0214] Calculate the minimum index score Z of the oxygen content data in the water at the current monitoring time O (min)

[0215] Z O (min) = Z O -B2=Z O -(k3*ΔZ G (max)+k4*ΔZ S (max));

[0216] The minimum index score Z according to the pH value data of water P (min), add acid and alkali reagents to adjust the pH value in the water to the target value;

[0217] The minimum index score Z based on the oxygen content data in the water O (min), add deoxidizer to control the oxygen content in water to the target content.

[0218] Intelligent reclaimed water treatment methods not only improve the technical performance of water treatment by integrating advanced information technology and automation control technology, but also help to achieve sustainable utilization of water resources and environmental protection.

[0219] In this embodiment, the TS values ​​are recorded to generate a data set TSD: during the grey water treatment process, samples are taken regularly to record the TS (Turbidity) values ​​of the grey water, and a data set TSD = [TS1, TS2…TSt…TSn] that changes over time is generated, where each TSt represents the turbidity value at the tth sampling after the start of treatment.

[0220] Calculation of actual rate of change VT: Based on the data set TSD, the actual rate of change VT of TS is calculated by difference or other numerical methods to reflect the rate of change of turbidity during the treatment process. Evaluation of theoretical and actual deviations Obtaining the theoretical rate of change VT': Based on previous water purification tests, determine the theoretical rate of change VT' of TS under ideal conditions. Calculation of error value MES: Compare VT and VT' and calculate the deviation between the two, that is, error value MES = VT-VT'.

[0221] Set threshold E: Set an acceptable maximum deviation threshold E for MES.

[0222] Triggering manual intervention: If MES>E, it indicates that the treatment effect deviates significantly from expectations and manual intervention is required.

[0223] Model library update

[0224] MES value and deviation analysis.

[0225] Parameter correction and new model generation: The manual end analyzes the causes of deviations based on the report content, adjusts control parameters, and generates a new greywater treatment model.

[0226] Model library update: After the new model is verified to be effective, it will be added to the reclaimed water treatment model library.

[0227] This embodiment ensures the continuous optimization of the reclaimed water treatment model through real-time monitoring and dynamic adjustment, and improves the treatment efficiency and water quality compliance rate. This data-driven model update mechanism not only improves the performance of the reclaimed water reuse system, but also provides a more flexible and intelligent solution for water resource management.

[0228] The specific steps and effects of dynamic updating of the grey water treatment model library were demonstrated. Through continuous data collection, analysis and manual intervention, the optimization and upgrading of the treatment model was achieved, which is of great significance to improving the stability and efficiency of the grey water treatment system.

[0229] Specific implementation of the dynamic update mechanism of the water treatment model library

[0230] Background and Objectives

[0231] In the grey water treatment system, the change of water quality parameters has a direct impact on the treatment effect. This embodiment aims to evaluate the treatment efficiency by real-time monitoring of the turbidity (TS) changes during the treatment process, and dynamically update the grey water treatment model library according to the evaluation results to improve the overall performance of the system.

[0232] Implementation steps

[0233] Data recording and analysis: Generate TS change data set TSD

[0234] Implementation details: The system automatically records the turbidity values ​​during the treatment process to form a data set

[0235] TSD = [TS1, TS2, ...TSt, ...TSn], where each element TSt represents the turbidity value from the start of processing to the tth sampling time, and n represents the total number of sampling times. Calculate the actual change rate VT implementation details: Use numerical analysis methods to calculate the actual change rate VT of turbidity based on the TSD data set. Obtain the theoretical change rate VT' implementation details: Refer to the water purification test results to obtain the theoretical turbidity change rate VT' under ideal conditions. Calculate the error value MES implementation details: Compare VT and VT' and calculate the difference between the two, that is, MES. Set the threshold E and judgment implementation details: Set the maximum acceptable threshold E of the error value MES. When MES>E, the system determines that the current model processing effect is not good.

[0236] Manual intervention and model modification

[0237] Implementation details: Send alarm information to the manual end, and professionals will analyze the cause of the deviation, adjust the control parameters, and design and verify the new processing model.

[0238] Implementation details: Add the new model to the reclaimed water treatment model library for automatic call in subsequent processing.

[0239] Improved system performance: Through dynamic adjustment, the model is ensured to match the actual water quality conditions, effectively improving the treatment efficiency and water quality compliance rate.

[0240] Cost saving: avoids waste of resources and reduces processing costs.

[0241] Data-driven decision-making: Analysis based on real-time data provides accurate decision-making basis for the human side.

[0242] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and substitutions can be made without departing from the technical principles of the present invention. These improvements and substitutions should also be regarded as the scope of protection of the present invention.

Claims

1. An intelligent reclaimed water treatment method, characterized in that: include: Establish a water index evaluation model based on historical data; Establish multiple monitoring time nodes, obtain the real-time parameters of the reclaimed water to be treated at the current monitoring time node, and generate the comprehensive score of the reclaimed water at the current monitoring time node based on the reclaimed water index evaluation model; According to the comprehensive score of the reclaimed water at the current monitoring time node, the current reclaimed water treatment strategy and the current reclaimed water monitoring cycle are set.

2. The intelligent reclaimed water treatment method according to claim 1, characterized in that: When establishing a water index evaluation model based on historical data, it includes: Obtain historical water quality data D, D = [G, S, P, O]; The historical water quality data D contains multiple types of sub-data sets, among which G represents the particle size data set in the reclaimed water, S represents the salt content data set in the reclaimed water, P represents the pH value data set in the reclaimed water, and O represents the oxygen content data set in the reclaimed water; G=[g1,g2…gi…gn]; S=[s1,s2…si…sn]; P=[p1,p2…pi…pn]; O=[o1,o2…oi…on]; gi represents the particle size data measured in the water for the i-th time, si represents the salt content data measured in the water for the i-th time, pi represents the pH value data measured in the water for the i-th time, oi represents the oxygen content data measured in the water for the i-th time, and n represents the total number of sampling times; Based on the historical water quality data D, the values ​​of each type of sub-data are divided into intervals to generate multiple interval gradients, and the multiple interval gradients are assigned values ​​to obtain the evaluation value Z of each type of water index, Z = (Z G ,Z S ,Z P ,Z O ); Among them, Z G Score the particle size data in water, Z S Score the indicator for the salinity data in water, Z P The indicator score for the pH value data in water is Z O Score the indicator data for oxygen content in water.

3. The intelligent reclaimed water treatment method according to claim 2, characterized in that: When generating the comprehensive score of reclaimed water at the current monitoring time node, it includes: Construct the historical water quality data matrix A[a ij ] n×4 ; a ij It represents the score of the jth data indicator of the i-th sampling; By a ij Calculate the weight p of the jth data index of the i-th sampling ij : Calculate the entropy weight e of the jth data indicator j : Calculate the coefficient of variation g of the jth data indicator j : g j =1-e j (j=1,2,3,4); Calculate the weight w of the jth data indicator j : Through the water quality scoring model, the scores Z of various data indicators of the reclaimed water to be treated are obtained, and the comprehensive score TS of the reclaimed water to be treated is calculated based on the scores Z of various data indicators of the reclaimed water; <h2 style=";text-align:left;direction:ltr">TS=W1*Z<h2 style=";text-align:left;direction:ltr"> G <h2 style=";text-align:left;direction:ltr"> +W2*Z<h2 style=";text-align:left;direction:ltr"> S <h2 style=";text-align:left;direction:ltr"> +W3*Z<h2 style=";text-align:left;direction:ltr"> P <h2 style=";text-align:left;direction:ltr"> +W4*Z<h2 style=";text-align:left;direction:ltr"> O <h2 style=";text-align:left;direction:ltr"> ; Among them, W1 is the weight of the particle size data in the water, W2 is the weight of the salt content data in the water, W3 is the weight of the pH value data in the water, and W4 is the weight of the oxygen content data in the water.

4. The intelligent reclaimed water treatment method according to claim 3, characterized in that: The setting of the current grey water treatment strategy and the current grey water monitoring cycle includes: According to the comprehensive score TS of the reclaimed water, the water quality status of the reclaimed water to be treated is judged, the corresponding monitoring cycle is set, and the time interval from the current monitoring time node to the next time node is determined; Get the index score Z of the particle size data in the water at the current monitoring time node G and water salinity data index score Z S ; If the index score of the particle size data in water is Z G and water salinity data index score Z S If they all reach their respective set thresholds, they enter the deep processing stage; The pretreatment stage includes: removing particulate impurities from the reclaimed water and desalting the reclaimed water; Obtain the particle size data change ΔZ during the removal of reclaimed water particles G And the salt content data ΔZ during the desalination process of reclaimed water S ; Generate the particle size correction value Z in water G ', Z G '=(Z G -ΔZ G ); Correction value Z of salt content data in water desalination process S ', Z S '=(Z S -ΔZ S ); Based on the change of particle size data ΔZ G And the salt content data ΔZ S , generate water quality correction parameter B; Based on the water quality correction parameter B, generate the pH correction value Z in the water P ' and the oxygen content correction value Z in water O '; The deep processing stage includes: Perform water quality acid-base balance treatment based on the corrected pH value of the water; Deoxygenation treatment is performed based on the corrected oxygen content in the water.

5. The intelligent reclaimed water treatment method according to claim 4, characterized in that: The setting of the corresponding monitoring period includes: Generate the average value μ of the comprehensive score TS of the reclaimed water through historical data, and the standard deviation σ of the comprehensive score TS of the reclaimed water in the historical data; Based on the average value μ and the standard deviation σ, the water quality status is divided, and according to the division of water quality status, the update time node of the comprehensive score of reclaimed water is formulated; Based on the water purification test, determine the adjustment range of the sampling frequency (u min ,u max ); u min is the minimum scale factor of the sampling frequency, u max is the maximum scaling factor of the sampling frequency; If TS∈(μ-σ,μ+σ), the current reclaimed water to be tested is defined as primary reclaimed water, the current water quality sampling frequency T0 is maintained, and the remaining amount of the primary acid-base reagent of the deoxidizer is predicted; If TS∈(0,μ-σ), the current water to be tested is defined as secondary water, and the sampling frequency T of the current water quality is corrected. m is the current water quality sampling frequency proportional factor, T = T0 / (1+m); If TS∈(μ+σ,+∞), the current water to be tested is defined as third-grade water, and the sampling frequency T of the current water quality is corrected. T = T0 / (1-m).

6. The intelligent reclaimed water treatment method according to claim 4, characterized in that: The method of removing particulate impurities from the reclaimed water comprises: Set the index threshold Z of the particle size data in water based on the water use index G (min); And based on the index score Z of the current water particle size data G , calculate the amount of coagulant input; Real-time monitoring of particle size data changes ΔZ during water particle impurity removal G ; When the index score of the particle size data in water is Z G When the index threshold is reached, the remaining colloids and suspended matter are removed by filtration; Get the particle size data change ΔZ at this time G (max).

7. The intelligent reclaimed water treatment method according to claim 6, characterized in that: The calculation of the amount of coagulant input includes: The coagulant input test was conducted to obtain the coagulant unit volume input coefficient k0; Calculate the amount of coagulant input Q; Q=k0*Z G *V; V is the volume of the water to be treated.

8. The intelligent reclaimed water treatment method according to claim 4, characterized in that: The desalination of the reclaimed water comprises: Set the salt content threshold Z of water based on water use indicators S (min); The indicator score Z is calculated based on the current water salinity data. S , calculate the time for water desalination in reverse osmosis; Real-time monitoring of salt content data changes ΔZ during the desalination process of reclaimed water S ; When the indicator score of the water salt content data is Z S When the indicator threshold is reached, obtain the granularity data change ΔZ at this time S (max).

9. The intelligent reclaimed water treatment method according to claim 4, characterized in that: Generate pH correction value Z in water P ' and the oxygen content correction value Z in water O ', including: Based on the change of particle size data ΔZ G And the salt content data ΔZ S , generate the water quality correction parameter B in the deep treatment stage, B = (B1, B2); B1=k1*ΔZ G +k2*ΔZ S ; B2=k3*ΔZ G +k4*ΔZ S ; k1 is the correction constant of the change of particle size data to pH value, k2 is the correction constant of the change of salt content data to pH value, k3 is the correction constant of the change of particle size data to oxygen content, k4 is the correction constant of salt content data to k2 to oxygen content; Generate pH correction value Z in water P ', Z P '=Z P -B1; And the oxygen content correction value Z in water O ', Z O '=Z O -B2; Among them, B1 is the correction parameter for pH value in the pretreatment stage, and B2 is the correction parameter for oxygen content in water in the pretreatment stage.

10. The intelligent reclaimed water treatment method according to claim 4, characterized in that: The deep processing stage includes: Calculate the minimum index score Z of the pH value data in the water at the current monitoring time P (min) WITH P (min)=Z P -B1=Z P -(k1*ΔZ G (max)+k2*ΔZ S (max)); Calculate the minimum index score Z of the oxygen content data in the water at the current monitoring time O (min) Z O (min)=Z O -B2=Z O -(k3*ΔZ G (max)+k4*ΔZ S (max)); The minimum index score Z according to the pH value data of water P (min), add acid and alkali reagents to adjust the pH value in the water to the target value; The minimum index score Z based on the oxygen content data in the water O (min), add deoxidizer to control the oxygen content in water to the target content.

Images