Improved boiler fan electrical system

Abstract

The invention discloses an improved boiler fan electrical system, and relates to the technical field of boiler fan electrical control, and the improved boiler fan electrical system comprises a boiler operation parameter acquisition module which is used for acquiring operation state parameters of a boiler; the time sequence characteristic prediction module is used for predicting the load change of the boiler according to the historical data and the real-time operation data; the fuzzy self-adaptive control module is used for dynamically controlling the rotating speed of the fan based on the time sequence characteristic prediction result and the real-time operation parameters; and the multi-layer feedback mechanism is used for receiving the error between the actual operation state and the prediction state of the boiler and optimizing control parameters, and the time sequence characteristic prediction module uses a long-short-term memory network model. According to the method, through combination of time sequence characteristic prediction and fuzzy self-adaptive control, accurate control over the boiler fan is achieved, the system can adjust the rotating speed and the air supply amount of the fan in advance according to prediction of the boiler load and changes of real-time parameters, and therefore the hysteresis phenomenon is reduced, and the control precision and the response speed of the system are remarkably improved.

Description

Technical Field

[0001] The invention relates to the technical field of boiler fan electrical control, in particular to an improved boiler fan electrical system. Background Art

[0002] With the acceleration of industrialization and the increase in energy demand, boiler systems, as core equipment in industrial production, are widely used in power generation, heating and other fields. In boiler systems, fans, as one of the key equipment, are responsible for providing the right amount of air for the combustion process, ensuring sufficient combustion and maintaining stable operation of the system. However, the existing electrical control system for boiler fans still has some obvious technical deficiencies, which restricts the operating efficiency and control accuracy of the system.

[0003] Traditional boiler fan control systems usually use fixed-parameter PID control. The fixed parameters of the control algorithm make it difficult for the system to quickly adjust when the boiler load changes. Especially when the load fluctuates greatly or the working conditions are complex, the existing control system often shows problems of insufficient control accuracy and delayed response. This makes it impossible for the boiler fan to be flexibly adjusted according to actual needs, which in turn affects the boiler's combustion efficiency and system stability.

[0004] The existing boiler fan control system lacks adaptive capabilities when facing complex working conditions and cannot effectively handle the dynamic changes in boiler load. Since system parameters need to be set manually, existing technologies cannot automatically adjust control strategies to adapt to new operating conditions when load changes or external environment changes. In addition, traditional control systems mostly rely on human intervention and have a low level of intelligence, making it difficult to meet the needs of modern industry for automation and intelligence.

[0005] In the existing technology, since the boiler fan usually operates at a fixed speed or a simple multi-stage control mode, the system cannot flexibly adjust the fan speed and air supply according to the actual load demand. This control mode lacking dynamic adjustment not only causes the fan to still consume a lot of energy at low load, but may also fail to fully meet the combustion demand at high load, thus affecting the combustion efficiency and causing energy waste.

[0006] Existing boiler fan control systems usually rely on feedback control with fixed parameters and cannot perceive the operating status and load changes of the boiler in real time. This single feedback mechanism is difficult to cope with complex and dynamic working conditions, causing the boiler system to be unstable when the load fluctuates. In addition, the existing technology lacks a mechanism for real-time optimization of operating parameters, and the system cannot adjust itself according to operating feedback. Long-term operation is prone to accumulate errors, affecting the service life and safety of the equipment.

[0007] To this end, those skilled in the art provide an improved boiler fan electrical system to solve the problems raised in the above background technology. Summary of the invention

[0008] In view of the problems existing in the existing improved boiler fan electrical system, the present invention is proposed.

[0009] Therefore, the problem to be solved by the present invention is that the prior art has the problems of low control accuracy, poor adaptability, high energy consumption and poor system stability.

[0010] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0011] In a first aspect, an embodiment of the present invention provides an improved boiler fan electrical system, which comprises:

[0012] Boiler operation parameter collection module: used to collect boiler operation status parameters;

[0013] Time series feature prediction module: used to predict boiler load changes based on historical data and real-time operation data;

[0014] Fuzzy adaptive control module: used to dynamically control the fan speed based on the time series feature prediction results and real-time operating parameters;

[0015] Multi-layer feedback mechanism: used to receive the error between the actual operating state and the predicted state of the boiler and optimize the control parameters.

[0016] As a preferred solution of the improved boiler fan electrical system of the present invention, the time series feature prediction module uses a long short-term memory network model to make predictions based on the following function, which is specifically expressed as:

[0017]

[0018] In the formula, is the load forecast value at the future time, x t+1 is the input data, W h and W x is the weight matrix, b h is the bias, h t is the hidden state at the previous moment.

[0019] As a preferred solution of the improved boiler fan electrical system described in the present invention, the time series feature prediction module generates a feature vector through a sliding window method, and the window length is a preset historical data time period to obtain the dynamic change trend of the boiler system.

[0020] As a preferred solution of the improved boiler fan electrical system of the present invention, the fuzzy adaptive control module includes:

[0021] A fuzzification unit is used to fuzzify the errors of boiler load and fan speed;

[0022] Fuzzy reasoning unit, which performs reasoning based on the fuzzy rule base;

[0023] The defuzzification unit outputs the specific fan speed adjustment value. The fuzzy reasoning process is based on the following calculation formula:

[0024]

[0025] In the formula, μ i is the fuzzy membership, u i is the corresponding control output.

[0026] As a preferred solution of the improved boiler fan electrical system of the present invention, the fuzzy rule base of the fuzzy reasoning unit includes a plurality of fuzzy rules based on boiler load and fan speed error, and the rules are determined according to the following conditions:

[0027] If the load increases rapidly and the air supply is insufficient, increase the fan speed;

[0028] If the load changes slowly and the air supply is sufficient, the fan speed remains unchanged.

[0029] As a preferred solution of the improved boiler fan electrical system of the present invention, the defuzzification unit adopts the centroid method to perform defuzzification processing, and the calculation formula is:

[0030]

[0031] Where x is the control variable and μ(x) is the membership function of the fuzzy set.

[0032] As a preferred solution of the improved boiler fan electrical system of the present invention, the multi-layer feedback mechanism is optimized and adjusted by an error accumulation calculation formula, which is specifically expressed as:

[0033]

[0034] In the formula, e t is the current error, is the predicted value, K p , K i , K d are the proportional, integral and differential coefficients of feedback control.

[0035] As a preferred solution of the improved boiler fan electrical system of the present invention, the multi-layer feedback mechanism is further combined with a self-learning module, and the control parameters are adjusted by a reinforcement learning algorithm, and the control strategy is optimized by the following Q learning update formula, which is specifically expressed as:

[0036]

[0037] In the formula, Q(s t ,a t ) is the value of the state-action pair, α is the learning rate, r t is the current reward, and γ is the discount factor.

[0038] In a second 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, any step of the above-mentioned improved boiler blower electrical system is implemented.

[0039] In a third 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 improved boiler blower electrical system is implemented.

[0040] The beneficial effects of the present invention are:

[0041] 1. The present invention realizes precise control of the boiler fan by combining time series feature prediction and fuzzy adaptive control. The system can adjust the fan speed and air supply in advance according to the prediction of boiler load and the change of real-time parameters, thereby reducing the lag phenomenon and significantly improving the control accuracy and response speed of the system.

[0042] 2. Through the multi-layer feedback mechanism and self-learning module, the system can automatically adjust the control parameters when the actual operation status of the boiler does not match the prediction, ensuring the optimization and self-adjustment capabilities during long-term operation. The introduction of the reinforcement learning algorithm further improves the adaptability of the system under different working conditions, making it highly intelligent and capable of sustainable optimization.

[0043] 3. The present invention adjusts the air supply according to the boiler load by dynamically controlling the fan speed to avoid unnecessary energy waste. In particular, under low load conditions, the fan can run at a lower speed to save energy; and under high load conditions, the system can quickly adjust the air supply to maintain the efficient combustion state of the boiler, significantly improving the energy efficiency of the boiler system. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] 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:

[0045] Figure 1This is a schematic diagram of the improved boiler fan electrical system. DETAILED DESCRIPTION

[0046] 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.

[0047] 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.

[0048] 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.

[0049] 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.

[0050] 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.

[0051] 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.

[0052] Example 1

[0053] Reference Figure 1 , which is the first embodiment of the present invention, provides an improved boiler fan electrical system, comprising:

[0054] Boiler operation parameter collection module: used to collect boiler operation status parameters;

[0055] The boiler operation parameter acquisition module includes: pressure sensor; temperature sensor; fan speed sensor; air supply volume sensor, which is used to collect the key operation parameters of the boiler and fan in real time;

[0056] The boiler operation parameter acquisition module communicates with the time series feature prediction module and the fuzzy adaptive control module through a wireless sensor network to achieve remote monitoring and data acquisition.

[0057] Specifically, the boiler operation parameter acquisition module is used to collect the key operating parameters of the boiler system to ensure that the control system can accurately adjust the operating status of the fan according to real-time data. The module integrates multiple high-precision sensors, including pressure sensors, temperature sensors, fan speed sensors and air supply sensors. These sensors are distributed in key parts of the boiler and can monitor the pressure, temperature, fan speed and air flow of the boiler in real time, so as to obtain dynamic operation information of the boiler system. These data provide accurate input for subsequent control decisions, so that the system can respond to changes in boiler load more quickly. The boiler operation parameter acquisition module communicates with the time series feature prediction module and the fuzzy adaptive control module through a wireless sensor network, making data collection and transmission more flexible and efficient. This wireless sensor network not only reduces the limitations of traditional wired connections, but also improves the maintainability and scalability of the system, and facilitates remote monitoring and management. Based on the real-time data of these sensors, the system can adjust the fan speed and air supply in time, realize accurate control of the boiler status, and ensure that the boiler operates under efficient and safe conditions. By introducing this module, the collection of boiler operating parameters is more comprehensive and accurate, thus providing a solid foundation for subsequent intelligent control and effectively improving the operating efficiency and response speed of the boiler system.

[0058] Time series feature prediction module: used to predict boiler load changes based on historical data and real-time operation data.

[0059] The time series feature prediction module uses the long short-term memory network model to make predictions based on the following functions:

[0060]

[0061] in, is the load forecast value at the future time, x t+1 is the input data, W hand W x is the weight matrix, b h is the bias, h t is the hidden state of the previous moment. The time series feature prediction module generates feature vectors through the sliding window method, and the window length is the preset historical data time period to obtain the dynamic change trend of the boiler system;

[0062] Specifically, it is used to predict the future load changes of the boiler based on the historical data and real-time operation data of the boiler system, ensuring that the system can respond in advance and avoiding system lag or instability caused by sudden load changes. This module uses the long short-term memory network (LSTM) model to capture complex time series features by deeply analyzing the historical data of the boiler's operating status. The advantage of the LSTM model is that it can remember the key information of long time series data while ignoring irrelevant short-term fluctuations, which makes it particularly suitable for predicting systems such as boilers with long operating cycles and complex load changes.

[0063] During the operation of the LSTM model, the input data at each moment (such as boiler pressure, temperature, fan speed, etc.) is combined with historical data and processed through the network layer to obtain the load forecast value at the future moment. The hidden state in the model can store long-term dependencies, while the weight matrix and bias are used to adjust the output of the model to make the prediction more accurate. In this way, LSTM can provide high-precision boiler load change predictions, provide advance adjustment for the control system, and avoid excessive or delayed response of the system due to boiler load changes.

[0064] In order to further improve the accuracy of the prediction, the time series feature prediction module also uses a sliding window method to generate feature vectors from the historical data of the boiler. The length of the sliding window is preset to a certain period of time, which ensures that the model always analyzes the latest historical data and adjusts the prediction results in a timely manner. This method helps to extract the dynamic change trend in the operation of the boiler, allowing the model to perceive the change trajectory of the load more quickly. By combining historical and real-time data, the time series feature prediction module can update the prediction results of the future load of the boiler in real time, thereby providing accurate data support for the adaptive control of the system. This forward-looking prediction function significantly improves the response speed and control accuracy of the boiler system, ensuring the smooth and efficient operation of the entire system.

[0065] Fuzzy adaptive control module: used to dynamically control the fan speed based on the time series feature prediction results and real-time operating parameters.

[0066] The fuzzy adaptive control module includes:

[0067] A fuzzification unit is used to fuzzify the errors of boiler load and fan speed;

[0068] Fuzzy reasoning unit, which performs reasoning based on the fuzzy rule base;

[0069] The defuzzification unit outputs the specific fan speed adjustment value. The fuzzy reasoning process is based on the following calculation formula:

[0070]

[0071] Among them, μ i is the fuzzy membership, u i is the corresponding control output.

[0072] The fuzzy rule base of the fuzzy reasoning unit includes multiple fuzzy rules based on boiler load and fan speed error. The rules are determined according to the following conditions:

[0073] If the load increases rapidly and the air supply is insufficient, increase the fan speed;

[0074] If the load changes slowly and the air supply is sufficient, the fan speed is kept constant;

[0075] The defuzzification unit uses the centroid method for defuzzification, and the calculation formula is:

[0076]

[0077] Among them, x is the control variable and μ(x) is the membership function of the fuzzy set.

[0078] Specifically, the fuzzy adaptive control module is used to dynamically control the fan speed based on the time series feature prediction results and the real-time operating parameters of the boiler system, thereby achieving an accurate response to changes in boiler load. The core of this module is to process the uncertainty and nonlinear characteristics of the system through fuzzy logic, making the adjustment of the fan speed more flexible and efficient. The fuzzy adaptive control module consists of three main parts: fuzzification unit, fuzzy reasoning unit and defuzzification unit.

[0079] First, the function of the fuzzification unit is to fuzzify input parameters such as boiler load and fan speed error. Due to the complex operating environment of the boiler system, the input parameters may have certain fuzziness or uncertainty. The fuzzification unit converts these precise values ​​into fuzzy sets for subsequent reasoning. This process converts continuous values ​​into several fuzzy levels, such as "low", "medium", and "high", to better describe the dynamic changes of boiler load and fan speed error.

[0080] Next, the fuzzy reasoning unit performs reasoning operations based on the preset fuzzy rule base. The fuzzy rule base is set according to the system's empirical knowledge and actual operating conditions, and contains multiple rules based on boiler load and fan speed errors. For example, "when the load increases rapidly and the gas supply is insufficient, increase the fan speed" or "when the load changes slowly and the gas supply is sufficient, keep the fan speed unchanged." Through these rules, the system can make corresponding adjustment decisions when facing different load changes. During the reasoning process, the results of different rules are weighted according to the fuzzy membership of the input parameters to determine the final fuzzy control output.

[0081] The function of the defuzzification unit is to convert the fuzzy output generated by the fuzzy reasoning unit into a specific fan speed adjustment value. In order to ensure the accuracy of the adjustment, the defuzzification process adopts the centroid method, which obtains the specific control output by weighted averaging the membership functions of the fuzzy set. The speed adjustment value calculated by the centroid method not only fully considers the contribution of each fuzzy rule, but also ensures that the fan speed adjustment meets the needs of the actual working conditions.

[0082] Through the fuzzy adaptive control module, the system can flexibly and accurately adjust the fan speed when the boiler load changes, so that it can adapt to the complex operating environment. Compared with the traditional fixed control method, fuzzy control can better handle the dynamic nonlinear characteristics of the boiler system and significantly improve the system's adaptive ability and control accuracy. The dynamic adjustment of the entire control process enables the system to respond quickly to sudden changes in load, ensuring the efficient and stable operation of the boiler while reducing energy waste and equipment loss.

[0083] Multi-layer feedback mechanism: used to receive the error between the actual operating state and the predicted state of the boiler and optimize the control parameters.

[0084] The multi-layer feedback mechanism is optimized and adjusted through the error accumulation calculation formula:

[0085]

[0086] Among them, e t is the current error, is the predicted value, K p , K i , K d are the proportional, integral and differential coefficients of feedback control.

[0087] The multi-layer feedback mechanism is further combined with the self-learning module to adjust the control parameters using the reinforcement learning algorithm and optimize the control strategy through the following Q-learning update formula:

[0088]

[0089] Among them, Q(s t ,at ) is the value of the state-action pair, α is the learning rate, r t is the current reward, and γ is the discount factor.

[0090] Specifically, the multi-layer feedback mechanism is designed to dynamically optimize and adjust the control system parameters by receiving the error between the actual operating state and the predicted state of the boiler, thereby ensuring that the system can maintain high-precision control during operation. This mechanism adjusts the various control parameters of the boiler system through feedback to quickly and flexibly respond to fluctuations in boiler load.

[0091] In the feedback process, the system adopts the error accumulation calculation method, comprehensively considers the error at the current moment and the error accumulated in the previous period, and optimizes the control parameters. Specifically, the current error is the difference between the actual operating state and the predicted state of the timing characteristics. The feedback mechanism processes the error through three coefficients: proportional (P), integral (I), and differential (D). The proportional coefficient is used to respond to the change of the error immediately, the integral coefficient is used to correct the long-term accumulated error, and the differential coefficient is used to predict the future error change trend, thereby ensuring the control system's rapid response to changes in boiler load. Through the combined effects of P, I, and D, the system can adjust the fan speed and air supply according to the dynamic changes of the error, so that the boiler always maintains a stable operating state.

[0092] In addition, the multi-layer feedback mechanism further integrates the self-learning module, and uses the reinforcement learning algorithm to self-optimize the control parameters. By introducing the Q-learning algorithm, this module can update the control strategy in the process of continuous interaction with the environment. Specifically, the Q-learning algorithm is updated based on the value of the state-action pair. After each control action is executed, the system will obtain a reward value based on the actual boiler operation results. By adjusting the learning rate and discount factor, the system can gradually optimize the control parameters to make them more in line with the actual working conditions. The learning rate determines the system's sensitivity to new information, while the discount factor is used to balance the impact of current rewards and future rewards. Through this reinforcement learning method, the system can continue to learn and adjust in long-term operation, gradually optimize the control strategy, and thus achieve higher adaptability and intelligent control.

[0093] The combination of multi-layer feedback mechanism and self-learning module enables the boiler fan electrical system to not only deal with short-term errors through traditional feedback control, but also improve the overall control effect through long-term learning and optimization. This mechanism not only enhances the robustness of the system, but also enables it to have the ability to adaptively adjust under complex working conditions, effectively improving the operating efficiency and stability of the boiler system.

[0094] Example 2

[0095] This embodiment also provides a computer device, which is suitable for the case of an improved boiler fan electrical system, including a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the improved boiler fan electrical system proposed in the above embodiment.

[0096] 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.

[0097] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the improved boiler fan electrical system proposed in the above embodiment is implemented.

[0098] The storage medium proposed in this embodiment and the data storage method proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be found in the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0099] Example 3

[0100] Based on the previous two embodiments, this embodiment provides an improved boiler fan electrical system, including:

[0101] Boiler operation parameter collection module:

[0102] The module collects key operating parameters in real time through sensors installed in different parts of the boiler:

[0103] Pressure sensor: used to monitor the steam pressure in the boiler, with a range of 0-2MPa and an accuracy of ±0.05MPa.

[0104] Temperature sensor: measures the temperature of steam in the boiler, with a temperature range of 0-500°C and a measurement accuracy of ±2°C.

[0105] Fan speed sensor: monitors the real-time speed of the fan, with a speed range of 500-5000RPM and an accuracy of ±20RPM.

[0106] Air supply flow sensor: used to detect the air supply flow of the fan, with a range of 0-5000m 3 / h, accuracy is ±50m 3 / h.

[0107] The collected data is transmitted to the time series feature prediction module and the fuzzy adaptive control module through the wireless sensor network to achieve real-time monitoring and control regulation.

[0108] Time series feature prediction module

[0109] This module uses historical data and real-time data to predict boiler load based on the long short-term memory network (LSTM). In this embodiment, the time series feature prediction module processes the historical operation data of the boiler in the past 24 hours, collects data every 5 minutes, and forms 288 data points as input. The sliding window length is set to 60 minutes, that is, the data of the past hour is used to predict the load change of the next hour.

[0110] Through LSTM model training, it is predicted that the possible change range of boiler steam pressure in the next hour will be between 1.2MPa and 1.5MPa, and the temperature change will be between 400℃ and 420℃. According to the prediction results, the control system can increase the fan speed and gas supply in advance when the load is about to increase, so as to prevent insufficient gas supply from affecting the boiler combustion efficiency.

[0111] Fuzzy adaptive control module

[0112] The fuzzy adaptive control module dynamically adjusts the fan speed and air supply according to the results of time series prediction and the real-time collected boiler operating parameters. Specifically:

[0113] When the boiler load increases rapidly and the air supply is insufficient, the fan speed increases from 2500RPM to 3200RPM and the air supply volume increases from 3500m 3 / h increased to 4300m 3 / h.

[0114] When the boiler load changes slowly and the air supply is sufficient, the fan speed is maintained at around 2000RPM and the air supply volume is maintained at 3000m 3 / h.

[0115] Through fuzzification, the load and speed errors are converted into three fuzzy sets of "low", "medium" and "high". Then, based on the preset fuzzy rule base (for example, "increase the speed when the load increases and the air supply is insufficient"), the corresponding fan adjustment strategy is inferred, and finally the specific fan speed adjustment value is obtained through the defuzzification process. In this embodiment, the fuzzy adaptive control module realizes the dynamic adjustment of the fan speed, ensuring that the fan can respond quickly when the load fluctuates greatly.

[0116] Multi-layer feedback mechanism Multi-layer feedback mechanism is used to correct the output of the control system, and adjust the control parameters by detecting the error between the actual operating state of the boiler and the predicted value. PID feedback control method is adopted:

[0117] Proportional coefficient K p Set it to 0.6 for immediate response to error changes.

[0118] Integration coefficient K i Set to 0.3 to correct the cumulative error.

[0119] Differential coefficient K d Set to 0.1 to predict the error trend.

[0120] In this embodiment, when the boiler steam pressure fluctuates from the predicted 1.5MPa to 1.45MPa, the system adjusts the fan speed from 3000RPM to 3100RPM through a multi-layer feedback mechanism and stabilizes the steam pressure at 1.48MPa within 30 seconds. This adjustment significantly improves the operational stability of the boiler.

[0121] Reinforcement learning algorithm for self-learning modules

[0122] In order to enable the system to gradually optimize the control strategy in long-term operation, this embodiment introduces a reinforcement learning algorithm. Through Q learning, the system adjusts the weight coefficient and rule base in the fuzzy controller according to the feedback results under different load conditions. After each adjustment of the fan speed, the system gives corresponding rewards or penalties according to the actual response and energy consumption of the boiler load, and gradually optimizes the control strategy through the learning rate (set to 0.05) and the discount factor (set to 0.9).

[0123] In long-term operation, through reinforcement learning, the self-learning module found that when the boiler load increased to 90%, the fan speed was optimally set to 3500RPM and the air supply volume was set to 4200m 3 / h. This intelligent adjustment greatly improves the adaptability and energy efficiency of the system.

[0124] Overall system effect

[0125] After three months of operation tests, the system performed well under conditions with large boiler load fluctuations, reducing the fan adjustment response time by 30%, improving the boiler operation stability by 20%, and saving 5% of energy consumption during high-load operation. The combination of fuzzy adaptive control and multi-layer feedback mechanism enables the system to achieve high-precision and fast-response control effects in complex dynamic environments. At the same time, the introduction of the self-learning module ensures that the system can continuously optimize the control strategy in long-term operation, significantly improving the overall efficiency and safety of the boiler system.

[0126] 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 can 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 present invention.

Claims

1. An improved boiler fan electrical system, characterized in that: include, Boiler operation parameter collection module: used to collect boiler operation status parameters; Time series feature prediction module: used to predict boiler load changes based on historical data and real-time operation data; Fuzzy adaptive control module: used to dynamically control the fan speed based on the time series feature prediction results and real-time operating parameters; Multi-layer feedback mechanism: used to receive the error between the actual operating state and the predicted state of the boiler and optimize the control parameters.

2. The improved boiler fan electrical system according to claim 1, characterized in that: The time series feature prediction module uses a long short-term memory network model to make predictions based on the following function, which is specifically expressed as: In the formula, is the load forecast value at the future time, x t+1 is the input data, W h and W x is the weight matrix, b h is the bias, h t is the hidden state at the previous moment.

3. The improved boiler fan electrical system according to claim 2, characterized in that: The time series feature prediction module generates a feature vector by a sliding window method, and the window length is a preset historical data time period to obtain the dynamic change trend of the boiler system.

4. The improved boiler fan electrical system according to claim 3, characterized in that: The fuzzy adaptive control module includes: A fuzzification unit is used to fuzzify the errors of boiler load and fan speed; Fuzzy reasoning unit, which performs reasoning based on the fuzzy rule base; The defuzzification unit outputs the specific fan speed adjustment value. The fuzzy reasoning process is based on the following calculation formula: In the formula, μ i is the fuzzy membership, u i is the corresponding control output.

5. The improved boiler fan electrical system according to claim 4, characterized in that: The fuzzy rule base of the fuzzy reasoning unit includes a plurality of fuzzy rules based on boiler load and fan speed error, and the rules are determined according to the following conditions: If the load increases rapidly and the air supply is insufficient, increase the fan speed; If the load changes slowly and the air supply is sufficient, the fan speed remains unchanged.

6. The improved boiler fan electrical system according to claim 5, characterized in that: The defuzzification unit uses the centroid method to perform defuzzification processing, and the calculation formula is: Where x is the control variable and μ(x) is the membership function of the fuzzy set.

7. The improved boiler fan electrical system according to claim 6, characterized in that: The multi-layer feedback mechanism is optimized and adjusted through the error accumulation calculation formula, which is specifically expressed as: In the formula, e t is the current error, is the predicted value, K p , K i , K d are the proportional, integral and differential coefficients of feedback control.

8. The improved boiler fan electrical system according to claim 7, characterized in that: The multi-layer feedback mechanism is further combined with the self-learning module, and the control parameters are adjusted using the reinforcement learning algorithm. The control strategy is optimized through the following Q learning update formula, which is specifically expressed as: In the formula, Q(s t ,a t ) is the value of the state-action pair, α is the learning rate, r t is the current reward, and γ is the discount factor.

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 improved boiler fan electrical system according to any one of claims 1 to 8 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 improved boiler fan electrical system according to any one of claims 1 to 7 are implemented.

Images