Real-time monitoring and control method, system, device and medium of hydraulic turbine

Abstract

The present invention discloses a real-time monitoring and control method, system, device and medium for a water turbine, relating to the technical field of hydropower station monitoring. When the water quality meets the requirements, the water is introduced into the water inlet of the water turbine through the water guide system; before being introduced into the water inlet, the expected water parameters are calculated based on the sensor data in the water guide system and the pre-measured head height; the blade angle of the water turbine is adjusted based on the obtained expected water parameters to make the generated electricity meet the demand; after the water enters the water turbine, data is collected to obtain the water parameter data curve inside the water turbine, the water parameter data curve is compared with the expected data curve for loss comparison to obtain the number of difference points, and corresponding measures are taken according to the number of difference points. The present invention can calculate the expected water parameters, compare the expected values with the actual values, continuously correct the parameters, and then adjust the blade angle of the water turbine in advance according to the expected parameters to solve the deficiency in the regulation flexibility of the Francis water turbine.

Description

Technical Field

[0001] The present invention relates to the technical field of hydropower station monitoring, in particular to a real-time monitoring and control method, system, device and medium for hydraulic turbines. Background Art

[0002] Many hydropower stations use mixed-flow hydraulic turbines, also known as Francis turbines. As the preferred type of hydraulic turbine under medium head and flow conditions, Francis turbines are favored for their compact structure, high efficiency and wide application. This type of hydraulic turbine can effectively convert the kinetic energy of water into mechanical energy, and then drive the generator to generate electrical energy. Its design enables it to maintain good performance over a wide range of flows and heads, especially in medium-head applications, where efficient energy conversion can be achieved.

[0003] However, Francis turbines have certain limitations in terms of regulation flexibility. Compared with Pelton or Kaplan turbines, Francis turbines have weaker adjustment speed and response ability when facing rapidly changing flows and heads. This characteristic may lead to problems in power generation efficiency and stability in modern power systems with large fluctuations in grid demand.

[0004] In order to overcome the deficiencies of Francis turbines in terms of regulation flexibility and improve their performance under varying head and flow conditions, more precise water parameter control strategies need to be implemented. By precisely controlling the water pressure, water flow rate and water flow velocity, the operating state of the hydraulic turbine can be optimized, thereby improving the energy conversion efficiency and the ability to adapt to grid demand.

[0005] Although improving the accuracy of water parameter control has obvious advantages, there are many challenges in actual operation. First of all, high-performance sensors and advanced data processing technologies are required to accurately measure and control water flow parameters in real time. In addition, environmental factors such as temperature changes, mechanical wear and sediment accumulation may affect the accuracy of sensors and the reliability of the system. In addition, the processing and feedback regulation mechanism of real-time data must be fast enough to respond to rapidly changing water flow conditions.

[0006] In view of the above problems, the present invention proposes a real-time monitoring and control method and system for hydropower stations. The invention aims to calculate in advance the expected water pressure, flow rate and flow velocity before the water resource enters the hydraulic turbine by integrating advanced sensing technologies, real-time data processing algorithms and automatic adjustment mechanisms. According to the expected parameters, the blade angle of the hydraulic turbine can be adjusted in advance to solve the deficiencies of Francis turbines in terms of regulation flexibility. And the present invention compares the real value with the predicted value to pre-judge the faults of the hydropower station. Through this system, the optimized operation of hydraulic power generation equipment such as Francis turbines can be realized, improving their regulation flexibility and overall power generation efficiency, and better meeting the needs of modern power grids. Summary of the Invention

[0007] In view of the above problems, the present invention is proposed.

[0008] Therefore, the problem to be solved by the present invention is that Francis turbines have certain limitations in terms of regulation flexibility.

[0009] To solve the above technical problems, the present invention provides the following technical solution: a real-time monitoring and control method for a water turbine, which includes that a local monitoring cabinet collects data of reservoir sensors to judge whether the water quality meets the requirements. If it meets the requirements, the water is introduced into the water turbine inlet through the water guide system; before introducing it into the inlet, the local monitoring cabinet calculates the predicted water parameters based on the sensor data in the water guide system and the pre-measured head height, and the water parameters include water pressure, flow rate and flow velocity; the local monitoring cabinet adjusts the blade angle of the water turbine based on the obtained predicted water parameters to make the power generation meet the demand; after the water enters the water turbine, based on the sensors in the water turbine, a water parameter data curve inside the water turbine is obtained, and the water parameter data curve is compared with the predicted data curve for loss comparison. If the loss comparison is greater than the preset threshold, the difference points are marked and the number of difference points is checked, and corresponding measures are taken according to the number of difference points; the predicted data curve is obtained by fitting through a neural network algorithm based on the historical data of the water turbine.

[0010] As a preferred solution of the real-time monitoring and control method for the water turbine of the present invention, wherein: judging whether the water quality meets the requirements includes obtaining the suspended matter coverage rate, pH value and conductivity index data in the reservoir based on the reservoir sensor data, and comparing the index data with the index threshold to judge whether it meets the requirements.

[0011] As a preferred solution of the real-time monitoring and control method for the water turbine of the present invention, wherein: calculating the predicted water parameters includes setting a measuring point at a predetermined interval distance in the water guide system to measure the water parameters; calculating the predicted water parameters based on the head height, and the water flow velocity calculation formula is expressed as,

[0012] ,

[0013] wherein, represents the water flow velocity, represents the acceleration due to gravity, represents the head height, represents the head loss; the head loss The calculation formula is expressed as,

[0014] ,

[0015] wherein, represents the friction factor, obtained from the Moody diagram, Denoted as the length of the water channel, Denoted as the diameter of the water channel; based on the water flow velocity calculation formula and the head loss Calculation formula, and the positions of each measuring point in the water guiding system, the final sectional water flow velocity The formula is expressed as,

[0016] ,

[0017] Wherein, Denoted as the head height from the water outlet of the reservoir to the th measuring point, Denoted as the length of the water channel from the water outlet of the reservoir to the th measuring point, Denoted as the total number of measuring points.

[0018] As a preferred solution of the real-time monitoring and control method of the water turbine described in the present invention, wherein: the calculated predicted water parameters further include that the calculation formula of the water pressure is expressed as,

[0019] ,

[0020] The calculation formula of the flow rate is expressed as,

[0021] ,

[0022] Wherein, Denoted as the water density, Denoted as the cross-sectional area of the water channel of the water guiding system; load the calculated predicted water parameters into the system, and start the water guiding work, collect the real water parameters collected at each measuring point, and based on the real water parameters, inversely calculate the real friction factor of each measuring point section through the sectional water flow velocity formula , and perform Update and replace, and calculate the total friction factor between the water outlet of the reservoir and the water inlet of the water turbine according to the mean formula Denoted as,

[0023] ,

[0024] For , subtract the real friction factor of each measuring point from the friction factor and compare it with the maximum allowable threshold , if , it is determined as an abnormal measuring point, if , is a normal measurement point; when the number of abnormal measurement points is less than or equal to 2, and if the number of abnormal measurement points is 2 and the positions of the two abnormal measurement points are not consecutive positions, it is determined that there is a sensor failure, and the normal operation of the hydropower station is maintained, but the friction factor data comparison at the abnormal measurement points is removed, and the sensor at the abnormal measurement point is repaired when the hydropower station is idle; when the number of abnormal measurement points is greater than 2, or the number of abnormal measurement points is 2 and the positions of the two abnormal measurement points are consecutive positions, it is determined that there is a water guide system failure or foreign matter in the water quality, and the operation of the hydropower station is stopped and repaired.

[0025] As a preferred solution of the real-time monitoring and control method of the water turbine described in the present invention, wherein: the adjusting the water turbine blade angle based on the obtained predicted water parameters includes substituting the calculated total friction factor and the total head height between the water outlet of the water storage tank and the water inlet of the water turbine collected in advance into the interval water flow velocity formula to obtain the predicted water turbine inlet water flow velocity ; according to the inlet water flow velocity calculate the effective head which is expressed as

[0026] ,

[0027] According to calculate the input flow velocity before entering the blade which is expressed as

[0028] ,

[0029] wherein is expressed as the blade angle; according to calculate the force of the blade being scoured , and then obtain the torque generated by the water turbine after being affected by the force and the rotational speed , which is expressed as

[0030] ,

[0031] ,

[0032] ,

[0033] wherein is expressed as the output water velocity after passing through the guide vane, which is k times of , and the value of k is calculated and fitted based on the specifications of different water turbines, is expressed as the runner radius, is expressed as the runner diameter; based on the maximum operable state of the water turbine, the constraint is expressed as

[0034] ,

[0035] ,

[0036] Among them, and respectively represent the maximum allowable operating speed and torque of the water turbine; according to the rotational speed calculate the angular velocity of the rotor connected to the guide wheel, which is expressed as

[0037] ,

[0038] and then calculate the expected power generation which is expressed as

[0039] ,

[0040] Among them, represents the conversion efficiency; replace the required power generation with the expected power generation, and load the expected water parameters calculated before importing the water inlet into the system, and inversely deduce the blade angle , and control the current blade angle to to meet the calculated which is greater than or equal to the required power generation.

[0041] As a preferred solution of the real-time monitoring and control method of the water turbine described in the present invention, wherein: the loss comparison between the water parameter data curve and the expected data curve includes loading the expected water parameters into a pre-trained neural network model to obtain an expected data curve, and collecting the actual water parameter data curve through internal sensors of the water turbine; comparing the loss between the water parameter data curve and the expected data curve, and the comparison rule is based on the measuring points of the internal sensors of the water turbine, calibrating the corresponding data points in the water parameter data curve, subtracting the corresponding values of the data points in the water parameter data curve from the data points in the expected data curve to obtain a difference value and comparing it with a preset threshold. If it is greater than the preset threshold, mark the corresponding data points in the water parameter data curve as difference points.

[0042] As a preferred solution of the real-time monitoring and control method of the water turbine of the present invention, wherein: the corresponding measures according to the number of difference points include that when the number of difference points is less than or equal to 2, and if the number of difference points is equal to 2 and the positions of the two difference points are not consecutive positions, it is determined as a sensor failure, the normal operation of the hydropower station is maintained, the difference points are marked in gray and treated as idle, and the sensors at the difference points are repaired when the hydropower station is idle; when the number of difference points is greater than 2, or the number of difference points is equal to 2 and the positions of the two difference points are consecutive positions, it is determined that there is an abnormality inside the water turbine, the current water turbine operation is stopped, the water resources that should flow into the current water turbine are introduced into the other water turbines through the water guiding system, and the blade angles of the other water turbines are adjusted according to the required power generation and constraints to meet the requirements, and the current water turbine is repaired.

[0043] Another object of the present invention is to provide a real-time monitoring and control system for a water turbine, which can monitor and control a hydropower station in real time, adjust the blade angle of the water turbine to ensure that the power generation meets the requirements, and can perform fault pre-judgment.

[0044] To solve the above technical problems, the present invention provides the following technical solutions: a system for the real-time monitoring and control method of a water turbine, including: a reservoir monitoring module, a water guiding system monitoring module, a blade angle control module, and a water turbine monitoring module; the reservoir monitoring module collects the data of the reservoir sensors, judges whether the water quality meets the requirements, and if so, introduces the water into the water inlet of the water turbine through the water guiding system; the water guiding system monitoring module calculates the expected water parameters before introducing the water into the water inlet based on the sensor data in the water guiding system and the pre-measured head height, and the water parameters include water pressure, flow rate, and flow velocity; the blade angle control module adjusts the blade angle of the water turbine based on the obtained expected water parameters to make the power generation meet the requirements; the water turbine monitoring module, after the water enters the water turbine, obtains the water parameter data curve inside the water turbine based on the sensors inside the water turbine, compares the loss of the water parameter data curve with the expected data curve, and if the loss comparison is greater than the preset threshold, marks the difference points and checks the number of difference points, and takes corresponding measures according to the number of difference points.

[0045] A computer device includes a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the steps of the real-time monitoring and control method of the water turbine as described above are implemented.

[0046] A computer-readable storage medium stores a computer program thereon, and when the computer program is executed by a processor, the steps of the real-time monitoring and control method of the water turbine as described above are implemented.

[0047] The beneficial effects of the present invention are as follows: Before the water resource enters the water turbine, the present invention can calculate the expected water pressure, flow rate and flow velocity in advance, compare the expected values with the actual values, continuously correct the parameters, enhance the authenticity of the expected values, and then adjust the blade angle of the water turbine in advance according to the expected parameters to solve the deficiency of the Francis turbine in regulation flexibility.

[0048] Moreover, by comparing the predicted value with the actual value measured by the sensor through a threshold, the present invention can pre-judge the faults of the hydropower station. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0050] Figure 1 It is a flowchart of the real-time monitoring and control method of the water turbine in Embodiment 1.

[0051] Figure 2 It is a module structure diagram of a real-time monitoring and control system for a hydropower station in Embodiment 3. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0052] To make the above objects, features and advantages of the present invention more obvious and understandable, the following will give a detailed description of the specific embodiments of the present invention with reference to the drawings in the specification.

[0053] In the following description, many specific details are set forth to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0054] Embodiment 1

[0055] Refer to Figure 1 , which is the first embodiment of the present invention. The real-time monitoring and control method of the water turbine provided by this embodiment includes, as Figure 1 shown:

[0056] Step 1: The local monitoring cabinet collects the data of the reservoir sensor, judges whether the water quality meets the requirements. If it meets the requirements, the water is introduced into the water turbine inlet through the water guide system.

[0057] The local monitoring cabinet is mainly responsible for the acquisition, analysis, storage, communication, display, alarm, human-computer interaction, etc. of the state data of sensors such as water pressure, flow rate, and flow velocity.

[0058] One on-site monitoring cabinet is configured for each unit. The on-site monitoring hardware for each unit is arranged in a standard cabinet beside the unit (on the right bank) or in the unit control room (on the left bank). The cabinet shall adopt the same model and style as the latest panel cabinets already installed at the site of each unit of the power station.

[0059] Based on the sensor data of the reservoir, the suspended solid coverage rate, pH value, and conductivity index data in the reservoir are obtained, and the index data is compared with the index threshold to determine whether the requirements are met.

[0060] If the suspended solid coverage rate is greater than the threshold, a flocculant is added to the water to aggregate the particles into lumps, which are removed by sedimentation or flotation. A filter screen is added before the water is introduced into the water turbine inlet to filter out the suspended solids.

[0061] If the pH value is greater than the threshold, selective water intake is carried out. The pH value of the water in the reservoir at different depths or different regions is measured. For the water in the regions where the pH value is greater than the threshold, it is discharged by controlling the gate of the drainage system, and the water in the regions that meet the requirements is introduced into the water turbine inlet; if there is a pH gradient in the reservoir, that is, the pH values of the water layers in different depth intervals are different, then by continuously shutting off between the gate of the drainage system and the gate of the water diversion system, the water resources entering the water diversion system meet the requirements.

[0062] If the conductivity is greater than the threshold, a water source with low salinity is introduced for dilution, or all the water resources in the reservoir are discharged. The sewage discharge volume in the upstream sewage outlet is adjusted to limit the entry of high-salt water into the upstream, and the water resources in the reservoir are stored again.

[0063] Adjusting the sewage discharge volume in the upstream sewage outlet here is to temporarily limit the sewage discharge into the upstream river. When the hydropower station stops generating electricity or the water quality meets the requirements, the limit is lifted.

[0064] Step 2: Before the water is introduced into the inlet, the on-site monitoring cabinet calculates the predicted water parameters through the sensor data in the water diversion system and the pre-measured water head height. The water parameters include water pressure, flow rate, and flow velocity.

[0065] A measuring point is set at a predetermined interval distance in the water diversion system to measure the water parameters; the predicted water parameters are calculated based on the water head height. The calculation formula for the water flow velocity is expressed as

[0066] ,

[0067] where represents the water flow velocity, represents the acceleration due to gravity, represents the water head height, represents the head loss.

[0068] Head loss The calculation formula is expressed as

[0069] ,

[0070] where is expressed as the friction factor and is obtained from the Moody diagram, is expressed as the length of the water channel, is expressed as the diameter of the water channel.

[0071] Based on the water flow velocity calculation formula and the calculation formula of the head loss and the positions of each measuring point in the water guiding system, the final interval water flow velocity formula is obtained and expressed as

[0072] ,

[0073] where is expressed as the head height from the water outlet of the reservoir to the th measuring point, is expressed as the length of the water channel from the water outlet of the reservoir to the th measuring point, is expressed as the total number of measuring points.

[0074] The calculation formula of water pressure is expressed as

[0075] ,

[0076] The calculation formula of flow rate is expressed as

[0077] ,

[0078] where is expressed as the water density, is expressed as the cross-sectional area of the water channel in the water guiding system.

[0079] Load the calculated predicted water parameters into the system and start the water guiding work. Collect the real water parameters collected at each measuring point. Based on the real water parameters and through the interval water flow velocity formula, inversely calculate the real friction factor of each measuring point interval , and is updated and replaced. Calculate the total friction factor from the water outlet of the reservoir to the water inlet of the water turbine according to the mean formula is expressed as

[0080] ,

[0081] For , subtract the real friction factor of each measuring point from the friction factor and compare it with the maximum allowable threshold . If , it is determined as an abnormal measurement point. If , it is a normal measurement point.

[0082] When the number of abnormal measurement points is less than or equal to 2, and if the number of abnormal measurement points is equal to 2 and the positions of the two abnormal measurement points are not consecutive positions, it is determined that there is a sensor failure, and the normal operation of the hydropower station is maintained, but the friction factor data comparison at the abnormal measurement points is removed. The sensors at the abnormal measurement points are repaired when the hydropower station is idle.

[0083] When the number of abnormal measurement points is greater than 2, or the number of abnormal measurement points is equal to 2 and the positions of the two abnormal measurement points are consecutive positions, it is determined that there is a failure in the water guiding system or there is foreign matter in the water quality, and the operation of the hydropower station is stopped for maintenance.

[0084] Explanation: Because the water flow of the hydropower station is very large and the sensors are constantly washed and corroded by water resources, they are inevitably damaged. Therefore, if only one or two places are found to have abnormal monitoring, it is very likely due to sensor failure. However, if abnormal monitoring phenomena are found in multiple places, it must be due to system failure or there are foreign matters and excessive sediment in the water body; the consecutive positions mentioned above mean that if two measurement points are far apart, generally according to historical data, it is also due to sensor failure. But if two consecutive measurement points are abnormal, it indicates that abnormalities occur in a certain area, and it is very likely due to the system and water body, because the probability of simultaneous failure of sensors in adjacent areas is extremely low.

[0085] Step 3: The on-site monitoring cabinet adjusts the water turbine blade angle based on the obtained expected water parameters to make the power generation meet the demand.

[0086] The calculated total friction factor and the total head height between the water outlet of the water storage tank and the water inlet of the water turbine collected in advance are substituted into the interval water flow velocity formula to obtain the expected water turbine inlet water flow velocity which is expressed as

[0087] ,

[0088] According to the inlet water flow velocity calculate the effective head which is expressed as

[0089] ,

[0090] According to calculate the input water flow velocity before entering the blade which is expressed as

[0091] ,

[0092] where Denoted as the blade angle.

[0093] According to Calculate the scouring force on the blade , and then obtain the torque generated by the water turbine after being subjected to the force and the rotational speed , denoted as,

[0094] ,

[0095] ,

[0096] ,

[0097] Among them, Denoted as the output water velocity after passing through the guide vane, generally k times of, and the value of k is calculated and fitted based on the specifications of different water turbines Denoted as the runner radius Denoted as the runner diameter.

[0098] Based on the maximum operable state of the water turbine, the constraint is denoted as

[0099] ,

[0100] ,

[0101] Among them, and Respectively denoted as the maximum allowable operating rotational speed and torque of the water turbine.

[0102] According to the rotational speed Calculate the angular velocity of the rotor connected to the runner Denoted as,

[0103] ,

[0104] Furthermore, calculate the expected power generation Denoted as,

[0105] ,

[0106] Among them, Denoted as the conversion efficiency; Replace the required power generation with the expected power generation, and load the expected water parameters calculated before importing into the water inlet into the system, and inversely deduce the blade angle , control the current blade angle to at, to meet the calculated greater than or equal to the required power generation.

[0107] For further explanation, the blade angle deduced at this time is the optimal blade angle. The blade angle needs to be adjusted in advance before water enters the water turbine. Since the operating conditions are different each time, the blade angle is different, so the blade angle is an unknown quantity. Therefore, the input flow velocity and other quantities related to the blade angle are all unknown quantities. For the sake of logical integrity of the present invention, the relationships between various quantities are described in advance. After replacing the required power generation with the predicted power generation, since the runner radius and k are fixed parameters, they are known quantities. Therefore is a known quantity, which is obtained by synthesizing the water turbine manual and actual measurements and is a known quantity. Therefore, can be calculated, and then is deduced. Since the runner diameter is a known quantity, can be obtained, and then the blade angle is deduced. At this time, can meet the required power generation after replacement, so it is the optimal blade angle.

[0108] Step 4: After water enters the water turbine, based on the sensors inside the water turbine, obtain the water parameter data curve inside the water turbine. Compare the loss between the water parameter data curve and the predicted data curve. If the loss comparison is greater than the preset threshold, calibrate the difference points and check the number of difference points, and take corresponding measures according to the number of difference points.

[0109] Load the predicted water parameters into a pre-trained neural network model to obtain the predicted data curve, and collect the actual water parameter data curve through the sensors inside the water turbine.

[0110] Compare the loss between the water parameter data curve and the predicted data curve. The comparison rule is based on the measuring points of the sensors inside the water turbine. Calibrate the corresponding data points in the water parameter data curve, subtract the values of the data points in the water parameter data curve from the corresponding data points in the predicted data curve to obtain the difference value, and compare it with the preset threshold. If it is greater than the preset threshold, mark the corresponding data points in the water parameter data curve as difference points.

[0111] When the number of difference points is less than or equal to 2, and if the number of difference points is 2 and the positions of the two difference points are not consecutive positions, it is determined that the sensor is faulty. Keep the hydropower station running normally, mark the difference points in gray for idle processing, and repair the sensors at the difference points when the hydropower station is idle.

[0112] When the number of difference points is greater than 2, or when the number of difference points is equal to 2 and the positions of the two difference points are consecutive positions, it is determined that an abnormality has occurred inside the water turbine. Stop the operation of the current water turbine, divert the water resources that should flow into the current water turbine into the other water turbines through the water guide system, and adjust the blade angles of the other water turbines according to the required power generation and constraints to meet the requirements, and repair the current water turbine.

[0113] The predicted data curve is obtained by fitting the historical data of the water turbine through a neural network algorithm as follows:

[0114] 1. Design a neural network with an input layer, two hidden layers, and an output layer. Its mathematical expression is:

[0115] Input layer: Input vector where is the number of input features.

[0116] The first hidden layer:

[0117] ,

[0118] where is the weight matrix of the first hidden layer, is the bias vector, is the activation function (such as ReLU).

[0119] The second hidden layer:

[0120] ,

[0121] where and are the weight matrix and bias vector of the second hidden layer.

[0122] Output layer:

[0123] ,

[0124] where is the output vector, containing the predicted image curve, and are the weight matrix and bias vector of the output layer.

[0125] 2. Training process

[0126] Training the neural network mainly involves minimizing the loss function through an optimization algorithm (such as gradient descent). For regression tasks, the mean squared error (MSE) is usually used as the loss function:

[0127] Loss function:

[0128] ,

[0129] wherein is the true value of the i-th sample, is the predicted value of the model, and n is the number of samples.

[0130] Optimization: By calculating the gradient of the loss function and updating the weights and biases:

[0131] ,

[0132] wherein, represents the learning rate.

[0133] 3. Prediction process

[0134] Given new input data x, calculate the output through forward propagation:

[0135] ,

[0136] where contains the predicted image curve.

[0137] Embodiment 2

[0138] In the second embodiment of the present invention, which is different from the first embodiment: The real-time monitoring and control method of the water turbine further includes, for verifying and explaining the technical effects adopted in this method, this embodiment uses the traditional technical solution and the method of the present invention for comparative testing, and uses scientific argumentation means to compare the test results to verify the real effects of this method.

[0139] Experimental group setting:

[0140] Experimental group A (the method of the present invention): Use the prediction model to calculate the water pressure, flow rate and flow velocity, and adjust the guide vane angle according to the predicted value.

[0141] Experimental group B (existing technology): Use the traditional reactive control strategy, that is, only adjust the guide vane angle according to the real-time sensor data, without the participation of the prediction model.

[0142] Test parameters:

[0143] Response time: The time from the parameter change to the completion of the guide vane adjustment.

[0144] Power generation efficiency: The ratio of the actual power generation to the maximum theoretical power generation.

[0145] Safety and failure rate: Record the number of any safety accidents or failures occurring during the operation.

[0146] Data collection: Two experimental groups were respectively loaded into the hydropower unit simulation model for simulation. Each group of experiments was simulated for at least 6 months of time series to collect sufficient operation data.

[0147] The obtained experimental data are shown in Table 1:

[0148] Table 1: Comparison table of experimental data

[0149] ,

[0150] Response time: Through advance prediction and adjustment, the present invention significantly reduces the time required for guide vane adjustment, from 15 seconds to 11 seconds.

[0151] Power generation efficiency: Through more optimized guide vane angle adjustment, the present invention improves the power generation efficiency of the water turbine, from 87% to 92%.

[0152] Number of safety accidents and misjudgments of failures: Due to more accurate water flow control and timely guide vane adjustment reducing mechanical stress and wear, the present invention has higher operation safety and lower failure rate. Moreover, by comparing the predicted value with the real value measured by the sensor through a threshold, the present invention can perform more accurate pre-judgment of failures for the hydropower station and reduce the number of misjudgments.

[0153] Example 3

[0154] Refer to Figure 2 , which is the third embodiment of the present invention. Different from the previous two embodiments, the system for the real-time monitoring and control method of the water turbine includes a reservoir monitoring module, a water diversion system monitoring module, a blade angle control module, and a water turbine monitoring module; the reservoir monitoring module collects reservoir sensor data and judges whether the water quality meets the requirements. If it meets, the water is introduced into the water turbine inlet through the water diversion system; the water diversion system monitoring module calculates the predicted water parameters before introducing it into the inlet through the sensor data in the water diversion system and the pre-measured head height, and the water parameters include water pressure, flow rate, and flow velocity; the blade angle control module adjusts the water turbine blade angle based on the obtained predicted water parameters to make the power generation meet the demand; after the water enters the water turbine, the water turbine monitoring module obtains the water parameter data curve inside the water turbine based on the sensors inside the water turbine, and compares the water parameter data curve with the predicted data curve for loss. If the loss comparison is greater than the preset threshold, the difference points are marked and the number of difference points is checked, and corresponding measures are taken according to the number of difference points.

[0155] If the above-mentioned functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs.

[0156] The logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch instructions from the instruction execution system, apparatus, or device and execute the instructions), or in combination with these instruction execution systems, apparatuses, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device.

[0157] More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection part with one or more wirings (electronic device), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber device, and portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, then editing, interpreting, or processing it in other suitable ways if necessary, and then storing it in a computer memory.

[0158] It should be understood that each part of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one of the following techniques known in the art or a combination thereof can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), and the like.

[0159] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. A real-time monitoring and control method for a water turbine, characterized in that: including, The on-site monitoring cabinet collects the sensor data of the reservoir, judges whether the water quality meets the requirements. If it meets the requirements, the water is introduced into the water inlet of the water turbine through the water guiding system; Before introducing the water into the water inlet, the on-site monitoring cabinet calculates the predicted water parameters through the sensor data in the water guiding system and the pre-measured water head height. The water parameters include water pressure, flow rate and flow velocity; The calculation of the predicted water parameters includes setting a measuring point at a predetermined interval distance in the water guiding system to measure the water parameters; calculating the predicted water parameters based on the water head height. The water flow velocity calculation formula is expressed as, Among them, v represents the water flow velocity, g represents the acceleration of gravity, h represents the head height, and h f represents the head loss; The head loss h f is calculated by the formula where f represents the friction factor, obtained from the Moody diagram, L represents the length of the water channel, and D represents the diameter of the water channel; Based on the water flow velocity calculation formula and the head loss h f of the calculation formula, and the positions of each measuring point in the water conduction system, the final interval water flow velocity v is obtained z The formula is expressed as Among them, h i represents the water head height from the water outlet of the reservoir to the i-th measuring point, and L i represents the water channel length from the water outlet of the reservoir to the i-th measuring point, and M represents the total number of measuring points; The calculation formula of the water pressure is expressed as, The calculation formula of the flow rate is expressed as, Q = A·v z where ρ represents the water density and A represents the cross-sectional area of the water guiding system water channel; Load the calculated predicted water parameters into the system and start the water guiding work. Collect the actual water parameters collected at each measuring point, and based on the actual water parameters, use the interval water flow velocity formula to inversely calculate the actual friction factor f for each measuring point interval. zi Then update and replace f, and calculate the total friction factor f between the reservoir outlet and the water turbine inlet according to the mean formula. c It is expressed as For f-f zi , subtract the true friction factor of each measurement point from the friction factor and compare it with the maximum allowable threshold C M . If |f - f zi | ≥ C M , it is determined as an abnormal measurement point. If |f - f zi | < C M , it is a normal measurement point; When the number of abnormal measuring points is less than or equal to 2, and if the number of abnormal measuring points is 2 and the positions of the two abnormal measuring points are not consecutive positions, it is determined as a sensor failure, and the normal operation of the hydropower station is maintained, but the friction factor data comparison at the abnormal measuring points is removed. The sensor at the abnormal measuring point is repaired when the hydropower station is idle; When the number of abnormal measuring points is greater than 2, or the number of abnormal measuring points is 2 and the positions of the two abnormal measuring points are consecutive positions, it is determined as a water guiding system failure or foreign matter in the water quality, and the operation of the hydropower station is stopped for maintenance; The on-site monitoring cabinet adjusts the blade angle of the water turbine based on the obtained predicted water parameters to make the power generation meet the requirements; The adjustment of the water turbine blade angle based on the obtained predicted water parameters includes substituting the calculated total friction factor f c and the total head height h c between the water outlet of the reservoir and the water inlet of the water turbine collected in advance into the interval water flow velocity formula to obtain the predicted water inlet flow velocity v c ; According to the inlet water flow velocity v c calculate the effective head H eff which is expressed as According to H eff Calculate the input flow velocity v before entering the blade in Expressed as where θ represents the blade angle; According to v in Calculate the scouring force F on the blade, and then obtain the torque T and rotational speed N generated by the water turbine after being subjected to the force, expressed as F = ρQ(v in - v out ) T = Fr Among them, v out represents the output water velocity after passing through the guide vane, which is k times that of v in . The value of k is obtained by calculation and fitting based on the specifications of different turbines. r represents the runner radius, and D y represents the runner diameter; The constraint based on the maximum operable state of the water turbine is expressed as, T = min(ρQ(v in - v out ) × r, T max ) Among them, N max and T max respectively represent the maximum allowable operating speed and torque of the water turbine; The angular velocity ω of the rotor connected to the guide wheel calculated according to the rotational speed N is expressed as, ω = 2πN Furthermore, the predicted power generation P is calculated. elec It is expressed as P elec = ηωT where η represents the conversion efficiency; Replace the required generated power with the predicted generated power, load the predicted water parameters calculated before the inlet into the system, and reverse calculate the blade angle θ, and control the current blade angle to θ to meet the calculated P elec Greater than or equal to the required generated power; After the water enters the water turbine, based on the sensors inside the water turbine, the water parameter data curve inside the water turbine is obtained. The water parameter data curve is compared with the predicted data curve for loss. If the loss comparison is greater than the preset threshold, the difference points are marked and the number of difference points is checked, and corresponding measures are taken according to the number of difference points; The comparison of the water parameter data curve with the predicted data curve for loss includes loading the predicted water parameters into a pre-trained neural network model to obtain the predicted data curve, and collecting the actual water parameter data curve through the sensors inside the water turbine; The water parameter data curve is compared with the predicted data curve for loss. The comparison rule is based on the measuring points of the sensors inside the water turbine. The corresponding data points are marked in the water parameter data curve. The values of the data points in the water parameter data curve are subtracted from the corresponding data points in the predicted data curve to obtain the difference value and compare it with the preset threshold. If it is greater than the preset threshold, the corresponding data points in the water parameter data curve are marked as difference points; The corresponding measures taken according to the number of difference points include that when the number of difference points is less than or equal to 2, and if the number of difference points is 2 and the positions of the two difference points are not consecutive positions, it is determined as a sensor failure, and the normal operation of the hydropower station is maintained. The difference points are marked in gray and left idle. The sensors at the difference points are repaired when the hydropower station is idle; When the number of difference points is greater than 2, or when the number of difference points is equal to 2 and the positions of the two difference points are consecutive positions, it is determined that there is an abnormality inside the water turbine. Stop the operation of the current water turbine, divert the water resources that should flow into the current water turbine into the other water turbines through the water guide system, and adjust the blade angles of the other water turbines according to the required power generation and constraints to meet the demand, and repair the current water turbine; The predicted data curve is obtained by fitting based on the historical data of the water turbine through a neural network algorithm.

2. The real-time monitoring and control method of a water turbine according to claim 1, characterized in that: The judgment of whether the water quality meets the requirements includes obtaining the suspended matter coverage rate, pH value, and conductivity index data in the reservoir based on the sensor data of the reservoir, and comparing the index data with the index threshold to determine whether it meets the requirements.

3. A system adopting the real-time monitoring and control method of the water turbine as described in any one of claims 1 to 2, characterized in that: It includes a reservoir monitoring module, a water guide system monitoring module, a blade angle control module, and a water turbine monitoring module; The reservoir monitoring module collects the sensor data of the reservoir, judges whether the water quality meets the requirements. If it meets the requirements, the water is diverted into the water inlet of the water turbine through the water guide system; Before the water is diverted into the water inlet, the water guide system monitoring module calculates the predicted water parameters based on the sensor data in the water guide system and the previously measured head height. The water parameters include water pressure, flow rate, and flow velocity; The blade angle control module adjusts the blade angle of the water turbine based on the obtained predicted water parameters to make the power generation meet the demand; After the water enters the water turbine, the water turbine monitoring module obtains the water parameter data curve inside the water turbine based on the sensors in the water turbine, compares the loss of the water parameter data curve with the predicted data curve. If the loss comparison is greater than the preset threshold, the difference points are marked and the number of difference points is checked, and corresponding measures are taken according to the number of difference points.

4. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that: When the processor executes the computer program, it realizes the steps of the real-time monitoring and control method of the water turbine according to any one of claims 1 to 2.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it realizes the steps of the real-time monitoring and control method of the water turbine according to any one of claims 1 to 2.

Images