Intelligent monitoring method for ammonium ions in water body based on electrochromic response of Prussian blue analogue

Abstract

The invention discloses a water ammonium ion intelligent monitoring method based on Prussian blue analogue electrochromic response, and belongs to the technical field of environment monitoring. In order to solve the problems that a traditional water ammonium ion concentration monitoring method depends on chemical reagents, response lags behind, and continuous online monitoring is difficult, a response electrode is constructed by loading a prussian blue analogue on a transparent conductive substrate. And the ammonium ions are driven to be embedded into / separated from the electrode, so that reversible switching of oxidation-reduction states and accompanying in-situ remarkable color change are realized. An electrode color image is captured in real time by using an image acquisition system, and after color features are extracted through an image recognition algorithm, a color feature-ammonium ion concentration prediction model is established. The segmented model trained based on standard data sets of different concentration intervals supports concentration self-adaption, and real-time monitoring is achieved. The device takes reagent-free electrochromic sensing as a core, has continuous, lossless, quick response and strong anti-interference capability, and is particularly suitable for online ammonium ion monitoring of scenes such as aquaculture wastewater and municipal sewage.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of environmental monitoring, and particularly relates to a water body ammonium ion intelligent monitoring method based on a Prussian blue analogue electrochromic response, which is used for real-time monitoring and early warning of ammonium ion concentration in water. BACKGROUND

[0002] Water pollution has always been the focus of environmental monitoring, and water quality deterioration poses a threat to the ecosystem and human health. Ammonia nitrogen is one of the important indicators of water pollution, and its excessive standard may cause water eutrophication, fish poisoning and drinking water safety hazards. Ammonia nitrogen exists in two forms in water, ammonium ion and free ammonia, and its distribution is related to the pH of the water body. In most water environments, the pH is neutral, and ammonia nitrogen mainly exists in the form of ammonium ion. Therefore, in environmental monitoring, ammonium ion as an important indicator of pollution, its concentration reflects the accumulation and treatment effect of pollutants in water. The current detection methods include Nessler's reagent colorimetric method, ion selective electrode method and ion chromatography method, but they generally have problems such as complicated operation, detection lag, expensive instruments or reagent consumption, which are difficult to meet the needs of on-site continuous monitoring and intelligent management.

[0003] In recent years, electrochromic materials have shown good application potential in the field of sensors due to their intuitive color response and fast response speed. In particular, Prussian blue and its analogues have good selectivity and reversible intercalation stability for ammonium ions under applied voltage, and different oxidation states are presented during the intercalation and deintercalation of ammonium ions, realizing reversible color change. However, existing researches mainly focus on reversible adsorption or capacitive deionization behavior, and the quantitative relationship between color change and specific ion concentration has not been systematically constructed and applied. Combined with image recognition and intelligent recognition model, it is expected to develop an intelligent monitoring method for water body ammonium ions without chemical reagents and complex operations. SUMMARY

[0004] The present application provides a water body ammonium ion intelligent monitoring method based on Prussian blue analogue electrochromic response, which solves the problems of existing water body ammonium ion monitoring methods, such as dependence on chemical reagents, complicated operation, poor real-time performance, and difficulty in on-site deployment. The method constructs a visual monitoring strategy that integrates selective electrochemical intercalation / deintercalation, image recognition analysis and intelligent model prediction, which can realize in-situ visual identification, continuous dynamic monitoring and remote early warning of ammonium ion concentration without reagents and electrode replacement, and is particularly suitable for application scenarios such as aquaculture wastewater, aquaculture and sewage treatment.

[0005] The present application realizes the monitoring of ammonium ions in real time without chemical reagents and complex operations by using the electrochromic characteristics of the Prussian blue analog response electrode, which produces a significant color change related to the concentration of ammonium ions at a specific potential, and the intelligent analysis of the image recognition algorithm. The method controls the ammonium ion exchange process by setting the embedding potential and de-embedding potential and their duration, and extracts color feature values by image acquisition, and combines various machine learning algorithms to build a prediction model of color and ammonium ion concentration in different intervals and establish a multi-model library, thereby realizing high-sensitivity detection of ammonium ion concentration, and adaptively switching different prediction models to adapt to different water background conditions and monitoring requirements. The method supports setting the concentration threshold according to the user scenario, realizes remote early warning and system linkage control. The method of the present application not only avoids the problems of the traditional monitoring method, but also emphasizes the intelligent feedback and model-driven mechanism at the system level, strengthens the real-time accuracy and scene adaptability of the change of ammonium ion concentration in complex environment, and improves the system stability, response speed and intelligent level.

[0006] The present application is a water body ammonium ion intelligent monitoring method based on the electrochromic response of Prussian blue analog:

[0007] According to the following steps:

[0008] Step one, build a working electrode: load Prussian blue analog material with reversible electrochromic performance and selective response to ammonium ions on a conductive glass substrate to form a working electrode;

[0009] Step two, assemble an electrochemical monitoring system: immerse the working electrode, the counter electrode and the reference electrode in the water to be tested, connect the electrochemical control module with periodic potential control function, set the embedding potential and duration of the working electrode and the de-embedding potential and duration, to drive the reversible embedding / de-embedding of ammonium ions in the working electrode;

[0010] Step three, collect electrode color image: in a closed and uniformly illuminated environment, use an image acquisition system to collect the working electrode image after the embedding and de-embedding process of ammonium ions in the working electrode is completed;

[0011] Step four, image preprocessing and color feature extraction: electrode region recognition, color space conversion, brightness normalization and noise removal processing are performed on the collected image, and color feature values are extracted as input variables for the subsequent color-concentration prediction model;

[0012] Step five, constructing a color-concentration prediction model library: ammonium ionic liquid with mass concentration of 1-1000 mg / L is divided into several sub-intervals according to concentration gradient, and standard solutions are configured respectively; for each sub-interval, different working electrode intercalation / deintercalation potentials and their duration parameters are set, and the image and color characteristics of the working electrode in the standard solution are obtained according to the methods described in steps two, three and four; based on the color characteristic-ammonium ion concentration data set collected in each sub-interval, a color-concentration prediction model is trained respectively by using a machine learning algorithm, and is stored in the model library;

[0013] Step six, intelligent monitoring and early warning output: in the real-time monitoring process, the color characteristic value extracted from the collected image is input into the color-concentration prediction model to obtain the predicted value of the ammonium ion concentration in the current water body; when the predicted value exceeds the applicable concentration interval of the current color-concentration prediction model, the working electrode intercalation / deintercalation potential and duration parameters are automatically adjusted, and other color-concentration prediction models in the model library are switched to, so as to realize continuous monitoring in a wide concentration range; the monitoring system supports the user to set an ammonium ion concentration threshold, and automatically triggers an audible and light alarm or remotely sends early warning information through a communication module when the predicted value exceeds the set ammonium ion concentration threshold.

[0014] The working electrode and the counter electrode are platinum, titanium or graphite electrodes. The reference electrode is an Ag / AgCl or Hg / Hg2Cl2 electrode.

[0015] The "suitable sub-interval" described in the application refers to a plurality of prediction concentration intervals divided in the concentration range of 1-1000 mg / L according to the color change amplitude and its resolvable accuracy of the CuHCF electrode under different potential and intercalation / deintercalation duration conditions. Since the color-concentration response range of the electrode under the same potential and time conditions is limited, if a single model is directly used to cover the full range, the prediction accuracy will be significantly reduced due to non-linear distortion. For example, at a lower potential and shorter time, the model is suitable for a higher concentration interval; at a higher potential and longer time, the model is suitable for a lower concentration interval, but saturation may occur for high concentrations. Therefore, the total concentration range is divided into a plurality of sub-intervals, each of which is matched with the optimal potential-time combination condition, and sample data is collected to establish a prediction model (R 2 ≥0.98) and stored in the model library.

[0016] Further, the Prussian blue analog is copper ferrocyanide or cobalt ferrocyanide.

[0017] Further, the working electrode is a thin film electrode formed by loading the Prussian blue analog on the surface of ITO or FTO conductive glass by drop coating, spin coating or electrodeposition, and the thickness of the thin film is 50-500 nm.

[0018] Further, the periodic potential control includes ion intercalation stage and deintercalation stage, respectively controlling ammonium ions into or release out of the electrode material; the intercalation potential is-0.5~0.7V vs. SHE, the deintercalation potential is 1.0~2.0V vs. SHE, and the intercalation and deintercalation duration ranges are 0.5~60 s and 1~100 s respectively; different potential and duration parameters will affect the color response rate and the number of intercalated ions of the electrode material, thereby affecting the prediction accuracy and the adaptive concentration range.

[0019] Further, the image acquisition system includes a ring-shaped LED light source with a color temperature of 4500-6000 K, a fixed-angle high-definition camera with a resolution of no less than 1920x1080, and a light collecting cavity with a black anti-reflective inner wall; image acquisition is performed immediately after each intercalation and deintercalation reaction is completed.

[0020] Further, the image preprocessing step includes: automatically identifying the electrode area using edge detection or image segmentation algorithm; converting the original RGB image to HSV color space for brightness normalization processing; applying Gaussian filter or median filter algorithm to the electrode image to remove light noise; extracting RGB or HSV channel average value, dominant color or color histogram as color feature input variable.

[0021] Further, the machine learning algorithm is trained based on the color feature values of the electrode images of different concentrations of ammonium ion standard solution collected under different intercalation potential, deintercalation potential and duration conditions, and the fitting accuracy R 2 is no less than 0.98 and the average absolute error is no higher than 5%; the machine learning algorithm is multiple linear regression model, support vector regression model, artificial neural network model, decision tree regression model or random forest model.

[0022] Further, the automatic adjustment of intercalation / deintercalation potential and duration parameters, wherein the system automatically switches to other adaptive models in the model library according to the detection signal when the concentration prediction result exceeds the applicable concentration interval of the current model, and adjusts the electrochemical operation parameters and switches to other adaptive models in the model library; wherein the electrochemical operation parameters are intercalation, deintercalation potential and duration.

[0023] Further, the intelligent monitoring method is based on program-controlled cyclic detection, which sets periodic intercalation-deintercalation reaction electrochemical parameters, image acquisition and identification prediction process, realizes automatic operation and data updating without manual intervention.

[0024] Further, the applicable concentration interval of each prediction model in step five refers to the fitting accuracy R2 A concentration range of not less than 0.98 and an average absolute error of not more than 5%.

[0025] Further, the intelligent monitoring method supports the user to set the ammonium ion concentration threshold according to different monitoring scenes, and automatically triggers an audible and light alarm or sends a remote early warning information through a communication module when the predicted value exceeds the set threshold, prompting the user to intervene.

[0026] Further, the intelligent monitoring method supports a remote communication module and a data recording function, has the functions of real-time monitoring of ammonium ion concentration, historical trend recording, local storage of data and wireless uploading, and realizes remote monitoring, intelligent early warning and traceability of monitoring data.

[0027] The present application comprises the following beneficial effects:

[0028] The present application provides an intelligent monitoring method for ammonium ions in water based on the electrochromic response of Prussian blue analogs, which combines the selectivity of electrochemical reaction and the intuitiveness of color response, realizes high sensitivity, low interference and visual intelligent monitoring of ammonium ions in water without additional chemical reagents. Through the synergistic effect of image processing algorithm and concentration prediction model, the change trend of ammonium ion concentration can be accurately reflected, and the model has self-adaptive switching ability and automatic warning ability, which has good site adaptability and promotion prospect. Its beneficial effects mainly reflect in the following aspects:

[0029] 1. In-situ electrochromic feedback mechanism: the present application utilizes the reversible color change of Prussian blue analog materials during the embedding and de-embedding process of ammonium ions, realizes reagent-free, stable, repeatable and visual in-situ monitoring feedback, avoids the pollution, complicated steps and response lag problems caused by traditional chemical colorimetric method, and has good response consistency and operation simplicity.

[0030] 2. High selectivity and anti-interference ability: the Prussian blue analog electrode selected by the present application has a preferential embedding ability for ammonium ions, even in actual complex water bodies containing Na + , K + and other common coexisting ions, it still maintains a stable response rule, ensuring the accuracy and selectivity of the monitoring process.

[0031] 3. Image intelligent analysis and model dynamic adjustment: the present application establishes a color-concentration prediction model library through image acquisition and intelligent algorithm (color recognition, machine learning), supports dynamic switching of the optimal model according to different water body backgrounds and concentration ranges. Combined with concentration prediction and process control, it realizes continuous monitoring without replacing the electrode, greatly improves the operation efficiency and reduces the cost.

[0032] 4. Early warning and intelligent operation and maintenance: the application supports users to set concentration threshold, and automatically warns when it exceeds the threshold, and records data for historical trend tracking and abnormality identification. The full-process automation design of "embedding identification-image acquisition-concentration prediction-embedding recovery" makes it suitable for online deployment and intelligent operation and maintenance in various scenes such as aquaculture wastewater and domestic sewage. BRIEF DESCRIPTION OF DRAWINGS

[0033] Figure 1 Figure 1 is a schematic diagram of the intelligent monitoring platform structure for water body ammonium ions based on CuHCF Prussian blue analogs;

[0034] Figure 2 Figure 5 is a cyclic voltammetry response curve of the CuHCF electrode in different cations;

[0035] Figure 3 Figure 6 is a color state change diagram of the CuHCF electrode before and after ammonium ion embedding, which gradually changes from the initial orange yellow to the deep red after embedding ammonium ions from left to right;

[0036] Figure 4 Figure 7 is a fitting effect diagram of the actual value and predicted value of the constructed ammonium ion concentration-color feature prediction model;

[0037] Figure 5 Figure 8 is a result diagram of ammonium ion concentration change under 30 times of dynamic cycle prediction. DETAILED DESCRIPTION

[0038] In order to make the purpose, technical scheme and advantages of the embodiments of the present application more clear and obvious, the spirit of the present application will be described in detail below, and any person skilled in the art can make changes and modifications to the technology taught by the present application without departing from the spirit and scope of the present application after understanding the embodiments of the present application.

[0039] The schematic embodiments of the present application and their descriptions are used to explain the present application, but not as a limitation of the present application.

[0040] Embodiment 1:

[0041] The present embodiment discloses a water body ammonium ion intelligent monitoring method based on CuHCF Prussian blue analog electrochromic response, which realizes rapid judgment and continuous monitoring of ammonium ion concentration in water body by combining reversible embedding and de-embedding mechanism and image color recognition algorithm. Figure 1 The intelligent monitoring platform structure schematic diagram relied on by the present method is shown, which mainly includes an electrochemical reaction module, an image acquisition module, a color recognition module, a concentration prediction module and a system control module.

[0042] The specific implementation steps of the embodiment are as follows:

[0043] 1. Construction of CuHCF thin film electrodes

[0044] CuHCF powder was synthesized via a coprecipitation method. Specifically, solution A was prepared by dissolving 5 mM K3[Fe(CN)6] in 50 mL of ultrapure water, and solution B was prepared by dissolving 10 mM CuSO4 in 50 mL of ultrapure water. Under continuous stirring (600 rpm), solutions A and B were simultaneously added dropwise to 100 mL of ultrapure water using a constant flow pump at a rate of 0.5 mL / min to ensure thorough mixing. After the reaction was complete, the precipitate was collected by vacuum filtration and washed three times alternately with ultrapure water and ethanol to remove unreacted ions and byproduct impurities. The resulting precipitate was then dried in a vacuum drying oven at 70°C. Subsequently, the obtained CuHCF powder was added to a 5% Nafion solution (1 μL / mg) and ethanol (1.5 μL / mg) solvent and ultrasonically dispersed for 30 min to obtain a homogeneous slurry. The slurry was uniformly coated onto the pretreated ITO conductive glass surface using a coating machine to form a CuHCF film electrode, which was then naturally dried at room temperature for later use. The final film thickness was approximately 300 nm.

[0045] 2. Electrochemical response of CuHCF thin film electrode

[0046] Cyclic voltammetry curves were performed on the CuHCF membrane electrode in 1 M NH4Cl, 1 M KCl, 1 M NaCl, 0.5 M CaCl2, and 0.5 M MgCl2. Figure 2 As shown, reversible redox peaks can be observed in its cyclic voltammetry curves, reflecting the reversible Faraday reaction mechanism caused by the ion insertion / extraction process, and CuHCF in NH4 + The reduction / oxidation peak current response in solution compared to Na + Mg 2+ The plasma was significantly enhanced, reflecting its ability to react with NH4. + Its selective responsiveness. Its insertion order for different cations is: NH4 + (0.93 V) > K + (0.88 V) > Na + (0.78 V) > Ca 2+ (0.77 V) = Mg 2+ (0.77 V). The order of current response intensity for different cations is: NH4 + (5.34 A·g) -1 K + (3.41 A·g) -1 Na + (3.09A·g) -1 Ca2+ (0.91 A·g -1 ) > Mg 2+ (0.03 A·g -1 ). This indicates that CuHCF has a preferential response to NH4 + . During the ion intercalation process, CuHCF is observed to gradually change from orange-yellow to deep red; while during the deintercalation process, the electrode returns to the initial color. Therefore, CuHCF not only has reversibility and selectivity for NH4 + intercalation reaction, but also has an electrochromic response, and the color change can be used as an in-situ optical indication of NH4 + intercalation / deintercalation.

[0047] 3. Intercalation / deintercalation driving and color image acquisition

[0048] The CuHCF film electrode is used as the working electrode, combined with a platinum counter electrode and an Ag / AgCl reference electrode, to form a three-electrode system, which is immersed in the water sample to be measured. The intercalation potential is set to -0.1 V vs. SHE, maintained for 3 s, to drive the intercalation of ammonium ions into the working electrode; immediately after the end of the intercalation reaction, the image is taken in a closed light chamber, and the electrode image is acquired (the image acquisition system includes a ring-shaped LED light source with a color temperature of 4500-6000 K, a fixed-angle high-definition camera with a resolution of not less than 1920x1080, and a light chamber with black anti-glare inner wall; image acquisition is performed immediately after the end of each intercalation and deintercalation reaction). The image is shown in Figure 3 from left to right, the images collected after the end of the intercalation reaction in standard solutions from 5 mg / L to 170 mg / L, the color gradually changes from orange-yellow to deep red, which reflects the significant electrochromic response characteristics of the material to NH4 + . After the end of the intercalation process, a set of deintercalation potential (1.2 V vs. SHE, 5 s) is applied to drive the release of intercalated ammonium ions back into the water body, and the electrode image is collected immediately after the end of the deintercalation reaction for subsequent judgment of whether the electrode color has returned to the initial state.

[0049] 4. Image processing and color-concentration prediction model construction

[0050] Image processing uses edge recognition algorithm to locate the electrode reaction area, ensuring the consistency of the extracted area; then the image is converted from RGB space to HSV space for normalization processing; on this basis, further local noise and pixel fluctuations are removed by Gaussian filtering and other methods to improve image quality and recognition stability; finally, the average value of the RGB three channels in the electrode area is extracted as the color feature, which is used as the input variable of the subsequent color-concentration prediction model.

[0051] The color-concentration prediction model construction steps are as follows: based on the configured known concentration standard solution, the image collected after the foregoing electrochemical treatment is subjected to feature extraction, a color feature and corresponding concentration dataset is constructed, the dataset is divided into a training set and a test set according to a 7:3 ratio, the RGB channel mean is taken as an input feature, the ammonium ion concentration is taken as an output variable, different machine learning algorithms are used to train the color-concentration prediction model, and 10-fold cross-validation is performed.

[0052] To realize wide-range concentration recognition in different scenarios, color feature data of standard ammonium ion solution is collected under different electrochemical operation parameters, three color-concentration prediction models are respectively established, and are stored in a model library. The fitting results of the three models are as shown in Figure 4 . Among them, model A is a medium concentration segment model, applicable to a concentration interval of 5-170 mg / L, electrochemical conditions are embedding potential-0.10 V vs. SHE, duration 3 s, de-embedding potential 1.2 V vs. SHE, duration 5 s, trained based on artificial neural network algorithm, test set fitting accuracy R 2 =0.993, root mean square error RMSE=3.89 mg / L; model B is a low concentration segment model, applicable to a concentration interval of 1-20 mg / L, electrochemical conditions are embedding potential-0.20 V vs. SHE, duration 6 s, de-embedding potential 1.2 V vs. SHE, duration 5 s, trained based on support vector regression algorithm, test set fitting accuracy R 2 =0.989, root mean square error RMSE=0.608 mg / L; model C is a high concentration segment model, applicable to a concentration interval of 170-850 mg / L, electrochemical conditions are embedding potential-0.10 V vs. SHE, duration 1 s, de-embedding potential 1.2 V vs. SHE, duration 5 s, trained based on random forest regression algorithm, test set fitting accuracy R 2 =0.989, root mean square error RMSE=20.77 mg / L. The three models cover different concentration intervals under their respective electrochemical parameters, the system can automatically switch and adjust the embedding / de-embedding potential and duration according to the real-time monitoring results and the applicable interval of the model, realize wide-range continuous monitoring, and the prediction accuracy is maintained at R 2 ≥0.98.

[0053] 5. Continuous cyclic monitoring

[0054] To realize real-time dynamic tracking of ammonium ion concentration in water, the method constructs a continuous cyclic monitoring mechanism based on color change of CuHCF electrode. The mechanism relies on the system control module to automatically coordinate the four processes of "embedding recognition-image acquisition-concentration prediction-de-embedding recovery", and can realize multi-round, non-manual intervention cyclic operation.

[0055] The specific process is as follows: first, by applying a set of embedding potential (-0.1 V vs. SHE, 3 s), ammonium ions are driven to embed into the CuHCF electrode material, triggering the electrode color to change from orange yellow to deep red; then the image acquisition module immediately acquires the electrode image, the color recognition module completes image preprocessing and color feature extraction, and the concentration prediction module outputs the current ammonium ion concentration value in the water body in real time. After identification, the system automatically switches to the de-embedding stage, applies a de-embedding potential (1.2 V vs. SHE, 5 s), and promotes the embedded ammonium ions to release back into the water body; at the same time, the electrode image is collected again, and the color difference comparison (AE calculation) with the initial state is performed to determine whether the electrode color has returned to the initial state; if the AE value is less than 2, it is judged that the color has completely recovered, and the next round of test can be performed, if the color has not recovered, the desorption time is automatically extended and a reminder is issued.

[0056] Figure 5 The results of the ammonium ion concentration change under 30 dynamic cycles are shown in the graph, and the results show that in the actual water body, the monitoring platform can realize sustainable operation in the whole cycle process, realize high-frequency, continuous, reagent-free, visual monitoring of ammonium ion concentration in the target water body, and has good repeatability and long-term stability. The cycle mechanism not only improves the monitoring efficiency and response frequency, but also can set the cycle interval and monitoring threshold according to different scenes, has good adaptability and engineering expansion potential. Combined with remote communication and data recording module, it can also be expanded into an intelligent water quality monitoring system with online monitoring-dynamic recording-alarm integrated.

[0057] The above examples verify the effectiveness of the intelligent monitoring method in selective response, color recognition and concentration prediction, and have the advantages of simple operation, rapid response, strong applicability, etc.

Claims

1. A smart monitoring method for ammonium ions in water based on the electrochromic response of Prussian blue analogues, characterized in that, It is done in the following steps: Step 1: Constructing the working electrode: A Prussian blue analog material with reversible electrochromic properties and selective response to ammonium ions is loaded onto a conductive glass substrate to form the working electrode; Step 2: Construct an electrochemical monitoring system: Immerse the working electrode, counter electrode, and reference electrode together in the water body to be tested, connect an electrochemical control module with periodic potential control function, and set the insertion potential and duration of the working electrode and the deintercalation potential and duration to drive the reversible insertion / deintercalation of ammonium ions in the working electrode. Step 3: Acquire electrode color images: In a closed, uniformly lit environment, use an image acquisition system to acquire images of the working electrode after the ammonium ion insertion and extraction processes are completed; Step 4: Image preprocessing and color feature extraction: Electrode region identification, color space conversion, brightness normalization, and noise removal are performed on the acquired images to extract color feature values, which are used as input variables for the subsequent color-density prediction model. Step 5: Construct a color-concentration prediction model library: Divide the ammonium ion liquid with a mass concentration of 1–1000 mg / L into several sub-intervals according to the concentration gradient, and prepare standard solutions for each sub-interval; For each sub-interval, set different working electrode insertion / extraction potentials and their duration parameters, and obtain the image of the working electrode in the standard solution and its color characteristics according to the methods described in Steps 2, 3 and 4. Based on the color feature-ammonium ion concentration dataset collected from each sub-interval, color-concentration prediction models were trained using machine learning algorithms and stored in the model library; Step 6, Intelligent Monitoring and Early Warning Output: During real-time monitoring, the color feature values ​​extracted from the collected images are input into the color-concentration prediction model to obtain the predicted value of ammonium ion concentration in the current water body; When the predicted value exceeds the applicable concentration range of the current color-concentration prediction model, the system automatically adjusts the working electrode insertion / extraction potential and duration parameters, and switches to other color-concentration prediction models in the model library to achieve continuous monitoring over a wide concentration range. The monitoring system supports users in setting ammonium ion concentration thresholds. When the predicted value exceeds the set ammonium ion concentration threshold, it automatically triggers an audible and visual alarm or sends a warning message remotely via the communication module.

2. The intelligent monitoring method for ammonium ions in water based on the electrochromic response of Prussian blue analogues according to claim 1, characterized in that, The Prussian blue analogues mentioned are copper ferrocyanide or cobalt ferrocyanide.

3. The intelligent monitoring method for ammonium ions in water based on the electrochromic response of Prussian blue analogues according to claim 1, characterized in that, The working electrode is formed by loading a Prussian blue analogue onto the surface of ITO or FTO conductive glass using drop coating, spin coating, or electrodeposition to form a thin film electrode with a thickness of 50–500 nm.

4. The intelligent monitoring method for ammonium ions in water based on the electrochromic response of Prussian blue analogues according to claim 1, characterized in that, The periodic potential control includes potential control for the ammonium ion insertion and extraction stages; the insertion potential is -0.5~0.7V vs. SHE relative to the standard hydrogen electrode, and the extraction potential is 1.0~2.0V vs. SHE relative to the standard hydrogen electrode, with insertion and extraction durations ranging from 0.5 to 60 s and 1 to 100 s, respectively.

5. The intelligent monitoring method for ammonium ions in water based on the electrochromic response of Prussian blue analogues according to claim 1, characterized in that, The image acquisition system includes a ring-shaped LED light source with a color temperature of 4500–6000 K, a fixed-angle high-definition camera with a resolution of not less than 1920×1080, and a light-collecting cavity with a black anti-reflective inner wall; image acquisition is performed immediately after each embedding and de-embedding reaction.

6. The intelligent monitoring method for ammonium ions in water based on the electrochromic response of Prussian blue analogues according to claim 1, characterized in that, The image preprocessing steps include: automatically identifying the electrode region using edge detection or image segmentation algorithms; converting the original RGB image to HSV color space for brightness normalization; applying Gaussian filtering or median filtering algorithms to the electrode image to remove illumination noise; and extracting the average value of RGB or HSV channels, the dominant color, or the color histogram as color feature input variables.

7. The intelligent monitoring method for ammonium ions in water based on the electrochromic response of Prussian blue analogues according to claim 1, characterized in that, The aforementioned training of color-concentration prediction models using machine learning algorithms is based on the color feature values ​​of electrode images of ammonium ion standard solutions at different concentrations, acquired under conditions of different insertion potentials, extraction potentials, and durations. The fitting accuracy R0 is [missing value]. 2 The mean absolute error is not less than 0.98 and not more than 5%; the machine learning algorithm is multiple linear regression, support vector regression, artificial neural network, decision tree regression or random forest.

8. The intelligent monitoring method for ammonium ions in water based on the electrochromic response of Prussian blue analogues according to claim 1, characterized in that, The automatic adjustment of the working electrode insertion / extraction potential and duration parameters includes automatic adjustment of the intelligent monitoring support model for automatic calling and switching. When the concentration prediction result exceeds the applicable concentration range of the current model, the intelligent monitoring adjusts the electrochemical operation parameters according to the detection signal and switches to other suitable color-concentration prediction models in the model library. The electrochemical operation parameters are insertion and extraction potentials and duration.

9. The intelligent monitoring method for ammonium ions in water based on the electrochromic response of Prussian blue analogues according to claim 1, characterized in that, The intelligent monitoring system supports program-controlled cyclic detection. By setting periodic working electrode insertion / deintercalation reaction electrochemical parameters, image acquisition and recognition prediction processes, it achieves automatic operation and data updates without human intervention.

10. The intelligent monitoring method for ammonium ions in water based on the electrochromic response of Prussian blue analogues according to claim 1, characterized in that, In step five, the applicable concentration range for each prediction model refers to the range under the corresponding electrochemical operating parameters that ensures the fitting accuracy R. 2 The concentration range is not less than 0.98 and the mean absolute error is not higher than 5%.

Images