A method for optimizing energy consumption ratio of sludge drying system based on big data

Abstract

The present invention discloses a method for optimizing the energy consumption ratio of a sludge drying system based on big data. The method belongs to the technical field of sludge treatment, and comprises the following steps: collecting the operating data of the sludge drying system through sensors; preprocessing the collected operating data to obtain stationary sequence data and generate a high-quality data set; extracting key characteristic parameters from the preprocessed high-quality data set; training the key characteristic parameters using a random forest algorithm, establishing an energy consumption ratio prediction model to predict the energy consumption ratio in the drying process in real time, and adjusting the operating parameters of the drying system according to the prediction results to obtain an optimized energy consumption ratio prediction model; visualizing the optimized energy consumption ratio prediction model data and generating a report; and automatically controlling and diagnosing faults in the sludge drying system. The present invention optimizes the energy consumption ratio of the sludge drying system by applying big data analysis and a random forest algorithm, and solves the problem of low energy consumption ratio of the sludge drying system in the prior art.

Description

Technical Field

[0001] The present invention relates to the technical field of sludge treatment, and in particular to an energy consumption ratio optimization method of a sludge drying system based on big data. Background Art

[0002] With the acceleration of urbanization and the improvement of environmental protection requirements, the efficiency and energy consumption of sludge treatment have become increasingly prominent. The sludge drying system is a combination of equipment and technology for treating sludge generated during sewage treatment. Its main purpose is to reduce the moisture content of sludge by physical, chemical or biological methods, thereby reducing its volume and weight for subsequent treatment, disposal or resource utilization. Traditional sludge treatment methods usually rely on a large amount of energy, resulting in high operating costs, serious energy waste, and easy secondary pollution to the environment. Therefore, finding efficient, energy-saving and environmentally friendly sludge treatment technology has become an important direction for the development of the industry.

[0003] The energy consumption ratio of the existing sludge drying system is optimized by real-time data collection and monitoring through intelligent Internet of Things technology, combined with time parameter setting and dynamic adjustment of operating speed. Real-time monitoring and adjustment of moisture content change value is achieved.

[0004] For example, the invention patent with announcement number: CN116282819B announces an energy consumption ratio optimization method for a sludge drying system based on an intelligent Internet of Things, including: obtaining the first sludge moisture content and the second sludge moisture content of a non-last chain network of the sludge drying system in real time; the initial operation time of each chain network is set to t, and the total operation time of the n-layer chain network is set to T; the difference between the first sludge moisture content and the second sludge moisture content is defined as a moisture content change value, and if the moisture content change value of the current chain network layer is continuously less than the first preset change value within a specified time range, the operation speed of the current chain network layer is increased according to the preset parameters, and at the same time, the operation speed of the last chain network layer is reduced according to the preset parameters to keep the total operation time T unchanged.

[0005] For example, the sludge pyrolysis resource utilization system and pyrolysis method disclosed in the invention patent with announcement number CN110066083B include: a specially designed spiral pyrolysis reactor that can realize forced mixing and rapid heat transfer of sludge. The solid heat carrier is mixed with the sludge for direct heating, which has high thermal efficiency and uniform heating compared with the indirect heating method; the spiral blades and stirring blades reasonably set in the pyrolysis reactor can realize full mixing and rapid heat transfer of sludge and heat carrier, fast pyrolysis reaction rate, strong system processing capacity, and effectively solve the coking problem caused by uneven sludge stirring, so as to realize long-term stable operation of the system; the waste heat flue gas is recycled to pre-dry the sludge, realizing the hierarchical utilization of energy, which can effectively reduce energy consumption and improve the energy utilization efficiency of the system.

[0006] However, in the process of implementing the technical solution of the invention in the embodiments of the present application, the present application found that the above technology has at least the following technical problems:

[0007] In the prior art, the traditional method for optimizing the energy consumption ratio of the sludge drying system removes moisture from the sludge while reducing energy consumption by selecting efficient and energy-saving drying equipment and heating equipment. However, the sludge drying process still requires a large amount of heat energy, resulting in a high overall energy consumption. Therefore, there is a problem of low energy consumption ratio of the sludge drying system. Summary of the invention

[0008] The embodiment of the present application solves the problem of low energy consumption ratio of sludge drying systems in the prior art by providing a method for optimizing the energy consumption ratio of sludge drying systems based on big data, thereby achieving optimization of the energy consumption ratio of sludge drying systems.

[0009] The embodiment of the present application provides a method for optimizing the energy consumption ratio of a sludge drying system based on big data, comprising the following steps: collecting operating data of the sludge drying system through sensors; preprocessing the collected operating data to obtain stationary sequence data and generate a high-quality data set; extracting key feature parameters from the preprocessed high-quality data set; training the key feature parameters using a random forest algorithm to establish an energy consumption ratio prediction model; predicting the energy consumption ratio in the drying process in real time according to the energy consumption ratio prediction model, and adjusting the operating parameters of the drying system according to the prediction results to obtain an optimized energy consumption ratio prediction model; visualizing the optimized energy consumption ratio prediction model data and generating a report; and automatically controlling and diagnosing faults of the sludge drying system.

[0010] Furthermore, the specific steps of collecting the operating data of the sludge drying system include: collecting the temperature, humidity, wind speed and energy consumption data of the sludge drying system in real time through temperature sensors, humidity sensors, wind speed sensors and energy consumption metering devices; integrating the real-time collected temperature, humidity, wind speed and energy consumption data of the sludge drying system using data synchronization technology to obtain a complete operating data set; and transmitting the complete operating data set to a database in real time and storing it.

[0011] Furthermore, the specific steps of the preprocessing are: using the Z score in the statistical analysis method to detect and remove outliers in the data; using the mean filtering technology to smooth the data; performing correlation analysis on the collected parameters; calculating the influence of each data in the high-quality data set on the energy consumption ratio; sorting according to the influence degree, giving priority to the data with greater influence; performing Z-score normalization on each data in the high-quality data set; obtaining the data distribution characteristics; performing data transformation according to the data distribution characteristics; using the exponential smoothing method to eliminate the trend component of the data to obtain stable sequence data.

[0012] Furthermore, the specific steps of extracting key feature parameters from the preprocessed high-quality data set are: extracting an initial feature parameter set from the preprocessed data set, wherein the initial feature parameter set includes temperature, humidity, wind speed, and energy consumption; using the PCA method to reduce the dimensionality of the initial feature parameters, converting high-dimensional data into low-dimensional data, and extracting the features that mainly affect the energy consumption ratio; using the Pearson correlation coefficient to calculate the correlation between each feature parameter and the energy consumption ratio; using the multivariate linear regression method, evaluating the contribution of each feature parameter to the energy consumption ratio; using the cross-validation method to compare the performance indicators of the model under different feature combinations and select the feature combination scheme with the best performance indicators to obtain the key feature parameters.

[0013] Furthermore, the steps of establishing the energy consumption ratio prediction model are: standardizing the input feature data to eliminate the dimension effect; introducing feature weights and combining feature data for weighted combination; using the random forest algorithm to build multiple decision trees for integrated prediction; randomly selecting feature subsets as input data for each decision tree; using feature subsets to train decision trees and generate prediction results; integrating the prediction results of all decision trees and obtaining the energy consumption ratio prediction model by weighted averaging.

[0014] Furthermore, the mathematical formula of the energy consumption ratio prediction model is:

[0015]

[0016] In the formula, represents the real-time energy consumption ratio prediction value, T represents the number of decision trees, α t represents the weight coefficient of the t-th decision tree, t represents the number of the decision tree, t=1,2,3,...,T, f t represents the prediction function of the t-th decision tree, ω i represents the feature weight coefficient, i represents the feature number, i = 1, 2, 3, 4, x i represents the standardized eigenvalue collected in real time, μ i Represents feature x i The mean value, σ i Represents feature x i The standard deviation of .

[0017] Furthermore, the specific steps of adjusting the operating parameters of the drying system according to the prediction results include:

[0018] The pre-processed real-time data is input into the trained energy consumption ratio prediction model to calculate the real-time energy consumption ratio prediction value; the actual energy consumption ratio is obtained by calculating the actual energy consumption and the amount of sludge treated; the deviation between the actual energy consumption ratio and the predicted energy consumption ratio is calculated; the operating parameters are dynamically adjusted according to the deviation to obtain the optimized energy consumption ratio prediction model formula.

[0019] Furthermore, the optimized energy consumption ratio prediction model formula is:

[0020]

[0021] In the formula, represents the optimized real-time energy consumption ratio prediction value, f represents the function of energy consumption ratio, which depends on the adjusted parameter θ0 and real-time characteristic data x, θ0 represents the adjusted operating parameter, k p Represents the proportional control coefficient, E a represents the actual energy consumption, M represents the amount of sludge treated, T represents the number of decision trees, t represents the number of decision trees, t=1,2,3,...,T,α t Represents the weight coefficient of each decision tree, f t represents the prediction function of the t-th decision tree, ω i represents the feature weight coefficient, i represents the feature number, i = 1, 2, 3, 4, x i represents the standardized eigenvalue collected in real time, μ i Represents feature x i The mean value, σ i Represents feature x i The standard deviation of .

[0022] Furthermore, the specific steps of visualizing the optimized energy consumption ratio prediction model data and generating a report include: displaying the real-time temperature, humidity, wind speed, and energy consumption of the sludge drying system through a data visualization tool; displaying the energy consumption ratio analysis results under different time periods and different operating parameters through a user interface; and automatically generating an energy consumption ratio optimization report based on the energy consumption ratio analysis results.

[0023] Furthermore, the specific steps of automating the control and fault diagnosis of the sludge drying system include: obtaining execution control commands; executing control commands through PLC automation equipment to adjust the system operation status in real time; using big data analysis technology to monitor the system operation status in real time and detect potential faults; if an abnormal situation is detected, identifying the cause and influencing factors of the fault data and issuing an early warning signal to notify maintenance personnel to inspect and handle it.

[0024] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0025] 1. By applying the principal component analysis method to reduce the dimension of the preprocessed data set and the random forest algorithm to train the key characteristic parameters, an energy consumption ratio prediction model is established, thereby achieving accurate prediction and real-time optimization of the energy consumption ratio, and then optimizing the energy consumption ratio of the sludge drying system, effectively solving the problem of low energy consumption ratio of the sludge drying system in the existing technology.

[0026] 2. The temperature, humidity, wind speed and energy consumption data of the sludge drying system collected in real time are integrated through data synchronization technology to obtain a complete operating data set, so that the system can respond to changes in the operating status in a timely manner and make scientific and reasonable parameter adjustments, thereby realizing efficient monitoring and optimization of the sludge drying system.

[0027] 3. The energy consumption ratio analysis results under different time periods and different operating parameters are displayed through the user interface, so that users can intuitively understand the operation of the system, thereby realizing efficient operation and management of the sludge drying system. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 A flow chart of a method for optimizing energy consumption ratio of a sludge drying system based on big data provided in an embodiment of the present application;

[0029] Figure 2 An optimized real-time energy consumption ratio prediction diagram provided in an embodiment of the present application. DETAILED DESCRIPTION

[0030] The embodiment of the present application solves the problem of low energy consumption ratio of sludge drying systems in the prior art by providing a method for optimizing the energy consumption ratio of sludge drying systems based on big data, and optimizes the energy consumption ratio of sludge drying systems by applying big data analysis and random forest algorithm.

[0031] The technical solution in the embodiment of the present application is to solve the problem of low energy consumption ratio of the above-mentioned sludge drying system, and the overall idea is as follows: collect operating data of the sludge drying system through sensors; preprocess the collected operating data to obtain stationary sequence data and generate a high-quality data set; extract key feature parameters from the preprocessed high-quality data set; use the random forest algorithm to train the key feature parameters and establish an energy consumption ratio prediction model; predict the energy consumption ratio in the drying process in real time according to the energy consumption ratio prediction model, and adjust the operating parameters of the drying system according to the prediction results to obtain an optimized energy consumption ratio prediction model; visualize the optimized energy consumption ratio prediction model data and generate a report; automatically control and diagnose the sludge drying system to achieve the optimization of the energy consumption ratio of the sludge drying system.

[0032] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0033] like Figure 1As shown, it is a flow chart of a method for optimizing the energy consumption ratio of a sludge drying system based on big data provided in an embodiment of the present application, and the method includes the following steps: collecting operating data of the sludge drying system through sensors; preprocessing the collected operating data to obtain stationary sequence data and generate a high-quality data set; extracting key feature parameters from the preprocessed high-quality data set; training the key feature parameters using a random forest algorithm to establish an energy consumption ratio prediction model; predicting the energy consumption ratio in the drying process in real time according to the energy consumption ratio prediction model, and adjusting the operating parameters of the drying system according to the prediction results to obtain an optimized energy consumption ratio prediction model; visualizing the optimized energy consumption ratio prediction model data and generating a report; and automating control and fault diagnosis of the sludge drying system.

[0034] In this embodiment, big data technology and random forest algorithm are applied to the sludge drying system, aiming to improve the energy consumption ratio, reduce the operating cost, and ensure the stability and reliability of the system. The application of big data technology can monitor and analyze a large amount of operating data in real time, including temperature, humidity, wind speed, energy consumption, etc. These data are collected in real time by sensors and transmitted to the data center for processing and storage. Through data preprocessing, outliers and noise are removed to ensure the high quality of data. Feature extraction and model training are the core links of the method. The feature parameters are trained by the random forest algorithm to establish an energy consumption ratio prediction model. This model can accurately predict the energy consumption ratio in the sludge drying process, providing a scientific basis for real-time optimization. Real-time prediction and optimization adjustment based on the model not only improve the energy efficiency of the system, but also significantly reduce the operating cost and energy consumption. The user interface and report generation function enhance the operability and visibility of the system. Through the data visualization tool, users can intuitively view the operating status, historical data and trend analysis results of the system, and make scientific decisions based on the optimization report. The automatic control and fault diagnosis functions ensure the stable operation of the system, and improve the reliability and maintenance efficiency of the system through real-time monitoring and automatic adjustment. This energy consumption ratio optimization method for sludge drying system based on big data and machine learning is not only innovative and advanced in technology, but also has significant economic and social benefits in practical applications. It provides an effective solution for energy conservation and emission reduction in the environmental protection industry and helps achieve sustainable development goals.

[0035] Furthermore, the specific steps of collecting the operating data of the sludge drying system include: collecting the temperature, humidity, wind speed and energy consumption data of the sludge drying system in real time through temperature sensors, humidity sensors, wind speed sensors and energy consumption metering devices; integrating the real-time collected temperature, humidity, wind speed and energy consumption data of the sludge drying system using data synchronization technology to obtain a complete operating data set; transmitting the complete operating data set to the database in real time and storing it.

[0036] In this embodiment, by real-time monitoring of temperature, humidity, wind speed and energy consumption parameters, the operating status of the system can be accurately grasped. The application of data synchronization technology ensures the consistency of data from different sensors in time and avoids analysis errors caused by data asynchrony. The complete operating data set is transmitted to the data center in real time through wireless transmission technology and stored. This real-time transmission and storage mechanism ensures the timeliness and integrity of the data and provides a reliable data basis for subsequent data analysis and optimization. The use of the big data platform makes data processing and storage more efficient and secure. The acquisition and processing of real-time data provides the necessary data support for the optimization of energy consumption ratio, so that the system can continuously optimize and adjust during operation, reduce energy consumption and improve economic benefits. In addition, real-time data acquisition also provides an important basis for fault diagnosis. By monitoring the changes in key parameters, abnormal conditions in the system can be discovered in time, early warning and processing can be carried out, unplanned downtime can be reduced, and reliable operation of the system can be ensured.

[0037] Furthermore, the specific steps of preprocessing are: using the Z-score in the statistical analysis method to detect and remove outliers in the data; using the mean filtering technology to smooth the data; performing correlation analysis on the collected parameters; calculating the influence of each data in the high-quality data set on the energy consumption ratio; sorting according to the influence, giving priority to the data with greater influence; performing Z-score normalization on each data in the high-quality data set; obtaining the data distribution characteristics; performing data transformation according to the data distribution characteristics; using the exponential smoothing method to eliminate the trend component of the data and obtain stable sequence data.

[0038] In this embodiment, the Z score is used to detect and remove outliers to ensure the accuracy and consistency of the data. Outliers are usually caused by sensor failure, operating errors or environmental interference. If not processed, they may have a greater impact on the analysis results. Smoothing the data by mean filtering technology can effectively reduce the noise in the data and improve the smoothness and analyzability of the data. By calculating the correlation between each parameter and the energy consumption ratio, screening out the key data closely related to the energy consumption ratio can reduce the data dimension, improve the analysis efficiency, and concentrate resources on the parameters that have the greatest impact on the energy consumption ratio. Sort each data item and give priority to the data with greater impact, so that the optimization process is more targeted and effective. Data normalization (such as Z-score normalization) can eliminate the dimensional differences between different parameters, so that the data can be compared and analyzed on the same scale. Data transformation, such as logarithmic transformation, square root transformation, etc., can improve the normality and linearity of the data and enhance the prediction ability of the model according to the characteristics of the data distribution. The trend component of the data is eliminated by the exponential smoothing method to obtain stable sequence data, which further improves the stability and predictability of the data. Data preprocessing not only improves the quality and availability of data, but also lays a good foundation for subsequent feature extraction and model training, making the energy consumption ratio optimization process more scientific and efficient.

[0039] Furthermore, the specific steps of extracting key feature parameters from the preprocessed high-quality data set are as follows: extract an initial feature parameter set from the preprocessed data set, wherein the initial feature parameter set includes temperature, humidity, wind speed, and energy consumption; use the PCA method to reduce the dimensionality of the initial feature parameters, convert high-dimensional data into low-dimensional data, and extract the features that mainly affect the energy consumption ratio; use the Pearson correlation coefficient to calculate the correlation between each feature parameter and the energy consumption ratio; use the multivariate linear regression method to evaluate the contribution of each feature parameter to the energy consumption ratio; use the cross-validation method to compare the performance indicators of the model under different feature combinations and select the feature combination scheme with the best performance indicators to obtain the key feature parameters.

[0040] In this embodiment, the PCA method is used to reduce the dimension of the initial feature parameters, convert high-dimensional data into low-dimensional data, and extract the features that mainly affect the energy consumption ratio. PCA is a commonly used dimensionality reduction technique. Through linear transformation, the original features are projected into a new feature space, the most important part of the data is retained, the data dimension is reduced, and the analysis efficiency is improved. The linear correlation between each feature parameter and the energy consumption ratio is evaluated by calculating the Pearson correlation coefficient. The Pearson correlation coefficient is a commonly used correlation measurement method that can quantify the linear relationship between two variables and screen out feature parameters that are highly correlated with the energy consumption ratio. The multiple linear regression method is used to evaluate the contribution of each feature parameter to the energy consumption ratio. Multiple linear regression is a commonly used regression analysis method that quantifies the degree of influence of each feature parameter on the energy consumption ratio by fitting a linear model. The cross-validation method is used to compare the performance indicators of the model under different feature combinations and select the optimal feature combination scheme. Prevent overfitting and improve the generalization ability of the model.

[0041] Furthermore, the steps of establishing the energy consumption ratio prediction model are as follows: standardize the input feature data to eliminate the dimension effect; introduce feature weights and combine them with feature data for weighted combination; use the random forest algorithm to build multiple decision trees for integrated prediction; randomly select feature subsets as input data for each decision tree; use feature subsets to train decision trees and generate prediction results; integrate the prediction results of all decision trees and obtain the energy consumption ratio prediction model by weighted averaging.

[0042] In this embodiment, the specific steps of establishing the energy consumption ratio prediction model include feature standardization, feature weighted combination, random forest algorithm to build decision trees, and integrated prediction. Model training is the core of the energy consumption ratio optimization method. By establishing a high-precision prediction model, effective control and optimization of the sludge drying process can be achieved. The input feature data is standardized to eliminate the dimensional differences between different feature data and ensure that the data is compared and analyzed on the same scale. By normalizing the mean and standard deviation of the data, the convergence speed and stability of the model can be improved. Feature weights are introduced and weighted combinations are performed in combination with feature data to calculate the contribution of each feature. The sensitivity of the model to important features can be enhanced and the prediction accuracy can be improved. Multiple decision trees are constructed using the random forest algorithm for integrated prediction. By constructing multiple decision trees and voting or weighted averaging the results, the prediction performance and robustness of the model can be significantly improved. Randomly selecting a feature subset as the input data for each decision tree can increase the diversity of the model and prevent overfitting. The t-th decision tree is trained using the feature subset to generate a prediction result. Each decision tree is trained independently, and the prediction results of all decision trees are integrated to finally obtain the energy consumption ratio prediction formula through weighted average.

[0043] Furthermore, the mathematical formula of the energy consumption ratio prediction model is:

[0044]

[0045] In the formula, represents the real-time energy consumption ratio prediction value, T represents the number of decision trees, α t represents the weight coefficient of the t-th decision tree, t represents the number of the decision tree, t=1,2,3,...,T, f t represents the prediction function of the t-th decision tree, ω i represents the weight coefficient of feature i, i represents the feature number, i = 1, 2, 3, 4, x i represents the standardized eigenvalue of the ith real-time acquisition, μ i Represents feature x i The mean value, σ i Represents feature x i The standard deviation of .

[0046] In this embodiment, It is also possible to update online by using the model trained with historical data and predicting based on the latest real-time data to obtain the real-time energy consumption ratio prediction value; T can be obtained through historical data; α t Expert advice can be obtained; t Multiple decision trees can be trained by the random forest algorithm. Each tree is trained independently and the prediction function of the decision tree is constructed using historical data. Ensemble learning methods, such as bagging, can also be used to construct multiple decision trees using different subsets of historical data and train them separately to obtain their own prediction functions. i The contribution of features to the target variable can be calculated by linear regression method, and feature weights can be calculated and assigned; x i The data can be collected by real-time sensors and standardized, or the real-time collected data can be standardized by the statistical information (mean and standard deviation) of historical data; μ i It can be obtained by calculating the mean of each feature through historical data, or by calculating the mean of the collected historical data; σ i It can be obtained by calculating the standard deviation of each feature using historical data, or by calculating the standard deviation of the collected historical data;

[0047] Furthermore, the specific steps of adjusting the operating parameters of the drying system according to the prediction results include: inputting the pre-processed real-time data into the trained energy consumption ratio prediction model to calculate the real-time energy consumption ratio prediction value; obtaining the actual energy consumption ratio by calculating the actual energy consumption and the amount of sludge treated; calculating the deviation between the actual energy consumption ratio and the predicted energy consumption ratio; and dynamically adjusting the operating parameters according to the deviation to obtain the optimized energy consumption ratio prediction model formula.

[0048] In this embodiment, the pre-processed real-time data is input into the trained energy consumption ratio prediction model to calculate the real-time energy consumption ratio prediction value. This step utilizes the previously trained model to predict the energy consumption ratio at the current moment by inputting the operating data of the current system. This real-time prediction function is based on the application of big data and machine learning technology, so that the system can be adjusted in time according to the current state. The actual energy consumption ratio is obtained by calculating the actual energy consumption and the amount of sludge treated. Real-time energy consumption data and the amount of sludge treated are collected in real time through sensors and metering devices. The calculation of the actual energy consumption ratio provides a comparison benchmark for the prediction model to ensure that the system can be adjusted according to actual conditions. Calculate the deviation between the actual energy consumption ratio and the predicted energy consumption ratio. This step is to evaluate the accuracy of the prediction model and guide subsequent parameter adjustments through the deviation value. The calculation formula for the deviation value is: Among them, Δy represents the deviation, y a is the actual energy consumption ratio, is the predicted value of the real-time energy consumption ratio. By calculating the deviation, the difference between the prediction model and the actual situation can be identified, thus providing a basis for parameter adjustment. The operating parameters are adjusted dynamically according to the deviation. The goal of adjusting the operating parameters is to make the actual energy consumption ratio of the system as close to the predicted value as possible, thereby achieving energy consumption optimization. The specific adjustment rules can be based on proportional control (P control) or other control algorithms. The adjusted operating parameters are recorded as θ0. The adjusted parameters are transmitted to each actuator through the control system to adjust the operating status of the system in real time.

[0049] Furthermore, the optimized energy consumption ratio prediction model formula is:

[0050]

[0051] In the formula, represents the optimized real-time energy consumption ratio prediction value, f represents the function of energy consumption ratio, which depends on the adjusted parameter θ0 and real-time characteristic data x, θ0 represents the adjusted operating parameter, k p Represents the proportional control coefficient, E a represents the actual energy consumption, M represents the amount of sludge treated, T represents the number of decision trees, t represents the number of decision trees, t=1,2,3,...,T,α t Represents the weight coefficient of each decision tree, f t represents the prediction function of the t-th decision tree, ω i represents the weight coefficient of feature i, i represents the feature number, i = 1, 2, 3, 4, x i represents the standardized eigenvalue of the ith real-time acquisition, μ i Represents feature x i The mean value, σ i Represents feature x i The standard deviation of .

[0052] In this embodiment, It can also be obtained by adjusting parameters in real time through feedback control systems; f can be obtained through historical data learning, or by manually defining or adjusting the energy consumption ratio function using historical data and expert experience; θ0 can be obtained by dynamically adjusting the deviation between the actual energy consumption ratio and the predicted energy consumption ratio through control algorithms (such as PID control, fuzzy control), or by optimizing parameters in offline mode using optimization algorithms (such as genetic algorithms, particle swarm optimization); k p The optimal proportional control coefficient can be obtained by determining the optimal proportional control coefficient through the parameter tuning process of the control system (such as the Ziegler-Nichols tuning method), or by manually adjusting and optimizing the proportional control coefficient through experiments and historical operation data analysis; E a The energy consumption data of the sludge drying system can be obtained by measuring the energy consumption of the sludge drying system in real time through the energy consumption metering device, and can also be estimated through historical energy consumption data and statistical analysis; M can be obtained by measuring the amount of sludge treated in real time through the sludge treatment metering equipment, and can also be estimated through historical treatment data and operation records. As shown in Table 1, the predicted value of the real-time energy consumption ratio after optimization:

[0053] Table 1 Prediction of real-time energy consumption ratio after optimization

[0054]

[0055]

[0056] like Figure 2 The optimized real-time energy consumption ratio prediction diagram is shown in the figure, where the number of decision trees T is 100 and the weight coefficient α of each decision tree is t is 0.01, feature x i The standard deviation σ i is 0.0707, feature x i The mean μ i is 1.2. As can be seen from the table and the image, the predicted value of the energy consumption ratio after optimization fluctuates between different serial numbers, ranging from 0.81 to 0.90. Overall, these values ​​are relatively close, indicating that the energy efficiency of the optimization model is relatively stable under different conditions. The predicted value of the energy consumption ratio after optimization is affected by multiple factors, including the adjusted operating parameters, actual energy consumption, the amount of sludge treated, and the proportional control coefficient.

[0057] Through the analysis of charts and images, it can be concluded that the predicted value of the optimized energy consumption ratio increases with the increase of the adjusted operating parameters, the amount of sludge treated and the proportional control coefficient, and decreases with the increase of the actual energy consumption. The adjusted operating parameter values ​​can comprehensively reflect the operating status and optimization effect of the system. Through real-time prediction and dynamic adjustment, the system can continuously optimize and adjust during operation, improve energy efficiency, reduce energy consumption, and realize intelligent and efficient management of the sludge drying system.

[0058] Furthermore, the specific steps of visualizing the optimized energy consumption ratio prediction model data and generating a report include: displaying the real-time temperature, humidity, wind speed, and energy consumption of the sludge drying system through a data visualization tool; displaying the energy consumption ratio analysis results under different time periods and different operating parameters through a user interface; and automatically generating an energy consumption ratio optimization report based on the energy consumption ratio analysis results.

[0059] In this embodiment, the real-time temperature, humidity, wind speed, energy consumption and other key parameters of the sludge drying system are displayed by a data visualization tool (such as Tableau). These data are collected in real time by sensors and transmitted to the data center for processing and storage through wireless transmission technology. Through the user interface, the operator can monitor the operating status of the system in real time and promptly discover and deal with potential problems. Data visualization technology can convert complex data into intuitive charts and dashboards, making data analysis easier and more efficient. The user interface displays historical data and trend analysis results. The display of historical data can help managers understand the long-term operation of the system and the trend of energy consumption changes. By comparing and analyzing the changes in energy consumption ratios under different time periods and different operating parameters, the key factors affecting the energy consumption ratio can be identified, and a scientific basis can be provided for system optimization. The trend analysis results can reveal the laws and abnormal changes of system operation and help managers formulate reasonable operation strategies. By displaying the comparative analysis results of energy consumption ratios under different time periods and different operating parameters, the automatic generation of energy consumption ratio optimization reports can assist managers in analyzing the energy consumption ratio situation.

[0060] These energy consumption ratio optimization reports include not only comparative analysis of energy consumption ratios, but also analysis of the impact of key parameters on energy consumption ratios, including adjusted operating parameters, proportional control coefficients, actual energy consumption, sludge volume treated, characteristic weight coefficients, and standardized characteristic values ​​collected in real time. By comparing and analyzing the results, managers can identify which parameters have a significant impact on the energy consumption ratio and take corresponding optimization measures.

[0061] Furthermore, the specific steps for automated control and fault diagnosis of the sludge drying system include: obtaining execution control commands; executing control commands through PLC automation equipment and adjusting the system operation status in real time; using big data analysis technology to monitor the system operation status in real time and detect potential faults; if an abnormal situation is detected, identifying the cause and influencing factors of the fault data and issuing an early warning signal to notify maintenance personnel to inspect and handle it.

[0062] In this embodiment, various operating parameters of the sludge drying system are monitored in real time through sensors and data acquisition systems, and the data is transmitted to the data center for analysis. Big data analysis technology can mine potential fault signals from massive data and promptly detect abnormal conditions in the system. By comparing and analyzing historical data and real-time data, possible faults can be predicted in advance and preventive maintenance can be performed. If an abnormality is detected, the cause and influencing factors of the fault data are identified and an early warning signal is issued to notify maintenance personnel to inspect and handle the situation. Through real-time monitoring and big data analysis, abnormal conditions in the system are promptly detected, fault diagnosis and analysis are performed, and the cause and influencing factors of the fault are identified. The system will issue an early warning signal to notify maintenance personnel to inspect and handle the situation.

[0063] To sum up: the energy consumption ratio optimization method of the sludge drying system based on big data in this embodiment, by applying the principal component analysis method to reduce the dimension of the preprocessed data set and the random forest algorithm to train the key characteristic parameters, an energy consumption ratio prediction model is established, thereby achieving accurate prediction and real-time optimization of the energy consumption ratio, and further realizing the intelligent management of the sludge drying system.

[0064] By applying big data analysis and random forest algorithm, accurate prediction and real-time optimization of energy consumption ratio are achieved, thereby optimizing the energy consumption ratio of the sludge drying system, effectively solving the problem of low energy consumption ratio of the sludge drying system in the existing technology.

[0065] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0066] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0067] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0068] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0069] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0070] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for optimizing energy consumption ratio of sludge drying system based on big data, characterized in that: The following steps are involved: Collect the operation data of the sludge drying system through sensors; Preprocess the collected operating data to obtain stable sequence data and generate high-quality data sets; Extract key feature parameters from the preprocessed high-quality data set; The key characteristic parameters are trained using the random forest algorithm to establish an energy consumption ratio prediction model; The energy consumption ratio in the drying process is predicted in real time according to the energy consumption ratio prediction model, and the operating parameters of the drying system are adjusted according to the prediction results to obtain an optimized energy consumption ratio prediction model; Visualize the optimized energy consumption ratio prediction model data and generate reports; Automatically control and diagnose faults in sludge drying systems; The steps of establishing the energy consumption ratio prediction model are: Standardize input feature data to eliminate dimension effects; Introduce feature weights and combine feature data for weighted combination; Use the random forest algorithm to build multiple decision trees for integrated prediction; Randomly select a subset of features as input data for each decision tree; Use the feature subset to train the decision tree and generate prediction results; Integrate the prediction results of all decision trees and obtain the energy consumption ratio prediction model by weighted average; The mathematical formula of the energy consumption ratio prediction model is: In the formula, represents the real-time energy consumption ratio prediction value, T represents the number of decision trees, α t represents the weight coefficient of the t-th decision tree, t represents the number of the decision tree, t=1,2,3,...,T, f t represents the prediction function of the t-th decision tree, ω i represents the weight coefficient of feature i, i represents the feature number, i = 1, 2, 3, 4, x i represents the standardized eigenvalue of the ith real-time acquisition, μ i Represents feature x i The mean value, σ i Represents feature x i The standard deviation of The specific steps of adjusting the operating parameters of the drying system according to the prediction results include: The preprocessed real-time data is input into the trained energy consumption ratio prediction model to calculate the real-time energy consumption ratio prediction value; The actual energy consumption ratio is obtained by calculating the actual energy consumption and the amount of sludge treated; Calculate the deviation between the actual energy consumption ratio and the predicted energy consumption ratio; Dynamically adjust the operating parameters according to the deviation to obtain the optimized energy consumption ratio prediction model formula; The optimized energy consumption ratio prediction model formula is: In the formula, represents the optimized real-time energy consumption ratio prediction value, f represents the function of energy consumption ratio, which depends on the adjusted parameter θ0 and real-time characteristic data x, θ0 represents the adjusted operating parameter, k p Represents the proportional control coefficient, E a represents the actual energy consumption, M represents the amount of sludge treated, T represents the number of decision trees, t represents the number of decision trees, t=1,2,3,...,T,α t represents the weight coefficient of the tth decision tree, f t represents the prediction function of the t-th decision tree, ω i represents the weight coefficient of feature i, i represents the feature number, i = 1, 2, 3, 4, x i represents the standardized eigenvalue of the ith real-time acquisition, μ i Represents feature x i The mean value, σ i Represents feature x i The standard deviation of .

2. The method for optimizing the energy consumption ratio of a sludge drying system based on big data as claimed in claim 1, characterized in that: The specific steps of collecting the operation data of the sludge drying system include: The temperature, humidity, wind speed and energy consumption data of the sludge drying system are collected in real time through temperature sensors, humidity sensors, wind speed sensors and energy consumption metering devices; The data synchronization technology is used to integrate the real-time collected temperature, humidity, wind speed, and energy consumption data of the sludge drying system to obtain a complete operating data set; The complete operational data set is transferred to the database in real time and stored.

3. The method for optimizing the energy consumption ratio of a sludge drying system based on big data as claimed in claim 1, characterized in that: The specific steps of the pretreatment are: Use the Z-score in statistical analysis to detect and remove outliers in the data; The mean filtering technique is used to smooth the data; Conduct correlation analysis on the collected parameters; Calculate the impact of each data item in the high-quality data set on the energy consumption ratio; Sort by impact, giving priority to data with greater impact; Perform Z-score normalization on each data item in the high-quality data set; Obtain data distribution characteristics; Perform data transformation according to data distribution characteristics; Exponential smoothing method is used to remove the trend component of the data and obtain stable sequence data.

4. The method for optimizing the energy consumption ratio of a sludge drying system based on big data as claimed in claim 1, characterized in that: The specific steps of extracting key feature parameters from the preprocessed high-quality data set are: Extracting an initial feature parameter set from the preprocessed data set, wherein the initial feature parameter set includes temperature, humidity, wind speed, and energy consumption; The PCA method is used to reduce the dimension of the initial feature parameters, convert high-dimensional data into low-dimensional data, and extract the features that mainly affect the energy consumption ratio; The correlation between each characteristic parameter and the energy consumption ratio was calculated using the Pearson correlation coefficient; The contribution of each characteristic parameter to the energy consumption ratio is evaluated by the multivariate linear regression method; The cross-validation method is used to compare the performance indicators of the model under different feature combinations and select the feature combination scheme with the best performance indicators to obtain the key feature parameters.

5. The method for optimizing the energy consumption ratio of a sludge drying system based on big data as claimed in claim 1, characterized in that: The specific steps of visualizing the optimized energy consumption ratio prediction model data and generating a report include: Use data visualization tools to display the real-time temperature, humidity, wind speed, and energy consumption of the sludge drying system; The energy consumption ratio analysis results under different time periods and different operating parameters are displayed through the user interface; Automatically generate energy consumption ratio optimization report based on energy consumption ratio analysis results.

6. The method for optimizing the energy consumption ratio of a sludge drying system based on big data as claimed in claim 1, characterized in that: The specific steps of automatic control and fault diagnosis of the sludge drying system include: Get execution control commands; Execute control commands through PLC automation equipment to adjust the system operation status in real time; Use big data analysis technology to monitor system operation status in real time and detect potential faults; If an abnormal situation is detected, the fault cause and influencing factors are identified from the fault data and an early warning signal is issued to notify maintenance personnel to check and handle the situation.

Images