Hydropower station energy-saving control system and method

Abstract

The embodiment of the invention provides an energy-saving control system and method for a hydropower station, and the system comprises a state monitoring module which is used for collecting the operation state data of a generator set and auxiliary equipment in real time; the state evaluation module is used for receiving the running state data, classifying the equipment state by adopting a pre-trained machine learning model and outputting a classification result, and the dynamic optimization control module is configured to generate a corresponding control instruction according to the classification result output by the state evaluation module and send the control instruction to the main control system. The operation parameters of the generator set and the auxiliary equipment are subjected to closed-loop adjustment; when the equipment state is classified as an abnormal state, the rotating speed and the exciting current of the generator set or the pressure and the flow of auxiliary equipment are automatically adjusted; when the equipment state is classified as an abnormal state and high-energy-consumption equipment is involved, a preset efficient operation mode is started preferentially; when the device state is classified as a fault state, a maintenance state is entered or a load reduction operation is performed. And real-time closed-loop optimization of the operation state of the equipment is realized.

Description

Technical Field

[0001] This application relates to the field of equipment operation and maintenance technology, and in particular to an energy-saving control system and method for hydropower stations. Background Technology

[0002] In the field of industrial automation and intelligent manufacturing, ensuring the stable and efficient operation of critical equipment is one of the core requirements. Currently, equipment condition monitoring and control systems are widely used. A common approach is to deploy various sensors (such as current, temperature, and vibration sensors) to collect the physical parameters of the equipment in real time and transmit the data to a programmable logic controller (PLC) or distributed control system (DCS) for centralized monitoring. Furthermore, with the development of big data and artificial intelligence technologies, some advanced systems have begun to introduce machine learning algorithms (such as support vector machines and random forests) to analyze the collected historical and real-time data to achieve equipment fault diagnosis and condition assessment, thereby determining whether the equipment is in a normal, abnormal, or potentially faulty state. This marks the initial shift in equipment management from traditional "reactive maintenance" to "predictive maintenance."

[0003] However, some related technologies still have significant shortcomings, mainly in the following aspects: First, most systems separate "status monitoring" from "operation control," forming an open-loop system. That is, the status monitoring model can only provide early warning information about "what has happened" or "what is about to happen," while subsequent control decisions (such as parameter adjustments, start-up and shutdown) still rely on manual judgment and operation, resulting in slow response and an inability to automatically execute optimization or protection actions at the first sign of abnormal conditions. Second, even if some systems possess certain automatic control functions, their control strategies are often static and fixed, lacking the ability to dynamically optimize and adaptively adjust based on the real-time health status of the equipment. This makes it difficult to achieve a dynamic balance between ensuring equipment safety and pursuing operational efficiency. For example, the system cannot automatically switch to a high-efficiency operating mode when it detects low equipment efficiency, or proactively reduce load to avoid downtime risks when potential fault risks are anticipated. Therefore, existing technologies are generally "strong in perception but weak in execution," lacking an integrated solution that combines intelligent diagnosis, dynamic decision-making, and closed-loop execution, resulting in room for improvement in the reliability, economy, and intelligence level of equipment operation. Summary of the Invention

[0004] In view of this, embodiments of this application provide an energy-saving control system and method for hydropower stations. One or more embodiments of this application also relate to a computing device, a computer-readable storage medium, and a computer program, to address the technical deficiencies existing in the prior art.

[0005] In a first aspect, embodiments of this application provide an energy-saving control system for a hydropower station, comprising: A status monitoring module is installed on the generator sets and auxiliary equipment of the hydropower station to collect real-time operating status data of the generator sets and auxiliary equipment. The status monitoring module includes a current transformer, a temperature sensor, a vibration sensor, and a pressure transmitter. The status assessment module is communicatively connected to the status monitoring module. It is used to receive the operating status data, classify the equipment status using a pre-trained machine learning model, and output the classification results, which include normal status, abnormal status, or fault status. The dynamic optimization control module is linked with the state assessment module and the main control system of the power plant. The dynamic optimization control module is configured to generate corresponding control commands based on the classification results output by the state assessment module and send them to the main control system to perform closed-loop adjustment of the operating parameters of the generator set and auxiliary equipment. The control commands include at least one of the following: When the equipment status is classified as abnormal, the generator set speed, excitation current, or the pressure and flow of auxiliary equipment are automatically adjusted. When the equipment status is classified as abnormal and involves high-energy-consuming equipment, the preset high-efficiency operation mode is activated first. When the equipment status is classified as faulty, the control equipment enters maintenance mode or performs load reduction operation in advance.

[0006] In one possible implementation, when the state assessment module performs state classification, the extracted features include the mean, variance, and peak values ​​of operating parameters, the spectral components of fault features, and the state change trend.

[0007] In one possible implementation, the status assessment module uses a health index to quantitatively assess the device status, wherein the health index is calculated using the following formula: in, Equipment health index; , , The preset weighting coefficients, and ; This is a standardization factor calculated based on temperature parameters; This is a normalization factor calculated based on current parameters; Provides the real-time output power of the equipment; The power at the optimal efficiency point of the equipment under the current operating conditions; This refers to the maximum allowable power of the equipment. This is the reliability attenuation factor derived from vibration spectrum analysis; The dynamic optimization control module selects the corresponding control strategy based on the numerical range of the health index H.

[0008] In one possible implementation, the reliability degradation factor is calculated using the following formula: in, An empirical coefficient related to the type of equipment; To at characteristic frequency The amplitude of the vibration acceleration at that point; The characteristic frequencies include rotational frequency, blade passing frequency, and their harmonics.

[0009] In one possible implementation, when the high-efficiency operation mode is enabled, the dynamic optimization control module dynamically adjusts the guide vane opening and excitation current based on real-time head and load demand using an energy efficiency deviation factor. The energy efficiency deviation factor is calculated using the following formula: in, Energy efficiency deviation factor This represents the actual flow rate of the water turbine. This represents the actual net head of the power station. This represents the actual output power of the generator. This represents the standard efficiency under the current head and load combination. The dynamic optimization control module aims to minimize |Δη| and iteratively adjusts the operating parameters.

[0010] In one possible implementation, the system further includes a cooling system optimization unit connected to the condition monitoring module, used to dynamically adjust the flow rate of cooling water and the speed of the cooling fan based on the generator winding temperature and the cooling water temperature.

[0011] In one possible implementation, the pre-trained machine learning model of the state assessment module is a random forest model or a deep learning model trained based on historical operating data and fault records.

[0012] In one possible implementation, the main control system is a programmable logic controller (PLC) or a distributed control system (DCS).

[0013] In one possible implementation, the dynamic optimization control module sends a warning message to the operation and maintenance personnel before the controlled equipment enters maintenance mode or reduces load, and performs corresponding operations after receiving a confirmation instruction or after a timeout due to no response.

[0014] In a second aspect, this application provides a hydropower station energy-saving control method, applied to the hydropower station energy-saving control system provided in the first aspect, including: real-time acquisition of operating status data of generator sets and auxiliary equipment, wherein the status monitoring module includes a current transformer, a temperature sensor, a vibration sensor and a pressure transmitter; The system receives the operating status data and uses a pre-trained machine learning model to classify the device status, outputting the classification results, which include normal status, abnormal status, or fault status. Based on the classification results output by the status assessment module, corresponding control commands are generated and sent to the main control system of the power plant to perform closed-loop regulation of the operating parameters of the generator set and auxiliary equipment. When the equipment status is classified as abnormal, the generator set speed, excitation current, or the pressure and flow of auxiliary equipment are automatically adjusted. When the equipment status is classified as abnormal and involves high-energy-consuming equipment, the preset high-efficiency operation mode is activated first. When the equipment status is classified as faulty, the control equipment enters maintenance mode or performs load reduction operation in advance.

[0015] Thirdly, embodiments of this application provide a computing device, including: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the above-mentioned hydropower station energy-saving control method are implemented.

[0016] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the above-described hydropower station energy-saving control method.

[0017] Fifthly, embodiments of this application provide a computer program, wherein when the computer program is executed in a computer, it causes the computer to perform the steps of the above-described hydropower station energy-saving control method.

[0018] The technical solution provided in this application achieves a complete automated process for hydropower station equipment, from state perception to intelligent decision-making and then to closed-loop control, through the collaborative work of a state monitoring module, a state assessment module, and a dynamic optimization control module. The implementation process is as follows: First, various sensors deployed on generator sets and auxiliary equipment collect operational data in real time; then, the state assessment module uses machine learning algorithms to intelligently analyze this data, automatically identifying whether the equipment is currently in a normal, abnormal, or faulty state; finally, based on the identification result, the dynamic optimization control module directly issues precise control commands to the main control system such as PLC / DCS, automatically executing operations such as parameter adjustment, mode switching, or load reduction protection. This technical solution effectively solves the problem of fragmented monitoring and control and response lag caused by reliance on manual intervention in the background technology, realizing real-time closed-loop optimization of equipment operating status. It can proactively adjust parameters in the early stages of anomalies to avoid faults and significantly reduce energy consumption through energy efficiency mode switching, thereby comprehensively improving the reliability, economy, and intelligence level of hydropower station operation. Attached Figure Description

[0019] Figure 1 This is a schematic diagram of the structure of an energy-saving control system for a hydropower station provided in one embodiment of this application; Figure 2 This is a flowchart of an energy-saving control method for a hydropower station provided in one embodiment of this application; Figure 3 This is a structural block diagram of a computing device provided in one embodiment of this application. Detailed Implementation

[0020] Many specific details are set forth in the following description to provide a full understanding of this application. However, this application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of this application; therefore, this application is not limited to the specific embodiments disclosed below.

[0021] The terminology used in one or more embodiments of this application is for the purpose of describing particular embodiments only and is not intended to limit the scope of one or more embodiments of this application. The singular forms “a” and “the” as used in one or more embodiments of this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in one or more embodiments of this application refers to and includes any or all possible combinations of one or more associated listed items.

[0022] It should be understood that although the terms first, second, etc., may be used to describe various information in one or more embodiments of this application, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, first may also be referred to as second without departing from the scope of one or more embodiments of this application, and similarly, second may also be referred to as first. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to a determination."

[0023] This application provides an energy-saving control system and method for hydropower stations. This application also relates to a computing device, a computer-readable storage medium, and a computer program, which will be described in detail in the following embodiments.

[0024] Figure 1 A schematic diagram of the structure of an energy-saving control system for a hydropower station provided in one embodiment of this application is shown.

[0025] Reference Figure 1 As shown, the system may include: The status monitoring module 101 is installed on the generator set and auxiliary equipment of the hydropower station to collect real-time operating status data of the generator set and auxiliary equipment. The status monitoring module includes a current transformer, a temperature sensor, a vibration sensor and a pressure transmitter. The status assessment module 102 is connected to the status monitoring module to receive operating status data and classify the equipment status using a pre-trained machine learning model, and output the classification results, which include normal status, abnormal status or fault status. The dynamic optimization control module 103 is linked with the state assessment module and the main control system of the power plant. The dynamic optimization control module is configured to generate corresponding control commands based on the classification results output by the state assessment module and send them to the main control system to perform closed-loop adjustment of the operating parameters of the generator set and auxiliary equipment. The control commands include at least one of the following: When the equipment status is classified as abnormal, the generator set speed, excitation current, or auxiliary equipment pressure and flow rate are automatically adjusted. When the equipment status is classified as abnormal and involves high-energy-consuming equipment, the preset high-efficiency operation mode is activated first. When the equipment status is classified as faulty, the control equipment enters maintenance mode or performs load reduction operation in advance.

[0026] In some embodiments, the condition monitoring module 101 achieves comprehensive data acquisition by deploying various dedicated sensors at specific locations on hydropower station generator sets (such as turbines and generators) and key auxiliary equipment (such as governors, main transformers, and cooling systems): current transformers are installed in the power circuit to monitor load and efficiency changes; temperature sensors are embedded in windings and bearings to detect overheating risks; vibration sensors are fixed to the housing and bearing seats to detect signs of mechanical imbalance or loosening; and pressure transmitters are connected to the hydraulic system and water pipelines to monitor pressure anomalies. These sensors constitute a distributed sensing network, transmitting multi-dimensional condition data to the central processing unit in real time via an industrial bus. This design overcomes the limitations of traditional single-parameter monitoring, providing a high-precision and high-reliability data foundation for subsequent condition assessment through simultaneous measurement of multiple physical quantities. It achieves a technological leap from "local sensing" to "comprehensive insight" of equipment operating status, laying a solid data foundation for predictive maintenance and precise control.

[0027] In some embodiments, the system further includes a cooling system optimization unit connected to the condition monitoring module, used to dynamically adjust the cooling water flow rate and cooling fan speed based on the generator winding temperature and cooling water temperature. The cooling system optimization unit acquires real-time temperature distribution and heat exchange temperature difference data through temperature sensors embedded in the generator stator winding and cooler inlet and outlet, and dynamically calculates the optimal heat dissipation requirements based on a built-in heat balance model and PID control algorithm. This unit changes the cooling water flow rate by adjusting the opening of the electric regulating valve, and simultaneously controls the cooling fan speed through a frequency converter, ensuring that the cooling intensity precisely matches the actual heat load of the generator. This design breaks through the traditional coarse-grained mode of constant power operation of cooling systems, achieving precise cooling on demand. While ensuring the safe operating temperature of the generator, it significantly reduces the energy consumption of auxiliary equipment and effectively solves the problems of "overcooling" or "undercooling" caused by seasonal changes and load variations in equipment.

[0028] In some embodiments, the condition assessment module receives multi-dimensional sensor data streams uploaded by the condition monitoring module in real time via an industrial communication network. First, it performs standardized filtering and outlier removal preprocessing on the raw data such as current, temperature, vibration, and pressure. Then, it uses a pre-trained machine learning model (such as a random forest classifier trained on historical data) to perform deep feature mining and pattern recognition on the preprocessed data. This module constructs a dynamic decision boundary by analyzing the statistical characteristics (such as variance and kurtosis), spectral characteristics (such as resonance peak energy distribution), and temporal trends (such as temperature gradient changes) of operating parameters, ultimately outputting three precise classification results: "normal state," "abnormal state," and "fault state." This implementation method overcomes the limitations of traditional threshold alarms. Through multi-feature fusion analysis and intelligent pattern recognition, it significantly improves the accuracy of equipment condition diagnosis and early warning capabilities, providing a reliable decision-making basis for the precise formulation of subsequent control strategies.

[0029] In some embodiments, when the condition assessment module performs condition classification, the extracted features include the mean, variance, and peak values ​​of operating parameters, the spectral components of fault features, and the trend of condition changes. During condition classification, the condition assessment module constructs a comprehensive diagnostic basis through multi-dimensional feature extraction: calculating the mean values ​​of operating parameters such as current and temperature to assess the overall load level, and analyzing their variance to perceive operational stability; capturing the peak values ​​of vibration signals to identify instantaneous impact events; performing fast Fourier transforms on vibration and current signals to extract the spectral components of fault features corresponding to specific fault modes such as bearing damage and air gap eccentricity; and simultaneously calculating the gradient changes of key parameters through a sliding time window to quantify their condition change trends, achieving comprehensive monitoring from static parameters to dynamic evolution. This multi-scale feature fusion method overcomes the limitations of single threshold judgment, can keenly capture early signs of equipment performance degradation, and provides high-value input features for machine learning models to distinguish different condition modes, forming the core technological foundation for achieving accurate predictive maintenance.

[0030] In some embodiments, the status assessment module uses a health index to quantitatively assess the device status, wherein the health index is calculated using the following formula: in, Equipment health index; , , The preset weighting coefficients, and ; This is a standardization factor calculated based on temperature parameters; This is a normalization factor calculated based on current parameters; Provides the real-time output power of the equipment; The power at the optimal efficiency point of the equipment under the current operating conditions; This refers to the maximum allowable power of the equipment. This is the reliability attenuation factor derived from vibration spectrum analysis; The dynamic optimization control module selects the corresponding control strategy based on the numerical range of the health index H.

[0031] The condition assessment module quantifies equipment condition by constructing a comprehensive health index. This index integrates standardized values ​​of temperature and current parameters, the deviation of real-time power from the optimal efficiency point under current operating conditions, and incorporates a reliability attenuation factor based on vibration spectrum analysis for weighted comprehensive calculation. In implementation, the system first normalizes and assigns weights to various basic parameters, then calculates the proximity of the power operating point to the ideal efficiency range, and finally converts the amplitude-frequency characteristics of specific frequency components in the vibration spectrum into reliability correction coefficients to dynamically adjust the health status. This quantitative assessment method integrates multi-dimensional heterogeneous information into a single index, overcoming the limitations of traditional single-parameter assessments. It can sensitively reflect the gradual degradation of equipment performance and capture sudden anomalies, providing accurate and intuitive decision-making basis for the dynamic optimization control module, achieving a technological leap from qualitative judgment to quantitative assessment.

[0032] In some embodiments, the reliability degradation factor is calculated using the following formula: in, An empirical coefficient related to the type of equipment; To at characteristic frequency The amplitude of the vibration acceleration at that point; The characteristic frequencies include rotational frequency, blade passing frequency, and their harmonics.

[0033] The condition assessment module quantifies the impact of mechanical condition on overall health by constructing a vibration reliability attenuation factor. In implementation, the system first collects spectral data from the equipment using vibration sensors, extracting specific characteristic frequencies related to the equipment's mechanical structure and their corresponding vibration amplitudes. Next, it calculates and sums the ratios of vibration amplitude to frequency at each characteristic frequency, effectively characterizing the different levels of harm between high-frequency weak vibrations and low-frequency severe vibrations. Finally, it introduces an empirical coefficient related to the equipment type to calibrate this accumulated value and maps it to a reliability attenuation factor between 0 and 1 through a reciprocal transformation. This process transforms complex spectral characteristics into intuitive reliability indicators, enabling sensitive identification of early signs of mechanical failures such as bearing wear and rotor imbalance. This allows health assessment to not only focus on electrical and thermal parameters but also deeply integrate mechanical vibration characteristics, significantly improving the comprehensiveness of condition assessment and the advance warning of failures.

[0034] In some embodiments, the machine learning model pre-trained by the state assessment module is a random forest model or a deep learning model trained based on historical operating data and fault records.

[0035] In some embodiments, the dynamic optimization control module acts as the decision-making and execution center of the system, establishing a bidirectional data link with the status assessment module and the power plant main control system through a standard industrial communication protocol. Its implementation process involves continuously receiving equipment status classification results from the status assessment module. Through a built-in expert knowledge base and strategy mapping table, it transforms abstract judgments such as "normal state," "abnormal state," and "fault state" into specific equipment control commands. Specifically, when an abnormal state is detected, it automatically generates parameter adjustment commands and sends them to the PLC / DCS system to adjust the unit speed and excitation current in real time. When an energy efficiency anomaly is diagnosed, it immediately triggers a high-efficiency operation mode switching command. When fault symptoms are detected, it generates load reduction or shutdown protection commands. This process forms a closed-loop control loop of "status perception - intelligent decision-making - precise execution," completely changing the traditional lagging control mode that relies on manual judgment. It achieves adaptive linkage between equipment operating status and the control system, effectively improving the automation level and safety reliability of hydropower station operation.

[0036] In some embodiments, when the high-efficiency operation mode is enabled, the dynamic optimization control module dynamically adjusts the guide vane opening and excitation current based on real-time head and load demand using an energy efficiency deviation factor. The energy efficiency deviation factor is calculated using the following formula: in, Energy efficiency deviation factor This represents the actual flow rate of the water turbine. This represents the actual net head of the power station. This represents the actual output power of the generator. This represents the standard efficiency under the current head and load combination. The dynamic optimization control module aims to minimize |Δη| and iteratively adjusts the operating parameters.

[0037] The dynamic optimization control module achieves precise optimization of the operating efficiency of the hydro-generator unit by constructing an energy efficiency deviation factor. This module acquires real-time data on the turbine's actual flow rate, the power station's actual net head, the generator's actual output power, and the standard efficiency value corresponding to the current operating condition. It then quantitatively compares the actual hydropower conversion efficiency with the theoretical optimal efficiency to calculate the degree of energy efficiency deviation. With the goal of eliminating this deviation, the system continuously fine-tunes the guide vane opening and excitation current through a closed-loop control algorithm, ensuring the unit always operates within its optimal efficiency range. This process transforms the traditional fixed-parameter operation mode into an adaptive adjustment mode based on real-time efficiency calculation, effectively solving the efficiency deviation problem caused by head fluctuations and load changes, significantly improving hydropower conversion efficiency, and maximizing power generation benefits.

[0038] In some embodiments, the main control system is a programmable logic controller (PLC) or a distributed control system (DCS).

[0039] In some embodiments, the dynamic optimization control module sends a warning message to maintenance personnel before the controlled equipment enters maintenance mode or reduces load operation, and performs corresponding operations upon receiving a confirmation instruction or after a timeout due to no response. Before determining that maintenance mode or reduced load operation needs to be triggered based on the status assessment results, the dynamic optimization control module first sends a warning message containing equipment status details, suggested operations, and risk analysis to the monitoring terminal of maintenance personnel through an integrated communication interface, and starts a configurable countdown mechanism; the system then enters a waiting state. If a confirmation instruction is received from maintenance personnel within a set time, the corresponding operation is executed immediately; if no response is received within the timeout, authorization is granted by default and preset protective operations are automatically executed. This implementation process constructs a dual guarantee mechanism of "human supervision - automatic execution," which respects the human decision-making power of maintenance personnel while ensuring that the system can still take protective measures autonomously when personnel fail to respond in a timely manner. This effectively solves the problem of fault escalation caused by delayed human response in traditional systems and significantly improves the reliability of equipment safety protection.

[0040] See Figure 2 , Figure 2 A flowchart of an energy-saving control method for a hydropower station according to an embodiment of this application is shown, which specifically includes the following steps.

[0041] Step 201: Real-time acquisition of operating status data of generator set and auxiliary equipment. The status monitoring module includes current transformer, temperature sensor, vibration sensor and pressure transmitter. Step 202: Receive the operating status data, and use a pre-trained machine learning model to classify the device status, and output the classification results, which include normal status, abnormal status or fault status. Step 203: Based on the classification results output by the status assessment module, generate corresponding control commands and send them to the main control system of the power station to perform closed-loop adjustment of the operating parameters of the generator set and auxiliary equipment; Step 204: When the equipment status is classified as abnormal, automatically adjust the speed of the generator set, the excitation current, or the pressure and flow of the auxiliary equipment; Step 205: When the equipment status is classified as abnormal and involves high-energy-consuming equipment, the preset high-efficiency operation mode is activated first. Step 206: When the equipment status is classified as a fault state, the control equipment enters maintenance state in advance or performs load reduction operation.

[0042] In one possible implementation, when performing state classification, the extracted features include the mean, variance, and peak values ​​of operating parameters, the spectral components of fault features, and the state change trend.

[0043] In one possible implementation, a health index is used to quantitatively assess the device status, wherein the health index is calculated using the following formula: in, Equipment health index; , , The preset weighting coefficients, and ; This is a standardization factor calculated based on temperature parameters; This is a normalization factor calculated based on current parameters; Provides the real-time output power of the equipment; The power at the optimal efficiency point of the equipment under the current operating conditions; This refers to the maximum allowable power of the equipment. This is the reliability attenuation factor derived from vibration spectrum analysis; The dynamic optimization control module selects the corresponding control strategy based on the numerical range of the health index H.

[0044] In one possible implementation, the reliability degradation factor is calculated using the following formula: in, An empirical coefficient related to the type of equipment; To at characteristic frequency The amplitude of the vibration acceleration at that point; The characteristic frequencies include rotational frequency, blade passing frequency, and their harmonics.

[0045] In one possible implementation, when the high-efficiency operation mode is enabled, the guide vane opening and excitation current are dynamically adjusted based on real-time head and load demand using an energy efficiency deviation factor, wherein the energy efficiency deviation factor is calculated using the following formula: in, Energy efficiency deviation factor This represents the actual flow rate of the water turbine. This represents the actual net head of the power station. This represents the actual output power of the generator. This represents the standard efficiency under the current head and load combination. The dynamic optimization control module aims to minimize |Δη| and iteratively adjusts the operating parameters.

[0046] In one possible implementation, the flow rate of the cooling water and the speed of the cooling fan are dynamically adjusted based on the generator winding temperature and the cooling water temperature.

[0047] In one possible implementation, the pre-trained machine learning model is a random forest model or a deep learning model trained based on historical operating data and fault records.

[0048] In one possible implementation, a warning message is sent to maintenance personnel before the control equipment enters maintenance mode or operates under reduced load, and corresponding operations are performed after receiving a confirmation instruction or after a timeout due to no response.

[0049] In a second aspect, this application provides a hydropower station energy-saving control method, applied to the hydropower station energy-saving control system provided in the first aspect, including: real-time acquisition of operating status data of generator sets and auxiliary equipment, wherein the status monitoring module includes a current transformer, a temperature sensor, a vibration sensor and a pressure transmitter; The system receives the operating status data and uses a pre-trained machine learning model to classify the device status, outputting the classification results, which include normal status, abnormal status, or fault status. Based on the classification results output by the status assessment module, corresponding control commands are generated and sent to the main control system of the power plant to perform closed-loop regulation of the operating parameters of the generator set and auxiliary equipment. When the equipment status is classified as abnormal, the generator set speed, excitation current, or the pressure and flow of auxiliary equipment are automatically adjusted. When the equipment status is classified as abnormal and involves high-energy-consuming equipment, the preset high-efficiency operation mode is activated first. When the equipment status is classified as faulty, the control equipment enters maintenance mode or performs load reduction operation in advance.

[0050] Figure 3 A structural block diagram of a computing device 300 according to an embodiment of this application is shown. The components of the computing device 300 include, but are not limited to, a memory 310 and a processor 320. The processor 320 is connected to the memory 310 via a bus 330, and a database 350 is used to store data.

[0051] The computing device 300 also includes an access device 340, which enables the computing device 300 to communicate via one or more networks 360. Examples of these networks include Public Switched Telephone Network (PSTN), Local Area Network (LAN), Wide Area Network (WAN), Personal Area Network (PAN), or combinations of communication networks such as the Internet. The access device 340 may include one or more of any type of wired or wireless network interface (e.g., a network interface card (NIC)), such as an IEEE 802.11 Wireless Local Area Network (WLAN) wireless interface, a Wi-MAX (Worldwide Interoperability for Microwave Access) interface, an Ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a Bluetooth interface, or a Near Field Communication (NFC) interface.

[0052] In one embodiment of this application, the aforementioned components of the computing device 300 and Figure 3 Other components, not shown, can also be connected to each other, for example, via a bus. It should be understood that... Figure 3 The block diagram of the computing device shown is for illustrative purposes only and is not intended to limit the scope of this application. Those skilled in the art can add or replace other components as needed.

[0053] The computing device 300 can be any type of stationary or mobile computing device, including mobile computers or mobile computing devices (e.g., tablet computers, personal digital assistants, laptop computers, notebook computers, netbooks, etc.), mobile phones (e.g., smartphones), wearable computing devices (e.g., smartwatches, smart glasses, etc.) or other types of mobile devices, or stationary computing devices such as desktop computers or personal computers (PCs). The computing device 300 can also be a mobile or stationary server.

[0054] The processor 320 is configured to execute the following computer-executable instructions, which, when executed by the processor, implement the steps of the aforementioned hydropower station energy-saving control method. The above is an illustrative scheme of a computing device according to this embodiment. It should be noted that the technical solution of this computing device and the technical solution of the aforementioned hydropower station energy-saving control method belong to the same concept. Details not described in detail in the technical solution of the computing device can be found in the description of the technical solution of the aforementioned hydropower station energy-saving control method.

[0055] An embodiment of this application also provides a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the above-described hydropower station energy-saving control method.

[0056] The above is an illustrative scheme of a computer-readable storage medium according to this embodiment. It should be noted that the technical solution of this storage medium belongs to the same concept as the technical solution of the above-described hydropower station energy-saving control method. For details not described in detail in the technical solution of the storage medium, please refer to the description of the technical solution of the above-described hydropower station energy-saving control method.

[0057] An embodiment of this application also provides a computer program, wherein when the computer program is executed in a computer, it causes the computer to perform the steps of the above-described hydropower station energy-saving control method.

[0058] The above is an illustrative scheme of a computer program according to this embodiment. It should be noted that the technical solution of this computer program and the technical solution of the above-described hydropower station energy-saving control method belong to the same concept. For details not described in detail in the technical solution of the computer program, please refer to the description of the technical solution of the above-described hydropower station energy-saving control method.

[0059] The foregoing has described specific embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired results. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0060] The computer instructions include computer program code, which may be in the form of source code, object code, executable file, or certain intermediate forms. The computer-readable medium may include any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium may be appropriately added to or subtracted according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media may not include electrical carrier signals and telecommunication signals.

[0061] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments of this application are not limited to the described order of actions, because according to the embodiments of this application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the embodiments of this application.

[0062] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0063] The preferred embodiments disclosed above are merely illustrative of this application. The optional embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. Clearly, many modifications and variations can be made based on the embodiments of this application. These embodiments are selected and specifically described in this application to better explain the principles and practical applications of the embodiments of this application, thereby enabling those skilled in the art to better understand and utilize this application. This application is limited only by the claims and their full scope and equivalents.

Claims

1. An energy-saving control system for a hydropower station, characterized in that, include: A status monitoring module is installed on the generator sets and auxiliary equipment of the hydropower station to collect real-time operating status data of the generator sets and auxiliary equipment. The status monitoring module includes a current transformer, a temperature sensor, a vibration sensor, and a pressure transmitter. The status assessment module is communicatively connected to the status monitoring module. It is used to receive the operating status data, classify the equipment status using a pre-trained machine learning model, and output the classification results, which include normal status, abnormal status, or fault status. The dynamic optimization control module is linked with the state assessment module and the power plant's main control system. The dynamic optimization control module is configured to generate corresponding control commands based on the classification results output by the state assessment module and send them to the main control system to perform closed-loop adjustment of the operating parameters of the generator set and auxiliary equipment. The control commands include at least one of the following: When the equipment status is classified as abnormal, the generator set speed, excitation current, or the pressure and flow of auxiliary equipment are automatically adjusted. When the equipment status is classified as abnormal and involves high-energy-consuming equipment, the preset high-efficiency operation mode is activated first. When the equipment status is classified as faulty, the control equipment enters maintenance mode or performs load reduction operation in advance.

2. The method according to claim 1, characterized in that, When the state assessment module performs state classification, the extracted features include the mean, variance, and peak values ​​of operating parameters, the spectral components of fault features, and the state change trend.

3. The method according to claim 1, characterized in that, The status assessment module uses a health index to quantitatively assess the equipment status, wherein the health index is calculated using the following formula: in, Equipment health index; , , The preset weighting coefficients, and ; This is a standardization factor calculated based on temperature parameters; This is a normalization factor calculated based on current parameters; Provides the real-time output power of the equipment; The power at the optimal efficiency point of the equipment under the current operating conditions; This refers to the maximum allowable power of the equipment. This is the reliability attenuation factor derived from vibration spectrum analysis; The dynamic optimization control module selects the corresponding control strategy based on the numerical range of the health index H.

4. The method according to claim 3, characterized in that, The reliability attenuation factor is calculated using the following formula: in, An empirical coefficient related to the type of equipment; To at characteristic frequency The amplitude of the vibration acceleration at that point; The characteristic frequencies include rotational frequency, blade passing frequency, and their harmonics.

5. The method according to claim 1, characterized in that, When the high-efficiency operation mode is activated, the dynamic optimization control module dynamically adjusts the guide vane opening and excitation current based on real-time head and load demand using an energy efficiency deviation factor. This energy efficiency deviation factor is calculated using the following formula: in, Energy efficiency deviation factor This represents the actual flow rate of the water turbine. This represents the actual net head of the power station. This represents the actual output power of the generator. This represents the standard efficiency under the current head and load combination. The dynamic optimization control module aims to minimize |Δη| and iteratively adjusts the operating parameters.

6. The method according to claim 1, characterized in that, The system also includes a cooling system optimization unit connected to the condition monitoring module, which dynamically adjusts the flow rate of cooling water and the speed of cooling fans based on the generator winding temperature and cooling water temperature.

7. The method according to claim 1, characterized in that, The pre-trained machine learning model for the state assessment module is a random forest model or a deep learning model trained based on historical operating data and fault records.

8. The hydropower station energy-saving control system according to claim 1, characterized in that, The main control system is a programmable logic controller (PLC) or a distributed control system (DCS).

9. The hydropower station energy-saving control system according to claim 1, characterized in that, Before the controlled equipment enters maintenance mode or reduces load, the dynamic optimization control module sends a warning message to the operation and maintenance personnel, and performs corresponding operations after receiving a confirmation instruction or after a timeout due to no response.

10. A method for energy-saving control of a hydropower station, characterized in that, The method, applied to the hydropower station energy-saving control system according to any one of claims 1-9, comprises: The real-time acquisition of operating status data of generator sets and auxiliary equipment, the status monitoring module includes a current transformer, a temperature sensor, a vibration sensor and a pressure transmitter; The system receives the operating status data and uses a pre-trained machine learning model to classify the device status, outputting the classification results, which include normal status, abnormal status, or fault status. Based on the classification results output by the status assessment module, corresponding control commands are generated and sent to the main control system of the power plant to perform closed-loop regulation of the operating parameters of the generator set and auxiliary equipment. When the equipment status is classified as abnormal, the generator set speed, excitation current, or the pressure and flow of auxiliary equipment are automatically adjusted. When the equipment status is classified as abnormal and involves high-energy-consuming equipment, the preset high-efficiency operation mode is activated first. When the equipment status is classified as faulty, the control equipment enters maintenance mode or performs load reduction operation in advance.

Images