Digital management method and system for preventing environmental protection parameters of coal-fired power plant from exceeding standard

Abstract

The invention discloses a digital management method and system for preventing environmental protection parameters of a coal-fired power plant from exceeding standards, and relates to the technical field of power plant management, and the method comprises the steps: transmitting the environmental parameters to a central data management region through a wireless transmission technology, and carrying out the preprocessing of the environmental parameters based on the central data management region; dynamic simulation learning is carried out by using a neural network of a digital twin model, and the exceeding condition of the environmental protection parameters is predicted; and digital management of environmental protection parameter exceeding is completed through an evaluation feedback mechanism. Real-time monitoring, prediction and dynamic optimization of the environmental protection parameters of the coal-fired power plant are achieved, noise data can be effectively filtered, the environmental protection parameter standard exceeding condition can be accurately predicted, the precision and efficiency of environmental protection parameter management are remarkably improved, compared with the prior art, environmental changes can be rapidly responded, environmental protection parameter standard exceeding is avoided, and the method is suitable for popularization and application. And environment-friendly standard operation of a coal-fired power plant is ensured, and remarkable economic and environmental benefits are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of power plant management, and in particular to a digital management method and system for preventing environmental protection parameters of a coal-fired power plant from exceeding standards. Background Art

[0002] At present, with the continuous enhancement of global environmental awareness, coal-fired power plants, as one of the important energy supply methods, are facing increasingly stringent environmental regulations and emission standards. All sectors of society have put forward higher requirements for reducing the emission of harmful substances generated in the coal-burning process, especially in terms of carbon emissions, flue gas treatment and wastewater and waste residue control. In order to meet these challenges, an advanced digital management method is urgently needed to monitor and control environmental parameters in real time, ensure that the operation of coal-fired power plants meets environmental standards, and reduce negative impacts on the environment.

[0003] At present, the traditional environmental parameter monitoring of coal-fired power plants mainly relies on manual detection and experience judgment, which has problems such as poor real-time performance, slow response speed and inaccurate data processing. It is difficult to effectively cope with the fluctuations of environmental parameters in the complex and changeable coal-fired process. In addition, the existing technology lacks an accurate prediction and optimization mechanism for the exceeding of environmental parameters, which leads to the lag of environmental protection measures and easily causes the exceeding of environmental parameters. The present invention introduces digital twin models and neural network dynamic simulation learning technology to realize real-time monitoring and secondary optimization of environmental parameters, thereby effectively solving the defects in the existing technology and improving the environmental management level of coal-fired power plants. Summary of the invention

[0004] In view of the problems existing in the existing digital management method and system for preventing environmental protection parameters from exceeding standards in existing coal-fired power plants, the present invention is proposed.

[0005] Therefore, the purpose of the present invention is to provide a digital management method and system for preventing environmental protection parameters from exceeding standards in coal-fired power plants. In view of the defects of the prior art in environmental protection parameter monitoring, such as poor real-time performance and lack of effective prediction, the present invention adopts a digital twin model and neural network dynamic simulation learning technology to solve the problems.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides a digital management method for preventing environmental parameters from exceeding standards in a coal-fired power plant, which includes arranging a sensor network based on environmental monitoring points in the coal-fired power plant, the sensor network collecting environmental parameters generated during the coal combustion process through an intelligent data collection model, transmitting the environmental parameters to a central data management area through wireless transmission technology, and preprocessing the environmental parameters based on the central data management area;

[0008] Establishing a digital twin model of a coal-fired power plant, using the neural network of the digital twin model to perform dynamic simulation learning, and predicting the exceeding of environmental protection parameters;

[0009] The digital management system of environmental protection parameters is used to analyze the exceeding of standards, and the operating parameters of the coal-fired power plant are optimized based on the analysis results. The digital management of the exceeding of environmental protection parameters is completed through the evaluation and feedback mechanism.

[0010] As a preferred solution of the digital management method for preventing environmental protection parameters from exceeding the standard in the coal-fired power plant of the present invention, the intelligent data acquisition model includes a gas sensor, a liquid sensor and a solid sensor according to a sensor network, and monitors the flue gas, wastewater and waste residue of the coal-fired power plant based on the gas sensor, the liquid sensor and the solid sensor;

[0011] The collection of environmental parameters generated during the coal combustion process includes filtering flue gas, waste water and waste residue, and the filtering includes denoising, correcting and normalizing the flue gas, waste water and waste residue, and the normalized data is used as the environmental parameters generated during the coal combustion process.

[0012] As a preferred solution of the digital management method for preventing environmental protection parameters from exceeding the standard in the coal-fired power plant of the present invention, the denoising includes using a moving average method to reduce noise interference in the process of sensor monitoring the coal-fired power plant, and the calculation formula of the moving average method is:

[0013]

[0014] in, represents the environmental parameters of the ith sensor after denoising at time t, n represents the window size of the denoising process, d i (t) represents the original environmental parameters of the i-th sensor at time t, j represents the accumulated index, and t represents the time point;

[0015] The correction includes correcting the measured value of the sensor network using the correction factor and calculating the corrected sensor network parameters using the linear correction model. The specific calculation formula is:

[0016]

[0017] Among them, d' i (t) represents the corrected sensor network parameters, α i represents the proportionality coefficient, b i Indicates the offset;

[0018] The normalization includes adjusting the denoised environmental parameters and sensor network parameters to the same scale, and the calculation formula for the adjustment is:

[0019]

[0020] Among them, d″ i (t) represents the environmental parameters generated during coal combustion, min(d' i ) represents the minimum corrected environmental parameter value, max(d' i ) represents the maximum corrected environmental parameter value.

[0021] As a preferred solution of the digital management method for preventing environmental parameters from exceeding the standard in the coal-fired power plant of the present invention, the preprocessing of the environmental parameters includes preprocessing the environmental parameters using a preprocessing algorithm based on the environmental parameters received by the central data management area, and the calculation formula of the preprocessing algorithm is:

[0022]

[0023] in, represents the historical average value of the original environmental parameters, γ represents the threshold coefficient, σ represents the standard deviation of the original environmental parameters; fluctuation range;

[0024] If the current time point t exceeds the difference between the original environmental parameters of the i-th sensor at time t and the historical average value, then it is determined whether the difference exceeds the limit determined by the standard deviation of the original environmental parameters and the threshold coefficient;

[0025] When the difference exceeds the limit determined between the standard deviation of the original environmental parameters and the threshold coefficient, the central data management area is used to exclude the difference exceeding the environmental parameters.

[0026] As a preferred solution of the digital management method for preventing environmental protection parameters from exceeding the standard in the coal-fired power plant of the present invention, wherein: the establishment of the digital twin model of the coal-fired power plant includes establishing the operation mechanism of the coal-fired power plant based on the environmental parameters that have not been exceeded in the preprocessing process, and using the data inflow interface of the sensor network to collect physical characteristic data in the operation mechanism;

[0027] When the collected physical feature data is incomplete, the digital twin model is used to automatically perform interpolation and completion, and the original environmental parameters are adjusted based on the interpolation results;

[0028] After adjustment, if the standard deviation of the original environmental parameter quadratically exceeds the limit determined between the standard deviation of the original environmental parameter and the threshold coefficient, the digital twin model will activate the anomaly detection mechanism;

[0029] The dynamic simulation learning includes using a neural network to analyze the change pattern of environmental parameters under different working conditions, simulating the nonlinear relationship of the change pattern through a multi-layer perceptron structure, using the input layer of the neural network to receive the pre-processed environmental parameters, activating the output layer through the hidden layer, and passing the pre-processed environmental parameters to the output layer for training;

[0030] If the current training error E(t) is less than the nonlinear relationship setting error ∈ of the simulated change mode, the neural network stops training and saves the current neural network weight parameters;

[0031] If the error between the output of the neural network and the actual environmental parameters |d' i -d i |When it is greater than the set error ∈, the neural network will automatically adjust the learning rate and retrain.

[0032] As a preferred solution of the digital management method for preventing environmental parameters from exceeding the standard in the coal-fired power plant of the present invention, the predicted environmental parameters exceeding the standard include entering the evaluation feedback mechanism stage according to the environmental parameters exceeding the standard detected by the abnormality detection mechanism, and the evaluation feedback mechanism stage includes using the digital twin model to give early warning of exceeding the standard, generating optimization suggestions, and optimizing the operating parameters of the coal-fired power plant according to the generated optimization suggestions. The specific steps of the optimization suggestions are:

[0033] When the neural network automatically adjusts the learning rate and retrains, if the trend of the monitored environmental protection parameters exceeding the standard gradually returns to normal, the digital management system will record the current optimization plan and establish a benchmark plan for future optimization;

[0034] If the error after retraining continues to expand, the digital management system will use the evaluation feedback mechanism to analyze the current operating conditions, call the neural network retraining mechanism, and re-optimize the operating parameters of the coal-fired power plant;

[0035] The secondary optimization of the operating parameters of the coal-fired power plant includes detecting the upward trend of the environmental protection parameters, calculating the slope of the trend to determine the secondary optimization control mechanism, and the calculation formula of the slope is:

[0036]

[0037] in, represents the slope, p(t n ) represents the secondary optimization of coal-fired power plant time t n The environmental protection parameters, p(t1) represents the environmental protection parameters at the starting time t1, t n and t1 represent time periods.

[0038] As a preferred solution of the digital management method for preventing environmental protection parameters from exceeding the standard in the coal-fired power plant of the present invention, the digital management includes: n ] to manage the average rate of change within;

[0039] If the slope is positive, the environmental protection parameters will rebound, and the digital management system needs to start the secondary optimization and control mechanism; if the slope is negative, the environmental protection parameters will decrease, and no further control is required to complete the digital management of environmental protection parameters exceeding the standard.

[0040] In a second aspect, an embodiment of the present invention provides a digital management system for preventing environmental parameters from exceeding standards in a coal-fired power plant, which includes: a preprocessing module, which transmits the environmental parameters to a central data management area through wireless transmission technology, and preprocesses the environmental parameters based on the central data management area;

[0041] A dynamic learning simulation module, which uses the neural network of the digital twin model to perform dynamic simulation learning to predict the exceeding of environmental protection parameters;

[0042] The management module completes the digital management of environmental protection parameter exceeding the standard through the evaluation feedback mechanism.

[0043] In a third aspect, an embodiment of the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein: when the processor executes the computer program, it implements any step of the above-mentioned digital management method for preventing environmental protection parameters of a coal-fired power plant from exceeding standards.

[0044] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the above-mentioned digital management method for preventing environmental protection parameters of a coal-fired power plant from exceeding standards is implemented.

[0045] The beneficial effects of the present invention are as follows: the present invention realizes real-time monitoring, prediction and dynamic optimization of environmental protection parameters of coal-fired power plants by constructing an intelligent environmental protection parameter monitoring and optimization system based on a digital twin model. It can effectively filter noise data and accurately predict the exceeding of environmental protection parameters. It performs secondary optimization of the operating parameters of coal-fired power plants through adaptive neural networks, thereby significantly improving the accuracy and efficiency of environmental protection parameter management. Compared with the prior art, the present invention can quickly respond to environmental changes, avoid exceeding of environmental protection parameters, ensure the environmental protection-compliant operation of coal-fired power plants, and has significant economic and environmental benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0047] Figure 1 A specific flow chart of a digital management method and system for preventing environmental protection parameters from exceeding standards in a coal-fired power plant provided by an embodiment of the present invention.

[0048] Figure 2 A preprocessing schematic diagram of a digital management method and system for preventing environmental protection parameters from exceeding standards in a coal-fired power plant is provided as an embodiment of the present invention. DETAILED DESCRIPTION

[0049] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0050] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0051] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0052] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0053] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0054] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0055] Example 1

[0056] Reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides a digital management method for preventing environmental protection parameters of a coal-fired power plant from exceeding the standard, comprising:

[0057] S1: A sensor network is arranged at the environmental monitoring points of coal-fired power plants. The sensor network collects environmental parameters generated during the coal combustion process through an intelligent data acquisition model, transmits the environmental parameters to the central data management area through wireless transmission technology, and pre-processes the environmental parameters based on the central data management area.

[0058] Among them, the intelligent data acquisition model includes monitoring the flue gas, wastewater and waste residue of coal-fired power plants based on gas sensors, liquid sensors and solid sensors according to the sensor network;

[0059] The collection of environmental parameters generated during the coal combustion process includes filtering flue gas, wastewater and waste residue. The filtering includes denoising, correcting and normalizing the flue gas, wastewater and waste residue. The normalized data is used as the environmental parameters generated during the coal combustion process.

[0060] Furthermore, the intelligent data acquisition model can realize real-time monitoring of flue gas, wastewater and waste residue generated by coal-fired power plants through a sensor network. The gas sensor can monitor SO2 and NO in the flue gas with a sampling frequency of 1 second. xThe detection accuracy can reach ±1ppm; the liquid sensor monitors the COD concentration in the wastewater with a sampling frequency of 0.5 seconds, and the detection accuracy is ±0.1mg / L; the solid sensor monitors the heavy metal content in the waste slag with a sampling frequency of 2 seconds, and the detection accuracy can reach ±0.01mg / kg. In terms of data processing, the original environmental parameters collected by the sensor are first denoised by the moving average method, and a sliding window with a window size of 5 is used to perform linear correction on the monitoring data according to the correction factors a=0.98 and b=0.05. The denoised and corrected data are normalized to the range of [0,1] as the environmental parameters generated in the coal combustion process for subsequent analysis and optimization.

[0061] S1.1: Denoising includes using the moving average method to reduce the noise interference of the sensor in the process of monitoring the coal-fired power plant. The calculation formula of the moving average method is:

[0062]

[0063] in, represents the environmental parameters of the ith sensor after denoising at time t, n represents the window size of the denoising process, d i (t) represents the original environmental parameters of the i-th sensor at time t, j represents the accumulated index, and t represents the time point;

[0064] The correction includes using the correction factor to correct the measured value of the sensor network and using the linear correction model to calculate the corrected sensor network parameters. The specific calculation formula is:

[0065]

[0066] Among them, d' i (t) represents the corrected sensor network parameters, α i represents the proportionality coefficient, b i Indicates the offset;

[0067] Normalization involves adjusting the denoised environmental parameters and sensor network parameters to the same scale. The adjustment calculation formula is:

[0068]

[0069] Among them, d″ i (t) represents the environmental parameters generated during coal combustion, min(d' i ) represents the minimum corrected environmental parameter value, max(d' i ) represents the maximum corrected environmental parameter value.

[0070] Furthermore, the original environmental parameter data collected by the sensor is interfered by noise. To reduce the interference, the moving average method is used to denoise the data. In a time window, the collected data points are 45.2, 46.1, 44.8, 45.5 and 45.9 respectively. After averaging these data points, the denoised environmental parameter is 45.5. In the subsequent calibration process, the correction factor is used to adjust the sensor's measurement value. For example, the original measurement value of 45.5 is adjusted to 46.2 to more accurately reflect the actual situation. Subsequently, these data need to be normalized, for example, the range of the denoised and corrected data is adjusted to between 0 and 1. Assume that the normalized data is 0.76. Through these processes, it is ensured that the collected environmental data has higher accuracy and consistency in subsequent analysis.

[0071] S1.2: Preprocessing the environmental parameters includes preprocessing the environmental parameters using a preprocessing algorithm based on the environmental parameters received from the central data management area. The calculation formula of the preprocessing algorithm is:

[0072]

[0073] in, represents the historical average value of the original environmental parameters, γ represents the threshold coefficient, σ i Indicates the standard deviation of the original environmental parameters; fluctuation range;

[0074] If the current time point t exceeds the difference between the original environmental parameters of the i-th sensor at time t and the historical average value, then it is determined whether the difference exceeds the limit determined by the standard deviation of the original environmental parameters and the threshold coefficient;

[0075] When the difference exceeds the limit determined between the standard deviation of the original environmental parameters and the threshold coefficient, the central data management area is used to exclude the difference exceeding the environmental parameters.

[0076] Furthermore, when preprocessing environmental parameters, the central data management area first receives environmental parameters from multiple sensors. The historical average value of a sensor in the past 24 hours is 50.3, while the environmental parameter at the current time point is 52.7. If the threshold coefficient is set to 1.5 and the standard deviation of the sensor is 0.8, the calculated allowable fluctuation range is 49.1 to 51.5. If the current environmental parameter 52.7 exceeds this range, the system will determine that the data is abnormal. At this time, the central data management area will start the preprocessing algorithm to process the excess part, such as excluding abnormal data, to ensure the accuracy and stability of the subsequent analysis of the system. The environmental parameter data is shown in Table 1 below:

[0077] Table 1 Environmental parameter data table

[0078] parameter value Historical average 50.3 Environmental parameters at the current time point 52.7 Threshold coefficient 1.5 Sensor standard deviation 0.8 Allowable fluctuation range 49.1 to 51.5

[0079] In the past 24 hours, the historical average environmental parameter of a sensor was 50.3, while the environmental parameter at the current time point is 52.7. The threshold coefficient set by the system is 1.5, the standard deviation of the sensor is 0.8, and the calculated allowable fluctuation range is 49.1 to 51.5. Since the current environmental parameter of 52.7 exceeds the allowable fluctuation range, the system determines that the data is abnormal and will start the preprocessing algorithm to process the abnormal part to ensure the accuracy and stability of subsequent analysis.

[0080] S2: Establish a digital twin model of the coal-fired power plant, use the neural network of the digital twin model to perform dynamic simulation learning, and predict the exceeding of environmental protection parameters.

[0081] Among them, the establishment of the digital twin model of the coal-fired power plant includes establishing the operation mechanism of the coal-fired power plant based on the environmental parameters that are not exceeded during the pretreatment process, and using the data inflow interface of the sensor network to collect the physical characteristic data in the operation mechanism;

[0082] When the collected physical feature data is incomplete, the digital twin model is used to automatically interpolate and complete it, and the original environmental parameters are adjusted based on the interpolation results;

[0083] After adjustment, if the standard deviation of the original environmental parameter quadratically exceeds the limit determined between the standard deviation of the original environmental parameter and the threshold coefficient, the digital twin model will activate the anomaly detection mechanism;

[0084] Dynamic simulation learning includes using neural networks to analyze the change patterns of environmental parameters under different working conditions, simulating the nonlinear relationship of the change patterns through a multi-layer perceptron structure, using the input layer of the neural network to receive the pre-processed environmental parameters, activating the output layer through the hidden layer, and passing the pre-processed environmental parameters to the output layer for training;

[0085] If the current training error E(t) is less than the nonlinear relationship setting error ∈ of the simulated change mode, the neural network stops training and saves the current neural network weight parameters;

[0086] If the error between the output of the neural network and the actual environmental parameters |d' i -d i |When it is greater than the set error ∈, the neural network will automatically adjust the learning rate and retrain.

[0087] Preferably, when establishing a digital twin model of a coal-fired power plant, the environmental parameters of flue gas (SO2 concentration is 120ppm), wastewater and waste residue are first collected through a sensor network, and the interpolation method is used to fill in the data missing (the boiler temperature is estimated to be 345°C). After adjustment, if the standard deviation of the environmental parameter (SO2 is 0.9ppm) exceeds the set threshold (1.2ppm), the model will activate the anomaly detection mechanism. In dynamic simulation learning, the neural network analyzes the parameter changes under different operating conditions. By adjusting the learning rate (0.01 to 0.005), the model prediction accuracy is optimized to ensure the effective management of environmental parameters.

[0088] S2.1: Predicting the exceeding of environmental parameters includes entering the evaluation and feedback mechanism stage according to the exceeding environmental parameters detected by the anomaly detection mechanism. The evaluation and feedback mechanism stage includes using the digital twin model to give early warning of exceeding conditions, generating optimization suggestions, and optimizing the operating parameters of the coal-fired power plant according to the generated optimization suggestions. The specific steps of the optimization suggestions are as follows:

[0089] When the neural network automatically adjusts the learning rate and retrains, if the trend of the monitored environmental protection parameters exceeding the standard gradually returns to normal, the digital management system will record the current optimization plan and establish a benchmark plan for future optimization;

[0090] If the error after retraining continues to expand, the digital management system will use the evaluation feedback mechanism to analyze the current operating conditions, call the neural network retraining mechanism, and re-optimize the operating parameters of the coal-fired power plant;

[0091] The secondary optimization of the operating parameters of the coal-fired power plant includes detecting the upward trend of the environmental parameters, calculating the slope of the trend to determine the control mechanism of the secondary optimization, and the calculation formula of the slope is:

[0092]

[0093] in, represents the slope, p(t n ) represents the secondary optimization of coal-fired power plant time t n The environmental protection parameters, p(t1) represents the environmental protection parameters at the starting time t1, t n and t1 represent time periods.

[0094] S3: Analyze the exceeding of environmental parameters through the digital management system of environmental parameters, optimize the operating parameters of coal-fired power plants according to the analysis results, and complete the digital management of environmental parameters exceeding the standard through the evaluation feedback mechanism.

[0095] The digital management includes the following steps: n ] to manage the average rate of change within;

[0096] If the slope is positive, the environmental protection parameters will rebound, and the digital management system needs to start the secondary optimization and control mechanism; if the slope is negative, the environmental protection parameters will decrease, and no further control is required to complete the digital management of environmental protection parameters exceeding the standard.

[0097] Furthermore, in digital management, management is performed based on the average rate of change of the slope within a time period. If the slope calculation result of the monitored environmental parameters in the past hour is a positive value, such as 0.05, and the environmental parameters rebound by 5% per hour, the digital management system will start the secondary optimization and control mechanism to further optimize the operating parameters of the coal-fired power plant. On the contrary, if the slope calculation result is a negative value, such as -0.03, and the environmental parameters decrease by 3% per hour, it indicates that the environmental parameters have decreased, and the digital management system will no longer perform further control, ending the digital management of environmental parameters exceeding the standard.

[0098] In a preferred embodiment, a digital management system for preventing environmental parameters from exceeding standards in a coal-fired power plant includes a preprocessing module, which transmits environmental parameters to a central data management area through wireless transmission technology and preprocesses the environmental parameters based on the central data management area; a dynamic learning simulation module, which uses a neural network of a digital twin model to perform dynamic simulation learning to predict the exceeding of environmental parameters; and a management module, which completes the digital management of environmental parameters exceeding standards through an evaluation feedback mechanism.

[0099] The above-mentioned unit modules may be embedded in or independent of a processor in a computer device in the form of hardware, or may be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to the above-mentioned modules.

[0100] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0101] In summary, the present invention realizes real-time monitoring, prediction and dynamic optimization of environmental protection parameters of coal-fired power plants by constructing an intelligent environmental protection parameter monitoring and optimization system based on a digital twin model. It can effectively filter noise data, accurately predict the exceeding of environmental protection parameters, and perform secondary optimization of the operating parameters of coal-fired power plants through adaptive neural networks, thereby significantly improving the accuracy and efficiency of environmental protection parameter management. Compared with the prior art, the present invention can quickly respond to environmental changes, avoid exceeding of environmental protection parameters, ensure the environmental protection operation of coal-fired power plants, and has significant economic and environmental benefits.

[0102] Example 2

[0103] Reference Figure 1 and Figure 2 , which is the second embodiment of the present invention, provides a digital management method for preventing environmental protection parameters from exceeding the standard in a coal-fired power plant. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through simulation experiments.

[0104] During the experiment, multiple sensor networks of coal-fired power plants were deployed to monitor the environmental parameters of flue gas, wastewater and waste residue in real time. In the experiment, data collected by a sensor within 72 hours was used for analysis. The historical average value was 48.6, and the environmental parameter at the current time point was 53.2. The system set the threshold coefficient to 1.8, the standard deviation of the sensor was 0.9, and the calculated allowable fluctuation range was 46.8 to 50.4. When the current environmental parameter 53.2 was detected to be beyond this range, the system determined that the data was abnormal, and the central data management area immediately started the preprocessing algorithm to remove abnormal data and automatically interpolate and complete. The operating parameters were optimized using dynamic simulation learning of neural networks. When the error reached 0.3%, the training stopped automatically and the current optimization plan was recorded. After secondary optimization, the recovery trend of environmental parameters was significantly slowed down. The experimental results show that the technical solution has high accuracy and stability under complex working conditions. The experimental data overview is shown in Table 2 below:

[0105] Table 2 Experimental data overview

[0106] parameter value Interpretation Sampling interval 15 minutes Collect environmental parameter data every 15 minutes Data interpolation and completion ratio 7％ The percentage of automatically interpolated data in the total data Anomaly detection trigger times 5 times The number of anomaly detections triggered within 72 hours Number of neural network training rounds 120 rounds The number of neural network training times to ensure model accuracy Duration of environmental parameters exceeding the standard 3 hours The length of time that environmental parameters continue to exceed the allowable fluctuation range Final optimization adjustment coefficient 0.85 Optimized parameter adjustment coefficients for model calibration

[0107] In this experiment, environmental parameters were measured through data collected by sensors, focusing on monitoring the changes in environmental parameters of coal-fired power plants under different working conditions. The experimental results show that the system can accurately trigger the preprocessing algorithm when an abnormality is detected, and the accuracy and stability of subsequent analysis are ensured by processing data that exceeds the range. During the experiment, key parameters such as the historical average value, real-time measurement value, threshold coefficient, and standard deviation of sensor data are displayed in detail in the table to verify the effectiveness of the system. The comparison between the present invention and the prior art is shown in Table 3 below:

[0108] Table 3 Comparison between the present invention and the prior art

[0109]

[0110] The above table compares the differences between the present invention and the prior art in terms of environmental parameter monitoring, data processing, parameter correction, environmental parameter exceeding warning, system adaptability and data stability. The present invention achieves higher data accuracy and system automation level through the application of multi-sensor networks, automatic correction and digital twin models, improves the real-time and accuracy of environmental parameter management, and enhances the system's adaptability in complex environments, which is significantly superior to the prior art.

[0111] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A digital management method for preventing environmental protection parameters from exceeding standards in coal-fired power plants, characterized in that: include, A sensor network is arranged at the environmental monitoring points of the coal-fired power plant. The sensor network collects environmental parameters generated during the coal-burning process through an intelligent data collection model, transmits the environmental parameters to a central data management area through wireless transmission technology, and pre-processes the environmental parameters based on the central data management area; Establishing a digital twin model of a coal-fired power plant, using the neural network of the digital twin model to perform dynamic simulation learning, and predicting the exceeding of environmental protection parameters; The digital management system of environmental parameters is used to analyze the exceeding of standards, and the operating parameters of the coal-fired power plant are optimized based on the analysis results. The digital management of the exceeding of environmental parameters is completed through the evaluation and feedback mechanism.

2. The digital management method for preventing environmental protection parameters from exceeding the standard in a coal-fired power plant according to claim 1, characterized in that: The intelligent data acquisition model includes a gas sensor, a liquid sensor and a solid sensor according to a sensor network, and monitors flue gas, waste water and waste residue of a coal-fired power plant based on the gas sensor, the liquid sensor and the solid sensor; The collection of environmental parameters generated during the coal combustion process includes filtering flue gas, waste water and waste residue, and the filtering includes denoising, correcting and normalizing the flue gas, waste water and waste residue, and the normalized data is used as the environmental parameters generated during the coal combustion process.

3. The digital management method for preventing environmental protection parameters from exceeding the standard in a coal-fired power plant according to claim 2, characterized in that: The denoising includes using a moving average method to reduce noise interference in the process of the sensor monitoring the coal-fired power plant. The calculation formula of the moving average method is: in, represents the environmental parameters of the ith sensor after denoising at time t, n represents the window size of the denoising process, d i (t) represents the original environmental parameters of the i-th sensor at time t, j represents the accumulated index, and t represents the time point; The correction includes correcting the measured value of the sensor network using the correction factor and calculating the corrected sensor network parameters using the linear correction model. The specific calculation formula is: Among them, d' i (t) represents the corrected sensor network parameters, α i represents the proportionality coefficient, b i Indicates the offset; The normalization includes adjusting the denoised environmental parameters and sensor network parameters to the same scale, and the calculation formula for the adjustment is: Among them, d″ i (t) represents the environmental parameters generated during coal combustion, min(d' i ) represents the minimum corrected environmental parameter value, max(d' i ) represents the maximum corrected environmental parameter value.

4. The digital management method for preventing environmental protection parameters from exceeding the standard in a coal-fired power plant according to claim 3, characterized in that: The preprocessing of the environmental parameters includes preprocessing the environmental parameters using a preprocessing algorithm based on the environmental parameters received by the central data management area. The calculation formula of the preprocessing algorithm is: in, represents the historical average value of the original environmental parameters, λ represents the threshold coefficient, σ i Indicates the standard deviation of the original environmental parameters; fluctuation range; If the current time point t exceeds the difference between the original environmental parameters of the i-th sensor at time t and the historical average value, then it is determined whether the difference exceeds the limit determined by the standard deviation of the original environmental parameters and the threshold coefficient; When the difference exceeds the limit determined between the standard deviation of the original environmental parameters and the threshold coefficient, the central data management area is used to exclude the difference exceeding the environmental parameters.

5. The digital management method for preventing environmental protection parameters from exceeding the standard in a coal-fired power plant according to claim 4, characterized in that: The establishment of the digital twin model of the coal-fired power plant includes establishing an operation mechanism of the coal-fired power plant based on environmental parameters that are not exceeded during the preprocessing process, and using a data inflow interface of a sensor network to collect physical characteristic data in the operation mechanism; When the collected physical feature data is incomplete, the digital twin model is used to automatically perform interpolation and completion, and the original environmental parameters are adjusted based on the interpolation results; After adjustment, if the standard deviation of the original environmental parameters exceeds the limit determined by the standard deviation of the original environmental parameters and the threshold coefficient twice, the digital twin model will start the abnormality detection mechanism; the dynamic simulation learning includes using a neural network to analyze the change pattern of the environmental parameters under different working conditions, simulating the nonlinear relationship of the change pattern through a multi-layer perceptron structure, using the input layer of the neural network to receive the preprocessed environmental parameters, activating the output layer through the hidden layer, and passing the preprocessed environmental parameters to the output layer for training; If the current training error E(t) is less than the nonlinear relationship setting error ∈ of the simulated change mode, the neural network stops training and saves the current neural network weight parameters; If the error between the output of the neural network and the actual environmental parameters |d' i -d i |When it is greater than the set error ∈, the neural network will automatically adjust the learning rate and retrain.

6. The digital management method for preventing environmental protection parameters from exceeding the standard in a coal-fired power plant according to claim 5, characterized in that: The predicted environmental parameter exceeding the standard includes entering the evaluation feedback mechanism stage according to the environmental parameter exceeding the standard detected by the abnormal detection mechanism. The evaluation feedback mechanism stage includes using the digital twin model to give early warning of the exceeding standard, generating optimization suggestions, and optimizing the operating parameters of the coal-fired power plant according to the generated optimization suggestions. The specific steps of the optimization suggestions are: When the neural network automatically adjusts the learning rate and retrains, if the trend of the monitored environmental protection parameters exceeding the standard gradually returns to normal, the digital management system will record the current optimization plan and establish a benchmark plan for future optimization; If the error after retraining continues to expand, the digital management system will use the evaluation feedback mechanism to analyze the current operating conditions, call the neural network retraining mechanism, and re-optimize the operating parameters of the coal-fired power plant; The secondary optimization of the operating parameters of the coal-fired power plant includes detecting the upward trend of the environmental protection parameters, calculating the slope of the trend to determine the secondary optimization control mechanism, and the calculation formula of the slope is: in, represents the slope, p(t n ) represents the secondary optimization of coal-fired power plant time t n The environmental protection parameters, p(t1) represents the environmental protection parameters at the starting time t1, t n and t1 represent time periods.

7. The digital management method for preventing environmental protection parameters from exceeding the standard in a coal-fired power plant according to claim 6, characterized in that: The digital management includes the following steps: n ] to manage the average rate of change within; If the slope is positive, the environmental protection parameters will rebound, and the digital management system needs to start the secondary optimization and control mechanism; if the slope is negative, the environmental protection parameters will decrease, and no further control is required to complete the digital management of environmental protection parameters exceeding the standard.

8. A digital management system for preventing environmental parameters from exceeding standards in a coal-fired power plant, based on the digital management method for preventing environmental parameters from exceeding standards in a coal-fired power plant according to any one of claims 1 to 7, characterized in that: include, A preprocessing module, which transmits the environmental parameters to a central data management area through wireless transmission technology, and preprocesses the environmental parameters based on the central data management area; A dynamic learning simulation module, which uses the neural network of the digital twin model to perform dynamic simulation learning to predict the exceeding of environmental protection parameters; The management module completes the digital management of environmental protection parameter exceeding the standard through the evaluation feedback mechanism.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the digital management method for preventing environmental protection parameters of a coal-fired power plant from exceeding the standard as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the digital management method for preventing environmental protection parameters of a coal-fired power plant from exceeding the standard as described in any one of claims 1 to 7 are implemented.

Images