A device and method for detecting chloride ions in industrial wastewater based on conductivity measurement
By combining barium salt pretreatment and silver salt precipitation reaction with conductivity measurement and support vector machine regression model, the accuracy and stability issues of chloride ion detection in complex industrial wastewater were solved, achieving automated and real-time monitoring.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- SHANDONG UNIV
- Filing Date
- 2026-04-27
- Publication Date
- 2026-06-12
Smart Images
Figure CN122193314A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the fields of environmental monitoring and water quality testing, and in particular to a device and method for detecting chloride ions in industrial wastewater based on conductivity measurement. Background Technology
[0002] Currently, the detection of chloride ions in industrial wastewater mainly relies on traditional chemical analysis methods (such as silver nitrate titration) and ion chromatography. Among these, silver nitrate titration uses Ag... + With Cl - Quantitative analysis can be achieved by generating AgCl precipitate, but this method is cumbersome, requiring manual determination of the titration endpoint, and is difficult to automate and continuously detect. While ion chromatography offers high detection accuracy, its instruments are bulky, and single-detection cycles are long, generally requiring a laboratory environment, making it unsuitable for real-time monitoring and online detection needs in industrial settings.
[0003] Conductivity detection technology has promising applications in water quality monitoring due to its simple structure, stable response, and ease of online and automated implementation. However, in complex industrial wastewater systems, multiple coexisting ions can have a cumulative effect on conductivity, leading to reduced detection accuracy of target ions. To improve detection selectivity, some studies have introduced silver nitrate precipitation reactions to convert chloride ions in the solution into silver chloride precipitate, thereby altering the ionic composition of the solution and causing changes in conductivity, thus achieving indirect detection of chloride ions. However, the above-mentioned conductivity detection methods based on precipitation reactions still have limitations: wastewater often contains sulfate ions, carbonate ions, suspended particulate matter, and various dissolved salts. These coexisting components can interfere with conductivity measurements, affecting the stability and reliability of the detection results. Summary of the Invention
[0004] To address the shortcomings of existing technologies, the present invention aims to provide a device and method for detecting chloride ions in industrial wastewater based on conductivity measurement. By pretreating the sample with barium salts to reduce interference from coexisting ions, and combining this with the multi-stage conductivity change characteristic analysis caused by silver salt precipitation reaction, stable quantitative detection of chloride ions in complex industrial wastewater can be achieved.
[0005] To achieve the above objectives, the present invention is implemented through the following technical solution: In a first aspect, embodiments of the present invention provide an industrial wastewater chloride ion detection device based on conductivity measurement, comprising a housing, wherein a fluid reaction and mixing module, a dynamic detection module, a control module and an intelligent analysis module are installed inside the housing; The fluid reaction and mixing module includes a reaction unit and multiple peristaltic pumps. The fluid reaction and mixing module is connected to at least a sample container, a barium salt reagent container, a silver salt reagent container, and a waste liquid container. The dynamic detection module includes a conductivity meter, which is connected to the reaction unit. The peristaltic pump and conductivity meter are both connected to the control module. The control module can add barium nitrate reagent to the reaction unit first, and then silver nitrate reagent, by controlling the peristaltic pump. The control module can also calculate the chloride ion content in the industrial wastewater based on real-time conductivity data and the intelligent analysis module.
[0006] As a further implementation, the housing is equipped with four peristaltic pumps, arranged in a double row and double column. Each peristaltic pump is connected to a sample container, barium nitrate container, silver nitrate container, and waste liquid container.
[0007] As a further implementation, the sample container, barium nitrate container, silver nitrate container, and waste liquid container are respectively connected to the reaction unit through reaction pipelines, and the peristaltic pump is installed on the corresponding reaction pipeline.
[0008] As a further implementation, the reaction unit is located on the same side of each peristaltic pump, and the conductivity meter is located below the peristaltic pumps and the reaction unit.
[0009] As a further implementation, the intelligent analysis module establishes a chloride ion concentration prediction relationship based on a concentration prediction model, and preferably uses a support vector machine regression model to quantitatively calculate the chloride ion concentration.
[0010] As a further implementation, the input features for constructing the chloride ion concentration prediction model include initial conductivity A, pre-treated conductivity B, conductivity after reaction completion C, and differential conductivity feature Δσ=CB. Preferably, it also includes pre-treated differential feature BA and dynamic conductivity features extracted based on the precipitation reaction process. The model outputs the chloride ion concentration value.
[0011] As a further implementation, a power module is also included, which is located above the conductivity meter and on the other side of the peristaltic pump.
[0012] Secondly, embodiments of the present invention also provide a method for detecting chloride ions in industrial wastewater based on conductivity measurement, employing the aforementioned detection device, comprising: The water sample to be tested is transported to the reaction unit, and the initial conductivity data of the sample is collected without the addition of reaction reagents. Barium nitrate solution was added to the reaction unit to remove interfering components; conductivity data after pretreatment were collected. Silver nitrate solution was added to the reaction unit, and conductivity change data were collected in real time during the reaction to obtain the dynamic conductivity characteristics during the reaction process. Multidimensional input features are constructed based on the collected initial conductivity, preprocessed conductivity, post-reaction conductivity, and differential conductivity features. The multidimensional input features are input into the concentration prediction model to calculate the chloride ion concentration.
[0013] As a further implementation, the conductivity signals before and after the reaction are compared and analyzed by differential conductivity detection, and the differential conductivity characteristic parameters are input into the concentration prediction model; wherein the differential conductivity characteristic parameters are Δσ=CB.
[0014] As a further implementation method, after the test is completed, the peristaltic pump connected to the waste liquid container is started to discharge the waste liquid; then clean water is delivered to the reaction unit for automatic cleaning.
[0015] The beneficial effects of this invention are as follows: This invention relates to an industrial wastewater chloride ion detection device based on conductivity measurement, integrating a fluid reaction and mixing module, a dynamic detection module, and a control module. The fluid reaction and mixing module includes a reaction unit and multiple peristaltic pumps, while the dynamic detection module includes a conductivity meter. Both the peristaltic pumps and the conductivity meter are connected to the control module. Under the regulation of the control module, the device can sequentially complete initial detection, barium salt pretreatment, silver salt precipitation reaction, and conductivity signal acquisition for the sample. By extracting multi-stage characteristics such as initial conductivity, conductivity after pretreatment, conductivity after reaction, and differential conductivity, and combining them with a concentration prediction model for calculation, the device can effectively reduce the interference of coexisting ions in complex industrial wastewater on chloride ion detection, improve the specific response characteristics of the conductivity signal to chloride ions and the stability of quantitative detection, and simultaneously achieve automation and continuous detection. Attached Figure Description
[0016] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.
[0017] Figure 1 This is a schematic diagram of the chloride ion detection device according to one or more embodiments of the present invention; Figure 2 This is a schematic diagram of the internal structure of a chloride ion detection device according to one or more embodiments of the present invention; Figure 3 This is a connection block diagram of a chloride ion detection device according to one or more embodiments of the present invention; Figure 4 This is a prediction capability diagram of the support vector machine model according to one or more embodiments of the present invention; Figure 5 These are 108 sets of data analysis curves for the specific detection of Cl- by conductivity method according to one or more embodiments of the present invention, wherein (a) represents the initial conductivity, (b) represents the conductivity after pretreatment, (c) represents the conductivity after the reaction is completed, and (d) is the differential conductivity characteristic parameter.
[0018] The components include: 1. Chamber; 2. Conductivity meter; 3. Reaction unit; 4. First peristaltic pump; 5. Second peristaltic pump; 6. Third peristaltic pump; 7. Fourth peristaltic pump; 8. Control module; 9. Cooling fan; 10. Sample container; 11. Barium nitrate container; 12. Silver nitrate container; 13. Touch screen display; 14. Power module; 15. Reaction pipeline; and 16. Driver. Detailed Implementation
[0019] It should be noted that the following detailed description is illustrative and intended to provide further explanation of the invention. Unless otherwise specified, all technical and scientific terms used in this invention have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.
[0020] For ease of description, the terms "upper," "lower," "left," and "right" appearing in this invention only indicate that they correspond to the upper, lower, left, and right directions of the accompanying drawings themselves, and do not limit the structure. They are merely for the purpose of facilitating the description of this invention and do not indicate or imply that the device or component referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention. In the description of this invention, terms such as "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.
[0021] Example 1: Existing conductivity detection methods based on precipitation reactions typically determine the reaction endpoint by identifying the abrupt change point in the conductivity titration curve. However, under conditions of high salinity or complex matrices, the conductivity change characteristics are often not obvious, making endpoint identification difficult and thus affecting the accuracy and stability of the detection results.
[0022] Based on this, this embodiment provides a device for detecting chloride ions in industrial wastewater based on conductivity measurement, such as... Figures 1-3 As shown, it includes a housing 1 and a reaction and mixing module, a dynamic detection module, a control module 8, an intelligent analysis module, etc. installed in the housing 1. The whole adopts a modular integrated structure to form an automated industrial wastewater chloride ion detection system.
[0023] The fluid reaction and mixing module includes a reaction unit 3 and multiple peristaltic pumps. The input end of the reaction unit 3 is connected to the sample container 10 and the reagent container. The dynamic detection module includes a conductivity meter 2, which is connected to the reaction unit 3 and is used to collect conductivity signals in real time during the reaction process. Both the peristaltic pumps and the conductivity meter 2 are electrically connected to the control module 8. The control module 8 can control the addition of reagents in sequence and, in conjunction with the intelligent analysis module, calculate the chloride ion content in the industrial wastewater based on the conductivity data.
[0024] like Figure 1 and Figure 2 As shown, the conductivity meter 2 is located on the lower left side of the housing 1, and the control module 8 is located on the right side of the conductivity meter 2. Each peristaltic pump is positioned above the conductivity meter 2, with the power module 14 located on the left side of the peristaltic pump area and the reaction unit 3 on the right. In this embodiment, the peristaltic pumps are all located above the reaction unit 3 and the conductivity meter 2. After the sample and reagent flow out of the pump, they can enter the reaction unit 3 from top to bottom in a short distance, simplifying the pipeline layout, avoiding residue, bubbles, and lag caused by excessively long pipelines, and improving the reaction and detection response speed. The modules are compactly arranged and highly integrated, adapting to the continuous testing needs of industrial sites.
[0025] Specifically, the fluid reaction and mixing module mainly performs sample delivery, reagent addition, mixing reaction, and waste liquid discharge functions. In this embodiment, four peristaltic pumps are arranged in a double row on the housing 1, namely, the first peristaltic pump 4, the second peristaltic pump 5, the third peristaltic pump 6, and the fourth peristaltic pump 7; the reagent containers include a barium nitrate container 11 and a silver nitrate container 12, such as... Figure 3 As shown, the sample container 10, barium nitrate container 11, silver nitrate container 12 and waste liquid container are connected to the reaction unit 3 through the reaction pipeline 15, and the first peristaltic pump 4, the second peristaltic pump 5, the third peristaltic pump 6 and the fourth peristaltic pump 7 are installed on the corresponding reaction pipeline 15.
[0026] In this embodiment, the reaction pipeline 15 is made of corrosion-resistant fluororubber, with an inner diameter of 0.3–0.8 mm and temperature resistance. At temperatures ranging from 20 to 200°C, a peristaltic pump can be used to achieve micro-volume, high-precision fluid delivery. The chamber volume of reaction unit 3 is approximately 35 mL. It is understood that in other embodiments, the size and material of the reaction pipeline 15 and the volume of reaction unit 3 can be adapted.
[0027] The dynamic detection module is the core detection component, and it also includes a corrosion-resistant electrode assembly and a data communication interface. In this embodiment, the conductivity meter 2 has a measurement accuracy of ±0.5%, and can continuously and dynamically acquire and display the conductivity of the water sample in its initial state, after barium nitrate pretreatment, and after the silver nitrate reaction. The electrodes adopt a polytetrafluoroethylene (PTFE) coated structure, suitable for strong acid and alkaline conditions with pH 0 to pH 14. The electrode assembly is connected to the cavity of the reaction unit 3 via threaded snaps, facilitating disassembly, calibration, and replacement. Furthermore, the conductivity meter 2 interacts with the control module 8 through the data communication interface, uploading conductivity data in real time to provide raw signals for chloride ion quantitative analysis.
[0028] The control module 8, centered on an MCU main control board, works with the driver 16 and touch display 13 to achieve automatic control and human-machine interaction. The driver 16 is located to the right of the peristaltic pump and above the reaction unit 3. The control module 8 can precisely control the operating sequence, injection volume, and reaction delay of each peristaltic pump, with an injection flow rate correction accuracy of 0.01 mL. During the detection process, the control module 8 first adds barium nitrate reagent to the reaction unit 3 for pretreatment according to a preset program, then adds silver nitrate reagent to cause a precipitation reaction. Simultaneously, it collects and plots the conductivity changes in real time. Figure 5 The reaction curve shown.
[0029] The intelligent analysis module is used to establish a chloride ion concentration prediction model based on multi-stage conductivity characteristics, realizing the quantitative conversion of conductivity signals to chloride ion concentration. The preferred model input features include the initial conductivity A of the water sample, the conductivity B after pretreatment, the conductivity C after the reaction, the differential conductivity feature Δσ=CB, and the pretreatment differential feature BA. In other embodiments, dynamic conductivity characteristics during the precipitation reaction process can be further introduced, including at least one of the following: conductivity change slope, time required to reach a steady state, and the area under the integral of the reaction curve. The model output is the chloride ion concentration value.
[0030] In this embodiment, the concentration prediction model is preferably constructed using a support vector machine regression model. During the model training phase, a training dataset is constructed using 108 sets of experimental data, including simulated wastewater samples and actual industrial wastewater samples; multi-stage conductivity characteristics are used as model inputs, and the actual chloride ion concentration of the corresponding samples is used as the model output. To reduce the impact of differences in the numerical range of different input features on the model calculation results, the input features are preferably standardized before model training and online prediction.
[0031] In this embodiment, cross-validation is used to train and optimize the support vector machine regression model. The penalty factor and kernel function parameters are optimized to establish a nonlinear mapping relationship between multi-stage conductivity characteristics and chloride ion concentration under complex industrial wastewater conditions. The trained support vector machine regression model is deployed in the intelligent analysis module, and the model is directly called to output chloride ion concentration results during online detection.
[0032] In other implementations, the concentration prediction model may also employ a random forest model, a K-nearest neighbor model, an XGBoost model, or an artificial neural network model, but a support vector machine regression model is preferred.
[0033] like Figure 1 As shown, the power module 14 is positioned above the conductivity meter 2 and to the left of the peristaltic pump. It features an internal active air-cooling structure, utilizing multiple cooling fans 9 for forced cooling to ensure long-term stable operation of the device in an industrial environment of 40–50 °C. In this embodiment, the power module 14 uses a 220V AC input and outputs 5V and 12V operating voltages via a DC-DC circuit to power each unit.
[0034] This embodiment also includes a cleaning and safety module to ensure long-term stable operation of the system. This module mainly includes an automatic cleaning program, a temperature monitoring unit, and a pipeline status detection unit. After each test, the system automatically performs drainage and cleaning operations to prevent reaction residues from affecting subsequent tests. Simultaneously, this module also has self-checking and log recording functions, supporting long-term continuous operation of the device.
[0035] This embodiment integrates modules such as sample injection, pretreatment, specific reaction, and conductivity detection into the same device, and uses control module 8 to uniformly schedule each peristaltic pump and detection unit to achieve automated operation of the detection process; and through volume optimization, the device is miniaturized and portable, thereby meeting the needs of rapid detection and real-time monitoring in industrial sites.
[0036] While keeping the overall structure of the device basically unchanged, quantitative detection of multiple ions can be achieved by replacing specific reaction reagents and matching the corresponding data analysis model.
[0037] Example 2: This embodiment provides a method for detecting chloride ions in industrial wastewater based on conductivity measurement. It employs the detection device described in Example 1, utilizing chloride ions (Cl... - ) and silver ions (Ag) +A specific precipitation reaction occurs, forming a poorly soluble silver chloride (AgCl) precipitate. During this reaction, the concentration of freely moving ions within the system undergoes regular changes, leading to significant fluctuations in the solution's conductivity. Conductivity signals throughout the entire reaction process are dynamically acquired using a conductivity meter 2, and multidimensional conductivity characteristic parameters are extracted. Combined with a trained and optimized intelligent analysis model, rapid and accurate quantitative detection of chloride ion concentration in water samples is achieved.
[0038] The specific testing process is as follows: Step (1) Sample injection and initial detection. The first peristaltic pump 4 is started to deliver the water sample to be tested to the reaction unit 3 at a constant flow rate. The delivery volume is set according to the volume of the reaction unit 3. After the water sample has stabilized in the reaction unit 3 for 30 to 60 seconds, the conductivity detector 2 is started to continuously collect 10 to 20 sets of initial conductivity data without adding any reaction reagents. After removing abnormal data, the average value is calculated as the initial conductivity benchmark value of the sample. This value is used to characterize the background conductivity level of the water sample itself. Step (2) Pretreatment to remove interfering ions. Start the second peristaltic pump 5. Based on the estimated volume of the water sample and the content of interfering ions, add barium nitrate solution quantitatively, at a volume of 5% to 10% of the water sample volume. After adding the barium nitrate solution, start the built-in stirring device of reaction unit 3 and stir for 1 to 2 minutes to ensure that the barium nitrate reacts fully with the interfering ions and that precipitation is complete. After stirring, let stand for 30 seconds to allow the precipitate to settle to the bottom of reaction unit 3.
[0039] Simultaneously, conductivity meter 2 continuously collects conductivity data after pretreatment, collecting 10-15 sets of data and calculating the average value, which is then compared with the initial conductivity benchmark value to confirm the removal effect of interfering ions. If the decrease in conductivity after pretreatment meets expectations, it indicates that the interfering ions have been effectively removed; if the decrease is insufficient, an appropriate amount of barium nitrate solution needs to be added, and the above operation repeated. After pretreatment, the precipitated waste liquid at the bottom of reaction unit 3 is discharged. Step (3) Specific reaction and dynamic conductivity detection. Start the third peristaltic pump 6 and add silver nitrate solution to the reaction system at a uniform rate. The amount of silver nitrate solution added should be set according to the estimated concentration of chloride ions to ensure that the molar ratio of silver ions to chloride ions is 1.1:1~1.2:1, which can ensure that the chloride ions react completely and prevent the conductivity from increasing abnormally due to excessive silver ions. The conductivity meter 2 continuously collects conductivity change data throughout the entire reaction process until the conductivity value tends to stabilize. After the data collection is completed, multidimensional conductivity feature parameters are extracted, preferably including initial conductivity A, pre-processed conductivity B, post-reaction conductivity C, differential conductivity feature Δσ=CB, and pre-processed differential feature BA; in other embodiments, at least one dynamic conductivity feature can be further extracted from the slope of conductivity change during the reaction process, the time required to reach a steady state, and the integral area of the reaction curve.
[0040] Step (4) Intelligent analysis and result output. The multidimensional conductivity characteristic parameters are standardized and input into the intelligent analysis module. A pre-trained and optimized machine learning model is then invoked to quickly calculate the chloride ion concentration in the water sample using a preset algorithm. After calculation, the detection results are displayed in real-time on the system's touchscreen. In this embodiment, the support vector machine regression model is obtained through a pre-constructed training dataset, which includes multiple simulated wastewater samples and actual industrial wastewater samples with known chloride ion concentrations. Multi-stage conductivity characteristics are used as model input, and the actual chloride ion concentration values of the corresponding samples are used as model output. Cross-validation is employed to optimize the model parameters, forming a nonlinear regression model suitable for predicting chloride ion concentration under complex industrial wastewater conditions. Step (5) The system automatically cleans. Start the fourth peristaltic pump 7 to discharge all waste liquid in the reaction unit 3 and pipeline into the waste liquid container. After the waste liquid is discharged, turn off the fourth peristaltic pump 7. Send clean water to the reaction unit 3 and the entire pipeline and continue to clean 3 to 4 times to ensure that the residual reactants on the inner wall of the pipeline, the surface of the reaction unit 3 and the surface of the conductivity detection probe are thoroughly rinsed clean. It should be noted that after each cleaning is completed, the fourth peristaltic pump 7 is started to discharge the cleaning wastewater.
[0041] This embodiment introduces a barium salt pretreatment step during the detection process. By adding barium nitrate to the water sample, interfering ions such as sulfate in the water sample precipitate, thereby reducing the influence of coexisting ions on conductivity measurement. By comparing and analyzing the conductivity signals before and after the reaction using differential conductivity detection, the interference caused by water sample matrix fluctuations and changes in the external environment can be effectively weakened, improving the stability and repeatability of the detection signal.
[0042] By dynamically acquiring conductivity change data during the reaction process, multi-dimensional feature information such as initial conductivity, pre-processed conductivity, post-reaction conductivity, and differential conductivity characteristic parameters are extracted. Combined with machine learning algorithms, a chloride ion concentration prediction model is established to achieve accurate conversion of conductivity signals to chloride ion concentration. Through training and optimization with experimental data, the system's detection accuracy under complex water sample conditions can be improved, and the model's adaptability to different water sample types can be enhanced.
[0043] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.
Claims
1. A device for detecting chloride ions in industrial wastewater based on conductivity measurement, characterized in that, The enclosure includes a fluid reaction and mixing module, a dynamic detection module, a control module, and an intelligent analysis module. The fluid reaction and mixing module includes a reaction unit and multiple peristaltic pumps. The fluid reaction and mixing module is connected to at least a sample container, a barium salt reagent container, a silver salt reagent container, and a waste liquid container. The dynamic detection module includes a conductivity meter, which is connected to the reaction unit. The peristaltic pump and conductivity meter are both connected to the control module. The control module controls the peristaltic pump to add the water sample to be tested, barium nitrate reagent, and silver nitrate reagent to the reaction unit in a preset order. The intelligent analysis module is used to extract multi-stage conductivity characteristics based on the collected conductivity data and calculate the chloride ion content in the industrial wastewater.
2. The industrial wastewater chloride ion detection device based on conductivity measurement according to claim 1, characterized in that, The housing is equipped with four peristaltic pumps, arranged in a double row and double column. Each peristaltic pump is connected to a sample container, barium nitrate container, silver nitrate container, and waste liquid container.
3. The industrial wastewater chloride ion detection device based on conductivity measurement according to claim 2, characterized in that, The sample container, barium nitrate container, silver nitrate container, and waste liquid container are respectively connected to the reaction unit through reaction pipelines, and the peristaltic pump is installed on the corresponding reaction pipeline.
4. A device for detecting chloride ions in industrial wastewater based on conductivity measurement according to any one of claims 1-3, characterized in that, The reaction unit is located on the same side of each peristaltic pump, and the conductivity meter is located below the peristaltic pumps and the reaction unit.
5. The industrial wastewater chloride ion detection device based on conductivity measurement according to claim 1, characterized in that, The intelligent analysis module establishes a chloride ion concentration prediction relationship based on a concentration prediction model.
6. The industrial wastewater chloride ion detection device based on conductivity measurement according to claim 5, characterized in that, The input features for constructing the concentration prediction model include the initial conductivity A, the conductivity after pretreatment B, the conductivity after the reaction is completed C, and the differential conductivity feature Δσ=CB; The model outputs the chloride ion concentration value.
7. The industrial wastewater chloride ion detection device based on conductivity measurement according to claim 1, characterized in that, It also includes a power module, which is located above the conductivity meter and on the other side of the peristaltic pump.
8. A method for detecting chloride ions in industrial wastewater based on conductivity measurement, characterized in that, The detection device as described in any one of claims 1-7 includes: The water sample to be tested is transported to the reaction unit, and the initial conductivity data of the sample is collected without the addition of reaction reagents. Barium nitrate solution was added to the reaction unit to remove interfering components; conductivity data after pretreatment were collected. Silver nitrate solution was added to the reaction unit, and conductivity change data were collected in real time during the reaction to obtain the dynamic conductivity characteristics during the reaction process. Multidimensional input features are constructed based on the collected initial conductivity, preprocessed conductivity, post-reaction conductivity, and differential conductivity features. The multidimensional input features are input into the concentration prediction model to calculate the chloride ion concentration.
9. The method for detecting chloride ions in industrial wastewater based on conductivity measurement according to claim 8, characterized in that, The conductivity signals before and after the reaction are compared and analyzed by differential conductivity detection, and the differential conductivity characteristic parameters are input into the concentration prediction model; wherein the differential conductivity characteristic parameter is Δσ=CB.
10. The method for detecting chloride ions in industrial wastewater based on conductivity measurement according to claim 8, characterized in that, After the test is completed, the peristaltic pump connected to the waste liquid container is started to discharge the waste liquid; then clean water is delivered to the reaction unit for automatic cleaning.