Hydroelectric generating set active power intelligent adjusting system based on remote centralized control

Abstract

The invention provides a hydroelectric generating set active power intelligent adjusting system based on remote centralized control. The hydroelectric generating set active power intelligent adjusting system comprises a communication module and a control module. The communication module receives a real-time active power target value from the remote centralized control system and various real-time operation data of the hydroelectric generating set, wherein the real-time operation data are regularly collected through a sensor. Wherein communication connection is established between the communication module and a remote centralized control system, a remote instruction packet is interacted through a predetermined communication protocol, and the remote instruction packet carries the real-time active power target value; the control module carries out rapid dynamic adjustment response based on the received real-time active power target value and various real-time operation data of the hydraulic turbine set so as to ensure the adjustment precision; and the control module continuously optimizes a control strategy of a hydroelectric generating set control model through an online self-learning algorithm to realize effective following of a power grid instruction. Through the scheme of the embodiment of the invention, the problem of how to realize real-time response and stable control on the active power of the hydroelectric generating set by a remote centralized control system can be solved.

Description

Technical Field

[0001] The present application relates to the technical field of hydropower generation, and in particular to an intelligent active power regulation system for hydropower units based on remote centralized control. Background Art

[0002] For the intelligent regulation system of active power of hydropower units based on remote centralized control, the system integrates advanced sensor technology, communication network and intelligent control algorithm to realize remote intelligent regulation of active power of hydropower units. This technology aims to improve the operation efficiency and automation level of power stations, making dispatch more accurate, thus ensuring that hydropower stations can more flexibly adapt to changes in power grid demand.

[0003] There are challenges in the implementation of the system, especially the time delay required for the control signal of the remote centralized control system to be transmitted to the hydropower unit. This problem may cause the hydropower unit to be unable to respond quickly and accurately to remote control instructions, which may affect the stability and safety of the system in some cases. Solving this challenge requires improving the reliability and bandwidth of the communication system, while optimizing the control logic to ensure that the real-time and accurate adjustment of active power can be achieved in any environment. Summary of the invention

[0004] In view of this, an embodiment of the present invention provides an intelligent active power regulation system for a hydropower unit based on remote centralized control, which at least partially solves the problems existing in the prior art.

[0005] In a first aspect, an embodiment of the present invention provides an intelligent active power regulation system for a hydropower unit based on remote centralized control, comprising: a communication module and a control module;

[0006] The communication module receives the real-time active power target value from the remote centralized control system and various real-time operating data of the hydropower unit collected regularly by sensors;

[0007] Wherein, a communication connection is established between the communication module and the remote centralized control system, and a remote instruction packet is exchanged through a predetermined communication protocol, wherein the remote instruction packet carries the real-time active power target value;

[0008] The control module performs fast dynamic regulation response based on the received real-time active power target value and various real-time operating data of the turbine unit to ensure regulation accuracy;

[0009] The control module uses an online self-learning algorithm to continuously optimize the unit control strategy to effectively follow the grid instructions.

[0010] In a specific implementation of the first aspect, the specific steps of the control module performing a fast dynamic adjustment response based on the received real-time active power target value include:

[0011] Based on the deviation and the working status information of the turbine unit, the water intake of the turbine is adjusted to achieve instant fine-tuning of the active power;

[0012] The deviation is the deviation between the actual active power of the hydro-turbine unit and the real-time active power target value, and the working status information of the hydro-turbine unit is obtained by analyzing various real-time operating data of the hydro-turbine unit received;

[0013] Start the PID control algorithm to test the instant fine-tuning effect, and make adjustments based on the test results to ensure that the deviation is controlled within the preset range.

[0014] In a specific implementation of the first aspect, the specific steps of the control module adjusting the water intake of the turbine to achieve instant fine-tuning of the active power include:

[0015] When the deviation exceeds the set first power change threshold, a fast gain adjustment mechanism is started to calculate the current capacity utilization rate CUR of the computer group;

[0016] If the current capacity utilization rate CUR is less than the capacity safety limit, the water volume increase rate is increased; and if the current capacity utilization rate CUR is greater than the capacity safety limit, the control module reduces the water volume reduction rate;

[0017] When the unit capacity utilization rate CUR is less than the capacity overload limit, the opening of the regulating valve of the hydropower unit is controlled in combination with whether the deviation exceeds the zero value;

[0018] After implementing the above steps, recalculate the new deviation and compare the new deviation with the allowable deviation range to verify the real-time fine-tuning effect.

[0019] In a specific implementation of the first aspect, the specific steps of the control module increasing the water volume increase rate and decreasing the water volume decrease rate include:

[0020] Obtain the maximum capacity and actual operating capacity of the hydropower unit and calculate the capacity ratio CUR, where the capacity ratio CUR is equal to the ratio of the actual operating capacity divided by the maximum capacity;

[0021] If the capacity ratio CUR is less than 7, the water control ratio WRC is set to 3 times the capacity ratio CUR to linearly increase the water supply rate; and when the capacity ratio CUR is greater than 9, the water control ratio WRC is set to 02 times the capacity ratio CUR to linearly reduce the water supply rate to ensure stability and safety;

[0022] After the water supply control ratio is adjusted, the new water level H is calculated, and the influence of water volume change on the water level is estimated using the formula: ΔH = (PWR*ΔT*WRC), where PWR is the water volume coefficient required for unit water level rise of the turbine, and ΔT is the adjustment period;

[0023] The stability under the new setting is confirmed based on the relationship between ΔH and the lower limit RWH_min and upper limit RWH_max within the allowable fluctuation range. If |ΔH|<|RWH_min| and |ΔH|≤RWHmax, it means that the new setting meets the regulation requirements. Otherwise, the water level needs to be adjusted according to the actual situation to ensure system stability.

[0024] In a specific implementation of the first aspect, the specific steps of the control module performing a rapid dynamic adjustment response based on the received real-time operating data of the hydro-turbine unit include:

[0025] Based on various real-time operating data of the hydro-turbine unit, obtaining and identifying whether the active power command change rate exceeds a set threshold value R1;

[0026] If the active power command change rate exceeds the set threshold R1, the gain ratio P is increased or decreased based on the preset strategy to adapt to its change rate;

[0027] During the fast dynamic regulation response process, it is detected whether the stability deviation exceeds the allowable range δ. If so, the integral constant I is adjusted to ensure system stability.

[0028] In a specific implementation of the first aspect, if the active power command change rate exceeds a set threshold R1, the preset strategy includes:

[0029] By comparing ΔP 当前 Is it greater than (ΔP 历史 *β) Determine whether the current working area is in the high load change range, where ΔP 当前 is the current active power command change, ΔP 历史 is the change in active power command at a certain moment in history, β>1;

[0030] If it is in the high load change range, it is determined that the load change is large at this time, then the gain adjustment factor is calculated according to the load increment, that is, Kp = K0*(ΔP 当前 / ΔP 历史 ), where K0 and Kp are the gain adjustment factors before and after adjustment respectively;

[0031] When the calculation result of the gain adjustment factor Kp is between 1 and the preset upper limit, the gain adjustment is performed using the above calculation result.

[0032] In a specific implementation of the first aspect, if it is determined that the load change is small at this time, the process of calculating the gain adjustment factor Kp according to the load increment further includes:

[0033] If the gain adjustment factor Kp≤1 and the load change is: ΔP 当前 <=ΔP 历史 / η, Kp is set to the default minimum value Kmin, 0<η<1;

[0034] Check the calculated Kp and K min The relationship between Kp = min (K min ,Kp) value validity to ensure effective adjustment of control gain;

[0035] According to the determined relationship, the gain ratio P of the current control system is updated to the updated P = P 原 *Kp;

[0036] During the adjustment process, monitor the control system for oscillation. If over-frequency adjustment is found, reconfigure Kp to suppress fluctuations.

[0037] In a specific implementation of the first aspect, the control module further performs the following steps:

[0038] In the process of monitoring whether there is oscillation, if more than two consecutive reverse overregulations are detected, it is considered that the control system is unstable. The reverse overregulation means that the overregulation direction of the current time step is opposite to the most recent regulation direction.

[0039] If the control system is considered unstable, a stability check is triggered to calculate whether the time interval between the current time step and the most recent oscillation meets the oscillation judgment criteria;

[0040] When the interval exceeds the maximum allowed oscillation interval, the control system is considered to have no obvious instability, and the control gain strategy can be kept unchanged to continue monitoring, otherwise the control system gain ratio P is halved to reduce its fluctuation amplitude;

[0041] After the update, continue to monitor for new oscillations.

[0042] In a specific implementation of the first aspect, the control module continuously optimizes the control strategy of the hydropower unit control model through an online self-learning algorithm to effectively follow the grid instruction, including:

[0043] Field feedback data is collected at pre-set time intervals or specific events and stored in a database. The collected field feedback data is identified online to obtain the status of the hydropower unit and the changes in the power grid, and then the input variables for updating the control model of the hydropower unit are established; the correlation between system deviations and adjustment actions is analyzed to extract effective adjustment modes to form update rules for the control model of the hydropower unit; and the update rules are continuously updated using an online self-learning algorithm to improve the control strategy and achieve intelligent optimization.

[0044] In a second aspect, an embodiment of the present invention provides a computer device, including:

[0045] at least one processor; and a memory in communication with the at least one processor;

[0046] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can perform the steps of the system described in any one of the first aspect and its specific implementation methods.

[0047] In an embodiment of the present invention, there is provided an intelligent active power regulation system for a hydropower unit based on remote centralized control, comprising: a communication module and a control module; the communication module receives the real-time active power target value from the remote centralized control system and various real-time operating data of the hydropower unit collected regularly by sensors; wherein a communication connection is established between the communication module and the remote centralized control system, and a remote instruction package is exchanged through a predetermined communication protocol, wherein the remote instruction package carries the real-time active power target value; the control module performs rapid dynamic regulation response based on the received real-time active power target value and various real-time operating data of the turbine unit to ensure regulation accuracy; the control module continuously optimizes the unit control strategy through an online self-learning algorithm to achieve effective following of power grid instructions. Through the above technical scheme of the embodiment of the present invention, it is possible to solve the problem of how to solve the real-time response and stable control of the active power of the hydropower unit by the remote centralized control system. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions of the exemplary implementation methods of the embodiments of the present disclosure, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the embodiments of the present disclosure and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0049] Figure 1 A system schematic diagram of an intelligent active power regulation system for a hydropower unit based on remote centralized control in an embodiment of the present invention;

[0050] Figure 2 A control flow diagram of an intelligent regulation system for active power of a hydropower unit based on remote centralized control in an embodiment of the present invention;

[0051] Figure 3 A schematic diagram of a control flow of a control module in an embodiment of the present invention that performs a fast dynamic adjustment response based on a received real-time active power target value;

[0052] Figure 4 A schematic diagram of a control flow in which a control module adjusts the water intake of a turbine to achieve instant fine-tuning of active power in an embodiment of the present invention;

[0053] Figure 5 A schematic diagram of a control flow of a control module in an embodiment of the present invention for increasing the rate at which water volume is increased and decreasing the rate at which water volume is decreased;

[0054] Figure 6 A schematic diagram of a control flow in which a control module in an embodiment of the present invention performs a rapid dynamic adjustment response based on various real-time operating data of a water turbine unit received;

[0055] Figure 7 A control flow diagram of a preset strategy if the active power instruction change rate exceeds a set threshold R1 in an embodiment of the present invention;

[0056] Figure 8 A schematic diagram of a flow chart of calculating a gain adjustment factor Kp according to a load increment in an embodiment of the present invention;

[0057] Fig. 9 FIG. 4 is a schematic diagram of the structure of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0059] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0060] The intelligent regulation system of active power of hydropower units based on remote centralized control is an advanced technical solution, which aims to improve the responsiveness and efficiency of hydropower plants to grid dispatch. The construction of the whole system consists of multiple interconnected parts, and the whole process from receiving instructions to final regulation has been carefully designed and intelligently processed.

[0061] In order to deeply explore the intelligent active power regulation system of hydropower units based on remote centralized control, this section will introduce in detail the various components of the system and their collaborative working mechanism. The system is mainly divided into two parts: communication module and control module.

[0062] like Figure 1 As shown, the intelligent active power regulation system 10 of the hydropower unit based on remote centralized control in the embodiment of the present invention includes a communication module 101 and a control module 102, wherein a communication connection is established between the communication module 101 and the remote centralized control system, and remote instruction packets are exchanged through a predetermined communication protocol, and the remote instruction packets carry real-time active power target values.

[0063] like Figure 2 As shown, the specific steps of intelligent regulation of the intelligent regulation system of active power of hydropower units based on remote centralized control in the embodiment of the present invention include:

[0064] Step S201: The communication module receives the real-time active power target value from the remote centralized control system and various real-time operation data of the hydropower unit collected regularly by sensors.

[0065] In the system 10, the communication module 101 plays the role of a link. Its primary responsibility is to send and receive information through a stable network connection. The information here includes the real-time active power instructions sent by the remote control center and various operating parameters collected by the on-site units. Specifically, when the remote instruction arrives, it will contain the real-time active power target required to be achieved by the hydropower unit. This process is similar to an automated system that performs corresponding adjustments after receiving an operation instruction. At the same time, the sensor transmits the collected relevant information back through this process, such as head height, flow rate, power at the generator outlet, etc. For example, in a typical scenario, assuming that the power grid dispatch requires an increase in the output of the hydropower unit in order to cope with load fluctuations in the power grid, the control center will send the corresponding instruction package to the communication module located at the hydropower station. The instructions are correctly received and interpreted to ensure that the information can be delivered in a short time and provide the necessary input conditions for control decisions.

[0066] Step S202: The control module performs a rapid dynamic adjustment response based on the received real-time active power target value and various real-time operating data of the turbine unit to ensure the adjustment accuracy.

[0067] Step S203: The control module continuously optimizes the control strategy of the hydropower unit control model through an online self-learning algorithm to effectively follow the grid instructions.

[0068] Next, another important functional part of the system 10 is introduced, the control module 102, which is responsible for the control process of the core of the entire system. After receiving the instruction, the adjustment signal is quickly generated according to the pre-set strategy and real-time monitoring data. It is worth noting that the online self-learning algorithm behind this can continuously learn and optimize the control model, so that the controller can make feedback adjustments more accurately and timely to ensure that the output is stable and meets the demand level without excessive fluctuations. For example, taking the example mentioned above as a case, the water machine control system begins to adjust the unit speed or valve state (such as increasing the opening of the water guide blade to allow more water to flow through the water wheel to increase power production) after receiving the task of increasing the output, so as to achieve the goal of the predetermined task while ensuring that the operation within the hydraulic safety boundary does not damage the equipment. As time goes by and data is continuously accumulated, optimized and updated, these dynamically changing parameters are recorded for reference in the same working conditions in the future, making the operation more intelligent and efficient, reducing the probability of human misjudgment and reducing the risk.

[0069] In summary, such an intelligent turbine regulation system solves the previous problem of how to remotely control the power station to quickly and accurately control the power generation efficiency of the turbine to support the changing power energy balance regulation task. It constitutes the entire solution architecture by establishing an effective two-way communication platform and introducing intelligent optimization calculation logic; on the one hand, it can effectively transmit command information to quickly reach the terminal site and make accurate responses to perform corresponding work actions; on the other hand, it can collect the on-site environmental conditions in real time and make corresponding changes and adjustments in time to ensure the smooth and orderly operation of the system, realizing the efficient, safe and reliable operation of large-scale water conservancy equipment groups in remote conditions.

[0070] Next, the specific steps of the control module for performing a fast dynamic adjustment response based on the received real-time active power target value are described, such as Figure 3 As shown, including:

[0071] Step S301: Based on the deviation and the working status information of the turbine unit, adjust the water intake of the turbine to achieve real-time fine-tuning of the active power.

[0072] Based on the deviation and the working status information of the turbine unit, the water intake of the turbine is adjusted to achieve instant fine-tuning of the active power; this step first requires measuring the current active power of the turbine and comparing it with the real-time active power target value obtained from the power system operation center to obtain the deviation. At the same time, this step will also consider the operating status of the turbine itself, such as vibration, speed and other data to determine the optimal proportion of adjusting the water intake. For example, if the actual power is lower than the set 350MW and the target is 380MW, and the system detects that the turbine unit is in a low load stable state, the control system will increase the water flow until it reaches or is closer to the target output power.

[0073] Among them, the deviation is the deviation between the actual active power of the turbine unit and the real-time active power target value. The working status information of the turbine unit is obtained by analyzing the real-time operating data of the received hydropower unit; this process emphasizes how to calculate and obtain these two parameters. For example, when the system finds that the power is only 300MW in the real-time data collected by the system but is required to reach 400MW, the system can calculate the deviation as -100MW (the actual value is lower than expected); combined with the status monitoring of other parameters such as temperature and pressure, it comprehensively judges whether adjustment is required and the specific adjustment range. If the temperature is normal, but the water inlet pressure is low, the system will increase the water inlet speed by increasing the opening of the water supply valve and then increase the power output to the predetermined value (400MW in this example).

[0074] Step S302: Start the PID control algorithm to test the instant fine-tuning effect, and make adjustments based on the test results to ensure that the deviation is controlled within a preset range.

[0075] Start the PID control algorithm to test the effect of the instant fine-tuning, and adjust according to the test results to ensure that the deviation is controlled within the preset range. Once the instant adjustment is completed, the control system will use the PID (proportional integral differential) algorithm to check the effect of this adjustment, that is, to see whether the power in the new state has reached the set point and there is no large fluctuation; if the result is satisfactory, no further operation is required, otherwise the above adjustment action (adjusting the inlet and outlet water volume) will be repeated until the error reaches an acceptable level or meets the requirements of safe operation. For example, according to the PID feedback, the actual power has been increased to the required 400MW and the system has been stable for one hour without large fluctuations, then the adjustment can be considered to be completed.

[0076] These specific steps help keep the hydropower plant's active output accurately tracking target requirements.

[0077] Next, the specific steps of adjusting the water intake of the turbine by the control module to achieve instant fine-tuning of the active power are described, such as Figure 4 As shown, including:

[0078] Step S401: When the deviation exceeds a set first power change threshold, a fast gain adjustment mechanism is started to calculate a current capacity utilization rate CUR of the computer group.

[0079] During the adjustment process, the first condition is to detect a large difference between the output power and its target or reference value, that is, the deviation exceeds the set first power change threshold.

[0080] When the deviation exceeds this threshold, the system's fast gain adjustment mechanism will be activated, which is the first link of instant fine-tuning, and its purpose is to intervene in the power generation unit with a faster response. For example, if the first power change threshold is set to ±10MW, and the difference between the actual active power currently observed and the target power commanded by the dispatching center exceeds this value, the control system will be triggered to perform further operations.

[0081] Step S402: if the current capacity utilization rate CUR is less than the capacity safety limit, the water volume increase rate is increased; and if the current capacity utilization rate CUR is greater than the capacity safety limit, the control module reduces the water volume reduction rate.

[0082] At this stage, the turbine's current capacity utilization rate (CUR) is evaluated - this value reflects the amount of water currently used by the generator and the proportion of the power generation capacity generated to its total design capacity. Continuing with the previous example, assume that the current actual power is different from the expected value. For example, if the actual utilization rate of the turbine generator at this point in time is 80%, then further evaluation of the current operation is needed to take appropriate measures to adjust the water volume.

[0083] Once the data of the current unit capacity utilization rate is obtained and compared with the set safety utilization rate standard: if the capacity safety limit is set to 90%, if the current utilization rate is less than 90%, it means that there is room to increase the water volume to increase the output power. At this time, the control system will increase the incremental rate of water volume regulation. For example, in the above scenario (current utilization rate is 80%), the control unit will increase the valve opening rate to quickly introduce more water and accelerate the production rate of active power; if the current utilization rate is close to full load operation, the process of controlling the water volume reduction will become slower to ensure that there will be no significant fluctuation or decrease in active power due to excessive slowing of the water volume.

[0084] Step S403: When the unit capacity utilization rate CUR is less than the capacity overload limit, the opening of the regulating valve of the hydropower unit is controlled in combination with whether the deviation exceeds the zero value.

[0085] After completing the adjustment of the water volume, adjust the water intake of the turbine unit according to the actual situation, especially considering the capacity utilization rate and the overload limit and real-time detection of whether there is a negative difference phenomenon exceeding the target output (the deviation is less than 0). Specifically, if CUR < capacity overload limit and power deviation > zero, then increase the opening of the regulating valve appropriately, otherwise reduce the opening. For example, if the hydropower unit is equipped with a regulating valve and has fully opened it, but the actual active power still cannot meet the set requirements, and the current CUR is only 70%, this means that there is still room for further increasing the water volume, and the purpose of quickly increasing the water intake can be achieved by further increasing the valve opening angle.

[0086] Step S404: recalculate the new deviation after the above steps are implemented, and compare the new deviation with the allowable deviation range to verify the real-time fine-tuning effect.

[0087] After completing the above process, it is necessary to update the new deviation data and compare the results with the established range to verify whether the required level of fine-tuning has been reached.

[0088] This adjustment mode can be repeated repeatedly until the error between actual and demand is compressed to an acceptable range, ensuring the stable and efficient operation of the power system.

[0089] Next, the specific steps of the control module to increase the water volume increase rate and reduce the water volume decrease rate are described, such as Figure 5 As shown, including:

[0090] Step 501: Obtain the maximum capacity and actual operating capacity of the hydropower unit, and calculate the capacity ratio CUR, wherein the capacity ratio CUR is equal to the ratio of the actual operating capacity divided by the maximum capacity.

[0091] First, the maximum capacity and actual operating capacity of the hydropower unit are obtained, and the capacity ratio CUR of the two is calculated. The capacity ratio CUR reflects the efficiency level of the hydropower unit currently used - it is equal to the value obtained by dividing the actual operating capacity by the maximum capacity. For example, assuming that the actual operating capacity of the hydropower unit is 1400 MW and its maximum capacity is 2000 MW, the capacity ratio CUR is calculated as 1400 / 2000, which is 0.7.

[0092] Step 502: If the capacity ratio CUR is less than 0.7, the water control ratio WRC is set to 3 times the capacity ratio CUR to linearly increase the water supply rate; and, when the capacity ratio CUR is greater than 0.9, the water control ratio WRC is set to 0.02 times the capacity ratio CUR to linearly reduce the water supply rate to ensure stability and safety.

[0093] Then, different water control ratios WRC are set. Specifically, if the above-calculated capacity ratio CUR is less than 4.7 (obviously outside this numerical range, but understood here as a theoretical step), such as 0.7 in the above example, the water control ratio WRC is set to three times its value, that is, 2.25 (set here for the sake of example) to increase the water supply rate and further increase the power generation of the hydropower plant. On the contrary, if the capacity ratio is greater than 0.9 (still explained in terms of numerical judgment rather than specific values, because this situation is rare in actual scenarios), the water control ratio WRC is set to 0.02 times its actual capacity ratio CUR to reduce the water supply rate and ensure that the equipment does not exceed the optimal operating efficiency. For example, when the actual ratio reaches 0.99, the ratio WRC at this time should be set to 0.99*0.02=0.0198 to reduce it.

[0094] Step 503, after completing the water supply control ratio adjustment, calculate the new water level H, and use the formula: ΔH = (PWR*ΔT*WRC) to estimate the impact of water volume changes on the water level, where PWR is the water volume coefficient required for unit water level rise of the turbine, and ΔT is the adjustment period.

[0095] After that, the new water level value H after adjusting the water volume is calculated based on the above settings. According to the preset model of the effect of water volume on water level change ΔH = (PWR × ΔT × WRC), the water level change under the new setting can be estimated. The variables assumed here are: assuming that the water volume coefficient PWR is 120 liters per meter·kilowatt-hour (the example uses a numerical value, not the actual one); ΔT assumes that the setting cycle is one hour; according to the two example values ​​of WRC in the above example, the expected water level changes in the two cases are calculated, the former ΔH = (120 × 1 × 2.25) = 270 liters; the latter ΔH = (120 × 1 × 0.0198) = about 2.38 liters.

[0096] Step 504: confirm the stability under the new setting according to the relationship between ΔH and the lower limit RWH_min and the upper limit RWH_max within the allowable fluctuation range. If |ΔH|<|RWH_min| and |ΔH|≤RWHmax, it means that the new setting meets the regulation requirements. Otherwise, the water level needs to be adjusted according to the actual situation to ensure system stability.

[0097] The last step is to determine whether the adjusted settings are reasonable: according to the preset calculated actual water level change range and the upper and lower limits of the safety threshold (RWH_min is the minimum acceptable change value such as -5 liters and RWH_max represents the maximum change value of 10 liters), confirm whether the above calculated ΔH is within this range. In the above example, ΔH = 270 is far beyond the threshold of RWH_max, so it is determined that this setting is inappropriate and needs to be optimized and adjusted, while the other set of parameters is within a reasonable range.

[0098] Next, the specific steps of the control module for fast dynamic regulation response based on the real-time operating data of the received turbine unit are described. This process involves three main steps, which are in a progressive relationship with each other to cope with the regulation response requirements of the turbine generator unit in different working conditions of the hydropower station. Figure 6 As shown, including:

[0099] Step 601: Based on various real-time operating data of the hydro-turbine unit, it is obtained and identified whether the active power instruction change rate exceeds a set threshold value R1.

[0100] The control module first enters the monitoring state and receives various data sent by the sensor element in real time. The data here not only includes basic working parameters such as water flow, speed, power and other indicators, but also the internal state data of the control system itself. After obtaining these real-time information, the system needs to check the change rate of active power, one of the variables that reflects the degree of change in the current system status. The goal of this check is to determine whether the change rate is fast enough to exceed a threshold R1 preset by the system. For example, this threshold R1 is set to 0.3pu / s (pu represents full load unit) as a standard for distinguishing rapid load changes; if a command issued by the power grid dispatcher requires the system to increase the active power by 5MW / s in a short time, if the preset threshold is set at a lower value (for example, 0.1pu / s), then this change rate beyond the normal range will trigger a special response program of the electronic control system. When the change rate does reach the threshold, the next link of the system, dynamic regulation, begins to play a role.

[0101] Step 602: If the active power command change rate exceeds the set threshold R1, the gain ratio P is increased or decreased based on a preset strategy to adapt to its change rate.

[0102] If it is confirmed that the change in the command exceeds R1 (such as the increase of 5MW / s in the above example), the control logic automatically adjusts the gain ratio (i.e., the amplification factor) in the controller according to the pre-planned strategy. In the PID controller, the weight of the P part will be increased or decreased according to the current rate of change. In the above scenario, due to the high rate of change, P may be increased from the normal setting (0.6, as a reference value) to a higher setting (such as 1.2 or more), which will make the electric control system respond faster to the change in the command. For example, when the system recognizes a high load increase trend, adjusting the gain ratio to a higher value can make the system respond more promptly.

[0103] Step 603: During the fast dynamic adjustment response process, detect whether the stability deviation exceeds the allowable range δ. If so, adjust the integral constant I to ensure system stability.

[0104] The control logic then needs to continuously monitor the state of the system output during the adjustment period to verify whether the preset safety and performance goals are met, and achieve this goal by continuously adjusting the PID parameters. In this fast adjustment response stage, if it is detected that the system state has a stable deviation that exceeds the predetermined range (for example, 0.15pu in this case), it indicates that the controller's adjustment action causes the actual response of the system to be too advanced or lagging; in order to correct this problem and restore to a more ideal adjustment level, the system will modify the integral constant I in the PID (assuming that the normal situation is 0.2, when the deviation exceeds the limit, the parameter is reduced to 0.1 or even less), so as to achieve the long-term stability of the system back to the allowable range (the deviation range is restored to less than or equal to 0.1pu). For example, in the case of system over-response mentioned above (the actual power increase exceeds the command value), the system can reduce the excessive cumulative impact of the system by appropriately reducing the i component, and finally reduce the deviation to a safe range.

[0105] In summary, the control system can effectively and timely handle the power changes at different rates and amplitudes during the operation of the hydro-generator set by executing the three steps S601-S603. Such dynamic response can optimize the utilization efficiency of the equipment and maintain the stability of the system to the greatest extent, which meets the basic demands of the power industry for efficient and stable energy generation and distribution.

[0106] Next, we describe the preset strategy if the active power command change rate exceeds the set threshold R1. We first clarify the specific content and logic of each step, and then give a simple example to help understand the whole process. Figure 7 As shown, including:

[0107] Step 701: By comparing ΔP 当前Is it greater than (ΔP 历史 *β) Determine whether the current working area is in the high load change range, where ΔP 当前 is the current active power command change, ΔP 历史 is the change in active power command at a historical moment, β>1.

[0108] The first stage of the preset strategy is to determine whether the current active power is in a high-speed change state. This judgment is made by comparing the change in the current active power command ΔP 当前 The change from the previous moment ΔP 历史 Specifically, it is to see whether ΔP currently exceeds the previous change value multiplied by the coefficient β (ΔP 历史 *β), the value of β needs to be set greater than 1.

[0109] For example, if the current rate of change ΔP 当前 =3%, and the last record was 1%, then β can be taken as 1.5 as the comparison benchmark. 当前 If the calculated result exceeds 1%*1.5=1.5%, it is confirmed that the active power is in a high-speed change range. This step is to promptly detect whether the active power command changes rapidly or jumps.

[0110] Step 702: If the load is in a high-change range and it is determined that the load change is large, the gain adjustment factor is calculated according to the load increment, that is, Kp=K0*(ΔP 当前 / ΔP 历史 ), where K0 and Kp are the gain adjustment factors before and after adjustment respectively.

[0111] The second stage is to proceed to the next step when confirming that the load is in a high change, that is, to adjust the control gain factor according to the change of the active power command at the current and previous moments. The adjustment formula is Kp = K0*(ΔP 当前 / ΔP 历史 ). Here, K0 and Kp are the original and adjusted gain adjustment factors respectively.

[0112] For example, assuming that the current change ΔP is still 3% and the previous change ΔP was 1%; assuming that the original gain value K0 is set to 2000, the adjusted control parameter Kp calculated based on the above formula is Kp=2000×(3% / 1%)=6000.

[0113] Step 703: When the calculation result of the gain adjustment factor Kp is between 1 and a preset upper limit, the gain adjustment is performed using the calculation result.

[0114] The last step is to constrain the value of the control parameter Kp, allowing the gain parameter to remain within the specified effective range after adjustment, that is, between 1 and a preset upper limit value (for example, 30000). This can ensure the safety of the system and avoid the risk of overload.

[0115] Let's continue with the above example. Suppose the calculated Kp value is 6000, which is within the range, so it will be applied to the system adjustment. But if a larger value such as 35000 is calculated in another scenario, it needs to be fixed at the preset upper limit value, assuming that the preset maximum upper limit is 30000.

[0116] Such an adjustment mechanism helps to adjust the system response in a timely manner when the system load changes suddenly and maintain its overall stable operation.

[0117] Next, we will describe the process of calculating the gain adjustment factor Kp based on the load increment when it is determined that the load change is small. We can explain it in several key steps, such as Figure 8 As shown, including:

[0118] Step 801: If the gain adjustment factor Kp≤1 and the load change is: ΔP 当前 <=ΔP 历史 / η, Kp is set to the default minimum value K min , 0<η<1.

[0119] First, if the load change is detected to be smaller than before, that is, it meets the condition ΔP current < ΔP history / η (0 < η < 1), and the calculated gain adjustment factor Kp is less than or equal to 1, then Kp will be set to its lowest allowable value, which is the default minimum value Kmin. This operation is to avoid the situation where the response is not sensitive enough or the control effect is weakened due to the Kp setting being too small. Assuming that the current Kp is 0.5, ΔP history = 20KW, and η is set to 0.5, then ΔP current must be less than or equal to ΔP history / η = 40KW to apply this logic. If the condition is met, Kp is reset to Kmin.

[0120] Step 802: Verify the calculated Kp and K min The relationship between Kp = min (K min ,Kp) value validity to ensure effective adjustment of control gain.

[0121] Next, after completing the above condition checks, it is necessary to verify the relationship between the calculated new value Kp and the default value Kmin, that is, to check which of the two should be used as the valid value for the final Kp: min(Kmi n, Kp). The purpose of such verification is to ensure that Kp does not cross the boundary and that the stability of the system is not affected. If the calculated Kp is still 0.5, and Kmin is set to 0.2, then the Kp in actual use should select the smaller of the two numbers, that is, Kp = min(0.2, 0.5) = 0.2, to adjust the system parameters.

[0122] Step 803: Update the gain ratio P of the current control system according to the determined relationship to an updated P=P 原 *Kp.

[0123] Then, after verifying that the Kp value is correct, the original gain coefficient P_new is updated according to the calculation result. Here, P_new needs to be multiplied by the corrected Kp value (for example, 0.2 calculated above) to obtain the coefficient of the proportional control part of the new system. For example, P_new may be 1 initially, then the updated new P should be P_new = P_new. 原 *Kp=1*0.2=0.2.

[0124] Step 804: During the adjustment process, monitor whether the control system has oscillation phenomenon. If over-frequency adjustment is found, reconfigure Kp to suppress fluctuations.

[0125] Finally, after tuning the entire system parameters, the new settings need to be monitored in real time to determine whether they will lead to unstable behavior of the control system such as frequent fluctuations or oscillations. If these negative phenomena are observed, measures such as modifying or reconfiguring the Kp value need to be taken to stabilize the system operation and reduce unnecessary disturbances and oscillations.

[0126] Through the above steps, the work of determining, verifying and adjusting the gain adjustment factor Kp can be completed when the load changes slightly. This mechanism can improve the response performance of the system while ensuring its stable operation.

[0127] Next, the control module is described to perform the following steps: First, in the process of monitoring whether there is an oscillation phenomenon, if more than two consecutive reverse over-regulations are detected, it is considered that the control system has an unstable phenomenon, and the reverse over-regulation means that the over-regulation direction of the current time step is opposite to the regulation direction of the most recent time step; Second, if the control system is considered to be unstable, a stability check is triggered to calculate whether the time interval between the current time step and the most recent oscillation meets the oscillation judgment standard; Third, when the interval exceeds the maximum allowable oscillation interval, it is considered that the control system has no obvious instability, and the control gain strategy can be kept unchanged and continue to monitor, otherwise the gain ratio P of the control system is halved to reduce its fluctuation amplitude; Fourth, after the update, continue to monitor whether there is a new oscillation phenomenon.

[0128] The first step in the control process described above involves identifying the occurrence of an unstable condition. The control module continuously monitors the system's regulation behavior to detect any potential oscillations or instability, especially reverse overregulation. Reverse overregulation is when the current direction of the control is reversed from the previous direction (e.g., the current regulation is to increase the temperature, but the most recent regulation was to decrease it). If two or more consecutive changes of direction are detected, the controller is showing signs of unstable oscillation. For example, in a heater control system, if the current heating output changes from decreasing to increasing (the first overregulation), and then the next control changes from increasing to decreasing (the second overregulation), then the control process is considered to be unstable.

[0129] The second step involves triggering the stability check process, where the time period from the first significant oscillation point to the present is evaluated to check whether this time span meets the pre-set judgment criteria. Continuing with the previous example, if the above-mentioned continuous reverse change of the heater is found, the time T from the moment when the system first obvious over-regulation occurs to the present is compared with the set maximum allowable interval \(T_{max}\).

[0130] The third step is to determine the subsequent strategy adjustment based on the interval judgment, that is, either stick to the original strategy and continue to implement supervision, or reduce the gain ratio in the feedback parameters in the control system to slow down its oscillation. For example, if the result time difference in actual operation is greater than the specified value, such as the interval time T is greater than the preset maximum value \(T_{max}=6\text{sec}\), it can be determined that the stability of the control system is within the acceptable range, and the previous control gain can be continued to be observed. In the opposite case, action should be taken to reduce the control gain to half.

[0131] Finally, the system applies these changes and continues to monitor for possible emerging oscillations to continue to ensure the robust operation of the system.

[0132] After processing and adjusting the strategy changes (if necessary) in the previous steps, the system will continue to the next monitoring phase. During this process, the above steps are repeated to ensure the stability and performance of the entire system.

[0133] Next, the control module is described to achieve effective following of power grid instructions by continuously optimizing the control strategy of the hydropower unit control model through an online self-learning algorithm. This step mainly includes collecting feedback data from the field at predetermined time intervals or under special circumstances and storing it in a database; based on the stored data, online identifying the current status of the hydropower equipment and changes in the power network, which are used as basic input data for model updating; through in-depth analysis of the relationship between system operation errors and their adjustment actions, a set of effective adjustment modes that can optimize the system response efficiency are summarized to construct a new hydropower unit control strategy; then, with the help of an online self-learning algorithm, the above control model and the adjustment criteria contained therein are continuously updated, thereby improving the overall control strategy to make it more intelligent and adaptable.

[0134] Specifically, the process begins with the control system collecting field information, such as unit current, frequency response time, and other related data, through various sensors installed in the hydropower station according to a fixed sampling cycle or under preset conditions (such as system fault alarms, etc.). Subsequently, this information will be stored in an electronic database in the central processing system and serve as a key information source for subsequent updates of the hydropower unit model input.

[0135] For example, it can be assumed that a group of small hydropower stations consisting of hydroelectric generating devices are in operation. At this time, if a real-time control signal for increasing power generation is required to be sent to the power station, real-time feedback can be provided based on the changing trends of a series of parameters such as head pressure, flow, power generation efficiency, etc. monitored by various sensors pre-deployed in the power generation system, and such data can be saved in the database. Then, the control system will automatically analyze these dynamically collected new situations, compare and evaluate them with the established control parameters, and summarize a more reasonable set of operating specifications and principles based on their interaction mechanism as the basic solution for optimizing the logical structure of the old turbine controller. Then, advanced machine autonomous learning methods such as fuzzy control theory, neural networks or genetic algorithms are used to add the newly acquired knowledge rules to the original framework, so that the hydropower station can more accurately capture the commands from the national dispatching center and quickly respond appropriately to rapidly adjust the power output level. This series of continuous and intelligent adjustment strategies helps to significantly reduce the probability of problems such as actual execution delays caused by fluctuations in the power market, and ensure that the hydropower generator always maintains stable and reliable operating quality.

[0136] Next, this description actually involves defining a general computer device and indicating that it can perform specific tasks (such as the tasks referred to in claims 1 to 9 mentioned above). This description is common in patent documents or other technical specification documents, and is intended to specify or explain a computer configuration that includes a specific functional software system.

[0137] Specific steps and examples are as follows Fig. 9 As shown, the computer device 90 includes at least one processor 901;

[0138] This means that the computer device must be equipped with at least one processing unit to process instructions, run programs, etc. This component is usually the brain of the entire computing system, used to execute various operating instructions, manage hardware resources, control the flow of input and output data, etc.

[0139] For example, a certain device is equipped with an i7 series central processing unit manufactured by Intel, which has 8 cores and a main frequency of 2.6GHz.

[0140] and a memory 902 (storage device) communicating with the processor 901;

[0141] The description here means that there is at least one memory module near the processor or in direct communication with it. This can help the system store temporary information and quickly access the data or instructions being processed to ensure that the system can run various operating tasks smoothly and quickly.

[0142] For example, the device is equipped with a 32GB RAM memory stick, which enables the i7 series CPU to quickly read and write running program files from the memory.

[0143] The memory 902 stores instructions (software, applications, etc.), and the storage device includes not only volatile storage areas such as RAM, but also more persistent information storage media such as hard disk drives. Here, it is mentioned that these storage spaces contain various specific instructions or programs that can be executed by the processor.

[0144] For example, the hard disk is loaded with professionally designed applications written in C++ and a system-level application framework (such as the core part of the operating system, etc.), so that the entire device can work normally after startup and perform the functions of the above claims.

[0145] By describing the device in this way, we can derive a simple example - a computer workstation dedicated to high-end design work. It has powerful processing performance, efficient storage mechanism and rich software resource support environment. When the technicians operate the device, the principles and technical configurations behind it follow the three steps mentioned above: from powerful hardware facilities to efficient calling and execution of the software layer, users can smoothly run various professional applications. Such system configuration and design fully demonstrate the role of IPD (product development concept and framework) in transforming customer needs into actual products.

[0146] The intelligent active power regulation system of hydropower units based on remote centralized control of the present invention includes: an innovative system architecture and methodology to improve the operating efficiency and flexibility of hydropower stations. The system consists of two core components: a communication module and a control module. This integrated solution aims to ensure that the hydropower station can accurately and responsively execute remote instructions and optimize the performance of the power station through an intelligent learning mechanism. The operating principle of this system and the technical problems it solves are described in detail below.

[0147] The main function of this system is to build an efficient and reliable information communication platform between the hydropower unit and the remote monitoring and control system. The specific process is as follows:

[0148] 1. Receive real-time commands and data

[0149] First, through the communication module with the remote centralized control system, the system will receive the target value of the expected active power output and other control instructions from the dispatch center. These remote instructions are encapsulated in a specially designed communication package and sent to the power generation unit in accordance with the predetermined communication protocol format.

[0150] 2. Transmit and process real-time clock synchronization data

[0151] The system integrates an advanced sensor network that can collect various operating parameters (such as speed, load and temperature) in a timely manner. These real-time data will then be transmitted back to the remote control center for further analysis and decision-making.

[0152] 3. Quick response regulation control

[0153] Once the communication module receives the updated instructions or adjustment requirements, the control module in the system will immediately start analyzing the difference between the current turbine operation and the new operation standard to ensure that the system can quickly adjust the power output to the expected value. Through the built-in fast dynamic adjustment strategy, the response delay can be minimized, which can effectively improve the control accuracy and stability.

[0154] 4. Dynamic self-learning algorithm tuning

[0155] During the long-term operation, the intelligent controller will also use self-learning technology to continuously fine-tune and improve its own set of strategy rules to cope with different working conditions, thereby improving overall performance efficiency and more closely matching the requirements of the dispatching department. It can also ensure that hydropower facilities always work in their optimal operating state under complex and changing external conditions.

[0156] Through this integrated solution, we have solved the problem that hydropower facilities could not immediately feedback dispatch signals or had weak control capabilities; through continuous optimization and intelligent control, hydropower stations can reduce unnecessary losses while ensuring grid demand is met. This has greatly promoted the rapid and flexible response of the power market and the most reasonable allocation and utilization of hydropower resources, and improved the overall value creation capabilities of the entire system.

[0157] The specific implementation methods described above further illustrate the purpose, technical solutions and beneficial effects of the embodiments of the present invention. It should be understood that the above description is only a specific implementation method of the embodiments of the present invention and is not intended to limit the protection scope of the embodiments of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present invention should be included in the protection scope of the embodiments of the present invention.

Claims

1. An intelligent active power regulation system for hydropower units based on remote centralized control, characterized in that: include: Communication module and control module; The communication module receives the real-time active power target value from the remote centralized control system and various real-time operating data of the hydropower unit collected regularly by sensors; Wherein, a communication connection is established between the communication module and the remote centralized control system, and a remote instruction packet is exchanged through a predetermined communication protocol, wherein the remote instruction packet carries the real-time active power target value; The control module performs fast dynamic regulation response based on the received real-time active power target value and various real-time operating data of the turbine unit to ensure regulation accuracy; The control module uses an online self-learning algorithm to continuously optimize the control strategy of the hydropower unit control model to effectively follow the power grid instructions.

2. The system according to claim 1, characterized in that The specific steps of the control module performing a fast dynamic adjustment response based on the received real-time active power target value include: Based on the deviation and the working status information of the turbine unit, the water intake of the turbine is adjusted to achieve instant fine-tuning of the active power; The deviation is the deviation between the actual active power of the hydro-turbine unit and the real-time active power target value, and the working status information of the hydro-turbine unit is obtained by analyzing various real-time operating data of the hydro-turbine unit received; Start the PID control algorithm to test the instant fine-tuning effect, and make adjustments based on the test results to ensure that the deviation is controlled within the preset range.

3. The system according to claim 2, characterized in that The specific steps of the control module adjusting the water intake of the turbine to achieve instant fine-tuning of the active power include: When the deviation exceeds the set first power change threshold, a fast gain adjustment mechanism is started to calculate the current capacity utilization rate CUR of the computer group; If the current capacity utilization rate CUR is less than the capacity safety limit, the water volume increase rate is increased; and if the current capacity utilization rate CUR is greater than the capacity safety limit, the control module reduces the water volume reduction rate; When the unit capacity utilization rate CUR is less than the capacity overload limit, the opening of the regulating valve of the hydropower unit is controlled in combination with whether the deviation exceeds the zero value; After implementing the above steps, recalculate the new deviation and compare the new deviation with the allowable deviation range to verify the real-time fine-tuning effect.

4. The system according to claim 3, characterized in that The specific steps of the control module increasing the water volume increase rate and decreasing the water volume decrease rate include: Obtain the maximum capacity and actual operating capacity of the hydropower unit and calculate the capacity ratio CUR, where the capacity ratio CUR is equal to the ratio of the actual operating capacity divided by the maximum capacity; If the capacity ratio CUR is less than 0.7, the water control ratio WRC is set to 3 times the capacity ratio CUR to linearly increase the water supply rate; and when the capacity ratio CUR is greater than 0.9, the water control ratio WRC is set to 0.02 times the capacity ratio CUR to linearly reduce the water supply rate to ensure stability and safety; After the water supply control ratio is adjusted, the new water level H is calculated, and the influence of water volume change on the water level is estimated using the formula: ΔH = (PWR*ΔT*WRC), where PWR is the water volume coefficient required for unit water level rise of the turbine, and ΔT is the adjustment period; The stability under the new setting is confirmed based on the relationship between ΔH and the lower limit RWH_min and upper limit RWH_max within the allowable fluctuation range. If |ΔH|<|RWH_min| and |ΔH|≤RWHmax, it means that the new setting meets the regulation requirements. Otherwise, the water level needs to be adjusted according to the actual situation to ensure system stability.

5. The system according to claim 1, characterized in that The specific steps of the control module performing fast dynamic adjustment response based on the received real-time operation data of the turbine group include: Based on various real-time operating data of the hydro-turbine unit, obtaining and identifying whether the active power command change rate exceeds a set threshold value R1; If the active power command change rate exceeds the set threshold R1, the gain ratio P is increased or decreased based on the preset strategy to adapt to its change rate; During the fast dynamic regulation response process, it is detected whether the stability deviation exceeds the allowable range δ. If so, the integral constant I is adjusted to ensure system stability.

6. The system according to claim 5, characterized in that If the active power command change rate exceeds the set threshold R1, the preset strategy includes: By comparing ΔP 当前 Is it greater than (ΔP 历史 *β) Determine whether the current working area is in the high load change range, where ΔP 当前 is the current active power command change, ΔP 历史 is the change in active power command at a certain moment in history, β>1; If it is in the high load change range, it is determined that the load change is large at this time, then the gain adjustment factor is calculated according to the load increment, that is, Kp = K0*(ΔP 当前 / ΔP 历史 ), where K0 and Kp are the gain adjustment factors before and after adjustment respectively; When the calculation result of the gain adjustment factor Kp is between 1 and the preset upper limit, the gain adjustment is performed using the above calculation result.

7. The system according to claim 6, characterized in that If it is determined that the load change is small at this time, the process of calculating the gain adjustment factor Kp according to the load increment also includes: If the gain adjustment factor Kp≤1 and the load change is: ΔP 当前 <=ΔP 历史 / η, Kp is set to the default minimum value K min , 0<η<1; Check the calculated Kp and K min The relationship between Kp = min (K min ,Kp) value validity to ensure effective adjustment of control gain; According to the determined relationship, the gain ratio P of the current control system is updated to the updated P = P 原 *Kp; During the adjustment process, monitor the control system for oscillation. If over-frequency adjustment is found, reconfigure Kp to suppress fluctuations.

8. The system according to claim 7, characterized in that The control module also performs the following steps: In the process of monitoring whether there is oscillation, if more than two consecutive reverse overregulations are detected, it is considered that the control system is unstable. The reverse overregulation means that the overregulation direction of the current time step is opposite to the most recent regulation direction. If the control system is considered unstable, a stability check is triggered to calculate whether the time interval between the current time step and the most recent oscillation meets the oscillation judgment criteria; When the interval exceeds the maximum allowed oscillation interval, the control system is considered to have no obvious instability, and the control gain strategy can be kept unchanged to continue monitoring, otherwise the control system gain ratio P is halved to reduce its fluctuation amplitude; After the update, continue to monitor for new oscillations.

9. The system according to claim 1, characterized in that The control module continuously optimizes the control strategy of the hydropower unit control model through an online self-learning algorithm to effectively follow the grid instructions, including: Field feedback data is collected at pre-set time intervals or specific events and stored in a database. The collected field feedback data is identified online to obtain the status of the hydropower unit and the changes in the power grid, and then the input variables for updating the control model of the hydropower unit are established; the correlation between system deviations and adjustment actions is analyzed to extract effective adjustment modes to form update rules for the control model of the hydropower unit; and the update rules are continuously updated using an online self-learning algorithm to improve the control strategy and achieve intelligent optimization.

10. A computer device, characterized in that: include: at least one processor; and a memory communicatively coupled to the at least one processor; The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the steps of the system according to any one of claims 1 to 9.

Images