Water quality monitoring method and device, storage medium and program product

Abstract

The invention discloses a water quality monitoring method and device, a storage medium and a program product, and relates to the technical field of water quality treatment.The method comprises the steps that water quality data collected by multiple sensors are preprocessed to obtain standardized water quality data, and the multiple sensors are arranged at key nodes of a clean workshop; inputting the standardized water quality data into a water quality prediction model obtained by training based on a convolutional neural network model to obtain water quality change trend data; and when the water quality change trend data reaches an early warning threshold value, triggering an early warning mechanism, and inputting the water quality data into the Bayesian fault model to obtain a water quality optimization strategy. After the water quality data is collected, the water quality prediction model can be used for accurately predicting the water quality change trend, early warning is performed when the water quality is possibly abnormal, and adjustment is performed through the water quality optimization strategy. The situation of hysteresis of an existing water quality monitoring method is avoided, so that the water quality problem can be solved in advance, and the quality and efficiency of the production water of the clean workshop are guaranteed.

Description

Technical Field

[0001] The present application relates to the field of water quality treatment technology, and in particular to a water quality monitoring method, device, storage medium and program product. Background Art

[0002] With the continuous improvement of clean environment requirements in modern industrial production, especially in the fields of electronics, medicine, precision manufacturing, etc., the requirements for water quality have reached an unprecedented level. Therefore, in the operation of clean workshops, the water quality guarantee of the water system is very important.

[0003] Traditional water quality monitoring methods generally have many limitations. For example, manual sampling and testing have long time intervals and are difficult to reflect water quality changes in real time, which can easily lead to water quality problems that cannot be discovered in time during the interval between two tests. Some conventional online monitoring equipment can only monitor a small number of water quality parameters, and lacks comprehensive monitoring capabilities for the complex water use environment of clean workshops and multiple key water quality indicators (such as microorganisms, particles, ion concentrations, etc.). When water quality changes are detected, serious water quality problems have already occurred, and there is a lag.

[0004] Therefore, existing water quality monitoring methods are generally in a passive monitoring state when water quality changes, which has a lag and is difficult to take proactive measures to prevent, which can easily lead to serious consequences such as production losses and reduced product quality. Summary of the invention

[0005] The main purpose of this application is to provide a water quality monitoring method, device, storage medium and program product, aiming to solve the technical problems that the existing water quality monitoring methods are generally in a passive monitoring state when the water quality changes, have lags, are difficult to take active precautions, and easily lead to production losses.

[0006] To achieve the above objectives, the present application proposes a water quality monitoring method, which comprises: Preprocessing the water quality data of the clean room collected by multiple sensors to obtain standardized water quality data, wherein the multiple sensors are pre-set at key nodes of the clean room; Inputting the standardized water quality data into a preset water quality prediction model to obtain water quality change trend data, wherein the water quality prediction model is obtained by training based on a convolutional neural network model; When the water quality change trend data reaches the warning threshold, triggering the warning mechanism; Based on the early warning mechanism, the water quality data is input into a preset Bayesian fault model to obtain a corresponding water quality optimization strategy.

[0007] In one embodiment, the step of preprocessing the water quality data of the clean room collected by multiple sensors to obtain standardized water quality data includes: Collecting water quality data of clean workshops by using multiple sensors at a preset sampling frequency, wherein the multiple sensors include at least one of a microbial sensor, a particle counting sensor, an ion concentration sensor, a pH sensor, and a dissolved oxygen sensor; The water quality data is preprocessed to obtain standardized water quality data, wherein the data preprocessing includes outlier processing, missing value filling and standardization processing.

[0008] In one embodiment, the step of preprocessing the water quality data to obtain standardized water quality data includes: When a data point of the water quality data exceeds a preset fluctuation range, determining the data point as an abnormal value; Removing the abnormal values ​​to obtain cleaned water quality data; Filling missing values ​​in the cleaned water quality data using a preset value filling method to obtain filled water quality data; The filled water quality data is mapped to a standard numerical range to obtain standardized water quality data.

[0009] In one embodiment, the step of inputting the standardized water quality data into a preset water quality prediction model to obtain water quality change trend data includes: Extracting water quality indicators of the standardized water quality data, wherein the water quality indicators include at least one of pH value, conductivity, dissolved oxygen, turbidity, temperature and ion concentration; Calculating the statistical index of the water quality index by a statistical analysis method, wherein the statistical index includes at least one of a mean, a standard deviation and a coefficient of variation; The water quality index and the statistical index are input into a preset water quality prediction model to obtain water quality change trend data. The water quality prediction model is obtained by training a convolutional neural network model using historical water quality data as training samples.

[0010] In one embodiment, the training process of the water quality prediction model includes: Obtain historical water quality indicators and historical statistical indicators of historical water quality data; Classify the historical statistical indicators according to the time dimension to obtain linear data and nonlinear data; Performing linear fitting on the linear data and regressing the nonlinear data by random forest regression method to obtain standardized data; The standardized data and the historical water quality indicators are input into a convolutional neural network model for correlation training to obtain a water quality prediction model.

[0011] In one embodiment, the step of inputting the water quality data into a preset Bayesian fault model based on the early warning mechanism to obtain a corresponding water quality optimization strategy includes: Based on the early warning mechanism, a preset Bayesian fault model is started, wherein the Bayesian fault model analyzes the causal relationship and probability between water quality data; Diagnose the water quality data through the Bayesian fault model and the preset expert system to determine the water treatment fault link and fault cause of the water quality data in the clean room; Generate a corresponding water quality optimization strategy according to the water treatment failure link and failure cause; According to the water quality optimization strategy, an early warning is given to maintenance personnel.

[0012] In one embodiment, the step of diagnosing the water quality data through the Bayesian fault model and the preset expert system to determine the water treatment fault link and fault cause of the water quality data in the clean room includes: The water quality indicator is used as an observation node and the sensor fault is used as a hidden node through the Bayesian fault model; Determining the causal relationship between water quality data according to the hidden nodes; Based on the historical water quality data, defining a conditional probability table between the causal relationship and the observation nodes; The water quality data is diagnosed based on the conditional probability table through a preset expert system to obtain the water treatment failure link and failure cause of the water quality data in the clean room.

[0013] In addition, to achieve the above purpose, the present application also proposes a water quality monitoring device, the device comprising: A preprocessing module, used to preprocess the water quality data of the clean room collected by multiple sensors to obtain standardized water quality data, wherein the multiple sensors are pre-set at key nodes of the clean room; A water quality prediction module, used to input the standardized water quality data into a preset water quality prediction model to obtain water quality change trend data, wherein the water quality prediction model is obtained by training based on a convolutional neural network model; An early warning mechanism module, used to trigger an early warning mechanism when the water quality change trend data reaches an early warning threshold; The optimization strategy module is used to input the water quality data into a preset Bayesian fault model based on the early warning mechanism to obtain a corresponding water quality optimization strategy.

[0014] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the water quality monitoring method described above are implemented.

[0015] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the water quality monitoring method described above are implemented.

[0016] One or more technical solutions proposed in the present application have at least the following technical effects: The water quality monitoring method of the present application includes: preprocessing the water quality data of the clean room collected by multiple sensors to obtain standardized water quality data, and the multiple sensors are pre-set at the key nodes of the clean room; inputting the standardized water quality data into a preset water quality prediction model to obtain water quality change trend data, and the water quality prediction model is obtained by training based on a convolutional neural network model; when the water quality change trend data reaches the warning threshold, triggering the warning mechanism; based on the warning mechanism, inputting the water quality data into a preset Bayesian fault model to obtain a corresponding water quality optimization strategy.

[0017] After collecting water quality data through multiple sensors, this application can use the water quality prediction model to accurately predict the trend of water quality changes, issue early warnings when water quality may be abnormal, and generate water quality optimization strategies for adjustment. This avoids the lag in existing water quality monitoring methods, thereby being able to respond to water quality problems in advance and ensuring the quality and efficiency of clean workshop production water. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0019] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0020] Figure 1 A schematic diagram of a process flow provided for the first embodiment of the water quality monitoring method of the present application; Figure 2 A schematic diagram of a process flow provided for the second embodiment of the water quality monitoring method of the present application; Figure 3 The overall process architecture diagram of the water quality monitoring process provided for this application; Figure 4 This is a schematic diagram of the module structure of the water quality monitoring device according to an embodiment of the present application.

[0021] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0022] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0023] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0024] Traditional manual sampling and testing usually collects water samples from water supply points or water-using equipment in the factory at fixed time intervals (such as several times a day or a week), and then sends them to the laboratory for analysis. The biggest disadvantage of this method is the time lag. If there is a sudden change in water quality between two samplings, such as the rapid growth of microorganisms and the accidental mixing of impurities in the water, it is difficult to detect it in time. In addition, the manual operation process is prone to introduce errors, including contamination during the sampling process, improper sample storage, etc., which affect the accuracy of the test results.

[0025] Although some online monitoring equipment can obtain data in real time, their functions are relatively simple. Common ones are some simple sensors that can only measure a few basic parameters such as pH value and conductivity. For the monitoring of microbial content, which is crucial for the production of modern clean plants, existing equipment may find it difficult to achieve high-precision detection and cannot distinguish between different types of microorganisms and their potential hazards to production. For example, in terms of particle counting, the monitoring of tiny particles (especially those with a particle size less than a certain degree) is not accurate enough, and these tiny particles may have a serious impact on precision manufacturing. For the monitoring of specific ion concentrations in water, it is generally only for a few common ions, and it is difficult to effectively measure trace ions that need to be strictly controlled in some special production processes.

[0026] Therefore, this application provides a solution that uses a variety of high-precision sensors to comprehensively monitor water quality parameters, which is more comprehensive than the existing technology of monitoring a single or a small number of parameters. At the same time, by using cloud computing and big data analysis technology, the problem that the existing technology is difficult to handle massive and complex data is overcome. It can also mine the value of data, accurately predict the trend of water quality changes, respond to water quality problems in advance, and improve production continuity and efficiency.

[0027] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, water quality prediction and water quality warning functions, such as a personal computer, a cloud server, etc., or an electronic device capable of realizing the above functions, a water quality monitoring device that executes the water quality monitoring method of this application, etc., and this embodiment does not limit this. The following takes a cloud server as an example to illustrate this embodiment and the following embodiments.

[0028] Based on this, the first embodiment of the present application is proposed. The present application embodiment provides a water quality monitoring method, referring to Figure 1 , Figure 1 A schematic diagram of the process flow provided for Example 1 of the water quality monitoring method of this application.

[0029] In this embodiment, the water quality monitoring method includes steps S10 to S40: Step S10: pre-processing the water quality data of the clean room collected by multiple sensors to obtain standardized water quality data, wherein the multiple sensors are pre-set at key nodes of the clean room.

[0030] It should be noted that a clean room can be a special room dedicated to water treatment related operations. In a clean room, there are strict environmental control requirements, the purpose of which is to ensure that the treated water quality reaches high standards. Therefore, in order to ensure the water quality of the clean room water system, it is necessary to monitor its water quality.

[0031] Since clean workshop production has extremely high requirements for water quality, traditional monitoring methods can generally only detect a limited number of parameters with limited accuracy. However, before conducting water quality monitoring, this application needs to plan the installation locations of water quality sensors (i.e., multiple sensors) used to collect water quality data in various locations in the clean workshop according to the water use process of the workshop, the requirements for water quality in different production areas, and the layout of the pipeline network during the construction or renovation of the clean workshop. The installation location is generally a typical location (i.e., key node) in the clean workshop that can reflect water quality changes. For example, for clean workshops for electronic chip manufacturing, sensors are installed at key locations such as various processing links of the ultrapure water preparation system (such as before and after the reverse osmosis device, before and after the ion exchange column, etc.), the main water supply pipeline leading to the production workshop, and the water inlet of each chip manufacturing equipment. For microbial sensors, they are mainly installed near water storage equipment and return pipes that are prone to breeding microorganisms to monitor the reproduction of microorganisms in real time.

[0032] After completing the installation of each sensor in accordance with compliance requirements, each sensor must be calibrated using a standard calibration solution. For example, for a microbial sensor, use a standard sample with a known microbial concentration to adjust the sensor's sensitivity and detection range so that its measurement results match the standard value. For a pH sensor, use a standard buffer solution with pH values ​​of 4.0, 7.0, and 10.0 for calibration to ensure the sensor's measurement accuracy in different pH environments.

[0033] At this point, the cloud server can be connected to the corresponding sensor, and appropriate sampling frequency, signal amplification factor and other parameters can be set according to the type of sensor and output signal characteristics. At the same time, the sensor's location information, type identification and other metadata settings are input into the data acquisition module.

[0034] Furthermore, to ensure stable data transmission between the cloud server and the sensor, a data concentrator can be set between the cloud server and the sensor to cache the data. For example, when a network failure occurs temporarily, the data concentrator can cache data for a certain period of time and continue to transmit after the network is restored to avoid data loss.

[0035] After configuring the above clean room settings, you can start real-time monitoring of water quality.

[0036] It is understandable that water quality data can be various quantitative information used to describe the quality characteristics of water bodies, such as water temperature, color, turbidity, transparency, acidity (pH value), dissolved oxygen content, concentration of heavy metal ions (such as mercury, cadmium, lead, etc.), etc.

[0037] Therefore, when the clean room is operating normally, various sensors can continuously collect the above water quality data at the preset sampling frequency, and then transmit the digital water quality data with metadata to the data concentrator in real time. The data concentrator receives data from various sensors, and preliminarily organizes and caches the data according to classification rules such as sensor type and water supply area, so as to facilitate subsequent unified processing and transmission. The data concentrator then transmits the cached data to the cloud server through the optical fiber network. During the transmission process, the data can be encrypted using the SSL / TLS encryption protocol to ensure the security of the data during network transmission. After receiving the encrypted data, the cloud server uses the corresponding decryption key to restore the data and stores it in a pre-configured database.

[0038] It should be noted that a distributed computing environment based on Hadoop and Spark can also be built on the cloud server, and database systems such as MySQL, HBase and MongoDB can be installed and configured. The corresponding database table structure can be created to store different types of data such as sensor information, water quality data, user permissions, etc. At the same time, the resource allocation strategy of the cloud server can be set, and the trigger conditions for automatic resource expansion can be configured, such as automatically increasing server nodes or storage capacity when the length of the data processing task queue exceeds a certain threshold or the storage usage rate reaches a certain ratio.

[0039] It should be understood that standardized water quality data may refer to data obtained after water quality data is standardized or normalized.

[0040] In the specific implementation, when the clean room is operating normally, various sensors can continuously collect the above water quality data according to the preset sampling frequency. Then the cloud server standardizes or regulates these water quality data to obtain standardized water quality data.

[0041] In a feasible implementation, step S10 of this embodiment may include the steps of: collecting water quality data of the clean room through multiple sensors at a preset sampling frequency, the multiple sensors including at least one of a microbial sensor, a particle counting sensor, an ion concentration sensor, a pH sensor and a dissolved oxygen sensor; performing data preprocessing on the water quality data to obtain standardized water quality data, the data preprocessing including outlier processing, missing value filling and standardization processing.

[0042] It should be noted that multi-sensors can include a variety of water quality sensors, such as microbial sensors that can accurately detect the content of microorganisms in water. Based on the principle of fluorescence detection, they can keenly capture microbial metabolism signals; particle counting sensors can continuously count and analyze the particle size of particles in water samples passing through the detection window, without missing tiny particle impurities; ion concentration sensors measure the concentration changes of specific ions through ion selective electrodes; pH sensors can measure the pH value of solutions in water samples; dissolved oxygen sensors can detect the dissolved oxygen content in water bodies. At the same time, when these sensors collect water quality data, metadata such as timestamps and sensor location codes can also be added.

[0043] These sensors fully cover key water quality parameters such as microorganisms, particles, ion concentration, pH value, dissolved oxygen, etc., and realize high-precision, all-round real-time monitoring of water quality, ensuring that any changes in water quality that may affect production can be discovered in a timely manner. Through the fusion of the above high-precision multi-parameter sensors, all-round and real-time monitoring of water quality can be achieved, overcoming the limitations of traditional monitoring methods of single or a few parameters.

[0044] It is understood that the preset sampling frequency is the frequency set on various sensors to collect water quality data of cleanrooms. For example, for pH and ion concentration sensors that change slowly, a relatively low sampling frequency (collecting data every 10 minutes) can be set; while for microbial content and particle count sensors that may change rapidly, a higher sampling frequency (collecting data once every minute) can be set.

[0045] In this embodiment, after receiving the water quality data, the cloud server can first perform data cleaning operations on the water quality data, such as identifying and removing outliers in the data, filling missing values ​​in the data, etc. Then, the cleaned water quality data is standardized to obtain standardized water quality data, thereby facilitating subsequent data analysis.

[0046] In another feasible implementation manner, the step of performing data preprocessing on the water quality data to obtain standardized water quality data described in this embodiment includes: when a data point of the water quality data exceeds a preset fluctuation range, determining that the data point is an outlier; removing the outlier to obtain cleaned water quality data; filling missing values ​​in the cleaned water quality data by a preset numerical filling method to obtain filled water quality data; and mapping the filled water quality data to a standard numerical interval to obtain standardized water quality data.

[0047] It should be noted that the preset fluctuation range may be a pre-set upper and lower limit range that allows normal fluctuations in water quality.

[0048] For example, for microbial sensor data, if the microbial concentration change at a data point exceeds the normal fluctuation range by several times (i.e., the preset fluctuation range) compared with the data at adjacent time points, and the change does not conform to the physical laws of water quality changes (such as no corresponding changes in temperature, pH value, etc.), then the data point is judged to be an outlier and is removed.

[0049] It is understandable that the preset value filling method can be a pre-set algorithm for filling missing parts when there are missing values ​​in the water quality data set, such as a linear interpolation method based on adjacent data points or a mean filling method based on the statistical law of historical data, etc., which is not limited in this embodiment.

[0050] In this embodiment, after receiving the water quality data, the cloud server first determines whether the data point of the water quality data exceeds the preset fluctuation range. If it exceeds the preset fluctuation range, the data point is determined to be an outlier; and the outlier is removed to obtain the cleaned water quality data. Then, according to the time series characteristics of the data and other relevant parameters, the missing values ​​of the cleaned water quality data are filled by linear interpolation based on adjacent data points or mean filling method based on the statistical law of historical data to obtain the filled water quality data. Finally, the cleaned water quality data is standardized, and water quality parameters of different magnitudes and units are uniformly mapped to a standard numerical range (for example, for different types of data, Min-Max normalization is used: (X-Min) / (Max-Min), X is the data point of the water quality data, so that its unit is unified), and standardized water quality data is obtained. Thus, through data processing, the water quality data is made more reasonable and accurate, which is convenient for subsequent data analysis.

[0051] Step S20: inputting the standardized water quality data into a preset water quality prediction model to obtain water quality change trend data, wherein the water quality prediction model is obtained by training based on a convolutional neural network model.

[0052] It should be noted that the water quality prediction model can be a model used to estimate and simulate changes in water quality. The water quality prediction model can be used to predict changes in the water quality of the clean room when it is polluted in the future.

[0053] It is understandable that the water quality change trend data can be the data that predicts the direction of change of water quality in a certain period of time, such as the trend of increasing concentration of certain harmful substances.

[0054] It should be understood that a Convolutional Neural Network (CNN) model may be a model for deep learning based on water quality data.

[0055] Considering the huge and complex amount of data generated by the above-mentioned clean workshop, it is difficult for traditional methods to process massive and complex data; and the traditional methods also have the problem of not conducting deep data mining. Therefore, this embodiment can be based on cloud servers and hybrid database storage to efficiently store and process massive data. A water quality prediction model is constructed through machine learning and deep learning (convolutional neural network) algorithms. Through deep mining of data by the model, the intrinsic relationship between water quality parameters and the changing trend in the short term in the future can be accurately analyzed. The time points of the accelerated reproduction of microorganisms and the impact of fluctuations in ion concentration on production can be known in advance, providing solid data support for subsequent decision-making, which is difficult to achieve with traditional methods.

[0056] In the specific implementation, the cloud server pre-learns the water quality data through the convolutional neural network model to obtain a water quality prediction model that can predict the direction of water quality changes in a certain period of time. After processing the standardized water quality data, the standardized water quality data can be input into the water quality prediction model to obtain the water quality change trend data of the clean room water body in the future period of time.

[0057] In a feasible implementation, step S20 of this embodiment may include the steps of: extracting water quality indicators of the standardized water quality data, the water quality indicators including at least one of pH value, conductivity, dissolved oxygen, turbidity, temperature and ion concentration; calculating statistical indicators of the water quality indicators through statistical analysis methods, the statistical indicators including at least one of mean, standard deviation and coefficient of variation; inputting the water quality indicators and the statistical indicators into a preset water quality prediction model to obtain water quality change trend data, the water quality prediction model is obtained by training a convolutional neural network model using historical water quality data as training samples.

[0058] It should be noted that water quality indicators can be a series of parameters used to measure the quality of water bodies. For example, pH value is used to reflect the acidity and alkalinity of water, conductivity indicates the ability of a solution to conduct electric current, temperature is the degree of hotness or coldness of water bodies, and ion concentration can refer to the content of specific ions in a solution. The above water quality indicators can be used to comprehensively evaluate the quality of water bodies.

[0059] It is understandable that the statistical analysis method can be a method for statistically analyzing the representative and accurate data of each water quality index in the standardized water quality data. For example, descriptive statistical analysis includes calculating the mean, median, standard deviation, etc. to summarize the central tendency and dispersion of the data; for example, inferential statistical analysis can estimate the overall characteristics and hypothesis test through sample data to determine whether there is a relationship between two or more variables.

[0060] Among them, statistical indicators can be parameters used to describe the characteristics of statistical analysis data. The mean is the average of standardized water quality data, reflecting the average level or center position of standardized water quality data; the standard deviation measures the degree of dispersion of standardized water quality data relative to the mean, indicating the dispersion of standardized water quality data; the coefficient of variation is the ratio of the standard deviation to the mean, which is used to compare the degree of dispersion of two or more groups of data with different means or different units, and can more intuitively reflect the relative degree of variation of the data.

[0061] These statistical indicators can reflect the average level, fluctuation and stability of water quality within a certain time range. For example, by calculating the standard deviation of the ion concentration of water supplied to a production area, we can understand the degree of change in ion concentration and determine whether there is a potential risk of water pollution.

[0062] At the same time, machine learning algorithms (such as support vector machines, random forests, etc.) and deep learning algorithms (such as convolutional neural networks) can also be used to establish water quality prediction models.

[0063] Among them, the training process of the water quality prediction model described in this embodiment includes: obtaining historical water quality indicators and historical statistical indicators of historical water quality data; classifying the historical statistical indicators according to the time dimension to obtain linear data and nonlinear data; performing linear fitting on the linear data and regressing the nonlinear data through the random forest regression method to obtain standardized data; inputting the standardized data and the historical water quality indicators into the convolutional neural network model for correlation training to obtain a water quality prediction model.

[0064] It should be noted that historical water quality data can be various quantitative information used to describe the historical water quality characteristics of the clean room; historical water quality indicators can be a series of parameters used to measure the historical water quality conditions of the clean room; historical statistical indicators can be parameters used to describe and statistically analyze the characteristics of the historical data of the clean room.

[0065] Historical water quality data can be used as training samples to learn the intrinsic relationship between water quality parameters and the patterns of change over time. For example, by analyzing the correlation between water temperature, microbial content, particle counts and other data in the past few months and water quality deterioration events, a support vector machine model is established to predict whether water quality will exceed the normal range in the short term in the future. For image data of particle counts, a convolutional neural network model is used to extract and analyze features to improve the recognition ability and prediction accuracy of tiny particle changes.

[0066] Specifically, the training process of the water quality prediction model includes the following steps: 1. Obtain historical water quality data (for example, use the data from the past two years for basic training), and process it to obtain historical water quality indicators and historical statistical indicators. Then, classify the above historical statistical indicators according to the time dimension, and divide them into linear data and nonlinear data; 2. For linear data, linear fitting is performed directly; for nonlinear data, random forest regression is used for regression to obtain standardized data. Among them, the water quality prediction model is suitable for nonlinear and multi-feature data types.

[0067] 3. Then, the standardized data, temperature, pH value, ion concentration and other historical water quality indicators are used as data input, and the goal is set to predict the health of water quality at different time periods.

[0068] 4. Then use the last two months as test data, compare the results of different parameters, select the optimal learning rate, number of trees, hidden layer size and other parameters to start correlation training.

[0069] 5. Finally, the model results are verified using mean square error, mean absolute error, determination coefficient, etc. to determine rationality and obtain the water quality prediction model.

[0070] In this embodiment, water quality indicators of standardized water quality data are extracted, and statistical indicators of water quality indicators are calculated through statistical analysis methods; then water quality indicators and statistical indicators are input into a preset water quality prediction model to obtain water quality change trend data. Thus, water quality change trends can be accurately predicted, water quality problems can be dealt with in advance, and production continuity and efficiency can be improved.

[0071] Step S30: When the water quality change trend data reaches the warning threshold, triggering the warning mechanism.

[0072] It should be noted that the warning threshold may be a value pre-set in the cloud server for warning of excessive water quality changes. When the cloud server monitors that the water quality change trend data reaches or exceeds the warning threshold, an alarm signal will be issued.

[0073] Among them, the warning threshold can be set according to the water quality requirements of different production processes. For example, for ultrapure water in electronic chip manufacturing workshops, the microbial content threshold is set to no more than 1 colony-forming unit per milliliter, and the number of particles with a particle size greater than 0.1 microns is no more than 10 per liter, etc. This embodiment does not impose any restrictions on this.

[0074] It is understandable that the early warning mechanism can be a program set up to warn managers. For example, early warning information is sent to managers through text messages, emails, mobile phone application push and other methods. The early warning information can list in detail the abnormal water quality parameters, the location of the problem (for example, accurately displayed on the plant water supply pipeline network diagram through sensor location coding), the possible scope of impact (based on the correlation analysis between the water supply pipeline network and the water use area), and the severity assessment of the problem (based on the degree of deviation of water quality parameters from the threshold and the potential impact on production).

[0075] Furthermore, the above data can be visualized, and real-time water quality data can be displayed to managers in the form of intuitive charts, dashboards, etc. on the cloud server. For example, a line chart can be used to show the trend of microbial content in a water-using area over time, and a bar chart can be used to compare the pH value differences in different areas. Managers can view these real-time data visualization interfaces anytime and anywhere through the web or mobile application to keep abreast of the water quality in the plant.

[0076] Step S40: Based on the early warning mechanism, the water quality data is input into a preset Bayesian fault model to obtain a corresponding water quality optimization strategy.

[0077] It should be noted that the Bayesian fault model can be a model based on Bayesian theory for analyzing clean room fault-related situations. Through the Bayesian fault model, the occurrence of faults in the clean room, the type of fault, the scope of impact of the fault, and the most likely type of fault can be determined after the water quality changes, which helps to make maintenance decisions in advance and reduce maintenance costs.

[0078] It is understandable that a water quality optimization strategy can be a collection of measures to improve and enhance water quality and to handle emergency situations.

[0079] Traditional fault diagnosis generally relies on the experience and judgment of on-site personnel, and the early warning information is not comprehensive. It can only indicate simple parameter out-of-limit, and cannot accurately assess the possible location, impact range, and severity of the fault, resulting in untimely or inaccurate response measures. However, this application can quickly analyze the causal relationship between water quality data through the Bayesian fault model, determine the root cause of the fault, such as filter blockage, disinfection equipment failure, pipeline leakage, etc., so as to take timely repair measures to avoid production interruptions or product quality degradation caused by water quality problems.

[0080] For example, for clean room failures, the response measures may include: based on the fault diagnosis results, the cloud server provides emergency treatment suggestions to the management personnel. If it is a problem of excessive microorganisms, it may be recommended to immediately increase the intensity or frequency of disinfection treatment, such as increasing the ultraviolet disinfection time or increasing the amount of disinfectant. For particle contamination problems, it may be recommended to check whether the filters in the corresponding areas are clogged, and if necessary, perform temporary bypass or replace the filter cartridge. At the same time, for serious water quality problems that may affect production, it is recommended to suspend the operation of related production equipment to avoid producing substandard products.

[0081] At the same time, the cloud server can assist in formulating a maintenance plan based on the type and severity of the fault. For some simple faults, such as sensor failure, it can provide an operating guide for replacing the sensor and a list of tools and accessories required. For complex faults, such as pipeline leakage or water treatment equipment failure, it can arrange maintenance personnel and maintenance time based on the fault location and possible maintenance steps involved, and estimate the resources and costs required for maintenance. During the maintenance process, water quality data can be continuously monitored to evaluate the maintenance effect and ensure that the water quality returns to normal.

[0082] After the fault is repaired, the cloud server can further provide adjustments to the water use strategy. The water use strategy of the clean room can be dynamically adjusted based on real-time water quality monitoring data and analysis results. For example, if the water quality in a certain area has been maintained at a high standard and the water consumption is stable, it can be recommended to appropriately reduce the frequency of water quality monitoring in that area, reduce the workload of the sensor, and adjust the intensity of water treatment. Reduce the amount of disinfectant or extend the filtration cycle to reduce operating costs. Conversely, if the water quality of a certain water use link fluctuates, it can be recommended to add additional treatment steps, such as adding an activated carbon filter device to the water supply pipeline or adjusting the working pressure and flow of the reverse osmosis membrane to ensure the water safety of key production equipment.

[0083] At the same time, water supply distribution can be optimized. If the production tasks of a certain production area are reduced and the water consumption is reduced, the opening of the water supply valve can be adjusted to reduce the water supply in this area and reasonably allocate the excess water resources to other areas with greater water demand. In the process of adjusting water supply distribution, it is necessary to fully consider the different requirements of different areas for water quality to avoid water quality problems caused by changes in water supply.

[0084] In the specific implementation, when the early warning mechanism is triggered, it means that the water quality in the clean room is abnormal. At this time, the cloud server can input the water quality data into the preset Bayesian fault model, output the fault diagnosis results and arrange maintenance personnel for repair, and generate corresponding water quality optimization strategies to adjust water supply distribution.

[0085] In the technical solution provided in this embodiment, when the clean room is operating normally, various sensors can continuously collect the above water quality data according to the preset sampling frequency. Then the cloud server standardizes or standardizes these water quality data to obtain standardized water quality data. Since the cloud server pre-determines the water quality prediction model that can predict the direction of change of water quality in a certain period of time by using the convolutional neural network model according to the water quality data, the standardized water quality data can be input into the water quality prediction model to obtain the water quality change trend data of the water body in the clean room in the future. If the water quality change trend data reaches the warning threshold, the warning mechanism is triggered, which indicates that the water quality of the clean room is abnormal. The cloud server can input the water quality data into the preset Bayesian fault model, output the fault diagnosis results and arrange maintenance personnel for maintenance, and generate the corresponding water quality optimization strategy to adjust the water supply distribution. Since the present embodiment can accurately predict the water quality change trend by using the water quality prediction model after collecting water quality data through multiple sensors, it can give an early warning when the water quality may be abnormal and generate a water quality optimization strategy for adjustment. This avoids the lag in existing water quality monitoring methods, making it possible to respond to water quality issues in advance and ensure the quality and efficiency of clean plant production water.

[0086] Based on the above-mentioned embodiment 1 of the present application, the embodiment 2 of the present application is proposed. In the second embodiment of the present application, the same or similar contents as those of the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated later. On this basis, please refer to Figure 2 , Figure 2 A schematic diagram of the flow chart provided for Example 2 of the water quality monitoring method of this application.

[0087] In this example, step S40 includes steps S41 to S44: Step S41: Based on the early warning mechanism, a preset Bayesian fault model is started, and the Bayesian fault model is analyzed through the causal relationship and probability between water quality data.

[0088] It should be noted that the causal relationship between water quality data can be a relationship in which the change of one water quality indicator directly leads to the change of one or more other water quality indicators. The probability is a measure of the likelihood of these causal relationships occurring.

[0089] For example, an increase in the organic matter content in water may lead to a decrease in dissolved oxygen, because the decomposition of organic matter consumes oxygen. By learning the causal relationship and probability between water quality data, the Bayesian fault model can better understand the mechanism of water quality change, predict the trend of water quality change, and thus formulate water quality protection and management strategies more effectively.

[0090] Step S42: diagnose the water quality data through the Bayesian fault model and the preset expert system to determine the water treatment fault link and fault cause of the water quality data in the clean room.

[0091] It should be noted that the expert system can be a rule base that stores a large amount of knowledge and experience of experts in the field about water quality issues. The rules of the expert system can be used to assist the Bayesian fault model in fault diagnosis, further help confirm the cause of the fault, and provide more accurate guidance for maintenance personnel.

[0092] For example, if an abnormal increase in the concentration of a certain specific ion in the water is detected, accompanied by abnormal operation of water-using equipment in a specific area, the expert experience rules of the expert system can be used to determine whether corrosion and leakage have occurred in the water supply pipes in the area, causing external ions to mix into the water supply system.

[0093] It is understandable that the water treatment failure link can be the solution to the problem in the entire water treatment system in the clean room. The cause of the failure can be the factors that cause the failure of this link, such as equipment aging, microbial growth blocking pipes or filter materials, etc.

[0094] For example, if the microbial content suddenly increases and the pH value decreases at the same time, the Bayesian fault model determines the possibility that a certain water treatment link fails, causing microbial growth and changing the pH of the water. The expert system considers various possible causes of failure, such as filter blockage, disinfection equipment failure, pipeline leakage, etc., and combines the changes in different sensor data to calculate the probability of each cause of failure. In this way, the possible root cause of the failure can be quickly located.

[0095] In a feasible implementation, step S42 of this example includes the steps of: using the Bayesian fault model to take the water quality index as an observation node, and the sensor fault as a hidden node; determining the causal relationship between the water quality data based on the hidden nodes; defining a conditional probability table between the causal relationship and the observation nodes based on the historical water quality data; and diagnosing the water quality data based on the conditional probability table through a preset expert system to obtain the water treatment fault link and fault cause of the water quality data in the clean workshop.

[0096] It should be noted that the observation node can be the Bayesian fault model that uses the directly measurable water quality indicators as visible and accessible reference objects; and the sensor failure is used as a hidden node because the sensor failure is difficult to be observed directly, but it will affect the observation of water quality indicators.

[0097] By establishing this model relationship with water quality indicators as observation nodes and sensor failures as hidden nodes, known water quality indicator observation data can be used to infer whether the sensor has failed and the probability of failure, so as to improve the accuracy and reliability of water quality monitoring.

[0098] It is understandable that the conditional probability table may be a probability result of the causal relationship of water quality, the relationship between the above water quality indicators and whether the sensor is faulty.

[0099] Specifically, for ease of understanding, the analysis steps of the Bayesian fault model are used as an example to illustrate: 1. Determine the nodes. Define the observation nodes as pH value, dissolved oxygen, and water turbidity; define the hidden nodes as sensor failure and data transmission anomaly.

[0100] 2. Determine the edge. Confirm the cause and effect relationship of water quality data. For example, water quality parameter abnormality caused by sensor failure; water quality data loss caused by abnormal data transmission, etc.

[0101] 3. Define the conditional probability table. Based on the historical water quality data, define the probability that the sensor (S1) is normal for parameters such as pH value to be normal as 95%; the probability that the sensor fails for abnormal pH value is 80%, and then establish the conditional probability table corresponding to the pH value, such as: P(pH=normal|S1=normal)=0.95; P(pH=abnormal|S1=normal)=0.05; P(pH=normal|S1=fault)=0.20; P(pH=abnormal|S1=fault)=0.80.

[0102] 4. Observe the current data performance to perform fault diagnosis and decision-making. If the pH is abnormal, the probability of sensor failure is 80%. At the same time, combining other parameters for multi-dimensional judgment can improve the judgment accuracy.

[0103] In this embodiment, the water quality index is first used as an observation node and the sensor failure is used as a hidden node through the Bayesian fault model; and the causal relationship between the water quality data is determined based on the hidden nodes. Then, based on the historical water quality data, a conditional probability table between the causal relationship and the observation node is defined. Finally, through the preset expert system, the water quality data is diagnosed based on the conditional probability table to obtain the water treatment failure link and failure cause of the water quality data in the clean room. By establishing this model relationship in which the water quality index is used as the observation node and the sensor failure is used as the hidden node, the known water quality index observation data can be used to infer whether the sensor fails, as well as information such as the probability of failure, so as to improve the accuracy and reliability of water quality monitoring.

[0104] Step S43: Generate a corresponding water quality optimization strategy according to the water treatment fault link and fault cause.

[0105] It should be noted that the water quality optimization strategy can be further combined with the long-term production plan of the clean plant to plan water quality assurance measures in advance. For example, in the off-season, when the number of production equipment in operation decreases and the water consumption decreases, the entire water system can be maintained and optimized. The water treatment equipment can be fully inspected and maintained, aging components can be replaced, and the operation mode of the water supply system can be adjusted to reduce unnecessary waste of water resources and water treatment costs. Before the peak production season arrives, according to the expected production scale and increase in water demand, water quality assurance measures can be adjusted in advance, such as increasing the frequency of water quality monitoring, strengthening water treatment intensity, and reserving key water treatment consumables, to ensure stable water quality during high-load production.

[0106] At the same time, the cloud server can also regularly conduct a comprehensive analysis of water quality monitoring data and system operation data, summarize the patterns of water quality changes and problems in system operation. According to the analysis results, continuous improvements are made to sensor layout, data collection parameters, data analysis models, warning thresholds, water use strategies, etc. For example, if it is found that the water quality change trend in a certain area deviates greatly from the existing water quality prediction model, the water quality data of the area is re-collected and analyzed, the parameters of the water quality prediction model are optimized, and the prediction accuracy is improved. Through the above continuous improvement methods, the cloud server's ability to monitor and manage clean plant water quality can be continuously improved to ensure smooth production and stable product quality.

[0107] Step S44: According to the water quality optimization strategy, an early warning is issued to maintenance personnel.

[0108] In this implementation, when an abnormal water quality warning occurs, the Bayesian fault model and rule-based expert system can be activated to analyze the causal relationship and probability between water quality data to determine the fault link and fault cause. This can not only quickly locate the fault, but also optimize the water use strategy based on real-time data and long-term planning, realize integrated innovation from early warning to decision support, and effectively guarantee production and optimize operating costs.

[0109] For example, in order to help understand the implementation process of the water quality monitoring method obtained by combining the above-mentioned embodiment 1 and embodiment 2, please refer to Figure 3 , Figure 3 The overall process architecture diagram of the water quality monitoring process provided for this application. Specifically: 1. Data collection. In terms of system architecture, first install a variety of high-precision microbial sensors such as fluorescence-based microbial sensors, laser scattering particle counting sensors, ion-selective electrode sensors, pH sensors, and dissolved oxygen sensors at key nodes of the cleanroom water system (such as water supply systems, water equipment connections, return pipes, and water treatment equipment inlets and outlets). These sensors can collect multi-dimensional data on water quality in real time (such as temperature, flow, pH value, microbial concentration, dissolved oxygen concentration, dissolved sulfur concentration, particulate matter concentration, metal ion concentration, etc.), and then convert the analog signals obtained by the sensors into digital signals, and add metadata such as timestamps and sensor location information.

[0110] 2. Data storage. Set up a data concentrator to receive data from sensors, and perform preliminary sorting and caching (such as intermittent caching and continuous caching). Then, the data is securely transmitted to the cloud server through a fiber optic network encrypted by SSL / TLS protocol to ensure the confidentiality and integrity of the data transmission process.

[0111] 3. Data processing. Then use the cloud server to obtain data and pre-process the water quality data (such as cleaning, standardization, etc.). Then classify the historical water quality data, use statistical analysis, machine learning (support vector machine, random forest, etc.) and deep learning (such as the above-mentioned convolutional neural network) algorithms to test the data for relevance, and establish a big data model (i.e., water quality prediction model) to predict the trend of water quality changes.

[0112] The cloud server can be built based on distributed computing architecture platforms such as Hadoop and Spark, combined with a hybrid database storage system consisting of MySQL, HBase, MongoDB, etc. It can process massive amounts of water quality data, has good scalability, and can flexibly allocate resources according to data volume and processing requirements.

[0113] 4. Data warning. When the water quality trend data exceeds the preset threshold or shows an abnormal trend, a threshold warning will be sent to the management personnel through SMS, email, mobile application push and other channels, and the data will be displayed to explain the abnormal situation, problem location, impact range and severity in detail.

[0114] 5. Water quality diagnosis. Finally, the Bayesian fault model and rule-based expert experience database are used to perform data diagnosis and model diagnosis to quickly determine the cause of abnormal water quality. At the same time, the water use strategy is optimized based on water quality data and production plans to achieve comprehensive management from daily monitoring, fault response to long-term water use planning, and ensure the quality and efficiency of clean plant production water.

[0115] Through the above-mentioned water quality monitoring method, water quality testing can be performed in fields with extremely high water quality requirements. For example, in the field of electronics industry, such as electronic chip manufacturing and other electronic industry clean workshops, the water quality requirements are extremely high. This method can accurately monitor parameters such as microorganisms, particles, and ion concentrations in the water to prevent chips from being contaminated due to water quality problems, ensure chip production quality and yield, and meet the strict requirements of the electronic production process for ultrapure water. For example, in the field of pharmaceutical manufacturing, such as the pharmaceutical production process, water quality directly affects the quality and safety of drugs. This method can monitor various indicators of pharmaceutical water in real time to ensure that impurities, microorganisms, etc. in the water are at extremely low levels, and ensure that drug production meets strict quality standards. It is particularly critical for the production of injections, eye drops, and other drugs that are sensitive to water quality. For example, in the field of precision optical instrument manufacturing, the production of precision optical components such as optical lenses requires high-purity water. By continuously monitoring parameters such as particle counts in water, tiny particles can be prevented from scratching and contaminating the optical surface, ensuring the accuracy and imaging quality of optical instruments, and providing strong support for the production of high-precision optical products. For example, in the chemical industry, such as chemical cleanrooms, accurate water quality monitoring helps control chemical reaction conditions. This method can ensure that water parameters such as pH value and ion concentration are appropriate, prevent equipment corrosion and adverse chemical reactions, and ensure the safety and stability of the chemical production process.

[0116] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the water quality monitoring method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0117] This application also provides a water quality monitoring device, please refer to Figure 4 , Figure 4 This is a schematic diagram of the module structure of the water quality monitoring device of the embodiment of the present application; the water quality monitoring device comprises: A preprocessing module 401 is used to preprocess the water quality data of the clean room collected by multiple sensors to obtain standardized water quality data, wherein the multiple sensors are pre-set at key nodes of the clean room; A water quality prediction module 402 is used to input the standardized water quality data into a preset water quality prediction model to obtain water quality change trend data, wherein the water quality prediction model is obtained by training based on a convolutional neural network model; An early warning mechanism module 403 is used to trigger an early warning mechanism when the water quality change trend data reaches an early warning threshold; The optimization strategy module 404 is used to input the water quality data into a preset Bayesian fault model based on the early warning mechanism to obtain a corresponding water quality optimization strategy.

[0118] As an embodiment, the preprocessing module 401 is also used to collect water quality data of the clean room through multiple sensors at a preset sampling frequency, and the multiple sensors include at least one of a microbial sensor, a particle counting sensor, an ion concentration sensor, a pH sensor and a dissolved oxygen sensor; the water quality data is preprocessed to obtain standardized water quality data, and the data preprocessing includes outlier processing, missing value filling and standardization processing.

[0119] As an implementation mode, the preprocessing module 401 is also used to determine that a data point of the water quality data is an outlier when the data point of the water quality data exceeds a preset fluctuation range; remove the outlier to obtain cleaned water quality data; fill in missing values ​​of the cleaned water quality data by a preset numerical filling method to obtain filled water quality data; map the filled water quality data to a standard numerical interval to obtain standardized water quality data.

[0120] As an implementation mode, the water quality prediction module 402 is also used to extract water quality indicators of the standardized water quality data, and the water quality indicators include at least one of pH value, conductivity, dissolved oxygen, turbidity, temperature and ion concentration; calculate the statistical indicators of the water quality indicators through statistical analysis methods, and the statistical indicators include at least one of mean, standard deviation and coefficient of variation; input the water quality indicators and the statistical indicators into a preset water quality prediction model to obtain water quality change trend data, and the water quality prediction model is obtained by training a convolutional neural network model with historical water quality data as training samples.

[0121] As an implementation mode, the water quality prediction module 402 is also used to obtain historical water quality indicators and historical statistical indicators of historical water quality data; classify the historical statistical indicators according to the time dimension to obtain linear data and nonlinear data; perform linear fitting on the linear data and regress the nonlinear data through the random forest regression method to obtain standardized data; input the standardized data and the historical water quality indicators into the convolutional neural network model for correlation training to obtain a water quality prediction model.

[0122] As an implementation mode, the early warning mechanism module 403 is also used to start a preset Bayesian fault model based on the early warning mechanism, and the Bayesian fault model is used to analyze the causal relationship and probability between water quality data; the water quality data is diagnosed through the Bayesian fault model and the preset expert system to determine the water treatment failure link and failure cause of the water quality data in the clean plant; according to the water treatment failure link and failure cause, a corresponding water quality optimization strategy is generated; according to the water quality optimization strategy, a warning is issued to maintenance personnel.

[0123] As an implementation mode, the optimization strategy module 404 is also used to use the Bayesian fault model to take the water quality index as an observation node and the sensor fault as a hidden node; determine the causal relationship between the water quality data according to the hidden nodes; define the conditional probability table between the causal relationship and the observation node based on the historical water quality data; diagnose the water quality data based on the conditional probability table through a preset expert system to obtain the water treatment fault link and fault cause of the water quality data in the clean workshop.

[0124] Other embodiments or specific implementations of the water quality monitoring device of the present application can refer to the above-mentioned method embodiments and will not be described in detail here.

[0125] The water quality monitoring device provided by the present application adopts the water quality monitoring method in the above-mentioned embodiment, which can solve the technical problem that the existing water quality monitoring method is generally in a passive monitoring state when the water quality changes, has hysteresis, is difficult to take active prevention measures, and is prone to production losses. Compared with the prior art, the beneficial effects of the water quality monitoring device provided by the present application are the same as the beneficial effects of the water quality monitoring method provided by the above-mentioned embodiment, and the other technical features of the water quality monitoring device are the same as the features disclosed in the above-mentioned embodiment method, which will not be repeated here.

[0126] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, wherein the computer-readable program instructions are used to execute the water quality monitoring method in the above-mentioned embodiment.

[0127] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared or semiconductor systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0128] The computer-readable storage medium may be included in the water quality monitoring device; or may exist independently without being installed in the water quality monitoring device.

[0129] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the water quality monitoring device, the water quality monitoring device: pre-processes the water quality data of the clean room collected by multiple sensors to obtain standardized water quality data, and the multiple sensors are pre-set at the key nodes of the clean room; inputs the standardized water quality data into a preset water quality prediction model to obtain water quality change trend data, and the water quality prediction model is obtained by training based on a convolutional neural network model; when the water quality change trend data reaches the warning threshold, the warning mechanism is triggered; based on the warning mechanism, the water quality data is input into a preset Bayesian fault model to obtain a corresponding water quality optimization strategy.

[0130] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0131] The flowchart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0132] The modules involved in the embodiments described in the present application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0133] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned water quality monitoring method, and can solve the technical problems that the existing water quality monitoring method is generally in a passive monitoring state when the water quality changes, has hysteresis, is difficult to take the initiative to prevent, and easily leads to production losses. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the water quality monitoring method provided by the above-mentioned embodiment, and will not be repeated here.

[0134] The present application also provides a computer program product, including a computer program, which implements the steps of the water quality monitoring method as described above when executed by a processor.

[0135] The computer program product provided by the present application can solve the technical problem that the existing water quality monitoring method is generally in a passive monitoring state when the water quality changes, has a hysteresis, is difficult to take active prevention, and easily leads to production losses. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the water quality monitoring method provided by the above embodiment, and will not be repeated here.

[0136] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A water quality monitoring method, characterized in that: The method comprises: Preprocessing the water quality data of the clean room collected by multiple sensors to obtain standardized water quality data, wherein the multiple sensors are pre-set at key nodes of the clean room; Inputting the standardized water quality data into a preset water quality prediction model to obtain water quality change trend data, wherein the water quality prediction model is obtained by training based on a convolutional neural network model; When the water quality change trend data reaches the warning threshold, triggering the warning mechanism; Based on the early warning mechanism, the water quality data is input into a preset Bayesian fault model to obtain a corresponding water quality optimization strategy.

2. The method according to claim 1, characterized in that The step of preprocessing the water quality data of the clean room collected by multiple sensors to obtain standardized water quality data includes: Collecting water quality data of clean workshops by using multiple sensors at a preset sampling frequency, wherein the multiple sensors include at least one of a microbial sensor, a particle counting sensor, an ion concentration sensor, a pH sensor, and a dissolved oxygen sensor; The water quality data is preprocessed to obtain standardized water quality data, wherein the data preprocessing includes outlier processing, missing value filling and standardization processing.

3. The method according to claim 2, characterized in that The step of preprocessing the water quality data to obtain standardized water quality data includes: When a data point of the water quality data exceeds a preset fluctuation range, determining the data point as an abnormal value; Removing the abnormal values ​​to obtain cleaned water quality data; Filling missing values ​​in the cleaned water quality data using a preset value filling method to obtain filled water quality data; The filled water quality data is mapped to a standard numerical range to obtain standardized water quality data.

4. The method according to any one of claims 1 to 3, characterized in that The step of inputting the standardized water quality data into a preset water quality prediction model to obtain water quality change trend data includes: Extracting water quality indicators of the standardized water quality data, wherein the water quality indicators include at least one of pH value, conductivity, dissolved oxygen, turbidity, temperature and ion concentration; Calculating the statistical index of the water quality index by a statistical analysis method, wherein the statistical index includes at least one of a mean, a standard deviation and a coefficient of variation; The water quality index and the statistical index are input into a preset water quality prediction model to obtain water quality change trend data. The water quality prediction model is obtained by training a convolutional neural network model using historical water quality data as training samples.

5. The method according to claim 4, characterized in that The training process of the water quality prediction model includes: Obtain historical water quality indicators and historical statistical indicators of historical water quality data; Classify the historical statistical indicators according to the time dimension to obtain linear data and nonlinear data; Performing linear fitting on the linear data and regressing the nonlinear data by random forest regression method to obtain standardized data; The standardized data and the historical water quality indicators are input into a convolutional neural network model for correlation training to obtain a water quality prediction model.

6. The method according to claim 4, characterized in that The step of inputting the water quality data into a preset Bayesian fault model based on the early warning mechanism to obtain a corresponding water quality optimization strategy includes: Based on the early warning mechanism, a preset Bayesian fault model is started, wherein the Bayesian fault model analyzes the causal relationship and probability between water quality data; Diagnose the water quality data through the Bayesian fault model and the preset expert system to determine the water treatment fault link and fault cause of the water quality data in the clean room; Generate a corresponding water quality optimization strategy according to the water treatment failure link and failure cause; According to the water quality optimization strategy, an early warning is given to maintenance personnel.

7. The method according to claim 6, characterized in that The step of diagnosing the water quality data through the Bayesian fault model and the preset expert system to determine the water treatment fault link and fault cause of the water quality data in the clean room includes: The water quality indicator is used as an observation node and the sensor fault is used as a hidden node through the Bayesian fault model; Determining the causal relationship between water quality data according to the hidden nodes; Based on the historical water quality data, defining a conditional probability table between the causal relationship and the observation nodes; The water quality data is diagnosed based on the conditional probability table through a preset expert system to obtain the water treatment failure link and failure cause of the water quality data in the clean room.

8. A water quality monitoring device, characterized in that: The device comprises: A preprocessing module, used to preprocess the water quality data of the clean room collected by multiple sensors to obtain standardized water quality data, wherein the multiple sensors are pre-set at key nodes of the clean room; A water quality prediction module, used to input the standardized water quality data into a preset water quality prediction model to obtain water quality change trend data, wherein the water quality prediction model is obtained by training based on a convolutional neural network model; An early warning mechanism module, used to trigger an early warning mechanism when the water quality change trend data reaches an early warning threshold; The optimization strategy module is used to input the water quality data into a preset Bayesian fault model based on the early warning mechanism to obtain a corresponding water quality optimization strategy.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the water quality monitoring method according to any one of claims 1 to 7 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the water quality monitoring method according to any one of claims 1 to 7 are implemented.

Images