Intelligent control method and system for boiler wastewater treatment

Abstract

The present application relates to the technical field of electric digital data processing, in particular to an intelligent control method and system for boiler wastewater treatment, comprising: obtaining a fluctuation degree of a boiler wastewater device at a current time node, the fluctuation degree being positively correlated with an abnormality degree of the boiler wastewater device at the current time node and negatively correlated with a dynamic lag time of the boiler wastewater device at the current time node; inputting the fluctuation degree into an improved machine learning model, inputting an operating state of the boiler wastewater device at the current time node, and controlling start and stop of the boiler wastewater device based on the operating state. The present application solves the problem of low prediction accuracy of existing machine learning models.

Description

Technical Field

[0001] This invention relates to the field of electronic digital data processing technology. More specifically, this invention relates to an intelligent control method and system for boiler wastewater treatment. Background Technology

[0002] Wastewater generation is inevitable during the operation of industrial boiler systems. Its quality and quantity are influenced by various factors, including boiler operating load, fuel properties, heat transfer efficiency, and makeup water volume. Boiler wastewater typically contains high temperature, high pressure, high hardness, and various impurities, particles, and chemicals. Improper treatment can easily lead to equipment corrosion, scaling, and excessive pollution emissions, thereby affecting the stable operation of the entire thermal system and the achievement of environmental protection targets. To improve the efficiency and intelligence of boiler wastewater treatment, more and more companies are introducing advanced data-driven methods and intelligent control systems into the wastewater treatment process to achieve real-time monitoring and automatic adjustment of wastewater quality, discharge volume, and operating status.

[0003] In recent years, with the continuous development of sensor, data acquisition, and edge computing technologies, the dimensions of wastewater treatment-related data obtainable in industrial sites have become increasingly rich, including various parameters such as flow rate, pressure, temperature, chemical composition concentration, conductivity, and inlet / outlet pressure difference, forming a typical time series structure. Based on this, researchers have widely introduced machine learning models, especially deep learning-based neural network models, attempting to train high-precision predictive models using historical operating data. These models can be used to identify potential abnormal behaviors in wastewater systems in advance, thereby providing feedforward decision support for the control system.

[0004] However, existing machine learning models still have many limitations in practical applications, especially in terms of prediction accuracy and generalization ability, which are insufficient to meet the high requirements of typical complex operating conditions such as boiler wastewater treatment. First, many models focus on fitting single or static features during their design, lacking sufficient modeling of the dynamic response process, hysteresis characteristics, and nonlinear fluctuation behavior of the equipment. This leads to significant deviations in prediction results when facing industrial environments with severe fluctuations or frequent anomalies. Second, most models fail to effectively incorporate dynamic evaluation mechanisms related to operating conditions in their loss function design, failing to identify the evolution of certain seemingly normal but actually abnormal key features. This results in insufficient predictive ability in the early stages of abnormal states, potentially leading to missed detections or misjudgments, and consequently, low prediction accuracy. Summary of the Invention

[0005] To address the problem of low prediction accuracy mentioned in the background art, the present invention provides solutions in the following aspects.

[0006] In a first aspect, the present invention provides an intelligent control method for boiler wastewater treatment, comprising: acquiring the fluctuation level of a boiler wastewater treatment device at a current time point, wherein the fluctuation level is positively correlated with the anomaly level of the boiler wastewater treatment device at the current time point and negatively correlated with the dynamic lag time of the boiler wastewater treatment device at the current time point; inputting the fluctuation level into an improved machine learning model, inputting the operating state of the boiler wastewater treatment device at the current time point, and controlling the start and stop of the boiler wastewater treatment device based on the operating state; wherein the improved machine learning model includes a loss function, wherein the loss function is positively correlated with the difference between the fluctuation level at the current time point and the mean of the fluctuation levels at multiple historical set time points, and negatively correlated with the standard deviation of the fluctuation levels at multiple historical set time points.

[0007] The aforementioned technical solution uses the fluctuation level, formed by combining the current anomaly level of the equipment with its dynamic lag time, as the core input. It then employs an improved machine learning model combined with the current operating state to control the equipment's start-up and shutdown. Furthermore, during model training, a loss function is designed based on the deviation of the fluctuation level from the historical average level and the historical fluctuation amplitude, thereby enhancing the model's sensitivity to abnormal fluctuations and suppressing interference from normal fluctuations. This construction logic effectively integrates the dynamic characteristics and historical behavior patterns of equipment operation, enabling the control system to more accurately identify and respond to abnormal states, thus improving operational stability and control precision.

[0008] Furthermore, the degree of fluctuation for: , For boiler wastewater equipment The degree of abnormality at each time point, For boiler wastewater equipment The dynamic lag time of a time node For the natural constant An exponential function with base 0.

[0009] The above technical solution combines an index representing the degree of anomaly with a lag time factor reflecting the system's response speed, and uses an exponential decay function to dynamically modulate the degree of anomaly. This makes the fluctuation more significant when the response lag is small, and automatically weakens the impact of fluctuation when the response lag is large, thereby enhancing the real abnormal signal and suppressing delayed noise.

[0010] Furthermore, the degree of abnormality for: , For boiler wastewater equipment Inlet and outlet pressure difference at a given time point This is the reference pressure difference under normal operating conditions for boiler wastewater equipment.

[0011] The above technical solution constructs an abnormal indicator that can dynamically reflect the degree of deviation of the equipment from the normal state by processing the ratio difference between the current inlet and outlet pressure difference of the equipment and the reference pressure difference under normal operating conditions, thereby quantifying the degree of abnormality of the current operating state of the equipment.

[0012] Furthermore, the dynamic lag time for: , The lag time of the boiler wastewater equipment in standby mode. The lag time of the boiler wastewater equipment under full load. For boiler wastewater equipment Wastewater flow rate at specific time points The maximum wastewater flow rate that the boiler wastewater equipment can handle. To set the size of the time window, This is the normalization function.

[0013] The above technical solution combines the wastewater flow rate changes within a set time window with the equipment's carrying capacity and normalizes them to construct a lag time index that can dynamically change with the load state. This results in a faster response and a shorter lag time when the equipment load is higher, thus more realistically reflecting the system's response characteristics under different operating conditions.

[0014] Furthermore, the loss function for: , For boiler wastewater equipment The degree of fluctuation at each point in time, This represents the average fluctuation of the boiler wastewater treatment equipment over multiple historical time points. The standard deviation of the fluctuation of boiler wastewater equipment at multiple historical time points. Set the number of time points for multiple historical events.

[0015] The aforementioned technical solution constructs a loss function centered on the deviation between the fluctuation level and the historical average, and normalizes it by incorporating the standard deviation of historical fluctuations. This allows the model to focus more on states that exhibit significant anomalies relative to historical behavior during training, thereby enhancing its sensitivity to unstable operating conditions. This construction logic strengthens the model's ability to identify abnormal fluctuations in equipment operation, effectively avoiding misjudgments caused by the inherently large or small historical fluctuations, and improving the robustness and generalization ability of anomaly detection.

[0016] Furthermore, when hour, ;when hour, .

[0017] The aforementioned technical solution, by employing the absolute value of the difference, uniformly measures the deviation magnitude regardless of whether the current fluctuation level is higher or lower than the historical average. This avoids the problem of error cancellation in the positive and negative directions, ensuring that the loss function gives equal attention to all abnormal fluctuations during training. This approach enhances the model's comprehensive perception of fluctuation trends, enabling accurate identification of abnormal states, whether excessively high or low, thereby strengthening the model's adaptability and robustness to the complex dynamic behavior of boiler wastewater systems.

[0018] Furthermore, the machine learning model is a long short-term memory neural network model.

[0019] Furthermore, the operating status is divided into normal and abnormal.

[0020] Furthermore, it also includes training the machine learning model, specifically: inputting the training set into the pre-built machine learning model for training; during the training process, calculating the loss between the output predicted value and the label; adjusting the model parameters using gradient descent to minimize the prediction error; iteratively adjusting the parameters of the machine learning model until the loss is less than a set value or the set number of training iterations is reached, and finally obtaining the trained machine learning model.

[0021] In a second aspect, the present invention provides an intelligent control system for boiler wastewater treatment, comprising a memory and a processor, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the intelligent control method for boiler wastewater treatment described in any of the above claims is implemented.

[0022] The beneficial effects of this invention are as follows:

[0023] This invention constructs a dynamic fluctuation index by combining the abnormal amplitude of equipment with the response lag characteristics, and uses it as the core input of a machine learning model. At the same time, the model training emphasizes the degree of deviation from the historical normal fluctuation range, enabling the system to identify operational anomalies in real time and accurately and automatically trigger start-stop control. This ensures high sensitivity to sudden anomalies while suppressing misjudgments caused by normal fluctuations, effectively improving the stability, response speed and robustness of the boiler wastewater treatment process. Attached Figure Description

[0024] Figure 1 This is a schematic flowchart illustrating an intelligent control method for boiler wastewater treatment according to an embodiment of the present invention;

[0025] Figure 2 This is a schematic block diagram illustrating the structure of an intelligent control system for boiler wastewater treatment according to an embodiment of the present invention. Detailed Implementation

[0026] An embodiment of an intelligent control method for boiler wastewater treatment.

[0027] like Figure 1 As shown in the flowchart, an embodiment of the present invention provides a method for intelligent control of boiler wastewater treatment, comprising the following steps:

[0028] S1: Obtain the fluctuation level of the boiler wastewater equipment at the current time point.

[0029] In one embodiment, the degree of fluctuation for: , For boiler wastewater equipment The degree of abnormality at each time point, For boiler wastewater equipment The dynamic lag time of a time node For the natural constant An exponential function with base 0.

[0030] By combining the degree of equipment anomaly with dynamic lag time and using an exponential function to attenuate the degree of anomaly, the impact of the anomaly gradually weakens as the lag time increases, reflecting the timeliness and actual dynamic characteristics of the system response. This design highlights the importance of immediate anomalies while effectively suppressing misjudgments caused by lag, improving the accuracy of anomaly detection and the response efficiency of control strategies.

[0031] In one embodiment, the degree of abnormality for: , For boiler wastewater equipment Inlet and outlet pressure difference at a given time point This is the reference pressure difference under normal operating conditions for boiler wastewater equipment.

[0032] By comparing the current inlet and outlet pressure difference of the equipment with the reference pressure difference under normal operating conditions, the relative difference between the two is calculated to quantify the degree of anomaly, thereby accurately reflecting deviations in the equipment's operating status. This construction logic, based on the direct measurement of physical quantities, can sensitively capture problems such as blockages or flow anomalies caused by pressure difference changes, improving the accuracy and real-time performance of anomaly detection and providing a reliable foundation for subsequent intelligent control.

[0033] In one embodiment, the dynamic lag time for: , The lag time of the boiler wastewater equipment in standby mode. The lag time of the boiler wastewater equipment under full load. For boiler wastewater equipment Wastewater flow rate at specific time points The maximum wastewater flow rate that the boiler wastewater equipment can handle. To set the size of the time window, This is the normalization function.

[0034] By normalizing the wastewater flow rate of the equipment within a set time window with its maximum carrying capacity, the lag time index is dynamically adjusted. This results in the equipment exhibiting a longer response lag when the load is low, while the lag time is shortened when the load is close to full load. This truly reflects the impact of the equipment's operating status on the response speed and improves the adaptability and response efficiency of the control strategy under different load conditions.

[0035] S2: Input the fluctuation level into the improved machine learning model, and input the operating status of the boiler wastewater equipment at the current time node.

[0036] In one embodiment, the improved machine learning model includes a loss function, the loss function for: , For boiler wastewater equipment The degree of fluctuation at each point in time, This represents the average fluctuation of the boiler wastewater treatment equipment over multiple historical time points. The standard deviation of the fluctuation of boiler wastewater equipment at multiple historical time points. Set the number of time points for multiple historical events.

[0037] By designing a normalized squared loss function based on the deviation of the fluctuation degree from its historical mean, the model pays more attention to abnormal states that significantly deviate from the historical normal fluctuation range during the training process. This improves the sensitivity and identification accuracy of abnormal equipment fluctuations, enhances the robustness and generalization ability of the model, and promotes the precise monitoring and intelligent control of the operating status of boiler wastewater equipment.

[0038] when hour, ;when hour, By processing the absolute value of the difference between the volatility level and the historical average, it is ensured that whether the volatility is higher or lower than the historical average level, it can be fairly quantified and included in the loss calculation. This avoids the calculation bias caused by the sign of the deviation, improves the comprehensive identification ability of abnormal volatility, and enhances the model's sensitivity and stability to various abnormal states.

[0039] The machine learning model is a long short-term memory neural network model. Training the machine learning model using the long short-term memory neural network model involves: inputting a training set into a pre-built machine learning model for training; the training set including multi-dimensional features such as historically collected fluctuations, anomalies, and lag times; calculating the loss between the output predicted value and the label (which is manually set); adjusting the model parameters using gradient descent to minimize the prediction error; iteratively adjusting the machine learning model parameters until the loss is less than a set value or a set number of training iterations is reached, ultimately obtaining a well-trained machine learning model.

[0040] S3: Control the start and stop of the boiler wastewater equipment based on the operating status.

[0041] In one embodiment, the operating status is divided into two categories: normal and abnormal. A normal status indicates that the equipment is in a stable operating state that meets the operating requirements and requires no intervention. An abnormal status, on the other hand, indicates that the current equipment operation has significantly deviated from the normal parameter range, posing a potential fault or system risk. In this case, the system will automatically trigger start-stop control commands based on the judgment result, promptly shutting down, performing maintenance, or adjusting operating parameters to prevent the spread of faults and excessive system emissions, thus ensuring the safety and stability of the boiler wastewater treatment system. The above control logic, based on model judgment results and combined with the dynamic characteristics of the equipment, achieves precise decision-making and rapid response for start-stop operations.

[0042] This invention constructs a fluctuation index that integrates anomaly degree and dynamic lag characteristics, introduces an improved machine learning model to intelligently judge the operating status of equipment, and thereby achieves dynamic control of the start-up and shutdown of boiler wastewater treatment equipment. Furthermore, by designing a loss function associated with historical fluctuation characteristics, the model is guided to focus on identifying abnormal fluctuations, thus improving the model's learning accuracy and generalization ability. This solution comprehensively considers the system's operational dynamism, real-time performance, and historical behavior patterns, possessing strong robustness and adaptability. It can effectively achieve intelligent monitoring and precise control of the boiler wastewater treatment process, reducing failure risks and improving operational efficiency and system safety.

[0043] An embodiment of an intelligent control system for boiler wastewater treatment:

[0044] like Figure 2 As shown in the figure, a structural block diagram of an intelligent control system for boiler wastewater treatment according to an embodiment of the present invention includes a processor and a memory.

[0045] This invention also provides an intelligent control system for boiler wastewater treatment. For example... Figure 2As shown, the system includes a processor and a memory. The memory stores computer program instructions, which, when executed by the processor, implement an intelligent control method for boiler wastewater treatment according to the present invention.

[0046] The intelligent control system for boiler wastewater treatment also includes other components well known to those skilled in the art, such as communication interfaces. Their settings and functions are known in the art and will not be described in detail here.

[0047] In this invention, the aforementioned memory can be any tangible medium containing or storing a program that can be used or combined with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium can be any suitable magnetic or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc., or any other medium that can be used to store desired information and can be accessed by an application, module, or both. Any such computer storage medium can be part of a device or accessible to or connected to a device. Any application or module described in this invention can be implemented by computer-readable / executable instructions stored or otherwise maintained on such a computer-readable medium.

[0048] In the description of this specification, "multiple" or "several" means at least two, such as two, three or more, unless otherwise explicitly specified.

[0049] While this specification has shown and described numerous embodiments of the invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Many modifications, alterations, and alternatives will occur to those skilled in the art without departing from the spirit and essence of the invention. It should be understood that various alternatives to the embodiments of the invention described herein may be employed in the practice of this invention.

Claims

1. An intelligent control method for boiler wastewater treatment, characterized in that, include: The fluctuation level of the boiler wastewater equipment at the current time point is obtained. The fluctuation level is positively correlated with the abnormality level of the boiler wastewater equipment at the current time point and negatively correlated with the dynamic lag time of the boiler wastewater equipment at the current time point. The dynamic lag time for: , The lag time of the boiler wastewater equipment in standby mode. The lag time of the boiler wastewater equipment under full load. For boiler wastewater equipment Wastewater flow rate at specific time points The maximum wastewater flow rate that the boiler wastewater equipment can handle. To set the size of the time window, This is the normalization function; The fluctuation level is input into the improved machine learning model, and the operating status of the boiler wastewater equipment at the current time point is input. The start and stop of the boiler wastewater equipment are controlled based on the operating status. The improved machine learning model includes a loss function that is positively correlated with the difference between the fluctuation level at the current time point and the mean of the fluctuation levels at multiple historical time points, and negatively correlated with the standard deviation of the fluctuation levels at multiple historical time points.

2. The intelligent control method for boiler wastewater treatment according to claim 1, characterized in that, The degree of fluctuation for: , For boiler wastewater equipment The degree of abnormality at each time point, For boiler wastewater equipment The dynamic lag time of a time node For the natural constant An exponential function with base 0.

3. The intelligent control method for boiler wastewater treatment according to claim 1, characterized in that, The degree of abnormality for: , For boiler wastewater equipment Inlet and outlet pressure difference at a given time point This is the reference pressure difference under normal operating conditions for boiler wastewater equipment.

4. The intelligent control method for boiler wastewater treatment according to claim 1, characterized in that, The loss function for: , For boiler wastewater equipment The degree of fluctuation at each point in time, This represents the average fluctuation of the boiler wastewater treatment equipment over multiple historical time points. The standard deviation of the fluctuation of boiler wastewater equipment at multiple historical time points. Set the number of time points for multiple historical events.

5. The intelligent control method for boiler wastewater treatment according to claim 4, characterized in that, when hour, ;when hour, .

6. The intelligent control method for boiler wastewater treatment according to claim 1, characterized in that, The machine learning model is a long short-term memory neural network model.

7. The intelligent control method for boiler wastewater treatment according to claim 1, characterized in that, The operating status is divided into normal and abnormal.

8. The intelligent control method for boiler wastewater treatment according to claim 1, characterized in that, This also includes training machine learning models, specifically: The training set is input into a pre-built machine learning model for training. During training, the loss between the output prediction value and the label is calculated; the model parameters are adjusted using gradient descent to minimize the prediction error; the parameters of the machine learning model are iteratively adjusted until the loss is less than a set value or the set number of training iterations is reached, and finally a trained machine learning model is obtained.

9. An intelligent control system for boiler wastewater treatment, characterized in that, It includes a memory and a processor, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the intelligent control method for boiler wastewater treatment as described in any one of claims 1 to 8 is implemented.

Images