Hydropower operation fault early warning system and method based on self-learning

Abstract

The invention provides a hydroelectric operation fault early warning system and method based on self-learning, and the method comprises the steps: starting a first controller in a first operation mode, and obtaining a water flow-time curve and a power generation capacity-time curve of each hydroelectric generating set; calculating the power generation efficiency of each hydroelectric generating set and the overall power generation efficiency of the system; when the overall power generation efficiency is lower than the first preset power generation efficiency, whether a hydroelectric generating set with obviously abnormal power generation efficiency exists or not is judged; when the hydroelectric generating set with obviously abnormal power generation efficiency exists, the hydroelectric generating set is closed or the power generation load of the hydroelectric generating set is reduced; when the hydroelectric generating set with the obviously abnormal power generation efficiency does not exist, the first operation mode is switched to the second operation mode, the second controller is started, and the first controller and the second controller generate an emergency adjustment instruction through cooperative control so as to improve the overall power generation efficiency; the safety and stability of hydroelectric generation can be powerfully improved.

Description

Technical Field

[0001] The present invention relates to the field of fault warning of hydropower operation, and in particular to a hydropower operation fault warning system and method based on self-learning. Background Art

[0002] Hydropower is a way of generating electricity by converting water flow energy into electrical energy. It mainly uses the potential energy contained in natural water bodies such as rivers and lakes when they flow from high to low, converts this potential energy into kinetic energy of turbines, and then drives the turbine motor to generate electricity. As an important part of renewable energy, hydropower has significant advantages such as environmental protection and economy. With the continuous increase in global demand for renewable energy and the continuous advancement of science and technology, the level of intelligence and digitalization of hydropower generation has been continuously improved, and functions such as remote monitoring, intelligent scheduling and fault warning have also been continuously emerging; but it also faces some challenges in the process of development, such as how to improve the safety and stability of hydropower generation, how to reduce the operating cost of hydropower generation, etc.

[0003] The existing hydropower operation fault warning system has the following main problems: First, hydropower units are customized products. The water head and single-unit capacity of each power station are different. Even for the same type of units, there are differences in their installation, which leads to different vibration characteristic values ​​of the units; even for the same unit, there are obvious differences in its vibration values ​​at different operating conditions, which makes it difficult to accurately warn of faults by obtaining the vibration state of the hydropower unit; secondly, the hydropower system has many functional modules and a complex structure. When monitoring it, it is often necessary to use sensors to obtain the operating parameters of each functional module. However, due to the limited installation position of the sensor, the operating parameters of some functional modules cannot be directly obtained and can only be simulated through special field simulation models and sensor data near the area, such as The simulation process requires a lot of time and computing power to simulate the stress state of the turbine motor impeller, the magnetic flux distribution of the turbine motor, etc., which makes it difficult to quickly generate and execute control instructions under abnormal conditions. At the same time, the large time lag in the hydropower system will also affect the rapid operation and maintenance of abnormal conditions. In addition, the operation failures of hydropower system equipment include the following situations: (1) Trend deterioration, which progresses slowly and generally does not substantially weaken the equipment's effectiveness. It is necessary to pay attention to its deterioration state and trigger abnormal warnings accordingly; (2) Occasional failures require the establishment of a rapid evaluation system based on pattern recognition to identify whether the sporadic abnormal data collected by online monitoring indicates that a failure is about to occur. How to achieve accurate and timely detection and positioning of the above two types of operation failures is of great significance to improving the safety and stability of hydropower generation. Summary of the invention

[0004] The purpose of the present invention is to provide a hydropower operation fault early warning system and method based on self-learning to solve the technical problems mentioned in the above background technology.

[0005] In order to achieve the above object, the specific technical solution adopted by the present invention is: A hydropower operation fault early warning method based on self-learning comprises the following steps: S1: In the first operation mode, start the first controller to obtain the water flow-time curve and power generation-time curve of each hydropower unit; S2: Calculate the power generation efficiency of each hydropower unit and the overall power generation efficiency of the system; S3: when the overall power generation efficiency is lower than the first preset power generation efficiency, determining whether there is a hydropower unit with obviously abnormal power generation efficiency; S4: When there are hydropower units with obviously abnormal power generation efficiency, shut them down or reduce their power generation load; S5: When there is no hydropower unit with obviously abnormal power generation efficiency, switch the first operation mode to the second operation mode, start the second controller, and the first and second controllers generate emergency adjustment instructions through coordinated control to improve the overall power generation efficiency; Optionally, also include: S6: When the overall power generation efficiency is improved to the second preset power generation efficiency, the second operation mode is switched to the third operation mode, and the abnormal situation is evaluated, located and operated; S7: when the overall power generation efficiency is increased to the third preset power generation efficiency, switching the third operation mode to the first operation mode; Optionally, the step S2: calculating the power generation efficiency of each hydropower unit and the overall power generation efficiency of the system includes: S21: Counting the water flow-time curve and power generation-time curve of each hydropower unit and the system as a whole respectively; S22: Based on the two time curves, integrate the time period (t1-t2) to obtain the water flow Q and power generation P in the time period; S23: Determine the power generation efficiency of each hydropower unit and the overall power generation efficiency based on the following formula: E = (P / Q) * k; Wherein, E represents power generation efficiency, and k is a preset coefficient, which is determined based on the relationship between water flow and power generation; Optionally, the S3: when the overall power generation efficiency is lower than the first preset power generation efficiency, determining whether there is a hydropower unit with obviously abnormal power generation efficiency includes: S31: comparing the overall power generation efficiency of the system with a first preset power generation efficiency, and when the overall power generation efficiency is lower than the first preset power generation efficiency, calculating the average power generation efficiency Eav of each hydropower unit; S32: Calculate the deviation degree W of the power generation efficiency e of each hydropower unit lower than the average power generation efficiency Eav based on the following formula; W = (Eav-e) / Eav; S33: determining a hydropower unit with obviously abnormal power generation efficiency based on the deviation degree, and when W exceeds a preset value, confirming the corresponding hydropower unit as a hydropower unit with obviously abnormal power generation efficiency; Optionally, the first operating mode, the second operating mode, and the third operating mode correspond to a normal operating mode, an emergency operating mode, and a safe operating mode, respectively; According to another aspect of the present invention, there is also provided a hydropower operation fault early warning system based on self-learning, comprising: a central control module, a data acquisition module, a storage module, and an alarm module; The central control module can analyze and process the parameter information collected by the data acquisition module to achieve fault warning for hydropower operation and generate corresponding adjustment instructions; The data acquisition module is used to collect different types of parameter information; The storage module can store the parameter information collected by the data acquisition module; The alarm module can sound an alarm when an abnormality occurs in the hydropower system; Optionally, the central control module can: in the first operating mode, start the first controller to obtain the water flow-time curve and power generation-time curve of each hydropower unit; calculate the power generation efficiency of each hydropower unit and the overall power generation efficiency of the system; when the overall power generation efficiency is lower than the first preset power generation efficiency, determine whether there are hydropower units with obviously abnormal power generation efficiency; when there are hydropower units with obviously abnormal power generation efficiency, shut them down or reduce their power generation load; when there are no hydropower units with obviously abnormal power generation efficiency, switch the first operating mode to the second operating mode, start the second controller, and the first and second controllers generate emergency adjustment instructions through collaborative control to improve the overall power generation efficiency; Optionally, the central control module can also: when the overall power generation efficiency is improved to the second preset power generation efficiency, switch the second operation mode to the third operation mode, and evaluate, locate and operate the abnormal situation; when the overall power generation efficiency is improved to the third preset power generation efficiency, switch the third operation mode to the first operation mode; Optionally, when there is no hydropower unit with obviously abnormal power generation efficiency, switching the first operation mode to the second operation mode, starting the second controller, and the first and second controllers generating emergency adjustment instructions through coordinated control to improve the overall power generation efficiency include: Start the second controller and increase the data acquisition rate of the sensor from H1 to H2; The collected parameter information is no longer automatically deleted, and the collected parameter information is stored and sent to the backend server; Optionally, it also includes: shutting down the field simulation model with a large amount of calculation, and using a preset control law with a small amount of calculation to replace the field simulation model to determine the operating parameters of the functional modules that are difficult to directly collect.

[0006] The present invention provides a self-learning-based hydropower operation fault warning system and method, including: in a first operation mode, starting a first controller to obtain the water flow-time curve and power generation-time curve of each hydropower unit; calculating the power generation efficiency of each hydropower unit and the overall power generation efficiency of the system; when the overall power generation efficiency is lower than the first preset power generation efficiency, judging whether there are hydropower units with obviously abnormal power generation efficiency; when there are hydropower units with obviously abnormal power generation efficiency, shutting them down or reducing their power generation load; when there are no hydropower units with obviously abnormal power generation efficiency, switching the first operation mode to the second operation mode, starting the second controller, and the first and second controllers generate emergency adjustment instructions through collaborative control to improve the overall power generation efficiency. The present invention has at least the following technical effects: (1) By calculating the overall power generation efficiency of each hydropower unit and the system, the operating status of the hydropower system can be judged, so as to avoid the influence of the differences of the hydropower units on the accurate monitoring of the operating status of the hydropower system; (2) Detect whether there are any hydropower units with obviously abnormal power generation efficiency. If there are any, use the parallel hydropower units to share their power generation load as much as possible, thereby improving the overall power generation efficiency of the hydropower system and ensuring the stability of the power supply of the hydropower system; (3) Switch different hydropower system operation modes under different circumstances to increase the speed of generating emergency regulation instructions and ensure the safety of hydropower system operation; (4) Simultaneously monitor the trend of deterioration and occasional failures of hydropower system operating equipment, so that people can quickly and accurately obtain the operating status of the hydropower system; (5) Realize rapid detection and location of abnormal nodes in the hydropower system and improve operation and maintenance speed. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1 It is a flow chart of the hydropower operation fault early warning method based on self-learning of the present invention; Figure 2 A schematic diagram of switching between three operating modes of the present invention; Figure 3 It is a schematic diagram of the three stages of the power generation process of the hydropower system of the present invention. DETAILED DESCRIPTION

[0008] In order to make the purpose, technical scheme and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. The specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. In addition, the technical features involved in each embodiment of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0009] A hydropower operation fault early warning method based on self-learning, such as Figure 1 As shown, it includes the following steps: S1: In the first operation mode, start the first controller to obtain the water flow-time curve and power generation-time curve of each hydropower unit; S2: Calculate the power generation efficiency of each hydropower unit and the overall power generation efficiency of the system; S3: when the overall power generation efficiency is lower than the first preset power generation efficiency, determining whether there is a hydropower unit with obviously abnormal power generation efficiency; S4: When there are hydropower units with obviously abnormal power generation efficiency, shut them down or reduce their power generation load; S5: When there is no hydropower unit with obviously abnormal power generation efficiency, switch the first operation mode to the second operation mode, start the second controller, and the first and second controllers generate emergency adjustment instructions through coordinated control to improve the overall power generation efficiency; Optionally, also include: S6: When the overall power generation efficiency is improved to the second preset power generation efficiency, the second operation mode is switched to the third operation mode, and the abnormal situation is evaluated, located and operated; S7: When the overall power generation efficiency is increased to the third preset power generation efficiency, switching the third operation mode to the first operation mode.

[0010] The hydropower system includes multiple functional modules such as water storage, diversion, diversion, hydropower units, power conversion and transmission, etc. Each functional module includes submodules responsible for and completing different actions; sensors are used to obtain parameter information such as water level, flow, stress, voltage, current, magnetic flux, etc. of different functional modules or submodules, and send them to the storage module for storage. The storage module is based on a circular storage and deletion mechanism, and deletes after a preset time period, and the first-in-first-out is first-out, which is convenient for later data tracing and viewing while saving storage space; the controller can analyze and process the collected parameter information to achieve fault warning for hydropower operation, and generate corresponding adjustment instructions to improve the operating status of the hydropower system; the functional module composition of the hydropower system, the type of sensor and the installation method are not specifically limited here, and those skilled in the art can select and set them according to actual needs; The first operating mode, the second operating mode, and the third operating mode respectively correspond to the normal operating mode, the emergency operating mode, and the safe operating mode; In the first and third operating modes, the data acquisition rates of the sensor are H1 and H3 respectively, and the collected parameter information is automatically deleted every preset time M1 and M2 respectively; in the second operating mode, the data acquisition rate of the sensor is H2, and the collected parameter information is no longer automatically deleted, but manually deleted by the staff to facilitate the later analysis of the abnormal reasons; H1 < H3 < H2; M1 < M2; as Figure 2 shown, the three operating modes can be automatically switched based on a preset control program; or can be switched manually; The first controller is the main controller. Under normal circumstances, only the first controller is started. The first controller can receive the real-time water flow rate, voltage, and current information sent by the sensor and generate a water flow rate-time curve and a power generation-time curve for each hydroelectric generating unit accordingly; the second controller is a standby controller, which is started under special circumstances and can improve the data analysis and processing speed of the system, thereby realizing the rapid generation of emergency adjustment instructions; In the first operating mode, the first controller is turned on; in the second and third operating modes, the first and second controllers are turned on simultaneously; It can be understood that the first operating mode is an operating mode suitable for normal circumstances, and its instruction generation speed, accuracy, computing power, and energy consumption are all moderate; the second operating mode is an operating mode suitable for emergency circumstances, with the fastest instruction generation speed, moderate accuracy, high computing power and energy consumption, facilitating the rapid generation of adjustment instructions in emergency situations; the third operating mode is an operating mode suitable for after the emergency has been alleviated, with a moderate instruction generation speed, relatively high accuracy, high computing power and energy consumption, facilitating the fine adjustment of the system and fault location; The hydropower system generally includes multiple parallel hydroelectric generating units. Under normal circumstances, different water flow rates per unit time in each branch will correspond to different power generations. The overall power generation efficiency of each hydroelectric generating unit and the system can be analyzed through the water flow rate and power generation in unit time to determine the degradation level of each hydroelectric generating unit and the overall system; S2: Calculate the power generation efficiency of each hydroelectric generating unit and the overall power generation efficiency of the system, including: S21: Respectively count the water flow rate-time curve and the power generation-time curve of each hydroelectric generating unit and the overall system; S22: Based on the two time curves, perform integration on the time period (t1 - t2) to obtain the water flow rate Q and the power generation P within the time period; S23: Respectively determine the power generation efficiency of each hydroelectric generating unit and the overall based on the following formula: E = (P / Q) * k; Wherein, E represents power generation efficiency, and k is a preset coefficient, which is determined based on the relationship between water flow and power generation; There are many factors that affect the overall power generation efficiency of the hydropower system, such as insufficient overall water storage, abnormalities in the power conversion and transmission modules, or low water flow due to stalling or water leakage of a single hydropower unit in parallel. S3: when the overall power generation efficiency is lower than the first preset power generation efficiency, determining whether there is a hydropower unit with obviously abnormal power generation efficiency includes: S31: comparing the overall power generation efficiency of the system with a first preset power generation efficiency, and when the overall power generation efficiency is lower than the first preset power generation efficiency, calculating the average power generation efficiency Eav of each hydropower unit; S32: Calculate the deviation degree W of the power generation efficiency e of each hydropower unit lower than the average power generation efficiency Eav based on the following formula; W = (Eav-e) / Eav; S33: determining a hydropower unit with obviously abnormal power generation efficiency based on the deviation degree, and when W exceeds a preset value, confirming the corresponding hydropower unit as a hydropower unit with obviously abnormal power generation efficiency; like Figure 3 As shown in Figure 1, the power generation process of the hydropower system can be divided into the following three stages: The first stage: when the water flow rate increases from zero to the first preset value, the hydropower unit starts to rotate and start generating electricity; The second stage: when the water flow rate is between the first preset value and the second preset value, the power generation of the hydropower unit increases with the increase of the water flow rate; The third stage: when the water flow exceeds the second preset value, the power generation of the hydropower unit is at the maximum value and will not increase with the increase of water flow; S4: When there is a hydropower unit with obviously abnormal power generation efficiency, shut it down or reduce its power generation load, including: S41: Determine the location and power generation load of the hydropower unit with obvious abnormal power generation efficiency; S42: Detect whether there is a hydropower unit in the second stage of power generation process among other parallel hydropower units. If there is no hydropower unit, keep the hydropower unit with obvious abnormality to continue power generation operation; S43: if the abnormality exists, determining whether other hydropower generating units in the second stage of power generation can share the power generation load of the hydropower generating unit with obvious abnormality; S44: when other hydropower generating units in the second stage of power generation can fully share the power generation load of the hydropower generating unit with obvious abnormality, the hydropower generating unit with obvious abnormality in power generation efficiency is shut down, and its corresponding water flow is distributed to other hydropower generating units in the second stage of power generation by adjusting the corresponding valve state; S45: when other hydropower generating units in the second stage of power generation can only partially share the power generation load of the hydropower generating unit with obvious abnormality, by adjusting the corresponding valve state, the corresponding water flow is partially distributed to other hydropower generating units in the second stage of power generation, thereby reducing the power generation load of the hydropower generating unit with obvious abnormality in power generation efficiency; Through the above scheme, the stability of the overall power supply of the hydropower system can be ensured and the overall power generation efficiency can be improved; When the overall power generation efficiency of the hydropower system is lower than the first preset power generation efficiency, and there is no hydropower unit with obviously abnormal power generation efficiency, it is considered that a key link of the hydropower system as a whole has a fault, such as a power collection module or a power conversion module. At this time, in order to avoid large property losses caused by equipment damage, the system switches to the second operation mode, that is, the emergency operation mode, to achieve rapid generation and execution of control instructions; S5: when there is no hydropower unit with obviously abnormal power generation efficiency, switching the first operation mode to the second operation mode, starting the second controller, and the first and second controllers generate emergency adjustment instructions through coordinated control to improve the overall power generation efficiency, including: S51: Start the second controller to increase the data acquisition rate of the sensor from H1 to H2; S52: the collected parameter information is no longer automatically deleted, and the collected parameter information is stored and sent to the backend server; As mentioned above, due to the limited installation location of sensors in the hydropower system, the operating parameters of some functional modules need to be simulated through a special field simulation model and sensor data near the area, which consumes a lot of time and computing power. The large time lag in the hydropower system will also affect the rapid operation and maintenance of abnormal situations, which will bring difficulties to the rapid generation and execution of control instructions in abnormal situations. Optionally, also include: S53: closing the field simulation model with a large amount of calculation, and using a preset control law with a small amount of calculation to replace the field simulation model to determine the operating parameters of the functional modules that are difficult to directly collect; The field simulation model may be a force distribution simulation model of a water turbine motor impeller and a magnetic flux distribution simulation model of the water turbine motor, which can be combined with data of an impeller force sensor installed near the area and data of a magnetometer to calculate and simulate the force distribution of the water turbine motor impeller and the magnetic flux distribution of the water turbine motor; The preset control law refers to the regular information pre-set for approximately determining the operating parameters of the functional modules that are difficult to directly collect; for example, when the water flow velocity is u1, the impeller force of the water turbine motor is determined to be f1, that is, the impeller force is indirectly approximately determined by the water flow velocity; when the speed of the water turbine motor is v1, the magnetic flux distribution state of the water turbine motor is determined to be Ψ1, that is, the magnetic flux distribution of the water turbine motor is indirectly approximately determined by the speed of the water turbine motor; this is only an example, and it can also be other regular information that can approximately determine the operating parameters of the functional modules that are difficult to directly collect; it can be understood that the preset control law can sacrifice the acquisition accuracy of some operating parameters, speed up the acquisition speed of the operating parameters, save computing power, and thus improve the generation speed of control instructions in emergency situations; Optionally, it also includes: S54: Based on the historical operation data, determine the time interval between the input and expected output data of each link, and when the interval is greater than a preset value, determine that it is a link with a large time delay; S55: Collect historical input and output data of the large time-delay link, train to obtain an input and output prediction model for the large time-delay link, and in the second operation mode, predict the output of the large time-delay link based on the input and output prediction model of the large time-delay link, and the controller will quickly generate corresponding emergency adjustment instructions based on the predicted output; The large time-delay link may be a peak power generation voltage and current determination link of the hydropower system, which is related to factors such as water storage height and water flow speed. Under normal circumstances, after factors such as water storage height and water flow speed change, it often takes a long time to determine the corresponding peak power generation voltage and current. The present invention can quickly obtain the corresponding peak voltage and peak current at a certain water storage height and water flow speed through the trained peak power generation voltage and current input and output prediction model, so as to further improve the generation speed of control instructions in emergency situations. Optionally, the input and output prediction model of the large time-delay link can be iteratively trained based on the collected data information periodically; S56: The first and second controllers cooperate to generate emergency adjustment instructions to adjust the operating parameters of the corresponding functional modules to improve and enhance the overall power generation efficiency; Specifically, the emergency adjustment instruction may be to increase, decrease or close the opening state of the valve, etc., or may be other control instructions that can alleviate the emergency abnormality, which are not specifically limited here; When the emergency situation of the hydropower system is alleviated by the emergency adjustment command and the corresponding overall power generation efficiency is temporarily restored, the hydropower system enters the safe operation mode, that is, the third operation mode, to further analyze, locate and handle the abnormal components and causes of the abnormality; S6: when the overall power generation efficiency is improved to the second preset power generation efficiency, switching the second operation mode to the third operation mode, evaluating, locating and operating the abnormal situation, including: S61: using sensors and transfer functions of each link to determine actual input, ideal output and actual output data of each link; Each link in the hydropower system is connected in sequence; the transfer function refers to the input and output relationship of each link, which can be obtained by analyzing historical data; S62: Quickly determine the location information of the abnormal link based on the dichotomy method, including: S621: Based on the actual input of the first node and the total transfer function from the first node to the intermediate node, the ideal output of the intermediate node is calculated, and the ideal output of the intermediate node is compared and analyzed with the actual output of the intermediate node obtained by the sensor to determine whether there is an abnormal node between the first node and the intermediate node; The comparing and analyzing the ideal output of the intermediate node with the actual output of the intermediate node obtained by the sensor includes: analyzing the mean, variance, peak value, fluctuation, etc. of the two, which are not specifically limited here; S622: When there are abnormal nodes between the first node and the intermediate node, the node segment with the abnormality is analyzed separately, and similar to the above process, the abnormal node status of the node segment with the abnormality is continuously determined until all the abnormal nodes are determined; S623: After all abnormal nodes are determined, the abnormal conditions of the abnormal nodes are reviewed in combination with the parameter information of the upstream and downstream nodes of the abnormal nodes; S624: When a misjudged node is found, the sensor of the misjudged node is considered to be abnormal, and the operating state of the sensor is verified; Optionally, the operation status of sensors can be periodically verified by combining the upstream and downstream data of nodes and unmanned inspection equipment equipped with fixed sensors to avoid misjudgment caused by sensor anomalies; Optionally, the method further includes: S625: when a sensor of a certain node is abnormal, the controller may approximately replace the parameter information collected by the abnormal sensor based on the transfer function of the node and the data information of the adjacent sensors, and continue to control the hydropower system; As mentioned above, the operation failure of hydropower system equipment includes trend deterioration. In order to facilitate people to obtain the degree of deterioration in real time and formulate a scientific and accurate inspection plan for hydropower equipment, the following options are optional: S63: in a third operation mode, based on an actual input of the node or the node segment, a transfer function of the node or a total transfer function of the node segment, determining an ideal output of the node or the node segment, and comparing the ideal output of the node or the node segment with an actual output to determine a degree of deterioration of the node or the node segment; Through the above scheme, accurate monitoring of the deterioration degree of a node or node segment can be achieved; it can be understood that in the third operating mode, the data acquisition rate is large and the second controller is turned on, and the activation of the field simulation model also makes data acquisition more accurate, and the analysis and monitoring of trend deterioration are also more accurate; Optionally, the step S7: when the overall power generation efficiency is increased to a third preset power generation efficiency, switching the third operation mode to the first operation mode includes: S71: After the assessment, location and operation of abnormal conditions are completed, the overall power generation efficiency of the hydropower system will be improved; S72: When the overall power generation efficiency is increased to the third preset power generation efficiency, switching the third operation mode to the first operation mode; The first preset power generation efficiency < the second preset power generation efficiency < the third preset power generation efficiency, and those skilled in the art may set the specific value according to the operation conditions of the hydropower system.

[0011] According to another aspect of the present invention, there is also provided a hydropower operation fault early warning system based on self-learning, the system comprising: a central control module, a data acquisition module, a storage module, and an alarm module; The central control module includes a first controller and a second controller. The central control module can analyze and process the parameter information collected by the data collection module to realize fault warning of hydropower operation, and generate corresponding adjustment instructions to improve the operation state of the hydropower system; The data acquisition module includes a water level sensor, a water flow sensor, a stress sensor, a voltage sensor, a current sensor, and a magnetometer, which are respectively used to collect different types of parameter information; The data acquisition modules are installed at the corresponding positions of each functional module or functional submodule of the hydropower system; the type and installation method of the data acquisition module are not specifically limited here, and those skilled in the art can select and set them according to actual needs; The hydropower system includes multiple functional modules such as water storage, flow diversion, flow diversion, hydropower units, power conversion and transmission, etc. Each functional module includes submodules responsible for and completing different actions; The storage module can store the parameter information collected by the data acquisition module. The storage module is based on a circular storage and deletion mechanism. It deletes data after a preset time period, and the first-in-first-out mechanism is adopted. This saves storage space while facilitating data tracing and viewing at a later stage. The alarm module can sound an alarm when an abnormality occurs in the water and electricity system; The central control module is capable of: in the first operation mode, starting the first controller to obtain the water flow-time curve and power generation-time curve of each hydropower unit; calculating the power generation efficiency of each hydropower unit and the overall power generation efficiency of the system; when the overall power generation efficiency is lower than the first preset power generation efficiency, determining whether there are hydropower units with obviously abnormal power generation efficiency; when there are hydropower units with obviously abnormal power generation efficiency, shutting them down or reducing their power generation load; when there are no hydropower units with obviously abnormal power generation efficiency, switching the first operation mode to the second operation mode, starting the second controller, and the first and second controllers generate emergency adjustment instructions through collaborative control to improve the overall power generation efficiency; Optionally, the central control module can also: when the overall power generation efficiency is improved to the second preset power generation efficiency, switch the second operation mode to the third operation mode, and evaluate, locate and operate the abnormal situation; when the overall power generation efficiency is improved to the third preset power generation efficiency, switch the third operation mode to the first operation mode; The first operation mode, the second operation mode, and the third operation mode correspond to the normal operation mode, the emergency operation mode, and the safety operation mode, respectively; In the first and third operating modes, the data acquisition rates of the sensor are H1 and H3 respectively, and the collected parameter information is automatically deleted at preset time intervals M1 and M2 respectively; in the second operating mode, the data acquisition rate of the sensor is H2, and the collected parameter information is no longer automatically deleted, but is manually deleted by the staff; the H1 <H3<H2;M1<M2; The first controller is a main controller, and the second controller is a standby controller; in the first operating mode, the first controller is turned on; in the second and third operating modes, the first and second controllers are turned on at the same time; The calculation of the power generation efficiency of each hydropower unit and the overall power generation efficiency of the system includes: Statistic the water flow-time curve and power generation-time curve of each hydropower unit and the system as a whole; Based on the two time curves, the time period (t1-t2) is integrated to obtain the water flow Q and power generation P in the time period; The power generation efficiency of each hydropower unit and the whole hydropower unit is determined based on the following formula: E = (P / Q) * k; Wherein, E represents power generation efficiency, and k is a preset coefficient, which is determined based on the relationship between water flow and power generation; When the overall power generation efficiency is lower than the first preset power generation efficiency, determining whether there is a hydropower unit with obviously abnormal power generation efficiency includes: The overall power generation efficiency of the system is compared with the first preset power generation efficiency. When the overall power generation efficiency is lower than the first preset power generation efficiency, the average power generation efficiency Eav of each hydropower unit is calculated; The deviation degree W of the power generation efficiency e of each hydropower unit lower than the average power generation efficiency Eav is calculated based on the following formula; W = (Eav-e) / Eav; Determine the hydropower unit with obviously abnormal power generation efficiency based on the deviation degree, and when W exceeds the preset value, confirm the corresponding hydropower unit as a hydropower unit with obviously abnormal power generation efficiency; When there is a hydropower unit with obviously abnormal power generation efficiency, shut it down or reduce its power generation load, including: Determine the location and generation load of hydropower units with significant abnormalities in generation efficiency; Detect whether there is a hydropower unit in the second stage of power generation process among other parallel hydropower units. If there is no hydropower unit, keep the hydropower unit with obvious abnormality to continue power generation operation; If there is an abnormality, determine whether other hydropower units in the second stage of power generation can share the power generation load of the hydropower unit with obvious abnormality; When other hydropower units in the second stage of power generation can fully share the power generation load of the hydropower unit with obvious abnormality, shut down the hydropower unit with obvious abnormality in power generation efficiency, and distribute its corresponding water flow to other hydropower units in the second stage of power generation by adjusting the corresponding valve state; Optionally, it also includes: when other hydropower units in the second stage of power generation can only partially share the power generation load of the hydropower unit with obvious abnormality, by adjusting the corresponding valve state, the corresponding water flow is partially distributed to other hydropower units in the second stage of power generation, so as to reduce the power generation load of the hydropower unit with obvious abnormality in power generation efficiency; When there is no hydropower unit with obviously abnormal power generation efficiency, the first operation mode is switched to the second operation mode, the second controller is started, and the first and second controllers generate emergency adjustment instructions through coordinated control to improve the overall power generation efficiency, including: Start the second controller and increase the data acquisition rate of the sensor from H1 to H2; The collected parameter information is no longer automatically deleted, and the collected parameter information is stored and sent to the backend server; Optionally, also include: Close the field simulation model with large computational complexity, and use the preset control law with small computational complexity to replace the field simulation model to determine the operating parameters of the functional modules that are difficult to directly collect; The field simulation model may be a force distribution simulation model of a hydraulic motor impeller or a magnetic flux distribution simulation model of a hydraulic motor; The preset control law refers to the regular information preset to approximately determine the operating parameters of the functional modules that are difficult to directly collect; Based on historical operation data, determine the time interval between the input and expected output data of each link. When the interval is greater than a preset value, it is determined to be a link with a large time lag; Collect historical input and output data of the large time-delay link, train the input and output prediction model of the large time-delay link, and in the second operation mode, predict the output of the large time-delay link based on the input and output prediction model of the large time-delay link, and the controller will quickly generate corresponding emergency adjustment instructions based on the predicted output; The first and second controllers cooperate to generate emergency adjustment instructions and adjust the operating parameters of the corresponding functional modules to improve and enhance the overall power generation efficiency; The emergency adjustment instruction may be to increase, decrease or close the opening state of the valve; Optionally, the input and output prediction model of the large time-delay link can be iteratively trained based on the collected data information periodically; When the overall power generation efficiency is improved to the second preset power generation efficiency, the second operation mode is switched to the third operation mode, and the abnormal situation is evaluated, located and operated, including: Use sensors and transfer functions of each link to determine the actual input, ideal output and actual output data of each link; Quickly determine the location information of abnormal links based on dichotomy; In a third operation mode, based on the actual input of the node or the node segment, the transfer function of the node or the total transfer function of the node segment, an ideal output of the node or the node segment is determined, and the ideal output of the node or the node segment is compared with the actual output to determine the degree of deterioration of the node or the node segment; The method of quickly determining the location information of the abnormal link based on the dichotomy method includes: Based on the actual input of the first node and the total transfer function from the first node to the intermediate node, the ideal output of the intermediate node is calculated, and the ideal output of the intermediate node is compared and analyzed with the actual output of the intermediate node obtained by the sensor to determine whether there is an abnormal node between the first node and the intermediate node; When there are abnormal nodes between the first node and the intermediate node, the node segment with the abnormality is analyzed separately, and similar to the above process, the abnormal node status of the node segment with the abnormality is continuously determined until all the abnormal nodes are determined; After all abnormal nodes are identified, the abnormal conditions of the abnormal nodes are reviewed in combination with the parameter information of the upstream and downstream nodes of the abnormal nodes; When a misjudged node is found, the sensor of the misjudged node is considered to be abnormal, and the operating status of the sensor is verified; Optionally, the operating status of the sensor can be periodically verified by combining the upstream and downstream data of the node and unmanned inspection equipment equipped with fixed sensors; Optionally, when a sensor of a certain node is abnormal, the controller may approximately replace the parameter information collected by the abnormal sensor based on the transfer function of the node and the data information of the neighboring sensors, and continue to control the hydropower system; When the overall power generation efficiency is increased to the third preset power generation efficiency, switching the third operation mode to the first operation mode includes: After the assessment, location and operation of abnormal situations are completed, the overall power generation efficiency of the hydropower system will be improved; When the overall power generation efficiency is increased to a third preset power generation efficiency, switching the third operation mode to the first operation mode; The first preset power generation efficiency<the second preset power generation efficiency<the third preset power generation efficiency.

[0012] The present invention provides a hydropower operation fault early warning system and method based on self-learning, comprising: in a first operation mode, starting a first controller to obtain a water flow-time curve and a power generation-time curve of each hydropower unit; calculating the power generation efficiency of each hydropower unit and the overall power generation efficiency of the system; when the overall power generation efficiency is lower than a first preset power generation efficiency, judging whether there are hydropower units with obviously abnormal power generation efficiency; when there are hydropower units with obviously abnormal power generation efficiency, shutting them down or reducing their power generation load; when there are no hydropower units with obviously abnormal power generation efficiency, switching the first operation mode to the second operation mode, starting the second controller, and the first and second controllers generate emergency adjustment instructions through collaborative control to improve the overall power generation efficiency.

[0013] The above contents are only the technical ideas of the present invention and cannot be used to limit the protection scope of the present invention. Any changes made on the basis of the technical solution in accordance with the technical ideas proposed by the present invention shall fall within the protection scope of the claims of the present invention.

Claims

1. A hydropower operation fault early warning method based on self-learning, characterized in that: The following steps are included: S1: In the first operation mode, start the first controller to obtain the water flow-time curve and power generation-time curve of each hydropower unit; S2: Calculate the power generation efficiency of each hydropower unit and the overall power generation efficiency of the system; S3: when the overall power generation efficiency is lower than the first preset power generation efficiency, determining whether there is a hydropower unit with obviously abnormal power generation efficiency; S4: When there are hydropower units with obviously abnormal power generation efficiency, shut them down or reduce their power generation load; S5: When there is no hydropower unit with obvious abnormal power generation efficiency, switch the first operation mode to the second operation mode, start the second controller, and the first and second controllers generate emergency adjustment instructions through coordinated control to improve the overall power generation efficiency.

2. The method according to claim 1, characterized in that The method further includes: S6: When the overall power generation efficiency is improved to the second preset power generation efficiency, the second operation mode is switched to the third operation mode, and the abnormal situation is evaluated, located and operated; S7: When the overall power generation efficiency is increased to the third preset power generation efficiency, switching the third operation mode to the first operation mode.

3. The method according to claim 2, characterized in that S2: Calculate the power generation efficiency of each hydropower unit and the overall power generation efficiency of the system, including: S21: Counting the water flow-time curve and power generation-time curve of each hydropower unit and the system as a whole respectively; S22: Based on the two time curves, integrate the time period (t1-t2) to obtain the water flow Q and power generation P in the time period; S23: Determine the power generation efficiency of each hydropower unit and the overall power generation efficiency based on the following formula: E = (P / Q) * k; Wherein, E represents power generation efficiency, and k is a preset coefficient, which is determined based on the relationship between water flow and power generation.

4. The method according to claim 3, characterized in that S3: when the overall power generation efficiency is lower than the first preset power generation efficiency, determining whether there is a hydropower unit with obviously abnormal power generation efficiency includes: S31: comparing the overall power generation efficiency of the system with a first preset power generation efficiency, and when the overall power generation efficiency is lower than the first preset power generation efficiency, calculating the average power generation efficiency Eav of each hydropower unit; S32: Calculate the deviation degree W of the power generation efficiency e of each hydropower unit lower than the average power generation efficiency Eav based on the following formula; W = (Eav-e) / Eav; S33: Determine the hydropower generating unit with obviously abnormal power generation efficiency based on the deviation degree, and when W exceeds a preset value, confirm the corresponding hydropower generating unit as a hydropower generating unit with obviously abnormal power generation efficiency.

5. The method according to claim 2, characterized in that: The first operation mode, the second operation mode, and the third operation mode correspond to a normal operation mode, an emergency operation mode, and a safety operation mode, respectively.

6. A hydropower operation fault early warning system based on self-learning based on the method according to any one of claims 1 to 5, characterized in that: The system includes: a central control module, a data acquisition module, a storage module, and an alarm module; The central control module can analyze and process the parameter information collected by the data acquisition module to achieve fault warning for hydropower operation and generate corresponding adjustment instructions; The data acquisition module is used to collect different types of parameter information; The storage module can store the parameter information collected by the data acquisition module; The alarm module can give an alarm when an abnormality occurs in the hydropower system.

7. The system according to claim 6, characterized in that The central control module is capable of: in a first operating mode, starting the first controller to obtain the water flow-time curve and power generation-time curve of each hydropower unit; calculating the power generation efficiency of each hydropower unit and the overall power generation efficiency of the system; when the overall power generation efficiency is lower than the first preset power generation efficiency, determining whether there are hydropower units with obviously abnormal power generation efficiency; when there are hydropower units with obviously abnormal power generation efficiency, shutting them down or reducing their power generation load; when there are no hydropower units with obviously abnormal power generation efficiency, switching the first operating mode to the second operating mode and starting the second controller, and the first and second controllers generate emergency adjustment instructions through collaborative control to improve the overall power generation efficiency.

8. The system according to claim 7, characterized in that The central control module can also: when the overall power generation efficiency is improved to the second preset power generation efficiency, switch the second operation mode to the third operation mode to evaluate, locate and operate the abnormal situation; when the overall power generation efficiency is improved to the third preset power generation efficiency, switch the third operation mode to the first operation mode.

9. The system according to claim 7, characterized in that When there is no hydropower unit with obviously abnormal power generation efficiency, the first operation mode is switched to the second operation mode, the second controller is started, and the first and second controllers generate emergency adjustment instructions through coordinated control to improve the overall power generation efficiency, including: Start the second controller and increase the data acquisition rate of the sensor from H1 to H2; The collected parameter information is no longer automatically deleted, and the collected parameter information is stored and sent to the background server.

10. The system according to claim 9, characterized in that Also includes: The field simulation model with large computational complexity is turned off, and the preset control law with small computational complexity is used to replace the field simulation model to determine the operating parameters of the functional modules that are difficult to directly collect.

Images