Intelligent treatment method and system for waste liquid in building construction process

Abstract

The invention provides an intelligent waste liquid treatment method and system in the building construction process. The method comprises the steps that concentration, temperature and SCOD value data in the waste liquid treatment process are collected in real time; preprocessing the waste liquid concentration data and converting into sequence data; judging the change degree of the data at the next moment based on the data at the previous moment, if the change degree is greater than a set value, performing clustering analysis to determine a division type, and extracting feature information to form a matrix; and the waste liquid analysis model is used for analysis, if abnormity occurs, abnormal data are analyzed, an early warning is generated, unprocessed equipment information is obtained, and the early warning is sent. According to the invention, the treatment efficiency can be effectively improved, the pollutant emission and carbon emission are reduced, and the construction site is assisted to realize the purposes of reducing pollution and carbon.

Description

Technical Field

[0001] This invention relates to the field of construction wastewater treatment technology, and more specifically, to an intelligent method and system for treating wastewater during the construction process. Background Technology

[0002] Wastewater treatment during construction has always been a challenging technical issue. Traditional wastewater treatment methods have several problems. First, manual monitoring of wastewater conditions is not only inefficient but also prone to errors, leading to untimely or incomplete treatment. Second, existing wastewater treatment equipment typically lacks intelligent control mechanisms, failing to dynamically adjust based on the actual state of the wastewater. This not only affects treatment effectiveness but may also lead to energy waste. Furthermore, traditional methods often neglect the environmental impact of wastewater treatment, particularly carbon emissions, which contradicts current global requirements for environmental protection and sustainable development. They lack scientific monitoring and control of the treatment process targeting effective indicators.

[0003] In implementing the embodiments of the present invention, the prior art has at least the following problems or defects: First, it is impossible to monitor key parameters in the waste liquid treatment process in real time and accurately, such as waste liquid concentration, temperature and SCOD value, resulting in poor controllability of the treatment process; second, there is a lack of effective data analysis and early warning mechanisms, making it impossible to detect and handle abnormal situations in the waste liquid treatment process in a timely manner; third, the coordination between waste liquid treatment equipment is poor, making it impossible to form an efficient treatment system; and fourth, the prior art does not adequately consider pollution reduction and carbon reduction, and cannot meet increasingly stringent environmental protection requirements. Summary of the Invention

[0004] This invention provides a method and system for intelligent treatment of waste liquid during the construction process.

[0005] In a first aspect of the present invention, a smart treatment method for waste liquid during building construction is provided, comprising: Real-time acquisition of waste liquid concentration data, temperature data, and SCOD values ​​during the waste liquid treatment process; The waste liquid concentration data is preprocessed to obtain preprocessed waste liquid concentration data; and the preprocessed waste liquid concentration data is converted into waste liquid concentration sequence data arranged in chronological order. Based on the waste liquid concentration sequence data of the previous moment, determine whether the degree of change in the waste liquid concentration sequence data of the next moment is greater than a set degree value; If so, cluster analysis is performed on the waste liquid concentration sequence data at the next time step to determine the classification type of the waste liquid concentration sequence data at the next time step, and feature extraction model is used to extract feature information from the waste liquid concentration sequence data at the next time step to form a feature information matrix. Based on the classification, the characteristic information matrix is ​​analyzed using the corresponding information analysis unit in the waste liquid analysis model to obtain the waste liquid analysis results; When the waste liquid analysis results show abnormal information, the abnormal waste liquid concentration sequence data for a set time period starting from the next moment is obtained, and the abnormal waste liquid concentration sequence data is analyzed using an anomaly analysis model to obtain the anomaly analysis results. Based on the anomaly analysis results and temperature data, an early warning message is generated; and information on waste liquid treatment equipment within a set range that has not yet processed the temperature data is obtained; and an early warning message is sent to the waste liquid treatment equipment based on the waste liquid treatment equipment information.

[0006] Furthermore, the step of determining whether the change in the waste liquid concentration sequence data at the next time moment is greater than a preset value based on the waste liquid concentration sequence data at the previous time moment includes: The waste liquid concentration sequence data is converted into concentration information sets and temperature information sets for corresponding channels through a dual-channel system of concentration and temperature, and then stored in chronological order. Obtain the concentration information set of the previous moment and the concentration information set of the next moment; The formula for calculating the degree of change between the concentration information set at the next time step and the concentration information set at the previous time step is as follows: in, This represents the i-th concentration value in the concentration information set at the next moment in the concentration channel. The concentration value is the i-th concentration value in the concentration information set of the previous time step; the value used to determine the degree of change is... Is it greater than the set level value?

[0007] Furthermore, the step of performing cluster analysis on the waste liquid concentration sequence data at the next time moment to determine the classification type of the waste liquid concentration sequence data at the next time moment includes: converting the waste liquid concentration sequence data at the next time moment into an initial cluster dataset through a preset converter; and analyzing the initial cluster dataset using a clustering model constructed based on historical waste liquid data to obtain the classification type.

[0008] Furthermore, the feature extraction model includes the following steps: dividing the waste liquid concentration sequence data at the next time step into multiple irregular segments; selecting segments that conform to the corresponding segmentation type from each segment data according to the segmentation type to obtain multiple key analysis data; and using a feature extractor to extract the feature information of each key analysis data to form multiple feature information matrices.

[0009] Furthermore, the processing procedure of the waste liquid analysis model includes: inputting each feature information matrix into the corresponding information analysis unit according to the classification type; each information analysis unit determines whether the feature information matrix conforms to the preset feature information database according to its own preset feature information database; when it does not conform to the preset standard, abnormal segment data is obtained, and waste liquid analysis results containing abnormal segment data information are obtained.

[0010] Furthermore, the setting criteria of the preset feature information database include the standard setting range of each element in the feature information matrix and the setting change range between the element and its surrounding elements.

[0011] Furthermore, the analysis process of the anomaly analysis model includes: based on the anomaly segmentation data information, screening sequences containing anomaly segmentation data from the anomaly waste liquid concentration sequence data to obtain anomaly sequence data; when the number of anomaly sequence data exceeds a preset number, analyzing each anomaly sequence data based on the preset anomaly information database corresponding to the classification type to determine the first anomaly probability value of each anomaly sequence data and the second anomaly probability value corresponding to the number of anomaly sequence data. The first and second anomaly probability values ​​are processed using a weighted average method to calculate the average anomaly probability value. The level corresponding to the average anomaly probability value is used as the anomaly level. Anomaly analysis results are formed based on the classification type, anomaly level, and data of each anomaly sequence.

[0012] Furthermore, the process of filtering the abnormal sequence data includes: based on the feature information matrix of the abnormal segmented data, determining whether the feature information matrix transformed from the abnormal waste liquid concentration sequence data contains a feature information matrix with a similarity exceeding a set similarity; if so, the abnormal waste liquid concentration sequence data is marked as abnormal sequence data.

[0013] Furthermore, the information analysis unit includes at least a waste liquid concentration analysis unit, a temperature analysis unit, an SCOD value analysis unit, a treatment efficiency analysis unit, and an equipment status analysis unit.

[0014] In a second aspect of the present invention, an intelligent wastewater treatment system for a building construction process is provided, comprising: The intelligent waste liquid recycling system includes a data acquisition module, a data preprocessing module, a waste liquid analysis module, an anomaly analysis module, a data storage module, and an early warning module; the intelligent waste liquid recycling system is used to realize the intelligent waste liquid recycling method through the cooperation between the modules.

[0015] The above embodiments of the present invention have at least the following beneficial effects: The intelligent wastewater treatment method and system for construction processes described in this invention can collect wastewater concentration data, temperature data, and SCOD values ​​in real time during the wastewater treatment process at construction sites. By preprocessing and serializing the wastewater concentration data, the wastewater treatment status can be monitored more accurately. Based on the wastewater concentration sequence data of the previous moment, the degree of data change at the next moment can be judged, and cluster analysis and feature extraction can be performed when the change exceeds a set value. This can effectively identify abnormal situations in the wastewater treatment process, take timely measures to adjust, and improve the stability and reliability of wastewater treatment.

[0016] Furthermore, this method and system can generate early warning information based on anomaly analysis results and temperature data, and send the warning information to wastewater treatment equipment that has not yet processed the corresponding temperature data, thus achieving collaborative control between equipment. This intelligent early warning and collaborative mechanism can optimize the wastewater treatment process, improve treatment efficiency, and reduce energy consumption, thereby reducing pollutant and carbon emissions during wastewater treatment and helping construction sites achieve their goals of energy conservation, emission reduction, and sustainable development. Attached Figure Description

[0017] The above and other objects, features, and advantages of exemplary embodiments of the present invention will become readily apparent from the following detailed description taken in conjunction with the accompanying drawings. Several embodiments of the invention are illustrated in the drawings by way of example and not limitation, wherein: Figure 1 A schematic flowchart of an intelligent wastewater treatment method for building construction process provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of an intelligent waste liquid treatment system for building construction process provided in an embodiment of the present invention; Figure 3 A schematic diagram of the structure of an electronic device according to an embodiment of the present invention is shown. Detailed Implementation

[0018] The principles and spirit of the invention will now be described with reference to several exemplary embodiments. It should be understood that these embodiments are provided merely to enable those skilled in the art to better understand and implement the invention, and are not intended to limit the scope of the invention in any way. Rather, these embodiments are provided to make the invention more thorough and complete, and to fully convey the scope of the invention to those skilled in the art.

[0019] Those skilled in the art will recognize that embodiments of the present invention can be implemented as a system, apparatus, device, method, or computer program product. Therefore, the present invention can be specifically implemented in the following forms: entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0020] It should be noted that the number of any elements in the accompanying drawings is for illustrative purposes only and not as a limitation, and any naming is for distinction only and has no limiting meaning.

[0021] The following is for reference. Figure 1 , Figure 1 This is a schematic flowchart illustrating an intelligent wastewater treatment method for building construction processes, provided as an embodiment of the present invention. Figure 1 As shown, a smart wastewater treatment method 100 for construction processes includes: Step 101: Real-time acquisition of waste liquid concentration data, temperature data, and SCOD value during the waste liquid treatment process; Step 102: Preprocess the waste liquid concentration data to obtain preprocessed waste liquid concentration data; and convert the preprocessed waste liquid concentration data into waste liquid concentration sequence data arranged in chronological order. Step 103: Based on the waste liquid concentration sequence data of the previous moment, determine whether the degree of change in the waste liquid concentration sequence data of the next moment is greater than a set degree value. Step 104: If yes, then perform cluster analysis on the waste liquid concentration sequence data at the next time step to determine the classification type of the waste liquid concentration sequence data at the next time step, and use a feature extraction model to extract the feature information in the waste liquid concentration sequence data at the next time step to form a feature information matrix. Step 105: Based on the classification type, the feature information matrix is ​​analyzed using the corresponding information analysis unit in the waste liquid analysis model to obtain the waste liquid analysis results; Step 106: When there is abnormal information in the waste liquid analysis results, obtain the abnormal waste liquid concentration sequence data for a set time period starting from the next moment, and use the abnormal analysis model to analyze the abnormal waste liquid concentration sequence data to obtain the abnormal analysis results. Step 107: Generate early warning information based on the anomaly analysis results and temperature data; and obtain information on waste liquid treatment equipment within a set range that is not processing the temperature data; and send early warning information to the waste liquid treatment equipment based on the waste liquid treatment equipment information.

[0022] It should be noted that the intelligent wastewater recycling method of this invention first involves real-time acquisition of wastewater concentration data, temperature data, and SCOD values ​​during the wastewater treatment process at construction sites. Here, wastewater concentration refers to the content of solid matter in the wastewater, usually expressed as mass concentration (e.g., g / L); temperature data refers to the temperature of the environment or the wastewater itself during the wastewater treatment process, usually expressed in degrees Celsius (°C); and SCOD value, or chemical oxygen demand, is an important indicator for measuring the organic matter content in the wastewater, usually expressed in mg / L. This real-time acquisition of these data is achieved through sensors installed at various key nodes at the construction site, which transmit the collected data to the central control system in real time.

[0023] Specifically, waste liquid concentration data can be collected using optical or ultrasonic sensors, which measure the concentration based on the optical and physical properties of the waste liquid. Temperature data is typically collected using thermocouples or resistance temperature detectors, which accurately measure temperature changes during waste liquid treatment. SCOD (Solar Organic Demand) values ​​require chemical analysis instruments, such as photometers or titrators, to determine the organic matter content in the waste liquid through chemical reactions. During data acquisition, a reasonable acquisition frequency needs to be set, such as acquiring data every 10 minutes, to ensure timely capture of dynamic changes during waste liquid treatment.

[0024] Preferably, the preprocessing of waste liquid concentration data may include data filtering to remove abnormal data points caused by sensor noise or measurement errors. For example, a moving average filtering algorithm can be used to average multiple continuously collected waste liquid concentration data points, thereby obtaining smoother and more accurate preprocessed waste liquid concentration data.

[0025] Furthermore, when converting the pretreated waste liquid concentration data into a waste liquid concentration sequence data arranged in chronological order, a time window can be set, such as every 30 minutes. The waste liquid concentration data within this time window is taken as a sequence data point, thereby forming a complete time series dataset, which provides a foundation for subsequent data analysis and processing.

[0026] In some embodiments, determining whether the change in waste liquid concentration sequence data at a subsequent time point is greater than a predetermined value based on the waste liquid concentration sequence data from the previous time point includes: The waste liquid concentration sequence data is converted into concentration information sets and temperature information sets for corresponding channels through a dual-channel system of concentration and temperature, and then stored in chronological order. Obtain the concentration information set of the previous moment and the concentration information set of the next moment; The formula for calculating the degree of change between the concentration information set at the next time step and the concentration information set at the previous time step is as follows: in, This represents the i-th concentration value in the concentration information set at the next moment in the concentration channel. The concentration value is the i-th concentration value in the concentration information set of the previous time step; the value used to determine the degree of change is... Is it greater than the set level value?

[0027] It should be noted that the step in this invention of determining whether the change in the waste liquid concentration sequence data at a subsequent time step exceeds a predetermined value based on the waste liquid concentration sequence data at the previous time step is achieved through time series analysis of the waste liquid concentration data. Here, the degree of change value refers to the difference between the waste liquid concentration sequence data at the subsequent time step and the previous time step, used to assess the trend of waste liquid concentration change over time. This assessment is crucial for the timely detection of abnormal changes in the waste liquid treatment process, as abnormal changes may indicate problems in the treatment process, such as equipment failure or deviations in process parameters.

[0028] In practical applications, the set degree value can be determined based on the normal fluctuation range of the waste liquid treatment process. For example, if the normal fluctuation range is ±5% of the waste liquid concentration change, then the set degree value can be set to 5% accordingly.

[0029] Preferably, to improve the accuracy and reliability of the change value calculation, a sliding window method can be used. For example, a sliding window containing 10 data points can be set. As new data is continuously collected, the data points in the window are continuously updated, and the change value is recalculated after each update. This ensures that the change value can reflect the latest trend of waste liquid concentration in a timely manner.

[0030] Furthermore, in addition to calculating the average degree of change, the standard deviation of the degree of change can also be calculated to assess the stability of the change. If the standard deviation is too large, it may indicate that the waste liquid concentration is unstable and requires further analysis and treatment.

[0031] In some embodiments, the step of performing cluster analysis on the waste liquid concentration sequence data at the next time moment to determine the classification type of the waste liquid concentration sequence data at the next time moment includes: converting the waste liquid concentration sequence data at the next time moment into an initial cluster dataset using a preset converter; and analyzing the initial cluster dataset using a clustering model constructed based on historical waste liquid data to obtain the classification type.

[0032] It should be noted that the step of performing cluster analysis on the waste liquid concentration sequence data at the next time step to determine its classification type is implemented using clustering algorithms from data mining techniques. Cluster analysis is a statistical analysis method that groups objects in a dataset, ensuring high similarity among objects within the same group and low similarity among objects in different groups. In this invention, the waste liquid concentration sequence data at the next time step is converted into an initial clustering dataset through a preset converter. The converter's function is to format the original data into a form suitable for processing by the clustering algorithm. The clustering model is built based on historical waste liquid data, and it can classify new data according to patterns and trends in historical data.

[0033] Specifically, a preset converter can be a data standardization or normalization tool that converts waste liquid concentration sequence data into a dimensionless form, allowing for comparison and analysis of data with different dimensions. For example, waste liquid concentration data can be normalized to the range of 0 to 1. Clustering models can employ algorithms such as K-means, hierarchical clustering, or DBSCAN. Each algorithm has its advantages: K-means is suitable for relatively uniform data distribution, hierarchical clustering can handle clusters of different sizes and shapes, and DBSCAN is robust to noisy data. When constructing a clustering model, it is necessary to select an appropriate clustering algorithm and parameters based on the characteristics of the historical waste liquid data, such as the number of clusters K in the K-means algorithm.

[0034] Preferably, to improve the accuracy and adaptability of cluster analysis, a method of dynamically adjusting clustering parameters can be adopted. For example, when using the K-means algorithm, the number of clusters K can be dynamically adjusted according to the distribution of waste liquid concentration data. This can be achieved through the Elbow Method, which calculates the ratio of intra-cluster variance to inter-cluster variance under different K values ​​and selects the K value with the smallest ratio as the optimal number of clusters.

[0035] Furthermore, to address potential noise in the data, a data cleaning step can be introduced before cluster analysis, such as removing obviously outlier data points or using robust statistical methods to reduce the impact of noise. This ensures that the clustering results more accurately reflect the actual distribution of the waste liquid concentration sequence data.

[0036] In some embodiments, the feature extraction process of the feature extraction model includes: dividing the waste liquid concentration sequence data at a later time into multiple irregular segments; selecting segments that conform to the corresponding segmentation type from each segment data according to the segmentation type to obtain multiple key analysis data; and using a feature extractor to extract the feature information of each key analysis data to form multiple feature information matrices.

[0037] It should be noted that the feature extraction model aims to extract key information from the waste liquid concentration sequence data at a later time step for subsequent analysis. This process first divides the data into multiple irregular segments based on the data's characteristics and trends, with the goal of capturing local features. Next, based on the segmentation type, segments matching the corresponding segmentation type are selected, resulting in multiple key analytical data points. Here, the segmentation type refers to the data category determined through cluster analysis, reflecting different patterns or states of the waste liquid concentration sequence data. Finally, a feature extractor extracts the feature information from each key analytical data point, forming multiple feature information matrices. These matrices contain the key features for further analysis.

[0038] Specifically, the segmentation step in the feature extraction model can employ various methods, such as time-window-based segmentation or data change rate-based segmentation. For example, a fixed time window can be set, such as every 30 minutes as a segmentation point, or segmentation can be performed based on the rate of change of waste liquid concentration, when the rate of change exceeds a certain threshold. When filtering segmented data that conforms to the segmentation type, specific parameters can be set, such as the magnitude and duration of concentration changes, to determine which segmented data are key analytical data. Feature extractors can use statistical methods, such as calculating the mean, variance, maximum, and minimum values, to extract feature information. These statistics can be used as elements of the feature information matrix for subsequent analysis.

[0039] Preferably, to improve the efficiency and accuracy of feature extraction, an adaptive segmentation method can be employed, which dynamically adjusts the segmentation strategy based on the real-time characteristics of the data. For example, machine learning algorithms can be introduced to predict the optimal segmentation point instead of using fixed rules. When extracting feature information, in addition to basic statistics, more complex features, such as frequency domain features and time-frequency domain features, can be considered to capture more details of the data.

[0040] Furthermore, in order to process high-dimensional feature information matrices, dimensionality reduction techniques, such as principal component analysis (PCA) or linear discriminant analysis (LDA), can be used to reduce the dimensionality of the data while retaining the most important information, thereby improving the efficiency and effectiveness of subsequent analysis.

[0041] In some embodiments, the processing of the waste liquid analysis model includes: inputting each feature information matrix into the corresponding information analysis unit according to the classification type; each information analysis unit determines whether the feature information matrix conforms to the preset feature information library's set standard according to its own preset feature information library; when it does not conform to the set standard, abnormal segment data is obtained, and waste liquid analysis results containing abnormal segment data information are obtained.

[0042] It's important to note that the waste liquid analysis model processes the extraction of a feature information matrix into corresponding information analysis units. These units then use a pre-defined feature information database to determine if the matrix conforms to a standard. Here, the information analysis unit refers to a module specifically designed for analyzing specific types of data, such as a waste liquid concentration analysis unit or a temperature analysis unit. The pre-defined feature information database is a dataset containing both normal and abnormal feature information, used as a judgment standard. When the feature information matrix does not meet the pre-defined standard, the analysis unit can identify abnormal data segments and generate waste liquid analysis results containing information about these abnormal segments. This is crucial for the timely detection and handling of problems in the waste liquid treatment process.

[0043] Specifically, the preset feature information library in the information analysis unit includes the standard set range for each element in the feature information matrix and the set variation range between each element and its surrounding elements. For example, for the waste liquid concentration analysis unit, the standard set range might be the normal waste liquid concentration range determined based on historical data and process requirements, such as 1000-3000 mg / L. The set variation range might refer to the reasonable range of concentration variation between adjacent data points, such as ±10%. These parameters need to be set based on a large amount of experimental data and actual operating experience to ensure the accuracy and reliability of the analysis results. During the analysis process, if an element in the feature information matrix exceeds the standard set range or variation range, the data segment containing that element will be marked as an abnormal segment.

[0044] Preferably, to improve the accuracy and adaptability of the waste liquid analysis model, a dynamically updated preset feature information database can be used. This means that as new data accumulates, the feature information database can be automatically updated and optimized to reflect the latest changes and trends in the waste liquid treatment process.

[0045] Furthermore, machine learning algorithms can be introduced to assist in the analysis, such as using support vector machines (SVM) or neural networks to identify anomalous patterns in the feature information matrix. These algorithms can learn complex relationships in the data and improve the ability to identify anomalies. Simultaneously, to improve the efficiency of the analysis, parallel processing techniques can be employed, enabling multiple information analysis units to analyze different feature information matrices simultaneously, thereby accelerating the entire analysis process.

[0046] In some embodiments, the setting criteria of the preset feature information database include the standard setting range of each element in the feature information matrix and the setting change range between the element and its surrounding elements.

[0047] It should be noted that the pre-defined criteria for the feature information database are crucial for determining whether the feature information matrix in the waste liquid analysis model conforms to normal operating conditions. These criteria include the standard setting range for each element in the feature information matrix, meaning each feature value should be within a predetermined reasonable range, as well as the set variation range between elements and their surrounding elements, referring to the allowable range of relative changes between feature values. These criteria are set to accurately identify abnormalities in the waste liquid treatment process, thereby enabling timely adjustments and treatments to ensure the stable operation of the waste liquid treatment system.

[0048] Specifically, the standard setting range can be determined based on the requirements of the wastewater treatment process and historical data statistics. For example, for the characteristic of wastewater concentration, the standard setting range might be the normal operating range derived from long-term operational data, such as 2000-3000 mg / L. The setting variation range considers the reasonable variation range of wastewater concentration within a short period of time, such as ±5%. The setting of these parameters needs to comprehensively consider factors such as the source of the wastewater, the characteristics of the treatment process, and the operating status of the equipment. In practical applications, these standards can be set using expert systems or data analysis software and can be adjusted and optimized according to actual operating conditions.

[0049] Preferably, to improve the accuracy and adaptability of the preset feature information database, an adaptive learning algorithm can be used to dynamically adjust the set standards. For example, using an online learning algorithm, the system can continuously update the standard setting range and the setting change range based on real-time collected data to adapt to seasonal changes or process adjustments that may occur during waste liquid treatment.

[0050] Furthermore, anomaly detection algorithms, such as the Local Anomaly Factor (LOF) algorithm, can be introduced to assist in identifying outliers in the feature information matrix. These algorithms can automatically identify feature values ​​that deviate from the normal pattern based on the data distribution characteristics, thereby improving the accuracy and sensitivity of anomaly detection. Simultaneously, to ensure the robustness of the system, a multi-level early warning mechanism can be set up, issuing an alert when the feature value deviates slightly from the set standard, and triggering emergency response measures when the deviation is severe.

[0051] In some embodiments, the analysis process of the anomaly analysis model includes: screening sequences containing abnormal segment data from abnormal waste liquid concentration sequence data according to abnormal segment data information to obtain abnormal sequence data; when the number of abnormal sequence data exceeds a preset number, analyzing each abnormal sequence data based on a preset anomaly information database corresponding to the classification type to determine the first anomaly probability value of each abnormal sequence data and the second anomaly probability value corresponding to the number of abnormal sequence data. The first and second anomaly probability values ​​are processed using a weighted average method to calculate the average anomaly probability value. The level corresponding to the average anomaly probability value is used as the anomaly level. Anomaly analysis results are formed based on the classification type, anomaly level, and data of each anomaly sequence.

[0052] It should be noted that the anomaly analysis model's analysis process is based on anomaly segmentation data information. It filters sequences containing anomaly segmentation data from the abnormal waste liquid concentration sequence data, i.e., anomaly sequence data. This process is to further determine the severity and nature of the anomaly. When the number of anomaly sequence data exceeds a preset number, the model will conduct in-depth analysis of each anomaly sequence data according to a preset anomaly information database corresponding to the classification type, determining the first anomaly probability value for each anomaly sequence data and the second anomaly probability value corresponding to the number of anomaly sequence data. Here, the first anomaly probability value refers to the likelihood of a single anomaly sequence data being abnormal, while the second anomaly probability value considers the impact of the number of anomaly sequence data on the overall anomaly situation. Finally, a weighted average method is used to process these two probability values, calculating the average anomaly probability value, and the corresponding level is used as the anomaly level, forming the final anomaly analysis result.

[0053] Specifically, the screening process for anomalous sequence data can be achieved by setting a threshold. For example, when the similarity between the feature information matrix of anomaly segment data and the normal feature information matrix is ​​lower than a certain set similarity threshold (e.g., 80%), the anomalous waste liquid concentration sequence data is marked as anomalous sequence data. The pre-defined anomalous information database contains features and probability models of anomalous sequence data under different classification types. These models are constructed based on historical anomalous data and expert knowledge. When calculating the first anomalous probability value, statistical methods or machine learning algorithms, such as logistic regression or decision trees, can be used to assess the anomalousness of a single anomalous sequence data. The calculation of the second anomalous probability value needs to consider the number of anomalous sequence data. A simple linear relationship or a more complex nonlinear model can be used to quantify the impact of quantity on the anomalous probability.

[0054] Preferably, to improve the accuracy of anomaly analysis, more advanced machine learning algorithms, such as convolutional neural networks (CNNs) or recurrent neural networks (RNNs) in deep learning, can be used to automatically learn the feature representations of anomalous sequence data and predict anomaly probabilities. These algorithms can capture complex patterns and time-series characteristics in the data, thereby improving the performance of anomaly detection.

[0055] Furthermore, the weights in the weighted average method can be dynamically adjusted based on the importance and reliability of the abnormal sequence data. For example, abnormal sequence data confirmed by multiple sensors can be assigned higher weights. Simultaneously, to better reflect the severity of the anomaly, the anomaly level can be further subdivided into multiple levels, and corresponding response measures can be set for each level, such as early warning, alarm, or emergency shutdown.

[0056] In some embodiments, the process of obtaining abnormal sequence data includes: based on the feature information matrix of abnormal segmented data, determining whether the feature information matrix transformed from abnormal waste liquid concentration sequence data contains a feature information matrix with a similarity exceeding a set similarity; if so, the abnormal waste liquid concentration sequence data is marked as abnormal sequence data.

[0057] It should be noted that the screening process for abnormal sequence data is based on the feature information matrix of the abnormal segmented data. The similarity between these feature information matrices and the normal feature information matrix is ​​used to determine whether the abnormal waste liquid concentration sequence data is abnormal. Here, similarity refers to the degree of closeness between two feature information matrices in terms of values, patterns, or distributions, usually represented by a quantitative index such as cosine similarity or Euclidean distance. If the feature information matrix transformed from the abnormal waste liquid concentration sequence data contains a feature information matrix whose similarity to the normal feature information matrix exceeds a set similarity threshold, then the abnormal waste liquid concentration sequence data is marked as abnormal. This process is crucial for accurately identifying and handling anomalies in the waste liquid treatment process.

[0058] Specifically, similarity can be calculated using various methods. For example, cosine similarity can be used to measure the directional similarity between two feature information matrices, calculated as the dot product of the two matrices divided by their respective moduli. The similarity threshold can be determined based on historical data and the distribution of the feature information matrices during normal operation. This threshold is typically adjusted according to the specific application scenario and the required sensitivity for anomaly detection. For instance, a lower threshold, such as 0.7, can be set to increase sensitivity to anomalies, while a higher threshold, such as 0.9, can be set to reduce false alarms. In practical applications, the calculation of similarity and the setting of the threshold need to be optimized in conjunction with the specific wastewater treatment process and equipment characteristics.

[0059] Preferably, to improve the accuracy and reliability of abnormal sequence data screening, a combination of multiple similarity measurement methods can be used, and machine learning algorithms can be employed to automatically select the optimal similarity measurement method and threshold. For example, ensemble learning methods, such as random forests or gradient boosting machines, can be used to comprehensively consider the results of different similarity measurement methods and learn the optimal decision boundary.

[0060] Furthermore, time series analysis methods can be introduced to consider the continuity and correlation of anomalous data segments over time, thereby more accurately identifying anomalous sequence data. For example, if anomalous data segments at multiple consecutive time points show a high similarity to normal data, then these data are more likely to be genuine anomalous sequence data. Simultaneously, to further verify the screening results, a feedback mechanism can be set up to compare the screened anomalous sequence data with the actual processing results. Based on the comparison results, the similarity measurement method and threshold can be adjusted to achieve self-optimization and learning.

[0061] In some embodiments, the information analysis unit includes at least a waste liquid concentration analysis unit, a temperature analysis unit, an SCOD value analysis unit, a treatment efficiency analysis unit, and an equipment status analysis unit.

[0062] It should be noted that the information analysis unit is a key component in the intelligent waste liquid recycling system used to analyze various data during the waste liquid treatment process. These units include at least a waste liquid concentration analysis unit, a temperature analysis unit, an SCOD value analysis unit, a treatment efficiency analysis unit, and an equipment status analysis unit. Each analysis unit focuses on a specific type of data analysis to ensure a comprehensive and accurate assessment of the waste liquid treatment process. For example, the waste liquid concentration analysis unit monitors changes in the solid content of the waste liquid, while the equipment status analysis unit focuses on the operating status of the treatment equipment, such as operating time and failure rate.

[0063] Specifically, the waste liquid concentration analysis unit can determine whether the waste liquid is in a normal treatment state by setting concentration thresholds. For example, if the waste liquid concentration exceeds the set upper threshold (e.g., 3500 mg / L) or falls below the lower threshold (e.g., 1500 mg / L), it may indicate an abnormality in the treatment process. The temperature analysis unit monitors temperature changes during the waste liquid treatment process; abnormal increases or decreases in temperature may affect the activity of microorganisms, thereby affecting the treatment effect. The SCOD value analysis unit is used to assess the degradation of organic matter in the waste liquid; significant changes in the SCOD value may indicate changes in treatment efficiency. The treatment efficiency analysis unit can assess the efficiency of the treatment process by comparing the quantity and quality of input and output waste liquid, while the equipment status analysis unit predicts potential equipment failures by monitoring equipment operating parameters such as motor current and pressure.

[0064] Preferably, to improve the accuracy and timeliness of the analysis, real-time data analysis techniques, such as online monitoring and instant feedback, can be employed. For example, the waste liquid concentration analysis unit can be equipped with real-time sensors capable of updating data every minute and performing immediate analysis. For the temperature analysis unit, high-precision temperature sensors can be used, combined with the rate of temperature change, to predict potential temperature anomalies. The SCOD value analysis unit can employ rapid chemical analysis methods, such as enzyme-linked immunosorbent assay (ELISA), to shorten analysis time. The treatment efficiency analysis unit can utilize advanced data mining techniques, such as association rule learning, to discover potential factors contributing to decreased treatment efficiency. The equipment status analysis unit can incorporate machine learning algorithms, such as support vector machines (SVM), to predict equipment failures. Furthermore, to achieve more efficient collaborative work, data sharing mechanisms can be established between the various analysis units, such as through a central database or distributed data platform, for comprehensive analysis and decision-making.

[0065] The above-described embodiments of the present invention have the following beneficial effects: The intelligent waste liquid recycling treatment method and system of the present invention can achieve refined monitoring and control of the waste liquid treatment process at construction sites. By collecting key data such as waste liquid concentration, temperature, and SCOD value in real time, and performing preprocessing and serialization analysis on the waste liquid concentration data, the system can accurately grasp the dynamic changes in waste liquid treatment. When the degree of change in waste liquid concentration sequence data exceeds a set value, cluster analysis and feature extraction models can be used to quickly determine the classification type of waste liquid concentration sequence data, extract feature information to form a matrix, and then conduct in-depth analysis through a waste liquid analysis model. This series of operations can promptly detect abnormalities in the waste liquid treatment process, providing a scientific basis for taking targeted treatment measures, thereby improving the efficiency and quality of waste liquid treatment and reducing environmental pollution caused by improper treatment.

[0066] Furthermore, upon detecting anomalies, this method and system can acquire abnormal wastewater concentration sequence data and perform detailed analysis using an anomaly analysis model to generate accurate early warning information. Combined with temperature data, the early warning information can be precisely sent to wastewater treatment equipment within the set range that has not yet reached the corresponding temperature data, achieving intelligent linkage and collaborative processing between devices. This early warning and collaborative mechanism not only optimizes the wastewater treatment process and improves the overall system's operational efficiency but also effectively reduces energy consumption and carbon emissions, which is of great significance for promoting the green development of the wastewater treatment industry. Simultaneously, by establishing feature information databases and anomaly information databases, the system can more accurately identify and handle abnormal situations, enhancing the intelligence level of wastewater treatment and providing strong support for the efficient operation and environmental sustainability of construction sites.

[0067] like Figure 2As shown in some embodiments, a smart wastewater treatment system 200 for a building construction process includes: The system comprises a data acquisition module 201, a data preprocessing module 202, a waste liquid analysis module 203, an anomaly analysis module 204, a data storage module 205, and an early warning module 206. The intelligent waste liquid recycling system is used to realize the intelligent waste liquid recycling method through the cooperation between the modules.

[0068] It is understandable that the modules described in the intelligent wastewater treatment system 200 during the construction process are consistent with the references. Figure 1 The steps in the intelligent wastewater treatment method for the building construction process described above correspond to each other. Therefore, the operation, characteristics, and beneficial effects of the intelligent wastewater treatment method for the building construction process described above also apply to the intelligent wastewater treatment system 200 for the building construction process and its included modules, and will not be repeated here.

[0069] The following is for reference. Figure 3 The diagram illustrates a structural schematic of an electronic device 300 suitable for implementing some embodiments of the present invention. The electronic devices in some embodiments of the present invention may include, but are not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 3 The terminal device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of the present invention.

[0070] like Figure 3 As shown, the electronic device 300 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. The RAM 303 also stores various programs and data required for the operation of the electronic device 300. The processing unit 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0071] Typically, the following devices can be connected to I / O interface 305: input devices 306 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 307 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 308 including, for example, magnetic tapes, hard disks, etc.; and communication devices 309. Communication device 309 allows electronic device 300 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 3 An electronic device 300 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively. Figure 3 Each box shown can represent a device or multiple devices as needed.

[0072] Furthermore, the storage medium in the embodiments of this application stores program instructions capable of implementing all the above methods. These program instructions can be stored in the storage medium in the form of a software product, including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks, or terminal devices such as computers, servers, mobile phones, and tablets.

[0073] The above description is merely an explanation of some preferred embodiments of the present invention and the technical principles employed. Those skilled in the art should understand that the scope of the invention as described in the embodiments of the present invention is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in the embodiments of the present invention.

Claims

1. A method for intelligent treatment of waste liquid in a building construction process, characterized in that, The method comprises the following steps: Real-time acquisition of waste liquid concentration data, temperature data and SCOD values; Pretreatment of waste liquid concentration data to obtain pretreated waste liquid concentration data; Converting the pretreated waste liquid concentration data into waste liquid concentration sequence data arranged in time sequence; Judging, based on the waste liquid concentration sequence data at the previous time, whether the change degree of the waste liquid concentration sequence data at the next time is greater than a set degree value; If yes, performing clustering analysis on the waste liquid concentration sequence data at the next time, determining the division type of the waste liquid concentration sequence data at the next time, and extracting feature information in the waste liquid concentration sequence data at the next time by using a feature extraction model to form a feature information matrix; According to the division type, analyzing the feature information matrix by using the corresponding information analysis unit in the waste liquid analysis model to obtain a waste liquid analysis result; When the waste liquid analysis result contains abnormal information, obtaining abnormal waste liquid concentration sequence data in a set time period starting from the next time, and analyzing the abnormal waste liquid concentration sequence data by using an abnormal analysis model to obtain an abnormal analysis result; Generating warning information according to the abnormal analysis result and the temperature data; and obtaining waste liquid treatment equipment information within a set range and not processed to the temperature data; and sending the warning information to the waste liquid treatment equipment through the waste liquid treatment equipment information.

2. The intelligent waste liquid recycling processing method according to claim 1, characterized in that, The method comprises the following steps: Converting the waste liquid concentration sequence data into concentration information sets and temperature information sets corresponding to the two channels through the concentration and temperature double channels, and storing them in time sequence; Obtaining the concentration information set at the previous time and the concentration information set at the next time; Calculating the change degree value between the concentration information set at the next time and the concentration information set at the previous time, and the calculation formula of the change degree value is: wherein, is the i-th concentration value in the concentration information set of the previous time instant of the concentration channel, is the i-th concentration value in the concentration information set of the previous time instant of the concentration channel; the change degree value is compared to a set degree value.

3. The intelligent waste liquid recycling processing method according to claim 1, characterized in that, The method comprises the following steps:

4. The intelligent waste liquid recycling processing method according to claim 1, characterized in that, Converting the waste liquid concentration sequence data at the next time into an initial clustering data set through a preset converter; and analyzing the initial clustering data set by using a clustering model constructed based on historical waste liquid data to obtain the division type.

5. The intelligent waste liquid recycling processing method according to claim 4, characterized in that, The extraction process of the feature extraction model comprises the following steps:

6. The intelligent waste liquid recycling processing method according to claim 5, characterized in that, Dividing the waste liquid concentration sequence data at the next time into a plurality of irregular segmented data; according to the division type, screening segmented data conforming to the corresponding division type from each segmented data to obtain a plurality of key analysis data; and extracting feature information of each key analysis data by using a feature extractor to form a plurality of feature information matrices. The processing process of the waste liquid analysis model comprises the following steps: According to the division type, inputting each feature information matrix into the corresponding information analysis unit; each information analysis unit judges whether the feature information matrix conforms to the set standard of the preset feature information library according to the preset feature information library of each information analysis unit; when the set standard is not met, obtaining abnormal segmented data, and obtaining a waste liquid analysis result containing abnormal segmented data information. The set standard of the preset feature information library comprises a standard setting interval of each element in the feature information matrix and a set change interval of the element and the surrounding elements.

7. The intelligent waste liquid recycling processing method according to claim 5, characterized in that, The analysis process of the anomaly analysis model comprises: screening the abnormal segment data information from the abnormal waste liquid concentration sequence data to obtain abnormal sequence data; when the number of abnormal sequence data exceeds a preset number, analyzing each abnormal sequence data based on the preset abnormal information library corresponding to the division type to determine a first abnormal probability value of each abnormal sequence data and a second abnormal probability value corresponding to the number of abnormal sequence data; The first abnormal probability value and the second abnormal probability value are processed by using a weighted average method to calculate an average abnormal probability value, and a level corresponding to the average abnormal probability value is taken as an abnormal level; an abnormal analysis result is formed according to the division type, the abnormal level and each abnormal sequence data.

8. The intelligent waste liquid recycling processing method according to claim 7, characterized in that, The screening process for obtaining abnormal sequence data comprises: judging whether the feature information matrix transformed from the abnormal waste liquid concentration sequence data contains a feature information matrix with a similarity exceeding a set similarity based on the feature information matrix of the abnormal segment data; if yes, the abnormal waste liquid concentration sequence data is marked as abnormal sequence data.

9. The intelligent waste liquid recycling processing method according to claim 1, characterized in that, The information analysis unit at least comprises a waste liquid concentration analysis unit, a temperature analysis unit, an SCOD value analysis unit, a treatment efficiency analysis unit and an equipment state analysis unit.

10. A waste liquid intelligent processing system for a building construction process, characterized in that, The waste liquid intelligent recycling treatment system comprises a data acquisition module, a data preprocessing module, a waste liquid analysis module, an anomaly analysis module, a data storage module and a warning module; the waste liquid intelligent recycling treatment system is used to realize the waste liquid intelligent recycling treatment method as claimed in any one of claims 1-9 through mutual cooperation between the modules.

Images